System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting data such as an operation history of a learner, a test result, and self-evaluation, a means for analyzing the collected data and identifying a thinking pattern and a cognitive style of the learner, a means for automatically generating individualized educational contents based on the analysis result, a means for delivering the automatically generated educational contents to the learner, and a means for dynamically adjusting an educational program according to the progress of the learner.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] Modern educational environments require responding to the individual learning needs of learners. However, conventional educational systems struggle to accurately grasp learners' thinking patterns and cognitive styles and provide personalized educational content based on those understanding. Furthermore, they lack mechanisms for dynamically adjusting educational programs according to learners' progress. As a result, they are unable to provide an educational experience that effectively promotes learners' self-growth and skill improvement. Therefore, the present invention aims to solve these problems. [Means for solving the problem]

[0005] The present invention provides a means for collecting data such as a learner's operation history, test results, and self-assessment. It then provides a means for analyzing the collected data and identifying the learner's thinking patterns and cognitive styles. It also provides a means for automatically generating personalized educational content based on the analysis results and a means for delivering the automatically generated educational content to the learner. It also incorporates a means for dynamically adjusting the educational program according to the learner's progress, making it possible to provide an optimal learning environment. By including an analysis means using a generative AI model and a means for generating and notifying feedback to be provided to the learner, the system responds to the learner's individual learning needs and achieves effective self-growth and skill improvement.

[0006] "Operation history" is a record of all clicks, inputs, scrolls, and other operations performed by a learner when using online learning materials.

[0007] "Test results" are data showing the answers given by learners to assignments and tests and the results of their grading.

[0008] "Self-assessment" refers to data that learners themselves evaluate regarding their level of understanding of the learning content and their own abilities.

[0009] "Analysis" is the process of identifying learners' thinking patterns and cognitive styles based on collected data.

[0010] "Thinking patterns" are characteristics that indicate the tendencies and methods by which learners process information and solve problems.

[0011] "Cognitive style" is a characteristic that refers to a learner's individual way or tendency to learn and understand new information.

[0012] "Educational content" refers to all educational materials, such as teaching materials, questions, videos, texts, etc., that are provided for learners to study.

[0013] "Automatic generation" refers to the use of artificial intelligence technology to generate educational content optimized for each learner based on collected and analyzed data.

[0014] "Delivery" means sending automatically generated educational content to the learner's device so that the learner can use it.

[0015] "Progress" is data that shows the process and results of a learner's learning as they use educational content.

[0016] "Dynamic adjustment" refers to changing the content and difficulty of an educational program in real time according to the learner's progress.

[0017] A "generative AI model" is an artificial intelligence model used to analyze collected data and identify learner characteristics.

[0018] "Feedback" is information that indicates areas for improvement in learning and next actions based on the learner's learning results and progress.

[0019] An "educational program" is the entire curriculum designed to help a learner achieve a specific learning goal. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[0042] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, the learning material selected by the user is provided. While using the learning material, data such as the learner's operation history, test results, and self-evaluation are sent from the terminal to the server.

[0043] The server collects this data and inputs it into a generative AI model for analysis. The AI ​​model performs detailed analysis of the data to identify the learner's thinking patterns and cognitive styles. Based on the results of this analysis, the server automatically generates educational content optimized for each learner.

[0044] The generated educational content is provided from the server to the learner's device, and the learner uses it to advance their studies. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback for the learner based on their learning progress and notifies them via their device.

[0045] Specific examples

[0046] Example 1: High school mathematics learning

[0047] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal.

[0048] When a user operates the learning material to solve geometry problems, the operation history and test results (e.g., answer to the problem, answer time, number of correct answers, etc.) are sent in real time from the device to the server. The server collects the data and inputs it into a generative AI model for analysis.

[0049] For example, the AI ​​model might determine that a user is strong in algebra but weak in geometry. Based on this analysis, the server automatically generates geometry reinforcement problems and provides them to the user's device. The user continues to solve the reinforcement problems, and the results are also sent back to the server.

[0050] The server uses this ongoing data to dynamically adjust the educational program to provide the user with an optimal learning experience, and also generates and notifies the user based on their progress, such as "Your understanding of a particular area of ​​geometry is improving."

[0051] In this way, the system of the present invention responds to the needs of individual learners and dynamically adjusts educational programs, thereby achieving effective learning and self-development.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user accesses the system from a terminal and logs in by entering the user ID and password.

[0055] Step 2:

[0056] The terminal transmits the entered authentication information to the server.

[0057] Step 3:

[0058] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[0059] Step 4:

[0060] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[0061] Step 5:

[0062] The terminal transmits the user's teaching material selection information to the server.

[0063] Step 6:

[0064] The server collects the selected teaching material data and transmits it to the terminal.

[0065] Step 7:

[0066] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[0067] Step 8:

[0068] The device records data such as the user's operation history, test results, and self-evaluation in real time and transmits it to the server.

[0069] Step 9:

[0070] The server preprocesses the received data and prepares it for input into the generative AI model.

[0071] Step 10:

[0072] The server inputs data into the generated AI model, which analyzes the learner's thinking patterns and cognitive style.

[0073] Step 11:

[0074] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content.

[0075] Step 12:

[0076] The server sends the generated educational content to the terminal and displays it to the learner.

[0077] Step 13:

[0078] The user continues learning by accessing new educational content, for example, by working on new geometry reinforcement problems.

[0079] Step 14:

[0080] The device continuously transmits operation data and test results to the server.

[0081] Step 15:

[0082] The server collects this data, monitors progress, and dynamically adjusts the educational program to change difficulty or content as needed.

[0083] Step 16:

[0084] The server generates feedback based on the learner's progress, including achievement levels, identified weaknesses, and recommended next learning steps.

[0085] Step 17:

[0086] The server generates feedback and sends it to the device.

[0087] Step 18:

[0088] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[0089] With this, the system continues to provide the learner with the optimal educational environment at all times.

[0090] Example 1

[0091] 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."

[0092] Conventional educational systems have struggled to provide personalized educational content tailored to each learner's progress and level of understanding. Furthermore, because real-time data collection and analysis were not performed, it was not possible to quickly identify learners' characteristics and weaknesses, making it impossible to provide effective learning support. Furthermore, there were insufficient means of collecting data such as user operation history, test results, and self-assessments, making it difficult to provide appropriate feedback based on this data.

[0093] 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.

[0094] In this invention, the server includes a means for collecting data such as a learner's operation history, test results, and self-assessment; a means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and a means for automatically generating personalized educational content based on the analysis results. This enables the provision of an optimal educational program tailored to the characteristics of each learner. Furthermore, by providing a means for monitoring the collected data in real time and generating feedback, a means for notifying the learner of the generated feedback, and a means for inputting data into a generative AI model using simple prompts and obtaining analysis results, dynamic adjustments can be made according to the learner's progress, resulting in more effective learning support.

[0095] An "operation history" is a record of a series of operations and actions performed by a learner using an educational system.

[0096] "Test results" refers to the answers given by a learner to a test taken in an educational system, and information on whether the answers were correct or incorrect.

[0097] "Self-assessment" refers to data on the evaluation and feedback that the learner has given themselves regarding the learning content and their own level of understanding.

[0098] "Means for collecting data" refers to devices or programs that have the function of automatically recording and saving learners' operation history, test results, self-assessments, etc.

[0099] "Means for analyzing data" refers to devices or programs that use collected data to process the data and identify learners' thinking patterns and cognitive styles.

[0100] "Means for automatically generating personalized educational content" refers to devices or programs that automatically create learning materials, workbooks, etc. that are appropriate for each learner based on the results of data analysis.

[0101] A "means for dynamically adjusting an educational program" is a device or program that changes the difficulty level or content of teaching materials or programs in real time according to the learner's progress and level of understanding.

[0102] "Means for generating feedback" refers to devices or programs that create appropriate advice and guidance in real time based on the learner's learning situation and analysis results.

[0103] A "generative AI model" is an artificial intelligence model used to analyze collected data and identify learner characteristics and weaknesses.

[0104] A "prompt" is a simple text or command that is input to a generative AI model to instruct it on how to analyze.

[0105] A "system" is an integrated structure that integrates the above means, devices, and programs to provide educational services.

[0106] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[0107] System Overview

[0108] The system uses the following hardware and software:

[0109] Server: Collects data, analyzes, generates content, and generates feedback. It mainly consists of a database server and an application server that runs generative AI models.

[0110] Terminal: A device operated by the learner (user). It has user interface functions such as data entry, display of teaching materials, and feedback notifications. Devices that can be used include PCs, tablets, and smartphones.

[0111] Details of system processing

[0112] 1. User login

[0113] Terminal: The learner enters their ID and password on the login screen.

[0114] Server: Receives authentication information, compares it with the user database, and returns the authentication result to the terminal. If authentication is successful, generates learning dashboard data and sends it to the terminal.

[0115] Device: Displays the learning dashboard and allows users to start learning.

[0116] 2. Selection and provision of teaching materials

[0117] User: Select the subjects and materials to study on the dashboard.

[0118] Terminal: Sends the selected teaching material request to the server.

[0119] Server: Receives the request, retrieves the relevant teaching material data from the teaching material database, and sends it to the terminal.

[0120] Terminal: Display the teaching materials.

[0121] 3. Data Collection

[0122] Users: Use the materials to study, solve problems, and take tests.

[0123] Terminal: Collects operation history and test results (answers to questions, answer time, number of correct answers, etc.) in real time and sends them to the server.

[0124] 4. Data Analysis

[0125] Server: Inputs collected data into the generative AI model.

[0126] Generative AI models: Analyze data in detail to identify a user's thinking patterns and cognitive styles, for example, identifying that a user is good at algebra but poor at geometry.

[0127] Server: Automatically generates personalized educational content based on the analysis results.

[0128] 5. Feedback and progress management

[0129] Server: Monitors learners' progress in real time, dynamically adjusts the content and difficulty of the learning materials as needed, and generates feedback based on the progress and sends it to the device.

[0130] Device: Displays feedback, notifications of new content, and provides learning guidance to users.

[0131] Specific examples

[0132] Example 1: High school mathematics learning

[0133] 1. Login and Dashboard

[0134] When a high school student (user) accesses the system and logs in, the server performs authentication and displays a learning dashboard to the user.

[0135] 2. Selecting and studying materials

[0136] When a user selects "Mathematics - Geometry," the server provides geometry teaching materials to the terminal. When the user manipulates the teaching materials to solve geometry problems, the operation history and test results are sent to the server.

[0137] 3. Data analysis and content generation

[0138] The server uses a generative AI model to analyze the user's data and determine whether the user is strong in algebra but weak in geometry. Based on the analysis results, the server automatically generates geometry reinforcement problems and provides them to the user's device.

[0139] 4. Dynamic Adjustment and Feedback

[0140] The server dynamically adjusts the educational program based on the user's progress, generates feedback such as "your understanding of a particular area of ​​geometry is improving," and notifies the user via their terminal.

[0141] Prompt Sentence Examples

[0142] Below are some example prompts to input to a generative AI model:

[0143] "My algebra skills are strong, but I struggle with geometry. Please generate teaching materials that will help me improve my geometry."

[0144] Based on this prompt, the AI ​​model can generate geometry reinforcement materials appropriate for the user.

[0145] In this way, the system of the present invention responds to the needs of each individual learner and dynamically adjusts the educational program, thereby realizing effective learning and self-development.

[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0147] Step 1:

[0148] The user enters their ID and password on the login screen.

[0149] Input: User ID and password.

[0150] Terminal: Sends the entered authentication information to the server.

[0151] Server: Receives the authentication information and checks it against a database.

[0152] Data calculation: The authentication information is compared with the user information in the database to see if they match.

[0153] Output: Authentication result (success / failure).

[0154] Server: If authentication is successful, a learning dashboard is generated based on the user's learning history and progress data and sent to the device.

[0155] Terminal: Receives dashboard data and displays the learning dashboard.

[0156] Step 2:

[0157] The user selects the course and materials from the learning dashboard.

[0158] Input: User-selected study subjects and materials.

[0159] Terminal: Sends the selected data to the server.

[0160] Server: Receives the request and retrieves the corresponding teaching material data from the teaching material database.

[0161] Data calculation: Extract relevant teaching material data through a database search.

[0162] Output: Teaching material data.

[0163] Server: Sends the teaching material data to the terminal.

[0164] Terminal: Receives the educational material and displays it to the user.

[0165] Step 3:

[0166] Users use the learning materials to study, solve problems, and take tests.

[0167] Input: User's learning behavior (operation history, test answers, etc.).

[0168] Terminal: Collects operation history and test results in real time and sends them to the server.

[0169] Data calculation: Collects and formats operation history and test result data in real time.

[0170] Output: Cleaned training data.

[0171] Server: Receives the training data and stores it in a database.

[0172] Step 4:

[0173] The server inputs the collected data into a generative AI model.

[0174] Input: Cleaned training data.

[0175] Server: Inputs training data into the generative AI model.

[0176] Data computation: The generative AI model analyzes the training data to identify the user's thinking patterns and cognitive style.

[0177] Output: Analysis results (user's strengths, weaknesses, thinking patterns, etc.).

[0178] Server: Automatically generates personalized educational content based on the analysis results.

[0179] Step 5:

[0180] Based on the analysis results of the generative AI model, personalized educational content is provided.

[0181] Input: Analysis results.

[0182] Server: Generates new educational content and sends it to the user's device.

[0183] Data calculation: Based on the analysis results, an algorithm is executed to generate optimal educational content.

[0184] Output: personalized educational content.

[0185] Terminal: Receives new educational content and displays it to the user.

[0186] Step 6:

[0187] The server monitors the learner's progress in real time and generates feedback.

[0188] Input: User learning progress data, analysis results.

[0189] Server: Generates feedback based on progress data and analysis results.

[0190] Data Calculation: Runs algorithms that analyze progress data and generate the necessary feedback.

[0191] Output: Feedback message.

[0192] Server: Notifies the user's device of the generated feedback.

[0193] Terminal: Receives feedback notifications and displays them to the user.

[0194] Through these steps, the system of the present invention responds to the individual needs of the learner and dynamically adjusts the educational program to provide effective learning and personal growth.

[0195] (Application example 1)

[0196] 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."

[0197] Traditional brick-and-mortar store customer experiences generally relied on standardized promotions and product proposals, which meant they could not adequately respond to the individual needs and purchasing patterns of each customer. Furthermore, it was difficult to provide dynamic product proposals in real time, making it difficult to provide an optimal purchasing experience based on customer interests. This limited the ability to improve customer satisfaction and maximize sales.

[0198] 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.

[0199] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for delivering the automatically generated educational content to the learner, means for dynamically adjusting the educational program according to the learner's progress, means for collecting customer operation history, purchase history, and movement data, means for analyzing the collected data and identifying the customer's purchasing pattern, means for automatically generating personalized product proposals based on the analysis results, means for delivering the automatically generated product proposals to the customer, and means for dynamically adjusting the product proposals according to the customer's situation. This makes it possible to personalize the customer's purchasing experience in a physical store in real time, improving customer satisfaction and maximizing sales.

[0200] "Student operation history" is a record of the operations performed by the learner on the system.

[0201] "Test results" refers to the grades or results of a test taken by a learner.

[0202] "Self-assessment" refers to data in which learners themselves evaluate their own learning content and progress.

[0203] "Means for collection" refers to the method or device for collecting user data into the system.

[0204] "Means for analyzing" refers to a method or device for analyzing collected data and extracting useful information.

[0205] "Means for identifying" refers to a method or device for recognizing a particular pattern or style based on the analyzed data.

[0206] "Personalized educational content" refers to educational materials that are customized to meet the needs of each individual learner.

[0207] "Means for automatic generation" refers to a method or device for automatically creating content based on the analysis results.

[0208] "Means for distribution" refers to a method or device for providing generated content to users.

[0209] "Dynamic adjustment means" refers to a method or device for changing the content of an educational program in real time or based on the learner's progress.

[0210] "Customer operation history" is a record of operations performed by a customer at a physical store or online store.

[0211] "Purchase history" is a record of products and services that a customer has purchased in the past.

[0212] "Movement data" refers to data on the locations where customers move within a physical store.

[0213] "Purchasing patterns" are the results of analyzing the trends and characteristics of customer purchasing behavior.

[0214] "Individualized product proposals" refer to individually optimized products that are proposed based on a customer's purchasing history and operation history.

[0215] This invention is a system that personalizes the customer's shopping experience in a physical store and improves customer satisfaction. To realize this embodiment, a server and a head-mounted display (HMD) are used. The hardware and software that make up this system, as well as the data processing method, are described in detail below.

[0216] Hardware and Software

[0217] Hardware:

[0218] Server: A server with high-performance computing resources that is responsible for analyzing data and generating content.

[0219] Head-mounted display (HMD): A device worn by the customer that displays content sent from the server.

[0220] Sensors (LiDAR, cameras) and Bluetooth beacons: Track customer movements within the store and collect data.

[0221] software:

[0222] Data collection module: Collects customer operation history, purchase history, and movement data in real time.

[0223] Data analysis module (using TensorFlow and PyTorch): Analyzes collected data to identify customer purchasing patterns and preferences.

[0224] Content generation module: Uses generative AI models to automatically generate personalized product recommendations.

[0225] Display module: delivers the generated content to the HMD and displays it to the customer.

[0226] Data processing and calculation

[0227] The server starts the process by having the customer put on the HMD when they enter the store and log in to the system. After logging in, the server performs the following processes:

[0228] 1. Data Collection:

[0229] Customers' past purchase history, movement data within the store, and operation history are collected in real time using sensors and Bluetooth beacons.

[0230] 2. Data Analysis:

[0231] The accumulated data is sent to a server and fed into a generative AI model, which uses TensorFlow and PyTorch to identify customer buying patterns and preferences.

[0232] 3. Content Generation:

[0233] Based on the analysis data, the system generates optimal product proposals and promotional information for customers. The generated content can be in the form of text, images, videos, etc.

[0234] 4. Content Delivery:

[0235] The generated content is delivered in real time to the HMD through the display module and displayed to the customer.

[0236] Specific examples

[0237] For example, if a customer has purchased a lot of red clothing in the past, the server will prioritize displaying new red items and discount information on the HMD. Also, if a customer shows a high interest in a particular brand, the server will provide real-time notifications of new arrivals and special sale information for that brand.

[0238] Prompt Sentence Examples

[0239] For example, you can input data into a generative AI model using prompt statements like the following:

[0240] Customer ID: 12345

[0241] Purchase history: Red clothes, black shoes

[0242] Operation history: clothing department, shoe department

[0243] As described above, this invention is a system that improves customer satisfaction and maximizes sales by personalizing the customer's purchasing experience in a physical store and making individualized product suggestions in real time.

[0244] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0245] Step 1:

[0246] First, the user (customer) wears a head-mounted display (HMD) and logs in to the system. The server verifies the customer's authentication information, and if authentication is successful, obtains the customer's profile data.

[0247] Enter your login credentials

[0248] Output: Customer profile data

[0249] Specific operation: When a customer wears an HMD and logs in, the device sends authentication information to the server. If authentication is successful, the server loads the customer's profile data.

[0250] Step 2:

[0251] The device uses sensors and Bluetooth beacons to collect customer location information, operation history, and purchase history, and this data is sent to a server in real time.

[0252] Input: Customer location information, operation history, purchase history

[0253] Output: Collected data

[0254] How it works: The device's sensors track the customer's movements within the store, and beacons identify the customer's location. Operation and purchase histories are also collected in real time.

[0255] Step 3:

[0256] The server analyzes the collected data and identifies customer purchasing patterns and preferences based on a generative AI model.

[0257] Input: Collected data (location information, operation history, purchase history)

[0258] Output: Purchasing patterns, customer preferences

[0259] How it works: The server inputs the collected data into a generative AI model using TensorFlow and PyTorch to identify customer purchasing patterns and preferences.

[0260] Step 4:

[0261] The server automatically generates personalized product suggestions and promotional information based on the analysis results.

[0262] Input: Purchasing patterns, customer preferences

[0263] Output: personalized product suggestions, promotional information

[0264] Specific operation: Based on the output of the generative AI model, the server creates optimal product proposals and promotional information for the customer.

[0265] Step 5:

[0266] Automatically generated product suggestions and promotional information are delivered to customers in real time via a head-mounted display.

[0267] Input: personalized product offers, promotional information

[0268] Output: Content displayed to the customer

[0269] Specific operation: The content generated by the server is sent to the HMD through the display module and displayed to the customer in real time.

[0270] Step 6:

[0271] When a customer selects a product or moves to a specific area, new data is sent to the server again, and the process of data analysis and product suggestions is repeated.

[0272] Input: New operation history, movement data

[0273] Output: Updated product offers and promotion information

[0274] What happens: Every time a customer takes a new action, that data is sent to the server, and the analysis and recommendation process continues.

[0275] This ensures that customers always have the latest information based on their interests and preferences, personalizing their shopping experience.

[0276] 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.

[0277] This system collects and analyzes learners' operation history, test results, and self-assessment data, and automatically generates and provides personalized educational content to them. Furthermore, it combines an emotion engine that recognizes and analyzes the learner's emotional state, aiming to provide a learning experience that is more emotionally adaptive. This system functions through the interaction of a server, terminals, and users.

[0278] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user of successful login. When the user selects the material they want to study from a list of provided materials, the server collects data on the selected material and sends it to the terminal. While using the material, the learner's operation history, test results, and self-assessment data are sent from the terminal to the server.

[0279] At the same time, the emotion engine analyzes the user's facial expressions, voice tone, sensor data, etc. in real time to recognize the user's emotional state. The collected operation data and emotion data are sent to the server and analyzed by the generative AI model.

[0280] The server analyzes the learner's thinking patterns, cognitive style, and emotional state based on this data. Based on the analysis results, personalized educational content is automatically generated. For example, if a learner struggles with geometry and feels stressed while solving problems, content combining geometry reinforcement questions and relaxing interactive games will be generated.

[0281] The generated educational content is sent from the server to the learner's device for use by the learner. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback based on the learner's progress and emotional state and notifies the device. The feedback includes the learner's achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[0282] Specific examples

[0283] Example 1: High school mathematics learning

[0284] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal. As the user solves geometry problems, the emotion engine analyzes the user's facial expressions and tone of voice to evaluate the level of stress the user is experiencing.

[0285] For example, if a user indicates a high level of stress in response to a problem, the data is sent to the server. The server analyzes this data using a generative AI model to identify the user's fear of geometry and stress. Based on this analysis, the server automatically generates a relaxing interactive game along with geometry reinforcement problems and provides them to the user's device.

[0286] The user continues learning with new educational content, and if they continue to feel stressed, they are offered more interactive relaxation content. The server monitors their progress and emotional state in real time, dynamically adjusting the educational program as needed. Feedback is also generated based on their achievements and learning progress.

[0287] In this way, the present invention can personalize educational content to the learner's needs and emotional state, providing a more effective and comfortable learning experience.

[0288] The processing flow will be explained below.

[0289] Step 1:

[0290] The user accesses the system from a terminal and logs in by entering the user ID and password.

[0291] Step 2:

[0292] The terminal transmits the entered authentication information to the server.

[0293] Step 3:

[0294] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[0295] Step 4:

[0296] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[0297] Step 5:

[0298] The terminal transmits the user's teaching material selection information to the server.

[0299] Step 6:

[0300] The server collects the selected teaching material data and transmits it to the terminal.

[0301] Step 7:

[0302] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[0303] Step 8:

[0304] The emotion engine analyzes the user's facial expressions, voice tone, and data from sensors to recognize the user's emotional state in real time.

[0305] Step 9:

[0306] The device records the user's operation history, test results, self-evaluation, emotional data, etc. in real time and transmits this data to the server.

[0307] Step 10:

[0308] The server preprocesses the received data and prepares it for input into the generative AI model.

[0309] Step 11:

[0310] The server feeds data into a generative AI model that analyzes the learner's thinking patterns, cognitive style, and emotional state.

[0311] Step 12:

[0312] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content. For example, if a learner is weak in geometry and experiences stress while solving problems, the server generates content that combines geometry reinforcement problems with relaxing interactive games.

[0313] Step 13:

[0314] The server sends the generated educational content to the terminal and displays it to the learner.

[0315] Step 14:

[0316] The user continues learning with new educational content, for example, new geometry reinforcement problems or relaxing games.

[0317] Step 15:

[0318] The device continuously transmits operation data, test results, and emotion data to the server.

[0319] Step 16:

[0320] The server collects this data and monitors progress and emotions in real time, dynamically adjusting the content and difficulty of the educational program as needed.

[0321] Step 17:

[0322] The server generates feedback based on the learner's progress and emotional state, including achievement, identification of weaknesses, recommended next learning steps, and advice on emotional state (e.g., how to relax).

[0323] Step 18:

[0324] The server generates feedback and sends it to the device.

[0325] Step 19:

[0326] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[0327] As a result, the system always provides the learner with the optimal educational environment and realizes a personalized learning experience that also takes into account their emotional state.

[0328] Example 2

[0329] 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."

[0330] The present invention solves the problem of conventional educational systems, which have difficulty adapting to the individual learning needs and emotional states of learners. Conventional systems have had difficulty accurately grasping each learner's learning data and emotional state and providing personalized educational content based on that data. Furthermore, they have been unable to provide real-time feedback based on the learner's emotional state, which has led to a problem of reduced learning effectiveness.

[0331] 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.

[0332] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for recognizing and analyzing the learner's emotional state in real time, and means for adjusting the educational content based on the recognized and analyzed emotional state, thereby making it possible to provide educational content adapted to the learner's individual learning needs and emotional state.

[0333] "Operation history" is a record of the operations performed by a learner on the system, including the number and location of clicks and taps, and the functions used.

[0334] "Test results" refers to the test scores and detailed data of the test taken by the learner, including specific scores, whether the answers were correct or incorrect, and the time it took to answer.

[0335] "Self-assessment" refers to data in which learners self-report their level of understanding and emotional state. For example, it includes a questionnaire in which learners rate their own level of understanding on a five-point scale.

[0336] "Thinking patterns" refer to the flow of thought and methods used by learners when solving problems. Examples include logical thinking and intuitive thinking.

[0337] "Cognitive style" refers to a learner's particular way or tendency to process information. Examples include visual, auditory, and kinesthetic information processing styles.

[0338] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate new content. For example, it includes models that use machine learning algorithms.

[0339] "Emotional state" refers to the learner's current emotional state, including, for example, feelings of stress, joy, excitement, fatigue, etc.

[0340] "Feedback" refers to advice or comments provided based on a learner's learning progress or emotional state, including information about achievement, identified weaknesses, and suggested next steps.

[0341] "Personalized educational content" refers to educational materials specifically designed based on a learner's thinking patterns, cognitive style, and emotional state, including, for example, specific remediation exercises and individualized learning plans.

[0342] "Means for recognition and analysis" refers to technical methods and devices for acquiring and analyzing data, including, for example, facial recognition systems and voice analysis systems.

[0343] The present invention is a system that automatically generates and provides personalized educational content to learners based on their operation history, test results, self-evaluation data, and emotional state. This system functions through the interaction of a server, terminals, and users.

[0344] Hardware and Software Configuration

[0345] Server: Stores and manages data and processes generative AI models.

[0346] Terminal (PC, tablet, etc.): Operates the user interface, transmits data, and runs the emotion engine.

[0347] User: Learner.

[0348] Processing flow

[0349] 1. Login and Authentication

[0350] A user logs in to the system using a terminal. The terminal sends the user's authentication information to the server, which verifies the authentication information and notifies the user if the login is successful.

[0351] 2. Select and send materials

[0352] The user selects the learning material they want to learn from a list of available learning materials, and the terminal sends this information to the server, which then collects the selected learning material data and provides it to the terminal.

[0353] 3. Data Collection

[0354] While the user is using the learning materials, the device collects operation history, test results, and self-evaluation data. The emotion engine also analyzes the user's facial expressions, voice tone, and sensor data in real time to recognize their emotional state. The collected operation and emotion data is then sent to the server.

[0355] 4. Data analysis and content generation

[0356] The server then passes the received data to a generative AI model for analysis. Based on the analysis results, personalized educational content is automatically generated. For example, if a user is weak in geometry and feels stressed, content including geometry reinforcement problems and relaxing interactive games will be generated.

[0357] 5. Content provision and dynamic adjustment

[0358] The generated educational content is sent from the server to the device for use by the user. The server monitors the learner's progress and emotional state in real time and dynamically adjusts the educational program as needed. It also generates feedback to the device, including achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[0359] Specific examples

[0360] Example 1: High school mathematics learning

[0361] 1. A high school student logs in to the system using a terminal. The terminal sends authentication information to the server, and if the server successfully authenticates, it generates a "Login successful" message.

[0362] 2. The user selects "Mathematics - Geometry" and the terminal sends the information to the server. The server retrieves the relevant geometry teaching material from the teaching material database and sends it to the terminal.

[0363] 3. While the user is solving geometry problems, the device records their operation history and test scores. At the same time, the emotion engine analyzes the user's facial expressions and recognizes that they are "highly stressed."

[0364] 4. The server inputs a prompt such as "high stress while learning geometry" into the generative AI model, analyzes it, and automatically generates geometry reinforcement problems and relaxation games and sends them to the device.

[0365] 5. The user continues learning by consuming new educational content. The server monitors the user's progress and emotional state in real time, generating feedback and displaying it on the device.

[0366] Prompt Sentence Examples

[0367] "Contents to support users who feel high stress while learning geometry"

[0368] "Next steps provided when users have gained a deeper understanding of basic mathematical problems"

[0369] In this way, the present invention can provide educational content that is adapted to the learner's individual learning needs and emotional state, providing a more effective and comfortable learning experience.

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] Step 1:

[0372] Login and Authentication

[0373] Input: The authentication information the user enters at the device (e.g., username and password)

[0374] Specific behavior:

[0375] The user enters authentication information into the login screen on the terminal.

[0376] The terminal sends this authentication information to the server.

[0377] The server checks the received authentication information against an authentication database.

[0378] Data processing and calculation: The server searches the authentication database to verify that the entered username and password match.

[0379] Output: If authentication is successful, the server sends a login success response to the terminal. If authentication fails, it sends an error message.

[0380] Step 2:

[0381] Selecting and sending materials

[0382] Input: Information about the learning material selected by the user (e.g., "Mathematics - Geometry")

[0383] Specific behavior:

[0384] The user selects the material they want to learn from a list of materials provided on the terminal.

[0385] The terminal transmits the selected teaching material information to the server.

[0386] The server collects data on the selected teaching materials from the teaching material database.

[0387] Data processing and calculation: The server obtains information about the selected teaching material and extracts the data corresponding to that teaching material from the teaching material database.

[0388] Output: The server sends the teaching material data to the terminal.

[0389] Step 3:

[0390] Data collection

[0391] Input: User operation history, test results, self-evaluation data, and emotional data

[0392] Specific behavior:

[0393] While the user is using the learning materials, the device collects operation history (e.g., clicks, taps, and their locations and number of times), test results, and self-evaluations.

[0394] The emotion engine recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and data from sensors in real time.

[0395] The terminal transmits the collected data to the server.

[0396] Data processing and calculation: The emotion engine analyzes the collected emotion data and evaluates the user's emotional state (e.g., stress level).

[0397] Output: Emotional state information and operation history data as the analysis results are sent to the server.

[0398] Step 4:

[0399] Data analysis and content generation

[0400] Input: Operation history, test results, self-evaluation data, emotional data

[0401] Specific behavior:

[0402] The server passes the collected data to a generative AI model.

[0403] The generative AI model identifies a learner's thinking patterns, cognitive style, and emotional state based on operation history, test results, and emotional data.

[0404] Automatically generate personalized educational content using generative AI models.

[0405] Data processing and calculation: The generative AI model analyzes the input data and generates educational content that suits the user's learning needs and emotional state.

[0406] Output: Generate personalized educational content data and return it to the server.

[0407] Step 5:

[0408] Content provision and dynamic adjustment

[0409] Input: Generated educational content data

[0410] Specific behavior:

[0411] The server transmits the generated educational content to the terminal.

[0412] The terminal displays the received educational content to the user and makes it available for use.

[0413] The server monitors the learner's progress and emotional state in real time.

[0414] If necessary, the generative AI model will make further adaptive adjustments to the educational content.

[0415] Generate and send feedback to the device.

[0416] Data processing and calculation: Feedback is generated by analyzing the user's progress data and emotional state data.

[0417] Output: Real-time adjusted educational content and feedback is displayed on the device.

[0418] The above is the flow of specific processing steps of this system.

[0419] (Application example 2)

[0420] 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."

[0421] In modern factory production lines, improving worker efficiency and reducing stress are important issues. There is also a need for automated support and training tailored to the characteristics of each individual worker. However, with conventional systems, it has been difficult to recognize and analyze a worker's emotional state in real time and provide individually optimized support content based on that information. Therefore, the present invention aims to solve these problems and provide a system that improves worker comfort and productivity in factories.

[0422] 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 collecting data such as a learner's operation history, test results, and self-assessment; means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and means for automatically generating personalized educational content based on the analysis results. This makes it possible to recognize and analyze the learner's emotional state using an emotion engine, collect the learner's work history and operation quality, and monitor work progress in real time. Furthermore, it becomes possible to automatically generate support content adapted to factory workers based on the collected emotion data and work data. This makes it possible to provide optimal support and feedback to individual workers, improving work efficiency and satisfaction.

[0423] An "operation history" is a record of a series of operations performed by a learner or worker using the system.

[0424] "Test results" are data obtained as a result of a test or assessment taken by a learner.

[0425] "Self-assessment" refers to the learner's own evaluation of their own knowledge and skills.

[0426] An "emotion engine" refers to a technology or system for recognizing and analyzing the emotional state of a learner or worker.

[0427] "Thinking patterns" are the tendencies and methods of thinking that learners generally adopt when studying or working.

[0428] A "cognitive style" is a set of tendencies or styles in which a learner perceives and understands information.

[0429] "Educational content" refers to materials and information used to improve a learner's knowledge and skills.

[0430] "Personalized educational content" refers to teaching materials and information that are tailored to the characteristics and needs of each learner based on collected data.

[0431] A "learner" is a user who uses this system to learn knowledge and skills.

[0432] "Progress" is a state that indicates how far a learner or worker has progressed in the course of learning or work.

[0433] "Dynamic adjustment" refers to changing the content and difficulty in real time according to the situation of the learner or worker.

[0434] "Work quality" is an index for evaluating the quality and accuracy of work performed by a worker.

[0435] "Support content" refers to the guidance and assistance provided to learners and workers to enable them to study or work effectively.

[0436] "Real time" means reacting or processing immediately in accordance with actual time.

[0437] "Feedback" refers to information or advice given to learners or workers based on an evaluation of their current situation and progress.

[0438] System Program

[0439] The system for realizing this invention collects and analyzes data such as the learner's or worker's operation history, test results, and self-assessment, and automatically generates personalized content and support. This system includes an "emotion engine" that recognizes and analyzes the learner's emotional state in real time, and a part that generates support content based on the analysis results using a generative AI model.

[0440] Hardware and Software

[0441] Hardware

[0442] Device: Smartphone or head-mounted display

[0443] Camera: Used to capture the learner's facial expressions

[0444] Microphone: Used to collect learner voice

[0445] software

[0446] OpenCV: Image processing library, used for face detection

[0447] Keras: A deep learning library used to recognize emotional states.

[0448] SpeechRecognition: A speech recognition library used to obtain operation history from the speech of a learner or worker.

[0449] Cloud services: AWS or Google Cloud, used to analyze and manage collected data

[0450] Data processing and calculation

[0451] Data collection

[0452] The device collects the learner's or worker's operation history, test results, and self-assessment data in real time and sends them to the server. Using a camera and microphone, the emotion engine analyzes the learner's facial expressions and voice tone to recognize their emotional state.

[0453] Data analysis

[0454] The server receives the collected operation and emotion data and analyzes it using a generative AI model. This analysis identifies the learner's thinking patterns, cognitive style, and emotional state. It then monitors the learner's progress and dynamically adjusts the content and difficulty of the educational program as needed.

[0455] Content provision

[0456] Based on the analysis results, personalized educational content is automatically generated and delivered to the device. For example, if a factory worker is feeling stressed, relaxing content (e.g., music) will be provided to promote work progress.

[0457] Examples of concrete examples and prompts

[0458] For example, if a factory worker is identified as feeling high stress from a particular task, this data is sent to a server, where it is analyzed using a generative AI model and the result is the automatic delivery of relaxing music to help the worker reduce stress.

[0459] Prompt Sentence Examples

[0460] python

[0461] emotion_state = emotion_recognition(frame)

[0462] if emotion_state == 0:

[0463] print("Stress detection, relaxation content provided")

[0464] Relaxing music playback function

[0465] In this way, the present invention can improve the efficiency and comfort of workers in factories and provide optimal individual support adapted to their emotional state.

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1:

[0468] A user logs in to the system. The user enters their username and password into the terminal, and the terminal sends the authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user that login was successful. In this step, the user's authentication information is given as input, and the result of authentication success or failure is obtained as output.

[0469] Step 2:

[0470] The terminal collects the learner's or worker's operation history, test results, and self-assessment data. Specifically, this includes the operations performed by the user, the information entered, test answers, and self-assessment results. The collected data is sent to the server in real time. The input of this step is the user's operation data, and the output is the transmission of the collected data to the server.

[0471] Step 3:

[0472] The device uses the built-in camera and microphone to capture the user's facial expressions and vocal tone, which are then analyzed by the emotion engine. Specifically, facial expressions are detected using OpenCV, and emotional states are estimated using a deep learning model trained with Keras. Emotions are also recognized from audio data using the SpeechRecognition library. The input for this step is video and audio data from the camera and microphone, and the output is the emotion recognition results from the emotion engine.

[0473] Step 4:

[0474] The server analyzes the collected operation data and emotion data using a generative AI model. The purpose of the analysis is to identify the user's thought patterns, cognitive style, and emotional state. Machine learning and deep learning techniques are used for this analysis. The input for this step is operation data and emotion data, and the output is the analysis results as a user profile.

[0475] Step 5:

[0476] The server automatically generates personalized educational content based on the analysis results and sends it to the device. Specifically, based on the generative AI model, learning materials and support content optimal for the user's needs and current learning state are generated. For example, if the user is feeling stressed, relaxing music or interactive games are generated. The input of this step is the analysis results, and the output is the generated educational content.

[0477] Step 6:

[0478] The user uses the provided educational content to study or work. The device continuously monitors the user's progress and emotional state in real time. The collected data is sent back to the server, and the content and difficulty of the educational program are dynamically adjusted as needed. The input of this step is the generated educational content, and the output is the user's progress and real-time data.

[0479] Step 7:

[0480] The server generates feedback to be provided to the user and notifies the user through the device. The feedback includes achievement, learning progress, identified weaknesses, recommended next learning steps, and even advice on emotional state. The input of this step is the user's progress and emotional data, and the output is a feedback message.

[0481] 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.

[0482] 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.

[0483] 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.

[0484] [Second embodiment]

[0485] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0486] 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.

[0487] 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).

[0488] 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.

[0489] 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.

[0490] 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).

[0491] 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.

[0492] 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.

[0493] 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.

[0494] 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.

[0495] 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.

[0496] 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."

[0497] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[0498] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, the learning material selected by the user is provided. While using the learning material, data such as the learner's operation history, test results, and self-evaluation are sent from the terminal to the server.

[0499] The server collects this data and inputs it into a generative AI model for analysis. The AI ​​model performs detailed analysis of the data to identify the learner's thinking patterns and cognitive styles. Based on the results of this analysis, the server automatically generates educational content optimized for each learner.

[0500] The generated educational content is provided from the server to the learner's device, and the learner uses it to advance their studies. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback for the learner based on their learning progress and notifies them via their device.

[0501] Specific examples

[0502] Example 1: High school mathematics learning

[0503] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal.

[0504] When a user operates the learning material to solve geometry problems, the operation history and test results (e.g., answer to the problem, answer time, number of correct answers, etc.) are sent in real time from the device to the server. The server collects the data and inputs it into a generative AI model for analysis.

[0505] For example, the AI ​​model might determine that a user is strong in algebra but weak in geometry. Based on this analysis, the server automatically generates geometry reinforcement problems and provides them to the user's device. The user continues to solve the reinforcement problems, and the results are also sent back to the server.

[0506] The server uses this ongoing data to dynamically adjust the educational program to provide the user with an optimal learning experience, and also generates and notifies the user based on their progress, such as "Your understanding of a particular area of ​​geometry is improving."

[0507] In this way, the system of the present invention responds to the needs of individual learners and dynamically adjusts educational programs, thereby achieving effective learning and self-development.

[0508] The processing flow will be explained below.

[0509] Step 1:

[0510] The user accesses the system from a terminal and logs in by entering the user ID and password.

[0511] Step 2:

[0512] The terminal transmits the entered authentication information to the server.

[0513] Step 3:

[0514] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[0515] Step 4:

[0516] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[0517] Step 5:

[0518] The terminal transmits the user's teaching material selection information to the server.

[0519] Step 6:

[0520] The server collects the selected teaching material data and transmits it to the terminal.

[0521] Step 7:

[0522] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[0523] Step 8:

[0524] The device records data such as the user's operation history, test results, and self-evaluation in real time and transmits it to the server.

[0525] Step 9:

[0526] The server preprocesses the received data and prepares it for input into the generative AI model.

[0527] Step 10:

[0528] The server inputs data into the generated AI model, which analyzes the learner's thinking patterns and cognitive style.

[0529] Step 11:

[0530] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content.

[0531] Step 12:

[0532] The server sends the generated educational content to the terminal and displays it to the learner.

[0533] Step 13:

[0534] The user continues learning by accessing new educational content, for example, by working on new geometry reinforcement problems.

[0535] Step 14:

[0536] The device continuously transmits operation data and test results to the server.

[0537] Step 15:

[0538] The server collects this data, monitors progress, and dynamically adjusts the educational program to change difficulty or content as needed.

[0539] Step 16:

[0540] The server generates feedback based on the learner's progress, including achievement levels, identified weaknesses, and recommended next learning steps.

[0541] Step 17:

[0542] The server generates feedback and sends it to the device.

[0543] Step 18:

[0544] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[0545] With this, the system continues to provide the learner with the optimal educational environment at all times.

[0546] Example 1

[0547] 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."

[0548] Conventional educational systems have struggled to provide personalized educational content tailored to each learner's progress and level of understanding. Furthermore, because real-time data collection and analysis were not performed, it was not possible to quickly identify learners' characteristics and weaknesses, making it impossible to provide effective learning support. Furthermore, there were insufficient means of collecting data such as user operation history, test results, and self-assessments, making it difficult to provide appropriate feedback based on this data.

[0549] 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.

[0550] In this invention, the server includes a means for collecting data such as a learner's operation history, test results, and self-assessment; a means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and a means for automatically generating personalized educational content based on the analysis results. This enables the provision of an optimal educational program tailored to the characteristics of each learner. Furthermore, by providing a means for monitoring the collected data in real time and generating feedback, a means for notifying the learner of the generated feedback, and a means for inputting data into a generative AI model using simple prompts and obtaining analysis results, dynamic adjustments can be made according to the learner's progress, resulting in more effective learning support.

[0551] An "operation history" is a record of a series of operations and actions performed by a learner using an educational system.

[0552] "Test results" refers to the answers given by a learner to a test taken in an educational system, and information on whether the answers were correct or incorrect.

[0553] "Self-assessment" refers to data on the evaluation and feedback that the learner has given themselves regarding the learning content and their own level of understanding.

[0554] "Means for collecting data" refers to devices or programs that have the function of automatically recording and saving learners' operation history, test results, self-assessments, etc.

[0555] "Means for analyzing data" refers to devices or programs that use collected data to process the data and identify learners' thinking patterns and cognitive styles.

[0556] "Means for automatically generating personalized educational content" refers to devices or programs that automatically create learning materials, workbooks, etc. that are appropriate for each learner based on the results of data analysis.

[0557] A "means for dynamically adjusting an educational program" is a device or program that changes the difficulty level or content of teaching materials or programs in real time according to the learner's progress and level of understanding.

[0558] "Means for generating feedback" refers to devices or programs that create appropriate advice and guidance in real time based on the learner's learning situation and analysis results.

[0559] A "generative AI model" is an artificial intelligence model used to analyze collected data and identify learner characteristics and weaknesses.

[0560] A "prompt" is a simple text or command that is input to a generative AI model to instruct it on how to analyze.

[0561] A "system" is an integrated structure that integrates the above means, devices, and programs to provide educational services.

[0562] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[0563] System Overview

[0564] The system uses the following hardware and software:

[0565] Server: Collects data, analyzes, generates content, and generates feedback. It mainly consists of a database server and an application server that runs generative AI models.

[0566] Terminal: A device operated by the learner (user). It has user interface functions such as data entry, display of teaching materials, and feedback notifications. Devices that can be used include PCs, tablets, and smartphones.

[0567] Details of system processing

[0568] 1. User login

[0569] Terminal: The learner enters their ID and password on the login screen.

[0570] Server: Receives authentication information, compares it with the user database, and returns the authentication result to the terminal. If authentication is successful, generates learning dashboard data and sends it to the terminal.

[0571] Device: Displays the learning dashboard and allows users to start learning.

[0572] 2. Selection and provision of teaching materials

[0573] User: Select the subjects and materials to study on the dashboard.

[0574] Terminal: Sends the selected teaching material request to the server.

[0575] Server: Receives the request, retrieves the relevant teaching material data from the teaching material database, and sends it to the terminal.

[0576] Terminal: Display the teaching materials.

[0577] 3. Data Collection

[0578] Users: Use the materials to study, solve problems, and take tests.

[0579] Terminal: Collects operation history and test results (answers to questions, answer time, number of correct answers, etc.) in real time and sends them to the server.

[0580] 4. Data Analysis

[0581] Server: Inputs collected data into the generative AI model.

[0582] Generative AI models: Analyze data in detail to identify a user's thinking patterns and cognitive styles, for example, identifying that a user is good at algebra but poor at geometry.

[0583] Server: Automatically generates personalized educational content based on the analysis results.

[0584] 5. Feedback and progress management

[0585] Server: Monitors learners' progress in real time, dynamically adjusts the content and difficulty of the learning materials as needed, and generates feedback based on the progress and sends it to the device.

[0586] Device: Displays feedback, notifications of new content, and provides learning guidance to users.

[0587] Specific examples

[0588] Example 1: High school mathematics learning

[0589] 1. Login and Dashboard

[0590] When a high school student (user) accesses the system and logs in, the server performs authentication and displays a learning dashboard to the user.

[0591] 2. Selecting and studying materials

[0592] When a user selects "Mathematics - Geometry," the server provides geometry teaching materials to the terminal. When the user manipulates the teaching materials to solve geometry problems, the operation history and test results are sent to the server.

[0593] 3. Data analysis and content generation

[0594] The server uses a generative AI model to analyze the user's data and determine whether the user is strong in algebra but weak in geometry. Based on the analysis results, the server automatically generates geometry reinforcement problems and provides them to the user's device.

[0595] 4. Dynamic Adjustment and Feedback

[0596] The server dynamically adjusts the educational program based on the user's progress, generates feedback such as "your understanding of a particular area of ​​geometry is improving," and notifies the user via their terminal.

[0597] Prompt Sentence Examples

[0598] Below are some example prompts to input to a generative AI model:

[0599] "My algebra skills are strong, but I struggle with geometry. Please generate teaching materials that will help me improve my geometry."

[0600] Based on this prompt, the AI ​​model can generate geometry reinforcement materials appropriate for the user.

[0601] In this way, the system of the present invention responds to the needs of each individual learner and dynamically adjusts the educational program, thereby realizing effective learning and self-development.

[0602] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0603] Step 1:

[0604] The user enters their ID and password on the login screen.

[0605] Input: User ID and password.

[0606] Terminal: Sends the entered authentication information to the server.

[0607] Server: Receives the authentication information and checks it against a database.

[0608] Data calculation: The authentication information is compared with the user information in the database to see if they match.

[0609] Output: Authentication result (success / failure).

[0610] Server: If authentication is successful, a learning dashboard is generated based on the user's learning history and progress data and sent to the device.

[0611] Terminal: Receives dashboard data and displays the learning dashboard.

[0612] Step 2:

[0613] The user selects the course and materials from the learning dashboard.

[0614] Input: User-selected study subjects and materials.

[0615] Terminal: Sends the selected data to the server.

[0616] Server: Receives the request and retrieves the corresponding teaching material data from the teaching material database.

[0617] Data calculation: Extract relevant teaching material data through a database search.

[0618] Output: Teaching material data.

[0619] Server: Sends the teaching material data to the terminal.

[0620] Terminal: Receives the educational material and displays it to the user.

[0621] Step 3:

[0622] Users use the learning materials to study, solve problems, and take tests.

[0623] Input: User's learning behavior (operation history, test answers, etc.).

[0624] Terminal: Collects operation history and test results in real time and sends them to the server.

[0625] Data calculation: Collects and formats operation history and test result data in real time.

[0626] Output: Cleaned training data.

[0627] Server: Receives the training data and stores it in a database.

[0628] Step 4:

[0629] The server inputs the collected data into a generative AI model.

[0630] Input: Cleaned training data.

[0631] Server: Inputs training data into the generative AI model.

[0632] Data computation: The generative AI model analyzes the training data to identify the user's thinking patterns and cognitive style.

[0633] Output: Analysis results (user's strengths, weaknesses, thinking patterns, etc.).

[0634] Server: Automatically generates personalized educational content based on the analysis results.

[0635] Step 5:

[0636] Based on the analysis results of the generative AI model, personalized educational content is provided.

[0637] Input: Analysis results.

[0638] Server: Generates new educational content and sends it to the user's device.

[0639] Data calculation: Based on the analysis results, an algorithm is executed to generate optimal educational content.

[0640] Output: personalized educational content.

[0641] Terminal: Receives new educational content and displays it to the user.

[0642] Step 6:

[0643] The server monitors the learner's progress in real time and generates feedback.

[0644] Input: User learning progress data, analysis results.

[0645] Server: Generates feedback based on progress data and analysis results.

[0646] Data Calculation: Runs algorithms that analyze progress data and generate the necessary feedback.

[0647] Output: Feedback message.

[0648] Server: Notifies the user's device of the generated feedback.

[0649] Terminal: Receives feedback notifications and displays them to the user.

[0650] Through these steps, the system of the present invention responds to the individual needs of the learner and dynamically adjusts the educational program to provide effective learning and personal growth.

[0651] (Application example 1)

[0652] 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."

[0653] Traditional brick-and-mortar store customer experiences generally relied on standardized promotions and product proposals, which meant they could not adequately respond to the individual needs and purchasing patterns of each customer. Furthermore, it was difficult to provide dynamic product proposals in real time, making it difficult to provide an optimal purchasing experience based on customer interests. This limited the ability to improve customer satisfaction and maximize sales.

[0654] 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.

[0655] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for delivering the automatically generated educational content to the learner, means for dynamically adjusting the educational program according to the learner's progress, means for collecting customer operation history, purchase history, and movement data, means for analyzing the collected data and identifying the customer's purchasing pattern, means for automatically generating personalized product proposals based on the analysis results, means for delivering the automatically generated product proposals to the customer, and means for dynamically adjusting the product proposals according to the customer's situation. This makes it possible to personalize the customer's purchasing experience in a physical store in real time, improving customer satisfaction and maximizing sales.

[0656] "Student operation history" is a record of the operations performed by the learner on the system.

[0657] "Test results" refers to the grades or results of a test taken by a learner.

[0658] "Self-assessment" refers to data in which learners themselves evaluate their own learning content and progress.

[0659] "Means for collection" refers to the method or device for collecting user data into the system.

[0660] "Means for analyzing" refers to a method or device for analyzing collected data and extracting useful information.

[0661] "Means for identifying" refers to a method or device for recognizing a particular pattern or style based on the analyzed data.

[0662] "Personalized educational content" refers to educational materials that are customized to meet the needs of each individual learner.

[0663] "Means for automatic generation" refers to a method or device for automatically creating content based on the analysis results.

[0664] "Means for distribution" refers to a method or device for providing generated content to users.

[0665] "Dynamic adjustment means" refers to a method or device for changing the content of an educational program in real time or based on the learner's progress.

[0666] "Customer operation history" is a record of operations performed by a customer at a physical store or online store.

[0667] "Purchase history" is a record of products and services that a customer has purchased in the past.

[0668] "Movement data" refers to data on the locations where customers move within a physical store.

[0669] "Purchasing patterns" are the results of analyzing the trends and characteristics of customer purchasing behavior.

[0670] "Individualized product proposals" refer to individually optimized products that are proposed based on a customer's purchasing history and operation history.

[0671] This invention is a system that personalizes the customer's shopping experience in a physical store and improves customer satisfaction. To realize this embodiment, a server and a head-mounted display (HMD) are used. The hardware and software that make up this system, as well as the data processing method, are described in detail below.

[0672] Hardware and Software

[0673] Hardware:

[0674] Server: A server with high-performance computing resources that is responsible for analyzing data and generating content.

[0675] Head-mounted display (HMD): A device worn by the customer that displays content sent from the server.

[0676] Sensors (LiDAR, cameras) and Bluetooth beacons: Track customer movements within the store and collect data.

[0677] software:

[0678] Data collection module: Collects customer operation history, purchase history, and movement data in real time.

[0679] Data analysis module (using TensorFlow and PyTorch): Analyzes collected data to identify customer purchasing patterns and preferences.

[0680] Content generation module: Uses generative AI models to automatically generate personalized product recommendations.

[0681] Display module: delivers the generated content to the HMD and displays it to the customer.

[0682] Data processing and calculation

[0683] The server starts the process by having the customer wear the HMD when they enter the store and log in to the system. After logging in, the server performs the following processes:

[0684] 1. Data Collection:

[0685] Customers' past purchase history, movement data within the store, and operation history are collected in real time using sensors and Bluetooth beacons.

[0686] 2. Data Analysis:

[0687] The accumulated data is sent to a server and fed into a generative AI model, which uses TensorFlow and PyTorch to identify customer buying patterns and preferences.

[0688] 3. Content Generation:

[0689] Based on the analysis data, the system generates optimal product proposals and promotional information for customers. The generated content can be in the form of text, images, videos, etc.

[0690] 4. Content Delivery:

[0691] The generated content is delivered in real time to the HMD through the display module and displayed to the customer.

[0692] Specific examples

[0693] For example, if a customer has purchased a lot of red clothing in the past, the server will prioritize displaying new red items and discount information on the HMD. Also, if a customer shows a high interest in a particular brand, the server will provide real-time notifications of new arrivals and special sale information for that brand.

[0694] Prompt Sentence Examples

[0695] For example, you can input data into a generative AI model using prompt statements like the following:

[0696] Customer ID: 12345

[0697] Purchase history: Red clothes, black shoes

[0698] Operation history: clothing department, shoe department

[0699] As described above, this invention is a system that improves customer satisfaction and maximizes sales by personalizing the customer's purchasing experience in a physical store and making individualized product suggestions in real time.

[0700] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0701] Step 1:

[0702] First, the user (customer) wears a head-mounted display (HMD) and logs in to the system. The server verifies the customer's authentication information, and if authentication is successful, obtains the customer's profile data.

[0703] Enter your login credentials

[0704] Output: Customer profile data

[0705] Specific operation: When a customer wears an HMD and logs in, the device sends authentication information to the server. If authentication is successful, the server loads the customer's profile data.

[0706] Step 2:

[0707] The device uses sensors and Bluetooth beacons to collect customer location information, operation history, and purchase history, and this data is sent to a server in real time.

[0708] Input: Customer location information, operation history, purchase history

[0709] Output: Collected data

[0710] How it works: The device's sensors track the customer's movements within the store, and beacons identify the customer's location. Operation and purchase histories are also collected in real time.

[0711] Step 3:

[0712] The server analyzes the collected data and identifies customer purchasing patterns and preferences based on a generative AI model.

[0713] Input: Collected data (location information, operation history, purchase history)

[0714] Output: Purchasing patterns, customer preferences

[0715] How it works: The server inputs the collected data into a generative AI model using TensorFlow and PyTorch to identify customer purchasing patterns and preferences.

[0716] Step 4:

[0717] The server automatically generates personalized product suggestions and promotional information based on the analysis results.

[0718] Input: Purchasing patterns, customer preferences

[0719] Output: personalized product suggestions, promotional information

[0720] Specific operation: Based on the output of the generative AI model, the server creates optimal product proposals and promotional information for the customer.

[0721] Step 5:

[0722] Automatically generated product suggestions and promotional information are delivered to customers in real time via a head-mounted display.

[0723] Input: personalized product offers, promotional information

[0724] Output: Content displayed to the customer

[0725] Specific operation: The content generated by the server is sent to the HMD through the display module and displayed to the customer in real time.

[0726] Step 6:

[0727] When a customer selects a product or moves to a specific area, new data is sent to the server again, and the process of data analysis and product suggestions is repeated.

[0728] Input: New operation history, movement data

[0729] Output: Updated product offers and promotion information

[0730] What happens: Every time a customer takes a new action, that data is sent to the server, and the analysis and recommendation process continues.

[0731] This ensures that customers always have the latest information based on their interests and preferences, personalizing their shopping experience.

[0732] 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.

[0733] This system collects and analyzes learners' operation history, test results, and self-assessment data, and automatically generates and provides personalized educational content to them. Furthermore, it combines an emotion engine that recognizes and analyzes the learner's emotional state, aiming to provide a learning experience that is more emotionally adaptive. This system functions through the interaction of a server, terminals, and users.

[0734] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user of successful login. When the user selects the material they want to study from a list of provided materials, the server collects data on the selected material and sends it to the terminal. While using the material, the learner's operation history, test results, and self-assessment data are sent from the terminal to the server.

[0735] At the same time, the emotion engine analyzes the user's facial expressions, voice tone, sensor data, etc. in real time to recognize the user's emotional state. The collected operation data and emotion data are sent to the server and analyzed by the generative AI model.

[0736] The server analyzes the learner's thinking patterns, cognitive style, and emotional state based on this data. Based on the analysis results, personalized educational content is automatically generated. For example, if a learner struggles with geometry and feels stressed while solving problems, content combining geometry reinforcement questions and relaxing interactive games will be generated.

[0737] The generated educational content is sent from the server to the learner's device for use by the learner. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback based on the learner's progress and emotional state and notifies the device. The feedback includes the learner's achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[0738] Specific examples

[0739] Example 1: High school mathematics learning

[0740] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal. As the user solves geometry problems, the emotion engine analyzes the user's facial expressions and tone of voice to evaluate the level of stress the user is experiencing.

[0741] For example, if a user indicates a high level of stress in response to a problem, the data is sent to the server. The server analyzes this data using a generative AI model to identify the user's fear of geometry and stress. Based on this analysis, the server automatically generates a relaxing interactive game along with geometry reinforcement problems and provides them to the user's device.

[0742] The user continues learning with new educational content, and if they continue to feel stressed, they are offered more interactive relaxation content. The server monitors their progress and emotional state in real time, dynamically adjusting the educational program as needed. Feedback is also generated based on their achievements and learning progress.

[0743] In this way, the present invention can personalize educational content to the learner's needs and emotional state, providing a more effective and comfortable learning experience.

[0744] The processing flow will be explained below.

[0745] Step 1:

[0746] The user accesses the system from a terminal and logs in by entering the user ID and password.

[0747] Step 2:

[0748] The terminal transmits the entered authentication information to the server.

[0749] Step 3:

[0750] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[0751] Step 4:

[0752] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[0753] Step 5:

[0754] The terminal transmits the user's teaching material selection information to the server.

[0755] Step 6:

[0756] The server collects the selected teaching material data and transmits it to the terminal.

[0757] Step 7:

[0758] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[0759] Step 8:

[0760] The emotion engine analyzes the user's facial expressions, voice tone, and data from sensors to recognize the user's emotional state in real time.

[0761] Step 9:

[0762] The device records the user's operation history, test results, self-evaluation, emotional data, etc. in real time and transmits this data to the server.

[0763] Step 10:

[0764] The server preprocesses the received data and prepares it for input into the generative AI model.

[0765] Step 11:

[0766] The server feeds data into a generative AI model that analyzes the learner's thinking patterns, cognitive style, and emotional state.

[0767] Step 12:

[0768] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content. For example, if a learner is weak in geometry and experiences stress while solving problems, the server generates content that combines geometry reinforcement problems with relaxing interactive games.

[0769] Step 13:

[0770] The server sends the generated educational content to the terminal and displays it to the learner.

[0771] Step 14:

[0772] The user continues learning with new educational content, for example, new geometry reinforcement problems or relaxing games.

[0773] Step 15:

[0774] The device continuously transmits operation data, test results, and emotion data to the server.

[0775] Step 16:

[0776] The server collects this data and monitors progress and emotions in real time, dynamically adjusting the content and difficulty of the educational program as needed.

[0777] Step 17:

[0778] The server generates feedback based on the learner's progress and emotional state, including achievement, identification of weaknesses, recommended next learning steps, and advice on emotional state (e.g., how to relax).

[0779] Step 18:

[0780] The server generates feedback and sends it to the device.

[0781] Step 19:

[0782] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[0783] As a result, the system always provides the learner with the optimal educational environment and realizes a personalized learning experience that also takes into account their emotional state.

[0784] Example 2

[0785] 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."

[0786] The present invention solves the problem of conventional educational systems, which have difficulty adapting to the individual learning needs and emotional states of learners. Conventional systems have had difficulty accurately grasping each learner's learning data and emotional state and providing personalized educational content based on that data. Furthermore, they have been unable to provide real-time feedback based on the learner's emotional state, which has led to a problem of reduced learning effectiveness.

[0787] 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.

[0788] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for recognizing and analyzing the learner's emotional state in real time, and means for adjusting the educational content based on the recognized and analyzed emotional state, thereby making it possible to provide educational content adapted to the learner's individual learning needs and emotional state.

[0789] "Operation history" is a record of the operations performed by a learner on the system, including the number and location of clicks and taps, and the functions used.

[0790] "Test results" refers to the test scores and detailed data of the test taken by the learner, including specific scores, whether the answers were correct or incorrect, and the time it took to answer.

[0791] "Self-assessment" refers to data in which learners self-report their level of understanding and emotional state. For example, it includes a questionnaire in which learners rate their own level of understanding on a five-point scale.

[0792] "Thinking patterns" refer to the flow of thought and methods used by learners when solving problems. Examples include logical thinking and intuitive thinking.

[0793] "Cognitive style" refers to a learner's particular way or tendency to process information. Examples include visual, auditory, and kinesthetic information processing styles.

[0794] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate new content. For example, it includes models that use machine learning algorithms.

[0795] "Emotional state" refers to the learner's current emotional state, including, for example, feelings of stress, joy, excitement, fatigue, etc.

[0796] "Feedback" refers to advice or comments provided based on a learner's learning progress or emotional state, including information about achievement, identified weaknesses, and suggested next steps.

[0797] "Personalized educational content" refers to educational materials specifically designed based on a learner's thinking patterns, cognitive style, and emotional state, including, for example, specific remediation exercises and individualized learning plans.

[0798] "Means for recognition and analysis" refers to technical methods and devices for acquiring and analyzing data, including, for example, facial recognition systems and voice analysis systems.

[0799] The present invention is a system that automatically generates and provides personalized educational content to learners based on their operation history, test results, self-evaluation data, and emotional state. This system functions through the interaction of a server, terminals, and users.

[0800] Hardware and Software Configuration

[0801] Server: Stores and manages data and processes generative AI models.

[0802] Terminal (PC, tablet, etc.): Operates the user interface, transmits data, and runs the emotion engine.

[0803] User: Learner.

[0804] Processing flow

[0805] 1. Login and Authentication

[0806] A user logs in to the system using a terminal. The terminal sends the user's authentication information to the server, which verifies the authentication information and notifies the user if the login is successful.

[0807] 2. Select and send materials

[0808] The user selects the learning material they want to learn from a list of available learning materials, and the terminal sends this information to the server, which then collects the selected learning material data and provides it to the terminal.

[0809] 3. Data Collection

[0810] While the user is using the learning materials, the device collects operation history, test results, and self-evaluation data. The emotion engine also analyzes the user's facial expressions, voice tone, and sensor data in real time to recognize their emotional state. The collected operation and emotion data is then sent to the server.

[0811] 4. Data analysis and content generation

[0812] The server then passes the received data to a generative AI model for analysis. Based on the analysis results, personalized educational content is automatically generated. For example, if a user is weak in geometry and feels stressed, content including geometry reinforcement problems and relaxing interactive games will be generated.

[0813] 5. Content provision and dynamic adjustment

[0814] The generated educational content is sent from the server to the device for use by the user. The server monitors the learner's progress and emotional state in real time and dynamically adjusts the educational program as needed. It also generates feedback to the device, including achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[0815] Specific examples

[0816] Example 1: High school mathematics learning

[0817] 1. A high school student logs in to the system using a terminal. The terminal sends authentication information to the server, and if the server successfully authenticates, it generates a "Login successful" message.

[0818] 2. The user selects "Mathematics - Geometry" and the terminal sends the information to the server. The server retrieves the relevant geometry teaching material from the teaching material database and sends it to the terminal.

[0819] 3. While the user is solving geometry problems, the device records their operation history and test scores. At the same time, the emotion engine analyzes the user's facial expressions and recognizes that they are "highly stressed."

[0820] 4. The server inputs a prompt such as "high stress while learning geometry" into the generative AI model, analyzes it, and automatically generates geometry reinforcement problems and relaxation games and sends them to the device.

[0821] 5. The user continues learning by consuming new educational content. The server monitors the user's progress and emotional state in real time, generating feedback and displaying it on the device.

[0822] Prompt Sentence Examples

[0823] "Contents to support users who feel high stress while learning geometry"

[0824] "Next steps provided when users have gained a deeper understanding of basic mathematical problems"

[0825] In this way, the present invention can provide educational content that is adapted to the learner's individual learning needs and emotional state, providing a more effective and comfortable learning experience.

[0826] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0827] Step 1:

[0828] Login and Authentication

[0829] Input: The authentication information the user enters at the device (e.g., username and password)

[0830] Specific behavior:

[0831] The user enters authentication information into the login screen on the terminal.

[0832] The terminal sends this authentication information to the server.

[0833] The server checks the received authentication information against an authentication database.

[0834] Data processing and calculation: The server searches the authentication database to verify that the entered username and password match.

[0835] Output: If authentication is successful, the server sends a login success response to the terminal. If authentication fails, it sends an error message.

[0836] Step 2:

[0837] Selecting and sending materials

[0838] Input: Information about the learning material selected by the user (e.g., "Mathematics - Geometry")

[0839] Specific behavior:

[0840] The user selects the material they want to learn from a list of materials provided on the terminal.

[0841] The terminal transmits the selected teaching material information to the server.

[0842] The server collects data on the selected teaching materials from the teaching material database.

[0843] Data processing and calculation: The server obtains information about the selected teaching material and extracts the data corresponding to that teaching material from the teaching material database.

[0844] Output: The server sends the teaching material data to the terminal.

[0845] Step 3:

[0846] Data collection

[0847] Input: User operation history, test results, self-evaluation data, and emotional data

[0848] Specific behavior:

[0849] While the user is using the learning materials, the device collects operation history (e.g., clicks, taps, and their locations and number of times), test results, and self-evaluations.

[0850] The emotion engine recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and data from sensors in real time.

[0851] The terminal transmits the collected data to the server.

[0852] Data processing and calculation: The emotion engine analyzes the collected emotion data and evaluates the user's emotional state (e.g., stress level).

[0853] Output: Emotional state information and operation history data as the analysis results are sent to the server.

[0854] Step 4:

[0855] Data analysis and content generation

[0856] Input: Operation history, test results, self-evaluation data, emotional data

[0857] Specific behavior:

[0858] The server passes the collected data to a generative AI model.

[0859] The generative AI model identifies a learner's thinking patterns, cognitive style, and emotional state based on operation history, test results, and emotional data.

[0860] Automatically generate personalized educational content using generative AI models.

[0861] Data processing and calculation: The generative AI model analyzes the input data and generates educational content that suits the user's learning needs and emotional state.

[0862] Output: Generate personalized educational content data and return it to the server.

[0863] Step 5:

[0864] Content provision and dynamic adjustment

[0865] Input: Generated educational content data

[0866] Specific behavior:

[0867] The server transmits the generated educational content to the terminal.

[0868] The terminal displays the received educational content to the user and makes it available for use.

[0869] The server monitors the learner's progress and emotional state in real time.

[0870] If necessary, the generative AI model will make further adaptive adjustments to the educational content.

[0871] Generate and send feedback to the device.

[0872] Data processing and calculation: Feedback is generated by analyzing the user's progress data and emotional state data.

[0873] Output: Real-time adjusted educational content and feedback is displayed on the device.

[0874] The above is the flow of specific processing steps of this system.

[0875] (Application example 2)

[0876] 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."

[0877] In modern factory production lines, improving worker efficiency and reducing stress are important issues. There is also a need for automated support and training tailored to the characteristics of each individual worker. However, with conventional systems, it has been difficult to recognize and analyze a worker's emotional state in real time and provide individually optimized support content based on that information. Therefore, the present invention aims to solve these problems and provide a system that improves worker comfort and productivity in factories.

[0878] 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 collecting data such as a learner's operation history, test results, and self-assessment; means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and means for automatically generating personalized educational content based on the analysis results. This makes it possible to recognize and analyze the learner's emotional state using an emotion engine, collect the learner's work history and operation quality, and monitor work progress in real time. Furthermore, it becomes possible to automatically generate support content adapted to factory workers based on the collected emotion data and work data. This makes it possible to provide optimal support and feedback to individual workers, improving work efficiency and satisfaction.

[0879] An "operation history" is a record of a series of operations performed by a learner or worker using the system.

[0880] "Test results" are data obtained as a result of a test or assessment taken by a learner.

[0881] "Self-assessment" refers to the learner's own evaluation of their own knowledge and skills.

[0882] An "emotion engine" refers to a technology or system for recognizing and analyzing the emotional state of a learner or worker.

[0883] "Thinking patterns" are the tendencies and methods of thinking that learners generally adopt when studying or working.

[0884] A "cognitive style" is a set of tendencies or styles in which a learner perceives and understands information.

[0885] "Educational content" refers to materials and information used to improve a learner's knowledge and skills.

[0886] "Personalized educational content" refers to teaching materials and information that are tailored to the characteristics and needs of each learner based on collected data.

[0887] A "learner" is a user who uses this system to learn knowledge and skills.

[0888] "Progress" is a state that indicates how far a learner or worker has progressed in the course of learning or work.

[0889] "Dynamic adjustment" refers to changing the content and difficulty in real time according to the situation of the learner or worker.

[0890] "Work quality" is an index for evaluating the quality and accuracy of work performed by a worker.

[0891] "Support content" refers to the guidance and assistance provided to learners and workers to enable them to study or work effectively.

[0892] "Real time" means reacting or processing immediately in accordance with actual time.

[0893] "Feedback" refers to information or advice given to learners or workers based on an evaluation of their current situation and progress.

[0894] System Program

[0895] The system for realizing this invention collects and analyzes data such as the learner's or worker's operation history, test results, and self-assessment, and automatically generates personalized content and support. This system includes an "emotion engine" that recognizes and analyzes the learner's emotional state in real time, and a part that generates support content based on the analysis results using a generative AI model.

[0896] Hardware and Software

[0897] Hardware

[0898] Device: Smartphone or head-mounted display

[0899] Camera: Used to capture the learner's facial expressions

[0900] Microphone: Used to collect learner voice

[0901] software

[0902] OpenCV: Image processing library, used for face detection

[0903] Keras: A deep learning library used to recognize emotional states.

[0904] SpeechRecognition: A speech recognition library used to obtain operation history from the speech of a learner or worker.

[0905] Cloud services: AWS or Google Cloud, used to analyze and manage collected data

[0906] Data processing and calculation

[0907] Data collection

[0908] The device collects the learner's or worker's operation history, test results, and self-assessment data in real time and sends them to the server. Using a camera and microphone, the emotion engine analyzes the learner's facial expressions and voice tone to recognize their emotional state.

[0909] Data analysis

[0910] The server receives the collected operation and emotion data and analyzes it using a generative AI model. This analysis identifies the learner's thinking patterns, cognitive style, and emotional state. It then monitors the learner's progress and dynamically adjusts the content and difficulty of the educational program as needed.

[0911] Content provision

[0912] Based on the analysis results, personalized educational content is automatically generated and delivered to the device. For example, if a factory worker is feeling stressed, relaxing content (e.g., music) will be provided to promote work progress.

[0913] Examples of concrete examples and prompts

[0914] For example, if a factory worker is identified as feeling high stress from a particular task, this data is sent to a server, where it is analyzed using a generative AI model and the result is the automatic delivery of relaxing music to help the worker reduce stress.

[0915] Prompt Sentence Examples

[0916] python

[0917] emotion_state = emotion_recognition(frame)

[0918] if emotion_state == 0:

[0919] print("Stress detection, relaxation content provided")

[0920] Relaxing music playback function

[0921] In this way, the present invention can improve the efficiency and comfort of workers in factories and provide optimal individual support adapted to their emotional state.

[0922] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0923] Step 1:

[0924] A user logs in to the system. The user enters their username and password into the terminal, and the terminal sends the authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user that login was successful. In this step, the user's authentication information is given as input, and the result of authentication success or failure is obtained as output.

[0925] Step 2:

[0926] The terminal collects the learner's or worker's operation history, test results, and self-assessment data. Specifically, this includes the operations performed by the user, the information entered, test answers, and self-assessment results. The collected data is sent to the server in real time. The input of this step is the user's operation data, and the output is the transmission of the collected data to the server.

[0927] Step 3:

[0928] The device uses the built-in camera and microphone to capture the user's facial expressions and vocal tone, which are then analyzed by the emotion engine. Specifically, facial expressions are detected using OpenCV, and emotional states are estimated using a deep learning model trained with Keras. Emotions are also recognized from audio data using the SpeechRecognition library. The input for this step is video and audio data from the camera and microphone, and the output is the emotion recognition results from the emotion engine.

[0929] Step 4:

[0930] The server analyzes the collected operation data and emotion data using a generative AI model. The purpose of the analysis is to identify the user's thought patterns, cognitive style, and emotional state. Machine learning and deep learning techniques are used for this analysis. The input for this step is operation data and emotion data, and the output is the analysis results as a user profile.

[0931] Step 5:

[0932] The server automatically generates personalized educational content based on the analysis results and sends it to the device. Specifically, based on the generative AI model, learning materials and support content optimal for the user's needs and current learning state are generated. For example, if the user is feeling stressed, relaxing music or interactive games are generated. The input of this step is the analysis results, and the output is the generated educational content.

[0933] Step 6:

[0934] The user uses the provided educational content to study or work. The device continuously monitors the user's progress and emotional state in real time. The collected data is sent back to the server, and the content and difficulty of the educational program are dynamically adjusted as needed. The input of this step is the generated educational content, and the output is the user's progress and real-time data.

[0935] Step 7:

[0936] The server generates feedback to be provided to the user and notifies the user through the device. The feedback includes achievement, learning progress, identified weaknesses, recommended next learning steps, and even advice on emotional state. The input of this step is the user's progress and emotional data, and the output is a feedback message.

[0937] 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.

[0938] 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.

[0939] 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.

[0940] [Third embodiment]

[0941] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0942] 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.

[0943] 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).

[0944] 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.

[0945] 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.

[0946] 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).

[0947] 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.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] 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.

[0952] 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."

[0953] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[0954] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, the learning material selected by the user is provided. While using the learning material, data such as the learner's operation history, test results, and self-evaluation are sent from the terminal to the server.

[0955] The server collects this data and inputs it into a generative AI model for analysis. The AI ​​model performs detailed analysis of the data to identify the learner's thinking patterns and cognitive styles. Based on the results of this analysis, the server automatically generates educational content optimized for each learner.

[0956] The generated educational content is provided from the server to the learner's device, and the learner uses it to advance their studies. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback for the learner based on their learning progress and notifies them via their device.

[0957] Specific examples

[0958] Example 1: High school mathematics learning

[0959] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal.

[0960] When a user operates the learning material to solve geometry problems, the operation history and test results (e.g., answer to the problem, answer time, number of correct answers, etc.) are sent in real time from the device to the server. The server collects the data and inputs it into a generative AI model for analysis.

[0961] For example, the AI ​​model might determine that a user is strong in algebra but weak in geometry. Based on this analysis, the server automatically generates geometry reinforcement problems and provides them to the user's device. The user continues to solve the reinforcement problems, and the results are also sent back to the server.

[0962] The server uses this ongoing data to dynamically adjust the educational program to provide the user with an optimal learning experience, and also generates and notifies the user based on their progress, such as "Your understanding of a particular area of ​​geometry is improving."

[0963] In this way, the system of the present invention responds to the needs of individual learners and dynamically adjusts educational programs, thereby achieving effective learning and self-development.

[0964] The processing flow will be explained below.

[0965] Step 1:

[0966] The user accesses the system from a terminal and logs in by entering the user ID and password.

[0967] Step 2:

[0968] The terminal transmits the entered authentication information to the server.

[0969] Step 3:

[0970] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[0971] Step 4:

[0972] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[0973] Step 5:

[0974] The terminal transmits the user's teaching material selection information to the server.

[0975] Step 6:

[0976] The server collects the selected teaching material data and transmits it to the terminal.

[0977] Step 7:

[0978] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[0979] Step 8:

[0980] The device records data such as the user's operation history, test results, and self-evaluation in real time and transmits it to the server.

[0981] Step 9:

[0982] The server preprocesses the received data and prepares it for input into the generative AI model.

[0983] Step 10:

[0984] The server inputs data into the generated AI model, which analyzes the learner's thinking patterns and cognitive style.

[0985] Step 11:

[0986] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content.

[0987] Step 12:

[0988] The server sends the generated educational content to the terminal and displays it to the learner.

[0989] Step 13:

[0990] The user continues learning by accessing new educational content, for example, by working on new geometry reinforcement problems.

[0991] Step 14:

[0992] The device continuously transmits operation data and test results to the server.

[0993] Step 15:

[0994] The server collects this data, monitors progress, and dynamically adjusts the educational program to change difficulty or content as needed.

[0995] Step 16:

[0996] The server generates feedback based on the learner's progress, including achievement levels, identified weaknesses, and recommended next learning steps.

[0997] Step 17:

[0998] The server generates feedback and sends it to the device.

[0999] Step 18:

[1000] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[1001] With this, the system continues to provide the learner with the optimal educational environment at all times.

[1002] Example 1

[1003] 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."

[1004] Conventional educational systems have struggled to provide personalized educational content tailored to each learner's progress and level of understanding. Furthermore, because real-time data collection and analysis were not performed, it was not possible to quickly identify learners' characteristics and weaknesses, making it impossible to provide effective learning support. Furthermore, there were insufficient means of collecting data such as user operation history, test results, and self-assessments, making it difficult to provide appropriate feedback based on this data.

[1005] 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.

[1006] In this invention, the server includes a means for collecting data such as a learner's operation history, test results, and self-assessment; a means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and a means for automatically generating personalized educational content based on the analysis results. This enables the provision of an optimal educational program tailored to the characteristics of each learner. Furthermore, by providing a means for monitoring the collected data in real time and generating feedback, a means for notifying the learner of the generated feedback, and a means for inputting data into a generative AI model using simple prompts and obtaining analysis results, dynamic adjustments can be made according to the learner's progress, resulting in more effective learning support.

[1007] An "operation history" is a record of a series of operations and actions performed by a learner using an educational system.

[1008] "Test results" refers to the answers given by a learner to a test taken in an educational system, and information on whether the answers were correct or incorrect.

[1009] "Self-assessment" refers to data on the evaluation and feedback that the learner has given themselves regarding the learning content and their own level of understanding.

[1010] "Means for collecting data" refers to devices or programs that have the function of automatically recording and saving learners' operation history, test results, self-assessments, etc.

[1011] "Means for analyzing data" refers to devices or programs that use collected data to process the data and identify learners' thinking patterns and cognitive styles.

[1012] "Means for automatically generating personalized educational content" refers to devices or programs that automatically create learning materials, workbooks, etc. that are appropriate for each learner based on the results of data analysis.

[1013] A "means for dynamically adjusting an educational program" is a device or program that changes the difficulty level or content of teaching materials or programs in real time according to the learner's progress and level of understanding.

[1014] "Means for generating feedback" refers to devices or programs that create appropriate advice and guidance in real time based on the learner's learning situation and analysis results.

[1015] A "generative AI model" is an artificial intelligence model used to analyze collected data and identify learner characteristics and weaknesses.

[1016] A "prompt" is a simple text or command that is input to a generative AI model to instruct it on how to analyze.

[1017] A "system" is an integrated structure that integrates the above means, devices, and programs to provide educational services.

[1018] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[1019] System Overview

[1020] The system uses the following hardware and software:

[1021] Server: Collects data, analyzes, generates content, and generates feedback. It mainly consists of a database server and an application server that runs generative AI models.

[1022] Terminal: A device operated by the learner (user). It has user interface functions such as data entry, display of teaching materials, and feedback notifications. Devices that can be used include PCs, tablets, and smartphones.

[1023] Details of system processing

[1024] 1. User login

[1025] Terminal: The learner enters their ID and password on the login screen.

[1026] Server: Receives authentication information, compares it with the user database, and returns the authentication result to the terminal. If authentication is successful, generates learning dashboard data and sends it to the terminal.

[1027] Device: Displays the learning dashboard and allows users to start learning.

[1028] 2. Selection and provision of teaching materials

[1029] User: Select the subjects and materials to study on the dashboard.

[1030] Terminal: Sends the selected teaching material request to the server.

[1031] Server: Receives the request, retrieves the relevant teaching material data from the teaching material database, and sends it to the terminal.

[1032] Terminal: Display the teaching materials.

[1033] 3. Data Collection

[1034] Users: Use the materials to study, solve problems, and take tests.

[1035] Terminal: Collects operation history and test results (answers to questions, answer time, number of correct answers, etc.) in real time and sends them to the server.

[1036] 4. Data Analysis

[1037] Server: Inputs collected data into the generative AI model.

[1038] Generative AI models: Analyze data in detail to identify a user's thinking patterns and cognitive styles, for example, identifying that a user is good at algebra but poor at geometry.

[1039] Server: Automatically generates personalized educational content based on the analysis results.

[1040] 5. Feedback and progress management

[1041] Server: Monitors learners' progress in real time, dynamically adjusts the content and difficulty of the learning materials as needed, and generates feedback based on the progress and sends it to the device.

[1042] Device: Displays feedback, notifications of new content, and provides learning guidance to users.

[1043] Specific examples

[1044] Example 1: High school mathematics learning

[1045] 1. Login and Dashboard

[1046] When a high school student (user) accesses the system and logs in, the server performs authentication and displays a learning dashboard to the user.

[1047] 2. Selecting and studying materials

[1048] When a user selects "Mathematics - Geometry," the server provides geometry teaching materials to the terminal. When the user manipulates the teaching materials to solve geometry problems, the operation history and test results are sent to the server.

[1049] 3. Data analysis and content generation

[1050] The server uses a generative AI model to analyze the user's data and determine whether the user is strong in algebra but weak in geometry. Based on the analysis results, the server automatically generates geometry reinforcement problems and provides them to the user's device.

[1051] 4. Dynamic Adjustment and Feedback

[1052] The server dynamically adjusts the educational program based on the user's progress, generates feedback such as "your understanding of a particular area of ​​geometry is improving," and notifies the user via their terminal.

[1053] Prompt Sentence Examples

[1054] Below are some example prompts to input to a generative AI model:

[1055] "My algebra skills are strong, but I struggle with geometry. Please generate teaching materials that will help me improve my geometry."

[1056] Based on this prompt, the AI ​​model can generate geometry reinforcement materials appropriate for the user.

[1057] In this way, the system of the present invention responds to the needs of each individual learner and dynamically adjusts the educational program, thereby realizing effective learning and self-development.

[1058] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1059] Step 1:

[1060] The user enters their ID and password on the login screen.

[1061] Input: User ID and password.

[1062] Terminal: Sends the entered authentication information to the server.

[1063] Server: Receives the authentication information and checks it against a database.

[1064] Data calculation: The authentication information is compared with the user information in the database to see if they match.

[1065] Output: Authentication result (success / failure).

[1066] Server: If authentication is successful, a learning dashboard is generated based on the user's learning history and progress data and sent to the device.

[1067] Terminal: Receives dashboard data and displays the learning dashboard.

[1068] Step 2:

[1069] The user selects the course and materials from the learning dashboard.

[1070] Input: User-selected study subjects and materials.

[1071] Terminal: Sends the selected data to the server.

[1072] Server: Receives the request and retrieves the corresponding teaching material data from the teaching material database.

[1073] Data calculation: Extract relevant teaching material data through a database search.

[1074] Output: Teaching material data.

[1075] Server: Sends the teaching material data to the terminal.

[1076] Terminal: Receives the educational material and displays it to the user.

[1077] Step 3:

[1078] Users use the learning materials to study, solve problems, and take tests.

[1079] Input: User's learning behavior (operation history, test answers, etc.).

[1080] Terminal: Collects operation history and test results in real time and sends them to the server.

[1081] Data calculation: Collects and formats operation history and test result data in real time.

[1082] Output: Cleaned training data.

[1083] Server: Receives the training data and stores it in a database.

[1084] Step 4:

[1085] The server inputs the collected data into a generative AI model.

[1086] Input: Cleaned training data.

[1087] Server: Inputs training data into the generative AI model.

[1088] Data computation: The generative AI model analyzes the training data to identify the user's thinking patterns and cognitive style.

[1089] Output: Analysis results (user's strengths, weaknesses, thinking patterns, etc.).

[1090] Server: Automatically generates personalized educational content based on the analysis results.

[1091] Step 5:

[1092] Based on the analysis results of the generative AI model, personalized educational content is provided.

[1093] Input: Analysis results.

[1094] Server: Generates new educational content and sends it to the user's device.

[1095] Data calculation: Based on the analysis results, an algorithm is executed to generate optimal educational content.

[1096] Output: personalized educational content.

[1097] Terminal: Receives new educational content and displays it to the user.

[1098] Step 6:

[1099] The server monitors the learner's progress in real time and generates feedback.

[1100] Input: User learning progress data, analysis results.

[1101] Server: Generates feedback based on progress data and analysis results.

[1102] Data Calculation: Runs algorithms that analyze progress data and generate the necessary feedback.

[1103] Output: Feedback message.

[1104] Server: Notifies the user's device of the generated feedback.

[1105] Terminal: Receives feedback notifications and displays them to the user.

[1106] Through these steps, the system of the present invention responds to the individual needs of the learner and dynamically adjusts the educational program to provide effective learning and personal growth.

[1107] (Application example 1)

[1108] 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."

[1109] Traditional brick-and-mortar store customer experiences generally relied on standardized promotions and product proposals, which meant they could not adequately respond to the individual needs and purchasing patterns of each customer. Furthermore, it was difficult to provide dynamic product proposals in real time, making it difficult to provide an optimal purchasing experience based on customer interests. This limited the ability to improve customer satisfaction and maximize sales.

[1110] 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.

[1111] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for delivering the automatically generated educational content to the learner, means for dynamically adjusting the educational program according to the learner's progress, means for collecting customer operation history, purchase history, and movement data, means for analyzing the collected data and identifying the customer's purchasing pattern, means for automatically generating personalized product proposals based on the analysis results, means for delivering the automatically generated product proposals to the customer, and means for dynamically adjusting the product proposals according to the customer's situation. This makes it possible to personalize the customer's purchasing experience in a physical store in real time, improving customer satisfaction and maximizing sales.

[1112] "Student operation history" is a record of the operations performed by the learner on the system.

[1113] "Test results" refers to the grades or results of a test taken by a learner.

[1114] "Self-assessment" refers to data in which learners themselves evaluate their own learning content and progress.

[1115] "Means for collection" refers to the method or device for collecting user data into the system.

[1116] "Means for analyzing" refers to a method or device for analyzing collected data and extracting useful information.

[1117] "Means for identifying" refers to a method or device for recognizing a particular pattern or style based on the analyzed data.

[1118] "Personalized educational content" refers to educational materials that are customized to meet the needs of each individual learner.

[1119] "Means for automatic generation" refers to a method or device for automatically creating content based on the analysis results.

[1120] "Means for distribution" refers to a method or device for providing generated content to users.

[1121] "Dynamic adjustment means" refers to a method or device for changing the content of an educational program in real time or based on the learner's progress.

[1122] "Customer operation history" is a record of operations performed by a customer at a physical store or online store.

[1123] "Purchase history" is a record of products and services that a customer has purchased in the past.

[1124] "Movement data" refers to data on the locations where customers move within a physical store.

[1125] "Purchasing patterns" are the results of analyzing the trends and characteristics of customer purchasing behavior.

[1126] "Individualized product proposals" refer to individually optimized products that are proposed based on a customer's purchasing history and operation history.

[1127] This invention is a system that personalizes the customer's shopping experience in a physical store and improves customer satisfaction. To realize this embodiment, a server and a head-mounted display (HMD) are used. The hardware and software that make up this system, as well as the data processing method, are described in detail below.

[1128] Hardware and Software

[1129] Hardware:

[1130] Server: A server with high-performance computing resources that is responsible for analyzing data and generating content.

[1131] Head-mounted display (HMD): A device worn by the customer that displays content sent from the server.

[1132] Sensors (LiDAR, cameras) and Bluetooth beacons: Track customer movements within the store and collect data.

[1133] software:

[1134] Data collection module: Collects customer operation history, purchase history, and movement data in real time.

[1135] Data analysis module (using TensorFlow and PyTorch): Analyzes collected data to identify customer purchasing patterns and preferences.

[1136] Content generation module: Uses generative AI models to automatically generate personalized product recommendations.

[1137] Display module: delivers the generated content to the HMD and displays it to the customer.

[1138] Data processing and calculation

[1139] The server starts the process by having the customer put on the HMD when they enter the store and log in to the system. After logging in, the server performs the following processes:

[1140] 1. Data Collection:

[1141] Customers' past purchase history, movement data within the store, and operation history are collected in real time using sensors and Bluetooth beacons.

[1142] 2. Data Analysis:

[1143] The accumulated data is sent to a server and fed into a generative AI model, which uses TensorFlow and PyTorch to identify customer buying patterns and preferences.

[1144] 3. Content Generation:

[1145] Based on the analysis data, the system generates optimal product proposals and promotional information for customers. The generated content can be in the form of text, images, videos, etc.

[1146] 4. Content Delivery:

[1147] The generated content is delivered in real time to the HMD through the display module and displayed to the customer.

[1148] Specific examples

[1149] For example, if a customer has purchased a lot of red clothing in the past, the server will prioritize displaying new red items and discount information on the HMD. Also, if a customer shows a high interest in a particular brand, the server will provide real-time notifications of new arrivals and special sale information for that brand.

[1150] Prompt Sentence Examples

[1151] For example, you can input data into a generative AI model using prompt statements like the following:

[1152] Customer ID: 12345

[1153] Purchase history: Red clothes, black shoes

[1154] Operation history: clothing department, shoe department

[1155] As described above, this invention is a system that improves customer satisfaction and maximizes sales by personalizing the customer's purchasing experience in a physical store and making individualized product suggestions in real time.

[1156] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1157] Step 1:

[1158] First, the user (customer) wears a head-mounted display (HMD) and logs in to the system. The server verifies the customer's authentication information, and if authentication is successful, obtains the customer's profile data.

[1159] Enter your login credentials

[1160] Output: Customer profile data

[1161] Specific operation: When a customer wears an HMD and logs in, the device sends authentication information to the server. If authentication is successful, the server loads the customer's profile data.

[1162] Step 2:

[1163] The device uses sensors and Bluetooth beacons to collect customer location information, operation history, and purchase history, and this data is sent to a server in real time.

[1164] Input: Customer location information, operation history, purchase history

[1165] Output: Collected data

[1166] How it works: The device's sensors track the customer's movements within the store, and beacons identify the customer's location. Operation and purchase histories are also collected in real time.

[1167] Step 3:

[1168] The server analyzes the collected data and identifies customer purchasing patterns and preferences based on a generative AI model.

[1169] Input: Collected data (location information, operation history, purchase history)

[1170] Output: Purchasing patterns, customer preferences

[1171] How it works: The server inputs the collected data into a generative AI model using TensorFlow and PyTorch to identify customer purchasing patterns and preferences.

[1172] Step 4:

[1173] The server automatically generates personalized product suggestions and promotional information based on the analysis results.

[1174] Input: Purchasing patterns, customer preferences

[1175] Output: personalized product suggestions, promotional information

[1176] Specific operation: Based on the output of the generative AI model, the server creates optimal product proposals and promotional information for the customer.

[1177] Step 5:

[1178] Automatically generated product suggestions and promotional information are delivered to customers in real time via a head-mounted display.

[1179] Input: personalized product offers, promotional information

[1180] Output: Content displayed to the customer

[1181] Specific operation: The content generated by the server is sent to the HMD through the display module and displayed to the customer in real time.

[1182] Step 6:

[1183] When a customer selects a product or moves to a specific area, new data is sent to the server again, and the process of data analysis and product suggestions is repeated.

[1184] Input: New operation history, movement data

[1185] Output: Updated product offers and promotion information

[1186] What happens: Every time a customer takes a new action, that data is sent to the server, and the analysis and recommendation process continues.

[1187] This ensures that customers always have the latest information based on their interests and preferences, personalizing their shopping experience.

[1188] 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.

[1189] This system collects and analyzes learners' operation history, test results, and self-assessment data, and automatically generates and provides personalized educational content to them. Furthermore, it combines an emotion engine that recognizes and analyzes the learner's emotional state, aiming to provide a learning experience that is more emotionally adaptive. This system functions through the interaction of a server, terminals, and users.

[1190] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user of successful login. When the user selects the material they want to study from a list of provided materials, the server collects data on the selected material and sends it to the terminal. While using the material, the learner's operation history, test results, and self-assessment data are sent from the terminal to the server.

[1191] At the same time, the emotion engine analyzes the user's facial expressions, voice tone, sensor data, etc. in real time to recognize the user's emotional state. The collected operation data and emotion data are sent to the server and analyzed by the generative AI model.

[1192] The server analyzes the learner's thinking patterns, cognitive style, and emotional state based on this data. Based on the analysis results, personalized educational content is automatically generated. For example, if a learner struggles with geometry and feels stressed while solving problems, content combining geometry reinforcement questions and relaxing interactive games will be generated.

[1193] The generated educational content is sent from the server to the learner's device for use by the learner. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback based on the learner's progress and emotional state and notifies the device. The feedback includes the learner's achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[1194] Specific examples

[1195] Example 1: High school mathematics learning

[1196] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal. As the user solves geometry problems, the emotion engine analyzes the user's facial expressions and tone of voice to evaluate the level of stress the user is experiencing.

[1197] For example, if a user indicates a high level of stress in response to a problem, the data is sent to the server. The server analyzes this data using a generative AI model to identify the user's fear of geometry and stress. Based on this analysis, the server automatically generates a relaxing interactive game along with geometry reinforcement problems and provides them to the user's device.

[1198] The user continues learning with new educational content, and if they continue to feel stressed, they are offered more interactive relaxation content. The server monitors their progress and emotional state in real time, dynamically adjusting the educational program as needed. Feedback is also generated based on their achievements and learning progress.

[1199] In this way, the present invention can personalize educational content to the learner's needs and emotional state, providing a more effective and comfortable learning experience.

[1200] The processing flow will be explained below.

[1201] Step 1:

[1202] The user accesses the system from a terminal and logs in by entering the user ID and password.

[1203] Step 2:

[1204] The terminal transmits the entered authentication information to the server.

[1205] Step 3:

[1206] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[1207] Step 4:

[1208] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[1209] Step 5:

[1210] The terminal transmits the user's teaching material selection information to the server.

[1211] Step 6:

[1212] The server collects the selected teaching material data and transmits it to the terminal.

[1213] Step 7:

[1214] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[1215] Step 8:

[1216] The emotion engine analyzes the user's facial expressions, voice tone, and data from sensors to recognize the user's emotional state in real time.

[1217] Step 9:

[1218] The device records the user's operation history, test results, self-evaluation, emotional data, etc. in real time and transmits this data to the server.

[1219] Step 10:

[1220] The server preprocesses the received data and prepares it for input into the generative AI model.

[1221] Step 11:

[1222] The server feeds data into a generative AI model that analyzes the learner's thinking patterns, cognitive style, and emotional state.

[1223] Step 12:

[1224] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content. For example, if a learner is weak in geometry and experiences stress while solving problems, the server generates content that combines geometry reinforcement problems with relaxing interactive games.

[1225] Step 13:

[1226] The server sends the generated educational content to the terminal and displays it to the learner.

[1227] Step 14:

[1228] The user continues learning with new educational content, for example, new geometry reinforcement problems or relaxing games.

[1229] Step 15:

[1230] The device continuously transmits operation data, test results, and emotion data to the server.

[1231] Step 16:

[1232] The server collects this data and monitors progress and emotions in real time, dynamically adjusting the content and difficulty of the educational program as needed.

[1233] Step 17:

[1234] The server generates feedback based on the learner's progress and emotional state, including achievement, identification of weaknesses, recommended next learning steps, and advice on emotional state (e.g., how to relax).

[1235] Step 18:

[1236] The server generates feedback and sends it to the device.

[1237] Step 19:

[1238] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[1239] As a result, the system always provides the learner with the optimal educational environment and realizes a personalized learning experience that also takes into account their emotional state.

[1240] Example 2

[1241] 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."

[1242] The present invention solves the problem of conventional educational systems, which have difficulty adapting to the individual learning needs and emotional states of learners. Conventional systems have had difficulty accurately grasping each learner's learning data and emotional state and providing personalized educational content based on that data. Furthermore, they have been unable to provide real-time feedback based on the learner's emotional state, which has led to a problem of reduced learning effectiveness.

[1243] 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.

[1244] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for recognizing and analyzing the learner's emotional state in real time, and means for adjusting the educational content based on the recognized and analyzed emotional state, thereby making it possible to provide educational content adapted to the learner's individual learning needs and emotional state.

[1245] "Operation history" is a record of the operations performed by a learner on the system, including the number and location of clicks and taps, and the functions used.

[1246] "Test results" refers to the test scores and detailed data of the test taken by the learner, including specific scores, whether the answers were correct or incorrect, and the time it took to answer.

[1247] "Self-assessment" refers to data in which learners self-report their level of understanding and emotional state. For example, it includes a questionnaire in which learners rate their own level of understanding on a five-point scale.

[1248] "Thinking patterns" refer to the flow of thought and methods used by learners when solving problems. Examples include logical thinking and intuitive thinking.

[1249] "Cognitive style" refers to a learner's particular way or tendency to process information. Examples include visual, auditory, and kinesthetic information processing styles.

[1250] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate new content. For example, it includes models that use machine learning algorithms.

[1251] "Emotional state" refers to the learner's current emotional state, including, for example, feelings of stress, joy, excitement, fatigue, etc.

[1252] "Feedback" refers to advice or comments provided based on a learner's learning progress or emotional state, including information about achievement, identified weaknesses, and suggested next steps.

[1253] "Personalized educational content" refers to educational materials specifically designed based on a learner's thinking patterns, cognitive style, and emotional state, including, for example, specific remediation exercises and individualized learning plans.

[1254] "Means for recognition and analysis" refers to technical methods and devices for acquiring and analyzing data, including, for example, facial recognition systems and voice analysis systems.

[1255] The present invention is a system that automatically generates and provides personalized educational content to learners based on their operation history, test results, self-evaluation data, and emotional state. This system functions through the interaction of a server, terminals, and users.

[1256] Hardware and Software Configuration

[1257] Server: Stores and manages data and processes generative AI models.

[1258] Terminal (PC, tablet, etc.): Operates the user interface, transmits data, and runs the emotion engine.

[1259] User: Learner.

[1260] Processing flow

[1261] 1. Login and Authentication

[1262] A user logs in to the system using a terminal. The terminal sends the user's authentication information to the server, which verifies the authentication information and notifies the user if the login is successful.

[1263] 2. Select and send materials

[1264] The user selects the learning material they want to learn from a list of available learning materials, and the terminal sends this information to the server, which then collects the selected learning material data and provides it to the terminal.

[1265] 3. Data Collection

[1266] While the user is using the learning materials, the device collects operation history, test results, and self-evaluation data. The emotion engine also analyzes the user's facial expressions, voice tone, and sensor data in real time to recognize their emotional state. The collected operation and emotion data is then sent to the server.

[1267] 4. Data analysis and content generation

[1268] The server then passes the received data to a generative AI model for analysis. Based on the analysis results, personalized educational content is automatically generated. For example, if a user is weak in geometry and feels stressed, content including geometry reinforcement problems and relaxing interactive games will be generated.

[1269] 5. Content provision and dynamic adjustment

[1270] The generated educational content is sent from the server to the device for use by the user. The server monitors the learner's progress and emotional state in real time and dynamically adjusts the educational program as needed. It also generates feedback to the device, including achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[1271] Specific examples

[1272] Example 1: High school mathematics learning

[1273] 1. A high school student logs in to the system using a terminal. The terminal sends authentication information to the server, and if the server successfully authenticates, it generates a "Login successful" message.

[1274] 2. The user selects "Mathematics - Geometry" and the terminal sends the information to the server. The server retrieves the relevant geometry teaching material from the teaching material database and sends it to the terminal.

[1275] 3. While the user is solving geometry problems, the device records their operation history and test scores. At the same time, the emotion engine analyzes the user's facial expressions and recognizes that they are "highly stressed."

[1276] 4. The server inputs a prompt such as "high stress while learning geometry" into the generative AI model, analyzes it, and automatically generates geometry reinforcement problems and relaxation games and sends them to the device.

[1277] 5. The user continues learning by consuming new educational content. The server monitors the user's progress and emotional state in real time, generating feedback and displaying it on the device.

[1278] Prompt Sentence Examples

[1279] "Contents to support users who feel high stress while learning geometry"

[1280] "Next steps provided when users have gained a deeper understanding of basic mathematical problems"

[1281] In this way, the present invention can provide educational content that is adapted to the learner's individual learning needs and emotional state, providing a more effective and comfortable learning experience.

[1282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1283] Step 1:

[1284] Login and Authentication

[1285] Input: The authentication information the user enters at the device (e.g., username and password)

[1286] Specific behavior:

[1287] The user enters authentication information into the login screen on the terminal.

[1288] The terminal sends this authentication information to the server.

[1289] The server checks the received authentication information against an authentication database.

[1290] Data processing and calculation: The server searches the authentication database to verify that the entered username and password match.

[1291] Output: If authentication is successful, the server sends a login success response to the terminal. If authentication fails, it sends an error message.

[1292] Step 2:

[1293] Selecting and sending materials

[1294] Input: Information about the learning material selected by the user (e.g., "Mathematics - Geometry")

[1295] Specific behavior:

[1296] The user selects the material they want to learn from a list of materials provided on the terminal.

[1297] The terminal transmits the selected teaching material information to the server.

[1298] The server collects data on the selected teaching materials from the teaching material database.

[1299] Data processing and calculation: The server obtains information about the selected teaching material and extracts the data corresponding to that teaching material from the teaching material database.

[1300] Output: The server sends the teaching material data to the terminal.

[1301] Step 3:

[1302] Data collection

[1303] Input: User operation history, test results, self-evaluation data, and emotional data

[1304] Specific behavior:

[1305] While the user is using the learning materials, the device collects operation history (e.g., clicks, taps, and their locations and number of times), test results, and self-evaluations.

[1306] The emotion engine recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and data from sensors in real time.

[1307] The terminal transmits the collected data to the server.

[1308] Data processing and calculation: The emotion engine analyzes the collected emotion data and evaluates the user's emotional state (e.g., stress level).

[1309] Output: Emotional state information and operation history data as the analysis results are sent to the server.

[1310] Step 4:

[1311] Data analysis and content generation

[1312] Input: Operation history, test results, self-evaluation data, emotional data

[1313] Specific behavior:

[1314] The server passes the collected data to a generative AI model.

[1315] The generative AI model identifies a learner's thinking patterns, cognitive style, and emotional state based on operation history, test results, and emotional data.

[1316] Automatically generate personalized educational content using generative AI models.

[1317] Data processing and calculation: The generative AI model analyzes the input data and generates educational content that suits the user's learning needs and emotional state.

[1318] Output: Generate personalized educational content data and return it to the server.

[1319] Step 5:

[1320] Content provision and dynamic adjustment

[1321] Input: Generated educational content data

[1322] Specific behavior:

[1323] The server transmits the generated educational content to the terminal.

[1324] The terminal displays the received educational content to the user and makes it available for use.

[1325] The server monitors the learner's progress and emotional state in real time.

[1326] If necessary, the generative AI model will make further adaptive adjustments to the educational content.

[1327] Generate and send feedback to the device.

[1328] Data processing and calculation: Feedback is generated by analyzing the user's progress data and emotional state data.

[1329] Output: Real-time adjusted educational content and feedback is displayed on the device.

[1330] The above is the flow of specific processing steps of this system.

[1331] (Application example 2)

[1332] 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."

[1333] In modern factory production lines, improving worker efficiency and reducing stress are important issues. There is also a need for automated support and training tailored to the characteristics of each individual worker. However, with conventional systems, it has been difficult to recognize and analyze a worker's emotional state in real time and provide individually optimized support content based on that information. Therefore, the present invention aims to solve these problems and provide a system that improves worker comfort and productivity in factories.

[1334] 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 collecting data such as a learner's operation history, test results, and self-assessment; means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and means for automatically generating personalized educational content based on the analysis results. This makes it possible to recognize and analyze the learner's emotional state using an emotion engine, collect the learner's work history and operation quality, and monitor work progress in real time. Furthermore, it becomes possible to automatically generate support content adapted to factory workers based on the collected emotion data and work data. This makes it possible to provide optimal support and feedback to individual workers, improving work efficiency and satisfaction.

[1335] An "operation history" is a record of a series of operations performed by a learner or worker using the system.

[1336] "Test results" are data obtained as a result of a test or assessment taken by a learner.

[1337] "Self-assessment" refers to the learner's own evaluation of their own knowledge and skills.

[1338] An "emotion engine" refers to a technology or system for recognizing and analyzing the emotional state of a learner or worker.

[1339] "Thinking patterns" are the tendencies and methods of thinking that learners generally adopt when studying or working.

[1340] A "cognitive style" is a set of tendencies or styles in which a learner perceives and understands information.

[1341] "Educational content" refers to materials and information used to improve a learner's knowledge and skills.

[1342] "Personalized educational content" refers to teaching materials and information that are tailored to the characteristics and needs of each learner based on collected data.

[1343] A "learner" is a user who uses this system to learn knowledge and skills.

[1344] "Progress" is a state that indicates how far a learner or worker has progressed in the course of learning or work.

[1345] "Dynamic adjustment" refers to changing the content and difficulty in real time according to the situation of the learner or worker.

[1346] "Work quality" is an index for evaluating the quality and accuracy of work performed by a worker.

[1347] "Support content" refers to the guidance and assistance provided to learners and workers to enable them to study or work effectively.

[1348] "Real time" means reacting or processing immediately in accordance with actual time.

[1349] "Feedback" refers to information or advice given to learners or workers based on an evaluation of their current situation and progress.

[1350] System Program

[1351] The system for realizing this invention collects and analyzes data such as the learner's or worker's operation history, test results, and self-assessment, and automatically generates personalized content and support. This system includes an "emotion engine" that recognizes and analyzes the learner's emotional state in real time, and a part that generates support content based on the analysis results using a generative AI model.

[1352] Hardware and Software

[1353] Hardware

[1354] Device: Smartphone or head-mounted display

[1355] Camera: Used to capture the learner's facial expressions

[1356] Microphone: Used to collect learner voice

[1357] software

[1358] OpenCV: Image processing library, used for face detection

[1359] Keras: A deep learning library used to recognize emotional states.

[1360] SpeechRecognition: A speech recognition library used to obtain operation history from the speech of a learner or worker.

[1361] Cloud services: AWS or Google Cloud, used to analyze and manage collected data

[1362] Data processing and calculation

[1363] Data collection

[1364] The device collects the learner's or worker's operation history, test results, and self-assessment data in real time and sends them to the server. Using a camera and microphone, the emotion engine analyzes the learner's facial expressions and voice tone to recognize their emotional state.

[1365] Data analysis

[1366] The server receives the collected operation and emotion data and analyzes it using a generative AI model. This analysis identifies the learner's thinking patterns, cognitive style, and emotional state. It then monitors the learner's progress and dynamically adjusts the content and difficulty of the educational program as needed.

[1367] Content provision

[1368] Based on the analysis results, personalized educational content is automatically generated and delivered to the device. For example, if a factory worker is feeling stressed, relaxing content (e.g., music) will be provided to promote work progress.

[1369] Examples of concrete examples and prompts

[1370] For example, if a factory worker is identified as feeling high stress from a particular task, this data is sent to a server, where it is analyzed using a generative AI model and the result is the automatic delivery of relaxing music to help the worker reduce stress.

[1371] Prompt Sentence Examples

[1372] python

[1373] emotion_state = emotion_recognition(frame)

[1374] if emotion_state == 0:

[1375] print("Stress detection, relaxation content provided")

[1376] Relaxing music playback function

[1377] In this way, the present invention can improve the efficiency and comfort of workers in factories and provide optimal individual support adapted to their emotional state.

[1378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1379] Step 1:

[1380] A user logs in to the system. The user enters their username and password into the terminal, and the terminal sends the authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user that login was successful. In this step, the user's authentication information is given as input, and the result of authentication success or failure is obtained as output.

[1381] Step 2:

[1382] The terminal collects the learner's or worker's operation history, test results, and self-assessment data. Specifically, this includes the operations performed by the user, the information entered, test answers, and self-assessment results. The collected data is sent to the server in real time. The input of this step is the user's operation data, and the output is the transmission of the collected data to the server.

[1383] Step 3:

[1384] The device uses the built-in camera and microphone to capture the user's facial expressions and vocal tone, which are then analyzed by the emotion engine. Specifically, facial expressions are detected using OpenCV, and emotional states are estimated using a deep learning model trained with Keras. Emotions are also recognized from audio data using the SpeechRecognition library. The input for this step is video and audio data from the camera and microphone, and the output is the emotion recognition results from the emotion engine.

[1385] Step 4:

[1386] The server analyzes the collected operation data and emotion data using a generative AI model. The purpose of the analysis is to identify the user's thought patterns, cognitive style, and emotional state. Machine learning and deep learning techniques are used for this analysis. The input for this step is operation data and emotion data, and the output is the analysis results as a user profile.

[1387] Step 5:

[1388] The server automatically generates personalized educational content based on the analysis results and sends it to the device. Specifically, based on the generative AI model, learning materials and support content optimal for the user's needs and current learning state are generated. For example, if the user is feeling stressed, relaxing music or interactive games are generated. The input of this step is the analysis results, and the output is the generated educational content.

[1389] Step 6:

[1390] The user uses the provided educational content to study or work. The device continuously monitors the user's progress and emotional state in real time. The collected data is sent back to the server, and the content and difficulty of the educational program are dynamically adjusted as needed. The input of this step is the generated educational content, and the output is the user's progress and real-time data.

[1391] Step 7:

[1392] The server generates feedback to be provided to the user and notifies the user through the device. The feedback includes achievement, learning progress, identified weaknesses, recommended next learning steps, and even advice on emotional state. The input of this step is the user's progress and emotional data, and the output is a feedback message.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] [Fourth embodiment]

[1397] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1398] 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.

[1399] 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).

[1400] 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.

[1401] 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.

[1402] 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).

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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."

[1410] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[1411] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, the learning material selected by the user is provided. While using the learning material, data such as the learner's operation history, test results, and self-evaluation are sent from the terminal to the server.

[1412] The server collects this data and inputs it into a generative AI model for analysis. The AI ​​model performs detailed analysis of the data to identify the learner's thinking patterns and cognitive styles. Based on the results of this analysis, the server automatically generates educational content optimized for each learner.

[1413] The generated educational content is provided from the server to the learner's device, and the learner uses it to advance their studies. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback for the learner based on their learning progress and notifies them via their device.

[1414] Specific examples

[1415] Example 1: High school mathematics learning

[1416] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal.

[1417] When a user operates the learning material to solve geometry problems, the operation history and test results (e.g., answer to the problem, answer time, number of correct answers, etc.) are sent in real time from the device to the server. The server collects the data and inputs it into a generative AI model for analysis.

[1418] For example, the AI ​​model might determine that a user is strong in algebra but weak in geometry. Based on this analysis, the server automatically generates geometry reinforcement problems and provides them to the user's device. The user continues to solve the reinforcement problems, and the results are also sent back to the server.

[1419] The server uses this ongoing data to dynamically adjust the educational program to provide the user with an optimal learning experience, and also generates and notifies the user based on their progress, such as "Your understanding of a particular area of ​​geometry is improving."

[1420] In this way, the system of the present invention responds to the needs of individual learners and dynamically adjusts educational programs, thereby achieving effective learning and self-development.

[1421] The processing flow will be explained below.

[1422] Step 1:

[1423] The user accesses the system from a terminal and logs in by entering the user ID and password.

[1424] Step 2:

[1425] The terminal transmits the entered authentication information to the server.

[1426] Step 3:

[1427] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[1428] Step 4:

[1429] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[1430] Step 5:

[1431] The terminal transmits the user's teaching material selection information to the server.

[1432] Step 6:

[1433] The server collects the selected teaching material data and transmits it to the terminal.

[1434] Step 7:

[1435] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[1436] Step 8:

[1437] The device records data such as the user's operation history, test results, and self-evaluation in real time and transmits it to the server.

[1438] Step 9:

[1439] The server preprocesses the received data and prepares it for input into the generative AI model.

[1440] Step 10:

[1441] The server inputs data into the generated AI model, which analyzes the learner's thinking patterns and cognitive style.

[1442] Step 11:

[1443] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content.

[1444] Step 12:

[1445] The server sends the generated educational content to the terminal and displays it to the learner.

[1446] Step 13:

[1447] The user continues learning by accessing new educational content, for example, by working on new geometry reinforcement problems.

[1448] Step 14:

[1449] The device continuously transmits operation data and test results to the server.

[1450] Step 15:

[1451] The server collects this data, monitors progress, and dynamically adjusts the educational program to change difficulty or content as needed.

[1452] Step 16:

[1453] The server generates feedback based on the learner's progress, including achievement levels, identified weaknesses, and recommended next learning steps.

[1454] Step 17:

[1455] The server generates feedback and sends it to the device.

[1456] Step 18:

[1457] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[1458] With this, the system continues to provide the learner with the optimal educational environment at all times.

[1459] Example 1

[1460] 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."

[1461] Conventional educational systems have struggled to provide personalized educational content tailored to each learner's progress and level of understanding. Furthermore, because real-time data collection and analysis were not performed, it was not possible to quickly identify learners' characteristics and weaknesses, making it impossible to provide effective learning support. Furthermore, there were insufficient means of collecting data such as user operation history, test results, and self-assessments, making it difficult to provide appropriate feedback based on this data.

[1462] 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.

[1463] In this invention, the server includes a means for collecting data such as a learner's operation history, test results, and self-assessment; a means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and a means for automatically generating personalized educational content based on the analysis results. This enables the provision of an optimal educational program tailored to the characteristics of each learner. Furthermore, by providing a means for monitoring the collected data in real time and generating feedback, a means for notifying the learner of the generated feedback, and a means for inputting data into a generative AI model using simple prompts and obtaining analysis results, dynamic adjustments can be made according to the learner's progress, resulting in more effective learning support.

[1464] An "operation history" is a record of a series of operations and actions performed by a learner using an educational system.

[1465] "Test results" refers to the answers given by a learner to a test taken in an educational system, and information on whether the answers were correct or incorrect.

[1466] "Self-assessment" refers to data on the evaluation and feedback that the learner has given themselves regarding the learning content and their own level of understanding.

[1467] "Means for collecting data" refers to devices or programs that have the function of automatically recording and saving learners' operation history, test results, self-assessments, etc.

[1468] "Means for analyzing data" refers to devices or programs that use collected data to process the data and identify learners' thinking patterns and cognitive styles.

[1469] "Means for automatically generating personalized educational content" refers to devices or programs that automatically create learning materials, workbooks, etc. that are appropriate for each learner based on the results of data analysis.

[1470] A "means for dynamically adjusting an educational program" is a device or program that changes the difficulty level or content of teaching materials or programs in real time according to the learner's progress and level of understanding.

[1471] "Means for generating feedback" refers to devices or programs that create appropriate advice and guidance in real time based on the learner's learning situation and analysis results.

[1472] A "generative AI model" is an artificial intelligence model used to analyze collected data and identify learner characteristics and weaknesses.

[1473] A "prompt" is a simple text or command that is input to a generative AI model to instruct it on how to analyze.

[1474] A "system" is an integrated structure that integrates the above means, devices, and programs to provide educational services.

[1475] This system collects and analyzes learners' operation history, test results, and self-assessment data, and then automatically generates and provides personalized educational content to learners. This system functions through interactions between a server, terminals, and users.

[1476] System Overview

[1477] The system uses the following hardware and software:

[1478] Server: Collects data, analyzes, generates content, and generates feedback. It mainly consists of a database server and an application server that runs generative AI models.

[1479] Terminal: A device operated by the learner (user). It has user interface functions such as data entry, display of teaching materials, and feedback notifications. Devices that can be used include PCs, tablets, and smartphones.

[1480] Details of system processing

[1481] 1. User login

[1482] Terminal: The learner enters their ID and password on the login screen.

[1483] Server: Receives authentication information, compares it with the user database, and returns the authentication result to the terminal. If authentication is successful, generates learning dashboard data and sends it to the terminal.

[1484] Device: Displays the learning dashboard and allows users to start learning.

[1485] 2. Selection and provision of teaching materials

[1486] User: Select the subjects and materials to study on the dashboard.

[1487] Terminal: Sends the selected teaching material request to the server.

[1488] Server: Receives the request, retrieves the relevant teaching material data from the teaching material database, and sends it to the terminal.

[1489] Terminal: Display the teaching materials.

[1490] 3. Data Collection

[1491] Users: Use the materials to study, solve problems, and take tests.

[1492] Terminal: Collects operation history and test results (answers to questions, answer time, number of correct answers, etc.) in real time and sends them to the server.

[1493] 4. Data Analysis

[1494] Server: Inputs collected data into the generative AI model.

[1495] Generative AI models: Analyze data in detail to identify a user's thinking patterns and cognitive styles, for example, identifying that a user is good at algebra but poor at geometry.

[1496] Server: Automatically generates personalized educational content based on the analysis results.

[1497] 5. Feedback and progress management

[1498] Server: Monitors learners' progress in real time, dynamically adjusts the content and difficulty of the learning materials as needed, and generates feedback based on the progress and sends it to the device.

[1499] Device: Displays feedback, notifications of new content, and provides learning guidance to users.

[1500] Specific examples

[1501] Example 1: High school mathematics learning

[1502] 1. Login and Dashboard

[1503] When a high school student (user) accesses the system and logs in, the server performs authentication and displays a learning dashboard to the user.

[1504] 2. Selecting and studying materials

[1505] When a user selects "Mathematics - Geometry," the server provides geometry teaching materials to the terminal. When the user manipulates the teaching materials to solve geometry problems, the operation history and test results are sent to the server.

[1506] 3. Data analysis and content generation

[1507] The server uses a generative AI model to analyze the user's data and determine whether the user is strong in algebra but weak in geometry. Based on the analysis results, the server automatically generates geometry reinforcement problems and provides them to the user's device.

[1508] 4. Dynamic Adjustment and Feedback

[1509] The server dynamically adjusts the educational program based on the user's progress, generates feedback such as "your understanding of a particular area of ​​geometry is improving," and notifies the user via their terminal.

[1510] Prompt Sentence Examples

[1511] Below are some example prompts to input to a generative AI model:

[1512] "My algebra skills are strong, but I struggle with geometry. Please generate teaching materials that will help me improve my geometry."

[1513] Based on this prompt, the AI ​​model can generate geometry reinforcement materials appropriate for the user.

[1514] In this way, the system of the present invention responds to the needs of each individual learner and dynamically adjusts the educational program, thereby realizing effective learning and self-development.

[1515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1516] Step 1:

[1517] The user enters their ID and password on the login screen.

[1518] Input: User ID and password.

[1519] Terminal: Sends the entered authentication information to the server.

[1520] Server: Receives the authentication information and checks it against a database.

[1521] Data calculation: The authentication information is compared with the user information in the database to see if they match.

[1522] Output: Authentication result (success / failure).

[1523] Server: If authentication is successful, a learning dashboard is generated based on the user's learning history and progress data and sent to the device.

[1524] Terminal: Receives dashboard data and displays the learning dashboard.

[1525] Step 2:

[1526] The user selects the course and materials from the learning dashboard.

[1527] Input: User-selected study subjects and materials.

[1528] Terminal: Sends the selected data to the server.

[1529] Server: Receives the request and retrieves the corresponding teaching material data from the teaching material database.

[1530] Data calculation: Extract relevant teaching material data through a database search.

[1531] Output: Teaching material data.

[1532] Server: Sends the teaching material data to the terminal.

[1533] Terminal: Receives the educational material and displays it to the user.

[1534] Step 3:

[1535] Users use the learning materials to study, solve problems, and take tests.

[1536] Input: User's learning behavior (operation history, test answers, etc.).

[1537] Terminal: Collects operation history and test results in real time and sends them to the server.

[1538] Data calculation: Collects and formats operation history and test result data in real time.

[1539] Output: Cleaned training data.

[1540] Server: Receives the training data and stores it in a database.

[1541] Step 4:

[1542] The server inputs the collected data into a generative AI model.

[1543] Input: Cleaned training data.

[1544] Server: Inputs training data into the generative AI model.

[1545] Data computation: The generative AI model analyzes the training data to identify the user's thinking patterns and cognitive style.

[1546] Output: Analysis results (user's strengths, weaknesses, thinking patterns, etc.).

[1547] Server: Automatically generates personalized educational content based on the analysis results.

[1548] Step 5:

[1549] Based on the analysis results of the generative AI model, personalized educational content is provided.

[1550] Input: Analysis results.

[1551] Server: Generates new educational content and sends it to the user's device.

[1552] Data calculation: Based on the analysis results, an algorithm is executed to generate optimal educational content.

[1553] Output: personalized educational content.

[1554] Terminal: Receives new educational content and displays it to the user.

[1555] Step 6:

[1556] The server monitors the learner's progress in real time and generates feedback.

[1557] Input: User learning progress data, analysis results.

[1558] Server: Generates feedback based on progress data and analysis results.

[1559] Data Calculation: Runs algorithms that analyze progress data and generate the necessary feedback.

[1560] Output: Feedback message.

[1561] Server: Notifies the user's device of the generated feedback.

[1562] Terminal: Receives feedback notifications and displays them to the user.

[1563] Through these steps, the system of the present invention responds to the individual needs of the learner and dynamically adjusts the educational program to provide effective learning and personal growth.

[1564] (Application example 1)

[1565] 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."

[1566] Traditional brick-and-mortar store customer experiences generally relied on standardized promotions and product proposals, which meant they could not adequately respond to the individual needs and purchasing patterns of each customer. Furthermore, it was difficult to provide dynamic product proposals in real time, making it difficult to provide an optimal purchasing experience based on customer interests. This limited the ability to improve customer satisfaction and maximize sales.

[1567] 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.

[1568] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for delivering the automatically generated educational content to the learner, means for dynamically adjusting the educational program according to the learner's progress, means for collecting customer operation history, purchase history, and movement data, means for analyzing the collected data and identifying the customer's purchasing pattern, means for automatically generating personalized product proposals based on the analysis results, means for delivering the automatically generated product proposals to the customer, and means for dynamically adjusting the product proposals according to the customer's situation. This makes it possible to personalize the customer's purchasing experience in a physical store in real time, improving customer satisfaction and maximizing sales.

[1569] "Student operation history" is a record of the operations performed by the learner on the system.

[1570] "Test results" refers to the grades or results of a test taken by a learner.

[1571] "Self-assessment" refers to data in which learners themselves evaluate their own learning content and progress.

[1572] "Means for collection" refers to the method or device for collecting user data into the system.

[1573] "Means for analyzing" refers to a method or device for analyzing collected data and extracting useful information.

[1574] "Means for identifying" refers to a method or device for recognizing a particular pattern or style based on the analyzed data.

[1575] "Personalized educational content" refers to educational materials that are customized to meet the needs of each individual learner.

[1576] "Means for automatic generation" refers to a method or device for automatically creating content based on the analysis results.

[1577] "Means for distribution" refers to a method or device for providing generated content to users.

[1578] "Dynamic adjustment means" refers to a method or device for changing the content of an educational program in real time or based on the learner's progress.

[1579] "Customer operation history" is a record of operations performed by a customer at a physical store or online store.

[1580] "Purchase history" is a record of products and services that a customer has purchased in the past.

[1581] "Movement data" refers to data on the locations where customers move within a physical store.

[1582] "Purchasing patterns" are the results of analyzing the trends and characteristics of customer purchasing behavior.

[1583] "Individualized product proposals" refer to individually optimized products that are proposed based on a customer's purchasing history and operation history.

[1584] This invention is a system that personalizes the customer's shopping experience in a physical store and improves customer satisfaction. To realize this embodiment, a server and a head-mounted display (HMD) are used. The hardware and software that make up this system, as well as the data processing method, are described in detail below.

[1585] Hardware and Software

[1586] Hardware:

[1587] Server: A server with high-performance computing resources that is responsible for analyzing data and generating content.

[1588] Head-mounted display (HMD): A device worn by the customer that displays content sent from the server.

[1589] Sensors (LiDAR, cameras) and Bluetooth beacons: Track customer movements within the store and collect data.

[1590] software:

[1591] Data collection module: Collects customer operation history, purchase history, and movement data in real time.

[1592] Data analysis module (using TensorFlow and PyTorch): Analyzes collected data to identify customer purchasing patterns and preferences.

[1593] Content generation module: Uses generative AI models to automatically generate personalized product recommendations.

[1594] Display module: delivers the generated content to the HMD and displays it to the customer.

[1595] Data processing and calculation

[1596] The server starts the process by having the customer put on the HMD when they enter the store and log in to the system. After logging in, the server performs the following processes:

[1597] 1. Data Collection:

[1598] Customers' past purchase history, movement data within the store, and operation history are collected in real time using sensors and Bluetooth beacons.

[1599] 2. Data Analysis:

[1600] The accumulated data is sent to a server and fed into a generative AI model, which uses TensorFlow and PyTorch to identify customer buying patterns and preferences.

[1601] 3. Content Generation:

[1602] Based on the analysis data, the system generates optimal product proposals and promotional information for customers. The generated content can be in the form of text, images, videos, etc.

[1603] 4. Content Delivery:

[1604] The generated content is delivered in real time to the HMD through the display module and displayed to the customer.

[1605] Specific examples

[1606] For example, if a customer has purchased a lot of red clothing in the past, the server will prioritize displaying new red items and discount information on the HMD. Also, if a customer shows a high interest in a particular brand, the server will provide real-time notifications of new arrivals and special sale information for that brand.

[1607] Prompt Sentence Examples

[1608] For example, you can input data into a generative AI model using prompt statements like the following:

[1609] Customer ID: 12345

[1610] Purchase history: Red clothes, black shoes

[1611] Operation history: clothing department, shoe department

[1612] As described above, this invention is a system that improves customer satisfaction and maximizes sales by personalizing the customer's purchasing experience in a physical store and making individualized product suggestions in real time.

[1613] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1614] Step 1:

[1615] First, the user (customer) wears a head-mounted display (HMD) and logs in to the system. The server verifies the customer's authentication information, and if authentication is successful, obtains the customer's profile data.

[1616] Enter your login credentials

[1617] Output: Customer profile data

[1618] Specific operation: When a customer wears an HMD and logs in, the device sends authentication information to the server. If authentication is successful, the server loads the customer's profile data.

[1619] Step 2:

[1620] The device uses sensors and Bluetooth beacons to collect customer location information, operation history, and purchase history, and this data is sent to a server in real time.

[1621] Input: Customer location information, operation history, purchase history

[1622] Output: Collected data

[1623] How it works: The device's sensors track the customer's movements within the store, and beacons identify the customer's location. Operation and purchase histories are also collected in real time.

[1624] Step 3:

[1625] The server analyzes the collected data and identifies customer purchasing patterns and preferences based on a generative AI model.

[1626] Input: Collected data (location information, operation history, purchase history)

[1627] Output: Purchasing patterns, customer preferences

[1628] How it works: The server inputs the collected data into a generative AI model using TensorFlow and PyTorch to identify customer purchasing patterns and preferences.

[1629] Step 4:

[1630] The server automatically generates personalized product suggestions and promotional information based on the analysis results.

[1631] Input: Purchasing patterns, customer preferences

[1632] Output: personalized product suggestions, promotional information

[1633] Specific operation: Based on the output of the generative AI model, the server creates optimal product proposals and promotional information for the customer.

[1634] Step 5:

[1635] Automatically generated product suggestions and promotional information are delivered to customers in real time via a head-mounted display.

[1636] Input: personalized product offers, promotional information

[1637] Output: Content displayed to the customer

[1638] Specific operation: The content generated by the server is sent to the HMD through the display module and displayed to the customer in real time.

[1639] Step 6:

[1640] When a customer selects a product or moves to a specific area, new data is sent to the server again, and the process of data analysis and product suggestions is repeated.

[1641] Input: New operation history, movement data

[1642] Output: Updated product offers and promotion information

[1643] What happens: Every time a customer takes a new action, that data is sent to the server, and the analysis and recommendation process continues.

[1644] This ensures that customers always have the latest information based on their interests and preferences, personalizing their shopping experience.

[1645] 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.

[1646] This system collects and analyzes learners' operation history, test results, and self-assessment data, and automatically generates and provides personalized educational content to them. Furthermore, it combines an emotion engine that recognizes and analyzes the learner's emotional state, aiming to provide a learning experience that is more emotionally adaptive. This system functions through the interaction of a server, terminals, and users.

[1647] When a learner logs in to the system, the terminal sends authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user of successful login. When the user selects the material they want to study from a list of provided materials, the server collects data on the selected material and sends it to the terminal. While using the material, the learner's operation history, test results, and self-assessment data are sent from the terminal to the server.

[1648] At the same time, the emotion engine analyzes the user's facial expressions, voice tone, sensor data, etc. in real time to recognize the user's emotional state. The collected operation data and emotion data are sent to the server and analyzed by the generative AI model.

[1649] The server analyzes the learner's thinking patterns, cognitive style, and emotional state based on this data. Based on the analysis results, personalized educational content is automatically generated. For example, if a learner struggles with geometry and feels stressed while solving problems, content combining geometry reinforcement questions and relaxing interactive games will be generated.

[1650] The generated educational content is sent from the server to the learner's device for use by the learner. The server monitors the learner's progress in real time and dynamically adjusts the content and difficulty of the educational program as needed. The server also generates feedback based on the learner's progress and emotional state and notifies the device. The feedback includes the learner's achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[1651] Specific examples

[1652] Example 1: High school mathematics learning

[1653] When a high school student (user) accesses the system and logs in, the server authenticates them and displays a learning dashboard to them. When the user selects "Mathematics - Geometry," the server provides geometry learning materials to the terminal. As the user solves geometry problems, the emotion engine analyzes the user's facial expressions and tone of voice to evaluate the level of stress the user is experiencing.

[1654] For example, if a user indicates a high level of stress in response to a problem, the data is sent to the server. The server analyzes this data using a generative AI model to identify the user's fear of geometry and stress. Based on this analysis, the server automatically generates a relaxing interactive game along with geometry reinforcement problems and provides them to the user's device.

[1655] The user continues learning with new educational content, and if they continue to feel stressed, they are offered more interactive relaxation content. The server monitors their progress and emotional state in real time, dynamically adjusting the educational program as needed. Feedback is also generated based on their achievements and learning progress.

[1656] In this way, the present invention can personalize educational content to the learner's needs and emotional state, providing a more effective and comfortable learning experience.

[1657] The processing flow will be explained below.

[1658] Step 1:

[1659] The user accesses the system from a terminal and logs in by entering the user ID and password.

[1660] Step 2:

[1661] The terminal transmits the entered authentication information to the server.

[1662] Step 3:

[1663] The server authenticates the user by checking the authentication information against a database, and if authentication is successful, starts a session and notifies the user that they have successfully logged in.

[1664] Step 4:

[1665] The user operates the terminal and selects the learning material they want to study from the list of available learning materials.

[1666] Step 5:

[1667] The terminal transmits the user's teaching material selection information to the server.

[1668] Step 6:

[1669] The server collects the selected teaching material data and transmits it to the terminal.

[1670] Step 7:

[1671] The user begins learning by using the learning materials, specifically by reading textbooks, watching videos, solving interactive problems, etc.

[1672] Step 8:

[1673] The emotion engine analyzes the user's facial expressions, voice tone, and data from sensors to recognize the user's emotional state in real time.

[1674] Step 9:

[1675] The device records the user's operation history, test results, self-evaluation, emotional data, etc. in real time and transmits this data to the server.

[1676] Step 10:

[1677] The server preprocesses the received data and prepares it for input into the generative AI model.

[1678] Step 11:

[1679] The server feeds data into a generative AI model that analyzes the learner's thinking patterns, cognitive style, and emotional state.

[1680] Step 12:

[1681] Based on the analysis results, the server uses an automatic generation algorithm to generate personalized educational content. For example, if a learner is weak in geometry and experiences stress while solving problems, the server generates content that combines geometry reinforcement problems with relaxing interactive games.

[1682] Step 13:

[1683] The server sends the generated educational content to the terminal and displays it to the learner.

[1684] Step 14:

[1685] The user continues learning with new educational content, for example, new geometry reinforcement problems or relaxing games.

[1686] Step 15:

[1687] The device continuously transmits operation data, test results, and emotion data to the server.

[1688] Step 16:

[1689] The server collects this data and monitors progress and emotions in real time, dynamically adjusting the content and difficulty of the educational program as needed.

[1690] Step 17:

[1691] The server generates feedback based on the learner's progress and emotional state, including achievement, identification of weaknesses, recommended next learning steps, and advice on emotional state (e.g., how to relax).

[1692] Step 18:

[1693] The server generates feedback and sends it to the device.

[1694] Step 19:

[1695] The device displays the feedback and notifies the user, who can then adjust their learning plan based on the feedback.

[1696] As a result, the system always provides the learner with the optimal educational environment and realizes a personalized learning experience that also takes into account their emotional state.

[1697] Example 2

[1698] 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."

[1699] The present invention solves the problem of conventional educational systems, which have difficulty adapting to the individual learning needs and emotional states of learners. Conventional systems have had difficulty accurately grasping each learner's learning data and emotional state and providing personalized educational content based on that data. Furthermore, they have been unable to provide real-time feedback based on the learner's emotional state, which has led to a problem of reduced learning effectiveness.

[1700] 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.

[1701] In this invention, the server includes means for collecting data such as a learner's operation history, test results, and self-assessment, means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style, means for automatically generating personalized educational content based on the analysis results, means for recognizing and analyzing the learner's emotional state in real time, and means for adjusting the educational content based on the recognized and analyzed emotional state, thereby making it possible to provide educational content adapted to the learner's individual learning needs and emotional state.

[1702] "Operation history" is a record of the operations performed by a learner on the system, including the number and location of clicks and taps, and the functions used.

[1703] "Test results" refers to the test scores and detailed data of the test taken by the learner, including specific scores, whether the answers were correct or incorrect, and the time it took to answer.

[1704] "Self-assessment" refers to data in which learners self-report their level of understanding and emotional state. For example, it includes a questionnaire in which learners rate their own level of understanding on a five-point scale.

[1705] "Thinking patterns" refer to the flow of thought and methods used by learners when solving problems. Examples include logical thinking and intuitive thinking.

[1706] "Cognitive style" refers to a learner's particular way or tendency to process information. Examples include visual, auditory, and kinesthetic information processing styles.

[1707] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate new content. For example, it includes models that use machine learning algorithms.

[1708] "Emotional state" refers to the learner's current emotional state, including, for example, feelings of stress, joy, excitement, fatigue, etc.

[1709] "Feedback" refers to advice or comments provided based on a learner's learning progress or emotional state, including information about achievement, identified weaknesses, and suggested next steps.

[1710] "Personalized educational content" refers to educational materials specifically designed based on a learner's thinking patterns, cognitive style, and emotional state, including, for example, specific remediation exercises and individualized learning plans.

[1711] "Means for recognition and analysis" refers to technical methods and devices for acquiring and analyzing data, including, for example, facial recognition systems and voice analysis systems.

[1712] The present invention is a system that automatically generates and provides personalized educational content to learners based on their operation history, test results, self-evaluation data, and emotional state. This system functions through the interaction of a server, terminals, and users.

[1713] Hardware and Software Configuration

[1714] Server: Stores and manages data and processes generative AI models.

[1715] Terminal (PC, tablet, etc.): Operates the user interface, transmits data, and runs the emotion engine.

[1716] User: Learner.

[1717] Processing flow

[1718] 1. Login and Authentication

[1719] A user logs in to the system using a terminal. The terminal sends the user's authentication information to the server, which verifies the authentication information and notifies the user if the login is successful.

[1720] 2. Select and send materials

[1721] The user selects the learning material they want to learn from a list of available learning materials, and the terminal sends this information to the server, which then collects the selected learning material data and provides it to the terminal.

[1722] 3. Data Collection

[1723] While the user is using the learning materials, the device collects operation history, test results, and self-evaluation data. The emotion engine also analyzes the user's facial expressions, voice tone, and sensor data in real time to recognize their emotional state. The collected operation and emotion data is then sent to the server.

[1724] 4. Data analysis and content generation

[1725] The server then passes the received data to a generative AI model for analysis. Based on the analysis results, personalized educational content is automatically generated. For example, if a user is weak in geometry and feels stressed, content including geometry reinforcement problems and relaxing interactive games will be generated.

[1726] 5. Content provision and dynamic adjustment

[1727] The generated educational content is sent from the server to the device for use by the user. The server monitors the learner's progress and emotional state in real time and dynamically adjusts the educational program as needed. It also generates feedback to the device, including achievement level, identified weaknesses, recommended next learning steps, and advice on emotional state (e.g., relaxation techniques).

[1728] Specific examples

[1729] Example 1: High school mathematics learning

[1730] 1. A high school student logs in to the system using a terminal. The terminal sends authentication information to the server, and if the server successfully authenticates, it generates a "Login successful" message.

[1731] 2. The user selects "Mathematics - Geometry" and the terminal sends the information to the server. The server retrieves the relevant geometry teaching material from the teaching material database and sends it to the terminal.

[1732] 3. While the user is solving geometry problems, the device records their operation history and test scores. At the same time, the emotion engine analyzes the user's facial expressions and recognizes that they are "highly stressed."

[1733] 4. The server inputs prompt statements such as "high stress while learning geometry" into the generative AI model, analyzes them, and automatically generates geometry reinforcement problems and relaxation games and sends them to the device.

[1734] 5. The user continues learning by consuming new educational content. The server monitors the user's progress and emotional state in real time, generating feedback and displaying it on the device.

[1735] Prompt Sentence Examples

[1736] "Contents to support users who feel high stress while learning geometry"

[1737] "Next steps provided when users have gained a deeper understanding of basic mathematical problems"

[1738] In this way, the present invention can provide educational content that is adapted to the learner's individual learning needs and emotional state, providing a more effective and comfortable learning experience.

[1739] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1740] Step 1:

[1741] Login and Authentication

[1742] Input: The authentication information the user enters at the device (e.g., username and password)

[1743] Specific behavior:

[1744] The user enters authentication information into the login screen on the terminal.

[1745] The terminal sends this authentication information to the server.

[1746] The server checks the received authentication information against an authentication database.

[1747] Data processing and calculation: The server searches the authentication database to verify that the entered username and password match.

[1748] Output: If authentication is successful, the server sends a login success response to the terminal. If authentication fails, it sends an error message.

[1749] Step 2:

[1750] Selecting and sending materials

[1751] Input: Information about the learning material selected by the user (e.g., "Mathematics - Geometry")

[1752] Specific behavior:

[1753] The user selects the material they want to learn from a list of materials provided on the terminal.

[1754] The terminal transmits the selected teaching material information to the server.

[1755] The server collects data on the selected teaching materials from the teaching material database.

[1756] Data processing and calculation: The server obtains information about the selected teaching material and extracts the data corresponding to that teaching material from the teaching material database.

[1757] Output: The server sends the teaching material data to the terminal.

[1758] Step 3:

[1759] Data collection

[1760] Input: User operation history, test results, self-evaluation data, and emotional data

[1761] Specific behavior:

[1762] While the user is using the learning materials, the device collects operation history (e.g., clicks, taps, and their locations and number of times), test results, and self-evaluations.

[1763] The emotion engine recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and data from sensors in real time.

[1764] The terminal transmits the collected data to the server.

[1765] Data processing and calculation: The emotion engine analyzes the collected emotion data and evaluates the user's emotional state (e.g., stress level).

[1766] Output: Emotional state information and operation history data as the analysis results are sent to the server.

[1767] Step 4:

[1768] Data analysis and content generation

[1769] Input: Operation history, test results, self-evaluation data, emotional data

[1770] Specific behavior:

[1771] The server passes the collected data to a generative AI model.

[1772] The generative AI model identifies a learner's thinking patterns, cognitive style, and emotional state based on operation history, test results, and emotional data.

[1773] Automatically generate personalized educational content using generative AI models.

[1774] Data processing and calculation: The generative AI model analyzes the input data and generates educational content that suits the user's learning needs and emotional state.

[1775] Output: Generate personalized educational content data and return it to the server.

[1776] Step 5:

[1777] Content provision and dynamic adjustment

[1778] Input: Generated educational content data

[1779] Specific behavior:

[1780] The server transmits the generated educational content to the terminal.

[1781] The terminal displays the received educational content to the user and makes it available for use.

[1782] The server monitors the learner's progress and emotional state in real time.

[1783] If necessary, the generative AI model will make further adaptive adjustments to the educational content.

[1784] Generate and send feedback to the device.

[1785] Data processing and calculation: Feedback is generated by analyzing the user's progress data and emotional state data.

[1786] Output: Real-time adjusted educational content and feedback is displayed on the device.

[1787] The above is the flow of specific processing steps of this system.

[1788] (Application example 2)

[1789] 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."

[1790] In modern factory production lines, improving worker efficiency and reducing stress are important issues. There is also a need for automated support and training tailored to the characteristics of each individual worker. However, with conventional systems, it has been difficult to recognize and analyze a worker's emotional state in real time and provide individually optimized support content based on that information. Therefore, the present invention aims to solve these problems and provide a system that improves worker comfort and productivity in factories.

[1791] 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 collecting data such as a learner's operation history, test results, and self-assessment; means for analyzing the collected data and identifying the learner's thinking pattern and cognitive style; and means for automatically generating personalized educational content based on the analysis results. This makes it possible to recognize and analyze the learner's emotional state using an emotion engine, collect the learner's work history and operation quality, and monitor work progress in real time. Furthermore, it becomes possible to automatically generate support content adapted to factory workers based on the collected emotion data and work data. This makes it possible to provide optimal support and feedback to individual workers, improving work efficiency and satisfaction.

[1792] An "operation history" is a record of a series of operations performed by a learner or worker using the system.

[1793] "Test results" are data obtained as a result of a test or assessment taken by a learner.

[1794] "Self-assessment" refers to the learner's own evaluation of their own knowledge and skills.

[1795] An "emotion engine" refers to a technology or system for recognizing and analyzing the emotional state of a learner or worker.

[1796] "Thinking patterns" are the tendencies and methods of thinking that learners generally adopt when studying or working.

[1797] A "cognitive style" is a set of tendencies or styles in which a learner perceives and understands information.

[1798] "Educational content" refers to materials and information used to improve a learner's knowledge and skills.

[1799] "Personalized educational content" refers to teaching materials and information that are tailored to the characteristics and needs of each learner based on collected data.

[1800] A "learner" is a user who uses this system to learn knowledge and skills.

[1801] "Progress" is a state that indicates how far a learner or worker has progressed in the course of learning or work.

[1802] "Dynamic adjustment" refers to changing the content and difficulty in real time according to the situation of the learner or worker.

[1803] "Work quality" is an index for evaluating the quality and accuracy of work performed by a worker.

[1804] "Support content" refers to the guidance and assistance provided to learners and workers to enable them to study or work effectively.

[1805] "Real time" means reacting or processing immediately in accordance with actual time.

[1806] "Feedback" refers to information or advice given to learners or workers based on an evaluation of their current situation and progress.

[1807] System Program

[1808] The system for realizing this invention collects and analyzes data such as the learner's or worker's operation history, test results, and self-assessment, and automatically generates personalized content and support. This system includes an "emotion engine" that recognizes and analyzes the learner's emotional state in real time, and a part that generates support content based on the analysis results using a generative AI model.

[1809] Hardware and Software

[1810] Hardware

[1811] Device: Smartphone or head-mounted display

[1812] Camera: Used to capture the learner's facial expressions

[1813] Microphone: Used to collect learner voice

[1814] software

[1815] OpenCV: Image processing library, used for face detection

[1816] Keras: A deep learning library used to recognize emotional states.

[1817] SpeechRecognition: A speech recognition library used to obtain operation history from the speech of a learner or worker.

[1818] Cloud services: AWS or Google Cloud, used to analyze and manage collected data

[1819] Data processing and calculation

[1820] Data collection

[1821] The device collects the learner's or worker's operation history, test results, and self-assessment data in real time and sends them to the server. Using a camera and microphone, the emotion engine analyzes the learner's facial expressions and voice tone to recognize their emotional state.

[1822] Data analysis

[1823] The server receives the collected operation and emotion data and analyzes it using a generative AI model. This analysis identifies the learner's thinking patterns, cognitive style, and emotional state. It then monitors the learner's progress and dynamically adjusts the content and difficulty of the educational program as needed.

[1824] Content provision

[1825] Based on the analysis results, personalized educational content is automatically generated and delivered to the device. For example, if a factory worker is feeling stressed, relaxing content (e.g., music) will be provided to promote work progress.

[1826] Examples of concrete examples and prompts

[1827] For example, if a factory worker is identified as feeling high stress from a particular task, this data is sent to a server, where it is analyzed using a generative AI model and the result is the automatic delivery of relaxing music to help the worker reduce stress.

[1828] Prompt Sentence Examples

[1829] python

[1830] emotion_state = emotion_recognition(frame)

[1831] if emotion_state == 0:

[1832] print("Stress detection, relaxation content provided")

[1833] Relaxing music playback function

[1834] In this way, the present invention can improve the efficiency and comfort of workers in factories and provide optimal individual support adapted to their emotional state.

[1835] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1836] Step 1:

[1837] A user logs in to the system. The user enters their username and password into the terminal, and the terminal sends the authentication information to the server. The server verifies the authentication information, and if authentication is successful, notifies the user that login was successful. In this step, the user's authentication information is given as input, and the result of authentication success or failure is obtained as output.

[1838] Step 2:

[1839] The terminal collects the learner's or worker's operation history, test results, and self-assessment data. Specifically, this includes the operations performed by the user, the information entered, test answers, and self-assessment results. The collected data is sent to the server in real time. The input of this step is the user's operation data, and the output is the transmission of the collected data to the server.

[1840] Step 3:

[1841] The device uses the built-in camera and microphone to capture the user's facial expressions and vocal tone, which are then analyzed by the emotion engine. Specifically, facial expressions are detected using OpenCV, and emotional states are estimated using a deep learning model trained with Keras. Emotions are also recognized from audio data using the SpeechRecognition library. The input for this step is video and audio data from the camera and microphone, and the output is the emotion recognition results from the emotion engine.

[1842] Step 4:

[1843] The server analyzes the collected operation data and emotion data using a generative AI model. The purpose of the analysis is to identify the user's thought patterns, cognitive style, and emotional state. Machine learning and deep learning techniques are used for this analysis. The input for this step is operation data and emotion data, and the output is the analysis results as a user profile.

[1844] Step 5:

[1845] The server automatically generates personalized educational content based on the analysis results and sends it to the device. Specifically, based on the generative AI model, learning materials and support content optimal for the user's needs and current learning state are generated. For example, if the user is feeling stressed, relaxing music or interactive games are generated. The input of this step is the analysis results, and the output is the generated educational content.

[1846] Step 6:

[1847] The user uses the provided educational content to study or work. The device continuously monitors the user's progress and emotional state in real time. The collected data is sent back to the server, and the content and difficulty of the educational program are dynamically adjusted as needed. The input of this step is the generated educational content, and the output is the user's progress and real-time data.

[1848] Step 7:

[1849] The server generates feedback to be provided to the user and notifies the user through the device. The feedback includes achievement, learning progress, identified weaknesses, recommended next learning steps, and even advice on emotional state. The input of this step is the user's progress and emotional data, and the output is a feedback message.

[1850] 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.

[1851] 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.

[1852] 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.

[1853] 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.

[1854] 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.

[1855] 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.

[1856] 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).

[1857] 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.

[1858] 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."

[1859] 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.

[1860] 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).

[1861] 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.

[1862] 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.

[1863] 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.

[1864] 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.

[1865] 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-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1866] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1867] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1868] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1869] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1870] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1871] The following is further disclosed regarding the above embodiment.

[1872] (Claim 1)

[1873] A means of collecting data such as learners' operation history, test results, and self-assessments;

[1874] a means of analyzing the collected data and identifying learners' thinking patterns and cognitive styles;

[1875] A means for automatically generating personalized educational content based on the analysis results;

[1876] a means for delivering automatically generated educational content to learners;

[1877] a means of dynamically adjusting the educational program according to the learner's progress;

[1878] A system including:

[1879] (Claim 2)

[1880] 10. The system of claim 1, wherein the system uses a generative AI model for analysis.

[1881] (Claim 3)

[1882] 10. The system of claim 1, further comprising means for generating and notifying the learner of feedback to be provided to the learner.

[1883] "Example 1"

[1884] (Claim 1)

[1885] A means of collecting data such as learners' operation history, test results, and self-assessments;

[1886] a means of analyzing the collected data and identifying learners' thinking patterns and cognitive styles;

[1887] A means for automatically generating personalized educational content based on the analysis results;

[1888] a means for delivering automatically generated educational content to learners;

[1889] a means of dynamically adjusting the educational program according to the learner's progress;

[1890] a means of monitoring the collected data in real time and generating feedback;

[1891] a means for notifying the learner of the generated feedback;

[1892] A means to input data into a generative AI model using simple prompts and obtain analytical results;

[1893] A system including:

[1894] (Claim 2)

[1895] 10. The system of claim 1, wherein the system uses a generative AI model for analysis.

[1896] (Claim 3)

[1897] 10. The system of claim 1, further comprising means for generating and notifying the learner of feedback to be provided to the learner.

[1898] "Application Example 1"

[1899] (Claim 1)

[1900] A means of collecting data such as learners' operation history, test results, and self-assessments;

[1901] a means of analyzing the collected data and identifying learners' thinking patterns and cognitive styles;

[1902] A means for automatically generating personalized educational content based on the analysis results;

[1903] a means for delivering automatically generated educational content to learners;

[1904] a means of dynamically adjusting the educational program according to the learner's progress;

[1905] A means for collecting customer operation history, purchase history, and movement data;

[1906] a means for analyzing the collected data to identify customer purchasing patterns;

[1907] means for automatically generating personalized product recommendations based on the analysis results;

[1908] a means for delivering automatically generated product suggestions to customers;

[1909] A means to dynamically adjust product recommendations based on customer circumstances;

[1910] A system including:

[1911] (Claim 2)

[1912] 10. The system of claim 1, wherein the system uses a generative AI model for analysis.

[1913] (Claim 3)

[1914] 10. The system of claim 1, further comprising means for generating and notifying the learner of feedback to be provided to the learner.

[1915] "Example 2: Combining Emotion Engines"

[1916] (Claim 1)

[1917] A means of collecting data such as learners' operation history, test results, and self-assessments;

[1918] a means of analyzing the collected data and identifying learners' thinking patterns and cognitive styles;

[1919] A means for automatically generating personalized educational content based on the analysis results;

[1920] a means for delivering automatically generated educational content to learners;

[1921] a means of dynamically adjusting the educational program according to the learner's progress;

[1922] A means of recognizing and analyzing the learner's emotional state in real time;

[1923] A means for adjusting educational content based on the recognized and analyzed emotional state;

[1924] A system including:

[1925] (Claim 2)

[1926] 10. The system of claim 1, which automatically generates analyzed and personalized educational content using a generative AI model.

[1927] (Claim 3)

[1928] 10. The system of claim 1, further comprising means for generating and notifying the learner of feedback to be provided to the learner.

[1929] "Application example 2 when combining emotion engines"

[1930] (Claim 1)

[1931] A means of collecting data such as learners' operation history, test results, and self-assessments;

[1932] a means of analyzing the collected data and identifying learners' thinking patterns and cognitive styles;

[1933] A means for automatically generating personalized educational content based on the analysis results;

[1934] a means for delivering automatically generated educational content to learners;

[1935] A means for recognizing and analyzing the emotional state of a learner using an emotion engine;

[1936] a means for collecting the learner's work history and operation quality and monitoring the work progress in real time;

[1937] A means for automatically generating support content adapted to factory workers based on the collected emotion data and work data;

[1938] a means of dynamically adjusting the educational program according to the learner's progress;

[1939] A system including:

[1940] (Claim 2)

[1941] 10. The system of claim 1, wherein the system uses a generative AI model for analysis.

[1942] (Claim 3)

[1943] 10. The system of claim 1, further comprising means for generating and notifying the learner of feedback to be provided to the learner. [Explanation of symbols]

[1944] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data such as learners' operation history, test results, and self-assessments; a means of analyzing the collected data and identifying learners' thinking patterns and cognitive styles; A means for automatically generating personalized educational content based on the analysis results; a means for delivering automatically generated educational content to learners; a means of dynamically adjusting the educational program according to the learner's progress; A system including:

2. The system of claim 1 , which uses a generative AI model for analysis.

3. 10. The system of claim 1, further comprising means for generating and notifying the learner of feedback to be provided to the learner.

Images