system

Abstract

We provide the system. [Solution] A data processing means for analyzing user answer information and identifying errors, A data analysis means using generation techniques to analyze the cause of the identified error, Information gathering means that automatically collects information related to user errors from external information resources, Information display means for providing collected information to the user, A communication means for transmitting answer information to a data server via a communication network, A means for receiving analysis results from a server and presenting them to the user, A system that includes this.

Description

Technical Field

[0004] , , ,

[0005] , , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In qualification exams and exam preparations, it takes a huge amount of time and effort to identify the parts where the user made mistakes and understand the causes. This process is inefficient and is a major obstacle especially for working people with limited time. The present invention aims to eliminate such inefficiencies, efficiently identify the causes of errors, and quickly provide relevant information, thereby dramatically improving the efficiency of the learning process.

Means for Solving the Problems

[0006] A "user" refers to an individual who uses the system for learning or preparing for exams.

[0007] "Answer data" refers to data related to the answers and results provided by users during the exam.

[0008] "Error" refers to an incorrect or wrong answer given by the user in response to an exam question.

[0009] "Generative technology" refers to techniques that use machine learning and artificial intelligence to analyze problems and identify their causes.

[0010] "External information sources" refer to information providers that exist outside the system, such as databases on the internet or publicly available educational resources.

[0011] "Information acquisition means" refers to methods and systems for automatically collecting relevant information from external sources.

[0012] "Display means" refers to a device or interface for visually providing the user with collected information and analysis results.

[0013] "Database management means" refers to a system or method for systematically accumulating, managing, and analyzing user error data.

[0014] A "learning plan" refers to a set of learning guidelines and plans that are individually optimized to help users learn efficiently. [Brief explanation of the drawing]

[0015] [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] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, 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.

[0019] 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. [[ID=二十一]] [[ID=二十二]]

[0020] [[ID=二十三]] [[ID=二十四]]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, etc. [[ID=二十五]] [[ID=二十六]]

[0021] [[ID=二十七]] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention provides a system that allows users to efficiently progress in their learning during qualification exams and exam preparation. The system begins with the user taking an exam and sending the results to a server. The user's answer data is collected on the server via an online environment.

[0037] Based on the received answer data, the server identifies the questions the user answered incorrectly. After the errors are identified, the server uses generation technology to analyze the causes of the errors and extract detailed information. This process clarifies whether the errors stemmed from a lack of knowledge on the part of the user or from a misunderstanding of a particular concept.

[0038] Next, the server automatically collects information related to the error from external sources. This is possible by leveraging open-access educational resources and online libraries. The collected information is extremely useful for deepening the user's understanding.

[0039] The terminal displays the analysis results and related information sent from the server to the user. This allows the user to specifically understand which areas they have made mistakes in and how to correct those deficiencies. The user can review the information provided on the terminal and supplement their learning.

[0040] For example, if a user makes a mistake on a probability and statistics problem in a math exam, the server analyzes the error and identifies that it stemmed from a lack of understanding of the fundamental laws of statistics. The server then retrieves detailed information and supplementary materials on these laws from external sources and displays them on the user's device. The user can then use this information to quickly improve their learning and overcome their weaknesses.

[0041] This entire system is built with the aim of providing efficient and effective learning support, allowing users to reliably get closer to passing the exam.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user completes the test and sends the answer data from the terminal to the server. The server receives this data and performs an initial analysis to determine which questions were answered correctly and which were answered incorrectly.

[0045] Step 2:

[0046] The server uses generation technology to analyze incorrect answers in detail. Specifically, it identifies which knowledge elements the user may have misunderstood based on the question content and answer choices.

[0047] Step 3:

[0048] The server retrieves information related to the identified error from external sources. This includes obtaining explanations and examples on the relevant topic from educational resources and databases on the internet.

[0049] Step 4:

[0050] The terminal displays analysis results and additional information sent from the server to the user. This information includes details about the reasons for errors and the knowledge needed for improvement.

[0051] Step 5:

[0052] Users advance their learning using the provided information. They supplement their knowledge and deepen their understanding based on the materials presented on their devices.

[0053] Step 6:

[0054] The server tracks the user's learning progress and stores error data in a database. Based on this information, common error patterns are identified, and learning support is enhanced so that it can be applied to other users.

[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 qualification exams and exam preparation, users are required to accurately analyze the causes of their incorrect answers and effectively reinforce their learning. However, conventional systems have not provided sufficient detailed analysis of individual errors or relevant information, making it difficult for users to efficiently deepen their understanding. Therefore, there is a need to provide support that enables users to understand their own errors and to learn effectively based on that understanding.

[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 information processing means for analyzing user answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and information acquisition means for automatically collecting information related to the user's errors from external information sources. This enables the user to understand the causes of their incorrect answers, efficiently acquire related information, and quickly address their weaknesses.

[0060] "Information processing means" refers to methods and technologies for analyzing user response data and identifying errors.

[0061] "Analysis methods using generative technology" refers to methods that utilize generative AI technology to clarify the cause of identified errors.

[0062] "Information acquisition means" refers to technologies and methods for automatically collecting information related to user errors from external sources.

[0063] "Display means" refers to the interface or mechanism for providing collected information to the user.

[0064] "User interface means" refers to an interface that visually displays relevant information based on analysis results and presents it in a way that is easy for the user to understand.

[0065] A "database management system" refers to a system that accumulates and analyzes user error data to identify common error patterns.

[0066] "Means for generating learning plans" refers to technologies that automatically generate individually optimized learning plans based on the user's error patterns.

[0067] This invention is a system designed to improve the learning efficiency of users in entrance exams and qualification tests. The user takes an exam and inputs their answers into a terminal. The terminal then transmits this answer data to a server via a network, where the data is analyzed.

[0068] The server uses an information processing program implemented in Python to analyze the received answer data. The analyzed data is then analyzed using AI technology to identify incorrect answers and determine whether the cause is a lack of knowledge or a misunderstanding. A generative AI model handles this analysis process, revealing the root cause of the problem.

[0069] Based on the analysis results, the server investigates external information sources and collects additional information to deepen the user's understanding. Web scraping tools (e.g., BeautifulSoup and Scrapy) targeting open-access information resources and online libraries on the web are used for information acquisition.

[0070] The collected information and analysis results are packaged and delivered to the device through an interface. The device visually presents this information to the user, allowing the user to understand their weaknesses and proceed with specific learning to overcome them.

[0071] As a concrete example, consider a case where a user makes a mistake on a "probability and statistics" problem in a math exam. The server identifies that the cause of the mistake is a lack of understanding of "basic statistical laws." The server then retrieves educational materials on these laws from an external source and presents them to the user's device, allowing the user to deepen their understanding in a short amount of time.

[0072] Examples of prompts used by this system are as follows:

[0073] "When a user makes a mistake on a specific question in an exam, please conduct an analysis to provide a cause analysis and related information. A possible reason for such a mistake is a lack of understanding of basic statistical principles."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user takes the test and inputs their answers into the terminal. Specifically, the user enters their answers to the test questions into a dedicated interface. This becomes the initial input data for this system.

[0077] Step 2:

[0078] The terminal sends the entered answer data to the server. The terminal uses an internet connection to send the answer data to the server via a security protocol. The transmitted answer data is used for the analysis process on the server.

[0079] Step 3:

[0080] The server receives the answer data and analyzes it using information processing tools. Specifically, the server uses a generative AI model to evaluate the accuracy of the answer data and identify which questions the user answered incorrectly. During this process, information on the accuracy rate and incorrect answers is output.

[0081] Step 4:

[0082] The server analyzes the causes of errors identified using generation technology. The server utilizes AI models to analyze whether the incorrect answers stem from a lack of knowledge or misunderstanding. The output of this step includes categories of the causes of the incorrect answers.

[0083] Step 5:

[0084] The server collects relevant information from external sources. Using scraping tools, the server accesses educational resources on the web and collects information related to incorrect answers. This information is then output as supplementary material for the user.

[0085] Step 6:

[0086] The server sends the analysis results and collected information to the terminal. The server sends the analysis results and related information to the terminal in a user-friendly format, preparing it for display on the terminal.

[0087] Step 7:

[0088] The terminal presents the user with analysis results and related information. The terminal displays the information on the interface in a user-friendly format. This allows the user to refer to information about their errors and how to correct them.

[0089] Step 8:

[0090] The user learns based on the information presented. The user utilizes this information to understand their own errors and reinforce their learning. This allows them to efficiently overcome their weaknesses.

[0091] (Application Example 1)

[0092] 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."

[0093] In qualification exams and exam preparation, there is a need for support systems that enable individual users to learn efficiently and effectively. However, conventional learning support systems have the challenge of being unable to analyze user errors in detail and provide appropriate information. Furthermore, there has been a lack of means to properly analyze user answer information and provide relevant information in real time.

[0094] 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.

[0095] In this invention, the server includes data processing means for analyzing user answer information and identifying errors, data analysis means using generation technology for analyzing the causes of identified errors, and information gathering means for automatically collecting information related to user errors from external information resources. This makes it possible to understand the causes of errors in real time for individual users and provide them with appropriate learning resources.

[0096] "Data processing means for analyzing user answer information and identifying errors" refers to computer system technology that analyzes answer data entered by users during exams or learning and determines whether it is correct or incorrect.

[0097] "Data analysis methods using generation techniques to analyze the causes of identified errors" refers to methods that utilize generation techniques to analyze data in detail in order to pinpoint the root cause of an error.

[0098] "Information gathering means for automatically collecting information related to user errors from external information resources" refers to technology that automatically acquires information related to user errors from external information sources such as educational materials and databases on the internet.

[0099] "A communication method for transmitting answer information to a data server via a communication network" refers to a communication technology for transmitting answer information entered by a user to a server located in a remote location via the internet.

[0100] "Result display means for receiving analysis results from a server and presenting them to the user" refers to a screen display system that presents the data results analyzed by the server to the user in an easy-to-understand manner.

[0101] This invention provides a support system for efficiently progressing with learning during qualification exams and exam preparation. The system mainly consists of a user terminal, network communication, and a data server.

[0102] Users input their exam answers from devices such as smartphones or computers. The entered answer information is transmitted via the internet to a remote data server using a communication method.

[0103] The server uses data processing means to analyze the received answer information and identify errors. The analyzed data is further analyzed by data analysis means using generation technology to pinpoint the cause of the errors. In this process, commonly misunderstood concepts and lack of knowledge are taken into consideration.

[0104] Subsequently, the server automatically collects relevant materials from external information resources. Through these information gathering methods, information obtained from educational materials, online libraries, and other sources is organized in a way that is directly useful for learning.

[0105] Finally, the analysis results and collected information from the server are presented to the user through the results display on their terminal. This allows the user to efficiently identify their weaknesses and proceed with learning to address them. For example, if a user makes a mistake in "probability and statistics" in mathematics, the server analysis will determine that they lack understanding of "basic statistical laws," and relevant materials will be provided.

[0106] An example of a prompt message when using a generative AI model might be: "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and suggest links to relevant learning materials."

[0107] This system enables the identification and overcoming of learning weaknesses in real time.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] Users input their test answers from their devices. This input is digitized as questionnaire or multiple-choice responses. The answer data is then transmitted to a server via a communication network. Secure protocols are used to ensure the data's safety during this process.

[0111] Step 2:

[0112] The server analyzes the received answer data using data processing tools. Based on the input data, it performs a correctness check and identifies errors. The data processing performed here involves detecting errors through statistical analysis and simple conditional branching. As output, the answer with identified errors is generated.

[0113] Step 3:

[0114] The server uses data analysis methods based on generative technology to further analyze the causes of identified errors. It receives error data as input and utilizes a generative AI model to pinpoint the causes. Data processing involves analyzing error patterns and identifying the root causes. The analysis results are obtained as output.

[0115] Step 4:

[0116] The server utilizes information gathering methods to collect relevant information from external information resources. The analysis results obtained in the previous step are used as input. Data processing involves searching educational materials and databases on the internet to extract relevant information. This results in the output of supplementary materials and related information.

[0117] Step 5:

[0118] The terminal receives analysis results and collected information sent from the server. The input is data provided by the server. On the terminal, a means of displaying results is used to present them to the user as visual information. Specifically, this involves displaying the results on the user interface so that the user can confirm them.

[0119] Step 6:

[0120] The user reviews the results displayed on the device and uses that information to further their learning. An example of a prompt message is, "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and suggest links to relevant learning materials." This allows for the creation of an effective learning plan.

[0121] 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.

[0122] This invention provides a learning support system that takes into account the user's emotional state in order to improve the user's learning efficiency. This system can recognize the user's emotions in real time using an emotion engine during the process of the user preparing for an exam, and dynamically adjust the learning plan based on that recognition.

[0123] The system's main configuration is as follows: First, the user takes an exam and sends their answer data from their terminal to the server. The server analyzes this data, identifies errors, and analyzes the causes using generation technology. The analysis results are enhanced through information acquisition means that collect relevant information from external educational resources, and this information is provided to the user.

[0124] Furthermore, this invention incorporates an emotion engine that analyzes the user's emotions from their facial expressions, tone of voice, and other factors. For example, if the device determines that the user is feeling stressed, it will recommend that the user access appropriate content or take a break to help them relax.

[0125] On the device, analysis results from the server and the output of the emotion engine are integrated, and a customized learning plan and feedback are presented to the user. This allows users to learn at their own pace and according to their emotional state.

[0126] Specifically, for example, suppose a user is solving an English grammar problem and the emotion engine detects that the user is feeling anxious. The server can then take this emotional information into consideration and present an explanation from a different perspective that is easier for the user to understand, and also suggest effective relaxation methods. In this way, the goal is to make the user's learning experience more intuitive and effective.

[0127] This system aims to maximize learning effectiveness by enabling detailed emotion recognition, thereby achieving even greater learning efficiency.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] Users take the test using their devices and enter their answers. The answer data is sent to the server in real time.

[0131] Step 2:

[0132] The server analyzes the submitted answer data to identify which questions the user answered incorrectly. The analysis also takes into account the user's past answer data.

[0133] Step 3:

[0134] The server uses generation techniques to analyze the cause of the error in detail. This includes identifying the user's misunderstood concepts and knowledge gaps.

[0135] Step 4:

[0136] The server automatically collects relevant supplementary information from external sources and prepares learning resources tailored to the user's needs.

[0137] Step 5:

[0138] Simultaneously, the emotion engine built into the device analyzes the user's facial expressions and voice data to recognize their current emotional state. This information is sent to the server in real time.

[0139] Step 6:

[0140] Based on the recognized emotional state, the server provides appropriate feedback and adjusts content for the user. Specifically, if the user is feeling stressed, it will suggest taking a break or present relaxation content.

[0141] Step 7:

[0142] The terminal provides the user with analysis results and feedback from the server. This includes detailed explanations and advice regarding the questions answered incorrectly.

[0143] Step 8:

[0144] Based on the information and feedback provided, users progress through their learning while implementing a learning plan that takes their emotional state into consideration. They can request further feedback from their device as needed.

[0145] Step 9:

[0146] The server continuously records learning progress and sentiment data, and updates the learning plan as needed. This data is also used to help other users.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] In recent years, there has been a growing demand for providing users with an environment in which they can learn effectively and efficiently. However, conventional learning support systems construct learning plans based solely on the user's answers, and therefore do not provide feedback or learning suggestions that take into account the user's emotional state. As a result, there is a problem in that a user's unique emotional state may affect their learning efficiency. In particular, there is a need to provide learning support that takes these emotions into account for users who are experiencing stress or anxiety.

[0150] 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.

[0151] In this invention, the server includes information processing means for analyzing the user's answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and emotion analysis means for analyzing the user's emotional state in real time. This makes it possible to provide a detailed learning plan tailored to the user's emotional state.

[0152] "Information processing means" refers to the system's function for analyzing user response data and identifying errors.

[0153] "Analysis methods using generative technology" refer to methods that utilize generative models to deeply analyze the causes of identified errors.

[0154] "Information acquisition means" refers to a function that automatically collects information related to user errors from external sources.

[0155] "Display means" refers to a device or function for providing collected information to the user visually.

[0156] "Emotion analysis means" refers to a function that analyzes the user's facial expressions, tone of voice, etc., to identify the user's emotional state in real time.

[0157] "Means of providing learning plans" refers to a function that presents users with individually optimized learning plans based on their error tendencies and emotional state.

[0158] "Database management means" refers to a means of accumulating user error data and identifying common error patterns from that data.

[0159] This learning support system performs real-time emotional state analysis and error correction to maximize the user's learning efficiency. The main components of the system include the user's terminal, a server, and a generative AI model.

[0160] First, users take tests and exercises using their own devices and input their answer data. This answer data is sent to the server via the device. The server immediately analyzes the received data and uses information processing tools to identify user errors. In this process, analysis tools using generation technology are used to deeply analyze the causes of the errors.

[0161] Furthermore, the server automatically retrieves relevant learning materials from external sources and provides them to the user through information retrieval means. For example, relevant video materials and supplementary materials are collected. This information is presented to the user visually through the terminal's display means.

[0162] On the other hand, the device is equipped with emotion analysis capabilities that analyze the user's facial expressions and tone of voice in real time. If the user's emotional state is stressful, relaxation methods and adjustments to the learning speed are recommended based on the analysis results.

[0163] This system allows users to receive optimized learning plans tailored to their emotional state and to get personalized feedback.

[0164] As a concrete example, suppose a user experiences anxiety while solving an English grammar problem. At this point, the user's anxiety is detected by an emotion analysis tool. Based on this data, the server generates feedback such as presenting explanations from other perspectives, additional materials, and playing music to help the user relax.

[0165] An example of a prompt to a generative AI model would be, "Please tell me how to learn when I feel anxious while solving English grammar problems. In particular, I would like to know more about easy-to-understand explanations and relaxation techniques." By using this prompt, the AI ​​model will generate answers that meet the user's needs and support the learning process.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The user uses a terminal to take tests and solve problems. The terminal collects answer data and prepares it for transmission to the server. In this process, the answers entered by the user are collected, encrypted, and converted into a format that can be sent to the server. The input is the user's answer data, and the output is the prepared data for transmission to the server.

[0169] Step 2:

[0170] The server analyzes the received answer data using information processing tools. Specifically, the server determines whether the answer is correct or incorrect and analyzes the cause of the error using analysis tools that utilize generation technology. The input is the user's answer data, and the output is the analysis results regarding the errors. This analysis clarifies the trends and causes of incorrect answers.

[0171] Step 3:

[0172] The server automatically collects relevant learning materials from external sources based on the analysis results. The server utilizes information acquisition methods to search for learning materials that are useful for the user's learning. The input is the error analysis results, and the output is data from relevant external learning resources. The server collects and reconstructs this information.

[0173] Step 4:

[0174] The terminal presents collected learning materials to the user through a display mechanism. The terminal displays information in a format that is visually easy for the user to understand. The input is data from external resources transferred from the server, and the output is a display of learning materials that the user can view.

[0175] Step 5:

[0176] The device uses emotion analysis techniques to analyze the user's facial expressions, voice tone, and other factors to evaluate their emotional state. Specifically, the device's sensors detect the user's voice patterns and facial movements. The input is real-time user audio and video data, and the output is the analyzed emotional state.

[0177] Step 6:

[0178] The device generates and provides a customized learning plan based on the user's emotional state. It initiates a protocol to propose an optimized learning plan to the user. The input is the result of the emotion analysis, and the output is an individually adjusted learning schedule. This plan is designed taking into account the user's level of understanding and mental state.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0181] In today's world, improving user learning efficiency requires providing appropriate support tailored to each individual's level of understanding. However, conventional learning systems lack dynamic learning adjustments that take into account the user's emotional state, making it difficult to promote learning while reducing learners' psychological stress.

[0182] 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.

[0183] In this invention, the server includes data processing means for analyzing the user's answer data and identifying errors, data analysis means using generation technology for analyzing the causes of the identified errors, and emotion recognition and plan adjustment means for detecting the user's emotions in real time and adjusting the learning plan based on those emotions. This makes it possible to provide learning support that takes into account the user's emotional state, thereby improving the user's learning efficiency.

[0184] "User response data" refers to the collective data of the answers that learners have submitted to various problems.

[0185] "Data processing means for identifying errors" refers to a device or method that is responsible for the process of detecting incorrect parts from the user's answer data.

[0186] "Data analysis means using generational technology" refers to a device or method that utilizes generational technology such as machine learning to deeply analyze the causes of identified errors.

[0187] "Data collection means" refers to a device or method that has the function of automatically collecting necessary information from external sources.

[0188] "Information display means" refers to a device or method for visually providing users with necessary information.

[0189] "Emotion recognition and plan adjustment means" refers to a device or method that has the function of detecting the user's emotions in real time and dynamically adjusting the learning plan based on those emotions.

[0190] A "database management system" refers to a data management system that stores user data and analyzes specific patterns.

[0191] A "learning plan generation means" is a device or method that has the function of creating an individually optimized learning plan according to the user's error tendencies and emotional state.

[0192] To realize this invention, a data analysis system is required to process learner response data and identify errors. The server uses a data processing device to analyze the response data received from the user. Specifically, it utilizes a data analysis device employing generation technology to detect errors and analyze their causes. Efficient analysis is possible by using data processing and AI libraries such as Apache® Kafka and TENSORFLOW®.

[0193] Furthermore, the device detects the user's emotions in real time based on the collected analysis data. This involves using emotion recognition technologies such as OpenCV to analyze the user's facial expressions and tone of voice to evaluate their emotional state. Based on this emotional information, the learning plan is dynamically adjusted to provide the learner with an optimal learning environment.

[0194] For example, if a user shows signs of anxiety while solving grammar problems, the server receives this emotional information and adjusts the learning plan accordingly. This could lead to the user being offered appropriate content to help them relax. Such a system provides support that takes the user's emotional state into account, resulting in more efficient learning and reduced stress.

[0195] It is also possible to construct appropriate prompt sentences by utilizing generative AI models. For example, instructions can be given to the AI ​​system using a prompt sentence such as, "If the user is feeling stressed, suggest ways to provide relaxation content or gentle guidance."

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server receives the answer data from the user as input and performs analysis using a data processing device. This process analyzes the answer data and performs basic calculations to determine whether each answer is correct or incorrect. After analysis, a list of incorrect answers is output.

[0199] Step 2:

[0200] The server uses the list of incorrect answers output in Step 1 as input and performs a data analysis using a generative AI model to deeply analyze the causes of errors. In this step, the generative AI model generates data to identify error trends and common causes, and outputs an analysis report.

[0201] Step 3:

[0202] The device uses OpenCV to analyze emotions using data obtained in real time from the user's camera and microphone as input. Through this analysis, it determines the user's emotional state from their facial expressions and tone of voice, and outputs that information.

[0203] Step 4:

[0204] The server receives the analysis report from step 2 and the emotional information from step 3 as input, and dynamically adjusts the learning plan using emotion recognition and plan adjustment mechanisms. This allows it to output a learning plan optimized for the learner's emotional state in real time.

[0205] Step 5:

[0206] The device displays the learning plan generated in step 4 to the user, providing an optimized learning experience. Specifically, it presents the learning plan and delivers emotion-based content.

[0207] Step 6:

[0208] If a user experiences stress or anxiety while progressing through their learning plan, prompt messages are input into the generative AI model, which then suggests specific guidance and support for relaxation. An example of a prompt message is, "If the user is feeling stressed, please suggest ways to provide relaxation content and gentle guidance."

[0209] 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.

[0210] Data generation model 58 is a type of 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.

[0211] 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.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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".

[0225] This invention provides a system that allows users to efficiently progress in their learning during qualification exams and exam preparation. The system begins with the user taking an exam and sending the results to a server. The user's answer data is collected on the server via an online environment.

[0226] Based on the received answer data, the server identifies the questions the user answered incorrectly. After the errors are identified, the server uses generation technology to analyze the causes of the errors and extract detailed information. This process clarifies whether the errors stemmed from a lack of knowledge on the part of the user or from a misunderstanding of a particular concept.

[0227] Next, the server automatically collects information related to the error from external sources. This is possible by leveraging open-access educational resources and online libraries. The collected information is extremely useful for deepening the user's understanding.

[0228] The terminal displays the analysis results and related information sent from the server to the user. This allows the user to specifically understand which areas they have made mistakes in and how to correct those deficiencies. The user can review the information provided on the terminal and supplement their learning.

[0229] For example, if a user makes a mistake on a probability and statistics problem in a math exam, the server analyzes the error and identifies that it stemmed from a lack of understanding of the fundamental laws of statistics. The server then retrieves detailed information and supplementary materials on these laws from external sources and displays them on the user's device. The user can then use this information to quickly improve their learning and overcome their weaknesses.

[0230] This entire system is built with the aim of providing efficient and effective learning support, allowing users to reliably get closer to passing the exam.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The user completes the test and sends the answer data from the terminal to the server. The server receives this data and performs an initial analysis to determine which questions were answered correctly and which were answered incorrectly.

[0234] Step 2:

[0235] The server uses generation technology to analyze incorrect answers in detail. Specifically, it identifies which knowledge elements the user may have misunderstood based on the question content and answer choices.

[0236] Step 3:

[0237] The server retrieves information related to the identified error from external sources. This includes obtaining explanations and examples on the relevant topic from educational resources and databases on the internet.

[0238] Step 4:

[0239] The terminal displays analysis results and additional information sent from the server to the user. This information includes details about the reasons for errors and the knowledge needed for improvement.

[0240] Step 5:

[0241] Users advance their learning using the provided information. They supplement their knowledge and deepen their understanding based on the materials presented on their devices.

[0242] Step 6:

[0243] The server tracks the user's learning progress and stores error data in a database. Based on this information, common error patterns are identified, and learning support is enhanced so that it can be applied to other users.

[0244] (Example 1)

[0245] 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."

[0246] In qualification exams and exam preparation, users are required to accurately analyze the causes of their incorrect answers and effectively reinforce their learning. However, conventional systems have not provided sufficient detailed analysis of individual errors or relevant information, making it difficult for users to efficiently deepen their understanding. Therefore, there is a need to provide support that enables users to understand their own errors and to learn effectively based on that understanding.

[0247] 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.

[0248] In this invention, the server includes information processing means for analyzing user answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and information acquisition means for automatically collecting information related to the user's errors from external information sources. This enables the user to understand the causes of their incorrect answers, efficiently acquire related information, and quickly address their weaknesses.

[0249] "Information processing means" refers to methods and technologies for analyzing user response data and identifying errors.

[0250] "Analysis methods using generative technology" refers to methods that utilize generative AI technology to clarify the cause of identified errors.

[0251] "Information acquisition means" refers to technologies and methods for automatically collecting information related to user errors from external sources.

[0252] "Display means" refers to the interface or mechanism for providing collected information to the user.

[0253] "User interface means" refers to an interface that visually displays relevant information based on analysis results and presents it in a way that is easy for the user to understand.

[0254] A "database management system" refers to a system that accumulates and analyzes user error data to identify common error patterns.

[0255] "Means for generating learning plans" refers to technologies that automatically generate individually optimized learning plans based on the user's error patterns.

[0256] This invention is a system designed to improve the learning efficiency of users in entrance exams and qualification tests. The user takes an exam and inputs their answers into a terminal. The terminal then transmits this answer data to a server via a network, where the data is analyzed.

[0257] The server uses an information processing program implemented in Python to analyze the received answer data. The analyzed data is then analyzed using AI technology to identify incorrect answers and determine whether the cause is a lack of knowledge or a misunderstanding. A generative AI model handles this analysis process, revealing the root cause of the problem.

[0258] Based on the analysis results, the server investigates external information sources and collects additional information to deepen the user's understanding. Web scraping tools (e.g., BeautifulSoup and Scrapy) targeting open-access information resources and online libraries on the web are used for information acquisition.

[0259] The collected information and analysis results are packaged and delivered to the device through an interface. The device visually presents this information to the user, allowing the user to understand their weaknesses and proceed with specific learning to overcome them.

[0260] As a concrete example, consider a case where a user makes a mistake on a "probability and statistics" problem in a math exam. The server identifies that the cause of the mistake is a lack of understanding of "basic statistical laws." The server then retrieves educational materials on these laws from an external source and presents them to the user's device, allowing the user to deepen their understanding in a short amount of time.

[0261] Examples of prompts used by this system are as follows:

[0262] "When a user makes a mistake on a specific question in an exam, please conduct an analysis to provide a cause analysis and related information. A possible reason for such a mistake is a lack of understanding of basic statistical principles."

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] The user takes the test and inputs their answers into the terminal. Specifically, the user enters their answers to the test questions into a dedicated interface. This becomes the initial input data for this system.

[0266] Step 2:

[0267] The terminal sends the entered answer data to the server. The terminal uses an internet connection to send the answer data to the server via a security protocol. The transmitted answer data is used for the analysis process on the server.

[0268] Step 3:

[0269] The server receives the answer data and analyzes it using information processing tools. Specifically, the server uses a generative AI model to evaluate the accuracy of the answer data and identify which questions the user answered incorrectly. During this process, information on the accuracy rate and incorrect answers is output.

[0270] Step 4:

[0271] The server analyzes the causes of errors identified using generation technology. The server utilizes AI models to analyze whether the incorrect answers stem from a lack of knowledge or misunderstanding. The output of this step includes categories of the causes of the incorrect answers.

[0272] Step 5:

[0273] The server collects relevant information from external sources. Using scraping tools, the server accesses educational resources on the web and collects information related to incorrect answers. This information is then output as supplementary material for the user.

[0274] Step 6:

[0275] The server sends the analysis results and collected information to the terminal. The server sends the analysis results and related information to the terminal in a user-friendly format, preparing it for display on the terminal.

[0276] Step 7:

[0277] The terminal presents the user with analysis results and related information. The terminal displays the information on the interface in a user-friendly format. This allows the user to refer to information about their errors and how to correct them.

[0278] Step 8:

[0279] The user learns based on the information presented. The user utilizes this information to understand their own errors and reinforce their learning. This allows them to efficiently overcome their weaknesses.

[0280] (Application Example 1)

[0281] 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."

[0282] In qualification exams and exam preparation, there is a need for support systems that enable individual users to learn efficiently and effectively. However, conventional learning support systems have the challenge of being unable to analyze user errors in detail and provide appropriate information. Furthermore, there has been a lack of means to properly analyze user answer information and provide relevant information in real time.

[0283] 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.

[0284] In this invention, the server includes data processing means for analyzing the user's answer information and identifying errors, data analysis means using generation technology for analyzing the causes of the identified errors, and information collection means for automatically collecting information related to the user's errors from external information resources. As a result, it becomes possible to understand the causes of errors in real time for individual users and provide appropriate learning resources.

[0285] The "data processing means for analyzing the user's answer information and identifying errors" is a technology of a computer system for analyzing the answer data input by the user during a test or learning and determining whether it is correct or incorrect.

[0286] The "data analysis means using generation technology for analyzing the causes of the identified errors" is a method of analyzing data in detail by utilizing generation technology to find out the root causes of errors.

[0287] The "information collection means for automatically collecting information related to the user's errors from external information resources" is a technology for automatically obtaining information related to the user's errors from external information sources such as educational materials and databases on the Internet.

[0288] The "communication means for transmitting answer information to the data server via a communication network" is a communication technology for transmitting the answer information input by the user to a server located remotely via the Internet.

[0289] The "result display means for receiving the analysis result from the server and presenting it to the user" is a screen display system for presenting the data result analyzed by the server to the user in an understandable manner.

[0290] This invention provides a support system for efficiently promoting learning in qualification exams and exam preparation. The system is mainly composed of a user terminal, network communication, a data server, etc.

[0291] Users input their exam answers from devices such as smartphones or computers. The entered answer information is transmitted via the internet to a remote data server using a communication method.

[0292] The server uses data processing means to analyze the received answer information and identify errors. The analyzed data is further analyzed by data analysis means using generation technology to pinpoint the cause of the errors. In this process, commonly misunderstood concepts and lack of knowledge are taken into consideration.

[0293] Subsequently, the server automatically collects relevant materials from external information resources. Through these information gathering methods, information obtained from educational materials, online libraries, and other sources is organized in a way that is directly useful for learning.

[0294] Finally, the analysis results and collected information from the server are presented to the user through the results display on their terminal. This allows the user to efficiently identify their weaknesses and proceed with learning to address them. For example, if a user makes a mistake in "probability and statistics" in mathematics, the server analysis will determine that they lack understanding of "basic statistical laws," and relevant materials will be provided.

[0295] An example of a prompt message when using a generative AI model might be: "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and suggest links to relevant learning materials."

[0296] This system enables the identification and overcoming of learning weaknesses in real time.

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] Users input their test answers from their devices. This input is digitized as questionnaire or multiple-choice responses. The answer data is then transmitted to a server via a communication network. Secure protocols are used to ensure the data's safety during this process.

[0300] Step 2:

[0301] The server analyzes the received answer data using data processing tools. Based on the input data, it performs a correctness check and identifies errors. The data processing performed here involves detecting errors through statistical analysis and simple conditional branching. As output, the answer with identified errors is generated.

[0302] Step 3:

[0303] The server uses data analysis methods based on generative technology to further analyze the causes of identified errors. It receives error data as input and utilizes a generative AI model to pinpoint the causes. Data processing involves analyzing error patterns and identifying the root causes. The analysis results are obtained as output.

[0304] Step 4:

[0305] The server utilizes information gathering methods to collect relevant information from external information resources. The analysis results obtained in the previous step are used as input. Data processing involves searching educational materials and databases on the internet to extract relevant information. This results in the output of supplementary materials and related information.

[0306] Step 5:

[0307] The terminal receives the analysis results sent from the server and the collected information. As input, data from the server is provided. On the terminal, result display means for presenting to the user as visual information is used. As a specific operation, the result is displayed on the user interface so that the user can confirm it.

[0308] Step 6:

[0309] The user checks the results displayed on the terminal and uses that information to further the learning process. By using an example of a prompt sentence such as "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and propose links to relevant teaching materials.", it becomes possible to create an effective learning plan.

[0310] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0311] The present invention provides a learning support system that takes into account the user's emotional state in order to improve the user's learning efficiency. This system can recognize the user's emotions in real time using an emotion engine during the process of the user preparing for an exam, and dynamically adjust the learning plan based on that.

[0312] As the main configuration of the system, first, the user takes an exam and sends the answer data from the terminal to the server. The server analyzes this data, identifies the errors, and analyzes the causes using generation techniques. The results of the analysis are enhanced through information acquisition means that collect relevant information from external educational resources, and that information is provided to the user.

[0313] Furthermore, this invention incorporates an emotion engine that analyzes the user's emotions from their facial expressions, tone of voice, and other factors. For example, if the device determines that the user is feeling stressed, it will recommend that the user access appropriate content or take a break to help them relax.

[0314] On the device, analysis results from the server and the output of the emotion engine are integrated, and a customized learning plan and feedback are presented to the user. This allows users to learn at their own pace and according to their emotional state.

[0315] Specifically, for example, suppose a user is solving an English grammar problem and the emotion engine detects that the user is feeling anxious. The server can then take this emotional information into consideration and present an explanation from a different perspective that is easier for the user to understand, and also suggest effective relaxation methods. In this way, the goal is to make the user's learning experience more intuitive and effective.

[0316] This system aims to maximize learning effectiveness by enabling detailed emotion recognition, thereby achieving even greater learning efficiency.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] Users take the test using their devices and enter their answers. The answer data is sent to the server in real time.

[0320] Step 2:

[0321] The server analyzes the submitted answer data to identify which questions the user answered incorrectly. The analysis also takes into account the user's past answer data.

[0322] Step 3:

[0323] The server uses generation techniques to analyze the cause of the error in detail. This includes identifying the user's misunderstood concepts and knowledge gaps.

[0324] Step 4:

[0325] The server automatically collects relevant supplementary information from external sources and prepares learning resources tailored to the user's needs.

[0326] Step 5:

[0327] Simultaneously, the emotion engine built into the device analyzes the user's facial expressions and voice data to recognize their current emotional state. This information is sent to the server in real time.

[0328] Step 6:

[0329] Based on the recognized emotional state, the server provides appropriate feedback and adjusts content for the user. Specifically, if the user is feeling stressed, it will suggest taking a break or present relaxation content.

[0330] Step 7:

[0331] The terminal provides the user with analysis results and feedback from the server. This includes detailed explanations and advice regarding the questions answered incorrectly.

[0332] Step 8:

[0333] Based on the information and feedback provided, users progress through their learning while implementing a learning plan that takes their emotional state into consideration. They can request further feedback from their device as needed.

[0334] Step 9:

[0335] The server continuously records learning progress and sentiment data, and updates the learning plan as needed. This data is also used to help other users.

[0336] (Example 2)

[0337] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0338] In recent years, there has been a growing demand for providing users with an environment in which they can learn effectively and efficiently. However, conventional learning support systems construct learning plans based solely on the user's answers, and therefore do not provide feedback or learning suggestions that take into account the user's emotional state. As a result, there is a problem in that a user's unique emotional state may affect their learning efficiency. In particular, there is a need to provide learning support that takes these emotions into account for users who are experiencing stress or anxiety.

[0339] 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.

[0340] In this invention, the server includes information processing means for analyzing the user's answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and emotion analysis means for analyzing the user's emotional state in real time. This makes it possible to provide a detailed learning plan tailored to the user's emotional state.

[0341] "Information processing means" refers to the system's function for analyzing user response data and identifying errors.

[0342] "Analysis methods using generative technology" refer to methods that utilize generative models to deeply analyze the causes of identified errors.

[0343] "Information acquisition means" refers to a function that automatically collects information related to user errors from external sources.

[0344] "Display means" refers to a device or function for providing collected information to the user visually.

[0345] "Emotion analysis means" refers to a function that analyzes the user's facial expressions, tone of voice, etc., to identify the user's emotional state in real time.

[0346] "Means of providing learning plans" refers to a function that presents users with individually optimized learning plans based on their error tendencies and emotional state.

[0347] "Database management means" refers to a means of accumulating user error data and identifying common error patterns from that data.

[0348] This learning support system performs real-time emotional state analysis and error correction to maximize the user's learning efficiency. The main components of the system include the user's terminal, a server, and a generative AI model.

[0349] First, users take tests and exercises using their own devices and input their answer data. This answer data is sent to the server via the device. The server immediately analyzes the received data and uses information processing tools to identify user errors. In this process, analysis tools using generation technology are used to deeply analyze the causes of the errors.

[0350] Furthermore, the server automatically retrieves relevant learning materials from external sources and provides them to the user through information retrieval means. For example, relevant video materials and supplementary materials are collected. This information is presented to the user visually through the terminal's display means.

[0351] On the other hand, the device is equipped with emotion analysis capabilities that analyze the user's facial expressions and tone of voice in real time. If the user's emotional state is stressful, relaxation methods and adjustments to the learning speed are recommended based on the analysis results.

[0352] This system allows users to receive optimized learning plans tailored to their emotional state and to get personalized feedback.

[0353] As a concrete example, suppose a user experiences anxiety while solving an English grammar problem. At this point, the user's anxiety is detected by an emotion analysis tool. Based on this data, the server generates feedback such as presenting explanations from other perspectives, additional materials, and playing music to help the user relax.

[0354] An example of a prompt to a generative AI model would be, "Please tell me how to learn when I feel anxious while solving English grammar problems. In particular, I would like to know more about easy-to-understand explanations and relaxation techniques." By using this prompt, the AI ​​model will generate answers that meet the user's needs and support the learning process.

[0355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0356] Step 1:

[0357] The user uses a terminal to take tests and solve problems. The terminal collects answer data and prepares it for transmission to the server. In this process, the answers entered by the user are collected, encrypted, and converted into a format that can be sent to the server. The input is the user's answer data, and the output is the prepared data for transmission to the server.

[0358] Step 2:

[0359] The server analyzes the received answer data using information processing tools. Specifically, the server determines whether the answer is correct or incorrect and analyzes the cause of the error using analysis tools that utilize generation technology. The input is the user's answer data, and the output is the analysis results regarding the errors. This analysis clarifies the trends and causes of incorrect answers.

[0360] Step 3:

[0361] The server automatically collects relevant learning materials from external sources based on the analysis results. The server utilizes information acquisition methods to search for learning materials that are useful for the user's learning. The input is the error analysis results, and the output is data from relevant external learning resources. The server collects and reconstructs this information.

[0362] Step 4:

[0363] The terminal presents collected learning materials to the user through a display mechanism. The terminal displays information in a format that is visually easy for the user to understand. The input is data from external resources transferred from the server, and the output is a display of learning materials that the user can view.

[0364] Step 5:

[0365] The device uses emotion analysis techniques to analyze the user's facial expressions, voice tone, and other factors to evaluate their emotional state. Specifically, the device's sensors detect the user's voice patterns and facial movements. The input is real-time user audio and video data, and the output is the analyzed emotional state.

[0366] Step 6:

[0367] The device generates and provides a customized learning plan based on the user's emotional state. It initiates a protocol to propose an optimized learning plan to the user. The input is the result of the emotion analysis, and the output is an individually adjusted learning schedule. This plan is designed taking into account the user's level of understanding and mental state.

[0368] (Application Example 2)

[0369] 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."

[0370] In today's world, improving user learning efficiency requires providing appropriate support tailored to each individual's level of understanding. However, conventional learning systems lack dynamic learning adjustments that take into account the user's emotional state, making it difficult to promote learning while reducing learners' psychological stress.

[0371] 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.

[0372] In this invention, the server includes data processing means for analyzing the user's answer data and identifying errors, data analysis means using generation technology for analyzing the causes of the identified errors, and emotion recognition and plan adjustment means for detecting the user's emotions in real time and adjusting the learning plan based on those emotions. This makes it possible to provide learning support that takes into account the user's emotional state, thereby improving the user's learning efficiency.

[0373] "User response data" refers to the collective data of the answers that learners have submitted to various problems.

[0374] "Data processing means for identifying errors" refers to a device or method that is responsible for the process of detecting incorrect parts from the user's answer data.

[0375] "Data analysis means using generational technology" refers to a device or method that utilizes generational technology such as machine learning to deeply analyze the causes of identified errors.

[0376] "Data collection means" refers to a device or method that has the function of automatically collecting necessary information from external sources.

[0377] "Information display means" refers to a device or method for visually providing users with necessary information.

[0378] "Emotion recognition and plan adjustment means" refers to a device or method that has the function of detecting the user's emotions in real time and dynamically adjusting the learning plan based on those emotions.

[0379] A "database management system" refers to a data management system that stores user data and analyzes specific patterns.

[0380] A "learning plan generation means" is a device or method that has the function of creating an individually optimized learning plan according to the user's error tendencies and emotional state.

[0381] To realize this invention, a data analysis system is required to process learner response data and identify errors. The server uses a data processing device to analyze the response data received from the user. Specifically, it utilizes a data analysis device employing generation technology to detect errors and analyze their causes. Efficient analysis is possible by using data processing and AI libraries such as Apache Kafka and TensorFlow.

[0382] Furthermore, the device detects the user's emotions in real time based on the collected analysis data. This involves using emotion recognition technologies such as OpenCV to analyze the user's facial expressions and tone of voice to evaluate their emotional state. Based on this emotional information, the learning plan is dynamically adjusted to provide the learner with an optimal learning environment.

[0383] For example, if a user shows signs of anxiety while solving grammar problems, the server receives this emotional information and adjusts the learning plan accordingly. This could lead to the user being offered appropriate content to help them relax. Such a system provides support that takes the user's emotional state into account, resulting in more efficient learning and reduced stress.

[0384] It is also possible to construct appropriate prompt sentences by utilizing generative AI models. For example, instructions can be given to the AI ​​system using a prompt sentence such as, "If the user is feeling stressed, suggest ways to provide relaxation content or gentle guidance."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server receives the answer data from the user as input and performs analysis using a data processing device. This process analyzes the answer data and performs basic calculations to determine whether each answer is correct or incorrect. After analysis, a list of incorrect answers is output.

[0388] Step 2:

[0389] The server uses the list of incorrect answers output in Step 1 as input and performs a data analysis using a generative AI model to deeply analyze the causes of errors. In this step, the generative AI model generates data to identify error trends and common causes, and outputs an analysis report.

[0390] Step 3:

[0391] The device uses OpenCV to analyze emotions using data obtained in real time from the user's camera and microphone as input. Through this analysis, it determines the user's emotional state from their facial expressions and tone of voice, and outputs that information.

[0392] Step 4:

[0393] The server receives the analysis report from step 2 and the emotional information from step 3 as input, and dynamically adjusts the learning plan using emotion recognition and plan adjustment mechanisms. This allows it to output a learning plan optimized for the learner's emotional state in real time.

[0394] Step 5:

[0395] The device displays the learning plan generated in step 4 to the user, providing an optimized learning experience. Specifically, it presents the learning plan and delivers emotion-based content.

[0396] Step 6:

[0397] If a user experiences stress or anxiety while progressing through their learning plan, prompt messages are input into the generative AI model, which then suggests specific guidance and support for relaxation. An example of a prompt message is, "If the user is feeling stressed, please suggest ways to provide relaxation content and gentle guidance."

[0398] 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.

[0399] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0400] 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.

[0401] [Third Embodiment]

[0402] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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".

[0414] This invention provides a system that allows users to efficiently progress in their learning during qualification exams and exam preparation. The system begins with the user taking an exam and sending the results to a server. The user's answer data is collected on the server via an online environment.

[0415] Based on the received answer data, the server identifies the questions the user answered incorrectly. After the errors are identified, the server uses generation technology to analyze the causes of the errors and extract detailed information. This process clarifies whether the errors stemmed from a lack of knowledge on the part of the user or from a misunderstanding of a particular concept.

[0416] Next, the server automatically collects information related to the error from external sources. This is possible by leveraging open-access educational resources and online libraries. The collected information is extremely useful for deepening the user's understanding.

[0417] The terminal displays the analysis results and related information sent from the server to the user. This allows the user to specifically understand which areas they have made mistakes in and how to correct those deficiencies. The user can review the information provided on the terminal and supplement their learning.

[0418] For example, if a user makes a mistake on a probability and statistics problem in a math exam, the server analyzes the error and identifies that it stemmed from a lack of understanding of the fundamental laws of statistics. The server then retrieves detailed information and supplementary materials on these laws from external sources and displays them on the user's device. The user can then use this information to quickly improve their learning and overcome their weaknesses.

[0419] This entire system is built with the aim of providing efficient and effective learning support, allowing users to reliably get closer to passing the exam.

[0420] The following describes the processing flow.

[0421] Step 1:

[0422] The user completes the test and sends the answer data from the terminal to the server. The server receives this data and performs an initial analysis to determine which questions were answered correctly and which were answered incorrectly.

[0423] Step 2:

[0424] The server uses generation technology to analyze incorrect answers in detail. Specifically, it identifies which knowledge elements the user may have misunderstood based on the question content and answer choices.

[0425] Step 3:

[0426] The server retrieves information related to the identified error from external sources. This includes obtaining explanations and examples on the relevant topic from educational resources and databases on the internet.

[0427] Step 4:

[0428] The terminal displays analysis results and additional information sent from the server to the user. This information includes details about the reasons for errors and the knowledge needed for improvement.

[0429] Step 5:

[0430] Users advance their learning using the provided information. They supplement their knowledge and deepen their understanding based on the materials presented on their devices.

[0431] Step 6:

[0432] The server tracks the user's learning progress and stores error data in a database. Based on this information, common error patterns are identified, and learning support is enhanced so that it can be applied to other users.

[0433] (Example 1)

[0434] 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."

[0435] In qualification exams and exam preparation, users are required to accurately analyze the causes of their incorrect answers and effectively reinforce their learning. However, conventional systems have not provided sufficient detailed analysis of individual errors or relevant information, making it difficult for users to efficiently deepen their understanding. Therefore, there is a need to provide support that enables users to understand their own errors and to learn effectively based on that understanding.

[0436] 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.

[0437] In this invention, the server includes information processing means for analyzing user answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and information acquisition means for automatically collecting information related to the user's errors from external information sources. This enables the user to understand the causes of their incorrect answers, efficiently acquire related information, and quickly address their weaknesses.

[0438] "Information processing means" refers to methods and technologies for analyzing user response data and identifying errors.

[0439] "Analysis methods using generative technology" refers to methods that utilize generative AI technology to clarify the cause of identified errors.

[0440] "Information acquisition means" refers to technologies and methods for automatically collecting information related to user errors from external sources.

[0441] "Display means" refers to the interface or mechanism for providing collected information to the user.

[0442] "User interface means" refers to an interface that visually displays relevant information based on analysis results and presents it in a way that is easy for the user to understand.

[0443] A "database management system" refers to a system that accumulates and analyzes user error data to identify common error patterns.

[0444] "Means for generating learning plans" refers to technologies that automatically generate individually optimized learning plans based on the user's error patterns.

[0445] This invention is a system designed to improve the learning efficiency of users in entrance exams and qualification tests. The user takes an exam and inputs their answers into a terminal. The terminal then transmits this answer data to a server via a network, where the data is analyzed.

[0446] The server uses an information processing program implemented in Python to analyze the received answer data. The analyzed data is then analyzed using AI technology to identify incorrect answers and determine whether the cause is a lack of knowledge or a misunderstanding. A generative AI model handles this analysis process, revealing the root cause of the problem.

[0447] Based on the analysis results, the server investigates external information sources and collects additional information to deepen the user's understanding. Web scraping tools (e.g., BeautifulSoup and Scrapy) targeting open-access information resources and online libraries on the web are used for information acquisition.

[0448] The collected information and analysis results are packaged and delivered to the device through an interface. The device visually presents this information to the user, allowing the user to understand their weaknesses and proceed with specific learning to overcome them.

[0449] As a concrete example, consider a case where a user makes a mistake on a "probability and statistics" problem in a math exam. The server identifies that the cause of the mistake is a lack of understanding of "basic statistical laws." The server then retrieves educational materials on these laws from an external source and presents them to the user's device, allowing the user to deepen their understanding in a short amount of time.

[0450] Examples of prompts used by this system are as follows:

[0451] "When a user makes a mistake on a specific question in an exam, please conduct an analysis to provide a cause analysis and related information. A possible reason for such a mistake is a lack of understanding of basic statistical principles."

[0452] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0453] Step 1:

[0454] The user takes the test and inputs their answers into the terminal. Specifically, the user enters their answers to the test questions into a dedicated interface. This becomes the initial input data for this system.

[0455] Step 2:

[0456] The terminal sends the entered answer data to the server. The terminal uses an internet connection to send the answer data to the server via a security protocol. The transmitted answer data is used for the analysis process on the server.

[0457] Step 3:

[0458] The server receives the answer data and analyzes it using information processing tools. Specifically, the server uses a generative AI model to evaluate the accuracy of the answer data and identify which questions the user answered incorrectly. During this process, information on the accuracy rate and incorrect answers is output.

[0459] Step 4:

[0460] The server analyzes the causes of errors identified using generation technology. The server utilizes AI models to analyze whether the incorrect answers stem from a lack of knowledge or misunderstanding. The output of this step includes categories of the causes of the incorrect answers.

[0461] Step 5:

[0462] The server collects relevant information from external sources. Using scraping tools, the server accesses educational resources on the web and collects information related to incorrect answers. This information is then output as supplementary material for the user.

[0463] Step 6:

[0464] The server sends the analysis results and collected information to the terminal. The server sends the analysis results and related information to the terminal in a user-friendly format, preparing it for display on the terminal.

[0465] Step 7:

[0466] The terminal presents the user with analysis results and related information. The terminal displays the information on the interface in a user-friendly format. This allows the user to refer to information about their errors and how to correct them.

[0467] Step 8:

[0468] The user learns based on the information presented. The user utilizes this information to understand their own errors and reinforce their learning. This allows them to efficiently overcome their weaknesses.

[0469] (Application Example 1)

[0470] 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."

[0471] In qualification exams and exam preparation, there is a need for support systems that enable individual users to learn efficiently and effectively. However, conventional learning support systems have the challenge of being unable to analyze user errors in detail and provide appropriate information. Furthermore, there has been a lack of means to properly analyze user answer information and provide relevant information in real time.

[0472] 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.

[0473] In this invention, the server includes data processing means for analyzing user answer information and identifying errors, data analysis means using generation technology for analyzing the causes of identified errors, and information gathering means for automatically collecting information related to user errors from external information resources. This makes it possible to understand the causes of errors in real time for individual users and provide them with appropriate learning resources.

[0474] "Data processing means for analyzing user answer information and identifying errors" refers to computer system technology that analyzes answer data entered by users during exams or learning and determines whether it is correct or incorrect.

[0475] "Data analysis methods using generation techniques to analyze the causes of identified errors" refers to methods that utilize generation techniques to analyze data in detail in order to pinpoint the root cause of an error.

[0476] "Information gathering means for automatically collecting information related to user errors from external information resources" refers to technology that automatically acquires information related to user errors from external information sources such as educational materials and databases on the internet.

[0477] "A communication method for transmitting answer information to a data server via a communication network" refers to a communication technology for transmitting answer information entered by a user to a server located in a remote location via the internet.

[0478] "Result display means for receiving analysis results from a server and presenting them to the user" refers to a screen display system that presents the data results analyzed by the server to the user in an easy-to-understand manner.

[0479] This invention provides a support system for efficiently progressing with learning during qualification exams and exam preparation. The system mainly consists of a user terminal, network communication, and a data server.

[0480] Users input their exam answers from devices such as smartphones or computers. The entered answer information is transmitted via the internet to a remote data server using a communication method.

[0481] The server uses data processing means to analyze the received answer information and identify errors. The analyzed data is further analyzed by data analysis means using generation technology to pinpoint the cause of the errors. In this process, commonly misunderstood concepts and lack of knowledge are taken into consideration.

[0482] Subsequently, the server automatically collects relevant materials from external information resources. Through these information gathering methods, information obtained from educational materials, online libraries, and other sources is organized in a way that is directly useful for learning.

[0483] Finally, the analysis results and collected information from the server are presented to the user through the results display on their terminal. This allows the user to efficiently identify their weaknesses and proceed with learning to address them. For example, if a user makes a mistake in "probability and statistics" in mathematics, the server analysis will determine that they lack understanding of "basic statistical laws," and relevant materials will be provided.

[0484] An example of a prompt message when using a generative AI model might be: "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and suggest links to relevant learning materials."

[0485] This system enables the identification and overcoming of learning weaknesses in real time.

[0486] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0487] Step 1:

[0488] Users input their test answers from their devices. This input is digitized as questionnaire or multiple-choice responses. The answer data is then transmitted to a server via a communication network. Secure protocols are used to ensure the data's safety during this process.

[0489] Step 2:

[0490] The server analyzes the received answer data using data processing tools. Based on the input data, it performs a correctness check and identifies errors. The data processing performed here involves detecting errors through statistical analysis and simple conditional branching. As output, the answer with identified errors is generated.

[0491] Step 3:

[0492] The server uses data analysis methods based on generative technology to further analyze the causes of identified errors. It receives error data as input and utilizes a generative AI model to pinpoint the causes. Data processing involves analyzing error patterns and identifying the root causes. The analysis results are obtained as output.

[0493] Step 4:

[0494] The server utilizes information gathering methods to collect relevant information from external information resources. The analysis results obtained in the previous step are used as input. Data processing involves searching educational materials and databases on the internet to extract relevant information. This results in the output of supplementary materials and related information.

[0495] Step 5:

[0496] The terminal receives analysis results and collected information sent from the server. The input is data provided by the server. On the terminal, a means of displaying results is used to present them to the user as visual information. Specifically, this involves displaying the results on the user interface so that the user can confirm them.

[0497] Step 6:

[0498] The user reviews the results displayed on the device and uses that information to further their learning. An example of a prompt message is, "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and suggest links to relevant learning materials." This allows for the creation of an effective learning plan.

[0499] 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.

[0500] This invention provides a learning support system that takes into account the user's emotional state in order to improve the user's learning efficiency. This system can recognize the user's emotions in real time using an emotion engine during the process of the user preparing for an exam, and dynamically adjust the learning plan based on that recognition.

[0501] The system's main configuration is as follows: First, the user takes an exam and sends their answer data from their terminal to the server. The server analyzes this data, identifies errors, and analyzes the causes using generation technology. The analysis results are enhanced through information acquisition means that collect relevant information from external educational resources, and this information is provided to the user.

[0502] Furthermore, this invention incorporates an emotion engine that analyzes the user's emotions from their facial expressions, tone of voice, and other factors. For example, if the device determines that the user is feeling stressed, it will recommend that the user access appropriate content or take a break to help them relax.

[0503] On the device, analysis results from the server and the output of the emotion engine are integrated, and a customized learning plan and feedback are presented to the user. This allows users to learn at their own pace and according to their emotional state.

[0504] Specifically, for example, suppose a user is solving an English grammar problem and the emotion engine detects that the user is feeling anxious. The server can then take this emotional information into consideration and present an explanation from a different perspective that is easier for the user to understand, and also suggest effective relaxation methods. In this way, the goal is to make the user's learning experience more intuitive and effective.

[0505] This system aims to maximize learning effectiveness by enabling detailed emotion recognition, thereby achieving even greater learning efficiency.

[0506] The following describes the processing flow.

[0507] Step 1:

[0508] Users take the test using their devices and enter their answers. The answer data is sent to the server in real time.

[0509] Step 2:

[0510] The server analyzes the submitted answer data to identify which questions the user answered incorrectly. The analysis also takes into account the user's past answer data.

[0511] Step 3:

[0512] The server uses generation techniques to analyze the cause of the error in detail. This includes identifying the user's misunderstood concepts and knowledge gaps.

[0513] Step 4:

[0514] The server automatically collects relevant supplementary information from external sources and prepares learning resources tailored to the user's needs.

[0515] Step 5:

[0516] Simultaneously, the emotion engine built into the device analyzes the user's facial expressions and voice data to recognize their current emotional state. This information is sent to the server in real time.

[0517] Step 6:

[0518] Based on the recognized emotional state, the server provides appropriate feedback and adjusts content for the user. Specifically, if the user is feeling stressed, it will suggest taking a break or present relaxation content.

[0519] Step 7:

[0520] The terminal provides the user with analysis results and feedback from the server. This includes detailed explanations and advice regarding the questions answered incorrectly.

[0521] Step 8:

[0522] Based on the information and feedback provided, users progress through their learning while implementing a learning plan that takes their emotional state into consideration. They can request further feedback from their device as needed.

[0523] Step 9:

[0524] The server continuously records learning progress and sentiment data, and updates the learning plan as needed. This data is also used to help other users.

[0525] (Example 2)

[0526] 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."

[0527] In recent years, there has been a growing demand for providing users with an environment in which they can learn effectively and efficiently. However, conventional learning support systems construct learning plans based solely on the user's answers, and therefore do not provide feedback or learning suggestions that take into account the user's emotional state. As a result, there is a problem in that a user's unique emotional state may affect their learning efficiency. In particular, there is a need to provide learning support that takes these emotions into account for users who are experiencing stress or anxiety.

[0528] 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.

[0529] In this invention, the server includes information processing means for analyzing the user's answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and emotion analysis means for analyzing the user's emotional state in real time. This makes it possible to provide a detailed learning plan tailored to the user's emotional state.

[0530] "Information processing means" refers to the system's function for analyzing user response data and identifying errors.

[0531] "Analysis methods using generative technology" refer to methods that utilize generative models to deeply analyze the causes of identified errors.

[0532] "Information acquisition means" refers to a function that automatically collects information related to user errors from external sources.

[0533] "Display means" refers to a device or function for providing collected information to the user visually.

[0534] "Emotion analysis means" refers to a function that analyzes the user's facial expressions, tone of voice, etc., to identify the user's emotional state in real time.

[0535] "Means of providing learning plans" refers to a function that presents users with individually optimized learning plans based on their error tendencies and emotional state.

[0536] "Database management means" refers to a means of accumulating user error data and identifying common error patterns from that data.

[0537] This learning support system performs real-time emotional state analysis and error correction to maximize the user's learning efficiency. The main components of the system include the user's terminal, a server, and a generative AI model.

[0538] First, users take tests and exercises using their own devices and input their answer data. This answer data is sent to the server via the device. The server immediately analyzes the received data and uses information processing tools to identify user errors. In this process, analysis tools using generation technology are used to deeply analyze the causes of the errors.

[0539] Furthermore, the server automatically retrieves relevant learning materials from external sources and provides them to the user through information retrieval means. For example, relevant video materials and supplementary materials are collected. This information is presented to the user visually through the terminal's display means.

[0540] On the other hand, the device is equipped with emotion analysis capabilities that analyze the user's facial expressions and tone of voice in real time. If the user's emotional state is stressful, relaxation methods and adjustments to the learning speed are recommended based on the analysis results.

[0541] This system allows users to receive optimized learning plans tailored to their emotional state and to get personalized feedback.

[0542] As a concrete example, suppose a user experiences anxiety while solving an English grammar problem. At this point, the user's anxiety is detected by an emotion analysis tool. Based on this data, the server generates feedback such as presenting explanations from other perspectives, additional materials, and playing music to help the user relax.

[0543] An example of a prompt to a generative AI model would be, "Please tell me how to learn when I feel anxious while solving English grammar problems. In particular, I would like to know more about easy-to-understand explanations and relaxation techniques." By using this prompt, the AI ​​model will generate answers that meet the user's needs and support the learning process.

[0544] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0545] Step 1:

[0546] The user uses a terminal to take tests and solve problems. The terminal collects answer data and prepares it for transmission to the server. In this process, the answers entered by the user are collected, encrypted, and converted into a format that can be sent to the server. The input is the user's answer data, and the output is the prepared data for transmission to the server.

[0547] Step 2:

[0548] The server analyzes the received answer data using information processing tools. Specifically, the server determines whether the answer is correct or incorrect and analyzes the cause of the error using analysis tools that utilize generation technology. The input is the user's answer data, and the output is the analysis results regarding the errors. This analysis clarifies the trends and causes of incorrect answers.

[0549] Step 3:

[0550] The server automatically collects relevant learning materials from external sources based on the analysis results. The server utilizes information acquisition methods to search for learning materials that are useful for the user's learning. The input is the error analysis results, and the output is data from relevant external learning resources. The server collects and reconstructs this information.

[0551] Step 4:

[0552] The terminal presents collected learning materials to the user through a display mechanism. The terminal displays information in a format that is visually easy for the user to understand. The input is data from external resources transferred from the server, and the output is a display of learning materials that the user can view.

[0553] Step 5:

[0554] The device uses emotion analysis techniques to analyze the user's facial expressions, voice tone, and other factors to evaluate their emotional state. Specifically, the device's sensors detect the user's voice patterns and facial movements. The input is real-time user audio and video data, and the output is the analyzed emotional state.

[0555] Step 6:

[0556] The device generates and provides a customized learning plan based on the user's emotional state. It initiates a protocol to propose an optimized learning plan to the user. The input is the result of the emotion analysis, and the output is an individually adjusted learning schedule. This plan is designed taking into account the user's level of understanding and mental state.

[0557] (Application Example 2)

[0558] 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."

[0559] In today's world, improving user learning efficiency requires providing appropriate support tailored to each individual's level of understanding. However, conventional learning systems lack dynamic learning adjustments that take into account the user's emotional state, making it difficult to promote learning while reducing learners' psychological stress.

[0560] 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.

[0561] In this invention, the server includes data processing means for analyzing the user's answer data and identifying errors, data analysis means using generation technology for analyzing the causes of the identified errors, and emotion recognition and plan adjustment means for detecting the user's emotions in real time and adjusting the learning plan based on those emotions. This makes it possible to provide learning support that takes into account the user's emotional state, thereby improving the user's learning efficiency.

[0562] "User response data" refers to the collective data of the answers that learners have submitted to various problems.

[0563] "Data processing means for identifying errors" refers to a device or method that is responsible for the process of detecting incorrect parts from the user's answer data.

[0564] "Data analysis means using generational technology" refers to a device or method that utilizes generational technology such as machine learning to deeply analyze the causes of identified errors.

[0565] "Data collection means" refers to a device or method that has the function of automatically collecting necessary information from external sources.

[0566] "Information display means" refers to a device or method for visually providing users with necessary information.

[0567] "Emotion recognition and plan adjustment means" refers to a device or method that has the function of detecting the user's emotions in real time and dynamically adjusting the learning plan based on those emotions.

[0568] A "database management system" refers to a data management system that stores user data and analyzes specific patterns.

[0569] A "learning plan generation means" is a device or method that has the function of creating an individually optimized learning plan according to the user's error tendencies and emotional state.

[0570] To realize this invention, a data analysis system is required to process learner response data and identify errors. The server uses a data processing device to analyze the response data received from the user. Specifically, it utilizes a data analysis device employing generation technology to detect errors and analyze their causes. Efficient analysis is possible by using data processing and AI libraries such as Apache Kafka and TensorFlow.

[0571] Furthermore, the device detects the user's emotions in real time based on the collected analysis data. This involves using emotion recognition technologies such as OpenCV to analyze the user's facial expressions and tone of voice to evaluate their emotional state. Based on this emotional information, the learning plan is dynamically adjusted to provide the learner with an optimal learning environment.

[0572] For example, if a user shows signs of anxiety while solving grammar problems, the server receives this emotional information and adjusts the learning plan accordingly. This could lead to the user being offered appropriate content to help them relax. Such a system provides support that takes the user's emotional state into account, resulting in more efficient learning and reduced stress.

[0573] It is also possible to construct appropriate prompt sentences by utilizing generative AI models. For example, instructions can be given to the AI ​​system using a prompt sentence such as, "If the user is feeling stressed, suggest ways to provide relaxation content or gentle guidance."

[0574] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0575] Step 1:

[0576] The server receives the answer data from the user as input and performs analysis using a data processing device. This process analyzes the answer data and performs basic calculations to determine whether each answer is correct or incorrect. After analysis, a list of incorrect answers is output.

[0577] Step 2:

[0578] The server uses the list of incorrect answers output in Step 1 as input and performs a data analysis using a generative AI model to deeply analyze the causes of errors. In this step, the generative AI model generates data to identify error trends and common causes, and outputs an analysis report.

[0579] Step 3:

[0580] The device uses OpenCV to analyze emotions using data obtained in real time from the user's camera and microphone as input. Through this analysis, it determines the user's emotional state from their facial expressions and tone of voice, and outputs that information.

[0581] Step 4:

[0582] The server receives the analysis report from step 2 and the emotional information from step 3 as input, and dynamically adjusts the learning plan using emotion recognition and plan adjustment mechanisms. This allows it to output a learning plan optimized for the learner's emotional state in real time.

[0583] Step 5:

[0584] The device displays the learning plan generated in step 4 to the user, providing an optimized learning experience. Specifically, it presents the learning plan and delivers emotion-based content.

[0585] Step 6:

[0586] If a user experiences stress or anxiety while progressing through their learning plan, prompt messages are input into the generative AI model, which then suggests specific guidance and support for relaxation. An example of a prompt message is, "If the user is feeling stressed, please suggest ways to provide relaxation content and gentle guidance."

[0587] 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.

[0588] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0589] 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.

[0590] [Fourth Embodiment]

[0591] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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).

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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.

[0603] 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".

[0604] This invention provides a system that allows users to efficiently progress in their learning during qualification exams and exam preparation. The system begins with the user taking an exam and sending the results to a server. The user's answer data is collected on the server via an online environment.

[0605] Based on the received answer data, the server identifies the questions the user answered incorrectly. After the errors are identified, the server uses generation technology to analyze the causes of the errors and extract detailed information. This process clarifies whether the errors stemmed from a lack of knowledge on the part of the user or from a misunderstanding of a particular concept.

[0606] Next, the server automatically collects information related to the error from external sources. This is possible by leveraging open-access educational resources and online libraries. The collected information is extremely useful for deepening the user's understanding.

[0607] The terminal displays the analysis results and related information sent from the server to the user. This allows the user to specifically understand which areas they have made mistakes in and how to correct those deficiencies. The user can review the information provided on the terminal and supplement their learning.

[0608] For example, if a user makes a mistake on a probability and statistics problem in a math exam, the server analyzes the error and identifies that it stemmed from a lack of understanding of the fundamental laws of statistics. The server then retrieves detailed information and supplementary materials on these laws from external sources and displays them on the user's device. The user can then use this information to quickly improve their learning and overcome their weaknesses.

[0609] This entire system is built with the aim of providing efficient and effective learning support, allowing users to reliably get closer to passing the exam.

[0610] The following describes the processing flow.

[0611] Step 1:

[0612] The user completes the test and sends the answer data from the terminal to the server. The server receives this data and performs an initial analysis to determine which questions were answered correctly and which were answered incorrectly.

[0613] Step 2:

[0614] The server uses generation technology to analyze incorrect answers in detail. Specifically, it identifies which knowledge elements the user may have misunderstood based on the question content and answer choices.

[0615] Step 3:

[0616] The server retrieves information related to the identified error from external sources. This includes obtaining explanations and examples on the relevant topic from educational resources and databases on the internet.

[0617] Step 4:

[0618] The terminal displays analysis results and additional information sent from the server to the user. This information includes details about the reasons for errors and the knowledge needed for improvement.

[0619] Step 5:

[0620] Users advance their learning using the provided information. They supplement their knowledge and deepen their understanding based on the materials presented on their devices.

[0621] Step 6:

[0622] The server tracks the user's learning progress and stores error data in a database. Based on this information, common error patterns are identified, and learning support is enhanced so that it can be applied to other users.

[0623] (Example 1)

[0624] 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".

[0625] In qualification exams and exam preparation, users are required to accurately analyze the causes of their incorrect answers and effectively reinforce their learning. However, conventional systems have not provided sufficient detailed analysis of individual errors or relevant information, making it difficult for users to efficiently deepen their understanding. Therefore, there is a need to provide support that enables users to understand their own errors and to learn effectively based on that understanding.

[0626] 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.

[0627] In this invention, the server includes information processing means for analyzing user answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and information acquisition means for automatically collecting information related to the user's errors from external information sources. This enables the user to understand the causes of their incorrect answers, efficiently acquire related information, and quickly address their weaknesses.

[0628] "Information processing means" refers to methods and technologies for analyzing user response data and identifying errors.

[0629] "Analysis methods using generative technology" refers to methods that utilize generative AI technology to clarify the cause of identified errors.

[0630] "Information acquisition means" refers to technologies and methods for automatically collecting information related to user errors from external sources.

[0631] "Display means" refers to the interface or mechanism for providing collected information to the user.

[0632] "User interface means" refers to an interface that visually displays relevant information based on analysis results and presents it in a way that is easy for the user to understand.

[0633] A "database management system" refers to a system that accumulates and analyzes user error data to identify common error patterns.

[0634] "Means for generating learning plans" refers to technologies that automatically generate individually optimized learning plans based on the user's error patterns.

[0635] This invention is a system designed to improve the learning efficiency of users in entrance exams and qualification tests. The user takes an exam and inputs their answers into a terminal. The terminal then transmits this answer data to a server via a network, where the data is analyzed.

[0636] The server uses an information processing program implemented in Python to analyze the received answer data. The analyzed data is then analyzed using AI technology to identify incorrect answers and determine whether the cause is a lack of knowledge or a misunderstanding. A generative AI model handles this analysis process, revealing the root cause of the problem.

[0637] Based on the analysis results, the server investigates external information sources and collects additional information to deepen the user's understanding. Web scraping tools (e.g., BeautifulSoup and Scrapy) targeting open-access information resources and online libraries on the web are used for information acquisition.

[0638] The collected information and analysis results are packaged and delivered to the device through an interface. The device visually presents this information to the user, allowing the user to understand their weaknesses and proceed with specific learning to overcome them.

[0639] As a concrete example, consider a case where a user makes a mistake on a "probability and statistics" problem in a math exam. The server identifies that the cause of the mistake is a lack of understanding of "basic statistical laws." The server then retrieves educational materials on these laws from an external source and presents them to the user's device, allowing the user to deepen their understanding in a short amount of time.

[0640] Examples of prompts used by this system are as follows:

[0641] "When a user makes a mistake on a specific question in an exam, please conduct an analysis to provide a cause analysis and related information. A possible reason for such a mistake is a lack of understanding of basic statistical principles."

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] The user takes the test and inputs their answers into the terminal. Specifically, the user enters their answers to the test questions into a dedicated interface. This becomes the initial input data for this system.

[0645] Step 2:

[0646] The terminal sends the entered answer data to the server. The terminal uses an internet connection to send the answer data to the server via a security protocol. The transmitted answer data is used for the analysis process on the server.

[0647] Step 3:

[0648] The server receives the answer data and analyzes it using information processing tools. Specifically, the server uses a generative AI model to evaluate the accuracy of the answer data and identify which questions the user answered incorrectly. During this process, information on the accuracy rate and incorrect answers is output.

[0649] Step 4:

[0650] The server analyzes the causes of errors identified using generation technology. The server utilizes AI models to analyze whether the incorrect answers stem from a lack of knowledge or misunderstanding. The output of this step includes categories of the causes of the incorrect answers.

[0651] Step 5:

[0652] The server collects relevant information from external sources. Using scraping tools, the server accesses educational resources on the web and collects information related to incorrect answers. This information is then output as supplementary material for the user.

[0653] Step 6:

[0654] The server sends the analysis results and collected information to the terminal. The server sends the analysis results and related information to the terminal in a user-friendly format, preparing it for display on the terminal.

[0655] Step 7:

[0656] The terminal presents the user with analysis results and related information. The terminal displays the information on the interface in a user-friendly format. This allows the user to refer to information about their errors and how to correct them.

[0657] Step 8:

[0658] The user learns based on the information presented. The user utilizes this information to understand their own errors and reinforce their learning. This allows them to efficiently overcome their weaknesses.

[0659] (Application Example 1)

[0660] 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".

[0661] In qualification exams and exam preparation, there is a need for support systems that enable individual users to learn efficiently and effectively. However, conventional learning support systems have the challenge of being unable to analyze user errors in detail and provide appropriate information. Furthermore, there has been a lack of means to properly analyze user answer information and provide relevant information in real time.

[0662] 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.

[0663] In this invention, the server includes data processing means for analyzing user answer information and identifying errors, data analysis means using generation technology for analyzing the causes of identified errors, and information gathering means for automatically collecting information related to user errors from external information resources. This makes it possible to understand the causes of errors in real time for individual users and provide them with appropriate learning resources.

[0664] "Data processing means for analyzing user answer information and identifying errors" refers to computer system technology that analyzes answer data entered by users during exams or learning and determines whether it is correct or incorrect.

[0665] "Data analysis methods using generation techniques to analyze the causes of identified errors" refers to methods that utilize generation techniques to analyze data in detail in order to pinpoint the root cause of an error.

[0666] "Information gathering means for automatically collecting information related to user errors from external information resources" refers to technology that automatically acquires information related to user errors from external information sources such as educational materials and databases on the internet.

[0667] "A communication method for transmitting answer information to a data server via a communication network" refers to a communication technology for transmitting answer information entered by a user to a server located in a remote location via the internet.

[0668] "Result display means for receiving analysis results from a server and presenting them to the user" refers to a screen display system that presents the data results analyzed by the server to the user in an easy-to-understand manner.

[0669] This invention provides a support system for efficiently progressing with learning during qualification exams and exam preparation. The system mainly consists of a user terminal, network communication, and a data server.

[0670] Users input their exam answers from devices such as smartphones or computers. The entered answer information is transmitted via the internet to a remote data server using a communication method.

[0671] The server uses data processing means to analyze the received answer information and identify errors. The analyzed data is further analyzed by data analysis means using generation technology to pinpoint the cause of the errors. In this process, commonly misunderstood concepts and lack of knowledge are taken into consideration.

[0672] Subsequently, the server automatically collects relevant materials from external information resources. Through these information gathering methods, information obtained from educational materials, online libraries, and other sources is organized in a way that is directly useful for learning.

[0673] Finally, the analysis results and collected information from the server are presented to the user through the results display on their terminal. This allows the user to efficiently identify their weaknesses and proceed with learning to address them. For example, if a user makes a mistake in "probability and statistics" in mathematics, the server analysis will determine that they lack understanding of "basic statistical laws," and relevant materials will be provided.

[0674] An example of a prompt message when using a generative AI model might be: "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and suggest links to relevant learning materials."

[0675] This system enables the identification and overcoming of learning weaknesses in real time.

[0676] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0677] Step 1:

[0678] Users input their test answers from their devices. This input is digitized as questionnaire or multiple-choice responses. The answer data is then transmitted to a server via a communication network. Secure protocols are used to ensure the data's safety during this process.

[0679] Step 2:

[0680] The server analyzes the received answer data using data processing tools. Based on the input data, it performs a correctness check and identifies errors. The data processing performed here involves detecting errors through statistical analysis and simple conditional branching. As output, the answer with identified errors is generated.

[0681] Step 3:

[0682] The server uses data analysis methods based on generative technology to further analyze the causes of identified errors. It receives error data as input and utilizes a generative AI model to pinpoint the causes. Data processing involves analyzing error patterns and identifying the root causes. The analysis results are obtained as output.

[0683] Step 4:

[0684] The server utilizes information gathering methods to collect relevant information from external information resources. The analysis results obtained in the previous step are used as input. Data processing involves searching educational materials and databases on the internet to extract relevant information. This results in the output of supplementary materials and related information.

[0685] Step 5:

[0686] The terminal receives analysis results and collected information sent from the server. The input is data provided by the server. On the terminal, a means of displaying results is used to present them to the user as visual information. Specifically, this involves displaying the results on the user interface so that the user can confirm them.

[0687] Step 6:

[0688] The user reviews the results displayed on the device and uses that information to further their learning. An example of a prompt message is, "Generate analysis results for exam preparation, identify the user's mistakes and their causes, and suggest links to relevant learning materials." This allows for the creation of an effective learning plan.

[0689] 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.

[0690] This invention provides a learning support system that takes into account the user's emotional state in order to improve the user's learning efficiency. This system can recognize the user's emotions in real time using an emotion engine during the process of the user preparing for an exam, and dynamically adjust the learning plan based on that recognition.

[0691] The system's main configuration is as follows: First, the user takes an exam and sends their answer data from their terminal to the server. The server analyzes this data, identifies errors, and analyzes the causes using generation technology. The analysis results are enhanced through information acquisition means that collect relevant information from external educational resources, and this information is provided to the user.

[0692] Furthermore, this invention incorporates an emotion engine that analyzes the user's emotions from their facial expressions, tone of voice, and other factors. For example, if the device determines that the user is feeling stressed, it will recommend that the user access appropriate content or take a break to help them relax.

[0693] On the device, analysis results from the server and the output of the emotion engine are integrated, and a customized learning plan and feedback are presented to the user. This allows users to learn at their own pace and according to their emotional state.

[0694] Specifically, for example, suppose a user is solving an English grammar problem and the emotion engine detects that the user is feeling anxious. The server can then take this emotional information into consideration and present an explanation from a different perspective that is easier for the user to understand, and also suggest effective relaxation methods. In this way, the goal is to make the user's learning experience more intuitive and effective.

[0695] This system aims to maximize learning effectiveness by enabling detailed emotion recognition, thereby achieving even greater learning efficiency.

[0696] The following describes the processing flow.

[0697] Step 1:

[0698] Users take the test using their devices and enter their answers. The answer data is sent to the server in real time.

[0699] Step 2:

[0700] The server analyzes the submitted answer data to identify which questions the user answered incorrectly. The analysis also takes into account the user's past answer data.

[0701] Step 3:

[0702] The server uses generation techniques to analyze the cause of the error in detail. This includes identifying the user's misunderstood concepts and knowledge gaps.

[0703] Step 4:

[0704] The server automatically collects relevant supplementary information from external sources and prepares learning resources tailored to the user's needs.

[0705] Step 5:

[0706] Simultaneously, the emotion engine built into the device analyzes the user's facial expressions and voice data to recognize their current emotional state. This information is sent to the server in real time.

[0707] Step 6:

[0708] Based on the recognized emotional state, the server provides appropriate feedback and adjusts content for the user. Specifically, if the user is feeling stressed, it will suggest taking a break or present relaxation content.

[0709] Step 7:

[0710] The terminal provides the user with analysis results and feedback from the server. This includes detailed explanations and advice regarding the questions answered incorrectly.

[0711] Step 8:

[0712] Based on the information and feedback provided, users progress through their learning while implementing a learning plan that takes their emotional state into consideration. They can request further feedback from their device as needed.

[0713] Step 9:

[0714] The server continuously records learning progress and sentiment data, and updates the learning plan as needed. This data is also used to help other users.

[0715] (Example 2)

[0716] 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".

[0717] In recent years, there has been a growing demand for providing users with an environment in which they can learn effectively and efficiently. However, conventional learning support systems construct learning plans based solely on the user's answers, and therefore do not provide feedback or learning suggestions that take into account the user's emotional state. As a result, there is a problem in that a user's unique emotional state may affect their learning efficiency. In particular, there is a need to provide learning support that takes these emotions into account for users who are experiencing stress or anxiety.

[0718] 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.

[0719] In this invention, the server includes information processing means for analyzing the user's answer data and identifying errors, analysis means using generation technology for analyzing the causes of the identified errors, and emotion analysis means for analyzing the user's emotional state in real time. This makes it possible to provide a detailed learning plan tailored to the user's emotional state.

[0720] "Information processing means" refers to the system's function for analyzing user response data and identifying errors.

[0721] "Analysis methods using generative technology" refer to methods that utilize generative models to deeply analyze the causes of identified errors.

[0722] "Information acquisition means" refers to a function that automatically collects information related to user errors from external sources.

[0723] "Display means" refers to a device or function for providing collected information to the user visually.

[0724] "Emotion analysis means" refers to a function that analyzes the user's facial expressions, tone of voice, etc., to identify the user's emotional state in real time.

[0725] "Means of providing learning plans" refers to a function that presents users with individually optimized learning plans based on their error tendencies and emotional state.

[0726] "Database management means" refers to a means of accumulating user error data and identifying common error patterns from that data.

[0727] This learning support system performs real-time emotional state analysis and error correction to maximize the user's learning efficiency. The main components of the system include the user's terminal, a server, and a generative AI model.

[0728] First, users take tests and exercises using their own devices and input their answer data. This answer data is sent to the server via the device. The server immediately analyzes the received data and uses information processing tools to identify user errors. In this process, analysis tools using generation technology are used to deeply analyze the causes of the errors.

[0729] Furthermore, the server automatically retrieves relevant learning materials from external sources and provides them to the user through information retrieval means. For example, relevant video materials and supplementary materials are collected. This information is presented to the user visually through the terminal's display means.

[0730] On the other hand, the device is equipped with emotion analysis capabilities that analyze the user's facial expressions and tone of voice in real time. If the user's emotional state is stressful, relaxation methods and adjustments to the learning speed are recommended based on the analysis results.

[0731] This system allows users to receive optimized learning plans tailored to their emotional state and to get personalized feedback.

[0732] As a concrete example, suppose a user experiences anxiety while solving an English grammar problem. At this point, the user's anxiety is detected by an emotion analysis tool. Based on this data, the server generates feedback such as presenting explanations from other perspectives, additional materials, and playing music to help the user relax.

[0733] An example of a prompt to a generative AI model would be, "Please tell me how to learn when I feel anxious while solving English grammar problems. In particular, I would like to know more about easy-to-understand explanations and relaxation techniques." By using this prompt, the AI ​​model will generate answers that meet the user's needs and support the learning process.

[0734] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0735] Step 1:

[0736] The user uses a terminal to take tests and solve problems. The terminal collects answer data and prepares it for transmission to the server. In this process, the answers entered by the user are collected, encrypted, and converted into a format that can be sent to the server. The input is the user's answer data, and the output is the prepared data for transmission to the server.

[0737] Step 2:

[0738] The server analyzes the received answer data using information processing tools. Specifically, the server determines whether the answer is correct or incorrect and analyzes the cause of the error using analysis tools that utilize generation technology. The input is the user's answer data, and the output is the analysis results regarding the errors. This analysis clarifies the trends and causes of incorrect answers.

[0739] Step 3:

[0740] The server automatically collects relevant learning materials from external sources based on the analysis results. The server utilizes information acquisition methods to search for learning materials that are useful for the user's learning. The input is the error analysis results, and the output is data from relevant external learning resources. The server collects and reconstructs this information.

[0741] Step 4:

[0742] The terminal presents collected learning materials to the user through a display mechanism. The terminal displays information in a format that is visually easy for the user to understand. The input is data from external resources transferred from the server, and the output is a display of learning materials that the user can view.

[0743] Step 5:

[0744] The device uses emotion analysis techniques to analyze the user's facial expressions, voice tone, and other factors to evaluate their emotional state. Specifically, the device's sensors detect the user's voice patterns and facial movements. The input is real-time user audio and video data, and the output is the analyzed emotional state.

[0745] Step 6:

[0746] The device generates and provides a customized learning plan based on the user's emotional state. It initiates a protocol to propose an optimized learning plan to the user. The input is the result of the emotion analysis, and the output is an individually adjusted learning schedule. This plan is designed taking into account the user's level of understanding and mental state.

[0747] (Application Example 2)

[0748] 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".

[0749] In today's world, improving user learning efficiency requires providing appropriate support tailored to each individual's level of understanding. However, conventional learning systems lack dynamic learning adjustments that take into account the user's emotional state, making it difficult to promote learning while reducing learners' psychological stress.

[0750] 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.

[0751] In this invention, the server includes data processing means for analyzing the user's answer data and identifying errors, data analysis means using generation technology for analyzing the causes of the identified errors, and emotion recognition and plan adjustment means for detecting the user's emotions in real time and adjusting the learning plan based on those emotions. This makes it possible to provide learning support that takes into account the user's emotional state, thereby improving the user's learning efficiency.

[0752] "User response data" refers to the collective data of the answers that learners have submitted to various problems.

[0753] "Data processing means for identifying errors" refers to a device or method that is responsible for the process of detecting incorrect parts from the user's answer data.

[0754] "Data analysis means using generational technology" refers to a device or method that utilizes generational technology such as machine learning to deeply analyze the causes of identified errors.

[0755] "Data collection means" refers to a device or method that has the function of automatically collecting necessary information from external sources.

[0756] "Information display means" refers to a device or method for visually providing users with necessary information.

[0757] "Emotion recognition and plan adjustment means" refers to a device or method that has the function of detecting the user's emotions in real time and dynamically adjusting the learning plan based on those emotions.

[0758] A "database management system" refers to a data management system that stores user data and analyzes specific patterns.

[0759] A "learning plan generation means" is a device or method that has the function of creating an individually optimized learning plan according to the user's error tendencies and emotional state.

[0760] To realize this invention, a data analysis system is required to process learner response data and identify errors. The server uses a data processing device to analyze the response data received from the user. Specifically, it utilizes a data analysis device employing generation technology to detect errors and analyze their causes. Efficient analysis is possible by using data processing and AI libraries such as Apache Kafka and TensorFlow.

[0761] Furthermore, the device detects the user's emotions in real time based on the collected analysis data. This involves using emotion recognition technologies such as OpenCV to analyze the user's facial expressions and tone of voice to evaluate their emotional state. Based on this emotional information, the learning plan is dynamically adjusted to provide the learner with an optimal learning environment.

[0762] For example, if a user shows signs of anxiety while solving grammar problems, the server receives this emotional information and adjusts the learning plan accordingly. This could lead to the user being offered appropriate content to help them relax. Such a system provides support that takes the user's emotional state into account, resulting in more efficient learning and reduced stress.

[0763] It is also possible to construct appropriate prompt sentences by utilizing generative AI models. For example, instructions can be given to the AI ​​system using a prompt sentence such as, "If the user is feeling stressed, suggest ways to provide relaxation content or gentle guidance."

[0764] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0765] Step 1:

[0766] The server receives the answer data from the user as input and performs analysis using a data processing device. This process analyzes the answer data and performs basic calculations to determine whether each answer is correct or incorrect. After analysis, a list of incorrect answers is output.

[0767] Step 2:

[0768] The server uses the list of incorrect answers output in Step 1 as input and performs a data analysis using a generative AI model to deeply analyze the causes of errors. In this step, the generative AI model generates data to identify error trends and common causes, and outputs an analysis report.

[0769] Step 3:

[0770] The device uses OpenCV to analyze emotions using data obtained in real time from the user's camera and microphone as input. Through this analysis, it determines the user's emotional state from their facial expressions and tone of voice, and outputs that information.

[0771] Step 4:

[0772] The server receives the analysis report from step 2 and the emotional information from step 3 as input, and dynamically adjusts the learning plan using emotion recognition and plan adjustment mechanisms. This allows it to output a learning plan optimized for the learner's emotional state in real time.

[0773] Step 5:

[0774] The device displays the learning plan generated in step 4 to the user, providing an optimized learning experience. Specifically, it presents the learning plan and delivers emotion-based content.

[0775] Step 6:

[0776] If a user experiences stress or anxiety while progressing through their learning plan, prompt messages are input into the generative AI model, which then suggests specific guidance and support for relaxation. An example of a prompt message is, "If the user is feeling stressed, please suggest ways to provide relaxation content and gentle guidance."

[0777] 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.

[0778] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0779] 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 robot 414.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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."

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] The following is further disclosed regarding the embodiments described above.

[0799] (Claim 1)

[0800] Information processing means for analyzing user response data and identifying errors,

[0801] Analysis means using generation techniques to analyze the cause of the identified error,

[0802] Information acquisition means for automatically collecting information related to user errors from external sources,

[0803] A display means for providing collected information to the user,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, comprising a database management means for accumulating error data of individual users and identifying common error patterns.

[0807] (Claim 3)

[0808] The system according to claim 1, comprising means for generating an individually optimized learning plan based on the user's error tendencies.

[0809] "Example 1"

[0810] (Claim 1)

[0811] Information processing means for analyzing user response data and identifying errors,

[0812] Analysis means using generation techniques to analyze the cause of the identified error,

[0813] Information acquisition means for automatically collecting information related to user errors from external sources,

[0814] A display means for providing collected information to the user,

[0815] A user interface means for visually displaying related information based on the analysis results,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, comprising a database management means for accumulating error data of individual users and identifying common error patterns.

[0819] (Claim 3)

[0820] The system according to claim 1, comprising means for generating an individually optimized learning plan based on the user's error tendencies.

[0821] "Application Example 1"

[0822] (Claim 1)

[0823] A data processing means for analyzing user answer information and identifying errors,

[0824] A data analysis means using generation techniques to analyze the cause of the identified error,

[0825] Information gathering means that automatically collects information related to user errors from external information resources,

[0826] Information display means for providing collected information to the user,

[0827] A communication means for transmitting answer information to a data server via a communication network,

[0828] A means for receiving analysis results from a server and presenting them to the user,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, comprising a database management means for accumulating error data of individual users and identifying common error patterns.

[0832] (Claim 3)

[0833] The system according to claim 1, comprising generation technology means for generating individually optimized learning plans based on the user's error tendencies.

[0834] "Example 2 of combining an emotion engine"

[0835] (Claim 1)

[0836] Information processing means for analyzing user response data and identifying errors,

[0837] Analysis means using generation techniques to analyze the cause of the identified error,

[0838] Information acquisition means for automatically collecting information related to user errors from external sources,

[0839] A display means for providing collected information to the user,

[0840] A means of analyzing the emotional state of users in real time,

[0841] A means of providing a customized learning plan based on emotional state,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, comprising a database management means for accumulating error data of individual users and identifying common error patterns.

[0845] (Claim 3)

[0846] The system according to claim 1, comprising means for generating an individually optimized learning plan based on the user's error tendencies and emotional state.

[0847] "Application example 2 when combining with an emotional engine"

[0848] (Claim 1)

[0849] A data processing means for analyzing user response data and identifying errors,

[0850] A data analysis means using generation techniques to analyze the cause of the identified error,

[0851] A data collection means that automatically collects information related to user errors from external sources,

[0852] Information display means for providing collected information to the user,

[0853] An emotion recognition and plan adjustment means for detecting user emotions in real time and adjusting the learning plan based on those emotions,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, comprising a database management means for accumulating error data and sentiment data of individual users and for identifying common error patterns and sentiment patterns.

[0857] (Claim 3)

[0858] The system according to claim 1, comprising a learning plan generation means that generates an individually optimized learning plan based on the user's error tendencies and emotional state. [Explanation of Symbols]

[0859] 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 data processing means for analyzing user answer information and identifying errors, A data analysis means using generation techniques to analyze the cause of the identified error, Information gathering means that automatically collects information related to user errors from external information resources, Information display means for providing collected information to the user, A communication means for transmitting answer information to a data server via a communication network, A means for receiving analysis results from a server and presenting them to the user, A system that includes this.

2. The system according to claim 1, further comprising a database management means for accumulating error data of individual users and identifying common error patterns.

3. The system according to claim 1, comprising generation technology means for generating individually optimized learning plans based on the user's error tendencies.

Images