System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting student information via a user device; means for transmitting and securely storing student information to a server; means for analyzing student traits and extracting learning patterns using a generative AI model; means for dynamically generating and transmitting customized materials to a user device; and means for collecting learning progress information from a user device and transmitting the learning progress information to a server; wherein the server continuously analyzes progress information and optimizes material content using a generative AI model.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] Traditional educational methods often do not adequately consider the individual learning needs and pace of each student, which can lead to reduced learning effectiveness and a decline in student motivation. Standardized teaching materials and curricula also make it difficult to provide education optimized for each student's learning style. To solve this problem, a system is needed that can provide a learning experience tailored to each individual student. [Means for solving the problem]

[0005] The present invention includes a means for collecting student information via user terminals and transmitting it to a server for secure storage. It also includes a means for analyzing student characteristics and extracting learning patterns using a generative AI model, which enables customized learning materials to be dynamically generated and transmitted to the user terminal. It also provides a means for collecting learning progress data from the user terminal and transmitting it to a server. Based on this, the server has a means for continuously analyzing the progress data and optimizing the learning material content using a generative AI model. In this way, a system is realized that provides a learning experience optimized for each student's learning style and pace.

[0006] "User terminal" refers to a device used by a student to input learning information and view customized learning materials.

[0007] A "server" is a computer system that receives, stores, and analyzes data from user terminals.

[0008] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze students' learning characteristics and generate optimal teaching materials.

[0009] "Student information" refers to various data about students, such as grade level, subjects of interest, past grades, and learning goals.

[0010] "Customized learning materials" are materials that provide specific learning content tailored to the learning needs and pace of each individual student.

[0011] "Learning progress data" refers to data such as the progress of students as they progress through their studies and the results of their problem answers, and is used to evaluate the effectiveness of education and optimize the content of their next studies.

[0012] "Optimization of teaching material content" is the process by which a generative AI model dynamically adjusts the difficulty and content of teaching materials based on student learning progress data. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

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

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0035] Overall system configuration

[0036] The system of the present invention consists of three main components: a user terminal, a server, and a generative AI model. These components work together to provide students with personalized learning experiences and educational materials.

[0037] The role of each component

[0038] 1. User Device:

[0039] This is a device that allows students to enter their personal information and learning needs during initial registration.

[0040] A tool for students to view and study customized learning materials and enter progress data.

[0041] 2. Server:

[0042] Its role is to receive data sent from the user terminal and store it safely.

[0043] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[0044] Learning progress data is continuously received and the content of the teaching materials is optimized.

[0045] 3. Generative AI Model:

[0046] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[0047] Continuous optimization process based on student progress data.

[0048] Processing flow and specific operations

[0049] The following describes how the components of the system work together to implement the present invention.

[0050] User terminal

[0051] 1. The student accesses the initial registration screen via the user device and enters personal information such as grade, subjects of interest, past grades, and learning goals.

[0052] 2. After completing the input, press the "Submit" button to send the data to the server.

[0053] 3. During learning, the user's device sends the student's current progress and answers to assignments to the server in real time.

[0054] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[0055] server

[0056] 1. The initial registration data received from the user terminal is stored in a database for safekeeping.

[0057] 2. Based on the saved data, the generative AI model is called up and used to analyze the student's learning characteristics.

[0058] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[0059] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[0060] 5. Continuously receive student progress data and store it in a database.

[0061] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[0062] Generative AI Models

[0063] 1. Using student information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[0064] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[0065] 3. Based on student progress data, continuous optimization is performed and new learning content is suggested.

[0066] Specific examples

[0067] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[0068] 1. User Device:

[0069] Student B starts up the user device and selects "calculus" as the subject he wants to learn.

[0070] Enter the necessary personal information and learning objectives and send them to the server.

[0071] 2. Server:

[0072] The server passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[0073] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "Calculus."

[0074] The generated teaching materials are sent to Student B's device.

[0075] 3. User Device:

[0076] Student B studies the provided teaching materials and sends his / her progress data and answer results from his / her terminal to the server.

[0077] 4. Server:

[0078] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[0079] In this way, the system can respond to each student's individual learning needs and provide a highly personalized learning experience.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] The user starts up the user terminal and accesses the initial registration screen, where they enter personal information such as their grade, subjects of interest, past grades, and learning goals.

[0083] Step 2:

[0084] The terminal sends the entered personal information to the server. After sending, a confirmation message is displayed to the user to confirm completion of sending.

[0085] Step 3:

[0086] To ensure safe storage of data received from the user terminal, the server stores it in a database, encrypting the data.

[0087] Step 4:

[0088] After the server has finished saving the data, it calls the generative AI model and issues instructions to analyze the collected data.

[0089] Step 5:

[0090] The generative AI model analyzes the user's learning characteristics based on student information provided by the server, and designs learning patterns and optimal learning routes.

[0091] Step 6:

[0092] The generative AI model returns the analysis results to the server, and the server receives the analysis results.

[0093] Step 7:

[0094] Based on the analysis results, the server starts the learning material generation engine, which then dynamically generates customized learning materials.

[0095] Step 8:

[0096] The server transmits the generated customized teaching materials to the user terminal.

[0097] Step 9:

[0098] The terminal displays the received learning material to the user, allowing the user to begin learning.

[0099] Step 10:

[0100] As the user progresses with their studies, they input their progress and answer questions into the device, which then transmits this data to the server in real time.

[0101] Step 11:

[0102] The server receives the progress data sent from the user terminal and stores it in a database.

[0103] Step 12:

[0104] Based on the progress data received by the server, the generative AI model is called again and has it analyze the new data.

[0105] Step 13:

[0106] The generative AI model analyzes progress data and adjusts the content and difficulty of the learning materials as needed.

[0107] Step 14:

[0108] The server then sends the new, adjusted learning materials back to the user's device, allowing the user to continue optimally learning.

[0109] Example 1

[0110] 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."

[0111] With conventional learning systems, it is difficult to provide learning materials and learning routes optimized for each student, making it difficult to realize personalized education that meets individual learning needs. In addition, because management and optimization of learning progress is done manually, efficient learning management is not possible. Therefore, it is necessary to provide an optimal learning experience tailored to each student and improve learning efficiency.

[0112] 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.

[0113] In this invention, the server includes means for collecting learner information via a user device, means for transmitting the learner information to a data management device and safely storing it, means for analyzing learner characteristics and extracting learning patterns using a generative AI model, means for dynamically generating customized educational materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the data management device, and means for the data management device to continuously analyze the progress data and optimize the educational material content using the generative AI model, thereby providing an optimized learning environment for each student and improving the quality and efficiency of learning.

[0114] "User equipment" refers to a terminal or device that a learner accesses and uses to input learning information.

[0115] A "data management device" is a server or data storage device for safely storing and managing learner information and progress data.

[0116] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics and generate optimal learning patterns and educational materials.

[0117] "Educational materials" refer to educational materials provided to learners, and include multimedia, written, and question formats.

[0118] A "learning pattern" is an optimal learning method or route generated based on the learner's characteristics and progress.

[0119] "Progress data" refers to data such as the learner's learning progress and answer results.

[0120] "Optimizing" means improving teaching materials and learning routes according to the individual needs of learners, thereby maximizing learning efficiency.

[0121] MODE FOR CARRYING OUT THE INVENTION

[0122] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0123] Overall system configuration

[0124] The system of the present invention consists of three main components: a user device, a data management device, and a generative AI model. These components work together to provide learners with personalized learning experiences and educational materials.

[0125] The role of each component

[0126] User equipment

[0127] This is a terminal where learners enter their personal information and learning needs during initial registration.

[0128] A tool for learners to view and study customized educational materials and enter progress data.

[0129] Data management device

[0130] Its role is to receive and securely store data sent from user devices.

[0131] A generative AI model is invoked based on the stored data to analyze the learner's learning characteristics and generate customized educational materials.

[0132] Continuously receive learning progress data and optimize the content of educational materials.

[0133] Generative AI Models

[0134] Machine learning algorithms are used to analyze learner characteristics and design optimal learning paths and content.

[0135] Continuous optimization processing is performed based on learner progress data.

[0136] Processing flow and specific operations

[0137] The following describes how the components of the system work together to implement the present invention.

[0138] User equipment

[0139] 1. The learner accesses the initial registration screen using the user device and enters personal information such as grade level, subjects of interest, past grades, and learning goals.

[0140] 2. After completing the input, press the "Send" button to send the data to the data management device.

[0141] 3. During learning, the user's device transmits the learner's current progress and the results of their answers to the assignments in real time to the data management device.

[0142] 4. When new customized educational materials are received, they are displayed to the learner to continue their learning.

[0143] Data management device

[0144] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[0145] 2. Based on the saved data, the generative AI model is called up and the learner's learning characteristics are analyzed.

[0146] 3. Based on the analysis results output by the generative AI model, a teaching material generation engine is launched to dynamically generate customized educational materials.

[0147] 4. The generated educational materials are sent to the user's device so that the learner can access them.

[0148] 5. Continuously receive learner progress data and store it in a database.

[0149] 6. Based on the received progress data, the generative AI model is called again and the content of the educational materials is optimized as needed.

[0150] Generative AI Models

[0151] 1. Using learner information provided by the data management device, individual learning patterns are analyzed and the optimal learning route is designed.

[0152] 2. Provide the data management device with configuration data for customized educational materials based on the analysis results.

[0153] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[0154] Specific examples

[0155] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[0156] User equipment

[0157] Student B turns on the user device and selects "calculus" as the subject they want to learn.

[0158] The necessary personal information and learning goals are entered and sent to the data management device.

[0159] Example prompt: "Hello! I would like to study calculus. I am a sophomore in high school and have received A's in math. My goal is to prepare for college entrance exams."

[0160] Data management device

[0161] The data management device passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[0162] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized educational materials for "Calculus."

[0163] The generated educational materials are sent to Student B's device.

[0164] User equipment

[0165] Student B studies the provided educational materials and transmits his / her progress data and answer results from his / her terminal to the data management device.

[0166] Data management device

[0167] The data management device receives the progress data and uses generative AI models to continuously optimize the content of educational materials, thus enabling the system to meet the individual learning needs of each learner and provide a highly personalized learning experience.

[0168] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0169] Step 1:

[0170] The user terminal inputs the learner information.

[0171] The user accesses the initial registration screen using the user terminal. The learner enters personal information such as grade, subjects of interest, past grades, and learning goals. The entered information is sent to the server by pressing the "Submit" button.

[0172] Specific input: grade level, subjects of interest, past grades, learning goals

[0173] Specific output: Student information sent to the server

[0174] Specific operation: The user device calls the API and sends the learner information to the server via a POST request.

[0175] Step 2:

[0176] The server receives and stores student information

[0177] The server receives learner information sent from the user device via API and stores it securely in a database. When storing data, security measures such as encryption are implemented.

[0178] Specific input: Learner information sent from the user device

[0179] Specific output: Student information stored in a database

[0180] What happens: The server uses a database connection module to store the data and encrypts it as a security measure.

[0181] Step 3:

[0182] The server calls the generative AI model and analyzes its learning characteristics.

[0183] The server sends an analysis request to the generative AI model based on the stored learner information. The generative AI model analyzes the learner's characteristics and extracts the optimal learning pattern.

[0184] Specific input: Learner information stored in a database

[0185] Specific output: Analysis results of learning characteristics by generative AI model

[0186] Specific operation: The server calls the API of the generated AI model, sends learner information, and receives the analysis results.

[0187] Step 4:

[0188] The server generates customized learning materials and sends them to the user's terminal.

[0189] The server starts the learning material generation engine based on the analysis results obtained from the generative AI model, and generates customized learning materials. The generated learning materials are sent to the user's device so that they can be viewed by the learner.

[0190] Specific input: Analysis results from a generative AI model

[0191] Specific output: Customized learning materials sent to the user's device

[0192] Specific operation: The server runs the teaching material generation engine and sends the generated teaching material data to the user's terminal.

[0193] Step 5:

[0194] The user device sends progress data to the server.

[0195] Learners study using customized learning materials and input their progress and answers. The progress data is sent to the server in real time.

[0196] Specific input: Learner progress data and answer results

[0197] Specific output: Progress data sent to the server

[0198] Specific operation: The user device uses the API to send progress data to the server via a POST request.

[0199] Step 6:

[0200] The server analyzes the progress data and optimizes the content of the learning materials.

[0201] The server stores the received progress data in a database and analyzes it using a generative AI model. Based on the analysis results, the content of the learning materials is optimized and new customized learning materials are generated.

[0202] Specific input: Progress data

[0203] Specific output: Optimized and customized teaching materials

[0204] Specific operation: The server saves the progress data in a database, calls the API of the generative AI model to receive the analysis results, and then uses the learning material generation engine to generate new learning materials based on the results and send them to the user's device.

[0205] (Application example 1)

[0206] 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."

[0207] Conventional learning systems have the problem that it is difficult to provide individually optimized learning materials based on the characteristics and learning progress of each student, making it difficult to achieve effective learning.In addition, conventional systems have limited formats for learning materials, which makes it easy for students to become bored and lose motivation to learn.

[0208] 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.

[0209] In this invention, the server includes: means for collecting personal information and learning needs via a user's terminal; means for transmitting the personal information and learning needs to the server and securely storing them; means for analyzing the learner's characteristics using a generative AI model and extracting the optimal learning route and curriculum; means for dynamically generating customized learning materials and transmitting them to the user's terminal; means for collecting learning progress data from the user's terminal and transmitting it to the server; and means for the server to continuously analyze the progress data and optimize the learning material content using the generative AI model. This makes it possible to provide learning materials optimized for each individual learner and maximize learning effectiveness. Furthermore, by providing a variety of learning material formats, including video, text, and quiz formats, an interactive learning experience can be provided, sustaining the learner's interest.

[0210] "User Device" means a device through which a student enters personal information and learning needs, views and studies customized learning materials, and enters progress data.

[0211] The "server" is a computer system that receives and securely stores data sent from user devices, and calls generative AI models to analyze the data and generate learning materials to provide an optimized learning experience.

[0212] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics, design optimal learning routes and curricula, and dynamically generate customized teaching materials.

[0213] "Learning characteristics" refers to various factors related to learning, such as a learner's individual learning style, level of comprehension, interests, and past grades.

[0214] "Customized learning materials" are individually optimized learning content that is generated based on the learner's characteristics and learning progress, and supports efficient learning.

[0215] "Personal information" refers to information that can identify a learner, such as the learner's name, grade, subjects of interest, past grades, and learning goals.

[0216] "Learning needs" refers to the content and goals that learners want to learn in a particular field or subject.

[0217] "Learning progress data" refers to data that indicates the progress of a learner's learning, such as the learning materials and assignments that the learner has worked on, and the answers they have given.

[0218] "Optimization" is the process of continuously adjusting and improving the content and sequence of the learning materials provided based on learner progress data.

[0219] An "interactive learning experience" is a learning environment designed to allow learners to actively participate in learning and receive feedback in real time.

[0220] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0221] Overall system configuration

[0222] The system of the present invention mainly consists of a user terminal, a server, and a generative AI model. These components work together to provide learners with individually optimized learning experiences and learning materials.

[0223] The role of each component

[0224] 1. User Device

[0225] This is a device that allows learners to enter their personal information and learning needs during initial registration.

[0226] It is a tool that allows learners to view and study customized learning materials and enter progress data.

[0227] 2. Server

[0228] It is a computer system that receives and securely stores data sent from user terminals.

[0229] Based on the stored data, a generative AI model is called up, which analyzes the learner's characteristics and designs and generates the optimal learning route and curriculum.

[0230] It continuously receives learning progress data and uses generative AI models to optimize the content of the learning materials.

[0231] 3. Generative AI Models

[0232] Machine learning algorithms are used to analyze learner characteristics and design optimal learning routes and curricula.

[0233] Continuous optimization processing is performed based on learner progress data.

[0234] Processing flow and specific operations

[0235] The following describes how the components of the system work together to implement the present invention.

[0236] User Device

[0237] 1. The learner accesses the initial registration screen via the user device and enters personal information such as name, grade, subjects of interest, past grades, and learning objectives.

[0238] 2. After completing the input, press the "Submit" button to send the data to the server.

[0239] 3. During learning, the user's device sends the learner's current progress and answers to the assignments to the server in real time.

[0240] 4. When new customized learning materials are received, they are displayed to the learner, allowing them to continue their learning.

[0241] server

[0242] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[0243] 2. Call up the generative AI model based on the saved data and have it analyze the learner's characteristics.

[0244] 3. Customized teaching materials are dynamically generated based on the analysis results output by the generative AI model.

[0245] 4. The generated teaching materials are sent to the user's device so that the learner can access them.

[0246] 5. Continuously receive learner progress data and store it in a database.

[0247] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[0248] Generative AI Models

[0249] 1. Using learner information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[0250] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[0251] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[0252] Specific examples

[0253] For example, if a third-year junior high school student wants to learn calculus:

[0254] 1. User Device

[0255] The learner starts up the user device and selects "calculus" as the subject they wish to learn.

[0256] Enter the necessary personal information and learning objectives and send them to the server.

[0257] 2. Server

[0258] The server passes the received information to an analysis engine, and the generative AI model analyzes the learner's characteristics.

[0259] Customized teaching materials are generated based on the analysis results provided by the generative AI model.

[0260] The generated teaching materials are sent to the learner's terminal.

[0261] 3. User Device

[0262] The learner studies the provided learning materials and transmits the progress data and answer results from the terminal to the server.

[0263] 4. Server

[0264] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[0265] In this way, the system can respond to each learner's individual learning needs and provide a highly personalized learning experience.

[0266] Example prompt sentence:

[0267] Student Profile: Name - Student, Grade - 3, Interests - Mathematics, Past Grades - B, Learning Objective - Understand Calculus

[0268] Generate the best study plan for you.

[0269] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0270] Step 1:

[0271] The user starts up the user device and accesses the initial registration screen. They enter personal information such as their name, grade, subjects of interest, past grades, and learning goals. This input data is sent from the user device to the server. The input data includes name, grade, subjects of interest, past grades, and learning goals. The server receives this data and stores it in a database for safekeeping.

[0272] Step 2:

[0273] The server calls the generative AI model using the stored user's personal information and learning needs data. The input data includes personal information and learning needs data. The generative AI model uses a machine learning algorithm to analyze the learner's characteristics and design the optimal learning route and curriculum. The output is the analyzed learning characteristics and the optimal learning route. Based on this, the server begins the process of generating customized learning materials according to the learner's characteristics.

[0274] Step 3:

[0275] The server dynamically generates the customized learning materials. The input data includes the learning route and curriculum data obtained by the generative AI model. The server uses this data to generate learning materials in the form of videos, text, and quizzes, and sends them to the user's device. The output is interactive learning materials. The user's device displays the received learning materials to the learner, who then begins learning using them.

[0276] Step 4:

[0277] As users study via their user devices, they input progress data and answer results in real time. The input data includes learning progress information and answer results. The user devices send this data to the server. The server continuously receives the progress data and stores it in a database.

[0278] Step 5:

[0279] The server analyzes the progress data and calls the generative AI model again. The input data is the progress data. The generative AI model continuously performs optimization processing based on the progress data. The output is new, optimized learning content and suggested learning materials. The server generates new customized learning materials based on this and sends them back to the user's device.

[0280] Step 6:

[0281] The user receives new customized learning materials and continues learning using them. The user's device again collects learning progress data and sends it to the server, providing a continuous learning experience that adapts to the learner's progress.

[0282] 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.

[0283] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0284] Overall system configuration

[0285] The system of the present invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[0286] The role of each component

[0287] 1. User Device:

[0288] This is a device that allows students to enter personal information, learning needs, and emotional data during initial registration.

[0289] It is a tool for students to view and study customized learning materials and enter progress and sentiment data.

[0290] 2. Server:

[0291] Its role is to receive data sent from the user terminal and store it safely.

[0292] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[0293] Learning progress data and emotional data are continuously received and the content of the learning materials is adjusted to suit the needs of the student.

[0294] 3. Generative AI Model:

[0295] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[0296] Emotional data is combined and analyzed to optimize the content of teaching materials.

[0297] 4. Emotion Engine:

[0298] This is a system for recognizing user emotions and analyzing emotional data.

[0299] Emotional data is sent to a server to help analyze learning patterns and generate teaching materials.

[0300] Processing flow and specific operations

[0301] The following describes how the components of the system work together to implement the present invention.

[0302] User terminal

[0303] 1. The student accesses the initial registration screen via the user terminal and enters personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state.

[0304] 2. After completing the input, press the "Submit" button to send the data to the server.

[0305] 3. During learning, the user device transmits the student's progress information and emotional data to the server in real time.

[0306] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[0307] server

[0308] 1. The initial registration data and emotion data received from the user device are stored in a database for safekeeping.

[0309] 2. Based on the stored data, a generative AI model is invoked to analyze the student's learning characteristics and emotional state.

[0310] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[0311] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[0312] 5. Continuously receive student progress information and emotional data and store them in a database.

[0313] 6. Based on the received progress and emotion data, the generative AI model is called again and the content of the teaching material is optimized as needed.

[0314] Generative AI Models

[0315] 1. Using student information and emotional data provided by the server, individual learning patterns and emotional states are analyzed and the optimal learning route is designed.

[0316] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[0317] 3. Continuously perform optimization processing based on student progress data and emotion data.

[0318] Emotion Engine

[0319] 1. Recognize user emotions and analyze emotional data in real time.

[0320] 2. The analysis results are sent to the server and incorporated into the analysis process of the generative AI model.

[0321] Specific examples

[0322] For example, if Student C, a second-year high school student, wants to learn about the "force laws of physics":

[0323] 1. User Device:

[0324] Student C starts up the user terminal and selects "Laws of Force in Physics" as the topic he wants to learn.

[0325] The necessary personal information and current emotional state are entered and sent to the server.

[0326] 2. Server:

[0327] The server passes the received information to the analysis engine, and the generative AI model analyzes Student C's characteristics and emotional state.

[0328] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "The Laws of Force in Physics."

[0329] The generated teaching materials are sent to Student C's device.

[0330] 3. User Device:

[0331] Student C studies the provided learning materials and transmits his / her progress and emotional data from his / her terminal to the server.

[0332] 4. Server:

[0333] The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[0334] In this way, the system can respond to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[0335] The processing flow will be explained below.

[0336] Step 1:

[0337] The user starts up the user terminal and accesses the initial registration screen. The user inputs personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state (e.g., self-assessment questionnaire or facial expression recognition).

[0338] Step 2:

[0339] The terminal transmits the input personal information and emotion data to the server, and displays a message to the user confirming completion of transmission.

[0340] Step 3:

[0341] The server stores the data received from the user terminal in a database for safe storage. At this time, the data is encrypted.

[0342] Step 4:

[0343] After the server has finished saving the data, it calls the generative AI model and emotion engine and issues instructions to analyze the collected data.

[0344] Step 5:

[0345] The generative AI model designs learning patterns and optimal learning routes based on student information provided by the server (learning characteristics, past grades, interests, etc.).

[0346] Step 6:

[0347] The emotion engine analyzes the emotion data provided by the server and evaluates the student's current emotional state.

[0348] Step 7:

[0349] The server compiles the analysis results of the generative AI model and the emotion engine and activates the teaching material generation engine to generate customized teaching materials.

[0350] Step 8:

[0351] Based on the analysis results, the teaching material generation engine dynamically generates customized teaching materials in the form of videos, text, and quizzes.

[0352] Step 9:

[0353] The server transmits the generated educational material to the user terminal so that the user can access it.

[0354] Step 10:

[0355] The user terminal displays the received customized learning material to the user, and the user begins learning.

[0356] Step 11:

[0357] As the user progresses with their learning, they input their progress, answering questions, and real-time emotional data into the device, which then transmits this data to the server.

[0358] Step 12:

[0359] The server receives the progress data and emotion data sent from the user terminal and stores them in a database.

[0360] Step 13:

[0361] Based on the progress data and emotion data received by the server, the generative AI model and emotion engine are called again to analyze the new data.

[0362] Step 14:

[0363] A generative AI model analyzes progress data and optimizes learning content based on learning patterns.

[0364] Step 15:

[0365] The emotional engine analyzes the latest emotional data and adjusts the content and learning methods to best suit the student's current emotional state.

[0366] Step 16:

[0367] The server then transmits the adjusted new learning materials to the user terminal again, allowing the user to continue optimal learning.

[0368] In this way, the system can adapt to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[0369] Example 2

[0370] 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."

[0371] Conventional learning systems have difficulty adapting to individual students' learning needs and emotional states, making it impossible to provide a personalized learning experience that maximizes learning effectiveness. Furthermore, they lack the technology to analyze users' progress and emotional data in real time and provide optimal learning materials. This results in a decline in students' motivation and effectiveness in learning.

[0372] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user information via a user device, means for transmitting the user information to the server and safely storing it, means for analyzing user characteristics and extracting learning patterns using a generative AI model, an emotion engine for analyzing emotional data, means for dynamically generating customized learning materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the server, and means for the server to continuously analyze the progress data and emotional data and optimize the learning material content using the generative AI model. This makes it possible to provide optimal learning materials in real time, responding to the learning needs and emotional state of individual students.

[0373] "User device" refers to a device on which a user enters personal information when registering for the first time, browses and studies customized learning materials, and enters progress data and emotional data.

[0374] A "server" is a computer system responsible for receiving and securely storing data sent from user devices.

[0375] A "generative AI model" is a system that uses machine learning algorithms to analyze user characteristics and design optimal learning routes and curricula.

[0376] The "emotion engine" is a system that recognizes the user's emotions and analyzes emotional data.

[0377] A "learning pattern" refers to an individually optimized learning process or tendency that is derived based on a user's past grades, learning history, behavior during learning, etc.

[0378] "Customized learning materials" are learning content that is dynamically generated based on the user's characteristics and emotional state.

[0379] "Progress data" refers to data on the progress and results achieved by a user during their studies.

[0380] "Emotion data" is data that represents the user's current emotional state.

[0381] The "database" is a data storage system for safely storing the initial registration data, progress data, and emotion data received by the server.

[0382] "Real-time" refers to a state in which processing and analysis are carried out the moment an event occurs, and the results are reflected immediately.

[0383] The following describes an embodiment of the present invention. The system of the present invention consists of four main components: a user device, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[0384] User Device

[0385] The user device is a device through which students enter their personal information, learning needs, and emotional data during initial registration. Through the user device, students can:

[0386] 1. Access the initial registration screen and enter personal information such as your grade level, subjects of interest, past grades, learning goals, and current emotional state.

[0387] 2. After completing the input, press the "Send" button to send the data to the server.

[0388] 3. During learning, progress information and emotional data are input in real time and sent to the server.

[0389] 4. View new, customized learning materials as they become available and continue your learning.

[0390] server

[0391] The server receives and securely stores data sent by the user device. The server performs the following operations:

[0392] 1. Initial registration data and emotion data are stored in a database.

[0393] 2. Invoke the generative AI model to analyze the student's learning characteristics and emotional state.

[0394] 3. Based on the analysis results, the teaching material generation engine is activated to dynamically generate customized teaching materials.

[0395] 4. The generated educational material is transmitted to the user device and made accessible.

[0396] 5. Continuously receive learning progress data and emotion data and store them in a database.

[0397] 6. The generated AI model is called again based on the received data to optimize the content of the teaching materials.

[0398] Generative AI Models

[0399] The generative AI model performs analysis using student information and emotion data provided by the server. The generative AI model operates as follows:

[0400] 1. Analyze each student's learning patterns and emotional state to design the optimal learning route.

[0401] 2. The analysis results are provided to the server and used as configuration data for customized teaching materials.

[0402] 3. Continuously perform optimization processing based on students' progress data and emotion data.

[0403] Emotion Engine

[0404] The emotion engine recognizes user emotions and analyzes emotion data in real time. The specific roles of the emotion engine are as follows:

[0405] 1. Recognize user emotions.

[0406] 2. Send the emotion data to the server.

[0407] 3. Emotional data can be incorporated into generative AI models to aid in the analysis process.

[0408] Specific examples

[0409] For example, suppose a second-year high school student C wants to learn about "the laws of force in physics." The process in this case is as follows:

[0410] 1. User Device: Student C starts up the user device and selects "Laws of Force in Physics" as the subject they want to learn. They enter the necessary personal information and their current emotional state and send it to the server.

[0411] 2. Server: The server passes the received information to the analysis engine, and the generative AI model analyzes the characteristics and emotional state of student C. Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials and sends them to the user device.

[0412] 3. User device: Student C studies the provided learning materials and transmits his / her progress and emotion data from his / her device to the server.

[0413] 4. Server: The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[0414] Prompt Sentence Examples

[0415] By inputting the following prompts into the generative AI model, personalized learning materials can be generated:

[0416] Student C is a second-year high school student who wants to learn about the laws of force in physics. He has an average of 80 points in physics in the past, and he spent a lot of time understanding force vector analysis. He is also currently in a slightly anxious emotional state. Based on this information, please generate customized learning materials that are best suited to Student C.

[0417] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0418] Step 1:

[0419] A user accesses the system for the first time through a user device. On the initial registration screen, the user enters information such as their grade, subjects of interest, past grades, learning goals, and current emotional state (input: personal information, learning needs, emotional state). After completing the input, the user clicks the "Submit" button to send this data to the server (output: transmitted data).

[0420] Step 2:

[0421] The server receives the initial registration data and emotional data sent from the user device (input: sent data). The server securely stores the received data in a database (output: stored data). This data includes grade level, subject interests, grades, learning goals, emotional state, etc.

[0422] Step 3:

[0423] The server calls the generative AI model based on data stored in the database (input: stored data). The generative AI model uses the provided data to analyze the user's characteristics and emotional state. The analysis process uses machine learning algorithms to design the optimal learning route and curriculum. The analysis results are returned to the server (output: analysis results).

[0424] Step 4:

[0425] The server launches a teaching material generation engine based on the analysis results provided by the generative AI model (input: analysis results). The teaching material generation engine dynamically generates teaching materials customized for each user. The generated teaching materials include content tailored to the user's learning needs and emotional state (output: customized teaching materials).

[0426] Step 5:

[0427] The server transmits the generated customized learning materials to the user device (input: customized learning materials). The user device displays the received learning materials on the screen (output: displayed learning materials). The user then proceeds with their studies using the provided customized learning materials.

[0428] Step 6:

[0429] During learning, the user inputs progress information and emotional data in real time and transmits them from the user device to the server (input: progress information, emotional data). The transmitted progress information includes the learning completion rate, the percentage of correct answers to questions, etc.

[0430] Step 7:

[0431] The server receives the progress information and emotional data sent from the user device and stores them in a database (input: progress information, emotional data). Based on the stored data, the server invokes the generative AI model again and optimizes the content of the learning materials (output: optimized learning materials). During the optimization process, the content and difficulty of the learning materials are adjusted taking into account new learning data and emotional information.

[0432] Step 8:

[0433] The server sends the optimized learning materials back to the user device (input: optimized learning materials). The user device displays the updated learning materials on the screen and allows the user to continue learning (output: displayed optimized learning materials).

[0434] (Application example 2)

[0435] 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."

[0436] Conventional virtual stores provide only general product information and do not adequately provide product suggestions based on the user's hobbies and purchasing trends, making it difficult to provide a personalized shopping experience. Furthermore, suggestions do not take into account the user's real-time emotional state, limiting their ability to improve user satisfaction and stimulate purchasing motivation. To solve this problem, a personalized product suggestion system that utilizes the user's individual characteristics and real-time emotional data is needed.

[0437] The identification processing by the identification 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 user information via a user terminal, means for transmitting the user information to the server and securely storing it, means for analyzing user characteristics and extracting interests and purchasing tendencies using a generative AI model, means for dynamically generating customized product proposals and transmitting them to the user terminal, means for collecting real-time emotional data from the user terminal and transmitting it to the server, and means for the server to continuously analyze the emotional data and behavioral data and optimize the product proposals using the generative AI model. This enables personalized product proposals based on the user's individual characteristics and real-time emotional state.

[0438] "User terminal" is a general term for a device through which a user inputs information and communicates with a server.

[0439] "User information" refers to data about a user's personal characteristics, such as hobbies, purchasing habits, and emotional state.

[0440] A "server" is a computer system that receives and stores user information and runs a generative AI model based on that information.

[0441] A "generative AI model" is an artificial intelligence model that includes algorithms to analyze user characteristics and make product suggestions based on individual interests and purchasing trends.

[0442] "Characteristics" refers to personal attributes and behavioral patterns such as a user's interests, hobbies, and purchasing tendencies.

[0443] "Purchase trends" are predictions of future purchasing behavior based on a user's past purchasing history and data on products they have shown interest in.

[0444] "Customized product recommendations" are the provision of specific products or services that are dynamically generated based on the user's characteristics and emotions.

[0445] "Emotional data" refers to data that indicates the user's real-time emotional state and is obtained through facial expression analysis and voice analysis.

[0446] "Behavioral data" refers to data such as the actions a user takes within an application and their browsing history.

[0447] "Product Suggestions" are lists of products and services presented to users based on their characteristics and real-time emotional state.

[0448] "Optimization" is the process of continually adjusting product offerings to maximize user satisfaction.

[0449] The system for implementing this invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. The cooperation of these components makes it possible to provide a personalized shopping experience for each user in a virtual store.

[0450] Hardware and Software Configuration

[0451] 1. User Device:

[0452] Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[0453] Software: Virtual store application

[0454] Function: Collects user input information and sends it to the server, receives and displays customized product suggestions, and obtains user behavior and emotion data in real time.

[0455] 2. Server:

[0456] Hardware: High-performance computer server

[0457] Software: Database servers (e.g., MySQL, PostgreSQL), cloud platforms (e.g., AWS, Google Cloud)

[0458] Function: Securely stores user information, controls and manages the generative AI model and emotion engine. Analyzes user characteristics using the generative AI model and dynamically generates optimal product recommendations based on purchasing trends and emotion data.

[0459] 3. Generative AI Model:

[0460] Software: Machine learning algorithms and natural language processing models (e.g., GPT)

[0461] Function: Analyzes user characteristics and generates customized product suggestions based on interests and purchasing trends. Outputs analysis results based on user information and emotional data provided by the server.

[0462] 4. Emotion Engine:

[0463] Software: Emotion analysis software

[0464] Function: Analyzes the user's real-time emotional data and sends it to the server. Identifies the user's emotional state using facial recognition and voice analysis technology.

[0465] Specific examples

[0466] When users shop in the virtual store, they input their personal information, interests, and current emotional state using their device, which is then sent to a server and securely stored.

[0467] The server calls up a generative AI model based on the received user information, analyzes the user's characteristics, and dynamically generates product and service suggestions based on their interests and purchasing trends.The server then sends the generated product suggestions to the user's device, where the user can view the products and services.

[0468] In addition, the user's real-time emotional data is analyzed by the emotion engine and sent to the server, which then calls the generative AI model again based on the overall data, including the emotional data, to optimize the product recommendations.

[0469] For example, if a user's hobby is sports, their interest category is books, and their current emotion is "happy," the prompt to the generative AI model would be:

[0470] "Please suggest the best products and services based on the user's hobby: sports, category of interest: books, and current emotional state: happy."

[0471] In this way, the present invention can provide a personalized shopping experience based on the user's individual characteristics and real-time emotional data.

[0472] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0473] Step 1:

[0474] Users input their personal information, hobbies, interest categories, and current emotional state via their device. This information is sent from the device to the server and securely stored. The input data includes the user's name, age, hobbies, purchase history, real-time emotional data, etc. This allows the server to collect individual user data.

[0475] Step 2:

[0476] The server provides the collected user information to the generative AI model. The generative AI model analyzes the user's hobbies, purchasing tendencies, and emotional state, and generates a prompt to suggest optimal products and services. For example, the prompt might be in the format "Please suggest optimal products and services based on the user's hobbies: sports, category of interest: books, and current emotional state: happy." By inputting this prompt into the generative AI model, customized product suggestions are output.

[0477] Step 3:

[0478] The generative AI model generates product suggestions based on the user's characteristics and sends the results back to the server. The generated product suggestions become a list of multiple products and services based on the user's preferences. The server receives this data and sends it to the user's device.

[0479] Step 4:

[0480] The user terminal receives the customized product proposals sent from the server and displays them to the user. The user browses the product proposals and selects the products they are interested in. The data of the selected products is then sent back to the server.

[0481] Step 5:

[0482] Behavioral data associated with user operations and selections, as well as emotional data acquired in real time, are sent from the user's device to the server. For example, emotional data from the user can be acquired using facial expression analysis or voice analysis. The server receives this data and provides it back to the generative AI model.

[0483] Step 6:

[0484] The server then calls the generative AI model again based on all data, including real-time emotional data and behavioral data, analyzed by the emotion engine, to optimize the content of the product suggestions. The generative AI model then generates a prompt sentence again and outputs the optimized product suggestions.

[0485] Step 7:

[0486] The optimized product suggestions are sent from the server to the user's device and provided to the user again, and the user then shops again based on these new suggestions, personalizing the entire purchasing process.

[0487] In this way, the collaboration between the user device, server, generative AI model, and emotion engine makes it possible to provide users with personalized product suggestions that are optimized in real time.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 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.

[0494] 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).

[0495] 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.

[0496] 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.

[0497] 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).

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] 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."

[0504] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0505] Overall system configuration

[0506] The system of the present invention consists of three main components: a user terminal, a server, and a generative AI model. These components work together to provide students with personalized learning experiences and educational materials.

[0507] The role of each component

[0508] 1. User Device:

[0509] This is a device that allows students to enter their personal information and learning needs during initial registration.

[0510] A tool for students to view and study customized learning materials and enter progress data.

[0511] 2. Server:

[0512] Its role is to receive data sent from the user terminal and store it safely.

[0513] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[0514] Learning progress data is continuously received and the content of the teaching materials is optimized.

[0515] 3. Generative AI Model:

[0516] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[0517] Continuous optimization process based on student progress data.

[0518] Processing flow and specific operations

[0519] The following describes how the components of the system work together to implement the present invention.

[0520] User terminal

[0521] 1. The student accesses the initial registration screen via the user device and enters personal information such as grade, subjects of interest, past grades, and learning goals.

[0522] 2. After completing the input, press the "Submit" button to send the data to the server.

[0523] 3. During learning, the user's device sends the student's current progress and answers to assignments to the server in real time.

[0524] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[0525] server

[0526] 1. The initial registration data received from the user terminal is stored in a database for safekeeping.

[0527] 2. Based on the saved data, the generative AI model is called up and used to analyze the student's learning characteristics.

[0528] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[0529] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[0530] 5. Continuously receive student progress data and store it in a database.

[0531] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[0532] Generative AI Models

[0533] 1. Using student information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[0534] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[0535] 3. Based on student progress data, continuous optimization is performed and new learning content is suggested.

[0536] Specific examples

[0537] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[0538] 1. User Device:

[0539] Student B starts up the user device and selects "calculus" as the subject he wants to learn.

[0540] Enter the necessary personal information and learning objectives and send them to the server.

[0541] 2. Server:

[0542] The server passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[0543] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "Calculus."

[0544] The generated teaching materials are sent to Student B's device.

[0545] 3. User Device:

[0546] Student B studies the provided teaching materials and sends his / her progress data and answer results from his / her terminal to the server.

[0547] 4. Server:

[0548] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[0549] In this way, the system can respond to each student's individual learning needs and provide a highly personalized learning experience.

[0550] The processing flow will be explained below.

[0551] Step 1:

[0552] The user starts up the user terminal and accesses the initial registration screen, where they enter personal information such as their grade, subjects of interest, past grades, and learning goals.

[0553] Step 2:

[0554] The terminal sends the entered personal information to the server. After sending, a confirmation message is displayed to the user to confirm completion of sending.

[0555] Step 3:

[0556] To ensure safe storage of data received from the user terminal, the server stores it in a database, encrypting the data.

[0557] Step 4:

[0558] After the server has finished saving the data, it calls the generative AI model and issues instructions to analyze the collected data.

[0559] Step 5:

[0560] The generative AI model analyzes the user's learning characteristics based on student information provided by the server, and designs learning patterns and optimal learning routes.

[0561] Step 6:

[0562] The generative AI model returns the analysis results to the server, and the server receives the analysis results.

[0563] Step 7:

[0564] Based on the analysis results, the server starts the learning material generation engine, which then dynamically generates customized learning materials.

[0565] Step 8:

[0566] The server transmits the generated customized teaching materials to the user terminal.

[0567] Step 9:

[0568] The terminal displays the received learning material to the user, allowing the user to begin learning.

[0569] Step 10:

[0570] As the user progresses with their studies, they input their progress and answer questions into the device, which then transmits this data to the server in real time.

[0571] Step 11:

[0572] The server receives the progress data sent from the user terminal and stores it in a database.

[0573] Step 12:

[0574] Based on the progress data received by the server, the generative AI model is called again and has it analyze the new data.

[0575] Step 13:

[0576] The generative AI model analyzes progress data and adjusts the content and difficulty of the learning materials as needed.

[0577] Step 14:

[0578] The server then sends the new, adjusted learning materials back to the user's device, allowing the user to continue optimally learning.

[0579] Example 1

[0580] 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."

[0581] With conventional learning systems, it is difficult to provide learning materials and learning routes optimized for each student, making it difficult to realize personalized education that meets individual learning needs. In addition, because management and optimization of learning progress is done manually, efficient learning management is not possible. Therefore, it is necessary to provide an optimal learning experience tailored to each student and improve learning efficiency.

[0582] 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.

[0583] In this invention, the server includes means for collecting learner information via a user device, means for transmitting the learner information to a data management device and safely storing it, means for analyzing learner characteristics and extracting learning patterns using a generative AI model, means for dynamically generating customized educational materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the data management device, and means for the data management device to continuously analyze the progress data and optimize the educational material content using the generative AI model, thereby providing an optimized learning environment for each student and improving the quality and efficiency of learning.

[0584] "User equipment" refers to a terminal or device that a learner accesses and uses to input learning information.

[0585] A "data management device" is a server or data storage device for safely storing and managing learner information and progress data.

[0586] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics and generate optimal learning patterns and educational materials.

[0587] "Educational materials" refer to educational materials provided to learners, and include multimedia, written, and question formats.

[0588] A "learning pattern" is an optimal learning method or route generated based on the learner's characteristics and progress.

[0589] "Progress data" refers to data such as the learner's learning progress and answer results.

[0590] "Optimizing" means improving teaching materials and learning routes according to the individual needs of learners, thereby maximizing learning efficiency.

[0591] MODE FOR CARRYING OUT THE INVENTION

[0592] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0593] Overall system configuration

[0594] The system of the present invention consists of three main components: a user device, a data management device, and a generative AI model. These components work together to provide learners with personalized learning experiences and educational materials.

[0595] The role of each component

[0596] User equipment

[0597] This is a terminal where learners enter their personal information and learning needs during initial registration.

[0598] A tool for learners to view and study customized educational materials and enter progress data.

[0599] Data management device

[0600] Its role is to receive and securely store data sent from user devices.

[0601] A generative AI model is invoked based on the stored data to analyze the learner's learning characteristics and generate customized educational materials.

[0602] Continuously receive learning progress data and optimize the content of educational materials.

[0603] Generative AI Models

[0604] Machine learning algorithms are used to analyze learner characteristics and design optimal learning paths and content.

[0605] Continuous optimization processing is performed based on learner progress data.

[0606] Processing flow and specific operations

[0607] The following describes how the components of the system work together to implement the present invention.

[0608] User equipment

[0609] 1. The learner accesses the initial registration screen using the user device and enters personal information such as grade level, subjects of interest, past grades, and learning goals.

[0610] 2. After completing the input, press the "Send" button to send the data to the data management device.

[0611] 3. During learning, the user's device transmits the learner's current progress and the results of their answers to the assignments in real time to the data management device.

[0612] 4. When new customized educational materials are received, they are displayed to the learner to continue their learning.

[0613] Data management device

[0614] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[0615] 2. Based on the saved data, the generative AI model is called up and the learner's learning characteristics are analyzed.

[0616] 3. Based on the analysis results output by the generative AI model, a teaching material generation engine is launched to dynamically generate customized educational materials.

[0617] 4. The generated educational materials are sent to the user's device so that the learner can access them.

[0618] 5. Continuously receive learner progress data and store it in a database.

[0619] 6. Based on the received progress data, the generative AI model is called again and the content of the educational materials is optimized as needed.

[0620] Generative AI Models

[0621] 1. Using learner information provided by the data management device, individual learning patterns are analyzed and the optimal learning route is designed.

[0622] 2. Provide the data management device with configuration data for customized educational materials based on the analysis results.

[0623] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[0624] Specific examples

[0625] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[0626] User equipment

[0627] Student B turns on the user device and selects "calculus" as the subject they want to learn.

[0628] The necessary personal information and learning goals are entered and sent to the data management device.

[0629] Example prompt: "Hello! I would like to study calculus. I am a sophomore in high school and have received A's in math. My goal is to prepare for college entrance exams."

[0630] Data management device

[0631] The data management device passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[0632] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized educational materials for "Calculus."

[0633] The generated educational materials are sent to Student B's device.

[0634] User equipment

[0635] Student B studies the provided educational materials and transmits his / her progress data and answer results from his / her terminal to the data management device.

[0636] Data management device

[0637] The data management device receives the progress data and uses generative AI models to continuously optimize the content of educational materials, thus enabling the system to meet the individual learning needs of each learner and provide a highly personalized learning experience.

[0638] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0639] Step 1:

[0640] The user terminal inputs the learner information.

[0641] The user accesses the initial registration screen using the user terminal. The learner enters personal information such as grade, subjects of interest, past grades, and learning goals. The entered information is sent to the server by pressing the "Submit" button.

[0642] Specific input: grade level, subjects of interest, past grades, learning goals

[0643] Specific output: Student information sent to the server

[0644] Specific operation: The user device calls the API and sends the learner information to the server via a POST request.

[0645] Step 2:

[0646] The server receives and stores student information

[0647] The server receives learner information sent from the user device via API and stores it securely in a database. When storing data, security measures such as encryption are implemented.

[0648] Specific input: Learner information sent from the user device

[0649] Specific output: Student information stored in a database

[0650] What happens: The server uses a database connection module to store the data and encrypts it as a security measure.

[0651] Step 3:

[0652] The server calls the generative AI model and analyzes its learning characteristics.

[0653] The server sends an analysis request to the generative AI model based on the stored learner information. The generative AI model analyzes the learner's characteristics and extracts the optimal learning pattern.

[0654] Specific input: Learner information stored in a database

[0655] Specific output: Analysis results of learning characteristics by generative AI model

[0656] Specific operation: The server calls the API of the generated AI model, sends learner information, and receives the analysis results.

[0657] Step 4:

[0658] The server generates customized learning materials and sends them to the user's terminal.

[0659] The server starts the learning material generation engine based on the analysis results obtained from the generative AI model, and generates customized learning materials. The generated learning materials are sent to the user's device so that they can be viewed by the learner.

[0660] Specific input: Analysis results from a generative AI model

[0661] Specific output: Customized learning materials sent to the user's device

[0662] Specific operation: The server runs the teaching material generation engine and sends the generated teaching material data to the user's terminal.

[0663] Step 5:

[0664] The user device sends progress data to the server.

[0665] Learners study using customized learning materials and input their progress and answers. The progress data is sent to the server in real time.

[0666] Specific input: Learner progress data and answer results

[0667] Specific output: Progress data sent to the server

[0668] Specific operation: The user device uses the API to send progress data to the server via a POST request.

[0669] Step 6:

[0670] The server analyzes the progress data and optimizes the content of the learning materials.

[0671] The server stores the received progress data in a database and analyzes it using a generative AI model. Based on the analysis results, the content of the learning materials is optimized and new customized learning materials are generated.

[0672] Specific input: Progress data

[0673] Specific output: Optimized and customized teaching materials

[0674] Specific operation: The server saves the progress data in a database, calls the API of the generative AI model to receive the analysis results, and then uses the learning material generation engine to generate new learning materials based on the results and send them to the user's device.

[0675] (Application example 1)

[0676] 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."

[0677] Conventional learning systems have the problem that it is difficult to provide individually optimized learning materials based on the characteristics and learning progress of each student, making it difficult to achieve effective learning.In addition, conventional systems have limited formats for learning materials, which makes it easy for students to become bored and lose motivation to learn.

[0678] 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.

[0679] In this invention, the server includes: means for collecting personal information and learning needs via a user's terminal; means for transmitting the personal information and learning needs to the server and securely storing them; means for analyzing the learner's characteristics using a generative AI model and extracting the optimal learning route and curriculum; means for dynamically generating customized learning materials and transmitting them to the user's terminal; means for collecting learning progress data from the user's terminal and transmitting it to the server; and means for the server to continuously analyze the progress data and optimize the learning material content using the generative AI model. This makes it possible to provide learning materials optimized for each individual learner and maximize learning effectiveness. Furthermore, by providing a variety of learning material formats, including video, text, and quiz formats, an interactive learning experience can be provided, sustaining the learner's interest.

[0680] "User Device" means a device through which a student enters personal information and learning needs, views and studies customized learning materials, and enters progress data.

[0681] The "server" is a computer system that receives and securely stores data sent from user devices, and calls generative AI models to analyze the data and generate learning materials to provide an optimized learning experience.

[0682] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics, design optimal learning routes and curricula, and dynamically generate customized teaching materials.

[0683] "Learning characteristics" refers to various factors related to learning, such as a learner's individual learning style, level of comprehension, interests, and past grades.

[0684] "Customized learning materials" are individually optimized learning content that is generated based on the learner's characteristics and learning progress, and supports efficient learning.

[0685] "Personal information" refers to information that can identify a learner, such as the learner's name, grade, subjects of interest, past grades, and learning goals.

[0686] "Learning needs" refers to the content and goals that learners want to learn in a particular field or subject.

[0687] "Learning progress data" refers to data that indicates the progress of a learner's learning, such as the learning materials and assignments that the learner has worked on, and the answers they have given.

[0688] "Optimization" is the process of continuously adjusting and improving the content and sequence of the learning materials provided based on learner progress data.

[0689] An "interactive learning experience" is a learning environment designed to allow learners to actively participate in learning and receive feedback in real time.

[0690] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0691] Overall system configuration

[0692] The system of the present invention mainly consists of a user terminal, a server, and a generative AI model. These components work together to provide learners with individually optimized learning experiences and learning materials.

[0693] The role of each component

[0694] 1. User Device

[0695] This is a device that allows learners to enter their personal information and learning needs during initial registration.

[0696] It is a tool that allows learners to view and study customized learning materials and enter progress data.

[0697] 2. Server

[0698] It is a computer system that receives and securely stores data sent from user terminals.

[0699] Based on the stored data, a generative AI model is called up, which analyzes the learner's characteristics and designs and generates the optimal learning route and curriculum.

[0700] It continuously receives learning progress data and uses generative AI models to optimize the content of the learning materials.

[0701] 3. Generative AI Models

[0702] Machine learning algorithms are used to analyze learner characteristics and design optimal learning routes and curricula.

[0703] Continuous optimization processing is performed based on learner progress data.

[0704] Processing flow and specific operations

[0705] The following describes how the components of the system work together to implement the present invention.

[0706] User Device

[0707] 1. The learner accesses the initial registration screen via the user device and enters personal information such as name, grade, subjects of interest, past grades, and learning objectives.

[0708] 2. After completing the input, press the "Submit" button to send the data to the server.

[0709] 3. During learning, the user's device sends the learner's current progress and answers to the assignments to the server in real time.

[0710] 4. When new customized learning materials are received, they are displayed to the learner, allowing them to continue their learning.

[0711] server

[0712] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[0713] 2. Call up the generative AI model based on the saved data and have it analyze the learner's characteristics.

[0714] 3. Customized teaching materials are dynamically generated based on the analysis results output by the generative AI model.

[0715] 4. The generated teaching materials are sent to the user's device so that the learner can access them.

[0716] 5. Continuously receive learner progress data and store it in a database.

[0717] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[0718] Generative AI Models

[0719] 1. Using learner information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[0720] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[0721] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[0722] Specific examples

[0723] For example, if a third-year junior high school student wants to learn calculus:

[0724] 1. User Device

[0725] The learner starts up the user device and selects "calculus" as the subject they wish to learn.

[0726] Enter the necessary personal information and learning objectives and send them to the server.

[0727] 2. Server

[0728] The server passes the received information to an analysis engine, and the generative AI model analyzes the learner's characteristics.

[0729] Customized teaching materials are generated based on the analysis results provided by the generative AI model.

[0730] The generated teaching materials are sent to the learner's terminal.

[0731] 3. User Device

[0732] The learner studies the provided learning materials and transmits the progress data and answer results from the terminal to the server.

[0733] 4. Server

[0734] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[0735] In this way, the system can respond to each learner's individual learning needs and provide a highly personalized learning experience.

[0736] Example prompt sentence:

[0737] Student Profile: Name - Student, Grade - 3, Interests - Mathematics, Past Grades - B, Learning Objective - Understand Calculus

[0738] Generate the best study plan for you.

[0739] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0740] Step 1:

[0741] The user starts up the user device and accesses the initial registration screen. They enter personal information such as their name, grade, subjects of interest, past grades, and learning goals. This input data is sent from the user device to the server. The input data includes name, grade, subjects of interest, past grades, and learning goals. The server receives this data and stores it in a database for safekeeping.

[0742] Step 2:

[0743] The server calls the generative AI model using the stored user's personal information and learning needs data. The input data includes personal information and learning needs data. The generative AI model uses a machine learning algorithm to analyze the learner's characteristics and design the optimal learning route and curriculum. The output is the analyzed learning characteristics and the optimal learning route. Based on this, the server begins the process of generating customized learning materials according to the learner's characteristics.

[0744] Step 3:

[0745] The server dynamically generates the customized learning materials. The input data includes the learning route and curriculum data obtained by the generative AI model. The server uses this data to generate learning materials in the form of videos, text, and quizzes, and sends them to the user's device. The output is interactive learning materials. The user's device displays the received learning materials to the learner, who then begins learning using them.

[0746] Step 4:

[0747] As users study via their user devices, they input progress data and answer results in real time. The input data includes learning progress information and answer results. The user devices send this data to the server. The server continuously receives the progress data and stores it in a database.

[0748] Step 5:

[0749] The server analyzes the progress data and calls the generative AI model again. The input data is the progress data. The generative AI model continuously performs optimization processing based on the progress data. The output is new, optimized learning content and suggested learning materials. The server generates new customized learning materials based on this and sends them back to the user's device.

[0750] Step 6:

[0751] The user receives new customized learning materials and continues learning using them. The user's device again collects learning progress data and sends it to the server, providing a continuous learning experience that adapts to the learner's progress.

[0752] 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.

[0753] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0754] Overall system configuration

[0755] The system of the present invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[0756] The role of each component

[0757] 1. User Device:

[0758] This is a device that allows students to enter personal information, learning needs, and emotional data during initial registration.

[0759] It is a tool for students to view and study customized learning materials and enter progress and sentiment data.

[0760] 2. Server:

[0761] Its role is to receive data sent from the user terminal and store it safely.

[0762] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[0763] Learning progress data and emotional data are continuously received and the content of the learning materials is adjusted to suit the needs of the student.

[0764] 3. Generative AI Model:

[0765] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[0766] Emotional data is combined and analyzed to optimize the content of teaching materials.

[0767] 4. Emotion Engine:

[0768] This is a system for recognizing user emotions and analyzing emotional data.

[0769] Emotional data is sent to a server to help analyze learning patterns and generate teaching materials.

[0770] Processing flow and specific operations

[0771] The following describes how the components of the system work together to implement the present invention.

[0772] User terminal

[0773] 1. The student accesses the initial registration screen via the user terminal and enters personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state.

[0774] 2. After completing the input, press the "Submit" button to send the data to the server.

[0775] 3. During learning, the user device transmits the student's progress information and emotional data to the server in real time.

[0776] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[0777] server

[0778] 1. The initial registration data and emotion data received from the user device are stored in a database for safekeeping.

[0779] 2. Based on the stored data, a generative AI model is invoked to analyze the student's learning characteristics and emotional state.

[0780] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[0781] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[0782] 5. Continuously receive student progress information and emotional data and store them in a database.

[0783] 6. Based on the received progress and emotion data, the generative AI model is called again and the content of the teaching material is optimized as needed.

[0784] Generative AI Models

[0785] 1. Using student information and emotional data provided by the server, individual learning patterns and emotional states are analyzed and the optimal learning route is designed.

[0786] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[0787] 3. Continuously perform optimization processing based on student progress data and emotion data.

[0788] Emotion Engine

[0789] 1. Recognize user emotions and analyze emotional data in real time.

[0790] 2. The analysis results are sent to the server and incorporated into the analysis process of the generative AI model.

[0791] Specific examples

[0792] For example, if Student C, a second-year high school student, wants to learn about the "force laws of physics":

[0793] 1. User Device:

[0794] Student C starts up the user terminal and selects "Laws of Force in Physics" as the topic he wants to learn.

[0795] The necessary personal information and current emotional state are entered and sent to the server.

[0796] 2. Server:

[0797] The server passes the received information to the analysis engine, and the generative AI model analyzes Student C's characteristics and emotional state.

[0798] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "The Laws of Force in Physics."

[0799] The generated teaching materials are sent to Student C's device.

[0800] 3. User Device:

[0801] Student C studies the provided learning materials and transmits his / her progress and emotional data from his / her terminal to the server.

[0802] 4. Server:

[0803] The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[0804] In this way, the system can respond to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[0805] The processing flow will be explained below.

[0806] Step 1:

[0807] The user starts up the user terminal and accesses the initial registration screen. The user inputs personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state (e.g., self-assessment questionnaire or facial expression recognition).

[0808] Step 2:

[0809] The terminal transmits the input personal information and emotion data to the server, and displays a message to the user confirming completion of transmission.

[0810] Step 3:

[0811] The server stores the data received from the user terminal in a database for safe storage. At this time, the data is encrypted.

[0812] Step 4:

[0813] After the server has finished saving the data, it calls the generative AI model and emotion engine and issues instructions to analyze the collected data.

[0814] Step 5:

[0815] The generative AI model designs learning patterns and optimal learning routes based on student information provided by the server (learning characteristics, past grades, interests, etc.).

[0816] Step 6:

[0817] The emotion engine analyzes the emotion data provided by the server and evaluates the student's current emotional state.

[0818] Step 7:

[0819] The server compiles the analysis results of the generative AI model and the emotion engine and activates the teaching material generation engine to generate customized teaching materials.

[0820] Step 8:

[0821] Based on the analysis results, the teaching material generation engine dynamically generates customized teaching materials in the form of videos, text, and quizzes.

[0822] Step 9:

[0823] The server transmits the generated educational material to the user terminal so that the user can access it.

[0824] Step 10:

[0825] The user terminal displays the received customized learning material to the user, and the user begins learning.

[0826] Step 11:

[0827] As the user progresses with their learning, they input their progress, answering questions, and real-time emotional data into the device, which then transmits this data to the server.

[0828] Step 12:

[0829] The server receives the progress data and emotion data sent from the user terminal and stores them in a database.

[0830] Step 13:

[0831] Based on the progress data and emotion data received by the server, the generative AI model and emotion engine are called again to analyze the new data.

[0832] Step 14:

[0833] A generative AI model analyzes progress data and optimizes learning content based on learning patterns.

[0834] Step 15:

[0835] The emotional engine analyzes the latest emotional data and adjusts the content and learning methods to best suit the student's current emotional state.

[0836] Step 16:

[0837] The server then transmits the adjusted new learning materials to the user terminal again, allowing the user to continue optimal learning.

[0838] In this way, the system can adapt to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[0839] Example 2

[0840] 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."

[0841] Conventional learning systems have difficulty adapting to individual students' learning needs and emotional states, making it impossible to provide a personalized learning experience that maximizes learning effectiveness. Furthermore, they lack the technology to analyze users' progress and emotional data in real time and provide optimal learning materials. This results in a decline in students' motivation and effectiveness in learning.

[0842] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user information via a user device, means for transmitting the user information to the server and safely storing it, means for analyzing user characteristics and extracting learning patterns using a generative AI model, an emotion engine for analyzing emotional data, means for dynamically generating customized learning materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the server, and means for the server to continuously analyze the progress data and emotional data and optimize the learning material content using the generative AI model. This makes it possible to provide optimal learning materials in real time, responding to the learning needs and emotional state of individual students.

[0843] "User device" refers to a device on which a user enters personal information when registering for the first time, browses and studies customized learning materials, and enters progress data and emotional data.

[0844] A "server" is a computer system responsible for receiving and securely storing data sent from user devices.

[0845] A "generative AI model" is a system that uses machine learning algorithms to analyze user characteristics and design optimal learning routes and curricula.

[0846] The "emotion engine" is a system that recognizes the user's emotions and analyzes emotional data.

[0847] A "learning pattern" refers to an individually optimized learning process or tendency that is derived based on a user's past grades, learning history, behavior during learning, etc.

[0848] "Customized learning materials" are learning content that is dynamically generated based on the user's characteristics and emotional state.

[0849] "Progress data" refers to data on the progress and results achieved by a user during their studies.

[0850] "Emotion data" is data that represents the user's current emotional state.

[0851] The "database" is a data storage system for safely storing the initial registration data, progress data, and emotion data received by the server.

[0852] "Real-time" refers to a state in which processing and analysis are carried out the moment an event occurs, and the results are reflected immediately.

[0853] The following describes an embodiment of the present invention. The system of the present invention consists of four main components: a user device, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[0854] User Device

[0855] The user device is a device through which students enter their personal information, learning needs, and emotional data during initial registration. Through the user device, students can:

[0856] 1. Access the initial registration screen and enter personal information such as your grade level, subjects of interest, past grades, learning goals, and current emotional state.

[0857] 2. After completing the input, press the "Send" button to send the data to the server.

[0858] 3. During learning, progress information and emotional data are input in real time and sent to the server.

[0859] 4. View new, customized learning materials as they become available and continue your learning.

[0860] server

[0861] The server receives and securely stores data sent by the user device. The server performs the following operations:

[0862] 1. Initial registration data and emotion data are stored in a database.

[0863] 2. Invoke the generative AI model to analyze the student's learning characteristics and emotional state.

[0864] 3. Based on the analysis results, the teaching material generation engine is activated to dynamically generate customized teaching materials.

[0865] 4. The generated educational material is transmitted to the user device and made accessible.

[0866] 5. Continuously receive learning progress data and emotion data and store them in a database.

[0867] 6. The generated AI model is called again based on the received data to optimize the content of the teaching materials.

[0868] Generative AI Models

[0869] The generative AI model performs analysis using student information and emotion data provided by the server. The generative AI model operates as follows:

[0870] 1. Analyze each student's learning patterns and emotional state to design the optimal learning route.

[0871] 2. The analysis results are provided to the server and used as configuration data for customized teaching materials.

[0872] 3. Continuously perform optimization processing based on students' progress data and emotion data.

[0873] Emotion Engine

[0874] The emotion engine recognizes user emotions and analyzes emotion data in real time. The specific roles of the emotion engine are as follows:

[0875] 1. Recognize user emotions.

[0876] 2. Send the emotion data to the server.

[0877] 3. Emotional data can be incorporated into generative AI models to aid in the analysis process.

[0878] Specific examples

[0879] For example, suppose a second-year high school student C wants to learn about "the laws of force in physics." The process in this case is as follows:

[0880] 1. User Device: Student C starts up the user device and selects "Laws of Force in Physics" as the subject they want to learn. They enter the necessary personal information and their current emotional state and send it to the server.

[0881] 2. Server: The server passes the received information to the analysis engine, and the generative AI model analyzes the characteristics and emotional state of student C. Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials and sends them to the user device.

[0882] 3. User device: Student C studies the provided learning materials and transmits his / her progress and emotion data from his / her device to the server.

[0883] 4. Server: The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[0884] Prompt Sentence Examples

[0885] By inputting the following prompts into the generative AI model, personalized learning materials can be generated:

[0886] Student C is a second-year high school student who wants to learn about the laws of force in physics. He has an average of 80 points in physics in the past, and he spent a lot of time understanding force vector analysis. He is also currently in a slightly anxious emotional state. Based on this information, please generate customized learning materials that are best suited to Student C.

[0887] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0888] Step 1:

[0889] A user accesses the system for the first time through a user device. On the initial registration screen, the user enters information such as their grade, subjects of interest, past grades, learning goals, and current emotional state (input: personal information, learning needs, emotional state). After completing the input, the user clicks the "Submit" button to send this data to the server (output: transmitted data).

[0890] Step 2:

[0891] The server receives the initial registration data and emotional data sent from the user device (input: sent data). The server securely stores the received data in a database (output: stored data). This data includes grade level, subject interests, grades, learning goals, emotional state, etc.

[0892] Step 3:

[0893] The server calls the generative AI model based on data stored in the database (input: stored data). The generative AI model uses the provided data to analyze the user's characteristics and emotional state. The analysis process uses machine learning algorithms to design the optimal learning route and curriculum. The analysis results are returned to the server (output: analysis results).

[0894] Step 4:

[0895] The server launches a teaching material generation engine based on the analysis results provided by the generative AI model (input: analysis results). The teaching material generation engine dynamically generates teaching materials customized for each user. The generated teaching materials include content tailored to the user's learning needs and emotional state (output: customized teaching materials).

[0896] Step 5:

[0897] The server transmits the generated customized learning materials to the user device (input: customized learning materials). The user device displays the received learning materials on the screen (output: displayed learning materials). The user then proceeds with their studies using the provided customized learning materials.

[0898] Step 6:

[0899] During learning, the user inputs progress information and emotional data in real time and transmits them from the user device to the server (input: progress information, emotional data). The transmitted progress information includes the learning completion rate, the percentage of correct answers to questions, etc.

[0900] Step 7:

[0901] The server receives the progress information and emotional data sent from the user device and stores them in a database (input: progress information, emotional data). Based on the stored data, the server invokes the generative AI model again and optimizes the content of the learning materials (output: optimized learning materials). During the optimization process, the content and difficulty of the learning materials are adjusted taking into account new learning data and emotional information.

[0902] Step 8:

[0903] The server sends the optimized learning materials back to the user device (input: optimized learning materials). The user device displays the updated learning materials on the screen and allows the user to continue learning (output: displayed optimized learning materials).

[0904] (Application example 2)

[0905] 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."

[0906] Conventional virtual stores provide only general product information and do not adequately provide product suggestions based on the user's hobbies and purchasing trends, making it difficult to provide a personalized shopping experience. Furthermore, suggestions do not take into account the user's real-time emotional state, limiting their ability to improve user satisfaction and stimulate purchasing motivation. To solve this problem, a personalized product suggestion system that utilizes the user's individual characteristics and real-time emotional data is needed.

[0907] The identification processing by the identification 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 user information via a user terminal, means for transmitting the user information to the server and securely storing it, means for analyzing user characteristics and extracting interests and purchasing tendencies using a generative AI model, means for dynamically generating customized product proposals and transmitting them to the user terminal, means for collecting real-time emotional data from the user terminal and transmitting it to the server, and means for the server to continuously analyze the emotional data and behavioral data and optimize the product proposals using the generative AI model. This enables personalized product proposals based on the user's individual characteristics and real-time emotional state.

[0908] "User terminal" is a general term for a device through which a user inputs information and communicates with a server.

[0909] "User information" refers to data about a user's personal characteristics, such as hobbies, purchasing habits, and emotional state.

[0910] A "server" is a computer system that receives and stores user information and runs a generative AI model based on that information.

[0911] A "generative AI model" is an artificial intelligence model that includes algorithms to analyze user characteristics and make product suggestions based on individual interests and purchasing trends.

[0912] "Characteristics" refers to personal attributes and behavioral patterns such as a user's interests, hobbies, and purchasing tendencies.

[0913] "Purchase trends" are predictions of future purchasing behavior based on a user's past purchasing history and data on products they have shown interest in.

[0914] "Customized product recommendations" are the provision of specific products or services that are dynamically generated based on the user's characteristics and emotions.

[0915] "Emotional data" refers to data that indicates the user's real-time emotional state and is obtained through facial expression analysis and voice analysis.

[0916] "Behavioral data" refers to data such as the actions a user takes within an application and their browsing history.

[0917] "Product Suggestions" are lists of products and services presented to users based on their characteristics and real-time emotional state.

[0918] "Optimization" is the process of continually adjusting product offerings to maximize user satisfaction.

[0919] The system for implementing this invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. The cooperation of these components makes it possible to provide a personalized shopping experience for each user in a virtual store.

[0920] Hardware and Software Configuration

[0921] 1. User Device:

[0922] Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[0923] Software: Virtual store application

[0924] Function: Collects user input information and sends it to the server, receives and displays customized product suggestions, and obtains user behavior and emotion data in real time.

[0925] 2. Server:

[0926] Hardware: High-performance computer server

[0927] Software: Database servers (e.g., MySQL, PostgreSQL), cloud platforms (e.g., AWS, Google Cloud)

[0928] Function: Securely stores user information, controls and manages the generative AI model and emotion engine. Analyzes user characteristics using the generative AI model and dynamically generates optimal product recommendations based on purchasing trends and emotion data.

[0929] 3. Generative AI Model:

[0930] Software: Machine learning algorithms and natural language processing models (e.g., GPT)

[0931] Function: Analyzes user characteristics and generates customized product suggestions based on interests and purchasing trends. Outputs analysis results based on user information and emotional data provided by the server.

[0932] 4. Emotion Engine:

[0933] Software: Emotion analysis software

[0934] Function: Analyzes the user's real-time emotional data and sends it to the server. Identifies the user's emotional state using facial recognition and voice analysis technology.

[0935] Specific examples

[0936] When users shop in the virtual store, they input their personal information, interests, and current emotional state using their device, which is then sent to a server and securely stored.

[0937] The server calls up a generative AI model based on the received user information, analyzes the user's characteristics, and dynamically generates product and service suggestions based on their interests and purchasing trends.The server then sends the generated product suggestions to the user's device, where the user can view the products and services.

[0938] In addition, the user's real-time emotional data is analyzed by the emotion engine and sent to the server, which then calls the generative AI model again based on the overall data, including the emotional data, to optimize the product recommendations.

[0939] For example, if a user's hobby is sports, their interest category is books, and their current emotion is "happy," the prompt to the generative AI model would be:

[0940] "Please suggest the best products and services based on the user's hobby: sports, category of interest: books, and current emotional state: happy."

[0941] In this way, the present invention can provide a personalized shopping experience based on the user's individual characteristics and real-time emotional data.

[0942] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0943] Step 1:

[0944] Users input their personal information, hobbies, interest categories, and current emotional state via their device. This information is sent from the device to the server and securely stored. The input data includes the user's name, age, hobbies, purchase history, real-time emotional data, etc. This allows the server to collect individual user data.

[0945] Step 2:

[0946] The server provides the collected user information to the generative AI model. The generative AI model analyzes the user's hobbies, purchasing tendencies, and emotional state, and generates a prompt to suggest optimal products and services. For example, the prompt might be in the format "Please suggest optimal products and services based on the user's hobbies: sports, category of interest: books, and current emotional state: happy." By inputting this prompt into the generative AI model, customized product suggestions are output.

[0947] Step 3:

[0948] The generative AI model generates product suggestions based on the user's characteristics and sends the results back to the server. The generated product suggestions become a list of multiple products and services based on the user's preferences. The server receives this data and sends it to the user's device.

[0949] Step 4:

[0950] The user terminal receives the customized product proposals sent from the server and displays them to the user. The user browses the product proposals and selects the products they are interested in. The data of the selected products is then sent back to the server.

[0951] Step 5:

[0952] Behavioral data associated with user operations and selections, as well as emotional data acquired in real time, are sent from the user's device to the server. For example, emotional data from the user can be acquired using facial expression analysis or voice analysis. The server receives this data and provides it back to the generative AI model.

[0953] Step 6:

[0954] The server then calls the generative AI model again based on all data, including real-time emotional data and behavioral data, analyzed by the emotion engine, to optimize the content of the product suggestions. The generative AI model then generates a prompt sentence again and outputs the optimized product suggestions.

[0955] Step 7:

[0956] The optimized product suggestions are sent from the server to the user's device and provided to the user again, and the user then shops again based on these new suggestions, personalizing the entire purchasing process.

[0957] In this way, the collaboration between the user device, server, generative AI model, and emotion engine makes it possible to provide users with personalized product suggestions that are optimized in real time.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] [Third embodiment]

[0962] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0963] 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.

[0964] 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).

[0965] 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.

[0966] 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.

[0967] 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).

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] 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.

[0973] 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."

[0974] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[0975] Overall system configuration

[0976] The system of the present invention consists of three main components: a user terminal, a server, and a generative AI model. These components work together to provide students with personalized learning experiences and educational materials.

[0977] The role of each component

[0978] 1. User Device:

[0979] This is a device that allows students to enter their personal information and learning needs during initial registration.

[0980] A tool for students to view and study customized learning materials and enter progress data.

[0981] 2. Server:

[0982] Its role is to receive data sent from the user terminal and store it safely.

[0983] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[0984] Learning progress data is continuously received and the content of the teaching materials is optimized.

[0985] 3. Generative AI Model:

[0986] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[0987] Continuous optimization process based on student progress data.

[0988] Processing flow and specific operations

[0989] The following describes how the components of the system work together to implement the present invention.

[0990] User terminal

[0991] 1. The student accesses the initial registration screen via the user device and enters personal information such as grade, subjects of interest, past grades, and learning goals.

[0992] 2. After completing the input, press the "Submit" button to send the data to the server.

[0993] 3. During learning, the user's device sends the student's current progress and answers to assignments to the server in real time.

[0994] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[0995] server

[0996] 1. The initial registration data received from the user terminal is stored in a database for safekeeping.

[0997] 2. Based on the saved data, the generative AI model is called up and used to analyze the student's learning characteristics.

[0998] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[0999] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[1000] 5. Continuously receive student progress data and store it in a database.

[1001] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[1002] Generative AI Models

[1003] 1. Using student information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[1004] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[1005] 3. Based on student progress data, continuous optimization is performed and new learning content is suggested.

[1006] Specific examples

[1007] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[1008] 1. User Device:

[1009] Student B starts up the user device and selects "calculus" as the subject he wants to learn.

[1010] Enter the necessary personal information and learning objectives and send them to the server.

[1011] 2. Server:

[1012] The server passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[1013] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "Calculus."

[1014] The generated teaching materials are sent to Student B's device.

[1015] 3. User Device:

[1016] Student B studies the provided teaching materials and sends his / her progress data and answer results from his / her terminal to the server.

[1017] 4. Server:

[1018] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[1019] In this way, the system can respond to each student's individual learning needs and provide a highly personalized learning experience.

[1020] The processing flow will be explained below.

[1021] Step 1:

[1022] The user starts up the user terminal and accesses the initial registration screen, where they enter personal information such as their grade, subjects of interest, past grades, and learning goals.

[1023] Step 2:

[1024] The terminal sends the entered personal information to the server. After sending, a confirmation message is displayed to the user to confirm completion of sending.

[1025] Step 3:

[1026] To ensure safe storage of data received from the user terminal, the server stores it in a database, encrypting the data.

[1027] Step 4:

[1028] After the server has finished saving the data, it calls the generative AI model and issues instructions to analyze the collected data.

[1029] Step 5:

[1030] The generative AI model analyzes the user's learning characteristics based on student information provided by the server, and designs learning patterns and optimal learning routes.

[1031] Step 6:

[1032] The generative AI model returns the analysis results to the server, and the server receives the analysis results.

[1033] Step 7:

[1034] Based on the analysis results, the server starts the learning material generation engine, which then dynamically generates customized learning materials.

[1035] Step 8:

[1036] The server transmits the generated customized teaching materials to the user terminal.

[1037] Step 9:

[1038] The terminal displays the received learning material to the user, allowing the user to begin learning.

[1039] Step 10:

[1040] As the user progresses with their studies, they input their progress and answer questions into the device, which then transmits this data to the server in real time.

[1041] Step 11:

[1042] The server receives the progress data sent from the user terminal and stores it in a database.

[1043] Step 12:

[1044] Based on the progress data received by the server, the generative AI model is called again and has it analyze the new data.

[1045] Step 13:

[1046] The generative AI model analyzes progress data and adjusts the content and difficulty of the learning materials as needed.

[1047] Step 14:

[1048] The server then sends the new, adjusted learning materials back to the user's device, allowing the user to continue optimally learning.

[1049] Example 1

[1050] 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."

[1051] With conventional learning systems, it is difficult to provide learning materials and learning routes optimized for each student, making it difficult to realize personalized education that meets individual learning needs. In addition, because management and optimization of learning progress is done manually, efficient learning management is not possible. Therefore, it is necessary to provide an optimal learning experience tailored to each student and improve learning efficiency.

[1052] 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.

[1053] In this invention, the server includes means for collecting learner information via a user device, means for transmitting the learner information to a data management device and safely storing it, means for analyzing learner characteristics and extracting learning patterns using a generative AI model, means for dynamically generating customized educational materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the data management device, and means for the data management device to continuously analyze the progress data and optimize the educational material content using the generative AI model, thereby providing an optimized learning environment for each student and improving the quality and efficiency of learning.

[1054] "User equipment" refers to a terminal or device that a learner accesses and uses to input learning information.

[1055] A "data management device" is a server or data storage device for safely storing and managing learner information and progress data.

[1056] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics and generate optimal learning patterns and educational materials.

[1057] "Educational materials" refer to educational materials provided to learners, and include multimedia, written, and question formats.

[1058] A "learning pattern" is an optimal learning method or route generated based on the learner's characteristics and progress.

[1059] "Progress data" refers to data such as the learner's learning progress and answer results.

[1060] "Optimizing" means improving teaching materials and learning routes according to the individual needs of learners, thereby maximizing learning efficiency.

[1061] MODE FOR CARRYING OUT THE INVENTION

[1062] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[1063] Overall system configuration

[1064] The system of the present invention consists of three main components: a user device, a data management device, and a generative AI model. These components work together to provide learners with personalized learning experiences and educational materials.

[1065] The role of each component

[1066] User equipment

[1067] This is a terminal where learners enter their personal information and learning needs during initial registration.

[1068] A tool for learners to view and study customized educational materials and enter progress data.

[1069] Data management device

[1070] Its role is to receive and securely store data sent from user devices.

[1071] A generative AI model is invoked based on the stored data to analyze the learner's learning characteristics and generate customized educational materials.

[1072] Continuously receive learning progress data and optimize the content of educational materials.

[1073] Generative AI Models

[1074] Machine learning algorithms are used to analyze learner characteristics and design optimal learning paths and content.

[1075] Continuous optimization processing is performed based on learner progress data.

[1076] Processing flow and specific operations

[1077] The following describes how the components of the system work together to implement the present invention.

[1078] User equipment

[1079] 1. The learner accesses the initial registration screen using the user device and enters personal information such as grade level, subjects of interest, past grades, and learning goals.

[1080] 2. After completing the input, press the "Send" button to send the data to the data management device.

[1081] 3. During learning, the user's device transmits the learner's current progress and the results of their answers to the assignments in real time to the data management device.

[1082] 4. When new customized educational materials are received, they are displayed to the learner to continue their learning.

[1083] Data management device

[1084] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[1085] 2. Based on the saved data, the generative AI model is called up and the learner's learning characteristics are analyzed.

[1086] 3. Based on the analysis results output by the generative AI model, a teaching material generation engine is launched to dynamically generate customized educational materials.

[1087] 4. The generated educational materials are sent to the user's device so that the learner can access them.

[1088] 5. Continuously receive learner progress data and store it in a database.

[1089] 6. Based on the received progress data, the generative AI model is called again and the content of the educational materials is optimized as needed.

[1090] Generative AI Models

[1091] 1. Using learner information provided by the data management device, individual learning patterns are analyzed and the optimal learning route is designed.

[1092] 2. Provide the data management device with configuration data for customized educational materials based on the analysis results.

[1093] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[1094] Specific examples

[1095] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[1096] User equipment

[1097] Student B turns on the user device and selects "calculus" as the subject they want to learn.

[1098] The necessary personal information and learning goals are entered and sent to the data management device.

[1099] Example prompt: "Hello! I would like to study calculus. I am a sophomore in high school and have received A's in math. My goal is to prepare for college entrance exams."

[1100] Data management device

[1101] The data management device passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[1102] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized educational materials for "Calculus."

[1103] The generated educational materials are sent to Student B's device.

[1104] User equipment

[1105] Student B studies the provided educational materials and transmits his / her progress data and answer results from his / her terminal to the data management device.

[1106] Data management device

[1107] The data management device receives the progress data and uses generative AI models to continuously optimize the content of educational materials, thus enabling the system to meet the individual learning needs of each learner and provide a highly personalized learning experience.

[1108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1109] Step 1:

[1110] The user terminal inputs the learner information.

[1111] The user accesses the initial registration screen using the user terminal. The learner enters personal information such as grade, subjects of interest, past grades, and learning goals. The entered information is sent to the server by pressing the "Submit" button.

[1112] Specific input: grade level, subjects of interest, past grades, learning goals

[1113] Specific output: Student information sent to the server

[1114] Specific operation: The user device calls the API and sends the learner information to the server via a POST request.

[1115] Step 2:

[1116] The server receives and stores student information

[1117] The server receives learner information sent from the user device via API and stores it securely in a database. When storing data, security measures such as encryption are implemented.

[1118] Specific input: Learner information sent from the user device

[1119] Specific output: Student information stored in a database

[1120] What happens: The server uses a database connection module to store the data and encrypts it as a security measure.

[1121] Step 3:

[1122] The server calls the generative AI model and analyzes its learning characteristics.

[1123] The server sends an analysis request to the generative AI model based on the stored learner information. The generative AI model analyzes the learner's characteristics and extracts the optimal learning pattern.

[1124] Specific input: Learner information stored in a database

[1125] Specific output: Analysis results of learning characteristics by generative AI model

[1126] Specific operation: The server calls the API of the generated AI model, sends learner information, and receives the analysis results.

[1127] Step 4:

[1128] The server generates customized learning materials and sends them to the user's terminal.

[1129] The server starts the learning material generation engine based on the analysis results obtained from the generative AI model, and generates customized learning materials. The generated learning materials are sent to the user's device so that they can be viewed by the learner.

[1130] Specific input: Analysis results from a generative AI model

[1131] Specific output: Customized learning materials sent to the user's device

[1132] Specific operation: The server runs the teaching material generation engine and sends the generated teaching material data to the user's terminal.

[1133] Step 5:

[1134] The user device sends progress data to the server.

[1135] Learners study using customized learning materials and input their progress and answers. The progress data is sent to the server in real time.

[1136] Specific input: Learner progress data and answer results

[1137] Specific output: Progress data sent to the server

[1138] Specific operation: The user device uses the API to send progress data to the server via a POST request.

[1139] Step 6:

[1140] The server analyzes the progress data and optimizes the content of the learning materials.

[1141] The server stores the received progress data in a database and analyzes it using a generative AI model. Based on the analysis results, the content of the learning materials is optimized and new customized learning materials are generated.

[1142] Specific input: Progress data

[1143] Specific output: Optimized and customized teaching materials

[1144] Specific operation: The server saves the progress data in a database, calls the API of the generative AI model to receive the analysis results, and then uses the learning material generation engine to generate new learning materials based on the results and send them to the user's device.

[1145] (Application example 1)

[1146] 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."

[1147] Conventional learning systems have the problem that it is difficult to provide individually optimized learning materials based on the characteristics and learning progress of each student, making it difficult to achieve effective learning.In addition, conventional systems have limited formats for learning materials, which makes it easy for students to become bored and lose motivation to learn.

[1148] 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.

[1149] In this invention, the server includes: means for collecting personal information and learning needs via a user's terminal; means for transmitting the personal information and learning needs to the server and securely storing them; means for analyzing the learner's characteristics using a generative AI model and extracting the optimal learning route and curriculum; means for dynamically generating customized learning materials and transmitting them to the user's terminal; means for collecting learning progress data from the user's terminal and transmitting it to the server; and means for the server to continuously analyze the progress data and optimize the learning material content using the generative AI model. This makes it possible to provide learning materials optimized for each individual learner and maximize learning effectiveness. Furthermore, by providing a variety of learning material formats, including video, text, and quiz formats, an interactive learning experience can be provided, sustaining the learner's interest.

[1150] "User Device" means a device through which a student enters personal information and learning needs, views and studies customized learning materials, and enters progress data.

[1151] The "server" is a computer system that receives and securely stores data sent from user devices, and calls generative AI models to analyze the data and generate learning materials to provide an optimized learning experience.

[1152] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics, design optimal learning routes and curricula, and dynamically generate customized teaching materials.

[1153] "Learning characteristics" refers to various factors related to learning, such as a learner's individual learning style, level of comprehension, interests, and past grades.

[1154] "Customized learning materials" are individually optimized learning content that is generated based on the learner's characteristics and learning progress, and supports efficient learning.

[1155] "Personal information" refers to information that can identify a learner, such as the learner's name, grade, subjects of interest, past grades, and learning goals.

[1156] "Learning needs" refers to the content and goals that learners want to learn in a particular field or subject.

[1157] "Learning progress data" refers to data that indicates the progress of a learner's learning, such as the learning materials and assignments that the learner has worked on, and the answers they have given.

[1158] "Optimization" is the process of continuously adjusting and improving the content and sequence of the learning materials provided based on learner progress data.

[1159] An "interactive learning experience" is a learning environment designed to allow learners to actively participate in learning and receive feedback in real time.

[1160] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[1161] Overall system configuration

[1162] The system of the present invention mainly consists of a user terminal, a server, and a generative AI model. These components work together to provide learners with individually optimized learning experiences and learning materials.

[1163] The role of each component

[1164] 1. User Device

[1165] This is a device that allows learners to enter their personal information and learning needs during initial registration.

[1166] It is a tool that allows learners to view and study customized learning materials and enter progress data.

[1167] 2. Server

[1168] It is a computer system that receives and securely stores data sent from user terminals.

[1169] Based on the stored data, a generative AI model is called up, which analyzes the learner's characteristics and designs and generates the optimal learning route and curriculum.

[1170] It continuously receives learning progress data and uses generative AI models to optimize the content of the learning materials.

[1171] 3. Generative AI Models

[1172] Machine learning algorithms are used to analyze learner characteristics and design optimal learning routes and curricula.

[1173] Continuous optimization processing is performed based on learner progress data.

[1174] Processing flow and specific operations

[1175] The following describes how the components of the system work together to implement the present invention.

[1176] User Device

[1177] 1. The learner accesses the initial registration screen via the user device and enters personal information such as name, grade, subjects of interest, past grades, and learning objectives.

[1178] 2. After completing the input, press the "Submit" button to send the data to the server.

[1179] 3. During learning, the user's device sends the learner's current progress and answers to the assignments to the server in real time.

[1180] 4. When new customized learning materials are received, they are displayed to the learner, allowing them to continue their learning.

[1181] server

[1182] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[1183] 2. Call up the generative AI model based on the saved data and have it analyze the learner's characteristics.

[1184] 3. Customized teaching materials are dynamically generated based on the analysis results output by the generative AI model.

[1185] 4. The generated teaching materials are sent to the user's device so that the learner can access them.

[1186] 5. Continuously receive learner progress data and store it in a database.

[1187] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[1188] Generative AI Models

[1189] 1. Using learner information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[1190] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[1191] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[1192] Specific examples

[1193] For example, if a third-year junior high school student wants to learn calculus:

[1194] 1. User Device

[1195] The learner starts up the user device and selects "calculus" as the subject they wish to learn.

[1196] Enter the necessary personal information and learning objectives and send them to the server.

[1197] 2. Server

[1198] The server passes the received information to an analysis engine, and the generative AI model analyzes the learner's characteristics.

[1199] Customized teaching materials are generated based on the analysis results provided by the generative AI model.

[1200] The generated teaching materials are sent to the learner's terminal.

[1201] 3. User Device

[1202] The learner studies the provided learning materials and transmits the progress data and answer results from the terminal to the server.

[1203] 4. Server

[1204] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[1205] In this way, the system can respond to each learner's individual learning needs and provide a highly personalized learning experience.

[1206] Example prompt sentence:

[1207] Student Profile: Name - Student, Grade - 3, Interests - Mathematics, Past Grades - B, Learning Objective - Understand Calculus

[1208] Generate the best study plan for you.

[1209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1210] Step 1:

[1211] The user starts up the user device and accesses the initial registration screen. They enter personal information such as their name, grade, subjects of interest, past grades, and learning goals. This input data is sent from the user device to the server. The input data includes name, grade, subjects of interest, past grades, and learning goals. The server receives this data and stores it in a database for safekeeping.

[1212] Step 2:

[1213] The server calls the generative AI model using the stored user's personal information and learning needs data. The input data includes personal information and learning needs data. The generative AI model uses a machine learning algorithm to analyze the learner's characteristics and design the optimal learning route and curriculum. The output is the analyzed learning characteristics and the optimal learning route. Based on this, the server begins the process of generating customized learning materials according to the learner's characteristics.

[1214] Step 3:

[1215] The server dynamically generates the customized learning materials. The input data includes the learning route and curriculum data obtained by the generative AI model. The server uses this data to generate learning materials in the form of videos, text, and quizzes, and sends them to the user's device. The output is interactive learning materials. The user's device displays the received learning materials to the learner, who then begins learning using them.

[1216] Step 4:

[1217] As users study via their user devices, they input progress data and answer results in real time. The input data includes learning progress information and answer results. The user devices send this data to the server. The server continuously receives the progress data and stores it in a database.

[1218] Step 5:

[1219] The server analyzes the progress data and calls the generative AI model again. The input data is the progress data. The generative AI model continuously performs optimization processing based on the progress data. The output is new, optimized learning content and suggested learning materials. The server generates new customized learning materials based on this and sends them back to the user's device.

[1220] Step 6:

[1221] The user receives new customized learning materials and continues learning using them. The user's device again collects learning progress data and sends it to the server, providing a continuous learning experience that adapts to the learner's progress.

[1222] 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.

[1223] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[1224] Overall system configuration

[1225] The system of the present invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[1226] The role of each component

[1227] 1. User Device:

[1228] This is a device that allows students to enter personal information, learning needs, and emotional data during initial registration.

[1229] It is a tool for students to view and study customized learning materials and enter progress and sentiment data.

[1230] 2. Server:

[1231] Its role is to receive data sent from the user terminal and store it safely.

[1232] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[1233] Learning progress data and emotional data are continuously received and the content of the learning materials is adjusted to suit the needs of the student.

[1234] 3. Generative AI Model:

[1235] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[1236] Emotional data is combined and analyzed to optimize the content of teaching materials.

[1237] 4. Emotion Engine:

[1238] This is a system for recognizing user emotions and analyzing emotional data.

[1239] Emotional data is sent to a server to help analyze learning patterns and generate teaching materials.

[1240] Processing flow and specific operations

[1241] The following describes how the components of the system work together to implement the present invention.

[1242] User terminal

[1243] 1. The student accesses the initial registration screen via the user terminal and enters personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state.

[1244] 2. After completing the input, press the "Submit" button to send the data to the server.

[1245] 3. During learning, the user device transmits the student's progress information and emotional data to the server in real time.

[1246] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[1247] server

[1248] 1. The initial registration data and emotion data received from the user device are stored in a database for safekeeping.

[1249] 2. Based on the stored data, a generative AI model is invoked to analyze the student's learning characteristics and emotional state.

[1250] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[1251] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[1252] 5. Continuously receive student progress information and emotional data and store them in a database.

[1253] 6. Based on the received progress and emotion data, the generative AI model is called again and the content of the teaching material is optimized as needed.

[1254] Generative AI Models

[1255] 1. Using student information and emotional data provided by the server, individual learning patterns and emotional states are analyzed and the optimal learning route is designed.

[1256] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[1257] 3. Continuously perform optimization processing based on student progress data and emotion data.

[1258] Emotion Engine

[1259] 1. Recognize user emotions and analyze emotional data in real time.

[1260] 2. The analysis results are sent to the server and incorporated into the analysis process of the generative AI model.

[1261] Specific examples

[1262] For example, if Student C, a second-year high school student, wants to learn about the "force laws of physics":

[1263] 1. User Device:

[1264] Student C starts up the user terminal and selects "Laws of Force in Physics" as the topic he wants to learn.

[1265] The necessary personal information and current emotional state are entered and sent to the server.

[1266] 2. Server:

[1267] The server passes the received information to the analysis engine, and the generative AI model analyzes Student C's characteristics and emotional state.

[1268] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "The Laws of Force in Physics."

[1269] The generated teaching materials are sent to Student C's device.

[1270] 3. User Device:

[1271] Student C studies the provided learning materials and transmits his / her progress and emotional data from his / her terminal to the server.

[1272] 4. Server:

[1273] The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[1274] In this way, the system can respond to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[1275] The processing flow will be explained below.

[1276] Step 1:

[1277] The user starts up the user terminal and accesses the initial registration screen. The user inputs personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state (e.g., self-assessment questionnaire or facial expression recognition).

[1278] Step 2:

[1279] The terminal transmits the input personal information and emotion data to the server, and displays a message to the user confirming completion of transmission.

[1280] Step 3:

[1281] The server stores the data received from the user terminal in a database for safe storage. At this time, the data is encrypted.

[1282] Step 4:

[1283] After the server has finished saving the data, it calls the generative AI model and emotion engine and issues instructions to analyze the collected data.

[1284] Step 5:

[1285] The generative AI model designs learning patterns and optimal learning routes based on student information provided by the server (learning characteristics, past grades, interests, etc.).

[1286] Step 6:

[1287] The emotion engine analyzes the emotion data provided by the server and evaluates the student's current emotional state.

[1288] Step 7:

[1289] The server compiles the analysis results of the generative AI model and the emotion engine and activates the teaching material generation engine to generate customized teaching materials.

[1290] Step 8:

[1291] Based on the analysis results, the teaching material generation engine dynamically generates customized teaching materials in the form of videos, text, and quizzes.

[1292] Step 9:

[1293] The server transmits the generated educational material to the user terminal so that the user can access it.

[1294] Step 10:

[1295] The user terminal displays the received customized learning material to the user, and the user begins learning.

[1296] Step 11:

[1297] As the user progresses with their learning, they input their progress, answering questions, and real-time emotional data into the device, which then transmits this data to the server.

[1298] Step 12:

[1299] The server receives the progress data and emotion data sent from the user terminal and stores them in a database.

[1300] Step 13:

[1301] Based on the progress data and emotion data received by the server, the generative AI model and emotion engine are called again to analyze the new data.

[1302] Step 14:

[1303] A generative AI model analyzes progress data and optimizes learning content based on learning patterns.

[1304] Step 15:

[1305] The emotional engine analyzes the latest emotional data and adjusts the content and learning methods to best suit the student's current emotional state.

[1306] Step 16:

[1307] The server then transmits the adjusted new learning materials to the user terminal again, allowing the user to continue optimal learning.

[1308] In this way, the system can adapt to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[1309] Example 2

[1310] 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."

[1311] Conventional learning systems have difficulty adapting to individual students' learning needs and emotional states, making it impossible to provide a personalized learning experience that maximizes learning effectiveness. Furthermore, they lack the technology to analyze users' progress and emotional data in real time and provide optimal learning materials. This results in a decline in students' motivation and effectiveness in learning.

[1312] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user information via a user device, means for transmitting the user information to the server and safely storing it, means for analyzing user characteristics and extracting learning patterns using a generative AI model, an emotion engine for analyzing emotional data, means for dynamically generating customized learning materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the server, and means for the server to continuously analyze the progress data and emotional data and optimize the learning material content using the generative AI model. This makes it possible to provide optimal learning materials in real time, responding to the learning needs and emotional state of individual students.

[1313] "User device" refers to a device on which a user enters personal information when registering for the first time, browses and studies customized learning materials, and enters progress data and emotional data.

[1314] A "server" is a computer system responsible for receiving and securely storing data sent from user devices.

[1315] A "generative AI model" is a system that uses machine learning algorithms to analyze user characteristics and design optimal learning routes and curricula.

[1316] The "emotion engine" is a system that recognizes the user's emotions and analyzes emotional data.

[1317] A "learning pattern" refers to an individually optimized learning process or tendency that is derived based on a user's past grades, learning history, behavior during learning, etc.

[1318] "Customized learning materials" are learning content that is dynamically generated based on the user's characteristics and emotional state.

[1319] "Progress data" refers to data on the progress and results achieved by a user during their studies.

[1320] "Emotion data" is data that represents the user's current emotional state.

[1321] The "database" is a data storage system for safely storing the initial registration data, progress data, and emotion data received by the server.

[1322] "Real-time" refers to a state in which processing and analysis are carried out the moment an event occurs, and the results are reflected immediately.

[1323] The following describes an embodiment of the present invention. The system of the present invention consists of four main components: a user device, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[1324] User Device

[1325] The user device is a device through which students enter their personal information, learning needs, and emotional data during initial registration. Through the user device, students can:

[1326] 1. Access the initial registration screen and enter personal information such as your grade level, subjects of interest, past grades, learning goals, and current emotional state.

[1327] 2. After completing the input, press the "Send" button to send the data to the server.

[1328] 3. During learning, progress information and emotional data are input in real time and sent to the server.

[1329] 4. View new, customized learning materials as they become available and continue your learning.

[1330] server

[1331] The server receives and securely stores data sent by the user device. The server performs the following operations:

[1332] 1. Initial registration data and emotion data are stored in a database.

[1333] 2. Invoke the generative AI model to analyze the student's learning characteristics and emotional state.

[1334] 3. Based on the analysis results, the teaching material generation engine is activated to dynamically generate customized teaching materials.

[1335] 4. The generated educational material is transmitted to the user device and made accessible.

[1336] 5. Continuously receive learning progress data and emotion data and store them in a database.

[1337] 6. The generated AI model is called again based on the received data to optimize the content of the teaching materials.

[1338] Generative AI Models

[1339] The generative AI model performs analysis using student information and emotion data provided by the server. The generative AI model operates as follows:

[1340] 1. Analyze each student's learning patterns and emotional state to design the optimal learning route.

[1341] 2. The analysis results are provided to the server and used as configuration data for customized teaching materials.

[1342] 3. Continuously perform optimization processing based on students' progress data and emotion data.

[1343] Emotion Engine

[1344] The emotion engine recognizes user emotions and analyzes emotion data in real time. The specific roles of the emotion engine are as follows:

[1345] 1. Recognize user emotions.

[1346] 2. Send the emotion data to the server.

[1347] 3. Emotional data can be incorporated into generative AI models to aid in the analysis process.

[1348] Specific examples

[1349] For example, suppose a second-year high school student C wants to learn about "the laws of force in physics." The process in this case is as follows:

[1350] 1. User Device: Student C starts up the user device and selects "Laws of Force in Physics" as the subject they want to learn. They enter the necessary personal information and their current emotional state and send it to the server.

[1351] 2. Server: The server passes the received information to the analysis engine, and the generative AI model analyzes the characteristics and emotional state of student C. Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials and sends them to the user device.

[1352] 3. User device: Student C studies the provided learning materials and transmits his / her progress and emotion data from his / her device to the server.

[1353] 4. Server: The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[1354] Prompt Sentence Examples

[1355] By inputting the following prompts into the generative AI model, personalized learning materials can be generated:

[1356] Student C is a second-year high school student who wants to learn about the laws of force in physics. He has an average of 80 points in physics in the past, and he spent a lot of time understanding force vector analysis. He is also currently in a slightly anxious emotional state. Based on this information, please generate customized learning materials that are best suited to Student C.

[1357] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1358] Step 1:

[1359] A user accesses the system for the first time through a user device. On the initial registration screen, the user enters information such as their grade, subjects of interest, past grades, learning goals, and current emotional state (input: personal information, learning needs, emotional state). After completing the input, the user clicks the "Submit" button to send this data to the server (output: transmitted data).

[1360] Step 2:

[1361] The server receives the initial registration data and emotional data sent from the user device (input: sent data). The server securely stores the received data in a database (output: stored data). This data includes grade level, subject interests, grades, learning goals, emotional state, etc.

[1362] Step 3:

[1363] The server calls the generative AI model based on data stored in the database (input: stored data). The generative AI model uses the provided data to analyze the user's characteristics and emotional state. The analysis process uses machine learning algorithms to design the optimal learning route and curriculum. The analysis results are returned to the server (output: analysis results).

[1364] Step 4:

[1365] The server launches a teaching material generation engine based on the analysis results provided by the generative AI model (input: analysis results). The teaching material generation engine dynamically generates teaching materials customized for each user. The generated teaching materials include content tailored to the user's learning needs and emotional state (output: customized teaching materials).

[1366] Step 5:

[1367] The server transmits the generated customized learning materials to the user device (input: customized learning materials). The user device displays the received learning materials on the screen (output: displayed learning materials). The user then proceeds with their studies using the provided customized learning materials.

[1368] Step 6:

[1369] During learning, the user inputs progress information and emotional data in real time and transmits them from the user device to the server (input: progress information, emotional data). The transmitted progress information includes the learning completion rate, the percentage of correct answers to questions, etc.

[1370] Step 7:

[1371] The server receives the progress information and emotional data sent from the user device and stores them in a database (input: progress information, emotional data). Based on the stored data, the server invokes the generative AI model again and optimizes the content of the learning materials (output: optimized learning materials). During the optimization process, the content and difficulty of the learning materials are adjusted taking into account new learning data and emotional information.

[1372] Step 8:

[1373] The server sends the optimized learning materials back to the user device (input: optimized learning materials). The user device displays the updated learning materials on the screen and allows the user to continue learning (output: displayed optimized learning materials).

[1374] (Application example 2)

[1375] 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."

[1376] Conventional virtual stores provide only general product information and do not adequately provide product suggestions based on the user's hobbies and purchasing trends, making it difficult to provide a personalized shopping experience. Furthermore, suggestions do not take into account the user's real-time emotional state, limiting their ability to improve user satisfaction and stimulate purchasing motivation. To solve this problem, a personalized product suggestion system that utilizes the user's individual characteristics and real-time emotional data is needed.

[1377] The identification processing by the identification 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 user information via a user terminal, means for transmitting the user information to the server and securely storing it, means for analyzing user characteristics and extracting interests and purchasing tendencies using a generative AI model, means for dynamically generating customized product proposals and transmitting them to the user terminal, means for collecting real-time emotional data from the user terminal and transmitting it to the server, and means for the server to continuously analyze the emotional data and behavioral data and optimize the product proposals using the generative AI model. This enables personalized product proposals based on the user's individual characteristics and real-time emotional state.

[1378] "User terminal" is a general term for a device through which a user inputs information and communicates with a server.

[1379] "User information" refers to data about a user's personal characteristics, such as hobbies, purchasing habits, and emotional state.

[1380] A "server" is a computer system that receives and stores user information and runs a generative AI model based on that information.

[1381] A "generative AI model" is an artificial intelligence model that includes algorithms to analyze user characteristics and make product suggestions based on individual interests and purchasing trends.

[1382] "Characteristics" refers to personal attributes and behavioral patterns such as a user's interests, hobbies, and purchasing tendencies.

[1383] "Purchase trends" are predictions of future purchasing behavior based on a user's past purchasing history and data on products they have shown interest in.

[1384] "Customized product recommendations" are the provision of specific products or services that are dynamically generated based on the user's characteristics and emotions.

[1385] "Emotional data" refers to data that indicates the user's real-time emotional state and is obtained through facial expression analysis and voice analysis.

[1386] "Behavioral data" refers to data such as the actions a user takes within an application and their browsing history.

[1387] "Product Suggestions" are lists of products and services presented to users based on their characteristics and real-time emotional state.

[1388] "Optimization" is the process of continually adjusting product offerings to maximize user satisfaction.

[1389] The system for implementing this invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. The cooperation of these components makes it possible to provide a personalized shopping experience for each user in a virtual store.

[1390] Hardware and Software Configuration

[1391] 1. User Device:

[1392] Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[1393] Software: Virtual store application

[1394] Function: Collects user input information and sends it to the server, receives and displays customized product suggestions, and obtains user behavior and emotion data in real time.

[1395] 2. Server:

[1396] Hardware: High-performance computer server

[1397] Software: Database servers (e.g., MySQL, PostgreSQL), cloud platforms (e.g., AWS, Google Cloud)

[1398] Function: Securely stores user information, controls and manages the generative AI model and emotion engine. Analyzes user characteristics using the generative AI model and dynamically generates optimal product recommendations based on purchasing trends and emotion data.

[1399] 3. Generative AI Model:

[1400] Software: Machine learning algorithms and natural language processing models (e.g., GPT)

[1401] Function: Analyzes user characteristics and generates customized product suggestions based on interests and purchasing trends. Outputs analysis results based on user information and emotional data provided by the server.

[1402] 4. Emotion Engine:

[1403] Software: Emotion analysis software

[1404] Function: Analyzes the user's real-time emotional data and sends it to the server. Identifies the user's emotional state using facial recognition and voice analysis technology.

[1405] Specific examples

[1406] When users shop in the virtual store, they input their personal information, interests, and current emotional state using their device, which is then sent to a server and securely stored.

[1407] The server calls up a generative AI model based on the received user information, analyzes the user's characteristics, and dynamically generates product and service suggestions based on their interests and purchasing trends.The server then sends the generated product suggestions to the user's device, where the user can view the products and services.

[1408] In addition, the user's real-time emotional data is analyzed by the emotion engine and sent to the server, which then calls the generative AI model again based on the overall data, including the emotional data, to optimize the product recommendations.

[1409] For example, if a user's hobby is sports, their interest category is books, and their current emotion is "happy," the prompt to the generative AI model would be:

[1410] "Please suggest the best products and services based on the user's hobby: sports, category of interest: books, and current emotional state: happy."

[1411] In this way, the present invention can provide a personalized shopping experience based on the user's individual characteristics and real-time emotional data.

[1412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1413] Step 1:

[1414] Users input their personal information, hobbies, interest categories, and current emotional state via their device. This information is sent from the device to the server and securely stored. The input data includes the user's name, age, hobbies, purchase history, real-time emotional data, etc. This allows the server to collect individual user data.

[1415] Step 2:

[1416] The server provides the collected user information to the generative AI model. The generative AI model analyzes the user's hobbies, purchasing tendencies, and emotional state, and generates a prompt to suggest optimal products and services. For example, the prompt might be in the format "Please suggest optimal products and services based on the user's hobbies: sports, category of interest: books, and current emotional state: happy." By inputting this prompt into the generative AI model, customized product suggestions are output.

[1417] Step 3:

[1418] The generative AI model generates product suggestions based on the user's characteristics and sends the results back to the server. The generated product suggestions become a list of multiple products and services based on the user's preferences. The server receives this data and sends it to the user's device.

[1419] Step 4:

[1420] The user terminal receives the customized product proposals sent from the server and displays them to the user. The user browses the product proposals and selects the products they are interested in. The data of the selected products is then sent back to the server.

[1421] Step 5:

[1422] Behavioral data associated with user operations and selections, as well as emotional data acquired in real time, are sent from the user's device to the server. For example, emotional data from the user can be acquired using facial expression analysis or voice analysis. The server receives this data and provides it back to the generative AI model.

[1423] Step 6:

[1424] The server then calls the generative AI model again based on all data, including real-time emotional data and behavioral data, analyzed by the emotion engine, to optimize the content of the product suggestions. The generative AI model then generates a prompt sentence again and outputs the optimized product suggestions.

[1425] Step 7:

[1426] The optimized product suggestions are sent from the server to the user's device and provided to the user again, and the user then shops again based on these new suggestions, personalizing the entire purchasing process.

[1427] In this way, the collaboration between the user device, server, generative AI model, and emotion engine makes it possible to provide users with personalized product suggestions that are optimized in real time.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] [Fourth embodiment]

[1432] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1433] 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.

[1434] 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).

[1435] 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.

[1436] 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.

[1437] 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).

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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."

[1445] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[1446] Overall system configuration

[1447] The system of the present invention consists of three main components: a user terminal, a server, and a generative AI model. These components work together to provide students with personalized learning experiences and educational materials.

[1448] The role of each component

[1449] 1. User Device:

[1450] This is a device that allows students to enter their personal information and learning needs during initial registration.

[1451] A tool for students to view and study customized learning materials and enter progress data.

[1452] 2. Server:

[1453] Its role is to receive data sent from the user terminal and store it safely.

[1454] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[1455] Learning progress data is continuously received and the content of the teaching materials is optimized.

[1456] 3. Generative AI Model:

[1457] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[1458] Continuous optimization process based on student progress data.

[1459] Processing flow and specific operations

[1460] The following describes how the components of the system work together to implement the present invention.

[1461] User terminal

[1462] 1. The student accesses the initial registration screen via the user device and enters personal information such as grade, subjects of interest, past grades, and learning goals.

[1463] 2. After completing the input, press the "Submit" button to send the data to the server.

[1464] 3. During learning, the user's device sends the student's current progress and answers to assignments to the server in real time.

[1465] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[1466] server

[1467] 1. The initial registration data received from the user terminal is stored in a database for safekeeping.

[1468] 2. Based on the saved data, the generative AI model is called up and used to analyze the student's learning characteristics.

[1469] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[1470] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[1471] 5. Continuously receive student progress data and store it in a database.

[1472] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[1473] Generative AI Models

[1474] 1. Using student information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[1475] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[1476] 3. Based on student progress data, continuous optimization is performed and new learning content is suggested.

[1477] Specific examples

[1478] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[1479] 1. User Device:

[1480] Student B starts up the user device and selects "calculus" as the subject he wants to learn.

[1481] Enter the necessary personal information and learning objectives and send them to the server.

[1482] 2. Server:

[1483] The server passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[1484] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "Calculus."

[1485] The generated teaching materials are sent to Student B's device.

[1486] 3. User Device:

[1487] Student B studies the provided teaching materials and sends his / her progress data and answer results from his / her terminal to the server.

[1488] 4. Server:

[1489] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[1490] In this way, the system can respond to each student's individual learning needs and provide a highly personalized learning experience.

[1491] The processing flow will be explained below.

[1492] Step 1:

[1493] The user starts up the user terminal and accesses the initial registration screen, where they enter personal information such as their grade, subjects of interest, past grades, and learning goals.

[1494] Step 2:

[1495] The terminal sends the entered personal information to the server. After sending, a confirmation message is displayed to the user to confirm completion of sending.

[1496] Step 3:

[1497] To ensure safe storage of data received from the user terminal, the server stores it in a database, encrypting the data.

[1498] Step 4:

[1499] After the server has finished saving the data, it calls the generative AI model and issues instructions to analyze the collected data.

[1500] Step 5:

[1501] The generative AI model analyzes the user's learning characteristics based on student information provided by the server, and designs learning patterns and optimal learning routes.

[1502] Step 6:

[1503] The generative AI model returns the analysis results to the server, and the server receives the analysis results.

[1504] Step 7:

[1505] Based on the analysis results, the server starts the learning material generation engine, which then dynamically generates customized learning materials.

[1506] Step 8:

[1507] The server transmits the generated customized teaching materials to the user terminal.

[1508] Step 9:

[1509] The terminal displays the received learning material to the user, allowing the user to begin learning.

[1510] Step 10:

[1511] As the user progresses with their studies, they input their progress and answer questions into the device, which then transmits this data to the server in real time.

[1512] Step 11:

[1513] The server receives the progress data sent from the user terminal and stores it in a database.

[1514] Step 12:

[1515] Based on the progress data received by the server, the generative AI model is called again and has it analyze the new data.

[1516] Step 13:

[1517] The generative AI model analyzes progress data and adjusts the content and difficulty of the learning materials as needed.

[1518] Step 14:

[1519] The server then sends the new, adjusted learning materials back to the user's device, allowing the user to continue optimally learning.

[1520] Example 1

[1521] 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."

[1522] With conventional learning systems, it is difficult to provide learning materials and learning routes optimized for each student, making it difficult to realize personalized education that meets individual learning needs. In addition, because management and optimization of learning progress is done manually, efficient learning management is not possible. Therefore, it is necessary to provide an optimal learning experience tailored to each student and improve learning efficiency.

[1523] 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.

[1524] In this invention, the server includes means for collecting learner information via a user device, means for transmitting the learner information to a data management device and safely storing it, means for analyzing learner characteristics and extracting learning patterns using a generative AI model, means for dynamically generating customized educational materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the data management device, and means for the data management device to continuously analyze the progress data and optimize the educational material content using the generative AI model, thereby providing an optimized learning environment for each student and improving the quality and efficiency of learning.

[1525] "User equipment" refers to a terminal or device that a learner accesses and uses to input learning information.

[1526] A "data management device" is a server or data storage device for safely storing and managing learner information and progress data.

[1527] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics and generate optimal learning patterns and educational materials.

[1528] "Educational materials" refer to educational materials provided to learners, and include multimedia, written, and question formats.

[1529] A "learning pattern" is an optimal learning method or route generated based on the learner's characteristics and progress.

[1530] "Progress data" refers to data such as the learner's learning progress and answer results.

[1531] "Optimizing" means improving teaching materials and learning routes according to the individual needs of learners, thereby maximizing learning efficiency.

[1532] MODE FOR CARRYING OUT THE INVENTION

[1533] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[1534] Overall system configuration

[1535] The system of the present invention consists of three main components: a user device, a data management device, and a generative AI model. These components work together to provide learners with personalized learning experiences and educational materials.

[1536] The role of each component

[1537] User equipment

[1538] This is a terminal where learners enter their personal information and learning needs during initial registration.

[1539] A tool for learners to view and study customized educational materials and enter progress data.

[1540] Data management device

[1541] Its role is to receive and securely store data sent from user devices.

[1542] A generative AI model is invoked based on the stored data to analyze the learner's learning characteristics and generate customized educational materials.

[1543] Continuously receive learning progress data and optimize the content of educational materials.

[1544] Generative AI Models

[1545] Machine learning algorithms are used to analyze learner characteristics and design optimal learning paths and content.

[1546] Continuous optimization processing is performed based on learner progress data.

[1547] Processing flow and specific operations

[1548] The following describes how the components of the system work together to implement the present invention.

[1549] User equipment

[1550] 1. The learner accesses the initial registration screen using the user device and enters personal information such as grade level, subjects of interest, past grades, and learning goals.

[1551] 2. After completing the input, press the "Send" button to send the data to the data management device.

[1552] 3. During learning, the user's device transmits the learner's current progress and the results of their answers to the assignments in real time to the data management device.

[1553] 4. When new customized educational materials are received, they are displayed to the learner to continue their learning.

[1554] Data management device

[1555] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[1556] 2. Based on the saved data, the generative AI model is called up and the learner's learning characteristics are analyzed.

[1557] 3. Based on the analysis results output by the generative AI model, a teaching material generation engine is launched to dynamically generate customized educational materials.

[1558] 4. The generated educational materials are sent to the user's device so that the learner can access them.

[1559] 5. Continuously receive learner progress data and store it in a database.

[1560] 6. Based on the received progress data, the generative AI model is called again and the content of the educational materials is optimized as needed.

[1561] Generative AI Models

[1562] 1. Using learner information provided by the data management device, individual learning patterns are analyzed and the optimal learning route is designed.

[1563] 2. Provide the data management device with configuration data for customized educational materials based on the analysis results.

[1564] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[1565] Specific examples

[1566] For example, if Student B, a second-year high school student, wants to learn "Calculus":

[1567] User equipment

[1568] Student B turns on the user device and selects "calculus" as the subject they want to learn.

[1569] The necessary personal information and learning goals are entered and sent to the data management device.

[1570] Example prompt: "Hello! I would like to study calculus. I am a sophomore in high school and have received A's in math. My goal is to prepare for college entrance exams."

[1571] Data management device

[1572] The data management device passes the received information to the analysis engine, and the generative AI model analyzes Student B's characteristics.

[1573] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized educational materials for "Calculus."

[1574] The generated educational materials are sent to Student B's device.

[1575] User equipment

[1576] Student B studies the provided educational materials and transmits his / her progress data and answer results from his / her terminal to the data management device.

[1577] Data management device

[1578] The data management device receives the progress data and uses generative AI models to continuously optimize the content of educational materials, thus enabling the system to meet the individual learning needs of each learner and provide a highly personalized learning experience.

[1579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1580] Step 1:

[1581] The user terminal inputs the learner information.

[1582] The user accesses the initial registration screen using the user terminal. The learner enters personal information such as grade, subjects of interest, past grades, and learning goals. The entered information is sent to the server by pressing the "Submit" button.

[1583] Specific input: grade level, subjects of interest, past grades, learning goals

[1584] Specific output: Student information sent to the server

[1585] Specific operation: The user device calls the API and sends the learner information to the server via a POST request.

[1586] Step 2:

[1587] The server receives and stores student information

[1588] The server receives learner information sent from the user device via API and stores it securely in a database. When storing data, security measures such as encryption are implemented.

[1589] Specific input: Learner information sent from the user device

[1590] Specific output: Student information stored in a database

[1591] What happens: The server uses a database connection module to store the data and encrypts it as a security measure.

[1592] Step 3:

[1593] The server calls the generative AI model and analyzes its learning characteristics.

[1594] The server sends an analysis request to the generative AI model based on the stored learner information. The generative AI model analyzes the learner's characteristics and extracts the optimal learning pattern.

[1595] Specific input: Learner information stored in a database

[1596] Specific output: Analysis results of learning characteristics by generative AI model

[1597] Specific operation: The server calls the API of the generated AI model, sends learner information, and receives the analysis results.

[1598] Step 4:

[1599] The server generates customized learning materials and sends them to the user's terminal.

[1600] The server starts the learning material generation engine based on the analysis results obtained from the generative AI model, and generates customized learning materials. The generated learning materials are sent to the user's device so that they can be viewed by the learner.

[1601] Specific input: Analysis results from a generative AI model

[1602] Specific output: Customized learning materials sent to the user's device

[1603] Specific operation: The server runs the teaching material generation engine and sends the generated teaching material data to the user's terminal.

[1604] Step 5:

[1605] The user device sends progress data to the server.

[1606] Learners study using customized learning materials and input their progress and answers. The progress data is sent to the server in real time.

[1607] Specific input: Learner progress data and answer results

[1608] Specific output: Progress data sent to the server

[1609] Specific operation: The user device uses the API to send progress data to the server via a POST request.

[1610] Step 6:

[1611] The server analyzes the progress data and optimizes the content of the learning materials.

[1612] The server stores the received progress data in a database and analyzes it using a generative AI model. Based on the analysis results, the content of the learning materials is optimized and new customized learning materials are generated.

[1613] Specific input: Progress data

[1614] Specific output: Optimized and customized teaching materials

[1615] Specific operation: The server saves the progress data in a database, calls the API of the generative AI model to receive the analysis results, and then uses the learning material generation engine to generate new learning materials based on the results and send them to the user's device.

[1616] (Application example 1)

[1617] 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."

[1618] Conventional learning systems have the problem that it is difficult to provide individually optimized learning materials based on the characteristics and learning progress of each student, making it difficult to achieve effective learning.In addition, conventional systems have limited formats for learning materials, which makes it easy for students to become bored and lose motivation to learn.

[1619] 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.

[1620] In this invention, the server includes: means for collecting personal information and learning needs via a user's terminal; means for transmitting the personal information and learning needs to the server and securely storing them; means for analyzing the learner's characteristics using a generative AI model and extracting the optimal learning route and curriculum; means for dynamically generating customized learning materials and transmitting them to the user's terminal; means for collecting learning progress data from the user's terminal and transmitting it to the server; and means for the server to continuously analyze the progress data and optimize the learning material content using the generative AI model. This makes it possible to provide learning materials optimized for each individual learner and maximize learning effectiveness. Furthermore, by providing a variety of learning material formats, including video, text, and quiz formats, an interactive learning experience can be provided, sustaining the learner's interest.

[1621] "User Device" means a device through which a student enters personal information and learning needs, views and studies customized learning materials, and enters progress data.

[1622] The "server" is a computer system that receives and securely stores data sent from user devices, and calls generative AI models to analyze the data and generate learning materials to provide an optimized learning experience.

[1623] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze learner characteristics, design optimal learning routes and curricula, and dynamically generate customized teaching materials.

[1624] "Learning characteristics" refers to various factors related to learning, such as a learner's individual learning style, level of comprehension, interests, and past grades.

[1625] "Customized learning materials" are individually optimized learning content that is generated based on the learner's characteristics and learning progress, and supports efficient learning.

[1626] "Personal information" refers to information that can identify a learner, such as the learner's name, grade, subjects of interest, past grades, and learning goals.

[1627] "Learning needs" refers to the content and goals that learners want to learn in a particular field or subject.

[1628] "Learning progress data" refers to data that indicates the progress of a learner's learning, such as the learning materials and assignments that the learner has worked on, and the answers they have given.

[1629] "Optimization" is the process of continuously adjusting and improving the content and sequence of the learning materials provided based on learner progress data.

[1630] An "interactive learning experience" is a learning environment designed to allow learners to actively participate in learning and receive feedback in real time.

[1631] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[1632] Overall system configuration

[1633] The system of the present invention mainly consists of a user terminal, a server, and a generative AI model. These components work together to provide learners with individually optimized learning experiences and learning materials.

[1634] The role of each component

[1635] 1. User Device

[1636] This is a device that allows learners to enter their personal information and learning needs during initial registration.

[1637] It is a tool that allows learners to view and study customized learning materials and enter progress data.

[1638] 2. Server

[1639] It is a computer system that receives and securely stores data sent from user terminals.

[1640] Based on the stored data, a generative AI model is called up, which analyzes the learner's characteristics and designs and generates the optimal learning route and curriculum.

[1641] It continuously receives learning progress data and uses generative AI models to optimize the content of the learning materials.

[1642] 3. Generative AI Models

[1643] Machine learning algorithms are used to analyze learner characteristics and design optimal learning routes and curricula.

[1644] Continuous optimization processing is performed based on learner progress data.

[1645] Processing flow and specific operations

[1646] The following describes how the components of the system work together to implement the present invention.

[1647] User Device

[1648] 1. The learner accesses the initial registration screen via the user device and enters personal information such as name, grade, subjects of interest, past grades, and learning objectives.

[1649] 2. After completing the input, press the "Submit" button to send the data to the server.

[1650] 3. During learning, the user's device sends the learner's current progress and answers to the assignments to the server in real time.

[1651] 4. When new customized learning materials are received, they are displayed to the learner, allowing them to continue their learning.

[1652] server

[1653] 1. The initial registration data received from the user device is stored in a database for safekeeping.

[1654] 2. Call up the generative AI model based on the saved data and have it analyze the learner's characteristics.

[1655] 3. Customized teaching materials are dynamically generated based on the analysis results output by the generative AI model.

[1656] 4. The generated teaching materials are sent to the user's device so that the learner can access them.

[1657] 5. Continuously receive learner progress data and store it in a database.

[1658] 6. Based on the received progress data, the generative AI model is called again and the content of the teaching materials is optimized as necessary.

[1659] Generative AI Models

[1660] 1. Using learner information provided by the server, individual learning patterns are analyzed and the optimal learning route is designed.

[1661] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[1662] 3. Based on the learner's progress data, continuous optimization processing is performed and new learning content is suggested.

[1663] Specific examples

[1664] For example, if a third-year junior high school student wants to learn calculus:

[1665] 1. User Device

[1666] The learner starts up the user device and selects "calculus" as the subject they wish to learn.

[1667] Enter the necessary personal information and learning objectives and send them to the server.

[1668] 2. Server

[1669] The server passes the received information to an analysis engine, and the generative AI model analyzes the learner's characteristics.

[1670] Customized teaching materials are generated based on the analysis results provided by the generative AI model.

[1671] The generated teaching materials are sent to the learner's terminal.

[1672] 3. User Device

[1673] The learner studies the provided learning materials and transmits the progress data and answer results from the terminal to the server.

[1674] 4. Server

[1675] The server receives progress data and continuously optimizes the content of the learning materials using a generative AI model.

[1676] In this way, the system can respond to each learner's individual learning needs and provide a highly personalized learning experience.

[1677] Example prompt sentence:

[1678] Student Profile: Name - Student, Grade - 3, Interests - Mathematics, Past Grades - B, Learning Objective - Understand Calculus

[1679] Generate the best study plan for you.

[1680] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1681] Step 1:

[1682] The user starts up the user device and accesses the initial registration screen. They enter personal information such as their name, grade, subjects of interest, past grades, and learning goals. This input data is sent from the user device to the server. The input data includes name, grade, subjects of interest, past grades, and learning goals. The server receives this data and stores it in a database for safekeeping.

[1683] Step 2:

[1684] The server calls the generative AI model using the stored user's personal information and learning needs data. The input data includes personal information and learning needs data. The generative AI model uses a machine learning algorithm to analyze the learner's characteristics and design the optimal learning route and curriculum. The output is the analyzed learning characteristics and the optimal learning route. Based on this, the server begins the process of generating customized learning materials according to the learner's characteristics.

[1685] Step 3:

[1686] The server dynamically generates the customized learning materials. The input data includes the learning route and curriculum data obtained by the generative AI model. The server uses this data to generate learning materials in the form of videos, text, and quizzes, and sends them to the user's device. The output is interactive learning materials. The user's device displays the received learning materials to the learner, who then begins learning using them.

[1687] Step 4:

[1688] As users study via their user devices, they input progress data and answer results in real time. The input data includes learning progress information and answer results. The user devices send this data to the server. The server continuously receives the progress data and stores it in a database.

[1689] Step 5:

[1690] The server analyzes the progress data and calls the generative AI model again. The input data is the progress data. The generative AI model continuously performs optimization processing based on the progress data. The output is new, optimized learning content and suggested learning materials. The server generates new customized learning materials based on this and sends them back to the user's device.

[1691] Step 6:

[1692] The user receives new customized learning materials and continues learning using them. The user's device again collects learning progress data and sends it to the server, providing a continuous learning experience that adapts to the learner's progress.

[1693] 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.

[1694] The overall configuration of the system, the role of each component, and the processing flow will be described below with respect to an embodiment of the present invention.

[1695] Overall system configuration

[1696] The system of the present invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[1697] The role of each component

[1698] 1. User Device:

[1699] This is a device that allows students to enter personal information, learning needs, and emotional data during initial registration.

[1700] It is a tool for students to view and study customized learning materials and enter progress and sentiment data.

[1701] 2. Server:

[1702] Its role is to receive data sent from the user terminal and store it safely.

[1703] Based on the stored data, a generative AI model is called up to analyze students' learning characteristics and generate customized teaching materials.

[1704] Learning progress data and emotional data are continuously received and the content of the learning materials is adjusted to suit the needs of the student.

[1705] 3. Generative AI Model:

[1706] Machine learning algorithms are used to analyze student characteristics and design optimal learning routes and curricula.

[1707] Emotional data is combined and analyzed to optimize the content of teaching materials.

[1708] 4. Emotion Engine:

[1709] This is a system for recognizing user emotions and analyzing emotional data.

[1710] Emotional data is sent to a server to help analyze learning patterns and generate teaching materials.

[1711] Processing flow and specific operations

[1712] The following describes how the components of the system work together to implement the present invention.

[1713] User terminal

[1714] 1. The student accesses the initial registration screen via the user terminal and enters personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state.

[1715] 2. After completing the input, press the "Submit" button to send the data to the server.

[1716] 3. During learning, the user device transmits the student's progress information and emotional data to the server in real time.

[1717] 4. When new customized learning materials are received, they are displayed to students to help them continue their learning.

[1718] server

[1719] 1. The initial registration data and emotion data received from the user device are stored in a database for safekeeping.

[1720] 2. Based on the stored data, a generative AI model is invoked to analyze the student's learning characteristics and emotional state.

[1721] 3. Based on the analysis results output by the generative AI model, the teaching material generation engine is launched to dynamically generate customized teaching materials.

[1722] 4. The generated teaching materials are sent to the user's terminal so that students can access them.

[1723] 5. Continuously receive student progress information and emotional data and store them in a database.

[1724] 6. Based on the received progress and emotion data, the generative AI model is called again and the content of the teaching material is optimized as needed.

[1725] Generative AI Models

[1726] 1. Using student information and emotional data provided by the server, individual learning patterns and emotional states are analyzed and the optimal learning route is designed.

[1727] 2. Provide the server with configuration data for customized teaching materials based on the analysis results.

[1728] 3. Continuously perform optimization processing based on student progress data and emotion data.

[1729] Emotion Engine

[1730] 1. Recognize user emotions and analyze emotional data in real time.

[1731] 2. The analysis results are sent to the server and incorporated into the analysis process of the generative AI model.

[1732] Specific examples

[1733] For example, if Student C, a second-year high school student, wants to learn about the "force laws of physics":

[1734] 1. User Device:

[1735] Student C starts up the user terminal and selects "Laws of Force in Physics" as the topic he wants to learn.

[1736] The necessary personal information and current emotional state are entered and sent to the server.

[1737] 2. Server:

[1738] The server passes the received information to the analysis engine, and the generative AI model analyzes Student C's characteristics and emotional state.

[1739] Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials for "The Laws of Force in Physics."

[1740] The generated teaching materials are sent to Student C's device.

[1741] 3. User Device:

[1742] Student C studies the provided learning materials and transmits his / her progress and emotional data from his / her terminal to the server.

[1743] 4. Server:

[1744] The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[1745] In this way, the system can respond to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[1746] The processing flow will be explained below.

[1747] Step 1:

[1748] The user starts up the user terminal and accesses the initial registration screen. The user inputs personal information such as grade, subjects of interest, past grades, learning goals, and current emotional state (e.g., self-assessment questionnaire or facial expression recognition).

[1749] Step 2:

[1750] The terminal transmits the input personal information and emotion data to the server, and displays a message to the user confirming completion of transmission.

[1751] Step 3:

[1752] The server stores the data received from the user terminal in a database for safe storage. At this time, the data is encrypted.

[1753] Step 4:

[1754] After the server has finished saving the data, it calls the generative AI model and emotion engine and issues instructions to analyze the collected data.

[1755] Step 5:

[1756] The generative AI model designs learning patterns and optimal learning routes based on student information provided by the server (learning characteristics, past grades, interests, etc.).

[1757] Step 6:

[1758] The emotion engine analyzes the emotion data provided by the server and evaluates the student's current emotional state.

[1759] Step 7:

[1760] The server compiles the analysis results of the generative AI model and the emotion engine and activates the teaching material generation engine to generate customized teaching materials.

[1761] Step 8:

[1762] Based on the analysis results, the teaching material generation engine dynamically generates customized teaching materials in the form of videos, text, and quizzes.

[1763] Step 9:

[1764] The server transmits the generated educational material to the user terminal so that the user can access it.

[1765] Step 10:

[1766] The user terminal displays the received customized learning material to the user, and the user begins learning.

[1767] Step 11:

[1768] As the user progresses with their learning, they input their progress, answering questions, and real-time emotional data into the device, which then transmits this data to the server.

[1769] Step 12:

[1770] The server receives the progress data and emotion data sent from the user terminal and stores them in a database.

[1771] Step 13:

[1772] Based on the progress data and emotion data received by the server, the generative AI model and emotion engine are called again to analyze the new data.

[1773] Step 14:

[1774] A generative AI model analyzes progress data and optimizes learning content based on learning patterns.

[1775] Step 15:

[1776] The emotional engine analyzes the latest emotional data and adjusts the content and learning methods to best suit the student's current emotional state.

[1777] Step 16:

[1778] The server then transmits the adjusted new learning materials to the user terminal again, allowing the user to continue optimal learning.

[1779] In this way, the system can adapt to each student's individual learning needs and emotional state, providing a highly personalized learning experience.

[1780] Example 2

[1781] 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."

[1782] Conventional learning systems have difficulty adapting to individual students' learning needs and emotional states, making it impossible to provide a personalized learning experience that maximizes learning effectiveness. Furthermore, they lack the technology to analyze users' progress and emotional data in real time and provide optimal learning materials. This results in a decline in students' motivation and effectiveness in learning.

[1783] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user information via a user device, means for transmitting the user information to the server and safely storing it, means for analyzing user characteristics and extracting learning patterns using a generative AI model, an emotion engine for analyzing emotional data, means for dynamically generating customized learning materials and transmitting them to the user device, means for collecting learning progress data from the user device and transmitting it to the server, and means for the server to continuously analyze the progress data and emotional data and optimize the learning material content using the generative AI model. This makes it possible to provide optimal learning materials in real time, responding to the learning needs and emotional state of individual students.

[1784] "User device" refers to a device on which a user enters personal information when registering for the first time, browses and studies customized learning materials, and enters progress data and emotional data.

[1785] A "server" is a computer system responsible for receiving and securely storing data sent from user devices.

[1786] A "generative AI model" is a system that uses machine learning algorithms to analyze user characteristics and design optimal learning routes and curricula.

[1787] The "emotion engine" is a system that recognizes the user's emotions and analyzes emotional data.

[1788] A "learning pattern" refers to an individually optimized learning process or tendency that is derived based on a user's past grades, learning history, behavior during learning, etc.

[1789] "Customized learning materials" are learning content that is dynamically generated based on the user's characteristics and emotional state.

[1790] "Progress data" refers to data on the progress and results achieved by a user during their studies.

[1791] "Emotion data" is data that represents the user's current emotional state.

[1792] The "database" is a data storage system for safely storing the initial registration data, progress data, and emotion data received by the server.

[1793] "Real-time" refers to a state in which processing and analysis are carried out the moment an event occurs, and the results are reflected immediately.

[1794] The following describes an embodiment of the present invention. The system of the present invention consists of four main components: a user device, a server, a generative AI model, and an emotion engine. These components work together to provide students with personalized learning experiences and educational materials.

[1795] User Device

[1796] The user device is a device through which students enter their personal information, learning needs, and emotional data during initial registration. Through the user device, students can:

[1797] 1. Access the initial registration screen and enter personal information such as your grade level, subjects of interest, past grades, learning goals, and current emotional state.

[1798] 2. After completing the input, press the "Send" button to send the data to the server.

[1799] 3. During learning, progress information and emotional data are input in real time and sent to the server.

[1800] 4. View new, customized learning materials as they become available and continue your learning.

[1801] server

[1802] The server receives and securely stores data sent by the user device. The server performs the following operations:

[1803] 1. Initial registration data and emotion data are stored in a database.

[1804] 2. Invoke the generative AI model to analyze the student's learning characteristics and emotional state.

[1805] 3. Based on the analysis results, the teaching material generation engine is activated to dynamically generate customized teaching materials.

[1806] 4. The generated educational material is transmitted to the user device and made accessible.

[1807] 5. Continuously receive learning progress data and emotion data and store them in a database.

[1808] 6. The generated AI model is called again based on the received data to optimize the content of the teaching materials.

[1809] Generative AI Models

[1810] The generative AI model performs analysis using student information and emotion data provided by the server. The generative AI model operates as follows:

[1811] 1. Analyze each student's learning patterns and emotional state to design the optimal learning route.

[1812] 2. The analysis results are provided to the server and used as configuration data for customized teaching materials.

[1813] 3. Continuously perform optimization processing based on students' progress data and emotion data.

[1814] Emotion Engine

[1815] The emotion engine recognizes user emotions and analyzes emotion data in real time. The specific roles of the emotion engine are as follows:

[1816] 1. Recognize user emotions.

[1817] 2. Send the emotion data to the server.

[1818] 3. Emotional data can be incorporated into generative AI models to aid in the analysis process.

[1819] Specific examples

[1820] For example, suppose a second-year high school student C wants to learn about "the laws of force in physics." The process in this case is as follows:

[1821] 1. User Device: Student C starts up the user device and selects "Laws of Force in Physics" as the subject they want to learn. They enter the necessary personal information and their current emotional state and send it to the server.

[1822] 2. Server: The server passes the received information to the analysis engine, and the generative AI model analyzes the characteristics and emotional state of student C. Based on the analysis results provided by the generative AI model, the teaching material generation engine generates customized teaching materials and sends them to the user device.

[1823] 3. User device: Student C studies the provided learning materials and transmits his / her progress and emotion data from his / her device to the server.

[1824] 4. Server: The server receives progress and emotion data and continuously optimizes the learning content using a generative AI model.

[1825] Prompt Sentence Examples

[1826] By inputting the following prompts into the generative AI model, personalized learning materials can be generated:

[1827] Student C is a second-year high school student who wants to learn about the laws of force in physics. He has an average of 80 points in physics in the past, and he spent a lot of time understanding force vector analysis. He is also currently in a slightly anxious emotional state. Based on this information, please generate customized learning materials that are best suited to Student C.

[1828] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1829] Step 1:

[1830] A user accesses the system for the first time through a user device. On the initial registration screen, the user enters information such as their grade, subjects of interest, past grades, learning goals, and current emotional state (input: personal information, learning needs, emotional state). After completing the input, the user clicks the "Submit" button to send this data to the server (output: transmitted data).

[1831] Step 2:

[1832] The server receives the initial registration data and emotional data sent from the user device (input: sent data). The server securely stores the received data in a database (output: stored data). This data includes grade level, subject interests, grades, learning goals, emotional state, etc.

[1833] Step 3:

[1834] The server calls the generative AI model based on data stored in the database (input: stored data). The generative AI model uses the provided data to analyze the user's characteristics and emotional state. The analysis process uses machine learning algorithms to design the optimal learning route and curriculum. The analysis results are returned to the server (output: analysis results).

[1835] Step 4:

[1836] The server launches a teaching material generation engine based on the analysis results provided by the generative AI model (input: analysis results). The teaching material generation engine dynamically generates teaching materials customized for each user. The generated teaching materials include content tailored to the user's learning needs and emotional state (output: customized teaching materials).

[1837] Step 5:

[1838] The server transmits the generated customized learning materials to the user device (input: customized learning materials). The user device displays the received learning materials on the screen (output: displayed learning materials). The user then proceeds with their studies using the provided customized learning materials.

[1839] Step 6:

[1840] During learning, the user inputs progress information and emotional data in real time and transmits them from the user device to the server (input: progress information, emotional data). The transmitted progress information includes the learning completion rate, the percentage of correct answers to questions, etc.

[1841] Step 7:

[1842] The server receives the progress information and emotional data sent from the user device and stores them in a database (input: progress information, emotional data). Based on the stored data, the server invokes the generative AI model again and optimizes the content of the learning materials (output: optimized learning materials). During the optimization process, the content and difficulty of the learning materials are adjusted taking into account new learning data and emotional information.

[1843] Step 8:

[1844] The server sends the optimized learning materials back to the user device (input: optimized learning materials). The user device displays the updated learning materials on the screen and allows the user to continue learning (output: displayed optimized learning materials).

[1845] (Application example 2)

[1846] 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."

[1847] Conventional virtual stores provide only general product information and do not adequately provide product suggestions based on the user's hobbies and purchasing trends, making it difficult to provide a personalized shopping experience. Furthermore, suggestions do not take into account the user's real-time emotional state, limiting their ability to improve user satisfaction and stimulate purchasing motivation. To solve this problem, a personalized product suggestion system that utilizes the user's individual characteristics and real-time emotional data is needed.

[1848] The identification processing by the identification 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 user information via a user terminal, means for transmitting the user information to the server and securely storing it, means for analyzing user characteristics and extracting interests and purchasing tendencies using a generative AI model, means for dynamically generating customized product proposals and transmitting them to the user terminal, means for collecting real-time emotional data from the user terminal and transmitting it to the server, and means for the server to continuously analyze the emotional data and behavioral data and optimize the product proposals using the generative AI model. This enables personalized product proposals based on the user's individual characteristics and real-time emotional state.

[1849] "User terminal" is a general term for a device through which a user inputs information and communicates with a server.

[1850] "User information" refers to data about a user's personal characteristics, such as hobbies, purchasing habits, and emotional state.

[1851] A "server" is a computer system that receives and stores user information and runs a generative AI model based on that information.

[1852] A "generative AI model" is an artificial intelligence model that includes algorithms to analyze user characteristics and make product suggestions based on individual interests and purchasing trends.

[1853] "Characteristics" refers to personal attributes and behavioral patterns such as a user's interests, hobbies, and purchasing tendencies.

[1854] "Purchase trends" are predictions of future purchasing behavior based on a user's past purchasing history and data on products they have shown interest in.

[1855] "Customized product recommendations" are the provision of specific products or services that are dynamically generated based on the user's characteristics and emotions.

[1856] "Emotional data" refers to data that indicates the user's real-time emotional state and is obtained through facial expression analysis and voice analysis.

[1857] "Behavioral data" refers to data such as the actions a user takes within an application and their browsing history.

[1858] "Product Suggestions" are lists of products and services presented to users based on their characteristics and real-time emotional state.

[1859] "Optimization" is the process of continually adjusting product offerings to maximize user satisfaction.

[1860] The system for implementing this invention consists of four main components: a user terminal, a server, a generative AI model, and an emotion engine. The cooperation of these components makes it possible to provide a personalized shopping experience for each user in a virtual store.

[1861] Hardware and Software Configuration

[1862] 1. User Device:

[1863] Hardware: Smartphones, smart glasses, head-mounted displays (HMDs)

[1864] Software: Virtual store application

[1865] Function: Collects user input information and sends it to the server, receives and displays customized product suggestions, and obtains user behavior and emotion data in real time.

[1866] 2. Server:

[1867] Hardware: High-performance computer server

[1868] Software: Database servers (e.g., MySQL, PostgreSQL), cloud platforms (e.g., AWS, Google Cloud)

[1869] Function: Securely stores user information, controls and manages the generative AI model and emotion engine. Analyzes user characteristics using the generative AI model and dynamically generates optimal product recommendations based on purchasing trends and emotion data.

[1870] 3. Generative AI Model:

[1871] Software: Machine learning algorithms and natural language processing models (e.g., GPT)

[1872] Function: Analyzes user characteristics and generates customized product suggestions based on interests and purchasing trends. Outputs analysis results based on user information and emotional data provided by the server.

[1873] 4. Emotion Engine:

[1874] Software: Emotion analysis software

[1875] Function: Analyzes the user's real-time emotional data and sends it to the server. Identifies the user's emotional state using facial recognition and voice analysis technology.

[1876] Specific examples

[1877] When users shop in the virtual store, they input their personal information, interests, and current emotional state using their device, which is then sent to a server and securely stored.

[1878] The server calls up a generative AI model based on the received user information, analyzes the user's characteristics, and dynamically generates product and service suggestions based on their interests and purchasing trends.The server then sends the generated product suggestions to the user's device, where the user can view the products and services.

[1879] In addition, the user's real-time emotional data is analyzed by the emotion engine and sent to the server, which then calls the generative AI model again based on the overall data, including the emotional data, to optimize the product recommendations.

[1880] For example, if a user's hobby is sports, their interest category is books, and their current emotion is "happy," the prompt to the generative AI model would be:

[1881] "Please suggest the best products and services based on the user's hobby: sports, category of interest: books, and current emotional state: happy."

[1882] In this way, the present invention can provide a personalized shopping experience based on the user's individual characteristics and real-time emotional data.

[1883] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1884] Step 1:

[1885] Users input their personal information, hobbies, interest categories, and current emotional state via their device. This information is sent from the device to the server and securely stored. The input data includes the user's name, age, hobbies, purchase history, real-time emotional data, etc. This allows the server to collect individual user data.

[1886] Step 2:

[1887] The server provides the collected user information to the generative AI model. The generative AI model analyzes the user's hobbies, purchasing tendencies, and emotional state, and generates a prompt to suggest optimal products and services. For example, the prompt might be in the format "Please suggest optimal products and services based on the user's hobbies: sports, category of interest: books, and current emotional state: happy." By inputting this prompt into the generative AI model, customized product suggestions are output.

[1888] Step 3:

[1889] The generative AI model generates product suggestions based on the user's characteristics and sends the results back to the server. The generated product suggestions become a list of multiple products and services based on the user's preferences. The server receives this data and sends it to the user's device.

[1890] Step 4:

[1891] The user terminal receives the customized product proposals sent from the server and displays them to the user. The user browses the product proposals and selects the products they are interested in. The data of the selected products is then sent back to the server.

[1892] Step 5:

[1893] Behavioral data associated with user operations and selections, as well as emotional data acquired in real time, are sent from the user's device to the server. For example, emotional data from the user can be acquired using facial expression analysis or voice analysis. The server receives this data and provides it back to the generative AI model.

[1894] Step 6:

[1895] The server then calls the generative AI model again based on all data, including real-time emotional data and behavioral data, analyzed by the emotion engine, to optimize the content of the product suggestions. The generative AI model then generates a prompt sentence again and outputs the optimized product suggestions.

[1896] Step 7:

[1897] The optimized product suggestions are sent from the server to the user's device and provided to the user again, and the user then shops again based on these new suggestions, personalizing the entire purchasing process.

[1898] In this way, the collaboration between the user device, server, generative AI model, and emotion engine makes it possible to provide users with personalized product suggestions that are optimized in real time.

[1899] 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.

[1900] 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.

[1901] 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.

[1902] 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.

[1903] 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.

[1904] 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.

[1905] 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).

[1906] 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.

[1907] 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."

[1908] 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.

[1909] 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).

[1910] 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.

[1911] 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.

[1912] 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.

[1913] 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.

[1914] 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.

[1915] 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.

[1916] 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.

[1917] 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.

[1918] 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.

[1919] 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.

[1920] The following is further disclosed regarding the above embodiment.

[1921] (Claim 1)

[1922] a means for collecting student information via user terminals;

[1923] a means for transmitting and securely storing student information on a server;

[1924] A means of analyzing student characteristics and extracting learning patterns using generative AI models;

[1925] means for dynamically generating and transmitting customized educational materials to a user terminal;

[1926] means for collecting learning progress data from the user terminal and transmitting it to a server;

[1927] A server continuously analyzes the progress data and optimizes the content of the learning materials using a generative AI model;

[1928] A system including:

[1929] (Claim 2)

[1930] 2. The system according to claim 1, wherein the educational material generating means generates educational materials in the form of video, text, or quiz.

[1931] (Claim 3)

[1932] 10. The system of claim 1, wherein progress data is collected and analyzed in real time.

[1933] "Example 1"

[1934] (Claim 1)

[1935] a means for collecting learner information via a user device;

[1936] means for transmitting and securely storing learner information to a data management device;

[1937] A means for analyzing learner characteristics and extracting learning patterns using a generative AI model;

[1938] means for dynamically generating and transmitting customized educational materials to the user device;

[1939] means for collecting learning progress data from the user device and transmitting the data to a data management device;

[1940] A means for the data management device to continuously analyze the progress data and use a generative AI model to optimize the content of the educational materials;

[1941] A system including:

[1942] (Claim 2)

[1943] 2. The system according to claim 1, wherein the educational material generating means generates educational materials in a multimedia format, a text format, or a question format.

[1944] (Claim 3)

[1945] 10. The system of claim 1, wherein progress data is collected and analyzed in real time.

[1946] "Application Example 1"

[1947] (Claim 1)

[1948] means of collecting personal information and learning needs via user devices;

[1949] A means of transmitting and securely storing personal information and learning needs on a server;

[1950] A means of analyzing learner characteristics using a generative AI model and extracting the optimal learning route and curriculum;

[1951] means for dynamically generating and transmitting customized educational materials to a user terminal;

[1952] means for collecting learning progress data from the user terminal and transmitting it to a server;

[1953] A server continuously analyzes the progress data and optimizes the content of the learning materials using a generative AI model;

[1954] A system including:

[1955] (Claim 2)

[1956] 2. The system according to claim 1, wherein the educational material generating means generates educational materials in the form of videos, texts, and quizzes to provide an interactive learning experience.

[1957] (Claim 3)

[1958] 2. The system of claim 1, wherein progress data is collected in real time, analyzed, and new learning materials are continually provided according to the learner's progress.

[1959] "Example 2: Combining Emotion Engines"

[1960] (Claim 1)

[1961] means for collecting user information via a user device;

[1962] A means for transmitting and securely storing user information on a server;

[1963] A means of analyzing user characteristics and extracting learning patterns using a generative AI model;

[1964] An emotion engine that analyzes emotion data;

[1965] means for dynamically generating and transmitting customized educational material to the user device;

[1966] means for collecting learning progress data from the user device and transmitting the data to a server;

[1967] A means for the server to continuously analyze the progress data and emotion data and optimize the content of the learning materials using a generative AI model;

[1968] A system including:

[1969] (Claim 2)

[1970] 2. The system according to claim 1, wherein the educational material generating means generates educational materials in the form of video, text, or quiz.

[1971] (Claim 3)

[1972] 10. The system of claim 1, wherein progress data and emotion data are collected and analyzed in real time.

[1973] "Application example 2 when combining emotion engines"

[1974] (Claim 1)

[1975] a means for collecting user information via a user terminal;

[1976] A means for transmitting and securely storing user information on a server;

[1977] A means of analyzing user characteristics using a generative AI model and extracting interests and purchasing trends;

[1978] means for dynamically generating and transmitting customized product suggestions to a user device;

[1979] A means for collecting real-time emotion data from a user terminal and transmitting it to a server;

[1980] A means for the server to continuously analyze emotional and behavioral data and optimize product recommendations using a generative AI model;

[1981] A system including:

[1982] (Claim 2)

[1983] 10. The system of claim 1, wherein the product suggestion generating means generates suggestions in text, image, or video format.

[1984] (Claim 3)

[1985] 10. The system of claim 1, wherein emotional data and behavioral data are collected and analyzed in real time. [Explanation of symbols]

[1986] 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 for collecting student information via user terminals; a means for transmitting and securely storing student information on a server; A means of analyzing student characteristics and extracting learning patterns using generative AI models; means for dynamically generating and transmitting customized educational materials to a user terminal; means for collecting learning progress data from the user terminal and transmitting it to a server; A server continuously analyzes the progress data and optimizes the content of the learning materials using a generative AI model; A system including:

2. 2. The system according to claim 1, wherein the educational material generating means generates educational materials in the form of video, text, or quiz.

3. 10. The system of claim 1, wherein progress data is collected and analyzed in real time.

Images