System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing student test response data using a generative artificial intelligence model to analyze response duration, response background, and generation process thereof; means for evaluating student learning proficiency and comprehension based on the analysis results; means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate student stress level; and means for automatically generating a study plan for each student based on the evaluation results.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional educational systems make it difficult to accurately grasp a student's learning proficiency, making it difficult to create effective study plans. Furthermore, selecting a preferred school requires a great deal of effort due to a lack of appropriate evaluation criteria. Furthermore, conventional methods do not analyze learning effects using physiological data such as students' heart rate or eye movements, resulting in insufficient learning support tailored to each student's condition. The goal of this project is to solve these issues and realize more personalized and efficient learning and exam support. [Means for solving the problem]

[0005] The present invention is a system that uses a generative artificial intelligence model to analyze students' test answer data, analyzing the time it takes to answer, the background of the answers, and the process by which they are generated. It also includes a means for evaluating the student's learning proficiency and comprehension based on the analysis results, and a means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the student's stress level. This allows the system to automatically generate and provide an optimal study plan based on each student's learning status and comprehension. Furthermore, the generative artificial intelligence model can be used to analyze past exam questions and understand question trends, further refining each student's study plan. Furthermore, it can efficiently provide exam support by calculating a matching score based on the student's progress data and entrance exam data for the student's preferred school, and suggesting the student's most suitable school.

[0006] A "generative artificial intelligence model" is an artificial intelligence algorithm that can analyze students' test response data and understand the time required to answer the questions, the background to the answers, and the process by which they were generated.

[0007] "Test response data" refers to the answers entered by students on a test and any accompanying information related to those answers.

[0008] "Learning proficiency" is an indicator of how well a student understands a particular subject or topic.

[0009] "Response time" is the time it takes a student to answer a particular test question.

[0010] "Background to the answer" refers to the thought process and reasons that led a student to a particular answer.

[0011] "Physiological data" refers to data that indicates a student's physical condition, such as heart rate and eye movements.

[0012] A "learning plan" is a specific plan that shows students what to learn and in what order to achieve specific learning goals.

[0013] "Past exam questions" are a collection of questions previously asked on a particular exam.

[0014] "Exam trends" refer to the frequency and patterns of questions on particular subjects or topics, derived from past exam questions.

[0015] "Stress level" refers to the degree of stress a student feels, estimated from physiological data such as heart rate and gaze data.

[0016] A "suitability score" is a score that indicates the degree to which a student is suited to a particular school of their choice, based on the student's learning progress data and the school's entrance examination data.

[0017] A "preferred school" is an educational institution that a student wishes to attend. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention is a system that utilizes a generative artificial intelligence model to analyze a student's learning proficiency, provide an effective study plan, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0040] First, a student (user) logs in to a device and prepares to take the test. The device displays test questions, and the student enters their answers. The entered answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the student's heart rate and gaze data, which are then sent to the server in parallel.

[0041] When the server receives the student's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the student chose that answer. It also analyzes physiological data, assessing stress levels during the exam from heart rate and eye movements. Based on this data, the student's learning proficiency and comprehension are evaluated.

[0042] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects or topics appearing in exams. Combining the student's analysis with this exam trend data, a personalized study plan is generated for each student. The study plan details which topics to focus on and the order in which they should be studied.

[0043] The server then periodically collects and evaluates the student's learning progress data and compares it with the entrance exam data of the schools of their choice to calculate a match score. Based on this match score, the server suggests the most suitable schools for the student. These suggestions are sent to the student's device and displayed for the student to review. The suggested list of schools includes each school's characteristics, past admissions records, and advice based on the student's strengths and weaknesses.

[0044] For example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if a student takes a long time to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0045] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0046] This invention allows students to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and an eye tracker.

[0050] Step 2:

[0051] The device transmits the student's answer data and physiological data in real time to a server, including the time it takes to answer each question, heart rate, and eye movements.

[0052] Step 3:

[0053] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer's time, background, and generation process.

[0054] Step 4:

[0055] The server analyzes the physiological data and assesses the student's stress level based on their heart rate and gaze data, and the results of this analysis are stored together with the student's answer data.

[0056] Step 5:

[0057] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, the topic will be identified as a weak point.

[0058] Step 6:

[0059] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze exam trends, revealing the frequency and patterns of appearance of specific subjects and topics.

[0060] Step 7:

[0061] The server combines the student's learning proficiency assessment results with analysis of past exam questions to generate a personalized learning plan, which outlines the topics to focus on and the learning priorities.

[0062] Step 8:

[0063] The server sends the generated learning plan to the terminal, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan.

[0064] Step 9:

[0065] The server periodically collects and evaluates student progress data, including which topics have been covered and to what extent.

[0066] Step 10:

[0067] The server calculates a match score for each school based on the school's entrance exam data and the student's learning progress data. The match score indicates the degree to which the student's learning status matches the school's requirements.

[0068] Step 11:

[0069] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[0070] Step 12:

[0071] The student user checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final preferred school.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] In the past, understanding students' learning proficiency and providing individualized learning plans required extensive time-consuming and laborious instruction and intervention. It was also difficult for students to accurately assess their own learning progress and stress levels, making it difficult to create effective learning plans and select the most appropriate schools. Furthermore, analyzing the question trends for specific topics one by one was time-consuming and hindered efficient learning. The goal of this project is to solve these problems and provide learning support tailored to each student.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for analyzing a user's test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the user's learning proficiency and comprehension, means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the user's stress level, means for automatically generating a study plan for each user, means for understanding the question trends for specific topics using a database of past test questions, means for analyzing the user's study progress data and calculating a match score with the entrance examination data of desired institutions, and means for suggesting desired institutions based on the match score, thereby enabling the provision of an individualized study plan, efficient learning, and the selection of the most suitable desired school.

[0077] A "generative artificial intelligence model" is a type of artificial intelligence that analyzes users' test response data and physiological data to evaluate their learning proficiency, comprehension, and stress level.

[0078] "Test answer data" refers to data that includes answer information entered by a user during an exam or test and the time it took to answer the answer.

[0079] "Learning proficiency" is an index that indicates to what extent the user has understood and mastered the learning content.

[0080] "Understanding" is a measure of how deeply a user understands a particular topic or subject.

[0081] "Physiological data" refers to data that indicates the user's physical and physiological state, such as heart rate, eye movement, and skin potential.

[0082] "Stress level" is an index that evaluates the degree of stress that the user feels during the test.

[0083] A "study plan" is a plan created by a user that includes specific topics and a timetable to help the user study efficiently.

[0084] "Exam trends" are the result of analyzing the frequency with which specific topics and subjects are tested using a database of past exam questions.

[0085] "Study progress data" is data that indicates the progress of the user's current learning activities and past learning history.

[0086] The "match score" is calculated based on the user's learning progress data and the entrance examination data of the institution of their choice, and indicates how well the user matches up with the institution.

[0087] "Desired institution" refers to the educational institution or school that the user wishes to attend or take the entrance exam for.

[0088] "Device" refers to the device a user uses to take a test or collect physiological data, including a computer, tablet, or smartphone.

[0089] "Analysis" is the act of analyzing collected data using computational processes and models to extract meaningful information.

[0090] "Automatic generation" refers to the process in which a system automatically creates plans and proposals based on data without human intervention.

[0091] The present invention is a system that utilizes a generative artificial intelligence model to analyze a user's learning proficiency, provide an effective study plan, and suggest the most suitable institution for the user. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0092] First, the user logs in to the device and prepares to take the test. The device displays test questions, and the user inputs their answers. The input answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the user's heart rate and gaze data, which are then sent to the server in parallel.

[0093] When the server receives the user's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the user chose that answer. It also analyzes physiological data, assessing stress levels during the test from heart rate and eye movements. Based on this data, the user's learning proficiency and comprehension are evaluated.

[0094] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of questions on specific subjects or topics. Combining the results of the user's analysis with this exam trend data, a personalized study plan is generated for each user. The study plan specifies which topics to focus on and in what order they should be studied.

[0095] The server then periodically collects and evaluates the user's learning progress data, compares it with the entrance exam data of the institutions of their choice, and calculates a match score. Based on this match score, the server suggests the most suitable institutions for the user. These suggestions are sent to the device and displayed for the user to review. The list of suggested institutions includes information such as each institution's characteristics, past success rates, and advice based on the user's strengths and weaknesses.

[0096] For example, when a user takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if an integer problem takes a long time to answer and is answered incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the user. Furthermore, after determining from heart rate data that the user was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0097] Furthermore, the system calculates a relevance score based on the entrance exam trend data of the institution the user is applying to, and suggests institutions where the user has a high chance of passing based on their current learning status. For example, it suggests institutions where many users with similar tendencies have passed in the past.

[0098] Examples of prompts include:

[0099] "Analyze solutions to math integer problems, identify your weaknesses, and suggest next study plans."

[0100] "Analyze users' heart rate data to assess their stress levels during the exam and plan their study accordingly."

[0101] "Use past exam data to suggest the best institutions for this user."

[0102] The present invention allows users to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable institution of choice, allowing users to effectively prepare for further education.

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1:

[0105] The user logs in to the terminal and prepares for the test.

[0106] Specifically, the user enters their ID and password into the login screen on the device and clicks the "Login" button. The entered login information is sent by the device to the server, and the server performs authentication. If authentication is successful, the device displays a test preparation screen.

[0107] Input: User login information (ID, password)

[0108] Output: Show test preparation screen

[0109] Step 2:

[0110] The user starts the test and enters the answers.

[0111] The device displays pre-prepared test questions on the screen. The user enters answers to each question and clicks the "Submit" button. The device records the user's answer data and the elapsed time from when the start button was pressed, and sends them to the server in real time.

[0112] Input: User test answer data, answer time

[0113] Output: Answer data and time information sent to the server

[0114] Step 3:

[0115] The device collects physiological data.

[0116] The heart rate sensor and gaze tracker connected to the device are activated to collect the user's heart rate data and gaze data in real time, which are then sent to the server.

[0117] Input: User's heart rate data, gaze data

[0118] Output: Heart rate data and gaze data sent to the server

[0119] Step 4:

[0120] The server analyzes the answer data and physiological data.

[0121] The server analyzes the received answer data and physiological data using a generative artificial intelligence model. Specifically, the AI ​​model processes the data to evaluate the user's learning proficiency and comprehension based on the time it took to answer, the context of the answer, heart rate, and gaze data.

[0122] Input: Answer data, heart rate data, gaze data

[0123] Output: User's learning proficiency, comprehension, and stress level evaluation results

[0124] Step 5:

[0125] The server generates a lesson plan.

[0126] The server compares the analysis results with a database of past exam questions and generates a customized study plan, including the topics to focus on and the order in which to study them. The system analyzes the frequency and patterns of questions on specific topics to determine which areas to study and in what order.

[0127] Input: learning proficiency, comprehension, stress level assessment results, past exam question data

[0128] Output: personalized learning plan

[0129] Step 6:

[0130] The server collects the learning progress data and calculates the relevance score.

[0131] The server periodically collects the user's learning progress data and compares it with the entrance exam data of the institution of choice to calculate a matching score. This process includes a function to match past learning data with entrance exam data using an SQL database.

[0132] Input: User's learning progress data, entrance exam data for desired institutions

[0133] Output: Relevance score

[0134] Step 7:

[0135] The server will suggest the most suitable institution for you to apply to.

[0136] The server then creates a list of the most suitable institutions for the user based on the relevance score. This list includes information about each institution's characteristics, past success rates, and advice on the user's strengths and weaknesses. This information is sent to the user's device for easy review.

[0137] Input: Matching score, desired institution data

[0138] Output: A list of preferred institutions sent to the user

[0139] (Application example 1)

[0140] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0141] With conventional methods for skill proficiency assessment and creating learning plans, it has been difficult to provide optimal learning plans that take into account the individual characteristics and stress levels of each worker. Furthermore, while detailed analysis, including work trends and physiological data, is necessary for efficient skill improvement, performing this manually is not practical. A system that can solve this problem is needed.

[0142] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0143] In this invention, the server includes means for analyzing the test answer data of the worker using a generative artificial intelligence model, and analyzing the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the worker's skill proficiency and understanding based on the evaluation results, and means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the worker's stress level. This makes it possible to provide a skill improvement plan based on the individual characteristics of the worker, enabling efficient learning and skill improvement.

[0144] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information based on input data.

[0145] "Test answer data" refers to answer information for test questions answered by a worker.

[0146] "Answering time" is the time it takes a worker to answer a particular test question.

[0147] "Background of the answer" refers to the process by which the worker arrived at the answer and the thinking behind it.

[0148] "Physiological data" refers to data that indicates the worker's physical condition, such as heart rate or eye tracking data.

[0149] "Stress level" refers to the degree of psychological or physiological stress experienced by an operator during a task or test.

[0150] "Skill proficiency" is an indicator that shows how well a worker has mastered a particular skill.

[0151] "Skills improvement plan" refers to a learning and training plan to effectively improve the skills of workers.

[0152] "Work trends" is information obtained by analyzing the work patterns, frequency, and content that a worker has performed in the past.

[0153] A "fit score" is an index that evaluates how well a worker's skills and characteristics are suited to a particular training program.

[0154] A "training program" is a specific plan of training and learning activities aimed at improving worker skills.

[0155] This invention is a system for efficiently improving the skills of factory workers, which utilizes a generative artificial intelligence model to analyze the skill proficiency of workers, provide an effective skill improvement plan, and propose an optimal training program. This system is implemented through a series of operations involving terminals, a server, and workers.

[0156] First, the worker (user) logs in to the terminal and prepares to take the test. The terminal displays the test questions, and the worker enters the answers. The answered data is sent to the server in real time. In addition, the worker's heart rate and gaze data are also collected by physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the terminal and sent to the server in parallel.

[0157] When the server receives the worker's test answer data, it begins analysis using a generative artificial intelligence model. The AI ​​model analyzes the time it takes to answer, the background to the answer, and the process by which it was generated to understand why the worker chose that answer. It also analyzes physiological data, assessing the worker's stress level during work from heart rate and eye movement. Based on this data, the worker's skill proficiency and level of understanding are evaluated.

[0158] The server then analyzes past work data and uses a generative artificial intelligence model to analyze past work patterns, identifying the frequency and patterns of specific tasks and processes. Combining the worker's analysis results with this work trend data generates a personalized skill development plan for each worker. The skill development plan specifies which topics to focus on and in what order they should be studied.

[0159] The server then periodically collects and evaluates the worker's learning progress data, compares it with the data from the adapted program, and calculates a compatibility score. Based on this compatibility score, the server suggests the best training program for the worker. These suggestions are sent to the terminal and displayed for the worker to review. The list of suggested training programs includes advice based on each program's features, past success, and the worker's strengths and weaknesses.

[0160] As a specific example, when a worker takes a robot operation test, the terminal sends the answers to a server, which uses a generative artificial intelligence model to analyze the answer process for each question. For example, if a worker takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as the worker's weakness. Furthermore, after confirming that the worker was in a high-stress state based on heart rate data, the AI ​​individually creates a plan for the next skill improvement, including stress control methods.

[0161] Furthermore, a compatibility score is calculated based on the trend data of the training program that the worker wishes to participate in, and a training program that is highly compatible with the worker's current skill level is suggested. For example, a training program that has been successful in the past for many workers with similar tendencies will be suggested.

[0162] An example of a prompt sentence is, "Analyze worker A's answer data and physiological data to identify his stress level and weaknesses. Based on the results, generate an optimal robot operation learning plan."

[0163] This allows workers to accurately grasp their own skill status and create efficient skill improvement plans. Furthermore, the process of selecting the most suitable training program is streamlined, enabling effective preparation for skill improvement.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] A user logs in to a terminal and prepares to take a test. The terminal displays test questions, and the user inputs answers. The input data here is the user's answer data, which is obtained through the terminal's display and input interface. The output data is the answer data sent to the server in real time.

[0167] Step 2:

[0168] Physiological data of the user is collected using a physiological data collection device (e.g., a heart rate sensor or gaze tracker) connected to the terminal. The collected data (heart rate data and gaze data) is transmitted to the server in real time. The input data of this step are various physiological data, and the output data is the physiological data transmitted to the server.

[0169] Step 3:

[0170] The server uses a generative artificial intelligence model to analyze the user's test answer data. Specifically, it analyzes the time it takes to answer, the background of the answer, and the process by which the answer was generated. The input data here is the answer data sent from the device, and the output data is the analysis results. This analysis helps understand why the user chose that answer.

[0171] Step 4:

[0172] The server analyzes the physiological data and evaluates the user's stress level based on their heart rate and eye movements. The input data is the physiological data, and the output data is the stress level evaluation result. This result indicates the degree of psychological and physiological stress on the user.

[0173] Step 5:

[0174] The server evaluates the user's skill proficiency and understanding based on the analysis results. The input data are the analysis results of the test answer data and the evaluation results of the physiological data, and the output data are the evaluation results of the skill proficiency and understanding. This evaluation indicates the user's current skill level and understanding.

[0175] Step 6:

[0176] The server analyzes past work data and uses a generative artificial intelligence model to understand past work patterns. The input data is past work data, and the output data is information indicating work trends. This reveals the frequency and patterns of specific work content and processes.

[0177] Step 7:

[0178] The server combines the skill proficiency and comprehension assessment results with the work tendency data to generate a personalized skill improvement plan for each user. The input data are the skill proficiency and comprehension assessment results and the work tendency data, and the output data is the personalized skill improvement plan. This plan specifies which topics should be studied intensively and in what order.

[0179] Step 8:

[0180] The server periodically collects the user's learning progress data, compares it with the data of the adaptive program, and calculates a matching score. The input data are the learning progress data and the data of the adaptive program, and the output data is the matching score. Based on this score, an optimal training program is suggested to the user.

[0181] Step 9:

[0182] The server proposes optimal training programs based on the relevance scores and sends the list to the terminal. The input data is the relevance scores, and the output data is a list of proposed training programs. The user can view this list through the terminal.

[0183] For example, when a user takes a robot operation test, the device sends the answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a user takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the underlying thought process and identifies that topic as the user's weak point. This analysis result is combined with heart rate data to create an optimal individual skill improvement plan.

[0184] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0185] The present invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0186] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[0187] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[0188] The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer, including the time it took, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data to assess the student's stress level from heart rate and gaze data, and further evaluates their emotional state. The results of this analysis are saved together with the student's answer data.

[0189] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if a student's comprehension of a particular topic is low, that topic is identified as a weak point. The server also uses an emotion engine to monitor changes in the student's emotions while they are studying. If stress or a decline in interest is detected, the server will revise the student's learning plan.

[0190] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student's analysis with this exam trend data generates a personalized study plan for each student. The study plan outlines the topics to focus on and the learning priorities.

[0191] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan. During the study, the emotion engine continuously monitors the student's emotional state, and the learning plan is adjusted as necessary.

[0192] Furthermore, the server periodically collects and evaluates the student's learning progress data. The learning progress data includes which topics have been covered and to what extent. Based on the learning progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's learning status and the requirements of the desired school.

[0193] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[0194] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0195] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0196] This invention allows students to accurately grasp their own learning and emotional state, allowing them to create an efficient study plan. It also streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[0197] The processing flow will be explained below.

[0198] Step 1:

[0199] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through a heart rate sensor and gaze tracker, and also collects facial expression and voice data using an emotion engine.

[0200] Step 2:

[0201] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[0202] Step 3:

[0203] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer, including the time it took to complete it, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data, such as heart rate and gaze data, to assess the student's stress level and emotional state.

[0204] Step 4:

[0205] The server evaluates the student's learning proficiency and comprehension based on these analysis results. If a student's understanding of a particular topic is low, that topic will be identified as a weak point. Furthermore, if the analysis using the emotion engine detects stress or a loss of interest, that data will also be reflected in the evaluation.

[0206] Step 5:

[0207] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions in specific subjects and topics.

[0208] Step 6:

[0209] The server combines the student's analysis results with past exam question analysis data to generate a personalized study plan, which includes topics to focus on and priorities for learning. It also suggests stress-reducing study methods based on emotional data.

[0210] Step 7:

[0211] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan, and the emotion engine continues to monitor the student's emotional state while they are studying.

[0212] Step 8:

[0213] The server periodically collects and evaluates students' learning progress data, including which topics have been covered and to what extent. An emotion engine keeps track of students' emotional states.

[0214] Step 9:

[0215] The server calculates a match score based on the student's learning progress data and the entrance exam data of the school of choice. This match score indicates the degree of match between the student's learning status and the requirements of the school of choice.

[0216] Step 10:

[0217] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[0218] Step 11:

[0219] The user, a student, checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list of preferred schools includes feedback based on each school's characteristics, past acceptance records, and the student's emotional state. Based on this information, the student selects their final preferred school.

[0220] Example 2

[0221] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0222] Conventional learning systems have difficulty accurately assessing students' learning proficiency and comprehension, making it difficult to provide optimal learning plans for each student. Furthermore, they are unable to create learning plans that reflect physiological and emotional data, and lack the ability to provide adaptive learning programs that take into account students' stress and emotional states. Furthermore, they are also inadequate in suggesting specific schools to attend based on learning progress data and school entrance exam data.

[0223] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0224] In this invention, the server includes a means for analyzing educator evaluation data using a generative artificial intelligence model to analyze the time required to answer questions, the background of the answers, and the process by which the answers were generated; a means for evaluating students' learning proficiency and comprehension; and a means for collecting and analyzing biometric data to evaluate students' stress levels. This enables accurate assessment of students' learning proficiency and comprehension and provides optimal learning plans for each student. Furthermore, by incorporating data obtained from a heart rate sensor and gaze tracker, and facial expression and voice data obtained using an emotion engine, it is possible to provide adaptive learning programs that take students' stress and emotional state into account. It is also possible to calculate a match score between learning progress data and university entrance exam data and suggest specific universities to attend.

[0225] A "generative artificial intelligence model" is a type of artificial intelligence used to analyze students' test response data and analyze the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[0226] "Assessment data" refers to data including student test response data, physiological data, and emotional data.

[0227] "Biometric data" refers to data obtained from heart rate sensors and eye trackers, which are used to assess students' stress levels and emotional states.

[0228] The "emotion engine" is a means of analyzing facial expression and voice data to assess a student's emotional state.

[0229] "Learning proficiency" is an indicator that shows the student's level of understanding of the content they have learned and their level of skill acquisition.

[0230] "Understanding" is an indicator of how well a student understands a particular topic or subject.

[0231] A "study plan" is a study schedule that sets out the optimal learning methods and content, taking into account the student's learning proficiency and comprehension, stress level, and emotional state.

[0232] A "heart rate sensor" is a device for measuring a student's heart rate.

[0233] An "eye tracker" is a device used to track students' eye movements.

[0234] "Facial expression data" is data that records and analyzes changes in students' facial expressions.

[0235] "Voice Data" refers to data that records and analyzes the tone and patterns of a student's voice.

[0236] An "adaptive learning plan" is a learning program that dynamically adjusts according to a student's real-time learning situation and emotional state.

[0237] "Progress data" is data that indicates how far a student has progressed in their studies.

[0238] "Entrance exam data" refers to data related to the entrance exam requirements and question trends of the school to which students wish to advance.

[0239] The "match score" is a score that indicates the degree of match between the student's learning data and the entrance examination data of the school they are going to.

[0240] The "school destination list" is a list of schools suggested based on the compatibility score.

[0241] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school for them to apply to. This system is implemented through a series of operations involving terminals, a server, and users.

[0242] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device is connected to devices such as a heart rate sensor, gaze tracker, and microphone, which collect physiological and emotional data in real time. For example, the heart rate sensor obtains the student's heart rate, the gaze tracker captures eye movements, and the camera and microphone collect facial expressions and voice.

[0243] The device transmits the user's answer data, physiological data, and emotional data to the server. The collected data includes the time it took to answer, the content of the answer, heart rate, eye movements, facial expressions, and voice tone. During this transmission process, the data is encrypted to ensure security. For example, the device performs batch processing at regular intervals and transmits the data to the server all at once.

[0244] The server inputs the received data into a generative AI model and begins analysis. The generative AI model analyzes the educator's evaluation data, digging deep into the time it took to answer the questions, the background, and the process by which they were generated. It also uses an emotion engine to analyze heart rate, gaze data, facial expression changes, and voice tone to assess the student's stress level and emotional state. For example, if a particular question takes a long time to answer and the heart rate rises, it can be determined that the question is causing stress.

[0245] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic is identified as a weak point. An emotion engine is used to monitor emotional changes during learning, and if stress or a decline in interest is detected, the learning plan is revised. At this stage, the generated learning plan becomes an adaptive learning program that incorporates heart rate sensors, gaze trackers, facial expression data, and voice data.

[0246] The server then accesses a database of past educational questions and uses a generative artificial intelligence model to analyze question trends, identifying the frequency and patterns of questions on specific subjects and topics. The analysis results are combined with the question trend data to generate a personalized learning plan for each student, which includes topics to focus on and priorities for learning.

[0247] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan. The emotion engine continues to monitor the student's emotional state while they are studying, and the learning plan is adjusted as necessary.

[0248] Furthermore, the server periodically collects and analyzes learning progress data. Based on the analysis results, a match score is calculated with the entrance exam data of the desired school. This match score is an indicator of the degree of match between the student's learning status and the requirements of the desired school. Based on the match score, the server generates a list of schools that are most suitable for the student and sends it to the device. The student can check the list of schools displayed on the device to help them select their preferred schools.

[0249] As a specific example, when a student takes a math test, their device sends physiological and emotional data along with their answers to a server. A generative AI model analyzes the answering process, identifies high-stress states from heart rate and emotional data, and individually creates a study plan for the next test. It also calculates a match score based on the student's desired university entrance exam trends and suggests universities where they have a high chance of being accepted.

[0250] Examples of prompts have the following format:

[0251] "Analyze students' answer data, physiological data (heart rate, gaze data), facial expression data, and voice data to assess their learning proficiency and emotional state. Then, generate an appropriate study plan and suggest the best schools for students."

[0252] This system allows students to accurately grasp their academic and emotional state, allowing them to create efficient study plans, streamline the process of selecting the most suitable school, and effectively prepare for entrance exams.

[0253] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0254] Step 1: User login and start testing

[0255] The user logs in to the terminal. A user ID and password are required as input. The terminal sends this authentication information to the server for authentication. If authentication is successful, the terminal displays a "Test Start" screen. Specifically, the user enters authentication information on the terminal, and the server verifies it to perform authentication. If authentication is successful, a test screen is displayed as output.

[0256] Step 2: Collect user responses and physiological data

[0257] The user enters answers to test questions displayed on the device. The input also includes physiological and emotional data collected using a heart rate sensor, gaze tracker, and microphone. The device collects this data in real time. Specifically, while the user enters answers using a keyboard or touchscreen, the heart rate sensor collects heart rate data, the gaze tracker collects eye movements, and the camera and microphone record facial expressions and tone of voice. The output is the collected answer data, physiological data, and emotional data.

[0258] Step 3: Send data from the device to the server

[0259] The device sends the collected answer data, physiological data, and emotional data to the server. The data collected in the previous step is required as input. The data is encrypted and transferred securely. Specifically, the device batch processes the data at regular intervals (for example, every minute) and uploads it to the server. The output is the data sent to the server.

[0260] Step 4: Data analysis by the server

[0261] The server inputs the received data into a generative artificial intelligence model and analyzes the content, background, and generation process of the answer. Inputs include collected answer data, physiological data, and emotional data. The server analyzes heart rate, gaze data, facial expression changes, and voice tone to evaluate stress levels and emotional states. For example, the server passes the answer data to the AI ​​model to evaluate the time required and accuracy, and further analyzes physiological data to understand the emotional state. The output is the analyzed learning proficiency, comprehension, and emotional state.

[0262] Step 5: Assess your learning proficiency and emotional state

[0263] The server evaluates the student's learning proficiency and comprehension based on the analysis results. The input includes the data analyzed in the previous step. For example, it evaluates the correct answer rate and response time for a specific topic and identifies weak points. It also uses an emotion engine to monitor emotional changes during learning and detect stress or loss of interest. The output is the evaluated learning proficiency and emotional state.

[0264] Step 6: Generate a lesson plan

[0265] The server accesses a database of past educational questions and analyzes question trends using a generative artificial intelligence model. Inputs include the student's learning proficiency and comprehension, and the database of past questions. The server generates an individualized learning plan for each student based on the question trends and analyzed data. For example, it analyzes the frequency and patterns of questions obtained from the database to determine the topics that should be focused on. The output is the generated learning plan.

[0266] Step 7: Provide and display your lesson plan

[0267] The server sends the generated lesson plan to the terminal. The input includes the generated lesson plan. The terminal receives it and displays it to the user. Specifically, the server sends the lesson plan to the terminal, the terminal receives it, and displays the lesson plan on the screen. The output is the lesson plan displayed on the terminal.

[0268] Step 8: Assessment of learning progress and school preference suggestions

[0269] The server periodically collects and analyzes learning progress data. Inputs include learning progress data and entrance exam data. The server compares this data with the entrance exam data of the schools of choice and calculates a matching score. For example, the server analyzes the learning progress data and calculates the degree of match with the entrance exam requirements of the schools of choice. The output is the calculated matching score and a generated list of schools of choice. This list of schools of choice is sent to the terminal and displayed to the user.

[0270] (Application example 2)

[0271] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0272] Conventional learning management systems have difficulty providing individualized learning plans that fully consider students' learning proficiency and stress levels. Furthermore, they are unable to grasp changes in students' emotional states in real time and provide learning support based on this, which can lead to students feeling stressed or losing motivation to study. Furthermore, they lack efficient suggestions based on appropriate data analysis when selecting a school of choice.

[0273] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing students' test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer; means for evaluating the students' learning proficiency and comprehension based on the analysis results; means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the students' stress levels; means for collecting students' facial expression data and voice data using an emotion engine to analyze their emotional states; and means for automatically generating individual study plans for each student based on the analysis results and emotional data, and providing the study plans including stress control methods. This enables a comprehensive evaluation of students' learning proficiency and emotional states, enabling efficient and personalized study support.

[0274] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes students' test response data and analyzes the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[0275] "Learning proficiency" is an indicator of how much a student understands and has mastered a particular topic or subject.

[0276] "Understanding" is a measure of how well a student understands a particular issue or topic.

[0277] "Physiological data" refers to data used to measure students' physical reactions and conditions, such as heart rate and gaze data.

[0278] "Stress level" is an indicator of the degree of stress a student feels while studying, assessed based on heart rate, gaze data, etc.

[0279] The "emotion engine" is a technology that analyzes facial expression and voice data to assess a student's emotional state.

[0280] "Automatically generated individualized learning plans that include stress control methods" are learning plans that are optimized based on each student's learning proficiency, stress level, and emotional state, and also incorporate stress reduction techniques.

[0281] A "suitability score" is a number that indicates how well a student is suited to their desired school by comparing their learning progress data with the entrance examination data of the school.

[0282] The "School of Choice List" is a list of schools that suggests the most suitable schools for students based on their compatibility scores.

[0283] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school of choice.

[0284] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[0285] The device transmits the student's answer data, physiological data, and emotional data to the server in real time. The transmitted data includes the time taken for each answer, heart rate, eye movements, facial expressions, and voice tone. The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer's time taken, the background of the answer, and the process by which it was generated. Furthermore, based on the physiological and emotional data, the system evaluates the student's stress level from heart rate and eye gaze data, as well as their emotional state.

[0286] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic will be identified as a weak point. The server also uses an emotion engine to monitor the student's emotional changes while they are studying, and if stress or a decline in interest is detected, the learning plan will be revised.

[0287] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student analysis with this exam trend data, a personalized study plan is generated for each student. The study plan outlines the topics to focus on and the learning priorities.

[0288] The server sends the generated study plan to the terminal and displays it to the student. The student then studies according to the study plan. During the study, the emotion engine continuously monitors the student's emotional state, and the study plan is adjusted as necessary. In addition, the server periodically collects and evaluates the student's study progress data. The study progress data includes which topics have been covered and to what extent. Based on the study progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's study state and the requirements of the desired school.

[0289] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[0290] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0291] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0292] An example of a prompt for the generative AI model is as follows:

[0293] Prompt statement:

[0294] [Student answer data] [Physiological data] [Emotional data]

[0295] for example:

[0296] "Answer: 4, Time taken: 30 seconds, Heart rate: 80, Gaze data: Concentrated, Emotion data: Neutral"

[0297] Based on the above data, evaluate your learning proficiency and stress level and create your next study plan.

[0298] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0299] Step 1:

[0300] The user logs in to the device and begins the test. The user enters answers to the test questions displayed on the device. During this process, the device collects physiological data using a heart rate sensor and gaze tracker. The device also collects facial expression and voice data using a microphone and camera.

[0301] Input: Test questions, answers, heart rate, physiological data, facial expression data, and voice data.

[0302] Output: Answer data, physiological data, emotional data.

[0303] Step 2:

[0304] The device transmits the collected data (answer data, physiological data, and emotional data) in real time to a server, which then receives the data for analysis.

[0305] Input: Answer data, physiological data, emotional data.

[0306] Output: Transmit data.

[0307] Step 3:

[0308] The server inputs the received answer data into the generative AI model and begins analysis, which examines in detail the time required to reach the answer, the background of the answer, and the process by which it was generated.

[0309] Input: Answer data.

[0310] Output: Analysis results (time required to get the answer, background of the answer, and how it was generated).

[0311] Step 4:

[0312] The server simultaneously analyzes physiological and emotional data, assessing students' stress levels based on their heart rate and gaze data, and using an emotion engine to assess their emotional state based on facial expression and voice data.

[0313] Input: physiological data, emotional data.

[0314] Output: Stress level, emotional state.

[0315] Step 5:

[0316] The server evaluates the student's learning proficiency and comprehension based on the analysis results of steps 3 and 4. This allows the server to understand how well the student has mastered a particular topic.

[0317] Input: Analysis results of answer data, stress level, emotional state.

[0318] Output: learning proficiency, comprehension.

[0319] Step 6:

[0320] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions on specific subjects and topics.

[0321] Input: Past exam question data.

[0322] Output: Question trend data.

[0323] Step 7:

[0324] The server combines the results of the learning proficiency and comprehension assessment in Step 5 with the question trend data in Step 6 to generate an individualized learning plan for each student, including the topics to focus on and learning priorities.

[0325] Input: learning proficiency, comprehension, and question trend data.

[0326] Output: Learning plan.

[0327] Step 8:

[0328] The server sends the generated learning plan to the terminal and notifies the student. The student then proceeds with their studies according to the learning plan displayed on the terminal.

[0329] Input: lesson plan.

[0330] Output: The displayed lesson plan.

[0331] Step 9:

[0332] During learning, the emotion engine continues to monitor the student's emotional state, and the server adjusts the learning plan as needed and sends it back to the device.

[0333] Input: Changes in emotional state.

[0334] Output: A tailored lesson plan.

[0335] Step 10:

[0336] The server periodically collects and analyzes the student's learning progress data, and calculates a match score with the entrance exam data of the school of choice based on the learning progress data.

[0337] Input: Learning progress data, entrance exam data for desired school.

[0338] Output: Relevance score.

[0339] Step 11:

[0340] The server generates a list of schools that best suit the student based on the relevance score, sends it to the terminal, and displays it. The student user then uses the list of schools displayed on the terminal to select their final school of choice.

[0341] Input: Relevance score.

[0342] Output: List of schools of choice.

[0343] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0344] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0345] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0346] [Second embodiment]

[0347] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0348] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0349] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0350] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0351] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0352] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0353] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0354] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0355] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0356] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0357] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0358] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0359] The present invention is a system that utilizes a generative artificial intelligence model to analyze a student's learning proficiency, provide an effective study plan, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0360] First, a student (user) logs in to a device and prepares to take the test. The device displays test questions, and the student enters their answers. The entered answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the student's heart rate and gaze data, which are then sent to the server in parallel.

[0361] When the server receives the student's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the student chose that answer. It also analyzes physiological data, assessing stress levels during the exam from heart rate and eye movements. Based on this data, the student's learning proficiency and comprehension are evaluated.

[0362] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects or topics appearing in exams. Combining the student's analysis with this exam trend data, a personalized study plan is generated for each student. The study plan details which topics to focus on and the order in which they should be studied.

[0363] The server then periodically collects and evaluates the student's learning progress data and compares it with the entrance exam data of the schools of their choice to calculate a match score. Based on this match score, the server suggests the most suitable schools for the student. These suggestions are sent to the student's device and displayed for the student to review. The suggested list of schools includes each school's characteristics, past admissions records, and advice based on the student's strengths and weaknesses.

[0364] For example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if a student takes a long time to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0365] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0366] This invention allows students to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[0367] The processing flow will be explained below.

[0368] Step 1:

[0369] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and an eye tracker.

[0370] Step 2:

[0371] The device transmits the student's answer data and physiological data in real time to a server, including the time it takes to answer each question, heart rate, and eye movements.

[0372] Step 3:

[0373] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer's time, background, and generation process.

[0374] Step 4:

[0375] The server analyzes the physiological data and assesses the student's stress level based on their heart rate and gaze data, and the results of this analysis are stored together with the student's answer data.

[0376] Step 5:

[0377] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, the topic will be identified as a weak point.

[0378] Step 6:

[0379] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze exam trends, revealing the frequency and patterns of appearance of specific subjects and topics.

[0380] Step 7:

[0381] The server combines the student's learning proficiency assessment results with analysis of past exam questions to generate a personalized learning plan, which outlines the topics to focus on and the learning priorities.

[0382] Step 8:

[0383] The server sends the generated learning plan to the terminal, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan.

[0384] Step 9:

[0385] The server periodically collects and evaluates student progress data, including which topics have been covered and to what extent.

[0386] Step 10:

[0387] The server calculates a match score for each school based on the school's entrance exam data and the student's learning progress data. The match score indicates the degree to which the student's learning status matches the school's requirements.

[0388] Step 11:

[0389] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[0390] Step 12:

[0391] The student user checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final preferred school.

[0392] Example 1

[0393] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0394] In the past, understanding students' learning proficiency and providing individualized learning plans required extensive time-consuming and laborious instruction and intervention. It was also difficult for students to accurately assess their own learning progress and stress levels, making it difficult to create effective learning plans and select the most appropriate schools. Furthermore, analyzing the question trends for specific topics one by one was time-consuming and hindered efficient learning. The goal of this project is to solve these problems and provide learning support tailored to each student.

[0395] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0396] In this invention, the server includes means for analyzing a user's test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the user's learning proficiency and comprehension, means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the user's stress level, means for automatically generating a study plan for each user, means for understanding the question trends for specific topics using a database of past test questions, means for analyzing the user's study progress data and calculating a match score with the entrance examination data of desired institutions, and means for suggesting desired institutions based on the match score, thereby enabling the provision of an individualized study plan, efficient learning, and the selection of the most suitable desired school.

[0397] A "generative artificial intelligence model" is a type of artificial intelligence that analyzes users' test response data and physiological data to evaluate their learning proficiency, comprehension, and stress level.

[0398] "Test answer data" refers to data that includes answer information entered by a user during an exam or test and the time it took to answer the answer.

[0399] "Learning proficiency" is an index that indicates to what extent the user has understood and mastered the learning content.

[0400] "Understanding" is a measure of how deeply a user understands a particular topic or subject.

[0401] "Physiological data" refers to data that indicates the user's physical and physiological state, such as heart rate, eye movement, and skin potential.

[0402] "Stress level" is an index that evaluates the degree of stress that the user feels during the test.

[0403] A "study plan" is a plan created by a user that includes specific topics and a timetable to help the user study efficiently.

[0404] "Exam trends" are the result of analyzing the frequency with which specific topics and subjects are tested using a database of past exam questions.

[0405] "Study progress data" is data that indicates the progress of the user's current learning activities and past learning history.

[0406] The "match score" is calculated based on the user's learning progress data and the entrance examination data of the institution of their choice, and indicates how well the user matches up with the institution.

[0407] "Desired institution" refers to the educational institution or school that the user wishes to attend or take the entrance exam for.

[0408] "Device" refers to the device a user uses to take a test or collect physiological data, including a computer, tablet, or smartphone.

[0409] "Analysis" is the act of analyzing collected data using computational processes and models to extract meaningful information.

[0410] "Automatic generation" refers to the process in which a system automatically creates plans and proposals based on data without human intervention.

[0411] The present invention is a system that utilizes a generative artificial intelligence model to analyze a user's learning proficiency, provide an effective study plan, and suggest the most suitable institution for the user. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0412] First, the user logs in to the device and prepares to take the test. The device displays test questions, and the user inputs their answers. The input answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the user's heart rate and gaze data, which are then sent to the server in parallel.

[0413] When the server receives the user's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the user chose that answer. It also analyzes physiological data, assessing stress levels during the test from heart rate and eye movements. Based on this data, the user's learning proficiency and comprehension are evaluated.

[0414] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of questions on specific subjects or topics. Combining the results of the user's analysis with this exam trend data, a personalized study plan is generated for each user. The study plan specifies which topics to focus on and in what order they should be studied.

[0415] The server then periodically collects and evaluates the user's learning progress data, compares it with the entrance exam data of the institutions of their choice, and calculates a match score. Based on this match score, the server suggests the most suitable institutions for the user. These suggestions are sent to the device and displayed for the user to review. The list of suggested institutions includes information such as each institution's characteristics, past success rates, and advice based on the user's strengths and weaknesses.

[0416] For example, when a user takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if an integer problem takes a long time to answer and is answered incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the user. Furthermore, after determining from heart rate data that the user was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0417] Furthermore, the system calculates a relevance score based on the entrance exam trend data of the institution the user is applying to, and suggests institutions where the user has a high chance of passing based on their current learning status. For example, it suggests institutions where many users with similar tendencies have passed in the past.

[0418] Examples of prompts include:

[0419] "Analyze solutions to math integer problems, identify your weaknesses, and suggest next study plans."

[0420] "Analyze users' heart rate data to assess their stress levels during the exam and plan their study accordingly."

[0421] "Use past exam data to suggest the best institutions for this user."

[0422] The present invention allows users to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable institution of choice, allowing users to effectively prepare for further education.

[0423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0424] Step 1:

[0425] The user logs in to the terminal and prepares for the test.

[0426] Specifically, the user enters their ID and password into the login screen on the device and clicks the "Login" button. The entered login information is sent by the device to the server, and the server performs authentication. If authentication is successful, the device displays a test preparation screen.

[0427] Input: User login information (ID, password)

[0428] Output: Show test preparation screen

[0429] Step 2:

[0430] The user starts the test and enters the answers.

[0431] The device displays pre-prepared test questions on the screen. The user enters answers to each question and clicks the "Submit" button. The device records the user's answer data and the elapsed time from when the start button was pressed, and sends them to the server in real time.

[0432] Input: User test answer data, answer time

[0433] Output: Answer data and time information sent to the server

[0434] Step 3:

[0435] The device collects physiological data.

[0436] The heart rate sensor and gaze tracker connected to the device are activated to collect the user's heart rate data and gaze data in real time, which are then sent to the server.

[0437] Input: User's heart rate data, gaze data

[0438] Output: Heart rate data and gaze data sent to the server

[0439] Step 4:

[0440] The server analyzes the answer data and physiological data.

[0441] The server analyzes the received answer data and physiological data using a generative artificial intelligence model. Specifically, the AI ​​model processes the data to evaluate the user's learning proficiency and comprehension based on the time it took to answer, the context of the answer, heart rate, and gaze data.

[0442] Input: Answer data, heart rate data, gaze data

[0443] Output: User's learning proficiency, comprehension, and stress level evaluation results

[0444] Step 5:

[0445] The server generates a lesson plan.

[0446] The server compares the analysis results with a database of past exam questions and generates a customized study plan, including the topics to focus on and the order in which to study them. The system analyzes the frequency and patterns of questions on specific topics to determine which areas to study and in what order.

[0447] Input: learning proficiency, comprehension, stress level assessment results, past exam question data

[0448] Output: personalized learning plan

[0449] Step 6:

[0450] The server collects the learning progress data and calculates the relevance score.

[0451] The server periodically collects the user's learning progress data and compares it with the entrance exam data of the institution of choice to calculate a matching score. This process includes a function to match past learning data with entrance exam data using an SQL database.

[0452] Input: User's learning progress data, entrance exam data for desired institutions

[0453] Output: Relevance score

[0454] Step 7:

[0455] The server will suggest the most suitable institution for you to apply to.

[0456] The server then creates a list of the most suitable institutions for the user based on the relevance score. This list includes information about each institution's characteristics, past success rates, and advice on the user's strengths and weaknesses. This information is sent to the user's device for easy review.

[0457] Input: Matching score, desired institution data

[0458] Output: A list of preferred institutions sent to the user

[0459] (Application example 1)

[0460] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0461] With conventional methods for skill proficiency assessment and creating learning plans, it has been difficult to provide optimal learning plans that take into account the individual characteristics and stress levels of each worker. Furthermore, while detailed analysis, including work trends and physiological data, is necessary for efficient skill improvement, performing this manually is not practical. A system that can solve this problem is needed.

[0462] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0463] In this invention, the server includes means for analyzing the test answer data of the worker using a generative artificial intelligence model, and analyzing the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the worker's skill proficiency and understanding based on the evaluation results, and means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the worker's stress level. This makes it possible to provide a skill improvement plan based on the individual characteristics of the worker, enabling efficient learning and skill improvement.

[0464] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information based on input data.

[0465] "Test answer data" refers to answer information for test questions answered by a worker.

[0466] "Answering time" is the time it takes a worker to answer a particular test question.

[0467] "Background of the answer" refers to the process by which the worker arrived at the answer and the thinking behind it.

[0468] "Physiological data" refers to data that indicates the worker's physical condition, such as heart rate or eye tracking data.

[0469] "Stress level" refers to the degree of psychological or physiological stress experienced by an operator during a task or test.

[0470] "Skill proficiency" is an indicator that shows how well a worker has mastered a particular skill.

[0471] "Skills improvement plan" refers to a learning and training plan to effectively improve the skills of workers.

[0472] "Work trends" is information obtained by analyzing the work patterns, frequency, and content that a worker has performed in the past.

[0473] A "fit score" is an index that evaluates how well a worker's skills and characteristics are suited to a particular training program.

[0474] A "training program" is a specific plan of training and learning activities aimed at improving worker skills.

[0475] This invention is a system for efficiently improving the skills of factory workers, which utilizes a generative artificial intelligence model to analyze the skill proficiency of workers, provide an effective skill improvement plan, and propose an optimal training program. This system is implemented through a series of operations involving terminals, a server, and workers.

[0476] First, the worker (user) logs in to the terminal and prepares to take the test. The terminal displays the test questions, and the worker enters the answers. The answered data is sent to the server in real time. In addition, the worker's heart rate and gaze data are also collected by physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the terminal and sent to the server in parallel.

[0477] When the server receives the worker's test answer data, it begins analysis using a generative artificial intelligence model. The AI ​​model analyzes the time it takes to answer, the background to the answer, and the process by which it was generated to understand why the worker chose that answer. It also analyzes physiological data, assessing the worker's stress level during work from heart rate and eye movement. Based on this data, the worker's skill proficiency and level of understanding are evaluated.

[0478] The server then analyzes past work data and uses a generative artificial intelligence model to analyze past work patterns, identifying the frequency and patterns of specific tasks and processes. Combining the worker's analysis results with this work trend data generates a personalized skill development plan for each worker. The skill development plan specifies which topics to focus on and in what order they should be studied.

[0479] The server then periodically collects and evaluates the worker's learning progress data, compares it with the data from the adapted program, and calculates a compatibility score. Based on this compatibility score, the server suggests the best training program for the worker. These suggestions are sent to the terminal and displayed for the worker to review. The list of suggested training programs includes advice based on each program's features, past success, and the worker's strengths and weaknesses.

[0480] As a specific example, when a worker takes a robot operation test, the terminal sends the answers to a server, which uses a generative artificial intelligence model to analyze the answer process for each question. For example, if a worker takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as the worker's weakness. Furthermore, after confirming that the worker was in a high-stress state based on heart rate data, the AI ​​individually creates a plan for the next skill improvement, including stress control methods.

[0481] Furthermore, a compatibility score is calculated based on the trend data of the training program that the worker wishes to participate in, and a training program that is highly compatible with the worker's current skill level is suggested. For example, a training program that has been successful in the past for many workers with similar tendencies will be suggested.

[0482] An example of a prompt sentence is, "Analyze worker A's answer data and physiological data to identify his stress level and weaknesses. Based on the results, generate an optimal robot operation learning plan."

[0483] This allows workers to accurately grasp their own skill status and create efficient skill improvement plans. Furthermore, the process of selecting the most suitable training program is streamlined, enabling effective preparation for skill improvement.

[0484] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0485] Step 1:

[0486] A user logs in to a terminal and prepares to take a test. The terminal displays test questions, and the user inputs answers. The input data here is the user's answer data, which is obtained through the terminal's display and input interface. The output data is the answer data sent to the server in real time.

[0487] Step 2:

[0488] Physiological data of the user is collected using a physiological data collection device (e.g., a heart rate sensor or gaze tracker) connected to the terminal. The collected data (heart rate data and gaze data) is transmitted to the server in real time. The input data of this step are various physiological data, and the output data is the physiological data transmitted to the server.

[0489] Step 3:

[0490] The server uses a generative artificial intelligence model to analyze the user's test answer data. Specifically, it analyzes the time it takes to answer, the background of the answer, and the process by which the answer was generated. The input data here is the answer data sent from the device, and the output data is the analysis results. This analysis helps understand why the user chose that answer.

[0491] Step 4:

[0492] The server analyzes the physiological data and evaluates the user's stress level based on their heart rate and eye movements. The input data is the physiological data, and the output data is the stress level evaluation result. This result indicates the degree of psychological and physiological stress on the user.

[0493] Step 5:

[0494] The server evaluates the user's skill proficiency and understanding based on the analysis results. The input data are the analysis results of the test answer data and the evaluation results of the physiological data, and the output data are the evaluation results of the skill proficiency and understanding. This evaluation indicates the user's current skill level and understanding.

[0495] Step 6:

[0496] The server analyzes past work data and uses a generative artificial intelligence model to understand past work patterns. The input data is past work data, and the output data is information indicating work trends. This reveals the frequency and patterns of specific work content and processes.

[0497] Step 7:

[0498] The server combines the skill proficiency and comprehension assessment results with the work tendency data to generate a personalized skill improvement plan for each user. The input data are the skill proficiency and comprehension assessment results and the work tendency data, and the output data is the personalized skill improvement plan. This plan specifies which topics should be studied intensively and in what order.

[0499] Step 8:

[0500] The server periodically collects the user's learning progress data, compares it with the data of the adaptive program, and calculates a matching score. The input data are the learning progress data and the data of the adaptive program, and the output data is the matching score. Based on this score, an optimal training program is suggested to the user.

[0501] Step 9:

[0502] The server proposes optimal training programs based on the relevance scores and sends the list to the terminal. The input data is the relevance scores, and the output data is a list of proposed training programs. The user can view this list through the terminal.

[0503] For example, when a user takes a robot operation test, the device sends the answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a user takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the underlying thought process and identifies that topic as the user's weak point. This analysis result is combined with heart rate data to create an optimal individual skill improvement plan.

[0504] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0505] The present invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0506] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[0507] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[0508] The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer, including the time it took, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data to assess the student's stress level from heart rate and gaze data, and further evaluates their emotional state. The results of this analysis are saved together with the student's answer data.

[0509] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if a student's comprehension of a particular topic is low, that topic is identified as a weak point. The server also uses an emotion engine to monitor changes in the student's emotions while they are studying. If stress or a decline in interest is detected, the server will revise the student's learning plan.

[0510] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student's analysis with this exam trend data generates a personalized study plan for each student. The study plan outlines the topics to focus on and the learning priorities.

[0511] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan. During the study, the emotion engine continuously monitors the student's emotional state, and the learning plan is adjusted as necessary.

[0512] Furthermore, the server periodically collects and evaluates the student's learning progress data. The learning progress data includes which topics have been covered and to what extent. Based on the learning progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's learning status and the requirements of the desired school.

[0513] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[0514] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0515] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0516] This invention allows students to accurately grasp their own learning and emotional state, allowing them to create an efficient study plan. It also streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through a heart rate sensor and gaze tracker, and also collects facial expression and voice data using an emotion engine.

[0520] Step 2:

[0521] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[0522] Step 3:

[0523] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer, including the time it took to complete it, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data, such as heart rate and gaze data, to assess the student's stress level and emotional state.

[0524] Step 4:

[0525] The server evaluates the student's learning proficiency and comprehension based on these analysis results. If a student's understanding of a particular topic is low, that topic will be identified as a weak point. Furthermore, if the analysis using the emotion engine detects stress or a loss of interest, that data will also be reflected in the evaluation.

[0526] Step 5:

[0527] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions in specific subjects and topics.

[0528] Step 6:

[0529] The server combines the student's analysis results with past exam question analysis data to generate a personalized study plan, which includes topics to focus on and priorities for learning. It also suggests stress-reducing study methods based on emotional data.

[0530] Step 7:

[0531] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan, and the emotion engine continues to monitor the student's emotional state while they are studying.

[0532] Step 8:

[0533] The server periodically collects and evaluates students' learning progress data, including which topics have been covered and to what extent. An emotion engine keeps track of students' emotional states.

[0534] Step 9:

[0535] The server calculates a match score based on the student's learning progress data and the entrance exam data of the school of choice. This match score indicates the degree of match between the student's learning status and the requirements of the school of choice.

[0536] Step 10:

[0537] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[0538] Step 11:

[0539] The user, a student, checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list of preferred schools includes feedback based on each school's characteristics, past acceptance records, and the student's emotional state. Based on this information, the student selects their final preferred school.

[0540] Example 2

[0541] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0542] Conventional learning systems have difficulty accurately assessing students' learning proficiency and comprehension, making it difficult to provide optimal learning plans for each student. Furthermore, they are unable to create learning plans that reflect physiological and emotional data, and lack the ability to provide adaptive learning programs that take into account students' stress and emotional states. Furthermore, they are also inadequate in suggesting specific schools to attend based on learning progress data and school entrance exam data.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0544] In this invention, the server includes a means for analyzing educator evaluation data using a generative artificial intelligence model to analyze the time required to answer questions, the background of the answers, and the process by which the answers were generated; a means for evaluating students' learning proficiency and comprehension; and a means for collecting and analyzing biometric data to evaluate students' stress levels. This enables accurate assessment of students' learning proficiency and comprehension and provides optimal learning plans for each student. Furthermore, by incorporating data obtained from a heart rate sensor and gaze tracker, and facial expression and voice data obtained using an emotion engine, it is possible to provide adaptive learning programs that take students' stress and emotional state into account. It is also possible to calculate a match score between learning progress data and university entrance exam data and suggest specific universities to attend.

[0545] A "generative artificial intelligence model" is a type of artificial intelligence used to analyze students' test response data and analyze the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[0546] "Assessment data" refers to data including student test response data, physiological data, and emotional data.

[0547] "Biometric data" refers to data obtained from heart rate sensors and eye trackers, which are used to assess students' stress levels and emotional states.

[0548] The "emotion engine" is a means of analyzing facial expression and voice data to assess a student's emotional state.

[0549] "Learning proficiency" is an indicator that shows the student's level of understanding of the content they have learned and their level of skill acquisition.

[0550] "Understanding" is an indicator of how well a student understands a particular topic or subject.

[0551] A "study plan" is a study schedule that sets out the optimal learning methods and content, taking into account the student's learning proficiency and comprehension, stress level, and emotional state.

[0552] A "heart rate sensor" is a device for measuring a student's heart rate.

[0553] An "eye tracker" is a device used to track students' eye movements.

[0554] "Facial expression data" is data that records and analyzes changes in students' facial expressions.

[0555] "Voice Data" refers to data that records and analyzes the tone and patterns of a student's voice.

[0556] An "adaptive learning plan" is a learning program that dynamically adjusts according to a student's real-time learning situation and emotional state.

[0557] "Progress data" is data that indicates how far a student has progressed in their studies.

[0558] "Entrance exam data" refers to data related to the entrance exam requirements and question trends of the school to which students wish to advance.

[0559] The "match score" is a score that indicates the degree of match between the student's learning data and the entrance examination data of the school they are going to.

[0560] The "school destination list" is a list of schools suggested based on the compatibility score.

[0561] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school for them to apply to. This system is implemented through a series of operations involving terminals, a server, and users.

[0562] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device is connected to devices such as a heart rate sensor, gaze tracker, and microphone, which collect physiological and emotional data in real time. For example, the heart rate sensor obtains the student's heart rate, the gaze tracker captures eye movements, and the camera and microphone collect facial expressions and voice.

[0563] The device transmits the user's answer data, physiological data, and emotional data to the server. The collected data includes the time it took to answer, the content of the answer, heart rate, eye movements, facial expressions, and voice tone. During this transmission process, the data is encrypted to ensure security. For example, the device performs batch processing at regular intervals and transmits the data to the server all at once.

[0564] The server inputs the received data into a generative AI model and begins analysis. The generative AI model analyzes the educator's evaluation data, digging deep into the time it took to answer the questions, the background, and the process by which they were generated. It also uses an emotion engine to analyze heart rate, gaze data, facial expression changes, and voice tone to assess the student's stress level and emotional state. For example, if a particular question takes a long time to answer and the heart rate rises, it can be determined that the question is causing stress.

[0565] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic is identified as a weak point. An emotion engine is used to monitor emotional changes during learning, and if stress or a decline in interest is detected, the learning plan is revised. At this stage, the generated learning plan becomes an adaptive learning program that incorporates heart rate sensors, gaze trackers, facial expression data, and voice data.

[0566] The server then accesses a database of past educational questions and uses a generative artificial intelligence model to analyze question trends, identifying the frequency and patterns of questions on specific subjects and topics. The analysis results are combined with the question trend data to generate a personalized learning plan for each student, which includes topics to focus on and priorities for learning.

[0567] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan. The emotion engine continues to monitor the student's emotional state while they are studying, and the learning plan is adjusted as necessary.

[0568] Furthermore, the server periodically collects and analyzes learning progress data. Based on the analysis results, a match score is calculated with the entrance exam data of the desired school. This match score is an indicator of the degree of match between the student's learning status and the requirements of the desired school. Based on the match score, the server generates a list of schools that are most suitable for the student and sends it to the device. The student can check the list of schools displayed on the device to help them select their preferred schools.

[0569] As a specific example, when a student takes a math test, their device sends physiological and emotional data along with their answers to a server. A generative AI model analyzes the answering process, identifies high-stress states from heart rate and emotional data, and individually creates a study plan for the next test. It also calculates a match score based on the student's desired university entrance exam trends and suggests universities where they have a high chance of being accepted.

[0570] Examples of prompts have the following format:

[0571] "Analyze students' answer data, physiological data (heart rate, gaze data), facial expression data, and voice data to assess their learning proficiency and emotional state. Then, generate an appropriate study plan and suggest the best schools for students."

[0572] This system allows students to accurately grasp their academic and emotional state, allowing them to create efficient study plans, streamline the process of selecting the most suitable school, and effectively prepare for entrance exams.

[0573] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0574] Step 1: User login and start testing

[0575] The user logs in to the terminal. A user ID and password are required as input. The terminal sends this authentication information to the server for authentication. If authentication is successful, the terminal displays a "Test Start" screen. Specifically, the user enters authentication information on the terminal, and the server verifies it to perform authentication. If authentication is successful, a test screen is displayed as output.

[0576] Step 2: Collect user responses and physiological data

[0577] The user enters answers to test questions displayed on the device. The input also includes physiological and emotional data collected using a heart rate sensor, gaze tracker, and microphone. The device collects this data in real time. Specifically, while the user enters answers using a keyboard or touchscreen, the heart rate sensor collects heart rate data, the gaze tracker collects eye movements, and the camera and microphone record facial expressions and tone of voice. The output is the collected answer data, physiological data, and emotional data.

[0578] Step 3: Send data from the device to the server

[0579] The device sends the collected answer data, physiological data, and emotional data to the server. The data collected in the previous step is required as input. The data is encrypted and transferred securely. Specifically, the device batch processes the data at regular intervals (for example, every minute) and uploads it to the server. The output is the data sent to the server.

[0580] Step 4: Data analysis by the server

[0581] The server inputs the received data into a generative artificial intelligence model and analyzes the content, background, and generation process of the answer. Inputs include collected answer data, physiological data, and emotional data. The server analyzes heart rate, gaze data, facial expression changes, and voice tone to evaluate stress levels and emotional states. For example, the server passes the answer data to the AI ​​model to evaluate the time required and accuracy, and further analyzes physiological data to understand the emotional state. The output is the analyzed learning proficiency, comprehension, and emotional state.

[0582] Step 5: Assess your learning proficiency and emotional state

[0583] The server evaluates the student's learning proficiency and comprehension based on the analysis results. The input includes the data analyzed in the previous step. For example, it evaluates the correct answer rate and response time for a specific topic and identifies weak points. It also uses an emotion engine to monitor emotional changes during learning and detect stress or loss of interest. The output is the evaluated learning proficiency and emotional state.

[0584] Step 6: Generate a lesson plan

[0585] The server accesses a database of past educational questions and analyzes question trends using a generative artificial intelligence model. Inputs include the student's learning proficiency and comprehension, and the database of past questions. The server generates an individualized learning plan for each student based on the question trends and analyzed data. For example, it analyzes the frequency and patterns of questions obtained from the database to determine the topics that should be focused on. The output is the generated learning plan.

[0586] Step 7: Provide and display your lesson plan

[0587] The server sends the generated lesson plan to the terminal. The input includes the generated lesson plan. The terminal receives it and displays it to the user. Specifically, the server sends the lesson plan to the terminal, the terminal receives it, and displays the lesson plan on the screen. The output is the lesson plan displayed on the terminal.

[0588] Step 8: Assessment of learning progress and school preference suggestions

[0589] The server periodically collects and analyzes learning progress data. Inputs include learning progress data and entrance exam data. The server compares this data with the entrance exam data of the schools of choice and calculates a matching score. For example, the server analyzes the learning progress data and calculates the degree of match with the entrance exam requirements of the schools of choice. The output is the calculated matching score and a generated list of schools of choice. This list of schools of choice is sent to the terminal and displayed to the user.

[0590] (Application example 2)

[0591] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] Conventional learning management systems have difficulty providing individualized learning plans that fully consider students' learning proficiency and stress levels. Furthermore, they are unable to grasp changes in students' emotional states in real time and provide learning support based on this, which can lead to students feeling stressed or losing motivation to study. Furthermore, they lack efficient suggestions based on appropriate data analysis when selecting a school of choice.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing students' test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer; means for evaluating the students' learning proficiency and comprehension based on the analysis results; means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the students' stress levels; means for collecting students' facial expression data and voice data using an emotion engine to analyze their emotional states; and means for automatically generating individual study plans for each student based on the analysis results and emotional data, and providing the study plans including stress control methods. This enables a comprehensive evaluation of students' learning proficiency and emotional states, enabling efficient and personalized study support.

[0594] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes students' test response data and analyzes the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[0595] "Learning proficiency" is an indicator of how much a student understands and has mastered a particular topic or subject.

[0596] "Understanding" is a measure of how well a student understands a particular issue or topic.

[0597] "Physiological data" refers to data used to measure students' physical reactions and conditions, such as heart rate and gaze data.

[0598] "Stress level" is an indicator of the degree of stress a student feels while studying, assessed based on heart rate, gaze data, etc.

[0599] The "emotion engine" is a technology that analyzes facial expression and voice data to assess a student's emotional state.

[0600] "Automatically generated individualized learning plans that include stress control methods" are learning plans that are optimized based on each student's learning proficiency, stress level, and emotional state, and also incorporate stress reduction techniques.

[0601] A "suitability score" is a number that indicates how well a student is suited to their desired school by comparing their learning progress data with the entrance examination data of the school.

[0602] The "School of Choice List" is a list of schools that suggests the most suitable schools for students based on their compatibility scores.

[0603] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school of choice.

[0604] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[0605] The device transmits the student's answer data, physiological data, and emotional data to the server in real time. The transmitted data includes the time taken for each answer, heart rate, eye movements, facial expressions, and voice tone. The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer's time taken, the background of the answer, and the process by which it was generated. Furthermore, based on the physiological and emotional data, the system evaluates the student's stress level from heart rate and eye gaze data, as well as their emotional state.

[0606] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic will be identified as a weak point. The server also uses an emotion engine to monitor the student's emotional changes while they are studying, and if stress or a decline in interest is detected, the learning plan will be revised.

[0607] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student analysis with this exam trend data, a personalized study plan is generated for each student. The study plan outlines the topics to focus on and the learning priorities.

[0608] The server sends the generated study plan to the terminal and displays it to the student. The student then studies according to the study plan. During the study, the emotion engine continuously monitors the student's emotional state, and the study plan is adjusted as necessary. In addition, the server periodically collects and evaluates the student's study progress data. The study progress data includes which topics have been covered and to what extent. Based on the study progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's study state and the requirements of the desired school.

[0609] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[0610] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0611] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0612] An example of a prompt for the generative AI model is as follows:

[0613] Prompt statement:

[0614] [Student answer data] [Physiological data] [Emotional data]

[0615] for example:

[0616] "Answer: 4, Time taken: 30 seconds, Heart rate: 80, Gaze data: Concentrated, Emotion data: Neutral"

[0617] Based on the above data, evaluate your learning proficiency and stress level and create your next study plan.

[0618] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0619] Step 1:

[0620] The user logs in to the device and begins the test. The user enters answers to the test questions displayed on the device. During this process, the device collects physiological data using a heart rate sensor and gaze tracker. The device also collects facial expression and voice data using a microphone and camera.

[0621] Input: Test questions, answers, heart rate, physiological data, facial expression data, and voice data.

[0622] Output: Answer data, physiological data, emotional data.

[0623] Step 2:

[0624] The device transmits the collected data (answer data, physiological data, and emotional data) in real time to a server, which then receives the data for analysis.

[0625] Input: Answer data, physiological data, emotional data.

[0626] Output: Transmit data.

[0627] Step 3:

[0628] The server inputs the received answer data into the generative AI model and begins analysis, which examines in detail the time required to reach the answer, the background of the answer, and the process by which it was generated.

[0629] Input: Answer data.

[0630] Output: Analysis results (time required to get the answer, background of the answer, and how it was generated).

[0631] Step 4:

[0632] The server simultaneously analyzes physiological and emotional data, assessing students' stress levels based on their heart rate and gaze data, and using an emotion engine to assess their emotional state based on facial expression and voice data.

[0633] Input: physiological data, emotional data.

[0634] Output: Stress level, emotional state.

[0635] Step 5:

[0636] The server evaluates the student's learning proficiency and comprehension based on the analysis results of steps 3 and 4. This allows the server to understand how well the student has mastered a particular topic.

[0637] Input: Analysis results of answer data, stress level, emotional state.

[0638] Output: learning proficiency, comprehension.

[0639] Step 6:

[0640] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions on specific subjects and topics.

[0641] Input: Past exam question data.

[0642] Output: Question trend data.

[0643] Step 7:

[0644] The server combines the results of the learning proficiency and comprehension assessment in Step 5 with the question trend data in Step 6 to generate an individualized learning plan for each student, including the topics to focus on and learning priorities.

[0645] Input: learning proficiency, comprehension, and question trend data.

[0646] Output: Learning plan.

[0647] Step 8:

[0648] The server sends the generated learning plan to the terminal and notifies the student. The student then proceeds with their studies according to the learning plan displayed on the terminal.

[0649] Input: lesson plan.

[0650] Output: The displayed lesson plan.

[0651] Step 9:

[0652] During learning, the emotion engine continues to monitor the student's emotional state, and the server adjusts the learning plan as needed and sends it back to the device.

[0653] Input: Changes in emotional state.

[0654] Output: A tailored lesson plan.

[0655] Step 10:

[0656] The server periodically collects and analyzes the student's learning progress data, and calculates a match score with the entrance exam data of the school of choice based on the learning progress data.

[0657] Input: Learning progress data, entrance exam data for desired school.

[0658] Output: Relevance score.

[0659] Step 11:

[0660] The server generates a list of schools that best suit the student based on the relevance score, sends it to the terminal, and displays it. The student user then uses the list of schools displayed on the terminal to select their final school of choice.

[0661] Input: Relevance score.

[0662] Output: List of schools of choice.

[0663] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0664] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0665] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0666] [Third embodiment]

[0667] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0668] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0669] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0670] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0671] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0672] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0673] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0674] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0675] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0676] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0677] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0678] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0679] The present invention is a system that utilizes a generative artificial intelligence model to analyze a student's learning proficiency, provide an effective study plan, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0680] First, a student (user) logs in to a device and prepares to take the test. The device displays test questions, and the student enters their answers. The entered answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the student's heart rate and gaze data, which are then sent to the server in parallel.

[0681] When the server receives the student's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the student chose that answer. It also analyzes physiological data, assessing stress levels during the exam from heart rate and eye movements. Based on this data, the student's learning proficiency and comprehension are evaluated.

[0682] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects or topics appearing in exams. Combining the student's analysis with this exam trend data, a personalized study plan is generated for each student. The study plan details which topics to focus on and the order in which they should be studied.

[0683] The server then periodically collects and evaluates the student's learning progress data and compares it with the entrance exam data of the schools of their choice to calculate a match score. Based on this match score, the server suggests the most suitable schools for the student. These suggestions are sent to the student's device and displayed for the student to review. The suggested list of schools includes each school's characteristics, past admissions records, and advice based on the student's strengths and weaknesses.

[0684] For example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if a student takes a long time to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0685] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0686] This invention allows students to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[0687] The processing flow will be explained below.

[0688] Step 1:

[0689] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and an eye tracker.

[0690] Step 2:

[0691] The device transmits the student's answer data and physiological data in real time to a server, including the time it takes to answer each question, heart rate, and eye movements.

[0692] Step 3:

[0693] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer's time, background, and generation process.

[0694] Step 4:

[0695] The server analyzes the physiological data and assesses the student's stress level based on their heart rate and gaze data, and the results of this analysis are stored together with the student's answer data.

[0696] Step 5:

[0697] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, the topic will be identified as a weak point.

[0698] Step 6:

[0699] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze exam trends, revealing the frequency and patterns of appearance of specific subjects and topics.

[0700] Step 7:

[0701] The server combines the student's learning proficiency assessment results with analysis of past exam questions to generate a personalized learning plan, which outlines the topics to focus on and the learning priorities.

[0702] Step 8:

[0703] The server sends the generated learning plan to the terminal, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan.

[0704] Step 9:

[0705] The server periodically collects and evaluates student progress data, including which topics have been covered and to what extent.

[0706] Step 10:

[0707] The server calculates a match score for each school based on the school's entrance exam data and the student's learning progress data. The match score indicates the degree to which the student's learning status matches the school's requirements.

[0708] Step 11:

[0709] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[0710] Step 12:

[0711] The student user checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final preferred school.

[0712] Example 1

[0713] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0714] In the past, understanding students' learning proficiency and providing individualized learning plans required extensive time-consuming and laborious instruction and intervention. It was also difficult for students to accurately assess their own learning progress and stress levels, making it difficult to create effective learning plans and select the most appropriate schools. Furthermore, analyzing the question trends for specific topics one by one was time-consuming and hindered efficient learning. The goal of this project is to solve these problems and provide learning support tailored to each student.

[0715] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0716] In this invention, the server includes means for analyzing a user's test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the user's learning proficiency and comprehension, means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the user's stress level, means for automatically generating a study plan for each user, means for understanding the question trends for specific topics using a database of past test questions, means for analyzing the user's study progress data and calculating a match score with the entrance examination data of desired institutions, and means for suggesting desired institutions based on the match score, thereby enabling the provision of an individualized study plan, efficient learning, and the selection of the most suitable desired school.

[0717] A "generative artificial intelligence model" is a type of artificial intelligence that analyzes users' test response data and physiological data to evaluate their learning proficiency, comprehension, and stress level.

[0718] "Test answer data" refers to data that includes answer information entered by a user during an exam or test and the time it took to answer the answer.

[0719] "Learning proficiency" is an index that indicates to what extent the user has understood and mastered the learning content.

[0720] "Understanding" is a measure of how deeply a user understands a particular topic or subject.

[0721] "Physiological data" refers to data that indicates the user's physical and physiological state, such as heart rate, eye movement, and skin potential.

[0722] "Stress level" is an index that evaluates the degree of stress that the user feels during the test.

[0723] A "study plan" is a plan created by a user that includes specific topics and a timetable to help the user study efficiently.

[0724] "Exam trends" are the result of analyzing the frequency with which specific topics and subjects are tested using a database of past exam questions.

[0725] "Study progress data" is data that indicates the progress of the user's current learning activities and past learning history.

[0726] The "match score" is calculated based on the user's learning progress data and the entrance examination data of the institution of their choice, and indicates how well the user matches up with the institution.

[0727] "Desired institution" refers to the educational institution or school that the user wishes to attend or take the entrance exam for.

[0728] "Device" refers to the device a user uses to take a test or collect physiological data, including a computer, tablet, or smartphone.

[0729] "Analysis" is the act of analyzing collected data using computational processes and models to extract meaningful information.

[0730] "Automatic generation" refers to the process in which a system automatically creates plans and proposals based on data without human intervention.

[0731] The present invention is a system that utilizes a generative artificial intelligence model to analyze a user's learning proficiency, provide an effective study plan, and suggest the most suitable institution for the user. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0732] First, the user logs in to the device and prepares to take the test. The device displays test questions, and the user inputs their answers. The input answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the user's heart rate and gaze data, which are then sent to the server in parallel.

[0733] When the server receives the user's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the user chose that answer. It also analyzes physiological data, assessing stress levels during the test from heart rate and eye movements. Based on this data, the user's learning proficiency and comprehension are evaluated.

[0734] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of questions on specific subjects or topics. Combining the results of the user's analysis with this exam trend data, a personalized study plan is generated for each user. The study plan specifies which topics to focus on and in what order they should be studied.

[0735] The server then periodically collects and evaluates the user's learning progress data, compares it with the entrance exam data of the institutions of their choice, and calculates a match score. Based on this match score, the server suggests the most suitable institutions for the user. These suggestions are sent to the device and displayed for the user to review. The list of suggested institutions includes information such as each institution's characteristics, past success rates, and advice based on the user's strengths and weaknesses.

[0736] For example, when a user takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if an integer problem takes a long time to answer and is answered incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the user. Furthermore, after determining from heart rate data that the user was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0737] Furthermore, the system calculates a relevance score based on the entrance exam trend data of the institution the user is applying to, and suggests institutions where the user has a high chance of passing based on their current learning status. For example, it suggests institutions where many users with similar tendencies have passed in the past.

[0738] Examples of prompts include:

[0739] "Analyze solutions to math integer problems, identify your weaknesses, and suggest next study plans."

[0740] "Analyze users' heart rate data to assess their stress levels during the exam and plan their study accordingly."

[0741] "Use past exam data to suggest the best institutions for this user."

[0742] The present invention allows users to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable institution of choice, allowing users to effectively prepare for further education.

[0743] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0744] Step 1:

[0745] The user logs in to the terminal and prepares for the test.

[0746] Specifically, the user enters their ID and password into the login screen on the device and clicks the "Login" button. The entered login information is sent by the device to the server, and the server performs authentication. If authentication is successful, the device displays a test preparation screen.

[0747] Input: User login information (ID, password)

[0748] Output: Show test preparation screen

[0749] Step 2:

[0750] The user starts the test and enters the answers.

[0751] The device displays pre-prepared test questions on the screen. The user enters answers to each question and clicks the "Submit" button. The device records the user's answer data and the elapsed time from when the start button was pressed, and sends them to the server in real time.

[0752] Input: User test answer data, answer time

[0753] Output: Answer data and time information sent to the server

[0754] Step 3:

[0755] The device collects physiological data.

[0756] The heart rate sensor and gaze tracker connected to the device are activated to collect the user's heart rate data and gaze data in real time, which are then sent to the server.

[0757] Input: User's heart rate data, gaze data

[0758] Output: Heart rate data and gaze data sent to the server

[0759] Step 4:

[0760] The server analyzes the answer data and physiological data.

[0761] The server analyzes the received answer data and physiological data using a generative artificial intelligence model. Specifically, the AI ​​model processes the data to evaluate the user's learning proficiency and comprehension based on the time it took to answer, the context of the answer, heart rate, and gaze data.

[0762] Input: Answer data, heart rate data, gaze data

[0763] Output: User's learning proficiency, comprehension, and stress level evaluation results

[0764] Step 5:

[0765] The server generates a lesson plan.

[0766] The server compares the analysis results with a database of past exam questions and generates a customized study plan, including the topics to focus on and the order in which to study them. The system analyzes the frequency and patterns of questions on specific topics to determine which areas to study and in what order.

[0767] Input: learning proficiency, comprehension, stress level assessment results, past exam question data

[0768] Output: personalized learning plan

[0769] Step 6:

[0770] The server collects the learning progress data and calculates the relevance score.

[0771] The server periodically collects the user's learning progress data and compares it with the entrance exam data of the institution of choice to calculate a matching score. This process includes a function to match past learning data with entrance exam data using an SQL database.

[0772] Input: User's learning progress data, entrance exam data for desired institutions

[0773] Output: Relevance score

[0774] Step 7:

[0775] The server will suggest the most suitable institution for you to apply to.

[0776] The server then creates a list of the most suitable institutions for the user based on the relevance score. This list includes information about each institution's characteristics, past success rates, and advice on the user's strengths and weaknesses. This information is sent to the user's device for easy review.

[0777] Input: Matching score, desired institution data

[0778] Output: A list of preferred institutions sent to the user

[0779] (Application example 1)

[0780] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0781] With conventional methods for skill proficiency assessment and creating learning plans, it has been difficult to provide optimal learning plans that take into account the individual characteristics and stress levels of each worker. Furthermore, while detailed analysis, including work trends and physiological data, is necessary for efficient skill improvement, performing this manually is not practical. A system that can solve this problem is needed.

[0782] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0783] In this invention, the server includes means for analyzing the test answer data of the worker using a generative artificial intelligence model, and analyzing the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the worker's skill proficiency and understanding based on the evaluation results, and means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the worker's stress level. This makes it possible to provide a skill improvement plan based on the individual characteristics of the worker, enabling efficient learning and skill improvement.

[0784] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information based on input data.

[0785] "Test answer data" refers to answer information for test questions answered by a worker.

[0786] "Answering time" is the time it takes a worker to answer a particular test question.

[0787] "Background of the answer" refers to the process by which the worker arrived at the answer and the thinking behind it.

[0788] "Physiological data" refers to data that indicates the worker's physical condition, such as heart rate or eye tracking data.

[0789] "Stress level" refers to the degree of psychological or physiological stress experienced by an operator during a task or test.

[0790] "Skill proficiency" is an indicator that shows how well a worker has mastered a particular skill.

[0791] "Skills improvement plan" refers to a learning and training plan to effectively improve the skills of workers.

[0792] "Work trends" is information obtained by analyzing the work patterns, frequency, and content that a worker has performed in the past.

[0793] A "fit score" is an index that evaluates how well a worker's skills and characteristics are suited to a particular training program.

[0794] A "training program" is a specific plan of training and learning activities aimed at improving worker skills.

[0795] This invention is a system for efficiently improving the skills of factory workers, which utilizes a generative artificial intelligence model to analyze the skill proficiency of workers, provide an effective skill improvement plan, and propose an optimal training program. This system is implemented through a series of operations involving terminals, a server, and workers.

[0796] First, the worker (user) logs in to the terminal and prepares to take the test. The terminal displays the test questions, and the worker enters the answers. The answered data is sent to the server in real time. In addition, the worker's heart rate and gaze data are also collected by physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the terminal and sent to the server in parallel.

[0797] When the server receives the worker's test answer data, it begins analysis using a generative artificial intelligence model. The AI ​​model analyzes the time it takes to answer, the background to the answer, and the process by which it was generated to understand why the worker chose that answer. It also analyzes physiological data, assessing the worker's stress level during work from heart rate and eye movement. Based on this data, the worker's skill proficiency and level of understanding are evaluated.

[0798] The server then analyzes past work data and uses a generative artificial intelligence model to analyze past work patterns, identifying the frequency and patterns of specific tasks and processes. Combining the worker's analysis results with this work trend data generates a personalized skill development plan for each worker. The skill development plan specifies which topics to focus on and in what order they should be studied.

[0799] The server then periodically collects and evaluates the worker's learning progress data, compares it with the data from the adapted program, and calculates a compatibility score. Based on this compatibility score, the server suggests the best training program for the worker. These suggestions are sent to the terminal and displayed for the worker to review. The list of suggested training programs includes advice based on each program's features, past success, and the worker's strengths and weaknesses.

[0800] As a specific example, when a worker takes a robot operation test, the terminal sends the answers to a server, which uses a generative artificial intelligence model to analyze the answer process for each question. For example, if a worker takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as the worker's weakness. Furthermore, after confirming that the worker was in a high-stress state based on heart rate data, the AI ​​individually creates a plan for the next skill improvement, including stress control methods.

[0801] Furthermore, a compatibility score is calculated based on the trend data of the training program that the worker wishes to participate in, and a training program that is highly compatible with the worker's current skill level is suggested. For example, a training program that has been successful in the past for many workers with similar tendencies will be suggested.

[0802] An example of a prompt sentence is, "Analyze worker A's answer data and physiological data to identify his stress level and weaknesses. Based on the results, generate an optimal robot operation learning plan."

[0803] This allows workers to accurately grasp their own skill status and create efficient skill improvement plans. Furthermore, the process of selecting the most suitable training program is streamlined, enabling effective preparation for skill improvement.

[0804] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0805] Step 1:

[0806] A user logs in to a terminal and prepares to take a test. The terminal displays test questions, and the user inputs answers. The input data here is the user's answer data, which is obtained through the terminal's display and input interface. The output data is the answer data sent to the server in real time.

[0807] Step 2:

[0808] Physiological data of the user is collected using a physiological data collection device (e.g., a heart rate sensor or gaze tracker) connected to the terminal. The collected data (heart rate data and gaze data) is transmitted to the server in real time. The input data of this step are various physiological data, and the output data is the physiological data transmitted to the server.

[0809] Step 3:

[0810] The server uses a generative artificial intelligence model to analyze the user's test answer data. Specifically, it analyzes the time it takes to answer, the background of the answer, and the process by which the answer was generated. The input data here is the answer data sent from the device, and the output data is the analysis results. This analysis helps understand why the user chose that answer.

[0811] Step 4:

[0812] The server analyzes the physiological data and evaluates the user's stress level based on their heart rate and eye movements. The input data is the physiological data, and the output data is the stress level evaluation result. This result indicates the degree of psychological and physiological stress on the user.

[0813] Step 5:

[0814] The server evaluates the user's skill proficiency and understanding based on the analysis results. The input data are the analysis results of the test answer data and the evaluation results of the physiological data, and the output data are the evaluation results of the skill proficiency and understanding. This evaluation indicates the user's current skill level and understanding.

[0815] Step 6:

[0816] The server analyzes past work data and uses a generative artificial intelligence model to understand past work patterns. The input data is past work data, and the output data is information indicating work trends. This reveals the frequency and patterns of specific work content and processes.

[0817] Step 7:

[0818] The server combines the skill proficiency and comprehension assessment results with the work tendency data to generate a personalized skill improvement plan for each user. The input data are the skill proficiency and comprehension assessment results and the work tendency data, and the output data is the personalized skill improvement plan. This plan specifies which topics should be studied intensively and in what order.

[0819] Step 8:

[0820] The server periodically collects the user's learning progress data, compares it with the data of the adaptive program, and calculates a matching score. The input data are the learning progress data and the data of the adaptive program, and the output data is the matching score. Based on this score, an optimal training program is suggested to the user.

[0821] Step 9:

[0822] The server proposes optimal training programs based on the relevance scores and sends the list to the terminal. The input data is the relevance scores, and the output data is a list of proposed training programs. The user can view this list through the terminal.

[0823] For example, when a user takes a robot operation test, the device sends the answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a user takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the underlying thought process and identifies that topic as the user's weak point. This analysis result is combined with heart rate data to create an optimal individual skill improvement plan.

[0824] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0825] The present invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[0826] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[0827] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[0828] The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer, including the time it took, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data to assess the student's stress level from heart rate and gaze data, and further evaluates their emotional state. The results of this analysis are saved together with the student's answer data.

[0829] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if a student's comprehension of a particular topic is low, that topic is identified as a weak point. The server also uses an emotion engine to monitor changes in the student's emotions while they are studying. If stress or a decline in interest is detected, the server will revise the student's learning plan.

[0830] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student's analysis with this exam trend data generates a personalized study plan for each student. The study plan outlines the topics to focus on and the learning priorities.

[0831] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan. During the study, the emotion engine continuously monitors the student's emotional state, and the learning plan is adjusted as necessary.

[0832] Furthermore, the server periodically collects and evaluates the student's learning progress data. The learning progress data includes which topics have been covered and to what extent. Based on the learning progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's learning status and the requirements of the desired school.

[0833] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[0834] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0835] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0836] This invention allows students to accurately grasp their own learning and emotional state, allowing them to create an efficient study plan. It also streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[0837] The processing flow will be explained below.

[0838] Step 1:

[0839] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through a heart rate sensor and gaze tracker, and also collects facial expression and voice data using an emotion engine.

[0840] Step 2:

[0841] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[0842] Step 3:

[0843] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer, including the time it took to complete it, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data, such as heart rate and gaze data, to assess the student's stress level and emotional state.

[0844] Step 4:

[0845] The server evaluates the student's learning proficiency and comprehension based on these analysis results. If a student's understanding of a particular topic is low, that topic will be identified as a weak point. Furthermore, if the analysis using the emotion engine detects stress or a loss of interest, that data will also be reflected in the evaluation.

[0846] Step 5:

[0847] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions in specific subjects and topics.

[0848] Step 6:

[0849] The server combines the student's analysis results with past exam question analysis data to generate a personalized study plan, which includes topics to focus on and priorities for learning. It also suggests stress-reducing study methods based on emotional data.

[0850] Step 7:

[0851] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan, and the emotion engine continues to monitor the student's emotional state while they are studying.

[0852] Step 8:

[0853] The server periodically collects and evaluates students' learning progress data, including which topics have been covered and to what extent. An emotion engine keeps track of students' emotional states.

[0854] Step 9:

[0855] The server calculates a match score based on the student's learning progress data and the entrance exam data of the school of choice. This match score indicates the degree of match between the student's learning status and the requirements of the school of choice.

[0856] Step 10:

[0857] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[0858] Step 11:

[0859] The user, a student, checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list of preferred schools includes feedback based on each school's characteristics, past acceptance records, and the student's emotional state. Based on this information, the student selects their final preferred school.

[0860] Example 2

[0861] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0862] Conventional learning systems have difficulty accurately assessing students' learning proficiency and comprehension, making it difficult to provide optimal learning plans for each student. Furthermore, they are unable to create learning plans that reflect physiological and emotional data, and lack the ability to provide adaptive learning programs that take into account students' stress and emotional states. Furthermore, they are also inadequate in suggesting specific schools to attend based on learning progress data and school entrance exam data.

[0863] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0864] In this invention, the server includes a means for analyzing educator evaluation data using a generative artificial intelligence model to analyze the time required to answer questions, the background of the answers, and the process by which the answers were generated; a means for evaluating students' learning proficiency and comprehension; and a means for collecting and analyzing biometric data to evaluate students' stress levels. This enables accurate assessment of students' learning proficiency and comprehension and provides optimal learning plans for each student. Furthermore, by incorporating data obtained from a heart rate sensor and gaze tracker, and facial expression and voice data obtained using an emotion engine, it is possible to provide adaptive learning programs that take students' stress and emotional state into account. It is also possible to calculate a match score between learning progress data and university entrance exam data and suggest specific universities to attend.

[0865] A "generative artificial intelligence model" is a type of artificial intelligence used to analyze students' test response data and analyze the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[0866] "Assessment data" refers to data including student test response data, physiological data, and emotional data.

[0867] "Biometric data" refers to data obtained from heart rate sensors and eye trackers, which are used to assess students' stress levels and emotional states.

[0868] The "emotion engine" is a means of analyzing facial expression and voice data to assess a student's emotional state.

[0869] "Learning proficiency" is an indicator that shows the student's level of understanding of the content they have learned and their level of skill acquisition.

[0870] "Understanding" is an indicator of how well a student understands a particular topic or subject.

[0871] A "study plan" is a study schedule that sets out the optimal learning methods and content, taking into account the student's learning proficiency and comprehension, stress level, and emotional state.

[0872] A "heart rate sensor" is a device for measuring a student's heart rate.

[0873] An "eye tracker" is a device used to track students' eye movements.

[0874] "Facial expression data" is data that records and analyzes changes in students' facial expressions.

[0875] "Voice Data" refers to data that records and analyzes the tone and patterns of a student's voice.

[0876] An "adaptive learning plan" is a learning program that dynamically adjusts according to a student's real-time learning situation and emotional state.

[0877] "Progress data" is data that indicates how far a student has progressed in their studies.

[0878] "Entrance exam data" refers to data related to the entrance exam requirements and question trends of the school to which students wish to advance.

[0879] The "match score" is a score that indicates the degree of match between the student's learning data and the entrance examination data of the school they are going to.

[0880] The "school destination list" is a list of schools suggested based on the compatibility score.

[0881] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school for them to apply to. This system is implemented through a series of operations involving terminals, a server, and users.

[0882] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device is connected to devices such as a heart rate sensor, gaze tracker, and microphone, which collect physiological and emotional data in real time. For example, the heart rate sensor obtains the student's heart rate, the gaze tracker captures eye movements, and the camera and microphone collect facial expressions and voice.

[0883] The device transmits the user's answer data, physiological data, and emotional data to the server. The collected data includes the time it took to answer, the content of the answer, heart rate, eye movements, facial expressions, and voice tone. During this transmission process, the data is encrypted to ensure security. For example, the device performs batch processing at regular intervals and transmits the data to the server all at once.

[0884] The server inputs the received data into a generative AI model and begins analysis. The generative AI model analyzes the educator's evaluation data, digging deep into the time it took to answer the questions, the background, and the process by which they were generated. It also uses an emotion engine to analyze heart rate, gaze data, facial expression changes, and voice tone to assess the student's stress level and emotional state. For example, if a particular question takes a long time to answer and the heart rate rises, it can be determined that the question is causing stress.

[0885] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic is identified as a weak point. An emotion engine is used to monitor emotional changes during learning, and if stress or a decline in interest is detected, the learning plan is revised. At this stage, the generated learning plan becomes an adaptive learning program that incorporates heart rate sensors, gaze trackers, facial expression data, and voice data.

[0886] The server then accesses a database of past educational questions and uses a generative artificial intelligence model to analyze question trends, identifying the frequency and patterns of questions on specific subjects and topics. The analysis results are combined with the question trend data to generate a personalized learning plan for each student, which includes topics to focus on and priorities for learning.

[0887] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan. The emotion engine continues to monitor the student's emotional state while they are studying, and the learning plan is adjusted as necessary.

[0888] Furthermore, the server periodically collects and analyzes learning progress data. Based on the analysis results, a match score is calculated with the entrance exam data of the desired school. This match score is an indicator of the degree of match between the student's learning status and the requirements of the desired school. Based on the match score, the server generates a list of schools that are most suitable for the student and sends it to the device. The student can check the list of schools displayed on the device to help them select their preferred schools.

[0889] As a specific example, when a student takes a math test, their device sends physiological and emotional data along with their answers to a server. A generative AI model analyzes the answering process, identifies high-stress states from heart rate and emotional data, and individually creates a study plan for the next test. It also calculates a match score based on the student's desired university entrance exam trends and suggests universities where they have a high chance of being accepted.

[0890] Examples of prompts have the following format:

[0891] "Analyze students' answer data, physiological data (heart rate, gaze data), facial expression data, and voice data to assess their learning proficiency and emotional state. Then, generate an appropriate study plan and suggest the best schools for students."

[0892] This system allows students to accurately grasp their academic and emotional state, allowing them to create efficient study plans, streamline the process of selecting the most suitable school, and effectively prepare for entrance exams.

[0893] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0894] Step 1: User login and start testing

[0895] The user logs in to the terminal. A user ID and password are required as input. The terminal sends this authentication information to the server for authentication. If authentication is successful, the terminal displays a "Test Start" screen. Specifically, the user enters authentication information on the terminal, and the server verifies it to perform authentication. If authentication is successful, a test screen is displayed as output.

[0896] Step 2: Collect user responses and physiological data

[0897] The user enters answers to test questions displayed on the device. The input also includes physiological and emotional data collected using a heart rate sensor, gaze tracker, and microphone. The device collects this data in real time. Specifically, while the user enters answers using a keyboard or touchscreen, the heart rate sensor collects heart rate data, the gaze tracker collects eye movements, and the camera and microphone record facial expressions and tone of voice. The output is the collected answer data, physiological data, and emotional data.

[0898] Step 3: Send data from the device to the server

[0899] The device sends the collected answer data, physiological data, and emotional data to the server. The data collected in the previous step is required as input. The data is encrypted and transferred securely. Specifically, the device batch processes the data at regular intervals (for example, every minute) and uploads it to the server. The output is the data sent to the server.

[0900] Step 4: Data analysis by the server

[0901] The server inputs the received data into a generative artificial intelligence model and analyzes the content, background, and generation process of the answer. Inputs include collected answer data, physiological data, and emotional data. The server analyzes heart rate, gaze data, facial expression changes, and voice tone to evaluate stress levels and emotional states. For example, the server passes the answer data to the AI ​​model to evaluate the time required and accuracy, and further analyzes physiological data to understand the emotional state. The output is the analyzed learning proficiency, comprehension, and emotional state.

[0902] Step 5: Assess your learning proficiency and emotional state

[0903] The server evaluates the student's learning proficiency and comprehension based on the analysis results. The input includes the data analyzed in the previous step. For example, it evaluates the correct answer rate and response time for a specific topic and identifies weak points. It also uses an emotion engine to monitor emotional changes during learning and detect stress or loss of interest. The output is the evaluated learning proficiency and emotional state.

[0904] Step 6: Generate a lesson plan

[0905] The server accesses a database of past educational questions and analyzes question trends using a generative artificial intelligence model. Inputs include the student's learning proficiency and comprehension, and the database of past questions. The server generates an individualized learning plan for each student based on the question trends and analyzed data. For example, it analyzes the frequency and patterns of questions obtained from the database to determine the topics that should be focused on. The output is the generated learning plan.

[0906] Step 7: Provide and display your lesson plan

[0907] The server sends the generated lesson plan to the terminal. The input includes the generated lesson plan. The terminal receives it and displays it to the user. Specifically, the server sends the lesson plan to the terminal, the terminal receives it, and displays the lesson plan on the screen. The output is the lesson plan displayed on the terminal.

[0908] Step 8: Assessment of learning progress and school preference suggestions

[0909] The server periodically collects and analyzes learning progress data. Inputs include learning progress data and entrance exam data. The server compares this data with the entrance exam data of the schools of choice and calculates a matching score. For example, the server analyzes the learning progress data and calculates the degree of match with the entrance exam requirements of the schools of choice. The output is the calculated matching score and a generated list of schools of choice. This list of schools of choice is sent to the terminal and displayed to the user.

[0910] (Application example 2)

[0911] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0912] Conventional learning management systems have difficulty providing individualized learning plans that fully consider students' learning proficiency and stress levels. Furthermore, they are unable to grasp changes in students' emotional states in real time and provide learning support based on this, which can lead to students feeling stressed or losing motivation to study. Furthermore, they lack efficient suggestions based on appropriate data analysis when selecting a school of choice.

[0913] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing students' test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer; means for evaluating the students' learning proficiency and comprehension based on the analysis results; means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the students' stress levels; means for collecting students' facial expression data and voice data using an emotion engine to analyze their emotional states; and means for automatically generating individual study plans for each student based on the analysis results and emotional data, and providing the study plans including stress control methods. This enables a comprehensive evaluation of students' learning proficiency and emotional states, enabling efficient and personalized study support.

[0914] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes students' test response data and analyzes the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[0915] "Learning proficiency" is an indicator of how much a student understands and has mastered a particular topic or subject.

[0916] "Understanding" is a measure of how well a student understands a particular issue or topic.

[0917] "Physiological data" refers to data used to measure students' physical reactions and conditions, such as heart rate and gaze data.

[0918] "Stress level" is an indicator of the degree of stress a student feels while studying, assessed based on heart rate, gaze data, etc.

[0919] The "emotion engine" is a technology that analyzes facial expression and voice data to assess a student's emotional state.

[0920] "Automatically generated individualized learning plans that include stress control methods" are learning plans that are optimized based on each student's learning proficiency, stress level, and emotional state, and also incorporate stress reduction techniques.

[0921] A "suitability score" is a number that indicates how well a student is suited to their desired school by comparing their learning progress data with the entrance examination data of the school.

[0922] The "School of Choice List" is a list of schools that suggests the most suitable schools for students based on their compatibility scores.

[0923] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school of choice.

[0924] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[0925] The device transmits the student's answer data, physiological data, and emotional data to the server in real time. The transmitted data includes the time taken for each answer, heart rate, eye movements, facial expressions, and voice tone. The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer's time taken, the background of the answer, and the process by which it was generated. Furthermore, based on the physiological and emotional data, the system evaluates the student's stress level from heart rate and eye gaze data, as well as their emotional state.

[0926] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic will be identified as a weak point. The server also uses an emotion engine to monitor the student's emotional changes while they are studying, and if stress or a decline in interest is detected, the learning plan will be revised.

[0927] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student analysis with this exam trend data, a personalized study plan is generated for each student. The study plan outlines the topics to focus on and the learning priorities.

[0928] The server sends the generated study plan to the terminal and displays it to the student. The student then studies according to the study plan. During the study, the emotion engine continuously monitors the student's emotional state, and the study plan is adjusted as necessary. In addition, the server periodically collects and evaluates the student's study progress data. The study progress data includes which topics have been covered and to what extent. Based on the study progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's study state and the requirements of the desired school.

[0929] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[0930] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[0931] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[0932] An example of a prompt for the generative AI model is as follows:

[0933] Prompt statement:

[0934] [Student answer data] [Physiological data] [Emotional data]

[0935] for example:

[0936] "Answer: 4, Time taken: 30 seconds, Heart rate: 80, Gaze data: Concentrated, Emotion data: Neutral"

[0937] Based on the above data, evaluate your learning proficiency and stress level and create your next study plan.

[0938] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0939] Step 1:

[0940] The user logs in to the device and begins the test. The user enters answers to the test questions displayed on the device. During this process, the device collects physiological data using a heart rate sensor and gaze tracker. The device also collects facial expression and voice data using a microphone and camera.

[0941] Input: Test questions, answers, heart rate, physiological data, facial expression data, and voice data.

[0942] Output: Answer data, physiological data, emotional data.

[0943] Step 2:

[0944] The device transmits the collected data (answer data, physiological data, and emotional data) in real time to a server, which then receives the data for analysis.

[0945] Input: Answer data, physiological data, emotional data.

[0946] Output: Transmit data.

[0947] Step 3:

[0948] The server inputs the received answer data into the generative AI model and begins analysis, which examines in detail the time required to reach the answer, the background of the answer, and the process by which it was generated.

[0949] Input: Answer data.

[0950] Output: Analysis results (time required to get the answer, background of the answer, and how it was generated).

[0951] Step 4:

[0952] The server simultaneously analyzes physiological and emotional data, assessing students' stress levels based on their heart rate and gaze data, and using an emotion engine to assess their emotional state based on facial expression and voice data.

[0953] Input: physiological data, emotional data.

[0954] Output: Stress level, emotional state.

[0955] Step 5:

[0956] The server evaluates the student's learning proficiency and comprehension based on the analysis results of steps 3 and 4. This allows the server to understand how well the student has mastered a particular topic.

[0957] Input: Analysis results of answer data, stress level, emotional state.

[0958] Output: learning proficiency, comprehension.

[0959] Step 6:

[0960] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions on specific subjects and topics.

[0961] Input: Past exam question data.

[0962] Output: Question trend data.

[0963] Step 7:

[0964] The server combines the results of the learning proficiency and comprehension assessment in Step 5 with the question trend data in Step 6 to generate an individualized learning plan for each student, including the topics to focus on and learning priorities.

[0965] Input: learning proficiency, comprehension, and question trend data.

[0966] Output: Learning plan.

[0967] Step 8:

[0968] The server sends the generated learning plan to the terminal and notifies the student. The student then proceeds with their studies according to the learning plan displayed on the terminal.

[0969] Input: lesson plan.

[0970] Output: The displayed lesson plan.

[0971] Step 9:

[0972] During learning, the emotion engine continues to monitor the student's emotional state, and the server adjusts the learning plan as needed and sends it back to the device.

[0973] Input: Changes in emotional state.

[0974] Output: A tailored lesson plan.

[0975] Step 10:

[0976] The server periodically collects and analyzes the student's learning progress data, and calculates a match score with the entrance exam data of the school of choice based on the learning progress data.

[0977] Input: Learning progress data, entrance exam data for desired school.

[0978] Output: Relevance score.

[0979] Step 11:

[0980] The server generates a list of schools that best suit the student based on the relevance score, sends it to the terminal, and displays it. The student user then uses the list of schools displayed on the terminal to select their final school of choice.

[0981] Input: Relevance score.

[0982] Output: List of schools of choice.

[0983] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0984] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0985] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0986] [Fourth embodiment]

[0987] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0988] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0989] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0990] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0991] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0992] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0993] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0994] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0995] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0996] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0997] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0998] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0999] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1000] The present invention is a system that utilizes a generative artificial intelligence model to analyze a student's learning proficiency, provide an effective study plan, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[1001] First, a student (user) logs in to a device and prepares to take the test. The device displays test questions, and the student enters their answers. The entered answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the student's heart rate and gaze data, which are then sent to the server in parallel.

[1002] When the server receives the student's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the student chose that answer. It also analyzes physiological data, assessing stress levels during the exam from heart rate and eye movements. Based on this data, the student's learning proficiency and comprehension are evaluated.

[1003] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects or topics appearing in exams. Combining the student's analysis with this exam trend data, a personalized study plan is generated for each student. The study plan details which topics to focus on and the order in which they should be studied.

[1004] The server then periodically collects and evaluates the student's learning progress data and compares it with the entrance exam data of the schools of their choice to calculate a match score. Based on this match score, the server suggests the most suitable schools for the student. These suggestions are sent to the student's device and displayed for the student to review. The suggested list of schools includes each school's characteristics, past admissions records, and advice based on the student's strengths and weaknesses.

[1005] For example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if a student takes a long time to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[1006] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[1007] This invention allows students to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[1008] The processing flow will be explained below.

[1009] Step 1:

[1010] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and an eye tracker.

[1011] Step 2:

[1012] The device transmits the student's answer data and physiological data in real time to a server, including the time it takes to answer each question, heart rate, and eye movements.

[1013] Step 3:

[1014] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer's time, background, and generation process.

[1015] Step 4:

[1016] The server analyzes the physiological data and assesses the student's stress level based on their heart rate and gaze data, and the results of this analysis are stored together with the student's answer data.

[1017] Step 5:

[1018] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, the topic will be identified as a weak point.

[1019] Step 6:

[1020] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze exam trends, revealing the frequency and patterns of appearance of specific subjects and topics.

[1021] Step 7:

[1022] The server combines the student's learning proficiency assessment results with analysis of past exam questions to generate a personalized learning plan, which outlines the topics to focus on and the learning priorities.

[1023] Step 8:

[1024] The server sends the generated learning plan to the terminal, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan.

[1025] Step 9:

[1026] The server periodically collects and evaluates student progress data, including which topics have been covered and to what extent.

[1027] Step 10:

[1028] The server calculates a match score for each school based on the school's entrance exam data and the student's learning progress data. The match score indicates the degree to which the student's learning status matches the school's requirements.

[1029] Step 11:

[1030] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[1031] Step 12:

[1032] The student user checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final preferred school.

[1033] Example 1

[1034] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1035] In the past, understanding students' learning proficiency and providing individualized learning plans required extensive time-consuming and laborious instruction and intervention. It was also difficult for students to accurately assess their own learning progress and stress levels, making it difficult to create effective learning plans and select the most appropriate schools. Furthermore, analyzing the question trends for specific topics one by one was time-consuming and hindered efficient learning. The goal of this project is to solve these problems and provide learning support tailored to each student.

[1036] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1037] In this invention, the server includes means for analyzing a user's test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the user's learning proficiency and comprehension, means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the user's stress level, means for automatically generating a study plan for each user, means for understanding the question trends for specific topics using a database of past test questions, means for analyzing the user's study progress data and calculating a match score with the entrance examination data of desired institutions, and means for suggesting desired institutions based on the match score, thereby enabling the provision of an individualized study plan, efficient learning, and the selection of the most suitable desired school.

[1038] A "generative artificial intelligence model" is a type of artificial intelligence that analyzes users' test response data and physiological data to evaluate their learning proficiency, comprehension, and stress level.

[1039] "Test answer data" refers to data that includes answer information entered by a user during an exam or test and the time it took to answer the answer.

[1040] "Learning proficiency" is an index that indicates to what extent the user has understood and mastered the learning content.

[1041] "Understanding" is a measure of how deeply a user understands a particular topic or subject.

[1042] "Physiological data" refers to data that indicates the user's physical and physiological state, such as heart rate, eye movement, and skin potential.

[1043] "Stress level" is an index that evaluates the degree of stress that the user feels during the test.

[1044] A "study plan" is a plan created by a user that includes specific topics and a timetable to help the user study efficiently.

[1045] "Exam trends" are the result of analyzing the frequency with which specific topics and subjects are tested using a database of past exam questions.

[1046] "Study progress data" is data that indicates the progress of the user's current learning activities and past learning history.

[1047] The "match score" is calculated based on the user's learning progress data and the entrance examination data of the institution of their choice, and indicates how well the user matches up with the institution.

[1048] "Desired institution" refers to the educational institution or school that the user wishes to attend or take the entrance exam for.

[1049] "Device" refers to the device a user uses to take a test or collect physiological data, including a computer, tablet, or smartphone.

[1050] "Analysis" is the act of analyzing collected data using computational processes and models to extract meaningful information.

[1051] "Automatic generation" refers to the process in which a system automatically creates plans and proposals based on data without human intervention.

[1052] The present invention is a system that utilizes a generative artificial intelligence model to analyze a user's learning proficiency, provide an effective study plan, and suggest the most suitable institution for the user. This system is implemented through a series of operations involving a terminal, a server, and a user.

[1053] First, the user logs in to the device and prepares to take the test. The device displays test questions, and the user inputs their answers. The input answer data is sent to the server in real time. In addition, physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the device also collect the user's heart rate and gaze data, which are then sent to the server in parallel.

[1054] When the server receives the user's test answer data, it begins analyzing it using a generative artificial intelligence model. The AI ​​model analyzes the time it took to answer, the background of the answer, and the process by which it was generated to understand why the user chose that answer. It also analyzes physiological data, assessing stress levels during the test from heart rate and eye movements. Based on this data, the user's learning proficiency and comprehension are evaluated.

[1055] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of questions on specific subjects or topics. Combining the results of the user's analysis with this exam trend data, a personalized study plan is generated for each user. The study plan specifies which topics to focus on and in what order they should be studied.

[1056] The server then periodically collects and evaluates the user's learning progress data, compares it with the entrance exam data of the institutions of their choice, and calculates a match score. Based on this match score, the server suggests the most suitable institutions for the user. These suggestions are sent to the device and displayed for the user to review. The list of suggested institutions includes information such as each institution's characteristics, past success rates, and advice based on the user's strengths and weaknesses.

[1057] For example, when a user takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the process of answering each question. For example, if an integer problem takes a long time to answer and is answered incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the user. Furthermore, after determining from heart rate data that the user was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[1058] Furthermore, the system calculates a relevance score based on the entrance exam trend data of the institution the user is applying to, and suggests institutions where the user has a high chance of passing based on their current learning status. For example, it suggests institutions where many users with similar tendencies have passed in the past.

[1059] Examples of prompts include:

[1060] "Analyze solutions to math integer problems, identify your weaknesses, and suggest next study plans."

[1061] "Analyze users' heart rate data to assess their stress levels during the exam and plan their study accordingly."

[1062] "Use past exam data to suggest the best institutions for this user."

[1063] The present invention allows users to accurately grasp their own learning status and create an efficient study plan. Furthermore, it streamlines the process of selecting the most suitable institution of choice, allowing users to effectively prepare for further education.

[1064] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1065] Step 1:

[1066] The user logs in to the terminal and prepares for the test.

[1067] Specifically, the user enters their ID and password into the login screen on the device and clicks the "Login" button. The entered login information is sent by the device to the server, and the server performs authentication. If authentication is successful, the device displays a test preparation screen.

[1068] Input: User login information (ID, password)

[1069] Output: Show test preparation screen

[1070] Step 2:

[1071] The user starts the test and enters the answers.

[1072] The device displays pre-prepared test questions on the screen. The user enters answers to each question and clicks the "Submit" button. The device records the user's answer data and the elapsed time from when the start button was pressed, and sends them to the server in real time.

[1073] Input: User test answer data, answer time

[1074] Output: Answer data and time information sent to the server

[1075] Step 3:

[1076] The device collects physiological data.

[1077] The heart rate sensor and gaze tracker connected to the device are activated to collect the user's heart rate data and gaze data in real time, which are then sent to the server.

[1078] Input: User's heart rate data, gaze data

[1079] Output: Heart rate data and gaze data sent to the server

[1080] Step 4:

[1081] The server analyzes the answer data and physiological data.

[1082] The server analyzes the received answer data and physiological data using a generative artificial intelligence model. Specifically, the AI ​​model processes the data to evaluate the user's learning proficiency and comprehension based on the time it took to answer, the context of the answer, heart rate, and gaze data.

[1083] Input: Answer data, heart rate data, gaze data

[1084] Output: User's learning proficiency, comprehension, and stress level evaluation results

[1085] Step 5:

[1086] The server generates a lesson plan.

[1087] The server compares the analysis results with a database of past exam questions and generates a customized study plan, including the topics to focus on and the order in which to study them. The system analyzes the frequency and patterns of questions on specific topics to determine which areas to study and in what order.

[1088] Input: learning proficiency, comprehension, stress level assessment results, past exam question data

[1089] Output: personalized learning plan

[1090] Step 6:

[1091] The server collects the learning progress data and calculates the relevance score.

[1092] The server periodically collects the user's learning progress data and compares it with the entrance exam data of the institution of choice to calculate a matching score. This process includes a function to match past learning data with entrance exam data using an SQL database.

[1093] Input: User's learning progress data, entrance exam data for desired institutions

[1094] Output: Relevance score

[1095] Step 7:

[1096] The server will suggest the most suitable institution for you to apply to.

[1097] The server then creates a list of the most suitable institutions for the user based on the relevance score. This list includes information about each institution's characteristics, past success rates, and advice on the user's strengths and weaknesses. This information is sent to the user's device for easy review.

[1098] Input: Matching score, desired institution data

[1099] Output: A list of preferred institutions sent to the user

[1100] (Application example 1)

[1101] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1102] With conventional methods for skill proficiency assessment and creating learning plans, it has been difficult to provide optimal learning plans that take into account the individual characteristics and stress levels of each worker. Furthermore, while detailed analysis, including work trends and physiological data, is necessary for efficient skill improvement, performing this manually is not practical. A system that can solve this problem is needed.

[1103] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1104] In this invention, the server includes means for analyzing the test answer data of the worker using a generative artificial intelligence model, and analyzing the time required to answer, the background of the answer, and the process of generating the answer, means for evaluating the worker's skill proficiency and understanding based on the evaluation results, and means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the worker's stress level. This makes it possible to provide a skill improvement plan based on the individual characteristics of the worker, enabling efficient learning and skill improvement.

[1105] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information based on input data.

[1106] "Test answer data" refers to answer information for test questions answered by a worker.

[1107] "Answering time" is the time it takes a worker to answer a particular test question.

[1108] "Background of the answer" refers to the process by which the worker arrived at the answer and the thinking behind it.

[1109] "Physiological data" refers to data that indicates the worker's physical condition, such as heart rate or eye tracking data.

[1110] "Stress level" refers to the degree of psychological or physiological stress experienced by an operator during a task or test.

[1111] "Skill proficiency" is an indicator that shows how well a worker has mastered a particular skill.

[1112] "Skills improvement plan" refers to a learning and training plan to effectively improve the skills of workers.

[1113] "Work trends" is information obtained by analyzing the work patterns, frequency, and content that a worker has performed in the past.

[1114] A "fit score" is an index that evaluates how well a worker's skills and characteristics are suited to a particular training program.

[1115] A "training program" is a specific plan of training and learning activities aimed at improving worker skills.

[1116] This invention is a system for efficiently improving the skills of factory workers, which utilizes a generative artificial intelligence model to analyze the skill proficiency of workers, provide an effective skill improvement plan, and propose an optimal training program. This system is implemented through a series of operations involving terminals, a server, and workers.

[1117] First, the worker (user) logs in to the terminal and prepares to take the test. The terminal displays the test questions, and the worker enters the answers. The answered data is sent to the server in real time. In addition, the worker's heart rate and gaze data are also collected by physiological data collection devices (e.g., heart rate sensors, gaze trackers) connected to the terminal and sent to the server in parallel.

[1118] When the server receives the worker's test answer data, it begins analysis using a generative artificial intelligence model. The AI ​​model analyzes the time it takes to answer, the background to the answer, and the process by which it was generated to understand why the worker chose that answer. It also analyzes physiological data, assessing the worker's stress level during work from heart rate and eye movement. Based on this data, the worker's skill proficiency and level of understanding are evaluated.

[1119] The server then analyzes past work data and uses a generative artificial intelligence model to analyze past work patterns, identifying the frequency and patterns of specific tasks and processes. Combining the worker's analysis results with this work trend data generates a personalized skill development plan for each worker. The skill development plan specifies which topics to focus on and in what order they should be studied.

[1120] The server then periodically collects and evaluates the worker's learning progress data, compares it with the data from the adapted program, and calculates a compatibility score. Based on this compatibility score, the server suggests the best training program for the worker. These suggestions are sent to the terminal and displayed for the worker to review. The list of suggested training programs includes advice based on each program's features, past success, and the worker's strengths and weaknesses.

[1121] As a specific example, when a worker takes a robot operation test, the terminal sends the answers to a server, which uses a generative artificial intelligence model to analyze the answer process for each question. For example, if a worker takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as the worker's weakness. Furthermore, after confirming that the worker was in a high-stress state based on heart rate data, the AI ​​individually creates a plan for the next skill improvement, including stress control methods.

[1122] Furthermore, a compatibility score is calculated based on the trend data of the training program that the worker wishes to participate in, and a training program that is highly compatible with the worker's current skill level is suggested. For example, a training program that has been successful in the past for many workers with similar tendencies will be suggested.

[1123] An example of a prompt sentence is, "Analyze worker A's answer data and physiological data to identify his stress level and weaknesses. Based on the results, generate an optimal robot operation learning plan."

[1124] This allows workers to accurately grasp their own skill status and create efficient skill improvement plans. Furthermore, the process of selecting the most suitable training program is streamlined, enabling effective preparation for skill improvement.

[1125] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1126] Step 1:

[1127] A user logs in to a terminal and prepares to take a test. The terminal displays test questions, and the user inputs answers. The input data here is the user's answer data, which is obtained through the terminal's display and input interface. The output data is the answer data sent to the server in real time.

[1128] Step 2:

[1129] Physiological data of the user is collected using a physiological data collection device (e.g., a heart rate sensor or gaze tracker) connected to the terminal. The collected data (heart rate data and gaze data) is transmitted to the server in real time. The input data of this step are various physiological data, and the output data is the physiological data transmitted to the server.

[1130] Step 3:

[1131] The server uses a generative artificial intelligence model to analyze the user's test answer data. Specifically, it analyzes the time it takes to answer, the background of the answer, and the process by which the answer was generated. The input data here is the answer data sent from the device, and the output data is the analysis results. This analysis helps understand why the user chose that answer.

[1132] Step 4:

[1133] The server analyzes the physiological data and evaluates the user's stress level based on their heart rate and eye movements. The input data is the physiological data, and the output data is the stress level evaluation result. This result indicates the degree of psychological and physiological stress on the user.

[1134] Step 5:

[1135] The server evaluates the user's skill proficiency and understanding based on the analysis results. The input data are the analysis results of the test answer data and the evaluation results of the physiological data, and the output data are the evaluation results of the skill proficiency and understanding. This evaluation indicates the user's current skill level and understanding.

[1136] Step 6:

[1137] The server analyzes past work data and uses a generative artificial intelligence model to understand past work patterns. The input data is past work data, and the output data is information indicating work trends. This reveals the frequency and patterns of specific work content and processes.

[1138] Step 7:

[1139] The server combines the skill proficiency and comprehension assessment results with the work tendency data to generate a personalized skill improvement plan for each user. The input data are the skill proficiency and comprehension assessment results and the work tendency data, and the output data is the personalized skill improvement plan. This plan specifies which topics should be studied intensively and in what order.

[1140] Step 8:

[1141] The server periodically collects the user's learning progress data, compares it with the data of the adaptive program, and calculates a matching score. The input data are the learning progress data and the data of the adaptive program, and the output data is the matching score. Based on this score, an optimal training program is suggested to the user.

[1142] Step 9:

[1143] The server proposes optimal training programs based on the relevance scores and sends the list to the terminal. The input data is the relevance scores, and the output data is a list of proposed training programs. The user can view this list through the terminal.

[1144] For example, when a user takes a robot operation test, the device sends the answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a user takes too long to answer a particular task and answers incorrectly, the AI ​​analyzes the underlying thought process and identifies that topic as the user's weak point. This analysis result is combined with heart rate data to create an optimal individual skill improvement plan.

[1145] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1146] The present invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school to apply to. This system is implemented through a series of operations involving a terminal, a server, and a user.

[1147] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[1148] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[1149] The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer, including the time it took, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data to assess the student's stress level from heart rate and gaze data, and further evaluates their emotional state. The results of this analysis are saved together with the student's answer data.

[1150] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if a student's comprehension of a particular topic is low, that topic is identified as a weak point. The server also uses an emotion engine to monitor changes in the student's emotions while they are studying. If stress or a decline in interest is detected, the server will revise the student's learning plan.

[1151] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student's analysis with this exam trend data generates a personalized study plan for each student. The study plan outlines the topics to focus on and the learning priorities.

[1152] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan. During the study, the emotion engine continuously monitors the student's emotional state, and the learning plan is adjusted as necessary.

[1153] Furthermore, the server periodically collects and evaluates the student's learning progress data. The learning progress data includes which topics have been covered and to what extent. Based on the learning progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's learning status and the requirements of the desired school.

[1154] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[1155] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[1156] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[1157] This invention allows students to accurately grasp their own learning and emotional state, allowing them to create an efficient study plan. It also streamlines the process of selecting the most suitable school of choice, allowing students to effectively prepare for entrance exams.

[1158] The processing flow will be explained below.

[1159] Step 1:

[1160] The student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through a heart rate sensor and gaze tracker, and also collects facial expression and voice data using an emotion engine.

[1161] Step 2:

[1162] The device transmits the student's answer data, physiological data, and emotional data in real time to a server, including the time it takes to answer each question, heart rate, eye movements, facial expressions, and tone of voice.

[1163] Step 3:

[1164] The server inputs the received answer data into a generative AI model and begins analysis. The AI ​​model analyzes each answer, including the time it took to complete it, the context of the answer, and the process by which it was generated. It also uses physiological and emotional data, such as heart rate and gaze data, to assess the student's stress level and emotional state.

[1165] Step 4:

[1166] The server evaluates the student's learning proficiency and comprehension based on these analysis results. If a student's understanding of a particular topic is low, that topic will be identified as a weak point. Furthermore, if the analysis using the emotion engine detects stress or a loss of interest, that data will also be reflected in the evaluation.

[1167] Step 5:

[1168] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions in specific subjects and topics.

[1169] Step 6:

[1170] The server combines the student's analysis results with past exam question analysis data to generate a personalized study plan, which includes topics to focus on and priorities for learning. It also suggests stress-reducing study methods based on emotional data.

[1171] Step 7:

[1172] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then studies according to the learning plan, and the emotion engine continues to monitor the student's emotional state while they are studying.

[1173] Step 8:

[1174] The server periodically collects and evaluates students' learning progress data, including which topics have been covered and to what extent. An emotion engine keeps track of students' emotional states.

[1175] Step 9:

[1176] The server calculates a match score based on the student's learning progress data and the entrance exam data of the school of choice. This match score indicates the degree of match between the student's learning status and the requirements of the school of choice.

[1177] Step 10:

[1178] The server generates a list of schools that are most suitable for the student based on the match score, and this list is sent to the device and displayed for the student to review.

[1179] Step 11:

[1180] The user, a student, checks the list of preferred schools displayed on the device and uses it as a reference for making a selection. The list of preferred schools includes feedback based on each school's characteristics, past acceptance records, and the student's emotional state. Based on this information, the student selects their final preferred school.

[1181] Example 2

[1182] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1183] Conventional learning systems have difficulty accurately assessing students' learning proficiency and comprehension, making it difficult to provide optimal learning plans for each student. Furthermore, they are unable to create learning plans that reflect physiological and emotional data, and lack the ability to provide adaptive learning programs that take into account students' stress and emotional states. Furthermore, they are also inadequate in suggesting specific schools to attend based on learning progress data and school entrance exam data.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1185] In this invention, the server includes a means for analyzing educator evaluation data using a generative artificial intelligence model to analyze the time required to answer questions, the background of the answers, and the process by which the answers were generated; a means for evaluating students' learning proficiency and comprehension; and a means for collecting and analyzing biometric data to evaluate students' stress levels. This enables accurate assessment of students' learning proficiency and comprehension and provides optimal learning plans for each student. Furthermore, by incorporating data obtained from a heart rate sensor and gaze tracker, and facial expression and voice data obtained using an emotion engine, it is possible to provide adaptive learning programs that take students' stress and emotional state into account. It is also possible to calculate a match score between learning progress data and university entrance exam data and suggest specific universities to attend.

[1186] A "generative artificial intelligence model" is a type of artificial intelligence used to analyze students' test response data and analyze the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[1187] "Assessment data" refers to data including student test response data, physiological data, and emotional data.

[1188] "Biometric data" refers to data obtained from heart rate sensors and eye trackers, which are used to assess students' stress levels and emotional states.

[1189] The "emotion engine" is a means of analyzing facial expression and voice data to assess a student's emotional state.

[1190] "Learning proficiency" is an indicator that shows the student's level of understanding of the content they have learned and their level of skill acquisition.

[1191] "Understanding" is an indicator of how well a student understands a particular topic or subject.

[1192] A "study plan" is a study schedule that sets out the optimal learning methods and content, taking into account the student's learning proficiency and comprehension, stress level, and emotional state.

[1193] A "heart rate sensor" is a device for measuring a student's heart rate.

[1194] An "eye tracker" is a device used to track students' eye movements.

[1195] "Facial expression data" is data that records and analyzes changes in students' facial expressions.

[1196] "Voice Data" refers to data that records and analyzes the tone and patterns of a student's voice.

[1197] An "adaptive learning plan" is a learning program that dynamically adjusts according to a student's real-time learning situation and emotional state.

[1198] "Progress data" is data that indicates how far a student has progressed in their studies.

[1199] "Entrance exam data" refers to data related to the entrance exam requirements and question trends of the school to which students wish to advance.

[1200] The "match score" is a score that indicates the degree of match between the student's learning data and the entrance examination data of the school they are going to.

[1201] The "school destination list" is a list of schools suggested based on the compatibility score.

[1202] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school for them to apply to. This system is implemented through a series of operations involving terminals, a server, and users.

[1203] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device is connected to devices such as a heart rate sensor, gaze tracker, and microphone, which collect physiological and emotional data in real time. For example, the heart rate sensor obtains the student's heart rate, the gaze tracker captures eye movements, and the camera and microphone collect facial expressions and voice.

[1204] The device transmits the user's answer data, physiological data, and emotional data to the server. The collected data includes the time it took to answer, the content of the answer, heart rate, eye movements, facial expressions, and voice tone. During this transmission process, the data is encrypted to ensure security. For example, the device performs batch processing at regular intervals and transmits the data to the server all at once.

[1205] The server inputs the received data into a generative AI model and begins analysis. The generative AI model analyzes the educator's evaluation data, digging deep into the time it took to answer the questions, the background, and the process by which they were generated. It also uses an emotion engine to analyze heart rate, gaze data, facial expression changes, and voice tone to assess the student's stress level and emotional state. For example, if a particular question takes a long time to answer and the heart rate rises, it can be determined that the question is causing stress.

[1206] The server then evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic is identified as a weak point. An emotion engine is used to monitor emotional changes during learning, and if stress or a decline in interest is detected, the learning plan is revised. At this stage, the generated learning plan becomes an adaptive learning program that incorporates heart rate sensors, gaze trackers, facial expression data, and voice data.

[1207] The server then accesses a database of past educational questions and uses a generative artificial intelligence model to analyze question trends, identifying the frequency and patterns of questions on specific subjects and topics. The analysis results are combined with the question trend data to generate a personalized learning plan for each student, which includes topics to focus on and priorities for learning.

[1208] The server sends the generated learning plan to the device, which receives it and displays it to the student. The student then proceeds with their studies according to the learning plan. The emotion engine continues to monitor the student's emotional state while they are studying, and the learning plan is adjusted as necessary.

[1209] Furthermore, the server periodically collects and analyzes learning progress data. Based on the analysis results, a match score is calculated with the entrance exam data of the desired school. This match score is an indicator of the degree of match between the student's learning status and the requirements of the desired school. Based on the match score, the server generates a list of schools that are most suitable for the student and sends it to the device. The student can check the list of schools displayed on the device to help them select their preferred schools.

[1210] As a specific example, when a student takes a math test, their device sends physiological and emotional data along with their answers to a server. A generative AI model analyzes the answering process, identifies high-stress states from heart rate and emotional data, and individually creates a study plan for the next test. It also calculates a match score based on the student's desired university entrance exam trends and suggests universities where they have a high chance of being accepted.

[1211] Examples of prompts have the following format:

[1212] "Analyze students' answer data, physiological data (heart rate, gaze data), facial expression data, and voice data to assess their learning proficiency and emotional state. Then, generate an appropriate study plan and suggest the best schools for students."

[1213] This system allows students to accurately grasp their academic and emotional state, allowing them to create efficient study plans, streamline the process of selecting the most suitable school, and effectively prepare for entrance exams.

[1214] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1215] Step 1: User login and start testing

[1216] The user logs in to the terminal. A user ID and password are required as input. The terminal sends this authentication information to the server for authentication. If authentication is successful, the terminal displays a "Test Start" screen. Specifically, the user enters authentication information on the terminal, and the server verifies it to perform authentication. If authentication is successful, a test screen is displayed as output.

[1217] Step 2: Collect user responses and physiological data

[1218] The user enters answers to test questions displayed on the device. The input also includes physiological and emotional data collected using a heart rate sensor, gaze tracker, and microphone. The device collects this data in real time. Specifically, while the user enters answers using a keyboard or touchscreen, the heart rate sensor collects heart rate data, the gaze tracker collects eye movements, and the camera and microphone record facial expressions and tone of voice. The output is the collected answer data, physiological data, and emotional data.

[1219] Step 3: Send data from the device to the server

[1220] The device sends the collected answer data, physiological data, and emotional data to the server. The data collected in the previous step is required as input. The data is encrypted and transferred securely. Specifically, the device batch processes the data at regular intervals (for example, every minute) and uploads it to the server. The output is the data sent to the server.

[1221] Step 4: Data analysis by the server

[1222] The server inputs the received data into a generative artificial intelligence model and analyzes the content, background, and generation process of the answer. Inputs include collected answer data, physiological data, and emotional data. The server analyzes heart rate, gaze data, facial expression changes, and voice tone to evaluate stress levels and emotional states. For example, the server passes the answer data to the AI ​​model to evaluate the time required and accuracy, and further analyzes physiological data to understand the emotional state. The output is the analyzed learning proficiency, comprehension, and emotional state.

[1223] Step 5: Assess your learning proficiency and emotional state

[1224] The server evaluates the student's learning proficiency and comprehension based on the analysis results. The input includes the data analyzed in the previous step. For example, it evaluates the correct answer rate and response time for a specific topic and identifies weak points. It also uses an emotion engine to monitor emotional changes during learning and detect stress or loss of interest. The output is the evaluated learning proficiency and emotional state.

[1225] Step 6: Generate a lesson plan

[1226] The server accesses a database of past educational questions and analyzes question trends using a generative artificial intelligence model. Inputs include the student's learning proficiency and comprehension, and the database of past questions. The server generates an individualized learning plan for each student based on the question trends and analyzed data. For example, it analyzes the frequency and patterns of questions obtained from the database to determine the topics that should be focused on. The output is the generated learning plan.

[1227] Step 7: Provide and display your lesson plan

[1228] The server sends the generated lesson plan to the terminal. The input includes the generated lesson plan. The terminal receives it and displays it to the user. Specifically, the server sends the lesson plan to the terminal, the terminal receives it, and displays the lesson plan on the screen. The output is the lesson plan displayed on the terminal.

[1229] Step 8: Assessment of learning progress and school preference suggestions

[1230] The server periodically collects and analyzes learning progress data. Inputs include learning progress data and entrance exam data. The server compares this data with the entrance exam data of the schools of choice and calculates a matching score. For example, the server analyzes the learning progress data and calculates the degree of match with the entrance exam requirements of the schools of choice. The output is the calculated matching score and a generated list of schools of choice. This list of schools of choice is sent to the terminal and displayed to the user.

[1231] (Application example 2)

[1232] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1233] Conventional learning management systems have difficulty providing individualized learning plans that fully consider students' learning proficiency and stress levels. Furthermore, they are unable to grasp changes in students' emotional states in real time and provide learning support based on this, which can lead to students feeling stressed or losing motivation to study. Furthermore, they lack efficient suggestions based on appropriate data analysis when selecting a school of choice.

[1234] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing students' test answer data using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer; means for evaluating the students' learning proficiency and comprehension based on the analysis results; means for collecting and analyzing physiological data such as heart rate and gaze data to evaluate the students' stress levels; means for collecting students' facial expression data and voice data using an emotion engine to analyze their emotional states; and means for automatically generating individual study plans for each student based on the analysis results and emotional data, and providing the study plans including stress control methods. This enables a comprehensive evaluation of students' learning proficiency and emotional states, enabling efficient and personalized study support.

[1235] A "generative artificial intelligence model" is an artificial intelligence technology that analyzes students' test response data and analyzes the time it takes to answer, the background of the answer, and the process by which the answer is generated.

[1236] "Learning proficiency" is an indicator of how much a student understands and has mastered a particular topic or subject.

[1237] "Understanding" is a measure of how well a student understands a particular issue or topic.

[1238] "Physiological data" refers to data used to measure students' physical reactions and conditions, such as heart rate and gaze data.

[1239] "Stress level" is an indicator of the degree of stress a student feels while studying, assessed based on heart rate, gaze data, etc.

[1240] The "emotion engine" is a technology that analyzes facial expression and voice data to assess a student's emotional state.

[1241] "Automatically generated individualized learning plans that include stress control methods" are learning plans that are optimized based on each student's learning proficiency, stress level, and emotional state, and also incorporate stress reduction techniques.

[1242] A "suitability score" is a number that indicates how well a student is suited to their desired school by comparing their learning progress data with the entrance examination data of the school.

[1243] The "School of Choice List" is a list of schools that suggests the most suitable schools for students based on their compatibility scores.

[1244] This invention is a system that utilizes a generative artificial intelligence model and an emotion engine to analyze a student's learning proficiency, provide an effective study plan that takes into account their emotional state, and suggest the most suitable school of choice.

[1245] First, the student user logs in to the device and begins the test. The student enters answers to the test questions displayed on the device. The device simultaneously collects physiological data through devices such as a heart rate sensor and gaze tracker. In addition, the emotion engine also collects the student's facial expression and voice data.

[1246] The device transmits the student's answer data, physiological data, and emotional data to the server in real time. The transmitted data includes the time taken for each answer, heart rate, eye movements, facial expressions, and voice tone. The server inputs the received answer data into a generative artificial intelligence model and begins analysis. The AI ​​model analyzes each answer's time taken, the background of the answer, and the process by which it was generated. Furthermore, based on the physiological and emotional data, the system evaluates the student's stress level from heart rate and eye gaze data, as well as their emotional state.

[1247] The server evaluates the student's learning proficiency and comprehension based on the analysis results. For example, if the student's comprehension of a particular topic is low, that topic will be identified as a weak point. The server also uses an emotion engine to monitor the student's emotional changes while they are studying, and if stress or a decline in interest is detected, the learning plan will be revised.

[1248] The server then accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions. This identifies exam trends, such as the frequency and patterns of specific subjects and topics. Combining the student analysis with this exam trend data, a personalized study plan is generated for each student. The study plan outlines the topics to focus on and the learning priorities.

[1249] The server sends the generated study plan to the terminal and displays it to the student. The student then studies according to the study plan. During the study, the emotion engine continuously monitors the student's emotional state, and the study plan is adjusted as necessary. In addition, the server periodically collects and evaluates the student's study progress data. The study progress data includes which topics have been covered and to what extent. Based on the study progress data, the server calculates a match score with the entrance exam data of the desired school. This match score indicates the degree of match between the student's study state and the requirements of the desired school.

[1250] The server generates a list of schools that best suit the student based on the match score. This list is sent to the device and displayed for the student to review. The student user then checks the list of schools displayed on the device and uses it as a reference for making a selection. The list includes each school's characteristics, past acceptance rates, and feedback. Based on this information, the student selects their final school of choice.

[1251] As a specific example, when a student takes a math test, their device sends their answers to a server, which uses a generative artificial intelligence model to analyze the answering process for each question. For example, if a student takes too long to answer an integer question and answers it incorrectly, the AI ​​analyzes the thought process behind it and identifies that topic as a weak point for the student. Furthermore, after determining from heart rate and emotional data that the student was in a high-stress state, the AI ​​creates an individualized study plan for the next lesson, including methods for stress control.

[1252] Furthermore, based on the entrance exam trend data of the university the student is applying to, a matching score is calculated and universities with a high probability of being accepted are suggested based on the student's current learning status. For example, universities that have been accepted by many students with similar trends in the past will be suggested.

[1253] An example of a prompt for the generative AI model is as follows:

[1254] Prompt statement:

[1255] [Student answer data] [Physiological data] [Emotional data]

[1256] for example:

[1257] "Answer: 4, Time taken: 30 seconds, Heart rate: 80, Gaze data: Concentrated, Emotion data: Neutral"

[1258] Based on the above data, evaluate your learning proficiency and stress level and create your next study plan.

[1259] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1260] Step 1:

[1261] The user logs in to the device and begins the test. The user enters answers to the test questions displayed on the device. During this process, the device collects physiological data using a heart rate sensor and gaze tracker. The device also collects facial expression and voice data using a microphone and camera.

[1262] Input: Test questions, answers, heart rate, physiological data, facial expression data, and voice data.

[1263] Output: Answer data, physiological data, emotional data.

[1264] Step 2:

[1265] The device transmits the collected data (answer data, physiological data, and emotional data) in real time to a server, which then receives the data for analysis.

[1266] Input: Answer data, physiological data, emotional data.

[1267] Output: Transmit data.

[1268] Step 3:

[1269] The server inputs the received answer data into the generative AI model and begins analysis, which examines in detail the time required to reach the answer, the background of the answer, and the process by which it was generated.

[1270] Input: Answer data.

[1271] Output: Analysis results (time required to get the answer, background of the answer, and how it was generated).

[1272] Step 4:

[1273] The server simultaneously analyzes physiological and emotional data, assessing students' stress levels based on their heart rate and gaze data, and using an emotion engine to assess their emotional state based on facial expression and voice data.

[1274] Input: physiological data, emotional data.

[1275] Output: Stress level, emotional state.

[1276] Step 5:

[1277] The server evaluates the student's learning proficiency and comprehension based on the analysis results of steps 3 and 4. This allows the server to understand how well the student has mastered a particular topic.

[1278] Input: Analysis results of answer data, stress level, emotional state.

[1279] Output: learning proficiency, comprehension.

[1280] Step 6:

[1281] The server accesses a database of past exam questions and uses a generative artificial intelligence model to analyze past exam questions, thereby understanding the frequency and patterns of questions on specific subjects and topics.

[1282] Input: Past exam question data.

[1283] Output: Question trend data.

[1284] Step 7:

[1285] The server combines the results of the learning proficiency and comprehension assessment in Step 5 with the question trend data in Step 6 to generate an individualized learning plan for each student, including the topics to focus on and learning priorities.

[1286] Input: learning proficiency, comprehension, and question trend data.

[1287] Output: Learning plan.

[1288] Step 8:

[1289] The server sends the generated learning plan to the terminal and notifies the student. The student then proceeds with their studies according to the learning plan displayed on the terminal.

[1290] Input: lesson plan.

[1291] Output: The displayed lesson plan.

[1292] Step 9:

[1293] During learning, the emotion engine continues to monitor the student's emotional state, and the server adjusts the learning plan as needed and sends it back to the device.

[1294] Input: Changes in emotional state.

[1295] Output: A tailored lesson plan.

[1296] Step 10:

[1297] The server periodically collects and analyzes the student's learning progress data, and calculates a match score with the entrance exam data of the school of choice based on the learning progress data.

[1298] Input: Learning progress data, entrance exam data for desired school.

[1299] Output: Relevance score.

[1300] Step 11:

[1301] The server generates a list of schools that best suit the student based on the relevance score, sends it to the terminal, and displays it. The student user then uses the list of schools displayed on the terminal to select their final school of choice.

[1302] Input: Relevance score.

[1303] Output: List of schools of choice.

[1304] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1305] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1306] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1307] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1308] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1309] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1310] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1311] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1312] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1313] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1314] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1315] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1316] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1317] 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.

[1318] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1319] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpos...

Claims

1. A means for analyzing test response data of students using a generative artificial intelligence model to analyze the time required to answer, the background of the answer, and the process of generating the answer; a means for evaluating the student's learning proficiency and understanding based on the analysis results; A means of collecting and analyzing physiological data such as heart rate and gaze data to assess students' stress levels; The system includes a means for automatically generating a learning plan for each student based on the evaluation results.

2. A means for analyzing past exam questions using the generative artificial intelligence model to understand question trends; a means for creating a study plan by combining the assessment results of the learning proficiency and comprehension level with the question tendency data; The system according to claim 1 , further comprising means for transmitting the lesson plan to a terminal and providing it to the student.

3. A means for analyzing the student's learning progress data and calculating a matching score with the entrance examination data of the student's desired school; A means for suggesting a desired school based on the compatibility score; 2. The system according to claim 1, further comprising means for transmitting the suggested list of preferred schools to a terminal and displaying the list to the student.

Images