system

Abstract

We provide the system. [Solution] A display means for showing a problem to a user and accepting answers, A means for collecting user answer data and past performance information, An analytical means for analyzing collected data to identify the user's strengths and weaknesses, A problem generation means that generates or selects the most suitable problem for the user based on the analysis results, A system that includes a means for presenting generated problems to users.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In test preparation question sets, there is a problem that it is only necessary to solve predetermined questions, and it is difficult to optimize learning according to the characteristics and needs of individual examinees. In particular, when an examinee has a sense of difficulty in a specific field, there are insufficient means to efficiently overcome it. For this reason, conventional question sets have a problem that they cannot present individually optimized questions according to each examinee, which impairs the efficiency of improving the examinees' academic ability.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for displaying problems to users and accepting answers, means for collecting user answer data and past performance information, means for analyzing the collected data to identify the user's strengths and weaknesses, means for generating or selecting optimal problems for the user based on the analysis results, and means for presenting the generated problems to the user. This enables test-takers to engage in individually optimized learning that efficiently overcomes their weaknesses, and furthermore, the analysis means can more effectively improve academic ability by presenting optimized problems based on answer trends and desired school information. In addition, since the problem generation means selects problems that are in line with the latest exam trends, test-takers can always prepare for the latest exams.

[0006] A "display means" is a means of providing an interface that visually presents a problem to the user and accepts the input of an answer.

[0007] "Data collection methods" refer to the means of recording answer data and past performance information provided by users, and collecting the data necessary for analysis.

[0008] "Analysis means" refers to methods for processing collected data and performing calculations and analyses to identify the user's strengths and weaknesses.

[0009] A "problem generation method" is a means of creating or selecting the most suitable problem for the user based on information obtained by an analysis method.

[0010] A "problem presentation method" is a means of notifying users of generated or selected problems, enabling them to engage in continuous learning. [Brief explanation of the drawing]

[0011] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled 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.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is a system for providing an individually optimized learning experience, generating an optimal set of problems according to the user's learning needs. The system includes a server, a terminal, and user interaction to support the user's learning activities.

[0033] The server is responsible for analyzing answer data and past performance information received from the terminal. This allows the server to identify areas where the user struggles. For example, if a user has a high error rate on differential calculus problems in mathematics, the server will identify this as a warning.

[0034] The terminal provides an interface between the server and the user, presenting problems to the user and receiving answers. When a user answers a problem, the answer data is sent to the server via the terminal. The displayed problems are dynamically updated based on the user's weak areas, past performance, and even the question trends of their target school.

[0035] Users solve problems presented on their devices and receive immediate feedback. The feedback sent from the server includes information about whether the answer is correct or incorrect, as well as explanations and related materials if the answer is wrong. For example, if a user gives an incorrect answer, the server sends a detailed explanation, which is then displayed on the device.

[0036] As an example of this system, suppose a user identifies English reading comprehension questions, which they frequently get wrong, as a weak point in their preparation for the entrance exam of a university they wish to attend. In this case, the server generates similar reading comprehension questions and provides them to the user via their terminal. The user answers these questions and receives further feedback based on their results, allowing them to efficiently overcome their weaknesses in preparation for the actual entrance exam.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The user receives the problem on their device. The device receives the problem sent from the server and presents it visually to the user via a display interface.

[0040] Step 2:

[0041] The user answers the question. Based on the presented question, the user enters the appropriate answer. The answer can be entered in the form of multiple-choice or written response.

[0042] Step 3:

[0043] The terminal collects user responses. It records the response data entered by the user and sends this data to the server in real time.

[0044] Step 4:

[0045] The server receives and analyzes the answer data. Based on the received answer data, it determines whether the questions are correct or incorrect, and updates the user's weaknesses and strengths by comparing them with past performance data.

[0046] Step 5:

[0047] The server selects the optimal problem to solve next. Based on the analysis results, it selects the most suitable problem to strengthen the user's weaknesses and leverage their strengths, while also taking into account the latest exam trends.

[0048] Step 6:

[0049] The server sends the newly selected problem to the terminal. To allow the user to continue learning, it immediately sends the next problem.

[0050] Step 7:

[0051] The terminal presents a new problem to the user. It receives the problem sent from the server and prepares to display it to the user.

[0052] Step 8:

[0053] The server generates feedback on the user's answers. In addition to indicating whether the answer is correct or incorrect and explaining the reasons for incorrect answers, it generates supplementary information to aid understanding and sends it to the terminal.

[0054] Step 9:

[0055] The device displays feedback to the user. It visually presents the feedback received from the server to the user, providing guidance for further learning.

[0056] (Example 1)

[0057] 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."

[0058] In today's educational environment, there is a need to effectively provide optimal learning tasks tailored to each learner's areas of weakness and specific goals. However, general educational systems often struggle to fully meet the individual needs of learners, resulting in the provision of uniform tasks. This hinders learners from further developing their strengths and efficiently overcoming their weaknesses.

[0059] 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.

[0060] In this invention, the server includes an interface means for displaying tasks to users and accepting answers, an information collection means for collecting user answer information and past performance history, and a data analysis means for analyzing the collected information to identify the user's strengths and weaknesses. This makes it possible to provide tasks optimized for individual learners and support efficient learning.

[0061] An "interface mechanism" is a system for displaying a problem to a user and receiving their solution.

[0062] "Information gathering means" refers to a mechanism for collecting users' answer information and past performance history.

[0063] A "data analysis method" is a system that identifies a user's strengths and weaknesses based on the information collected.

[0064] A "task generation mechanism" is a system for generating tasks suitable for the user based on analysis results.

[0065] A "problem presentation method" is a mechanism for providing generated problems to users.

[0066] An "evaluation tool" is a mechanism for evaluating users' answers and providing feedback based on the evaluation results.

[0067] This invention is a system that provides learners with an individually optimized learning experience, and includes the interaction of a server, a terminal, and a user.

[0068] The server collects user answer information and past performance history for central data management and analysis. The server stores this information in a database and performs analysis using a generative AI model. Specifically, the generative AI model executes prompts such as "Analyze the latest answer data and identify areas of weakness," thereby identifying the user's strengths and weaknesses.

[0069] The terminal provides a user interface between the user and the server. The terminal displays tasks received from the server to the user, and when the user answers a task, it sends the answer data to the server. The terminal also displays feedback from the server, conveying evaluation results and suggestions for improvement to the user.

[0070] Users progress through their learning via their devices. For example, if a user identifies areas where they frequently make mistakes while preparing for a specific university entrance exam, the server generates similar assignments and provides them through the device. Through this process, users can efficiently progress through their learning and overcome their weak areas.

[0071] An example of a prompt message would be an instruction such as, "Generate English reading comprehension questions based on the user's performance data." This allows the server to generate the most suitable tasks based on the analysis results, thereby individually optimizing the user's learning experience.

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

[0073] Step 1:

[0074] The server receives user response information sent from the terminal and stores it in the database. This input includes the user's response content, timestamp, and user identification information. The server organizes this information in preparation for future analysis.

[0075] Step 2:

[0076] The server uses accumulated answer data and past performance history to perform data analysis using a generative AI model. As input, it analyzes the user's performance data and answer history based on the prompt "Analyze the latest answer data and identify areas of weakness," and generates a report that clearly identifies the user's strengths and weaknesses.

[0077] Step 3:

[0078] The server generates tasks tailored to the user's areas of weakness based on the data analysis results. This task generation uses the prompt "Create tasks that focus on the identified areas of weakness." The generated tasks are tailored to the user's needs and include specific content.

[0079] Step 4:

[0080] The terminal receives tasks generated from the server and provides an interface to display them to the user. The terminal acts as a platform for the user to solve the tasks and sends the user's answers back to the server. The inputs here are the tasks from the server and the user's answers, and the output is the answer results sent back to the server.

[0081] Step 5:

[0082] The server immediately evaluates the answers received from the user and determines whether they are correct or incorrect. Based on the evaluation results, feedback is generated, and a prompt is used asking, "Please provide the evaluation results for your answer and suggestions for improvement." The generated feedback is then provided to the user via the terminal.

[0083] (Application Example 1)

[0084] 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."

[0085] Traditional systems were limited to users' past performance data, making it difficult to personalize learning experiences that took into account users' interests and browsing history. As a result, there was a problem in that the system could not adequately suggest learning courses and problem sets that were truly necessary for the user, thus hindering learning efficiency.

[0086] 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.

[0087] In this invention, the server includes a presentation means for displaying problems to the user and accepting answers, an information collection means for collecting the user's answer information and past performance information, an analysis means for analyzing the collected information to identify the user's strengths and weaknesses, and a customization generation means. This makes it possible to provide individually optimized learning courses and materials based on the user's past purchase and browsing history.

[0088] "A means of displaying problems and accepting answers" refers to a device or software that displays learning problems on a screen for the user and provides an interface for inputting answers.

[0089] "Information gathering means" refers to a device or software for transmitting and storing users' answer information and past performance information on a server.

[0090] "Analysis tools" refer to devices or software that analyze collected information and execute algorithms to identify the user's strengths and weaknesses.

[0091] "Problem generation means" refers to a device or software for creating or selecting optimal learning problems for the user based on the results obtained by the analysis means.

[0092] "Problem presentation means" refers to a device or software for providing users with generated or selected learning problems.

[0093] A "customization generation method" refers to a device or software that individually optimizes and generates learning courses and materials based on a user's past purchase and browsing history.

[0094] This system provides users with a personalized learning experience. First, the server plays a central role in collecting answer data and past performance information transmitted from the user's device. This information is efficiently stored using data collection tools. The server then analyzes this collected information using Python and other data analysis tools.

[0095] The server then uses analytical tools to identify the user's strengths and weaknesses. This is done using data analysis algorithms based on each user's unique patterns. For example, if a user has a high error rate in a particular subject or topic, that area is identified as a weak point.

[0096] Based on this identified information, the problem generation system operates to generate or select a problem set optimized for the user. The generated problems are then displayed on the terminal via the problem presentation system, allowing the user to answer them. Once the user enters their answer, it is sent back to the server, and feedback is immediately provided to the user.

[0097] Furthermore, the system includes a customization generation mechanism that utilizes the user's purchase and browsing history to individually optimize learning courses and materials. This allows users to easily create a learning plan that suits them.

[0098] As a concrete example, for a user who frequently makes mistakes on English reading comprehension questions, the server automatically presents more questions in that area to help them overcome their difficulties at their own pace. Generative AI models may also be used in this process.

[0099] An example of a prompt text for a generative AI model is, "Recommend an appropriate learning course based on the user's past purchase history."

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

[0101] Step 1:

[0102] The server receives user answer information and past performance data from the terminal. The input at this stage is data such as the user's answer choices and scores, and the output is storing this data in a database on the server. Verification is performed during this information collection process to maintain data consistency.

[0103] Step 2:

[0104] The server analyzes the collected data to identify the user's strengths and weaknesses. The input is the answer information stored in step 1. The server uses a data analysis algorithm to identify strengths and weaknesses. This output is obtained as the analysis result, and areas where the user shows a high error rate are recorded as weaknesses.

[0105] Step 3:

[0106] The server uses a problem generation mechanism based on the analysis results to create learning problems optimized for the user. The input is the analysis results obtained in step 2. In this step, a set of problems corresponding to the user's weak areas is selected or a new set is generated, and the results are output. The set of problems is selected comprehensively, taking prior knowledge into consideration.

[0107] Step 4:

[0108] The terminal presents the user with generated or selected learning problems. The input is a set of problems received from the server, and the output is the display of those problems on the user's screen. The user can then review the problems and provide answers, and the answer data is sent back to the server via the terminal.

[0109] Step 5:

[0110] The server receives the answer and immediately generates and sends feedback to the user. The input at this stage is the question and the user's answer. The server performs a correct / incorrect analysis and immediately sends feedback to the user, including explanations and suggestions for improvement. The output is the detailed feedback information provided to the user.

[0111] Step 6:

[0112] The server uses a customization generation method to personalize learning courses based on the user's past purchase and browsing history. The input is the user's purchase and browsing history. Here, the aforementioned generative AI model is utilized to optimize the learning content. This output is then provided to the user as a personalized learning plan.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] This invention is a system designed to provide an individually optimized learning experience, and has the function of recognizing the user's emotional state and adjusting the learning process accordingly. This system works in conjunction with a server, terminal, and emotion engine to provide the user with the optimal learning experience.

[0115] The server analyzes the user's answer data and past performance information to identify the user's strengths and weaknesses. Based on this information, the server uses a question generation system to create or select the most suitable questions for the user, and sends the questions to the terminal while taking into account the latest exam trends.

[0116] The terminal displays problems received from the server to the user, receives the user's answers, and sends them back to the server. Furthermore, it incorporates an emotion engine that analyzes the user's emotional state. This engine uses cameras, microphones, or sensors to monitor and analyze the user's facial expressions, voice, and behavior.

[0117] Users answer questions displayed on their devices, and their emotions are recorded through the device by an emotion engine during this process. For example, if stress is detected, that information is sent to a server, and feedback is generated to appropriately adjust the difficulty level of the questions.

[0118] As a concrete example, suppose a user is working on a math problem, and the emotion engine detects anxiety or fatigue from the user's facial expressions and voice. In this case, the server takes this emotional information into account and adjusts the next problem presented, selecting a slightly easier problem or providing a more detailed explanation, in order to maintain the user's motivation to learn. This allows the user to continue learning in a comfortable environment and improve their academic ability efficiently.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The user works on learning problems presented on the device. The device displays the problems received from the server on the screen and provides input fields for the user to answer the problems.

[0122] Step 2:

[0123] The emotion engine monitors the user's emotional state. It analyzes the user's facial expressions, voice tone, and body movements in real time via the device's built-in camera and microphone, and transmits emotional information to the emotion engine.

[0124] Step 3:

[0125] The user answers the question and enters the answer into the terminal. The terminal immediately sends this data to the server, and the process proceeds to the next analysis stage.

[0126] Step 4:

[0127] The server analyzes the answer data and sentiment information. It determines whether the received answers are correct or incorrect and uses the sentiment information to understand the user's mental state. This data is recorded in the user's learning profile.

[0128] Step 5:

[0129] The server selects the next problem to present based on the analysis results. It adjusts the difficulty level of the problems according to the user's areas of difficulty and emotional state, generating or selecting appropriate problems.

[0130] Step 6:

[0131] The server sends the generated problems and learning feedback to the device. The feedback may include detailed explanations of the solutions and motivational messages.

[0132] Step 7:

[0133] The device displays newly received problems and feedback to the user. Based on the feedback, the user self-assessss their learning and prepares to continue learning.

[0134] Step 8:

[0135] The user then solves newly presented problems again. This perpetuates the learning loop, allowing for knowledge improvement and self-improvement in each cycle.

[0136] (Example 2)

[0137] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0138] In today's educational environment, individualized learning is necessary to accommodate the diverse learning abilities and styles of each user. However, existing systems have limitations in providing problems tailored to users' strengths and weaknesses, and they cannot quickly respond to changes in motivation and emotions. Furthermore, real-time adjustment of learning content based on emotional states is required, but achieving this has been difficult.

[0139] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0140] In this invention, the server includes a collection means for collecting user answer data and past performance information, an analysis means for analyzing the collected data to identify the user's strengths and weaknesses, and an emotion analysis means for monitoring and analyzing the user's emotional state. This enables the provision of optimal problems tailored to the user's individual learning needs and the adjustment of the learning experience based on real-time emotion data.

[0141] "Display means" refers to a device or function that visually presents a problem to the user and accepts the user's answer as input.

[0142] "Collection means" refers to a device or function that collects user answer data and past performance information.

[0143] "Analysis means" refers to a device or function that identifies a user's strengths and weaknesses based on collected data.

[0144] "Problem generation means" refers to a device or function that generates or selects the most suitable problem for the user based on the analysis results from the analysis means.

[0145] "Emotional analysis means" refers to a device or function that monitors a user's emotional state and analyzes that information.

[0146] "Adjustment means" refers to a device or function that adjusts the difficulty level and presentation method of generated problems based on user sentiment data.

[0147] "Generation means" refers to a device or function that utilizes a generation AI model to provide information to problem generation and adjustment means.

[0148] This invention provides a learning system that offers a learning experience individually optimized for each user. The implementation of this invention primarily involves a server, terminals, and a system with sentiment analysis capabilities.

[0149] The server has the functionality to lead data analysis. It collects user answer data and past performance information, and uses this data to analyze strengths and weaknesses. This analysis utilizes a database management system and machine learning algorithms. In addition, a generative AI model generates optimal problems tailored to the user's needs and sends them to the terminal.

[0150] The terminal serves to present problems to the user. Equipped with a display and input device, it displays problems received from the server and accepts the user's answers. The terminal also features sentiment analysis capabilities, collecting and analyzing user sentiment data through its camera, microphone, and sensors, and transmitting it to the server.

[0151] As users answer questions presented via their devices, they exhibit natural emotional changes. If stress or anxiety is detected, the user's emotional state is reflected on the server as data to adjust the difficulty level and presentation method of the questions.

[0152] For example, if a user is working on a math problem and the device's emotion analysis function detects stress from the user's facial expressions and voice, the server will decide to reduce the difficulty of the next problem or provide more detailed explanations. This process allows the user to effectively maintain their motivation to learn and enjoy a comfortable learning environment.

[0153] An example of a prompt for a generative AI model is, "If user anxiety is detected, how should the next problem presented be adjusted?" This prompt is used to enable the model to provide appropriate feedback based on sentiment data.

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

[0155] Step 1:

[0156] The server collects basic user information, past performance data, and current answer data from the terminal. User data provided by the terminal is used as input and stored in the database. This allows the server to create individual datasets for each user.

[0157] Step 2:

[0158] The server analyzes the collected data. Using machine learning algorithms, it identifies the user's strengths and weaknesses from the input data. The output of this analysis is a personalized learning report for each user. This report is then used to generate problems.

[0159] Step 3:

[0160] The server utilizes a generative AI model to generate or select optimal problems based on the user's strengths and weaknesses. A specialized learning report is used as input. The output of the problem generation process is a personalized learning problem, which is then sent to the user's terminal.

[0161] Step 4:

[0162] The terminal displays the received questions to the user. The input here is a learning question sent from the server. The user answers the question through the terminal, and the answer is recorded by the terminal and sent to the server.

[0163] Step 5:

[0164] The device monitors the user's emotional state using its built-in emotion analysis function. It uses audio and image data acquired by the device's camera and microphone as input. The analyzed emotion data is used to determine whether the user is experiencing stress or anxiety, and is then sent to the server.

[0165] Step 6:

[0166] The server receives sentiment analysis data and uses it to adjust the user's learning process. Sentimental state data and answer results are used as input. The server generates output that adjusts the difficulty of the next question or changes the presentation method, and sends this output to the terminal.

[0167] (Application Example 2)

[0168] 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".

[0169] Traditional virtual stores failed to consider the emotional state of users when making product recommendations, instead offering uniform information. Therefore, it was difficult to provide a personalized experience that reflected each user's unique purchasing intentions and interests. A system was needed to solve this problem and increase user satisfaction.

[0170] 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.

[0171] In this invention, the server includes a display device that displays information to the user and accepts responses, a data collection device that collects user response data and past performance information, and an emotion analysis device that recognizes the user's emotional state. This makes it possible to provide personalized information that takes the user's emotional state into consideration in real time.

[0172] A "user" refers to an individual who utilizes a system, receives information through a display device, and responds.

[0173] "Information" refers to data, including content and choices presented to the user.

[0174] A "display device" is a device used to present information to a user visually or audibly.

[0175] "Response data" refers to data generated as a result of selections and interactions that a user makes with a display device.

[0176] "Performance information" refers to information about past user behavior patterns and the results achieved.

[0177] "Collection device" refers to a device or software used to acquire response data and result information.

[0178] An "analysis device" is a device used to analyze collected data and understand the characteristics of the user.

[0179] "Areas of expertise" refers to the fields in which users are recognized as excelling, as identified through analysis.

[0180] A "weakness" is an area identified through analysis as a result of which users perceive as a challenge.

[0181] An "information generation device" is a device that creates or selects optimized information for the user based on analysis results.

[0182] A "presentation device" refers to a device used to present generated information to a user.

[0183] "Emotional state" refers to the user's current psychological or emotional state.

[0184] An "emotion analysis device" is a device that recognizes and analyzes a user's emotional state.

[0185] The system used to realize this application provides users with an interactive experience in a virtual store. The server uses a display device and an emotion analysis device that recognizes the user's emotional state via smart glasses worn by the user. This allows the system to adjust the suggested content in real time according to the user's emotional state.

[0186] The server uses a Python program that leverages OpenCV and TENSORFLOW® to analyze facial expression data acquired by the smart glasses' camera. This allows for real-time recognition of the user's emotional state. Furthermore, voice input is converted to text using Google® Cloud Speech-to-Text API and other tools, and sentiment analysis is performed.

[0187] For example, if a user visits a virtual store and smiles when viewing a specific product, it's possible to provide them with product recommendations or information about exclusive campaigns. This stimulates the user's desire to purchase and creates a personalized shopping experience.

[0188] An example of a prompt might be: "Based on the emotional state of the product the user has shown interest in, provide suggestions and explanations here. Generate example suggestions for when the user is smiling, and also recommend related products." This prompt allows the generative AI model to generate information optimized for the user, enriching the user experience.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server receives image data from the smart glasses and preprocesses it using OpenCV. The input is raw image data from the smart glasses, and the output is image data with the face portion extracted. This image data is then used for subsequent emotion analysis.

[0192] Step 2:

[0193] The server inputs the extracted facial images into an emotion analysis model using TensorFlow to estimate the user's emotional state. In this step, the input is facial image data, and the output is an emotion label such as "interested," "satisfied," or "anxious."

[0194] Step 3:

[0195] The server converts the audio received from the smart glasses into text data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes it possible to analyze the content of the user's speech.

[0196] Step 4:

[0197] The server combines the obtained sentiment labels and text data to perform analysis to determine what interested the user. The input is sentiment labels and text data, and the output is information about the user's interests.

[0198] Step 5:

[0199] The terminal displays information on its screen based on the user's emotional state and interests, which are transmitted from the server. The input is optimized suggestion information from the server, and the output is the information the user receives visually.

[0200] Step 6:

[0201] The user reviews the information displayed on the screen and interacts with products and services that interest them further. The results of this interaction are fed back into all steps, and the system updates the information accordingly.

[0202] 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.

[0203] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0204] 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.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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".

[0218] This invention is a system for providing an individually optimized learning experience, generating an optimal set of problems according to the user's learning needs. The system includes a server, a terminal, and user interaction to support the user's learning activities.

[0219] The server is responsible for analyzing answer data and past performance information received from the terminal. This allows the server to identify areas where the user struggles. For example, if a user has a high error rate on differential calculus problems in mathematics, the server will identify this as a warning.

[0220] The terminal provides an interface between the server and the user, presenting problems to the user and receiving answers. When a user answers a problem, the answer data is sent to the server via the terminal. The displayed problems are dynamically updated based on the user's weak areas, past performance, and even the question trends of their target school.

[0221] Users solve problems presented on their devices and receive immediate feedback. The feedback sent from the server includes information about whether the answer is correct or incorrect, as well as explanations and related materials if the answer is wrong. For example, if a user gives an incorrect answer, the server sends a detailed explanation, which is then displayed on the device.

[0222] As an example of this system, suppose a user identifies English reading comprehension questions, which they frequently get wrong, as a weak point in their preparation for the entrance exam of a university they wish to attend. In this case, the server generates similar reading comprehension questions and provides them to the user via their terminal. The user answers these questions and receives further feedback based on their results, allowing them to efficiently overcome their weaknesses in preparation for the actual entrance exam.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The user receives the problem on their device. The device receives the problem sent from the server and presents it visually to the user via a display interface.

[0226] Step 2:

[0227] The user answers the question. Based on the presented question, the user enters the appropriate answer. The answer can be entered in the form of multiple-choice or written response.

[0228] Step 3:

[0229] The terminal collects user responses. It records the response data entered by the user and sends this data to the server in real time.

[0230] Step 4:

[0231] The server receives and analyzes the answer data. Based on the received answer data, it determines whether the questions are correct or incorrect, and updates the user's weaknesses and strengths by comparing them with past performance data.

[0232] Step 5:

[0233] The server selects the optimal problem to solve next. Based on the analysis results, it selects the most suitable problem to strengthen the user's weaknesses and leverage their strengths, while also taking into account the latest exam trends.

[0234] Step 6:

[0235] The server sends the newly selected problem to the terminal. To allow the user to continue learning, it immediately sends the next problem.

[0236] Step 7:

[0237] The terminal presents a new problem to the user. It receives the problem sent from the server and prepares to display it to the user.

[0238] Step 8:

[0239] The server generates feedback on the user's answers. In addition to indicating whether the answer is correct or incorrect and explaining the reasons for incorrect answers, it generates supplementary information to aid understanding and sends it to the terminal.

[0240] Step 9:

[0241] The device displays feedback to the user. It visually presents the feedback received from the server to the user, providing guidance for further learning.

[0242] (Example 1)

[0243] 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".

[0244] In today's educational environment, there is a need to effectively provide optimal learning tasks tailored to each learner's areas of weakness and specific goals. However, general educational systems often struggle to fully meet the individual needs of learners, resulting in the provision of uniform tasks. This hinders learners from further developing their strengths and efficiently overcoming their weaknesses.

[0245] 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.

[0246] In this invention, the server includes an interface means for displaying tasks to users and accepting answers, an information collection means for collecting user answer information and past performance history, and a data analysis means for analyzing the collected information to identify the user's strengths and weaknesses. This makes it possible to provide tasks optimized for individual learners and support efficient learning.

[0247] An "interface mechanism" is a system for displaying a problem to a user and receiving their solution.

[0248] "Information gathering means" refers to a mechanism for collecting users' answer information and past performance history.

[0249] A "data analysis method" is a system that identifies a user's strengths and weaknesses based on the information collected.

[0250] A "task generation mechanism" is a system for generating tasks suitable for the user based on analysis results.

[0251] A "problem presentation method" is a mechanism for providing generated problems to users.

[0252] An "evaluation tool" is a mechanism for evaluating users' answers and providing feedback based on the evaluation results.

[0253] This invention is a system that provides learners with an individually optimized learning experience, and includes the interaction of a server, a terminal, and a user.

[0254] The server collects user answer information and past performance history for central data management and analysis. The server stores this information in a database and performs analysis using a generative AI model. Specifically, the generative AI model executes prompts such as "Analyze the latest answer data and identify areas of weakness," thereby identifying the user's strengths and weaknesses.

[0255] The terminal provides a user interface between the user and the server. The terminal displays tasks received from the server to the user, and when the user answers a task, it sends the answer data to the server. The terminal also displays feedback from the server, conveying evaluation results and suggestions for improvement to the user.

[0256] Users progress through their learning via their devices. For example, if a user identifies areas where they frequently make mistakes while preparing for a specific university entrance exam, the server generates similar assignments and provides them through the device. Through this process, users can efficiently progress through their learning and overcome their weak areas.

[0257] An example of a prompt message would be an instruction such as, "Generate English reading comprehension questions based on the user's performance data." This allows the server to generate the most suitable tasks based on the analysis results, thereby individually optimizing the user's learning experience.

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The server receives user response information sent from the terminal and stores it in the database. This input includes the user's response content, timestamp, and user identification information. The server organizes this information in preparation for future analysis.

[0261] Step 2:

[0262] The server uses accumulated answer data and past performance history to perform data analysis using a generative AI model. As input, it analyzes the user's performance data and answer history based on the prompt "Analyze the latest answer data and identify areas of weakness," and generates a report that clearly identifies the user's strengths and weaknesses.

[0263] Step 3:

[0264] The server generates tasks tailored to the user's areas of weakness based on the data analysis results. This task generation uses the prompt "Create tasks that focus on the identified areas of weakness." The generated tasks are tailored to the user's needs and include specific content.

[0265] Step 4:

[0266] The terminal receives tasks generated from the server and provides an interface to display them to the user. The terminal acts as a platform for the user to solve the tasks and sends the user's answers back to the server. The inputs here are the tasks from the server and the user's answers, and the output is the answer results sent back to the server.

[0267] Step 5:

[0268] The server immediately evaluates the answers received from the user and determines whether they are correct or incorrect. Based on the evaluation results, feedback is generated, and a prompt is used asking, "Please provide the evaluation results for your answer and suggestions for improvement." The generated feedback is then provided to the user via the terminal.

[0269] (Application Example 1)

[0270] 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."

[0271] Traditional systems were limited to users' past performance data, making it difficult to personalize learning experiences that took into account users' interests and browsing history. As a result, there was a problem in that the system could not adequately suggest learning courses and problem sets that were truly necessary for the user, thus hindering learning efficiency.

[0272] 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.

[0273] In this invention, the server includes a presentation means for displaying problems to the user and accepting answers, an information collection means for collecting the user's answer information and past performance information, an analysis means for analyzing the collected information to identify the user's strengths and weaknesses, and a customization generation means. This makes it possible to provide individually optimized learning courses and materials based on the user's past purchase and browsing history.

[0274] "A means of displaying problems and accepting answers" refers to a device or software that displays learning problems on a screen for the user and provides an interface for inputting answers.

[0275] "Information gathering means" refers to a device or software for transmitting and storing users' answer information and past performance information on a server.

[0276] "Analysis tools" refer to devices or software that analyze collected information and execute algorithms to identify the user's strengths and weaknesses.

[0277] "Problem generation means" refers to a device or software for creating or selecting optimal learning problems for the user based on the results obtained by the analysis means.

[0278] "Problem presentation means" refers to a device or software for providing users with generated or selected learning problems.

[0279] A "customization generation method" refers to a device or software that individually optimizes and generates learning courses and materials based on a user's past purchase and browsing history.

[0280] This system provides users with a personalized learning experience. First, the server plays a central role in collecting answer data and past performance information transmitted from the user's device. This information is efficiently stored using data collection tools. The server then analyzes this collected information using Python and other data analysis tools.

[0281] The server then uses analytical tools to identify the user's strengths and weaknesses. This is done using data analysis algorithms based on each user's unique patterns. For example, if a user has a high error rate in a particular subject or topic, that area is identified as a weak point.

[0282] Based on this identified information, the problem generation system operates to generate or select a problem set optimized for the user. The generated problems are then displayed on the terminal via the problem presentation system, allowing the user to answer them. Once the user enters their answer, it is sent back to the server, and feedback is immediately provided to the user.

[0283] In addition, the system has customization generation means, which utilizes the user's purchase history and browsing history to individually optimize learning courses and teaching materials. As a result, the user can easily construct a learning plan suitable for themselves.

[0284] As a specific example, for a user who frequently answers long English reading comprehension questions incorrectly, the server automatically presents more questions in that area and supports them to overcome them at their own pace. In this process, a generative AI model may also be used.

[0285] As an example of the prompt text of the generative AI model, there is the text "Please recommend an appropriate learning course based on the user's past purchase history."

[0286] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0287] Step 1:

[0288] The server receives the user's answer information and past performance information from the terminal. The input at this stage is data such as the user's answer options and scores, and the output is to store this data in the database within the server. In the process of collecting this information, verification is performed to maintain data consistency.

[0289] Step 2:

[0290] The server analyzes the collected data to identify the user's strong areas and weak areas. The input is the answer information stored in Step 1. The server uses a data analysis algorithm to identify the strong and weak areas. This output is obtained as the analysis result, and the areas where the user shows a high incorrect answer rate are recorded as weaknesses.

[0291] Step 3:

[0292] The server uses a problem generation mechanism based on the analysis results to create learning problems optimized for the user. The input is the analysis results obtained in step 2. In this step, a set of problems corresponding to the user's weak areas is selected or a new set is generated, and the results are output. The set of problems is selected comprehensively, taking prior knowledge into consideration.

[0293] Step 4:

[0294] The terminal presents the user with generated or selected learning problems. The input is a set of problems received from the server, and the output is the display of those problems on the user's screen. The user can then review the problems and provide answers, and the answer data is sent back to the server via the terminal.

[0295] Step 5:

[0296] The server receives the answer and immediately generates and sends feedback to the user. The input at this stage is the question and the user's answer. The server performs a correct / incorrect analysis and immediately sends feedback to the user, including explanations and suggestions for improvement. The output is the detailed feedback information provided to the user.

[0297] Step 6:

[0298] The server uses a customization generation method to personalize learning courses based on the user's past purchase and browsing history. The input is the user's purchase and browsing history. Here, the aforementioned generative AI model is utilized to optimize the learning content. This output is then provided to the user as a personalized learning plan.

[0299] 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.

[0300] This invention is a system designed to provide an individually optimized learning experience, and has the function of recognizing the user's emotional state and adjusting the learning process accordingly. This system works in conjunction with a server, terminal, and emotion engine to provide the user with the optimal learning experience.

[0301] The server analyzes the user's answer data and past performance information to identify the user's strengths and weaknesses. Based on this information, the server uses a question generation system to create or select the most suitable questions for the user, and sends the questions to the terminal while taking into account the latest exam trends.

[0302] The terminal displays problems received from the server to the user, receives the user's answers, and sends them back to the server. Furthermore, it incorporates an emotion engine that analyzes the user's emotional state. This engine uses cameras, microphones, or sensors to monitor and analyze the user's facial expressions, voice, and behavior.

[0303] Users answer questions displayed on their devices, and their emotions are recorded through the device by an emotion engine during this process. For example, if stress is detected, that information is sent to a server, and feedback is generated to appropriately adjust the difficulty level of the questions.

[0304] As a concrete example, suppose a user is working on a math problem, and the emotion engine detects anxiety or fatigue from the user's facial expressions and voice. In this case, the server takes this emotional information into account and adjusts the next problem presented, selecting a slightly easier problem or providing a more detailed explanation, in order to maintain the user's motivation to learn. This allows the user to continue learning in a comfortable environment and improve their academic ability efficiently.

[0305] The following describes the processing flow.

[0306] Step 1:

[0307] The user works on the learning problems presented on the terminal. The terminal displays the problems received from the server on the screen and provides an input field for the user to answer the problems.

[0308] Step 2:

[0309] The emotion engine monitors the user's emotional state. Through the camera and microphone built into the terminal, the user's expressions, voice tones, and body movements are analyzed in real time, and the emotion information is sent to the emotion engine.

[0310] Step 3:

[0311] The user answers the problem and inputs the answer into the terminal. The terminal immediately sends this data to the server and proceeds to the next analysis stage.

[0312] Step 4:

[0313] The server analyzes the answer data and emotion information. It determines the correctness of the received answer and grasps the user's mental state by referring to the emotion information. This data is recorded in the user's learning profile.

[0314] Step 5:

[0315] The server selects the next problem to be presented based on the analysis results. It adjusts the difficulty level of the problem according to the user's weak areas and emotional state, and generates or selects an appropriate problem.

[0316] Step 6:

[0317] The server sends the generated problem and learning feedback to the terminal. The feedback may include a detailed explanation of the answer and a message to arouse motivation.

[0318] Step 7:

[0319] The device displays newly received problems and feedback to the user. Based on the feedback, the user self-assessss their learning and prepares to continue learning.

[0320] Step 8:

[0321] The user then solves newly presented problems again. This perpetuates the learning loop, allowing for knowledge improvement and self-improvement in each cycle.

[0322] (Example 2)

[0323] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0324] In today's educational environment, individualized learning is necessary to accommodate the diverse learning abilities and styles of each user. However, existing systems have limitations in providing problems tailored to users' strengths and weaknesses, and they cannot quickly respond to changes in motivation and emotions. Furthermore, real-time adjustment of learning content based on emotional states is required, but achieving this has been difficult.

[0325] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0326] In this invention, the server includes a collection means for collecting user answer data and past performance information, an analysis means for analyzing the collected data to identify the user's strengths and weaknesses, and an emotion analysis means for monitoring and analyzing the user's emotional state. This enables the provision of optimal problems tailored to the user's individual learning needs and the adjustment of the learning experience based on real-time emotion data.

[0327] "Display means" refers to a device or function that visually presents a problem to the user and accepts the user's answer as input.

[0328] "Collection means" refers to a device or function that collects user answer data and past performance information.

[0329] "Analysis means" refers to a device or function that identifies a user's strengths and weaknesses based on collected data.

[0330] "Problem generation means" refers to a device or function that generates or selects the most suitable problem for the user based on the analysis results from the analysis means.

[0331] "Emotional analysis means" refers to a device or function that monitors a user's emotional state and analyzes that information.

[0332] "Adjustment means" refers to a device or function that adjusts the difficulty level and presentation method of generated problems based on user sentiment data.

[0333] "Generation means" refers to a device or function that utilizes a generation AI model to provide information to problem generation and adjustment means.

[0334] This invention provides a learning system that offers a learning experience individually optimized for each user. The implementation of this invention primarily involves a server, terminals, and a system with sentiment analysis capabilities.

[0335] The server has the functionality to lead data analysis. It collects user answer data and past performance information, and uses this data to analyze strengths and weaknesses. This analysis utilizes a database management system and machine learning algorithms. In addition, a generative AI model generates optimal problems tailored to the user's needs and sends them to the terminal.

[0336] The terminal serves to present problems to the user. Equipped with a display and input device, it displays problems received from the server and accepts the user's answers. The terminal also features sentiment analysis capabilities, collecting and analyzing user sentiment data through its camera, microphone, and sensors, and transmitting it to the server.

[0337] As users answer questions presented via their devices, they exhibit natural emotional changes. If stress or anxiety is detected, the user's emotional state is reflected on the server as data to adjust the difficulty level and presentation method of the questions.

[0338] For example, if a user is working on a math problem and the device's emotion analysis function detects stress from the user's facial expressions and voice, the server will decide to reduce the difficulty of the next problem or provide more detailed explanations. This process allows the user to effectively maintain their motivation to learn and enjoy a comfortable learning environment.

[0339] An example of a prompt for a generative AI model is, "If user anxiety is detected, how should the next problem presented be adjusted?" This prompt is used to enable the model to provide appropriate feedback based on sentiment data.

[0340] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0341] Step 1:

[0342] The server collects basic user information, past performance data, and current answer data from the terminal. User data provided by the terminal is used as input and stored in the database. This allows the server to create individual datasets for each user.

[0343] Step 2:

[0344] The server analyzes the collected data. Using machine learning algorithms, it identifies the user's strengths and weaknesses from the input data. The output of this analysis is a personalized learning report for each user. This report is then used to generate problems.

[0345] Step 3:

[0346] The server utilizes a generative AI model to generate or select optimal problems based on the user's strengths and weaknesses. A specialized learning report is used as input. The output of the problem generation process is a personalized learning problem, which is then sent to the user's terminal.

[0347] Step 4:

[0348] The terminal displays the received questions to the user. The input here is a learning question sent from the server. The user answers the question through the terminal, and the answer is recorded by the terminal and sent to the server.

[0349] Step 5:

[0350] The device monitors the user's emotional state using its built-in emotion analysis function. It uses audio and image data acquired by the device's camera and microphone as input. The analyzed emotion data is used to determine whether the user is experiencing stress or anxiety, and is then sent to the server.

[0351] Step 6:

[0352] The server receives sentiment analysis data and uses it to adjust the user's learning process. Sentimental state data and answer results are used as input. The server generates output that adjusts the difficulty of the next question or changes the presentation method, and sends this output to the terminal.

[0353] (Application Example 2)

[0354] 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."

[0355] Traditional virtual stores failed to consider the emotional state of users when making product recommendations, instead offering uniform information. Therefore, it was difficult to provide a personalized experience that reflected each user's unique purchasing intentions and interests. A system was needed to solve this problem and increase user satisfaction.

[0356] 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.

[0357] In this invention, the server includes a display device that displays information to the user and accepts responses, a data collection device that collects user response data and past performance information, and an emotion analysis device that recognizes the user's emotional state. This makes it possible to provide personalized information that takes the user's emotional state into consideration in real time.

[0358] A "user" refers to an individual who utilizes a system, receives information through a display device, and responds.

[0359] "Information" refers to data, including content and choices presented to the user.

[0360] A "display device" is a device used to present information to a user visually or audibly.

[0361] "Response data" refers to data generated as a result of selections and interactions that a user makes with a display device.

[0362] "Performance information" refers to information about past user behavior patterns and the results achieved.

[0363] "Collection device" refers to a device or software used to acquire response data and result information.

[0364] An "analysis device" is a device used to analyze collected data and understand the characteristics of the user.

[0365] "Areas of expertise" refers to the fields in which users are recognized as excelling, as identified through analysis.

[0366] A "weakness" is an area identified through analysis as a result of which users perceive as a challenge.

[0367] An "information generation device" is a device that creates or selects optimized information for the user based on analysis results.

[0368] A "presentation device" refers to a device used to present generated information to a user.

[0369] "Emotional state" refers to the user's current psychological or emotional state.

[0370] An "emotion analysis device" is a device that recognizes and analyzes a user's emotional state.

[0371] The system used to realize this application provides users with an interactive experience in a virtual store. The server uses a display device and an emotion analysis device that recognizes the user's emotional state via smart glasses worn by the user. This allows the system to adjust the suggested content in real time according to the user's emotional state.

[0372] The server uses a Python program that leverages OpenCV and TensorFlow to analyze facial expression data acquired from the smart glasses' camera. This allows for real-time recognition of the user's emotional state. Furthermore, voice input is converted to text using the Google Cloud Speech-to-Text API and other tools, and sentiment analysis is performed.

[0373] For example, if a user visits a virtual store and smiles when viewing a specific product, it's possible to provide them with product recommendations or information about exclusive campaigns. This stimulates the user's desire to purchase and creates a personalized shopping experience.

[0374] An example of a prompt might be: "Based on the emotional state of the product the user has shown interest in, provide suggestions and explanations here. Generate example suggestions for when the user is smiling, and also recommend related products." This prompt allows the generative AI model to generate information optimized for the user, enriching the user experience.

[0375] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0376] Step 1:

[0377] The server receives image data from the smart glasses and preprocesses it using OpenCV. The input is raw image data from the smart glasses, and the output is image data with the face portion extracted. This image data is then used for subsequent emotion analysis.

[0378] Step 2:

[0379] The server inputs the extracted facial images into an emotion analysis model using TensorFlow to estimate the user's emotional state. In this step, the input is facial image data, and the output is an emotion label such as "interested," "satisfied," or "anxious."

[0380] Step 3:

[0381] The server converts the audio received from the smart glasses into text data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes it possible to analyze the content of the user's speech.

[0382] Step 4:

[0383] The server combines the obtained sentiment labels and text data to perform analysis to determine what interested the user. The input is sentiment labels and text data, and the output is information about the user's interests.

[0384] Step 5:

[0385] The terminal displays information on its screen based on the user's emotional state and interests, which are transmitted from the server. The input is optimized suggestion information from the server, and the output is the information the user receives visually.

[0386] Step 6:

[0387] The user reviews the information displayed on the screen and interacts with products and services that interest them further. The results of this interaction are fed back into all steps, and the system updates the information accordingly.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] [Third Embodiment]

[0392] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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".

[0404] This invention is a system for providing an individually optimized learning experience, generating an optimal set of problems according to the user's learning needs. The system includes a server, a terminal, and user interaction to support the user's learning activities.

[0405] The server is responsible for analyzing answer data and past performance information received from the terminal. This allows the server to identify areas where the user struggles. For example, if a user has a high error rate on differential calculus problems in mathematics, the server will identify this as a warning.

[0406] The terminal provides an interface between the server and the user, presenting problems to the user and receiving answers. When a user answers a problem, the answer data is sent to the server via the terminal. The displayed problems are dynamically updated based on the user's weak areas, past performance, and even the question trends of their target school.

[0407] Users solve problems presented on their devices and receive immediate feedback. The feedback sent from the server includes information about whether the answer is correct or incorrect, as well as explanations and related materials if the answer is wrong. For example, if a user gives an incorrect answer, the server sends a detailed explanation, which is then displayed on the device.

[0408] As an example of this system, suppose a user identifies English reading comprehension questions, which they frequently get wrong, as a weak point in their preparation for the entrance exam of a university they wish to attend. In this case, the server generates similar reading comprehension questions and provides them to the user via their terminal. The user answers these questions and receives further feedback based on their results, allowing them to efficiently overcome their weaknesses in preparation for the actual entrance exam.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The user receives the problem on their device. The device receives the problem sent from the server and presents it visually to the user via a display interface.

[0412] Step 2:

[0413] The user answers the question. Based on the presented question, the user enters the appropriate answer. The answer can be entered in the form of multiple-choice or written response.

[0414] Step 3:

[0415] The terminal collects user responses. It records the response data entered by the user and sends this data to the server in real time.

[0416] Step 4:

[0417] The server receives and analyzes the answer data. Based on the received answer data, it determines whether the questions are correct or incorrect, and updates the user's weaknesses and strengths by comparing them with past performance data.

[0418] Step 5:

[0419] The server selects the optimal problem to solve next. Based on the analysis results, it selects the most suitable problem to strengthen the user's weaknesses and leverage their strengths, while also taking into account the latest exam trends.

[0420] Step 6:

[0421] The server sends the newly selected problem to the terminal. To allow the user to continue learning, it immediately sends the next problem.

[0422] Step 7:

[0423] The terminal presents a new problem to the user. It receives the problem sent from the server and prepares to display it to the user.

[0424] Step 8:

[0425] The server generates feedback on the user's answers. In addition to indicating whether the answer is correct or incorrect and explaining the reasons for incorrect answers, it generates supplementary information to aid understanding and sends it to the terminal.

[0426] Step 9:

[0427] The device displays feedback to the user. It visually presents the feedback received from the server to the user, providing guidance for further learning.

[0428] (Example 1)

[0429] 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."

[0430] In today's educational environment, there is a need to effectively provide optimal learning tasks tailored to each learner's areas of weakness and specific goals. However, general educational systems often struggle to fully meet the individual needs of learners, resulting in the provision of uniform tasks. This hinders learners from further developing their strengths and efficiently overcoming their weaknesses.

[0431] 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.

[0432] In this invention, the server includes an interface means for displaying tasks to users and accepting answers, an information collection means for collecting user answer information and past performance history, and a data analysis means for analyzing the collected information to identify the user's strengths and weaknesses. This makes it possible to provide tasks optimized for individual learners and support efficient learning.

[0433] An "interface mechanism" is a system for displaying a problem to a user and receiving their solution.

[0434] "Information gathering means" refers to a mechanism for collecting users' answer information and past performance history.

[0435] A "data analysis method" is a system that identifies a user's strengths and weaknesses based on the information collected.

[0436] A "task generation mechanism" is a system for generating tasks suitable for the user based on analysis results.

[0437] A "problem presentation method" is a mechanism for providing generated problems to users.

[0438] An "evaluation tool" is a mechanism for evaluating users' answers and providing feedback based on the evaluation results.

[0439] This invention is a system that provides learners with an individually optimized learning experience, and includes the interaction of a server, a terminal, and a user.

[0440] The server collects user answer information and past performance history for central data management and analysis. The server stores this information in a database and performs analysis using a generative AI model. Specifically, the generative AI model executes prompts such as "Analyze the latest answer data and identify areas of weakness," thereby identifying the user's strengths and weaknesses.

[0441] The terminal provides a user interface between the user and the server. The terminal displays tasks received from the server to the user, and when the user answers a task, it sends the answer data to the server. The terminal also displays feedback from the server, conveying evaluation results and suggestions for improvement to the user.

[0442] Users progress through their learning via their devices. For example, if a user identifies areas where they frequently make mistakes while preparing for a specific university entrance exam, the server generates similar assignments and provides them through the device. Through this process, users can efficiently progress through their learning and overcome their weak areas.

[0443] An example of a prompt message would be an instruction such as, "Generate English reading comprehension questions based on the user's performance data." This allows the server to generate the most suitable tasks based on the analysis results, thereby individually optimizing the user's learning experience.

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The server receives user response information sent from the terminal and stores it in the database. This input includes the user's response content, timestamp, and user identification information. The server organizes this information in preparation for future analysis.

[0447] Step 2:

[0448] The server uses accumulated answer data and past performance history to perform data analysis using a generative AI model. As input, it analyzes the user's performance data and answer history based on the prompt "Analyze the latest answer data and identify areas of weakness," and generates a report that clearly identifies the user's strengths and weaknesses.

[0449] Step 3:

[0450] The server generates tasks tailored to the user's areas of weakness based on the data analysis results. This task generation uses the prompt "Create tasks that focus on the identified areas of weakness." The generated tasks are tailored to the user's needs and include specific content.

[0451] Step 4:

[0452] The terminal receives tasks generated from the server and provides an interface to display them to the user. The terminal acts as a platform for the user to solve the tasks and sends the user's answers back to the server. The inputs here are the tasks from the server and the user's answers, and the output is the answer results sent back to the server.

[0453] Step 5:

[0454] The server immediately evaluates the answers received from the user and determines whether they are correct or incorrect. Based on the evaluation results, feedback is generated, and a prompt is used asking, "Please provide the evaluation results for your answer and suggestions for improvement." The generated feedback is then provided to the user via the terminal.

[0455] (Application Example 1)

[0456] 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."

[0457] Traditional systems were limited to users' past performance data, making it difficult to personalize learning experiences that took into account users' interests and browsing history. As a result, there was a problem in that the system could not adequately suggest learning courses and problem sets that were truly necessary for the user, thus hindering learning efficiency.

[0458] 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.

[0459] In this invention, the server includes a presentation means for displaying problems to the user and accepting answers, an information collection means for collecting the user's answer information and past performance information, an analysis means for analyzing the collected information to identify the user's strengths and weaknesses, and a customization generation means. This makes it possible to provide individually optimized learning courses and materials based on the user's past purchase and browsing history.

[0460] "A means of displaying problems and accepting answers" refers to a device or software that displays learning problems on a screen for the user and provides an interface for inputting answers.

[0461] "Information gathering means" refers to a device or software for transmitting and storing users' answer information and past performance information on a server.

[0462] "Analysis tools" refer to devices or software that analyze collected information and execute algorithms to identify the user's strengths and weaknesses.

[0463] "Problem generation means" refers to a device or software for creating or selecting optimal learning problems for the user based on the results obtained by the analysis means.

[0464] "Problem presentation means" refers to a device or software for providing users with generated or selected learning problems.

[0465] A "customization generation method" refers to a device or software that individually optimizes and generates learning courses and materials based on a user's past purchase and browsing history.

[0466] This system provides users with a personalized learning experience. First, the server plays a central role in collecting answer data and past performance information transmitted from the user's device. This information is efficiently stored using data collection tools. The server then analyzes this collected information using Python and other data analysis tools.

[0467] The server then uses analytical tools to identify the user's strengths and weaknesses. This is done using data analysis algorithms based on each user's unique patterns. For example, if a user has a high error rate in a particular subject or topic, that area is identified as a weak point.

[0468] Based on this identified information, the problem generation system operates to generate or select a problem set optimized for the user. The generated problems are then displayed on the terminal via the problem presentation system, allowing the user to answer them. Once the user enters their answer, it is sent back to the server, and feedback is immediately provided to the user.

[0469] Furthermore, the system includes a customization generation mechanism that utilizes the user's purchase and browsing history to individually optimize learning courses and materials. This allows users to easily create a learning plan that suits them.

[0470] As a concrete example, for a user who frequently makes mistakes on English reading comprehension questions, the server automatically presents more questions in that area to help them overcome their difficulties at their own pace. Generative AI models may also be used in this process.

[0471] An example of a prompt text for a generative AI model is, "Recommend an appropriate learning course based on the user's past purchase history."

[0472] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0473] Step 1:

[0474] The server receives user answer information and past performance data from the terminal. The input at this stage is data such as the user's answer choices and scores, and the output is storing this data in a database on the server. Verification is performed during this information collection process to maintain data consistency.

[0475] Step 2:

[0476] The server analyzes the collected data to identify the user's strengths and weaknesses. The input is the answer information stored in step 1. The server uses a data analysis algorithm to identify strengths and weaknesses. This output is obtained as the analysis result, and areas where the user shows a high error rate are recorded as weaknesses.

[0477] Step 3:

[0478] The server uses a problem generation mechanism based on the analysis results to create learning problems optimized for the user. The input is the analysis results obtained in step 2. In this step, a set of problems corresponding to the user's weak areas is selected or a new set is generated, and the results are output. The set of problems is selected comprehensively, taking prior knowledge into consideration.

[0479] Step 4:

[0480] The terminal presents the user with generated or selected learning problems. The input is a set of problems received from the server, and the output is the display of those problems on the user's screen. The user can then review the problems and provide answers, and the answer data is sent back to the server via the terminal.

[0481] Step 5:

[0482] The server receives the answer and immediately generates and sends feedback to the user. The input at this stage is the question and the user's answer. The server performs a correct / incorrect analysis and immediately sends feedback to the user, including explanations and suggestions for improvement. The output is the detailed feedback information provided to the user.

[0483] Step 6:

[0484] The server uses a customization generation method to personalize learning courses based on the user's past purchase and browsing history. The input is the user's purchase and browsing history. Here, the aforementioned generative AI model is utilized to optimize the learning content. This output is then provided to the user as a personalized learning plan.

[0485] 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.

[0486] This invention is a system designed to provide an individually optimized learning experience, and has the function of recognizing the user's emotional state and adjusting the learning process accordingly. This system works in conjunction with a server, terminal, and emotion engine to provide the user with the optimal learning experience.

[0487] The server analyzes the user's answer data and past performance information to identify the user's strengths and weaknesses. Based on this information, the server uses a question generation system to create or select the most suitable questions for the user, and sends the questions to the terminal while taking into account the latest exam trends.

[0488] The terminal displays problems received from the server to the user, receives the user's answers, and sends them back to the server. Furthermore, it incorporates an emotion engine that analyzes the user's emotional state. This engine uses cameras, microphones, or sensors to monitor and analyze the user's facial expressions, voice, and behavior.

[0489] Users answer questions displayed on their devices, and their emotions are recorded through the device by an emotion engine during this process. For example, if stress is detected, that information is sent to a server, and feedback is generated to appropriately adjust the difficulty level of the questions.

[0490] As a concrete example, suppose a user is working on a math problem, and the emotion engine detects anxiety or fatigue from the user's facial expressions and voice. In this case, the server takes this emotional information into account and adjusts the next problem presented, selecting a slightly easier problem or providing a more detailed explanation, in order to maintain the user's motivation to learn. This allows the user to continue learning in a comfortable environment and improve their academic ability efficiently.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The user works on learning problems presented on the device. The device displays the problems received from the server on the screen and provides input fields for the user to answer the problems.

[0494] Step 2:

[0495] The emotion engine monitors the user's emotional state. It analyzes the user's facial expressions, voice tone, and body movements in real time via the device's built-in camera and microphone, and transmits emotional information to the emotion engine.

[0496] Step 3:

[0497] The user answers the question and enters the answer into the terminal. The terminal immediately sends this data to the server, and the process proceeds to the next analysis stage.

[0498] Step 4:

[0499] The server analyzes the answer data and sentiment information. It determines whether the received answers are correct or incorrect and uses the sentiment information to understand the user's mental state. This data is recorded in the user's learning profile.

[0500] Step 5:

[0501] The server selects the next problem to present based on the analysis results. It adjusts the difficulty level of the problems according to the user's areas of difficulty and emotional state, generating or selecting appropriate problems.

[0502] Step 6:

[0503] The server sends the generated problems and learning feedback to the device. The feedback may include detailed explanations of the solutions and motivational messages.

[0504] Step 7:

[0505] The device displays newly received problems and feedback to the user. Based on the feedback, the user self-assessss their learning and prepares to continue learning.

[0506] Step 8:

[0507] The user then solves newly presented problems again. This perpetuates the learning loop, allowing for knowledge improvement and self-improvement in each cycle.

[0508] (Example 2)

[0509] 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."

[0510] In today's educational environment, individualized learning is necessary to accommodate the diverse learning abilities and styles of each user. However, existing systems have limitations in providing problems tailored to users' strengths and weaknesses, and they cannot quickly respond to changes in motivation and emotions. Furthermore, real-time adjustment of learning content based on emotional states is required, but achieving this has been difficult.

[0511] 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.

[0512] In this invention, the server includes a collection means for collecting user answer data and past performance information, an analysis means for analyzing the collected data to identify the user's strengths and weaknesses, and an emotion analysis means for monitoring and analyzing the user's emotional state. This enables the provision of optimal problems tailored to the user's individual learning needs and the adjustment of the learning experience based on real-time emotion data.

[0513] "Display means" refers to a device or function that visually presents a problem to the user and accepts the user's answer as input.

[0514] "Collection means" refers to a device or function that collects user answer data and past performance information.

[0515] "Analysis means" refers to a device or function that identifies a user's strengths and weaknesses based on collected data.

[0516] "Problem generation means" refers to a device or function that generates or selects the most suitable problem for the user based on the analysis results from the analysis means.

[0517] "Emotional analysis means" refers to a device or function that monitors a user's emotional state and analyzes that information.

[0518] "Adjustment means" refers to a device or function that adjusts the difficulty level and presentation method of generated problems based on user sentiment data.

[0519] "Generation means" refers to a device or function that utilizes a generation AI model to provide information to problem generation and adjustment means.

[0520] This invention provides a learning system that offers a learning experience individually optimized for each user. The implementation of this invention primarily involves a server, terminals, and a system with sentiment analysis capabilities.

[0521] The server has the functionality to lead data analysis. It collects user answer data and past performance information, and uses this data to analyze strengths and weaknesses. This analysis utilizes a database management system and machine learning algorithms. In addition, a generative AI model generates optimal problems tailored to the user's needs and sends them to the terminal.

[0522] The terminal serves to present problems to the user. Equipped with a display and input device, it displays problems received from the server and accepts the user's answers. The terminal also features sentiment analysis capabilities, collecting and analyzing user sentiment data through its camera, microphone, and sensors, and transmitting it to the server.

[0523] As users answer questions presented via their devices, they exhibit natural emotional changes. If stress or anxiety is detected, the user's emotional state is reflected on the server as data to adjust the difficulty level and presentation method of the questions.

[0524] For example, if a user is working on a math problem and the device's emotion analysis function detects stress from the user's facial expressions and voice, the server will decide to reduce the difficulty of the next problem or provide more detailed explanations. This process allows the user to effectively maintain their motivation to learn and enjoy a comfortable learning environment.

[0525] An example of a prompt for a generative AI model is, "If user anxiety is detected, how should the next problem presented be adjusted?" This prompt is used to enable the model to provide appropriate feedback based on sentiment data.

[0526] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0527] Step 1:

[0528] The server collects basic user information, past performance data, and current answer data from the terminal. User data provided by the terminal is used as input and stored in the database. This allows the server to create individual datasets for each user.

[0529] Step 2:

[0530] The server analyzes the collected data. Using machine learning algorithms, it identifies the user's strengths and weaknesses from the input data. The output of this analysis is a personalized learning report for each user. This report is then used to generate problems.

[0531] Step 3:

[0532] The server utilizes a generative AI model to generate or select optimal problems based on the user's strengths and weaknesses. A specialized learning report is used as input. The output of the problem generation process is a personalized learning problem, which is then sent to the user's terminal.

[0533] Step 4:

[0534] The terminal displays the received questions to the user. The input here is a learning question sent from the server. The user answers the question through the terminal, and the answer is recorded by the terminal and sent to the server.

[0535] Step 5:

[0536] The device monitors the user's emotional state using its built-in emotion analysis function. It uses audio and image data acquired by the device's camera and microphone as input. The analyzed emotion data is used to determine whether the user is experiencing stress or anxiety, and is then sent to the server.

[0537] Step 6:

[0538] The server receives sentiment analysis data and uses it to adjust the user's learning process. Sentimental state data and answer results are used as input. The server generates output that adjusts the difficulty of the next question or changes the presentation method, and sends this output to the terminal.

[0539] (Application Example 2)

[0540] 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."

[0541] Traditional virtual stores failed to consider the emotional state of users when making product recommendations, instead offering uniform information. Therefore, it was difficult to provide a personalized experience that reflected each user's unique purchasing intentions and interests. A system was needed to solve this problem and increase user satisfaction.

[0542] 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.

[0543] In this invention, the server includes a display device that displays information to the user and accepts responses, a data collection device that collects user response data and past performance information, and an emotion analysis device that recognizes the user's emotional state. This makes it possible to provide personalized information that takes the user's emotional state into consideration in real time.

[0544] A "user" refers to an individual who utilizes a system, receives information through a display device, and responds.

[0545] "Information" refers to data, including content and choices presented to the user.

[0546] A "display device" is a device used to present information to a user visually or audibly.

[0547] "Response data" refers to data generated as a result of selections and interactions that a user makes with a display device.

[0548] "Performance information" refers to information about past user behavior patterns and the results achieved.

[0549] "Collection device" refers to a device or software used to acquire response data and result information.

[0550] An "analysis device" is a device used to analyze collected data and understand the characteristics of the user.

[0551] "Areas of expertise" refers to the fields in which users are recognized as excelling, as identified through analysis.

[0552] A "weakness" is an area identified through analysis as a result of which users perceive as a challenge.

[0553] An "information generation device" is a device that creates or selects optimized information for the user based on analysis results.

[0554] A "presentation device" refers to a device used to present generated information to a user.

[0555] "Emotional state" refers to the user's current psychological or emotional state.

[0556] An "emotion analysis device" is a device that recognizes and analyzes a user's emotional state.

[0557] The system used to realize this application provides users with an interactive experience in a virtual store. The server uses a display device and an emotion analysis device that recognizes the user's emotional state via smart glasses worn by the user. This allows the system to adjust the suggested content in real time according to the user's emotional state.

[0558] The server uses a Python program that leverages OpenCV and TensorFlow to analyze facial expression data acquired from the smart glasses' camera. This allows for real-time recognition of the user's emotional state. Furthermore, voice input is converted to text using the Google Cloud Speech-to-Text API and other tools, and sentiment analysis is performed.

[0559] For example, if a user visits a virtual store and smiles when viewing a specific product, it's possible to provide them with product recommendations or information about exclusive campaigns. This stimulates the user's desire to purchase and creates a personalized shopping experience.

[0560] An example of a prompt might be: "Based on the emotional state of the product the user has shown interest in, provide suggestions and explanations here. Generate example suggestions for when the user is smiling, and also recommend related products." This prompt allows the generative AI model to generate information optimized for the user, enriching the user experience.

[0561] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0562] Step 1:

[0563] The server receives image data from the smart glasses and preprocesses it using OpenCV. The input is raw image data from the smart glasses, and the output is image data with the face portion extracted. This image data is then used for subsequent emotion analysis.

[0564] Step 2:

[0565] The server inputs the extracted facial images into an emotion analysis model using TensorFlow to estimate the user's emotional state. In this step, the input is facial image data, and the output is an emotion label such as "interested," "satisfied," or "anxious."

[0566] Step 3:

[0567] The server converts the audio received from the smart glasses into text data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes it possible to analyze the content of the user's speech.

[0568] Step 4:

[0569] The server combines the obtained sentiment labels and text data to perform analysis to determine what interested the user. The input is sentiment labels and text data, and the output is information about the user's interests.

[0570] Step 5:

[0571] The terminal displays information on its screen based on the user's emotional state and interests, which are transmitted from the server. The input is optimized suggestion information from the server, and the output is the information the user receives visually.

[0572] Step 6:

[0573] The user reviews the information displayed on the screen and interacts with products and services that interest them further. The results of this interaction are fed back into all steps, and the system updates the information accordingly.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] [Fourth Embodiment]

[0578] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0579] 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.

[0580] 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).

[0581] 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.

[0582] 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.

[0583] 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).

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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".

[0591] This invention is a system for providing an individually optimized learning experience, generating an optimal set of problems according to the user's learning needs. The system includes a server, a terminal, and user interaction to support the user's learning activities.

[0592] The server is responsible for analyzing answer data and past performance information received from the terminal. This allows the server to identify areas where the user struggles. For example, if a user has a high error rate on differential calculus problems in mathematics, the server will identify this as a warning.

[0593] The terminal provides an interface between the server and the user, presenting problems to the user and receiving answers. When a user answers a problem, the answer data is sent to the server via the terminal. The displayed problems are dynamically updated based on the user's weak areas, past performance, and even the question trends of their target school.

[0594] Users solve problems presented on their devices and receive immediate feedback. The feedback sent from the server includes information about whether the answer is correct or incorrect, as well as explanations and related materials if the answer is wrong. For example, if a user gives an incorrect answer, the server sends a detailed explanation, which is then displayed on the device.

[0595] As an example of this system, suppose a user identifies English reading comprehension questions, which they frequently get wrong, as a weak point in their preparation for the entrance exam of a university they wish to attend. In this case, the server generates similar reading comprehension questions and provides them to the user via their terminal. The user answers these questions and receives further feedback based on their results, allowing them to efficiently overcome their weaknesses in preparation for the actual entrance exam.

[0596] The following describes the processing flow.

[0597] Step 1:

[0598] The user receives the problem on their device. The device receives the problem sent from the server and presents it visually to the user via a display interface.

[0599] Step 2:

[0600] The user answers the question. Based on the presented question, the user enters the appropriate answer. The answer can be entered in the form of multiple-choice or written response.

[0601] Step 3:

[0602] The terminal collects user responses. It records the response data entered by the user and sends this data to the server in real time.

[0603] Step 4:

[0604] The server receives and analyzes the answer data. Based on the received answer data, it determines whether the questions are correct or incorrect, and updates the user's weaknesses and strengths by comparing them with past performance data.

[0605] Step 5:

[0606] The server selects the optimal problem to solve next. Based on the analysis results, it selects the most suitable problem to strengthen the user's weaknesses and leverage their strengths, while also taking into account the latest exam trends.

[0607] Step 6:

[0608] The server sends the newly selected problem to the terminal. To allow the user to continue learning, it immediately sends the next problem.

[0609] Step 7:

[0610] The terminal presents a new problem to the user. It receives the problem sent from the server and prepares to display it to the user.

[0611] Step 8:

[0612] The server generates feedback on the user's answers. In addition to indicating whether the answer is correct or incorrect and explaining the reasons for incorrect answers, it generates supplementary information to aid understanding and sends it to the terminal.

[0613] Step 9:

[0614] The device displays feedback to the user. It visually presents the feedback received from the server to the user, providing guidance for further learning.

[0615] (Example 1)

[0616] 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".

[0617] In today's educational environment, there is a need to effectively provide optimal learning tasks tailored to each learner's areas of weakness and specific goals. However, general educational systems often struggle to fully meet the individual needs of learners, resulting in the provision of uniform tasks. This hinders learners from further developing their strengths and efficiently overcoming their weaknesses.

[0618] 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.

[0619] In this invention, the server includes an interface means for displaying tasks to users and accepting answers, an information collection means for collecting user answer information and past performance history, and a data analysis means for analyzing the collected information to identify the user's strengths and weaknesses. This makes it possible to provide tasks optimized for individual learners and support efficient learning.

[0620] An "interface mechanism" is a system for displaying a problem to a user and receiving their solution.

[0621] "Information gathering means" refers to a mechanism for collecting users' answer information and past performance history.

[0622] A "data analysis method" is a system that identifies a user's strengths and weaknesses based on the information collected.

[0623] A "task generation mechanism" is a system for generating tasks suitable for the user based on analysis results.

[0624] A "problem presentation method" is a mechanism for providing generated problems to users.

[0625] An "evaluation tool" is a mechanism for evaluating users' answers and providing feedback based on the evaluation results.

[0626] This invention is a system that provides learners with an individually optimized learning experience, and includes the interaction of a server, a terminal, and a user.

[0627] The server collects user answer information and past performance history for central data management and analysis. The server stores this information in a database and performs analysis using a generative AI model. Specifically, the generative AI model executes prompts such as "Analyze the latest answer data and identify areas of weakness," thereby identifying the user's strengths and weaknesses.

[0628] The terminal provides a user interface between the user and the server. The terminal displays tasks received from the server to the user, and when the user answers a task, it sends the answer data to the server. The terminal also displays feedback from the server, conveying evaluation results and suggestions for improvement to the user.

[0629] Users progress through their learning via their devices. For example, if a user identifies areas where they frequently make mistakes while preparing for a specific university entrance exam, the server generates similar assignments and provides them through the device. Through this process, users can efficiently progress through their learning and overcome their weak areas.

[0630] An example of a prompt message would be an instruction such as, "Generate English reading comprehension questions based on the user's performance data." This allows the server to generate the most suitable tasks based on the analysis results, thereby individually optimizing the user's learning experience.

[0631] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0632] Step 1:

[0633] The server receives user response information sent from the terminal and stores it in the database. This input includes the user's response content, timestamp, and user identification information. The server organizes this information in preparation for future analysis.

[0634] Step 2:

[0635] The server uses accumulated answer data and past performance history to perform data analysis using a generative AI model. As input, it analyzes the user's performance data and answer history based on the prompt "Analyze the latest answer data and identify areas of weakness," and generates a report that clearly identifies the user's strengths and weaknesses.

[0636] Step 3:

[0637] The server generates tasks tailored to the user's areas of weakness based on the data analysis results. This task generation uses the prompt "Create tasks that focus on the identified areas of weakness." The generated tasks are tailored to the user's needs and include specific content.

[0638] Step 4:

[0639] The terminal receives tasks generated from the server and provides an interface to display them to the user. The terminal acts as a platform for the user to solve the tasks and sends the user's answers back to the server. The inputs here are the tasks from the server and the user's answers, and the output is the answer results sent back to the server.

[0640] Step 5:

[0641] The server immediately evaluates the answers received from the user and determines whether they are correct or incorrect. Based on the evaluation results, feedback is generated, and a prompt is used asking, "Please provide the evaluation results for your answer and suggestions for improvement." The generated feedback is then provided to the user via the terminal.

[0642] (Application Example 1)

[0643] 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".

[0644] Traditional systems were limited to users' past performance data, making it difficult to personalize learning experiences that took into account users' interests and browsing history. As a result, there was a problem in that the system could not adequately suggest learning courses and problem sets that were truly necessary for the user, thus hindering learning efficiency.

[0645] 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.

[0646] In this invention, the server includes a presentation means for displaying problems to the user and accepting answers, an information collection means for collecting the user's answer information and past performance information, an analysis means for analyzing the collected information to identify the user's strengths and weaknesses, and a customization generation means. This makes it possible to provide individually optimized learning courses and materials based on the user's past purchase and browsing history.

[0647] "A means of displaying problems and accepting answers" refers to a device or software that displays learning problems on a screen for the user and provides an interface for inputting answers.

[0648] "Information gathering means" refers to a device or software for transmitting and storing users' answer information and past performance information on a server.

[0649] "Analysis tools" refer to devices or software that analyze collected information and execute algorithms to identify the user's strengths and weaknesses.

[0650] "Problem generation means" refers to a device or software for creating or selecting optimal learning problems for the user based on the results obtained by the analysis means.

[0651] "Problem presentation means" refers to a device or software for providing users with generated or selected learning problems.

[0652] A "customization generation method" refers to a device or software that individually optimizes and generates learning courses and materials based on a user's past purchase and browsing history.

[0653] This system provides users with a personalized learning experience. First, the server plays a central role in collecting answer data and past performance information transmitted from the user's device. This information is efficiently stored using data collection methods. The server then analyzes this collected information using Python and other data analysis tools.

[0654] The server then uses analytical tools to identify the user's strengths and weaknesses. This is done using data analysis algorithms based on each user's unique patterns. For example, if a user has a high error rate in a particular subject or topic, that area is identified as a weak point.

[0655] Based on this identified information, the problem generation system operates to generate or select a problem set optimized for the user. The generated problems are then displayed on the terminal via the problem presentation system, allowing the user to answer them. Once the user enters their answer, it is sent back to the server, and feedback is immediately provided to the user.

[0656] Furthermore, the system includes a customization generation mechanism that utilizes the user's purchase and browsing history to individually optimize learning courses and materials. This allows users to easily create a learning plan that suits them.

[0657] As a concrete example, for a user who frequently makes mistakes on English reading comprehension questions, the server automatically presents more questions in that area to help them overcome their difficulties at their own pace. Generative AI models may also be used in this process.

[0658] An example of a prompt text for a generative AI model is, "Recommend an appropriate learning course based on the user's past purchase history."

[0659] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0660] Step 1:

[0661] The server receives user answer information and past performance data from the terminal. The input at this stage is data such as the user's answer choices and scores, and the output is storing this data in a database on the server. Verification is performed during this information collection process to maintain data consistency.

[0662] Step 2:

[0663] The server analyzes the collected data to identify the user's strengths and weaknesses. The input is the answer information stored in step 1. The server uses a data analysis algorithm to identify strengths and weaknesses. This output is obtained as the analysis result, and areas where the user shows a high error rate are recorded as weaknesses.

[0664] Step 3:

[0665] The server uses a problem generation mechanism based on the analysis results to create learning problems optimized for the user. The input is the analysis results obtained in step 2. In this step, a set of problems corresponding to the user's weak areas is selected or a new set is generated, and the results are output. The set of problems is selected comprehensively, taking prior knowledge into consideration.

[0666] Step 4:

[0667] The terminal presents the user with generated or selected learning problems. The input is a set of problems received from the server, and the output is the display of those problems on the user's screen. The user can then review the problems and provide answers, and the answer data is sent back to the server via the terminal.

[0668] Step 5:

[0669] The server receives the answer and immediately generates and sends feedback to the user. The input at this stage is the question and the user's answer. The server performs a correct / incorrect analysis and immediately sends feedback to the user, including explanations and suggestions for improvement. The output is the detailed feedback information provided to the user.

[0670] Step 6:

[0671] The server uses a customization generation method to personalize learning courses based on the user's past purchase and browsing history. The input is the user's purchase and browsing history. Here, the aforementioned generative AI model is utilized to optimize the learning content. This output is then provided to the user as a personalized learning plan.

[0672] 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.

[0673] This invention is a system designed to provide an individually optimized learning experience, and has the function of recognizing the user's emotional state and adjusting the learning process accordingly. This system works in conjunction with a server, terminal, and emotion engine to provide the user with the optimal learning experience.

[0674] The server analyzes the user's answer data and past performance information to identify the user's strengths and weaknesses. Based on this information, the server uses a question generation system to create or select the most suitable questions for the user, and sends the questions to the terminal while taking into account the latest exam trends.

[0675] The terminal displays problems received from the server to the user, receives the user's answers, and sends them back to the server. Furthermore, it incorporates an emotion engine that analyzes the user's emotional state. This engine uses cameras, microphones, or sensors to monitor and analyze the user's facial expressions, voice, and behavior.

[0676] Users answer questions displayed on their devices, and their emotions are recorded through the device by an emotion engine during this process. For example, if stress is detected, that information is sent to a server, and feedback is generated to appropriately adjust the difficulty level of the questions.

[0677] As a concrete example, suppose a user is working on a math problem, and the emotion engine detects anxiety or fatigue from the user's facial expressions and voice. In this case, the server takes this emotional information into account and adjusts the next problem presented, selecting a slightly easier problem or providing a more detailed explanation, in order to maintain the user's motivation to learn. This allows the user to continue learning in a comfortable environment and improve their academic ability efficiently.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The user works on learning problems presented on the device. The device displays the problems received from the server on the screen and provides input fields for the user to answer the problems.

[0681] Step 2:

[0682] The emotion engine monitors the user's emotional state. It analyzes the user's facial expressions, voice tone, and body movements in real time via the device's built-in camera and microphone, and transmits emotional information to the emotion engine.

[0683] Step 3:

[0684] The user answers the question and enters the answer into the terminal. The terminal immediately sends this data to the server, and the process proceeds to the next analysis stage.

[0685] Step 4:

[0686] The server analyzes the answer data and sentiment information. It determines whether the received answers are correct or incorrect and uses the sentiment information to understand the user's mental state. This data is recorded in the user's learning profile.

[0687] Step 5:

[0688] The server selects the next problem to present based on the analysis results. It adjusts the difficulty level of the problems according to the user's areas of difficulty and emotional state, generating or selecting appropriate problems.

[0689] Step 6:

[0690] The server sends the generated problem and learning feedback to the device. The feedback may include detailed explanations of the solution and motivational messages.

[0691] Step 7:

[0692] The device displays newly received problems and feedback to the user. Based on the feedback, the user self-assessss their learning and prepares to continue learning.

[0693] Step 8:

[0694] The user then solves newly presented problems again. This perpetuates the learning loop, allowing for knowledge improvement and self-improvement in each cycle.

[0695] (Example 2)

[0696] 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".

[0697] In today's educational environment, individualized learning is necessary to accommodate the diverse learning abilities and styles of each user. However, existing systems have limitations in providing problems tailored to users' strengths and weaknesses, and they cannot quickly respond to changes in motivation and emotions. Furthermore, real-time adjustment of learning content based on emotional states is required, but achieving this has been difficult.

[0698] 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.

[0699] In this invention, the server includes a collection means for collecting user answer data and past performance information, an analysis means for analyzing the collected data to identify the user's strengths and weaknesses, and an emotion analysis means for monitoring and analyzing the user's emotional state. This enables the provision of optimal problems tailored to the user's individual learning needs and the adjustment of the learning experience based on real-time emotion data.

[0700] "Display means" refers to a device or function that visually presents a problem to the user and accepts the user's answer as input.

[0701] "Collection means" refers to a device or function that collects user answer data and past performance information.

[0702] "Analysis means" refers to a device or function that identifies a user's strengths and weaknesses based on collected data.

[0703] "Problem generation means" refers to a device or function that generates or selects the most suitable problem for the user based on the analysis results from the analysis means.

[0704] "Emotional analysis means" refers to a device or function that monitors a user's emotional state and analyzes that information.

[0705] "Adjustment means" refers to a device or function that adjusts the difficulty level and presentation method of generated problems based on user sentiment data.

[0706] "Generation means" refers to a device or function that utilizes a generation AI model to provide information to problem generation and adjustment means.

[0707] This invention provides a learning system that offers a learning experience individually optimized for each user. The implementation of this invention primarily involves a server, terminals, and a system with sentiment analysis capabilities.

[0708] The server has the functionality to lead data analysis. It collects user answer data and past performance information, and uses this data to analyze strengths and weaknesses. This analysis utilizes a database management system and machine learning algorithms. In addition, a generative AI model generates optimal problems tailored to the user's needs and sends them to the terminal.

[0709] The terminal serves to present problems to the user. Equipped with a display and input device, it displays problems received from the server and accepts the user's answers. The terminal also features sentiment analysis capabilities, collecting and analyzing user sentiment data through its camera, microphone, and sensors, and transmitting it to the server.

[0710] As users answer questions presented via their devices, they exhibit natural emotional changes. If stress or anxiety is detected, the user's emotional state is reflected on the server as data to adjust the difficulty level and presentation method of the questions.

[0711] For example, if a user is working on a math problem and the device's emotion analysis function detects stress from the user's facial expressions and voice, the server will decide to reduce the difficulty of the next problem or provide more detailed explanations. This process allows the user to effectively maintain their motivation to learn and enjoy a comfortable learning environment.

[0712] An example of a prompt for a generative AI model is, "If user anxiety is detected, how should the next problem presented be adjusted?" This prompt is used to enable the model to provide appropriate feedback based on sentiment data.

[0713] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0714] Step 1:

[0715] The server collects basic user information, past performance data, and current answer data from the terminal. User data provided by the terminal is used as input and stored in the database. This allows the server to create individual datasets for each user.

[0716] Step 2:

[0717] The server analyzes the collected data. Using machine learning algorithms, it identifies the user's strengths and weaknesses from the input data. The output of this analysis is a personalized learning report for each user. This report is then used to generate problems.

[0718] Step 3:

[0719] The server utilizes a generative AI model to generate or select optimal problems based on the user's strengths and weaknesses. A specialized learning report is used as input. The output of the problem generation process is a personalized learning problem, which is then sent to the user's terminal.

[0720] Step 4:

[0721] The terminal displays the received questions to the user. The input here is a learning question sent from the server. The user answers the question through the terminal, and the answer is recorded by the terminal and sent to the server.

[0722] Step 5:

[0723] The device monitors the user's emotional state using its built-in emotion analysis function. It uses audio and image data acquired by the device's camera and microphone as input. The analyzed emotion data is used to determine whether the user is experiencing stress or anxiety, and is then sent to the server.

[0724] Step 6:

[0725] The server receives sentiment analysis data and uses it to adjust the user's learning process. Sentimental state data and answer results are used as input. The server generates output that adjusts the difficulty of the next question or changes the presentation method, and sends this output to the terminal.

[0726] (Application Example 2)

[0727] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0728] Traditional virtual stores failed to consider the emotional state of users when making product recommendations, instead offering uniform information. Therefore, it was difficult to provide a personalized experience that reflected each user's unique purchasing intentions and interests. A system was needed to solve this problem and increase user satisfaction.

[0729] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0730] In this invention, the server includes a display device that displays information to the user and accepts responses, a data collection device that collects user response data and past performance information, and an emotion analysis device that recognizes the user's emotional state. This makes it possible to provide personalized information that takes the user's emotional state into consideration in real time.

[0731] A "user" refers to an individual who utilizes a system, receives information through a display device, and responds.

[0732] "Information" refers to data, including content and choices presented to the user.

[0733] A "display device" is a device used to present information to a user visually or audibly.

[0734] "Response data" refers to data generated as a result of selections and interactions that a user makes with a display device.

[0735] "Performance information" refers to information about past user behavior patterns and the results achieved.

[0736] "Collection device" refers to a device or software used to acquire response data and result information.

[0737] An "analysis device" is a device used to analyze collected data and understand the characteristics of the user.

[0738] "Areas of expertise" refers to the fields in which users are recognized as excelling, as identified through analysis.

[0739] A "weakness" is an area identified through analysis as a result of which users perceive as a challenge.

[0740] An "information generation device" is a device that creates or selects optimized information for the user based on analysis results.

[0741] A "presentation device" refers to a device used to present generated information to a user.

[0742] "Emotional state" refers to the user's current psychological or emotional state.

[0743] An "emotion analysis device" is a device that recognizes and analyzes a user's emotional state.

[0744] The system used to realize this application provides users with an interactive experience in a virtual store. The server uses a display device and an emotion analysis device that recognizes the user's emotional state via smart glasses worn by the user. This allows the system to adjust the suggested content in real time according to the user's emotional state.

[0745] The server uses a Python program that leverages OpenCV and TensorFlow to analyze facial expression data acquired from the smart glasses' camera. This allows for real-time recognition of the user's emotional state. Furthermore, voice input is converted to text using the Google Cloud Speech-to-Text API and other tools, and sentiment analysis is performed.

[0746] For example, if a user visits a virtual store and smiles when viewing a specific product, it's possible to provide them with product recommendations or information about exclusive campaigns. This stimulates the user's desire to purchase and creates a personalized shopping experience.

[0747] An example of a prompt might be: "Based on the emotional state of the product the user has shown interest in, provide suggestions and explanations here. Generate example suggestions for when the user is smiling, and also recommend related products." This prompt allows the generative AI model to generate information optimized for the user, enriching the user experience.

[0748] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0749] Step 1:

[0750] The server receives image data from the smart glasses and preprocesses it using OpenCV. The input is raw image data from the smart glasses, and the output is image data with the face portion extracted. This image data is then used for subsequent emotion analysis.

[0751] Step 2:

[0752] The server inputs the extracted facial images into an emotion analysis model using TensorFlow to estimate the user's emotional state. In this step, the input is facial image data, and the output is an emotion label such as "interested," "satisfied," or "anxious."

[0753] Step 3:

[0754] The server converts the audio received from the smart glasses into text data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes it possible to analyze the content of the user's speech.

[0755] Step 4:

[0756] The server combines the obtained sentiment labels and text data to perform analysis to determine what interested the user. The input is sentiment labels and text data, and the output is information about the user's interests.

[0757] Step 5:

[0758] The terminal displays information on its screen based on the user's emotional state and interests, which are transmitted from the server. The input is optimized suggestion information from the server, and the output is the information the user receives visually.

[0759] Step 6:

[0760] The user reviews the information displayed on the screen and interacts with products and services that interest them further. The results of this interaction are fed back into all steps, and the system updates the information accordingly.

[0761] 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.

[0762] 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.

[0763] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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 based, for example, 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.

[0769] 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."

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] The following is further disclosed regarding the embodiments described above.

[0783] (Claim 1)

[0784] A display means for showing a problem to a user and accepting answers,

[0785] A means for collecting user answer data and past performance information,

[0786] An analytical means for analyzing collected data to identify the user's strengths and weaknesses,

[0787] A problem generation means that generates or selects the most suitable problem for the user based on the analysis results,

[0788] A system that includes a means for presenting generated problems to users.

[0789] (Claim 2)

[0790] The system according to claim 1, wherein the analysis means optimizes the problem based on the user's answering tendencies and desired school information.

[0791] (Claim 3)

[0792] The system according to claim 1, wherein the problem generation means selects problems that conform to the latest exam trends.

[0793] "Example 1"

[0794] (Claim 1)

[0795] An interface means for displaying a task to the user and accepting answers,

[0796] Information gathering means for collecting user answer information and past performance history,

[0797] A data analysis method that analyzes collected information to identify the user's strengths and weaknesses,

[0798] A task generation means that generates tasks optimized for the user based on the analysis results,

[0799] A means of presenting tasks to users, and

[0800] A system that includes an evaluation mechanism to evaluate users' answers to assigned tasks and provide immediate feedback.

[0801] (Claim 2)

[0802] The system according to claim 1, wherein the analysis means optimizes the task based on the user's answer patterns and target school information.

[0803] (Claim 3)

[0804] The system according to claim 1, wherein the task generation means generates tasks that are in line with current testing trends.

[0805] "Application Example 1"

[0806] (Claim 1)

[0807] A means of displaying a problem to the user and accepting answers,

[0808] Information gathering means for collecting user answer information and past performance information,

[0809] An analytical method that analyzes collected information to identify the user's strengths and weaknesses,

[0810] A problem generation means that generates or selects the most suitable problem for the user based on the analysis results,

[0811] A problem presentation means that presents the generated problem to the user,

[0812] A system including a customization generation method that personalizes learning courses based on the user's past purchase and browsing history.

[0813] (Claim 2)

[0814] The system according to claim 1, wherein the analysis means optimizes the problem based on the user's answer trends and desired position information.

[0815] (Claim 3)

[0816] The system according to claim 1, wherein the problem generation means selects problems that conform to the latest exam trends.

[0817] "Example 2 of combining an emotion engine"

[0818] (Claim 1)

[0819] A display means for showing a problem to a user and accepting answers,

[0820] A means for collecting user answer data and past performance information,

[0821] An analytical means for analyzing collected data to identify the user's strengths and weaknesses,

[0822] A problem generation means that generates or selects the most suitable problem for the user based on the analysis results,

[0823] A means of emotional analysis that monitors and analyzes the emotional state of users,

[0824] To present the generated problems to users in the most optimal way, adjustment means are provided to adjust the difficulty level and presentation method of the problems, taking into account the user's emotional data.

[0825] A generation means that provides information to a problem generation and adjustment means using a generative AI model,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, wherein the analysis means optimizes the problems based on the user's answering tendencies and desired school information, and the sentiment analysis means provides data to improve the user's motivation to learn.

[0829] (Claim 3)

[0830] The system according to claim 1, wherein the problem generation means selects problems that conform to the latest exam trends, and the adjustment means optimizes the learning experience based on the user's real-time sentiment data.

[0831] "Application example 2 when combining with an emotional engine"

[0832] (Claim 1)

[0833] A display device that shows information to the user and accepts responses,

[0834] A collection device that collects user response data and past performance information,

[0835] An analysis device that analyzes collected data to identify the user's strengths and weaknesses,

[0836] An information generation device that generates or selects the most suitable information for the user based on the analysis results,

[0837] A presentation device that presents the generated information to the user,

[0838] An emotion analysis device that recognizes the user's emotional state,

[0839] A system including an adjustment device that adjusts the information presented based on the user's emotional state.

[0840] (Claim 2)

[0841] The system according to claim 1, wherein the analysis device optimizes information based on the user's emotional state and preference information.

[0842] (Claim 3)

[0843] The system according to claim 1, wherein the information generating device selects information that is in line with the latest trends. [Explanation of Symbols]

[0844] 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 display means for showing a problem to a user and accepting answers, A means for collecting user answer data and past performance information, An analytical means for analyzing collected data to identify the user's strengths and weaknesses, A problem generation means that generates or selects the most suitable problem for the user based on the analysis results, A system that includes a means for presenting generated problems to users.

2. The system according to claim 1, wherein the analysis means optimizes the problem based on the user's answering tendencies and desired school information.

3. The system according to claim 1, wherein the problem generation means selects problems that conform to the latest exam trends.

Images