System

Abstract

A system is provided.SOLUTION: A system comprising: means for storing registration information received from a user in a database; means for receiving an educational material request from a user; means for generating an educational material based on the user's request using artificial intelligence; means for storing the generated educational material in the database and notifying the user; means for delivering the educational material when the user makes a download request; and means for collecting user feedback and storing it in the database.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] In today's educational settings, it is difficult to provide learning materials tailored to the needs of each learner, and uniform teaching materials are not enough to improve learning outcomes. Furthermore, the time and cost required to create teaching materials makes it difficult to customize them for specific topics or grade levels. Furthermore, there are insufficient means to utilize user feedback to improve the quality of teaching materials, making it difficult to expect improvements in learning outcomes. [Means for solving the problem]

[0005] The present invention provides a means for storing registration information received from users in a database, thereby managing individual learner information. It also provides a means for receiving learning material requests from users and a means for generating learning materials based on the requests using artificial intelligence. The generated learning materials are stored in a database, and a means for notifying the user is provided, thereby enabling rapid delivery of the learning materials. It also provides a means for delivering learning materials when a user makes a download request, allowing for easy access. Furthermore, the system provides a means for collecting user feedback and storing it in a database, allowing for continuous improvement of the quality of the learning materials. The present invention provides learning materials optimized for each grade and topic, significantly improving user learning efficiency. Furthermore, improving the quality of the learning materials using the collected feedback can enhance learning effectiveness.

[0006] "User" refers to an individual or corporation that uses the system, specifically students and instructors at a cram school.

[0007] "Registration information" refers to personal information and authentication information provided by users to use the system, including names, email addresses, passwords, etc.

[0008] A "database" is an electronic system for efficiently managing and storing data such as user information, educational materials, and feedback.

[0009] A "learning material request" is a user's instruction to the system to generate learning materials based on the content and topics required for learning.

[0010] "Artificial intelligence" refers to algorithms and their implementations that are programmed to analyze a wide variety of data and solve specific problems.

[0011] "Notifications" are messages sent by the system to inform the user of the completion of generated learning materials or other important information.

[0012] A "download request" is a request made by a user to obtain specific educational material data from the system.

[0013] "Feedback" refers to the user providing the system with their opinion, such as an evaluation or suggestions for improvement, regarding the learning material they have used.

[0014] "Grade-specific" refers to the optimization of teaching materials for different grades, meaning that teaching materials are created with content and difficulty appropriate for each grade.

[0015] "Topic-specific" refers to optimizing learning materials based on specific learning content or subject matter, and generating learning materials appropriate for each topic.

[0016] "Quality improvement" is the process of using collected feedback and data to improve the content and structure of educational materials and enhance user learning outcomes. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of the learning materials based on the feedback. Specific program processing and operation of this system are described below.

[0039] User Registration

[0040] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[0041] 2. The terminal sends the entered information to the server.

[0042] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[0043] Request teaching materials

[0044] 1. The user logs in and fills out a request form for the desired teaching materials based on the grade level and topic to be used.

[0045] 2. The terminal sends the user's request to the server.

[0046] 3. The server issues instructions to the artificial intelligence based on the received request and generates teaching materials based on the specified content.

[0047] Teaching material generation

[0048] 1. The server uses artificial intelligence to automatically generate teaching materials optimal for a specified grade and topic. For example, it creates teaching materials on linear equations for second-year junior high school students.

[0049] 2. The server saves the generated teaching materials in a database and notifies the user that the teaching materials are complete.

[0050] Teaching material distribution

[0051] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[0052] 2. The device sends a download request to the server.

[0053] 3. The server sends the educational material data to the terminal so that the user can download it.

[0054] Feedback collection

[0055] 1. After using the teaching materials, users enter feedback such as their experience and areas for improvement.

[0056] 2. The terminal sends the feedback information to the server.

[0057] 3. The server stores the feedback in a database and reflects it in the next generation of teaching materials.

[0058] Specific examples

[0059] Case 1: A request for math materials for eighth grade students

[0060] 1. User: Junior high school student A registers and logs in to the system.

[0061] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[0062] 3. Terminal: Sends the request to the server.

[0063] 4. Server: Based on the request, the AI ​​generates teaching materials on "linear equations."

[0064] 5. Server: Saves the generated teaching materials in a database and notifies Person A that the teaching materials are complete.

[0065] 6. User: Receive notifications and download materials.

[0066] 7. Device: Sends download request to server.

[0067] 8. Server: Sends the teaching material data to the terminal and Person A downloads it.

[0068] 9. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples."

[0069] 10. Device: Send feedback to the server.

[0070] 11. Server: The feedback is saved in the database and reflected in the next generation of teaching materials.

[0071] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality. This configuration maximizes learning effectiveness and provides efficient learning support.

[0072] The processing flow will be explained below.

[0073] User Registration

[0074] Step 1:

[0075] A user accesses the system, opens the registration form, and enters the required information, such as name, email address, and password.

[0076] Step 2:

[0077] The device sends the entered information to the server, where the data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[0078] Step 3:

[0079] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[0080] Step 4:

[0081] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[0082] Request teaching materials

[0083] Step 1:

[0084] The user logs in to the system and opens the materials request form, entering the grade level, topic, and desired materials.

[0085] Step 2:

[0086] The device sends the input request content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[0087] Step 3:

[0088] The server analyzes the received request and prepares to pass the request to the generative AI.

[0089] Teaching material generation

[0090] Step 1:

[0091] The server passes the request to the generative AI and instructs it to generate teaching materials appropriate for the specified grade and topic.

[0092] Step 2:

[0093] The generative AI on the server creates optimal teaching materials (e.g., explanations and practice problems for linear equations) based on past data and learning algorithms.

[0094] Step 3:

[0095] The server stores the generated teaching materials in a database, along with the metadata of the teaching materials (such as the creation date and related tags).

[0096] Step 4:

[0097] The server sends an email to the user notifying them that the educational material is ready.

[0098] Teaching material distribution

[0099] Step 1:

[0100] The user receives a notification email and clicks on the link to request the download of the materials.

[0101] Step 2:

[0102] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[0103] Step 3:

[0104] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[0105] Step 4:

[0106] The server sends the generated download link to the user's terminal.

[0107] Step 5:

[0108] The user clicks the download link to download the learning material data.

[0109] Feedback collection

[0110] Step 1:

[0111] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[0112] Step 2:

[0113] The terminal transmits the input feedback to the server.

[0114] Step 3:

[0115] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, etc.).

[0116] Step 4:

[0117] The server periodically analyzes the collected feedback and uses it to generate the next learning material, thereby continuously improving the quality of the learning material.

[0118] As described above, this system efficiently generates and distributes teaching materials that meet the individual needs of users, and by incorporating user feedback, it is possible to improve the quality of the teaching materials.

[0119] Example 1

[0120] 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."

[0121] Conventional online education systems have difficulty responding to individual learning needs because they are unable to generate learning materials quickly and accurately in response to user requests. It is also difficult to improve the quality of learning materials by incorporating user feedback, preventing maximum learning effectiveness.

[0122] 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.

[0123] In this invention, the server includes means for storing registration information received from users in a database, means for receiving learning material requests from users, means for generating learning materials based on the user requests using a generative AI model, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, and means for reflecting the collected feedback in the generation of the next learning material. This makes it possible to provide appropriate learning materials that meet the individual learning needs of users and to improve the quality of the learning materials by reflecting the feedback.

[0124] "User" refers to a person who uses the system to perform operations such as registration, requests, downloads, and feedback.

[0125] "Server" refers to the central processing unit that processes data received from users, stores it in a database, generates teaching materials through AI models, and notifies and distributes them to users.

[0126] "Database" refers to a system that systematically stores and manages data such as user registration information, request details, generated learning materials, and collected feedback.

[0127] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates optimal teaching materials based on user requests.

[0128] "Teaching materials" refers to learning materials and educational content created to meet the learning needs of users.

[0129] "Feedback" refers to the evaluation and suggestions for improvement provided by the user regarding the educational materials used.

[0130] A "request" refers to a request made by a user to the system regarding the content and format of the educational material desired by the user.

[0131] "Notification" refers to the act of a system conveying information to a user by means of email, screen display, or other means.

[0132] "Download Request" refers to a request made by a User to save generated educational materials to their own device.

[0133] "Storage" refers to the act of keeping data or information in a database or storage so that it can be accessed later.

[0134] The system of the present invention allows users to request individually optimized learning materials online and improve the quality of the learning materials based on the user's feedback. The system's main components are the user, a terminal, and a server.

[0135] User Registration

[0136] First, a user accesses the system and enters the required information such as name, email address, and password into the new registration form. The terminal then converts this input information into JSON format and sends it to the server as an HTTP POST request. The server parses the received data and saves it in a database (e.g., MySQL or PostgreSQL). After saving is complete, the server uses an email sending library (e.g., SMTP or SendGrid) to send a registration completion notification to the user.

[0137] Request teaching materials

[0138] After logging in to the system, the user enters the necessary information into a request form for teaching materials based on the desired grade and topic. The device then converts this information back into JSON format and sends it to the server as an HTTP POST request. The server parses the received request data, creates a prompt for the generative AI model (e.g., GPT-4), and sends the request. An example of a prompt is, "Please generate teaching materials related to linear equations in mathematics for second-year junior high school students."

[0139] Teaching material generation

[0140] The generative AI model generates optimal learning materials based on prompts received from the server. For example, it generates learning materials that include example problems and explanations for linear equations in mathematics for second-year junior high school students. The generated learning materials are saved in a database by the server, and once saved, the server sends a notification to the user that the learning materials are complete.

[0141] Teaching material distribution

[0142] When a user receives a notification that the teaching materials are complete, they click the link in the notification to access the materials download page. When the user clicks the "Download" button, the device sends a download request to the server. The server retrieves the teaching materials data from the database and sends it to the user's device as an HTTP response. This allows the user to download the teaching materials to their device.

[0143] Feedback collection

[0144] After using the learning materials, the user enters their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request. The server stores the received feedback data in a database and reflects it the next time learning materials are generated.

[0145] Specific examples

[0146] A junior high school student, Mr. A, registers and requests "teaching materials related to linear equations" for "second-year junior high school mathematics." The device sends the request to the server, which then sends a prompt to the generative AI model saying, "Please generate teaching materials related to linear equations." The generated teaching materials are saved in the database, and the user is notified that the teaching materials are complete. Mr. A receives the notification, downloads and uses the teaching materials, and then sends feedback saying, "It's easy to understand, but I'd like more example problems." The device sends the feedback to the server, which saves it in the database and reflects it in the next teaching material generation.

[0147] This system enables the rapid provision of individually optimized learning materials tailored to the user's learning needs, and also makes it possible to continuously improve the quality of the learning materials by utilizing user feedback.

[0148] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0149] Step 1: User Registration

[0150] A user accesses the system's new registration page and enters the required information, including name, email address, and password, into the form. The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0151] Input: User's name, email address, and password

[0152] Output: HTTP POST request to the server

[0153] Specific operation: The device converts the input content of the HTML form into JSON using JavaScript and sends a POST request to the server's API endpoint.

[0154] Step 2: Processing and database storage of registration information

[0155] The server parses the received JSON data, verifies its validity, and then stores the user information in a database (e.g., MySQL or PostgreSQL).

[0156] Input: JSON data sent from the terminal

[0157] Output: Save user information to database

[0158] What happens: The server validates the data and then saves it to the database using an SQL query.

[0159] Step 3: Sending a registration completion notice

[0160] The server sends a registration completion email to the user. Using an email sending library (e.g., SMTP or SendGrid), a registration completion notification is sent to the user's email address.

[0161] Input: The fact that registration information was saved, the user's email address

[0162] Output: Registration completion notification email sent to user

[0163] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[0164] Step 4: Complete and submit your materials request

[0165] A user logs in and enters the necessary information into a request form for the desired teaching materials based on grade level and topic. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0166] Input: Grade level, topic, and details of the desired teaching materials

[0167] Output: HTTP POST request to the server

[0168] Specific operation: The device converts the input content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[0169] Step 5: Process the request data and teach the AI ​​model

[0170] The server parses the received request data, checks the contents, and creates a prompt to the generative AI model (e.g., GPT-4) and sends the request.

[0171] Input: Request data sent from the terminal

[0172] Output: The prompt to send to the generative AI model

[0173] Specific operation: The server parses the request data, generates a prompt sentence, and sends it to the AI ​​model.

[0174] Step 6: Creating and saving teaching materials

[0175] The generative AI model generates teaching materials based on the prompts received from the server, which then receives the teaching material data and stores it in a database.

[0176] Input: The prompt sent to the generative AI model

[0177] Output: Teaching material data stored in the database

[0178] Specific operation: The AI ​​model generates teaching material data, the server receives it, and stores it in a database using an SQL query.

[0179] Step 7: Sending notification of completion of materials

[0180] The server notifies the user that the learning material is complete. An email containing a link to the completed learning material is sent to the user using the email sending library.

[0181] Input: Generated teaching material data, user email address

[0182] Output: Email to user notifying them of completion of the teaching material

[0183] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[0184] Step 8: Request download of materials

[0185] The user clicks the link in the completion notification email to access the download page. When the user clicks the "Download" button, the device sends a download request to the server.

[0186] Input: User download request

[0187] Output: HTTP GET request to the server

[0188] Specific operation: The device detects user operation and sends a GET request to the server's API endpoint.

[0189] Step 9: Submit the teaching materials data

[0190] The server retrieves the teaching material data from the database and sends it to the user's terminal as an HTTP response.

[0191] Input: Download request received from user

[0192] Output: Sending educational material data to the user's device

[0193] Specific operation: The server retrieves the teaching material data using an SQL query and sends it to the terminal as an HTTP response.

[0194] Step 10: Submitting feedback input

[0195] After using the learning materials, users enter their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request.

[0196] Input: User feedback

[0197] Output: HTTP POST request to the server

[0198] Specific operation: The terminal converts the feedback content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[0199] Step 11: Save and incorporate feedback

[0200] The server parses the received feedback data, stores it in a database, and instructs the AI ​​model to reflect that feedback the next time it generates teaching materials.

[0201] Input: Feedback data submitted by the user

[0202] Output: Save feedback to the database and instruct the AI ​​model to reflect the feedback

[0203] Specific operation: The server analyzes the feedback data, stores it in a database using an SQL query, and processes it so that it is reflected in the next prompt sentence for the AI ​​model.

[0204] These are the processing steps of the system. By generating individual learning materials based on user requests and incorporating feedback, learning materials optimized for learning needs are provided.

[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 online learning systems take time for users to receive individually optimized learning materials, which does not sufficiently improve learning efficiency. Furthermore, they lack real-time learning support using smart devices and do not sufficiently consider user convenience. Therefore, there is a need for a method to optimize users' learning experience in real time and quickly respond to individual needs.

[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 storing registration information received from a user in a database, means for receiving a learning material request from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, means for providing optimized learning materials in real time using a smart device, and means for analyzing the user's voice commands or gesture inputs, thereby making it possible to provide individually optimized learning materials to the user in real time and improve learning efficiency.

[0210] The "means for storing registration information received from a user in a database" refers to a method or device for recording personal information and other registration information provided by a user in a database on the server side.

[0211] The "means for receiving a learning material request from a user" refers to an interface or method by which a user specifies the content and requirements of the learning material desired by the user to the system.

[0212] "Means for generating teaching materials based on user requests using artificial intelligence" refers to a method or device for creating teaching materials that are optimal for specified conditions using an artificial intelligence algorithm in response to a user's request for teaching materials.

[0213] The "means for storing the generated teaching materials in a database and notifying the user" refers to a means for recording the generated teaching materials in a database and notifying the user about it.

[0214] The "means for delivering educational materials when a user makes a download request" refers to a method or device for transmitting educational materials to a user's terminal when the user requests the download of the educational materials.

[0215] The "means for collecting user feedback and storing it in a database" refers to a method or device for collecting opinions and evaluations provided by users after use and recording them in a database.

[0216] "Means for providing optimized educational materials in real time using a smart device" refers to a method or apparatus for providing users with educational materials that are optimized on the spot through a smart device such as a smartphone or smart glasses.

[0217] "Means for analyzing user voice commands or gesture inputs" refers to a method or device for interpreting the content of user voice or gesture instructions and executing an action in response to them.

[0218] The system of the present invention allows users to quickly obtain individually optimized learning materials online and study them in real time through their smart devices. The components of this system and their detailed program processing are described below.

[0219] System configuration

[0220] 1. User Registration

[0221] Device: Smart device (e.g. smartphone, smart glasses)

[0222] Server: A central server for storing registration information (such as name, email address, and password) in a database.

[0223] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[0224] 2. Request for teaching materials

[0225] Terminal: An interface where users can make requests via voice commands or touch gestures.

[0226] Server: Receives the request and saves it in the database

[0227] Software: Natural Language Processing (NLP) engine (e.g., Google Cloud Natural Language API)

[0228] 3. Teaching material generation

[0229] Server: Generates educational materials using artificial intelligence based on user requests

[0230] Software: Generative AI models (e.g., OpenAI GPT-4)

[0231] 4. Teaching material distribution

[0232] Device: Receive notifications of educational material distribution and send download requests

[0233] Server: Deliver learning materials when a user makes a download request

[0234] Software: Cloud storage (e.g. Google Cloud Storage)

[0235] 5. Feedback Collection

[0236] On your device: Enter feedback using voice commands or touch gestures

[0237] Server: Receives feedback and stores it in a database

[0238] Software: Speech recognition engine, NLP engine

[0239] Program processing

[0240] User Registration

[0241] The user provides registration information by voice input using a smart device. This information is converted into text by a voice recognition engine and sent to the server. The server stores this registration information in a database and sends a notification to the user that registration is complete.

[0242] Request teaching materials

[0243] Users request learning materials using voice commands or touch gestures. The voice data is analyzed by an NLP engine, and the request is sent in text format to the server. The server then passes the request to an AI model to generate learning materials.

[0244] Teaching material generation

[0245] The server uses a generative AI model to generate optimal learning materials based on the user's request. For example, if a user requests "learning materials on linear equations for second-year junior high school mathematics," the AI ​​model will create the learning materials. The generated learning materials are stored in a database.

[0246] Teaching material distribution

[0247] Once the learning materials are generated, the user is notified. The user then sends a download request from their smart device, and the server sends the learning materials data to the device.

[0248] Feedback collection

[0249] After using the learning materials, users can input feedback using voice commands or touch gestures. The feedback is analyzed by a speech recognition engine and an NLP engine and sent to the server in text format. The server stores this in a database and reflects it in the next generation of learning materials.

[0250] Specific examples

[0251] Prompt Sentence Examples

[0252] Material Request:

[0253] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[0254] feedback:

[0255] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[0256] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality, thereby maximizing learning effectiveness and providing efficient learning support.

[0257] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0258] Step 1:

[0259] The user provides registration information using a smart device.

[0260] Specifically, the user uses voice input to input information such as name, email address, and password into the terminal.

[0261] The input data is audio data.

[0262] The device converts the voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API).

[0263] Step 2:

[0264] The terminal transmits the converted text data to the server.

[0265] The data to be transmitted is text data.

[0266] The server receives this text data and stores it in a database.

[0267] The server will send an email to the user notifying them of the completion of registration.

[0268] The output data is an email notifying the completion of registration.

[0269] Step 3:

[0270] Users can request educational materials using their smart devices.

[0271] Specifically, the user inputs a request for teaching materials according to grade level or topic using voice commands or touch gestures.

[0272] The input data is voice data or gesture data.

[0273] The device converts the voice data into text data using a speech recognition engine and analyzes the request using an NLP engine (e.g., Google Cloud Natural Language API).

[0274] The parsed text data is sent to the server.

[0275] Step 4:

[0276] The server receives the requested text data and generates optimal teaching materials using a generative AI model (e.g., OpenAI GPT-4).

[0277] The input data is the text data of the request.

[0278] The generated teaching materials are output in multiple data formats, including text, images, graphs, etc.

[0279] The server stores the generated teaching material data in a database and notifies the user that the teaching material has been completed.

[0280] Step 5:

[0281] The user receives a notification that the teaching material is complete and sends a download request using a smart device.

[0282] The input data is a download request sent from the terminal.

[0283] The terminal sends a request to the server, which provides a download link to the user.

[0284] The output data is a download link.

[0285] Step 6:

[0286] Users click on the download link from their smart device to obtain the learning materials.

[0287] The data to be input is the click operation of the user.

[0288] The server transmits the educational material data to the terminal, and the user is then able to use the educational material.

[0289] The output data is teaching material data.

[0290] Step 7:

[0291] Users provide feedback on the learning material using their smart devices.

[0292] Specifically, the user inputs feedback using voice commands or touch gestures.

[0293] The input data is voice data or gesture data.

[0294] The device converts the voice data into text data using a voice recognition engine, analyzes it using an NLP engine, and then sends it to the server.

[0295] The server stores the received feedback in a database and reflects it in the next generation of teaching materials.

[0296] Specific examples

[0297] Prompt Sentence Examples

[0298] Material Request:

[0299] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[0300] feedback:

[0301] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[0302] Through the above processing steps, users can obtain optimized learning materials in real time, and a system that can quickly respond to individual needs is realized.

[0303] 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.

[0304] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[0305] User Registration

[0306] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[0307] 2. The terminal sends the entered information to the server.

[0308] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[0309] Request teaching materials

[0310] 1. The user logs in and fills out a request form for the desired teaching materials based on grade level and topic.

[0311] 2. The terminal sends the user's request to the server.

[0312] 3. The server uses the emotion engine based on the received request to determine the user's emotion.

[0313] Emotion recognition by emotion engine

[0314] 1. The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[0315] 2. The server issues instructions to the AI ​​based on the user's emotional state and generates teaching materials optimized for the user's emotions.

[0316] Teaching material generation

[0317] 1. The server issues instructions to the generative AI to generate learning materials appropriate for the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data.

[0318] 2. The server stores the generated teaching materials in a database and notifies the user.

[0319] Teaching material distribution

[0320] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[0321] 2. The terminal sends a download request to the server. This request includes the user ID and the learning material ID.

[0322] 3. The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[0323] 4. The server sends the generated download link to the user's device.

[0324] 5. The user clicks the download link to download the teaching material data.

[0325] Feedback collection

[0326] 1. After using the learning materials, the user opens the feedback form and enters feedback such as an evaluation and areas for improvement.

[0327] 2. The terminal sends the feedback information to the server.

[0328] 3. The server stores the received feedback in a database, which may include emotional data during training.

[0329] 4. The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[0330] Specific examples

[0331] Case 1: A request for math materials for eighth grade students

[0332] 1. User: A junior high school student registers and logs into the system.

[0333] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[0334] 3. Terminal: Sends the request to the server.

[0335] 4. Server: Based on the request content, the emotion engine evaluates the user's emotional state.

[0336] 5. Server: Based on the emotional data, the AI ​​is instructed to generate educational materials on "linear equations." For example, if the user is tired, the AI ​​will increase the number of examples to make it easier to understand.

[0337] 6. Server: Stores the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[0338] 7. User: Receive notifications and download materials.

[0339] 8. Device: Sends download request to server.

[0340] 9. Server: Sends the teaching material data to the terminal and the user downloads it.

[0341] 10. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the study.

[0342] 11. Device: Send feedback to the server.

[0343] 12. Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[0344] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[0345] The processing flow will be explained below.

[0346] User Registration

[0347] Step 1:

[0348] A user accesses the system and enters the required information such as name, email address, and password into the new registration form.

[0349] Step 2:

[0350] The terminal sends the entered user information to the server. The data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[0351] Step 3:

[0352] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[0353] Step 4:

[0354] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[0355] Request teaching materials

[0356] Step 1:

[0357] Users log in to the system and fill out a request form for the teaching materials they want based on grade level and topic.

[0358] Step 2:

[0359] The terminal sends the user's desired content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[0360] Step 3:

[0361] The server analyzes the received request and prepares to pass the request to the generative AI.

[0362] Emotion recognition by emotion engine

[0363] Step 1:

[0364] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[0365] Step 2:

[0366] The server issues instructions to the AI ​​based on the user's emotional state and configures it to generate teaching materials optimized for the user's emotions.

[0367] Teaching material generation

[0368] Step 1:

[0369] The server issues instructions to the generative AI to generate teaching materials according to the specified grade and topic. For example, if it determines that the user is tired, it will adjust the difficulty level to a lower level.

[0370] Step 2:

[0371] The server stores the generated learning materials in a database, along with the learning materials' metadata (such as the creation date, associated tags, and emotional state).

[0372] Step 3:

[0373] The server sends an email to the user notifying them that the educational material is ready.

[0374] Teaching material distribution

[0375] Step 1:

[0376] The user receives a notification that the materials are complete and clicks on the link to request a download.

[0377] Step 2:

[0378] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[0379] Step 3:

[0380] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[0381] Step 4:

[0382] The server sends the generated download link to the user's terminal.

[0383] Step 5:

[0384] The user clicks the download link to download the learning material data.

[0385] Feedback collection

[0386] Step 1:

[0387] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[0388] Step 2:

[0389] The terminal transmits the input feedback to the server.

[0390] Step 3:

[0391] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, emotional state, etc.).

[0392] Step 4:

[0393] The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[0394] Specific examples

[0395] Case 1: A request for math materials for eighth grade students

[0396] Step 1:

[0397] User: A junior high school student registers and logs into the system.

[0398] Step 2:

[0399] User: Requests "teaching materials on linear equations" for "8th grade mathematics."

[0400] Step 3:

[0401] Terminal: Sends the request to the server.

[0402] Step 4:

[0403] Server: Based on the request content, the emotion engine evaluates the user's emotional state. For example, it detects if the user is showing signs of impatience or fatigue when making a request.

[0404] Step 5:

[0405] Server: Based on the emotional data, the AI ​​is instructed to generate teaching materials on "linear equations." If the user is tired, the AI ​​will provide more examples and more detailed explanations.

[0406] Step 6:

[0407] Server: Saves the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[0408] Step 7:

[0409] Users: Receive notifications and download learning materials.

[0410] Step 8:

[0411] Device: Sends a download request to the server.

[0412] Step 9:

[0413] Server: Sends educational material data to the terminal and users download it.

[0414] Step 10:

[0415] User: After using the learning materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the learning process.

[0416] Step 11:

[0417] Device: Send feedback to the server.

[0418] Step 12:

[0419] Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[0420] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[0421] Example 2

[0422] 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."

[0423] Conventional online learning systems do not provide learning materials that take into account the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to improve the quality of learning materials based on feedback, making it difficult to continuously improve the learning experience.

[0424] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0425] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for analyzing the user's emotions using an emotion engine, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, and means for collecting user feedback, storing it in a database, and analyzing it. This makes it possible to provide learning materials optimized according to the user's emotional state and to continuously improve the quality of the learning materials by utilizing the collected feedback and emotion data.

[0426] "Registration Information" refers to personal information that a User provides when accessing the System, including name, email address, password, etc.

[0427] A "material request" is a request made by a user to the system for material related to a particular grade or topic.

[0428] An "emotion engine" is a technology that analyzes a user's input data, usage status, facial expression recognition data, etc. to evaluate their emotional state.

[0429] "Artificial intelligence" is a type of computational technology that generates optimized learning materials based on the user's requests and emotional state.

[0430] The "database" is an information management system that centrally stores and manages data such as registration information, teaching materials, and feedback within the system.

[0431] "Feedback" refers to information about evaluations and improvements provided by users after using educational materials.

[0432] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[0433] User Registration

[0434] First, the user accesses the system's web page and enters the required information, such as name, email address, and password, into the new registration form. The information entered by the user is sent from the terminal to the server using the HTTPS protocol. The server stores the received registration information in a database such as MySQL and sends a registration completion notification to the user's email address. This process is carried out using PHP or Python scripts.

[0435] Request teaching materials

[0436] Next, the user logs into the system and fills out a request form for the desired teaching materials based on grade level and topic. The request is sent from the terminal to the server, and the server uses an emotion engine to evaluate the user's emotional state based on the received request. The emotion engine uses input speed, error rate, facial expression recognition data, etc.

[0437] Emotion recognition by emotion engine

[0438] The server collects emotional data from user input, usage, camera input, etc. This data is input into an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), which then makes an API call to evaluate the emotional data. As a result, the server conveys the user's emotional state to the AI.

[0439] Teaching material generation

[0440] Based on the received emotional data, the server issues instructions to a generative AI (e.g., GPT-4) to generate learning materials appropriate for the specified grade and topic. During this process, the difficulty and content of the learning materials are adjusted based on the user's emotional state. The generated learning materials are stored in a database and notified to the user. As a specific example, if the user is "tired," the AI ​​is instructed to increase the number of example questions to make the material easier to understand.

[0441] Example prompt sentence:

[0442] If the grade level is "8th grade," the topic is "linear equations," and the emotional state is "tired," then: "Create teaching materials for 8th grade linear equations with more examples that are easy to understand for users who are tired."

[0443] Teaching material distribution

[0444] When the user receives notification that the teaching materials are complete, they click a link to request a download of the materials. The device sends a download request including the user ID and teaching material ID to the server. The server retrieves the teaching material data from the database, generates a temporary download link, and sends it to the user's device. The user clicks the link to download the teaching material data.

[0445] Feedback collection

[0446] After using the learning materials, users enter their evaluation and suggestions for improvement in a feedback form. This feedback information is sent from the device to the server, which stores the information in a database. The feedback may also include emotional data from the learning process. The server analyzes the collected feedback and emotional data and reflects this in the next generation of learning materials, thereby continuously improving the quality of the learning materials and the user's learning experience.

[0447] The above is a specific embodiment of the system of the present invention. By providing learning materials optimized according to the user's emotional state and continuously improving the quality of the learning materials based on feedback and emotional data, more effective learning support is realized.

[0448] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0449] Specific processing steps

[0450] Step 1: User Registration

[0451] Input: Registration information such as user name, email address, and password

[0452] The terminal sends this information using the HTTPS protocol to be stored on the server.

[0453] The server stores the received registration information in a database.

[0454] Output: A notification email is sent to the user notifying them of successful registration.

[0455] Specific operation: The user enters information into a form on a web page and clicks the "Register" button. The device sends this information to the server, which stores it in a database using a PHP or Python script and sends a confirmation email via the SMTP protocol.

[0456] Step 2: Log in and complete the request form

[0457] Input: User login information (email address, password), grade and topic information of the requested teaching material

[0458] The server receives this and authenticates the user.

[0459] Output: The request is sent to the server.

[0460] Specific operation: The user enters authentication information on the login screen and clicks the "Login" button. Then, the user fills in details such as grade and topic in the request form and clicks the "Submit" button. The device then sends this information to the server.

[0461] Step 3: Emotion analysis using the emotion engine

[0462] Input: User request content, input speed, error rate, facial expression recognition data (using camera input)

[0463] The server passes this data to the emotion engine and makes an API call, which analyzes the emotional state and returns the results to the server.

[0464] Output: Emotional state data

[0465] Specific operation: The server collects input data, calls an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), and receives analysis results from the API.

[0466] Step 4: Generating teaching materials using generative AI models

[0467] Input: Request information, emotional state data

[0468] The server passes the prompt to a generative AI model (e.g., GPT-4) to generate learning materials based on the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the emotional data.

[0469] Output: Generated teaching materials

[0470] Specific operation: The server inputs a prompt into the AI ​​model and retrieves the generated teaching material data. An example of a prompt is: "Please create teaching materials for second-year junior high school students about linear equations with more easy-to-understand examples for users who are tired."

[0471] Step 5: Save and notify the material

[0472] Input: Generated teaching material data

[0473] The server stores this data in a database and notifies the user when the learning material is complete.

[0474] Output: Saving teaching material data, sending notification emails

[0475] Specific operation: The generated teaching materials are stored in a database and a notification email is sent to the user via the SMTP protocol.

[0476] Step 6: Request to download materials

[0477] Input: User ID, learning material ID

[0478] The terminal sends a request containing this information to the server.

[0479] The server retrieves the learning material data from the database and generates a download link.

[0480] Output: Generate and send a download link

[0481] Specific operation: The user clicks the link in the email and opens the learning material page in a browser. A request is sent from the device to the server, and the server generates a download link and sends it back to the device.

[0482] Step 7: Complete and submit the feedback form

[0483] Input: User feedback, emotional data during training

[0484] The terminal transmits this information to the server.

[0485] The server stores the received feedback in a database and periodically analyzes it.

[0486] Output: Save feedback data and analysis results

[0487] Specific operation: The user opens the feedback form and enters their opinions and thoughts. The device sends this to the server, which stores it in a database. The feedback and emotion data are then analyzed and reflected in the next generation of teaching materials.

[0488] Through the above processing steps, a system is realized that provides optimal learning materials that reflect the user's emotional state and feedback, thereby enabling more effective learning support.

[0489] (Application example 2)

[0490] 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."

[0491] While conventional online learning systems can provide learning materials based on a user's learning progress and level of understanding, they have limitations in providing learning materials that take into account the user's emotional state and psychological burden. This has led to problems such as reduced learning efficiency and satisfaction. Furthermore, there has been no established method for efficiently incorporating collected feedback to improve the quality of learning materials.

[0492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0493] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing the feedback in a database, and means for adjusting the difficulty and content of the learning materials based on the user's emotional state using an emotion engine for analyzing the user's emotional data. This makes it possible to provide optimal learning materials according to the user's emotional state and improve learning efficiency and satisfaction. It is also possible to continuously improve the quality of the learning materials using the collected feedback and emotion data.

[0494] "User" refers to an individual who utilizes the system to request learning materials and study.

[0495] "Registration Information" refers to personal information such as name, email address, and password provided by a User when accessing the System.

[0496] "Database" refers to a system that systematically stores and manages data such as user registration information, teaching materials, and feedback.

[0497] "Teaching material request" refers to the act of requesting the system for the content of teaching materials needed based on the grade and topic specified by the user.

[0498] "Artificial intelligence" refers to a computer system that can learn from large amounts of data, recognize patterns, and make decisions like a human.

[0499] "Learning material generation" refers to the process by which artificial intelligence automatically creates learning materials based on user requests.

[0500] "Notification" refers to a communication means for informing the user that the educational material has been generated or that preparation for distribution has been completed.

[0501] "Download request" refers to a request made by a user to receive educational materials online.

[0502] "Feedback" refers to information such as evaluations and improvements provided by users after they have used the learning materials.

[0503] An "emotion engine" refers to software that analyzes a user's input speed, facial expression recognition data, etc., to evaluate the user's emotional state.

[0504] "Emotional data" refers to data that reflects the user's psychological state and emotions.

[0505] "Optimization" refers to the act of adjusting the difficulty and content of learning materials to improve users' learning efficiency and satisfaction.

[0506] "Quality improvement" refers to the process of continuously improving the content and structure of learning materials based on collected feedback and sentiment data.

[0507] MODE FOR CARRYING OUT THE INVENTION

[0508] The present invention provides a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. A specific embodiment of this system will be described.

[0509] System Configuration

[0510] Hardware

[0511] User devices such as smartphones, tablets, and personal computers

[0512] Camera (for facial expression recognition)

[0513] Server (data processing, storage, teaching material generation)

[0514] software

[0515] Emotion engine (e.g. Microsoft Azure Face API)

[0516] Generative AI (e.g. OpenAI GPT-3)

[0517] Database system (e.g. MySQL)

[0518] Communication interface (e.g. HTTP API)

[0519] What the program does

[0520] User Registration

[0521] A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form. The terminal sends the entered information to the server, which stores it in a database. A notification of registration completion is also sent to the user by email.

[0522] Request teaching materials

[0523] Users log in and request the learning materials they want based on their grade level and topic. The device sends the user's request to the server, which then uses an emotion engine to determine the user's emotion based on the received request.

[0524] Emotion recognition by emotion engine

[0525] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state. This evaluation includes input speed, error rate, and facial expression recognition data (using camera input). Based on the emotional state, the server issues instructions to the AI ​​to generate learning materials optimized for the user's emotions.

[0526] Teaching material generation

[0527] The server issues instructions to the generative AI, which generates learning materials according to the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data. For example, if the user is tired, the system will increase the number of example questions to make it easier to understand.

[0528] Teaching material distribution

[0529] The generated teaching materials are saved in a database and notified to the user. The user receives the notification that the teaching materials are complete and clicks a link to request a download of the materials. The device sends a download request to the server, and the server sends the teaching material data to the device. The user clicks the download link to download the teaching material data.

[0530] Feedback collection

[0531] After using the learning materials, the user opens a feedback form and enters feedback such as an evaluation and areas for improvement. The device sends the feedback information to the server, which then stores the received feedback in a database. The feedback may also include emotional data from the learning process. The collected feedback and emotional data are used to generate the next learning material.

[0532] Specific examples

[0533] Example 1: Request for math materials for 8th grade students

[0534] 1. User: A middle school student requests learning materials on "8th Grade Math - Linear Equations."

[0535] 2. Server: Evaluate the user's emotional state using the emotion engine and determine that the user is tired.

[0536] 3. Server: Based on the emotion data, the generative AI is instructed to generate teaching materials related to "linear equations." For example, if the user is tired, the server increases the number of example problems to make the material easier to understand.

[0537] 4. Example prompt for generative AI model:

[0538] "Please create teaching materials on linear equations for second-year junior high school students. Since the target users are feeling fatigued, please increase the number of examples and make the questions easier. Also, please use many illustrations and diagrams to improve comprehension."

[0539] 5. User: Receives and downloads the generated learning materials.

[0540] 6. User: Provide feedback after using the learning materials and also send emotional data about the learning experience.

[0541] This invention allows for the provision of learning materials that take into account the user's emotional state, significantly improving learning efficiency and satisfaction. Furthermore, the quality of the learning materials can be continuously improved based on the collected feedback and emotional data.

[0542] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0543] Step 1:

[0544] The user enters registration information

[0545] A user accesses the system and enters information such as name, email address, and password into the new registration form. The terminal sends this input data to the server. The server saves the received registration information in a database and sends a notification of registration completion to the user by email. Here, the input is "registration information" and the output is "saving to the database" and "sending a notification email of registration completion."

[0546] Step 2:

[0547] User requests learning materials

[0548] A user logs in and requests learning materials based on the desired grade and topic. The terminal sends the user's request data to the server. The server receives and analyzes this request. Here, the input is the "request data for grade and topic" and the output is "data analysis within the server."

[0549] Step 3:

[0550] Emotion recognition using an emotion engine

[0551] The server acquires emotional data such as the user's input speed, error rate, and facial expression data, and uses an emotion engine to evaluate the user's emotional state. The evaluation results are passed to the generative AI. The input is "emotional data," and the output is the "emotional state evaluation result."

[0552] Step 4:

[0553] Generative AI-based learning materials generation

[0554] Based on the evaluation results of the emotion engine, the server issues specific instructions to the generative AI to generate teaching materials. Based on this, the generative AI generates teaching materials appropriate for the grade and topic, adjusting the content according to the difficulty level and the user's level of understanding. Here, the input is "generation instructions and evaluation results," and the output is "generated teaching materials."

[0555] Step 5:

[0556] Saving and notifying materials

[0557] The server saves the generated teaching materials in a database and notifies the user that the teaching materials are complete. The user receives the notification and clicks a link to request download of the teaching materials. The inputs are "generated teaching materials" and "notification to user", and the outputs are "saving teaching materials in a database" and "generating a notification link".

[0558] Step 6:

[0559] Download materials

[0560] The user receives a notification that the teaching material is complete and clicks the link to make a download request. The terminal sends the request data to the server, and the server retrieves the teaching material data from the database and sends it to the user's terminal. The user then downloads and uses the teaching material data. The input is a "download request" and the output is "sending and downloading the teaching material data."

[0561] Step 7:

[0562] Gathering feedback

[0563] After using the learning materials, users enter their evaluations and suggestions for improvement through a feedback form. The device sends the feedback data to the server, which then stores the received feedback and emotion data in a database. This data is later used when generating new learning materials. The input is "user feedback data," and the output is "storage in the database and analysis."

[0564] This series of processing steps allows us to provide individually optimized learning materials that take into account the user's emotional data, improving learning efficiency and satisfaction. Furthermore, we can continuously improve the quality of the learning materials using feedback and emotional data.

[0565] 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.

[0566] 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.

[0567] 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.

[0568] [Second embodiment]

[0569] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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).

[0575] 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. 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.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] In the smart glasses 214, 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.

[0580] 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."

[0581] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of the learning materials based on the feedback. Specific program processing and operation of this system are described below.

[0582] User Registration

[0583] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[0584] 2. The terminal sends the entered information to the server.

[0585] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[0586] Request teaching materials

[0587] 1. The user logs in and fills out a request form for the desired teaching materials based on the grade level and topic to be used.

[0588] 2. The terminal sends the user's request to the server.

[0589] 3. The server issues instructions to the artificial intelligence based on the received request and generates teaching materials based on the specified content.

[0590] Teaching material generation

[0591] 1. The server uses artificial intelligence to automatically generate teaching materials optimal for a specified grade and topic. For example, it creates teaching materials on linear equations for second-year junior high school students.

[0592] 2. The server saves the generated teaching materials in a database and notifies the user that the teaching materials are complete.

[0593] Teaching material distribution

[0594] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[0595] 2. The device sends a download request to the server.

[0596] 3. The server sends the educational material data to the terminal so that the user can download it.

[0597] Feedback collection

[0598] 1. After using the teaching materials, users enter feedback such as their experience and areas for improvement.

[0599] 2. The terminal sends the feedback information to the server.

[0600] 3. The server stores the feedback in a database and reflects it in the next generation of teaching materials.

[0601] Specific examples

[0602] Case 1: A request for math materials for eighth grade students

[0603] 1. User: Junior high school student A registers and logs in to the system.

[0604] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[0605] 3. Terminal: Sends the request to the server.

[0606] 4. Server: Based on the request, the AI ​​generates teaching materials on "linear equations."

[0607] 5. Server: Saves the generated teaching materials in a database and notifies Person A that the teaching materials are complete.

[0608] 6. User: Receive notifications and download materials.

[0609] 7. Device: Sends download request to server.

[0610] 8. Server: Sends the teaching material data to the terminal and Person A downloads it.

[0611] 9. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples."

[0612] 10. Device: Send feedback to the server.

[0613] 11. Server: The feedback is saved in the database and reflected in the next generation of teaching materials.

[0614] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality. This configuration maximizes learning effectiveness and provides efficient learning support.

[0615] The processing flow will be explained below.

[0616] User Registration

[0617] Step 1:

[0618] A user accesses the system, opens the registration form, and enters the required information, such as name, email address, and password.

[0619] Step 2:

[0620] The device sends the entered information to the server, where the data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[0621] Step 3:

[0622] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[0623] Step 4:

[0624] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[0625] Request teaching materials

[0626] Step 1:

[0627] The user logs in to the system and opens the materials request form, entering the grade level, topic, and desired materials.

[0628] Step 2:

[0629] The device sends the input request content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[0630] Step 3:

[0631] The server analyzes the received request and prepares to pass the request to the generative AI.

[0632] Teaching material generation

[0633] Step 1:

[0634] The server passes the request to the generative AI and instructs it to generate teaching materials appropriate for the specified grade and topic.

[0635] Step 2:

[0636] The generative AI on the server creates optimal teaching materials (e.g., explanations and practice problems for linear equations) based on past data and learning algorithms.

[0637] Step 3:

[0638] The server stores the generated teaching materials in a database, along with the metadata of the teaching materials (such as the creation date and related tags).

[0639] Step 4:

[0640] The server sends an email to the user notifying them that the educational material is ready.

[0641] Teaching material distribution

[0642] Step 1:

[0643] The user receives a notification email and clicks on the link to request the download of the materials.

[0644] Step 2:

[0645] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[0646] Step 3:

[0647] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[0648] Step 4:

[0649] The server sends the generated download link to the user's terminal.

[0650] Step 5:

[0651] The user clicks the download link to download the learning material data.

[0652] Feedback collection

[0653] Step 1:

[0654] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[0655] Step 2:

[0656] The terminal transmits the input feedback to the server.

[0657] Step 3:

[0658] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, etc.).

[0659] Step 4:

[0660] The server periodically analyzes the collected feedback and uses it to generate the next learning material, thereby continuously improving the quality of the learning material.

[0661] As described above, this system efficiently generates and distributes teaching materials that meet the individual needs of users, and by incorporating user feedback, it is possible to improve the quality of the teaching materials.

[0662] Example 1

[0663] 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."

[0664] Conventional online education systems have difficulty responding to individual learning needs because they are unable to generate learning materials quickly and accurately in response to user requests. It is also difficult to improve the quality of learning materials by incorporating user feedback, preventing maximum learning effectiveness.

[0665] 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.

[0666] In this invention, the server includes means for storing registration information received from users in a database, means for receiving learning material requests from users, means for generating learning materials based on the user requests using a generative AI model, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, and means for reflecting the collected feedback in the generation of the next learning material. This makes it possible to provide appropriate learning materials that meet the individual learning needs of users and to improve the quality of the learning materials by reflecting the feedback.

[0667] "User" refers to a person who uses the system to perform operations such as registration, requests, downloads, and feedback.

[0668] "Server" refers to the central processing unit that processes data received from users, stores it in a database, generates teaching materials through AI models, and notifies and distributes them to users.

[0669] "Database" refers to a system that systematically stores and manages data such as user registration information, request details, generated learning materials, and collected feedback.

[0670] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates optimal teaching materials based on user requests.

[0671] "Teaching materials" refers to learning materials and educational content created to meet the learning needs of users.

[0672] "Feedback" refers to the evaluation and suggestions for improvement provided by the user regarding the educational materials used.

[0673] A "request" refers to a request made by a user to the system regarding the content and format of the educational material desired by the user.

[0674] "Notification" refers to the act of a system conveying information to a user by means of email, screen display, or other means.

[0675] "Download Request" refers to a request made by a User to save generated educational materials to their own device.

[0676] "Storage" refers to the act of keeping data or information in a database or storage so that it can be accessed later.

[0677] The system of the present invention allows users to request individually optimized learning materials online and improve the quality of the learning materials based on the user's feedback. The system's main components are the user, a terminal, and a server.

[0678] User Registration

[0679] First, a user accesses the system and enters the required information such as name, email address, and password into the new registration form. The terminal then converts this input information into JSON format and sends it to the server as an HTTP POST request. The server parses the received data and saves it in a database (e.g., MySQL or PostgreSQL). After saving is complete, the server uses an email sending library (e.g., SMTP or SendGrid) to send a registration completion notification to the user.

[0680] Request teaching materials

[0681] After logging in to the system, the user enters the necessary information into a request form for teaching materials based on the desired grade and topic. The device then converts this information back into JSON format and sends it to the server as an HTTP POST request. The server parses the received request data, creates a prompt for the generative AI model (e.g., GPT-4), and sends the request. An example of a prompt is, "Please generate teaching materials related to linear equations in mathematics for second-year junior high school students."

[0682] Teaching material generation

[0683] The generative AI model generates optimal learning materials based on prompts received from the server. For example, it generates learning materials that include example problems and explanations for linear equations in mathematics for second-year junior high school students. The generated learning materials are saved in a database by the server, and once saved, the server sends a notification to the user that the learning materials are complete.

[0684] Teaching material distribution

[0685] When a user receives a notification that the teaching materials are complete, they click the link in the notification to access the materials download page. When the user clicks the "Download" button, the device sends a download request to the server. The server retrieves the teaching materials data from the database and sends it to the user's device as an HTTP response. This allows the user to download the teaching materials to their device.

[0686] Feedback collection

[0687] After using the learning materials, the user enters their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request. The server stores the received feedback data in a database and reflects it the next time learning materials are generated.

[0688] Specific examples

[0689] A junior high school student, Mr. A, registers and requests "teaching materials related to linear equations" for "second-year junior high school mathematics." The device sends the request to the server, which then sends a prompt to the generative AI model saying, "Please generate teaching materials related to linear equations." The generated teaching materials are saved in the database, and the user is notified that the teaching materials are complete. Mr. A receives the notification, downloads and uses the teaching materials, and then sends feedback saying, "It's easy to understand, but I'd like more example problems." The device sends the feedback to the server, which saves it in the database and reflects it in the next teaching material generation.

[0690] This system enables the rapid provision of individually optimized learning materials tailored to the user's learning needs, and also makes it possible to continuously improve the quality of the learning materials by utilizing user feedback.

[0691] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0692] Step 1: User Registration

[0693] A user accesses the system's new registration page and enters the required information, including name, email address, and password, into the form. The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0694] Input: User's name, email address, and password

[0695] Output: HTTP POST request to the server

[0696] Specific operation: The device converts the input content of the HTML form into JSON using JavaScript and sends a POST request to the server's API endpoint.

[0697] Step 2: Processing and database storage of registration information

[0698] The server parses the received JSON data, verifies its validity, and then stores the user information in a database (e.g., MySQL or PostgreSQL).

[0699] Input: JSON data sent from the terminal

[0700] Output: Save user information to database

[0701] What happens: The server validates the data and then saves it to the database using an SQL query.

[0702] Step 3: Sending a registration completion notice

[0703] The server sends a registration completion email to the user. Using an email sending library (e.g., SMTP or SendGrid), a registration completion notification is sent to the user's email address.

[0704] Input: The fact that registration information was saved, the user's email address

[0705] Output: Registration completion notification email sent to user

[0706] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[0707] Step 4: Complete and submit your materials request

[0708] A user logs in and enters the necessary information into a request form for the desired teaching materials based on grade level and topic. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[0709] Input: Grade level, topic, and details of the desired teaching materials

[0710] Output: HTTP POST request to the server

[0711] Specific operation: The device converts the input content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[0712] Step 5: Process the request data and teach the AI ​​model

[0713] The server parses the received request data, checks the contents, and creates a prompt to the generative AI model (e.g., GPT-4) and sends the request.

[0714] Input: Request data sent from the terminal

[0715] Output: The prompt to send to the generative AI model

[0716] Specific operation: The server parses the request data, generates a prompt sentence, and sends it to the AI ​​model.

[0717] Step 6: Creating and saving teaching materials

[0718] The generative AI model generates teaching materials based on the prompts received from the server, which then receives the teaching material data and stores it in a database.

[0719] Input: The prompt sent to the generative AI model

[0720] Output: Teaching material data stored in the database

[0721] Specific operation: The AI ​​model generates teaching material data, the server receives it, and stores it in a database using an SQL query.

[0722] Step 7: Sending notification of completion of materials

[0723] The server notifies the user that the learning material is complete. An email containing a link to the completed learning material is sent to the user using the email sending library.

[0724] Input: Generated teaching material data, user email address

[0725] Output: Email to user notifying them of completion of the teaching material

[0726] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[0727] Step 8: Request download of materials

[0728] The user clicks the link in the completion notification email to access the download page. When the user clicks the "Download" button, the device sends a download request to the server.

[0729] Input: User download request

[0730] Output: HTTP GET request to the server

[0731] Specific operation: The device detects user operation and sends a GET request to the server's API endpoint.

[0732] Step 9: Submit the teaching materials data

[0733] The server retrieves the teaching material data from the database and sends it to the user's terminal as an HTTP response.

[0734] Input: Download request received from user

[0735] Output: Sending educational material data to the user's device

[0736] Specific operation: The server retrieves the teaching material data using an SQL query and sends it to the terminal as an HTTP response.

[0737] Step 10: Submitting feedback input

[0738] After using the learning materials, users enter their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request.

[0739] Input: User feedback

[0740] Output: HTTP POST request to the server

[0741] Specific operation: The terminal converts the feedback content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[0742] Step 11: Save and incorporate feedback

[0743] The server parses the received feedback data, stores it in a database, and instructs the AI ​​model to reflect that feedback the next time it generates teaching materials.

[0744] Input: Feedback data submitted by the user

[0745] Output: Save feedback to the database and instruct the AI ​​model to reflect the feedback

[0746] Specific operation: The server analyzes the feedback data, stores it in a database using an SQL query, and processes it so that it is reflected in the next prompt sentence for the AI ​​model.

[0747] These are the processing steps of the system. By generating individual learning materials based on user requests and incorporating feedback, learning materials optimized for learning needs are provided.

[0748] (Application example 1)

[0749] 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."

[0750] Conventional online learning systems take time for users to receive individually optimized learning materials, which does not sufficiently improve learning efficiency. Furthermore, they lack real-time learning support using smart devices and do not sufficiently consider user convenience. Therefore, there is a need for a method to optimize users' learning experience in real time and quickly respond to individual needs.

[0751] 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.

[0752] In this invention, the server includes means for storing registration information received from a user in a database, means for receiving a learning material request from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, means for providing optimized learning materials in real time using a smart device, and means for analyzing the user's voice commands or gesture inputs, thereby making it possible to provide individually optimized learning materials to the user in real time and improve learning efficiency.

[0753] The "means for storing registration information received from a user in a database" refers to a method or device for recording personal information and other registration information provided by a user in a database on the server side.

[0754] The "means for receiving a learning material request from a user" refers to an interface or method by which a user specifies the content and requirements of the learning material desired by the user to the system.

[0755] "Means for generating teaching materials based on user requests using artificial intelligence" refers to a method or device for creating teaching materials that are optimal for specified conditions using an artificial intelligence algorithm in response to a user's request for teaching materials.

[0756] The "means for storing the generated teaching materials in a database and notifying the user" refers to a means for recording the generated teaching materials in a database and notifying the user about it.

[0757] The "means for delivering educational materials when a user makes a download request" refers to a method or device for transmitting educational materials to a user's terminal when the user requests the download of the educational materials.

[0758] The "means for collecting user feedback and storing it in a database" refers to a method or device for collecting opinions and evaluations provided by users after use and recording them in a database.

[0759] "Means for providing optimized educational materials in real time using a smart device" refers to a method or apparatus for providing users with educational materials that are optimized on the spot through a smart device such as a smartphone or smart glasses.

[0760] "Means for analyzing user voice commands or gesture inputs" refers to a method or device for interpreting the content of user voice or gesture instructions and executing an action in response to them.

[0761] The system of the present invention allows users to quickly obtain individually optimized learning materials online and study them in real time through their smart devices. The components of this system and their detailed program processing are described below.

[0762] System configuration

[0763] 1. User Registration

[0764] Device: Smart device (e.g. smartphone, smart glasses)

[0765] Server: A central server for storing registration information (such as name, email address, and password) in a database.

[0766] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[0767] 2. Request for teaching materials

[0768] Terminal: An interface where users can make requests via voice commands or touch gestures.

[0769] Server: Receives the request and saves it in the database

[0770] Software: Natural Language Processing (NLP) engine (e.g., Google Cloud Natural Language API)

[0771] 3. Teaching material generation

[0772] Server: Generates educational materials using artificial intelligence based on user requests

[0773] Software: Generative AI models (e.g., OpenAI GPT-4)

[0774] 4. Teaching material distribution

[0775] Device: Receive notifications of educational material distribution and send download requests

[0776] Server: Deliver learning materials when a user makes a download request

[0777] Software: Cloud storage (e.g. Google Cloud Storage)

[0778] 5. Feedback Collection

[0779] On your device: Enter feedback using voice commands or touch gestures

[0780] Server: Receives feedback and stores it in a database

[0781] Software: Speech recognition engine, NLP engine

[0782] Program processing

[0783] User Registration

[0784] The user provides registration information by voice input using a smart device. This information is converted into text by a voice recognition engine and sent to the server. The server stores this registration information in a database and sends a notification to the user that registration is complete.

[0785] Request teaching materials

[0786] Users request learning materials using voice commands or touch gestures. The voice data is analyzed by an NLP engine, and the request is sent in text format to the server. The server then passes the request to an AI model to generate learning materials.

[0787] Teaching material generation

[0788] The server uses a generative AI model to generate optimal learning materials based on the user's request. For example, if a user requests "learning materials on linear equations for second-year junior high school mathematics," the AI ​​model will create the learning materials. The generated learning materials are stored in a database.

[0789] Teaching material distribution

[0790] Once the learning materials are generated, the user is notified. The user then sends a download request from their smart device, and the server sends the learning materials data to the device.

[0791] Feedback collection

[0792] After using the learning materials, users can input feedback using voice commands or touch gestures. The feedback is analyzed by a speech recognition engine and an NLP engine and sent to the server in text format. The server stores this in a database and reflects it in the next generation of learning materials.

[0793] Specific examples

[0794] Prompt Sentence Examples

[0795] Material Request:

[0796] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[0797] feedback:

[0798] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[0799] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality, thereby maximizing learning effectiveness and providing efficient learning support.

[0800] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0801] Step 1:

[0802] The user provides registration information using a smart device.

[0803] Specifically, the user uses voice input to input information such as name, email address, and password into the terminal.

[0804] The input data is audio data.

[0805] The device converts the voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API).

[0806] Step 2:

[0807] The terminal transmits the converted text data to the server.

[0808] The data to be transmitted is text data.

[0809] The server receives this text data and stores it in a database.

[0810] The server will send an email to the user notifying them of the completion of registration.

[0811] The output data is an email notifying the completion of registration.

[0812] Step 3:

[0813] Users can request educational materials using their smart devices.

[0814] Specifically, the user inputs a request for teaching materials according to grade level or topic using voice commands or touch gestures.

[0815] The input data is voice data or gesture data.

[0816] The device converts the voice data into text data using a speech recognition engine and analyzes the request using an NLP engine (e.g., Google Cloud Natural Language API).

[0817] The parsed text data is sent to the server.

[0818] Step 4:

[0819] The server receives the requested text data and generates optimal teaching materials using a generative AI model (e.g., OpenAI GPT-4).

[0820] The input data is the text data of the request.

[0821] The generated teaching materials are output in multiple data formats, including text, images, graphs, etc.

[0822] The server stores the generated teaching material data in a database and notifies the user that the teaching material has been completed.

[0823] Step 5:

[0824] The user receives a notification that the teaching material is complete and sends a download request using a smart device.

[0825] The input data is a download request sent from the terminal.

[0826] The terminal sends a request to the server, which provides a download link to the user.

[0827] The output data is a download link.

[0828] Step 6:

[0829] Users click on the download link from their smart device to obtain the learning materials.

[0830] The data to be input is the click operation of the user.

[0831] The server transmits the educational material data to the terminal, and the user is then able to use the educational material.

[0832] The output data is teaching material data.

[0833] Step 7:

[0834] Users provide feedback on the learning material using their smart devices.

[0835] Specifically, the user inputs feedback using voice commands or touch gestures.

[0836] The input data is voice data or gesture data.

[0837] The device converts the voice data into text data using a voice recognition engine, analyzes it using an NLP engine, and then sends it to the server.

[0838] The server stores the received feedback in a database and reflects it in the next generation of teaching materials.

[0839] Specific examples

[0840] Prompt Sentence Examples

[0841] Material Request:

[0842] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[0843] feedback:

[0844] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[0845] Through the above processing steps, users can obtain optimized learning materials in real time, and a system that can quickly respond to individual needs is realized.

[0846] 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.

[0847] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[0848] User Registration

[0849] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[0850] 2. The terminal sends the entered information to the server.

[0851] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[0852] Request teaching materials

[0853] 1. The user logs in and fills out a request form for the desired teaching materials based on grade level and topic.

[0854] 2. The terminal sends the user's request to the server.

[0855] 3. The server uses the emotion engine based on the received request to determine the user's emotion.

[0856] Emotion recognition by emotion engine

[0857] 1. The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[0858] 2. The server issues instructions to the AI ​​based on the user's emotional state and generates teaching materials optimized for the user's emotions.

[0859] Teaching material generation

[0860] 1. The server issues instructions to the generative AI to generate learning materials appropriate for the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data.

[0861] 2. The server stores the generated teaching materials in a database and notifies the user.

[0862] Teaching material distribution

[0863] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[0864] 2. The terminal sends a download request to the server. This request includes the user ID and the learning material ID.

[0865] 3. The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[0866] 4. The server sends the generated download link to the user's device.

[0867] 5. The user clicks the download link to download the teaching material data.

[0868] Feedback collection

[0869] 1. After using the learning materials, the user opens the feedback form and enters feedback such as an evaluation and areas for improvement.

[0870] 2. The terminal sends the feedback information to the server.

[0871] 3. The server stores the received feedback in a database, which may include emotional data during training.

[0872] 4. The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[0873] Specific examples

[0874] Case 1: A request for math materials for eighth grade students

[0875] 1. User: A junior high school student registers and logs into the system.

[0876] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[0877] 3. Terminal: Sends the request to the server.

[0878] 4. Server: Based on the request content, the emotion engine evaluates the user's emotional state.

[0879] 5. Server: Based on the emotional data, the AI ​​is instructed to generate educational materials on "linear equations." For example, if the user is tired, the AI ​​will increase the number of examples to make it easier to understand.

[0880] 6. Server: Stores the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[0881] 7. User: Receive notifications and download materials.

[0882] 8. Device: Sends download request to server.

[0883] 9. Server: Sends the teaching material data to the terminal and the user downloads it.

[0884] 10. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the study.

[0885] 11. Device: Send feedback to the server.

[0886] 12. Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[0887] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[0888] The processing flow will be explained below.

[0889] User Registration

[0890] Step 1:

[0891] A user accesses the system and enters the required information such as name, email address, and password into the new registration form.

[0892] Step 2:

[0893] The terminal sends the entered user information to the server. The data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[0894] Step 3:

[0895] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[0896] Step 4:

[0897] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[0898] Request teaching materials

[0899] Step 1:

[0900] Users log in to the system and fill out a request form for the teaching materials they want based on grade level and topic.

[0901] Step 2:

[0902] The terminal sends the user's desired content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[0903] Step 3:

[0904] The server analyzes the received request and prepares to pass the request to the generative AI.

[0905] Emotion recognition by emotion engine

[0906] Step 1:

[0907] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[0908] Step 2:

[0909] The server issues instructions to the AI ​​based on the user's emotional state and configures it to generate teaching materials optimized for the user's emotions.

[0910] Teaching material generation

[0911] Step 1:

[0912] The server issues instructions to the generative AI to generate teaching materials according to the specified grade and topic. For example, if it determines that the user is tired, it will adjust the difficulty level to a lower level.

[0913] Step 2:

[0914] The server stores the generated learning materials in a database, along with the learning materials' metadata (such as the creation date, associated tags, and emotional state).

[0915] Step 3:

[0916] The server sends an email to the user notifying them that the educational material is ready.

[0917] Teaching material distribution

[0918] Step 1:

[0919] The user receives a notification that the materials are complete and clicks on the link to request a download.

[0920] Step 2:

[0921] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[0922] Step 3:

[0923] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[0924] Step 4:

[0925] The server sends the generated download link to the user's terminal.

[0926] Step 5:

[0927] The user clicks the download link to download the learning material data.

[0928] Feedback collection

[0929] Step 1:

[0930] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[0931] Step 2:

[0932] The terminal transmits the input feedback to the server.

[0933] Step 3:

[0934] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, emotional state, etc.).

[0935] Step 4:

[0936] The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[0937] Specific examples

[0938] Case 1: A request for math materials for eighth grade students

[0939] Step 1:

[0940] User: A junior high school student registers and logs into the system.

[0941] Step 2:

[0942] User: Requests "teaching materials on linear equations" for "8th grade mathematics."

[0943] Step 3:

[0944] Terminal: Sends the request to the server.

[0945] Step 4:

[0946] Server: Based on the request content, the emotion engine evaluates the user's emotional state. For example, it detects if the user is showing signs of impatience or fatigue when making a request.

[0947] Step 5:

[0948] Server: Based on the emotional data, the AI ​​is instructed to generate teaching materials on "linear equations." If the user is tired, the AI ​​will provide more examples and more detailed explanations.

[0949] Step 6:

[0950] Server: Saves the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[0951] Step 7:

[0952] Users: Receive notifications and download learning materials.

[0953] Step 8:

[0954] Device: Sends a download request to the server.

[0955] Step 9:

[0956] Server: Sends educational material data to the terminal and users download it.

[0957] Step 10:

[0958] User: After using the learning materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the learning process.

[0959] Step 11:

[0960] Device: Send feedback to the server.

[0961] Step 12:

[0962] Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[0963] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[0964] Example 2

[0965] 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."

[0966] Conventional online learning systems do not provide learning materials that take into account the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to improve the quality of learning materials based on feedback, making it difficult to continuously improve the learning experience.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0968] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for analyzing the user's emotions using an emotion engine, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, and means for collecting user feedback, storing it in a database, and analyzing it. This makes it possible to provide learning materials optimized according to the user's emotional state and to continuously improve the quality of the learning materials by utilizing the collected feedback and emotion data.

[0969] "Registration Information" refers to personal information that a User provides when accessing the System, including name, email address, password, etc.

[0970] A "material request" is a request made by a user to the system for material related to a particular grade or topic.

[0971] An "emotion engine" is a technology that analyzes a user's input data, usage status, facial expression recognition data, etc. to evaluate their emotional state.

[0972] "Artificial intelligence" is a type of computational technology that generates optimized learning materials based on the user's requests and emotional state.

[0973] The "database" is an information management system that centrally stores and manages data such as registration information, teaching materials, and feedback within the system.

[0974] "Feedback" refers to information about evaluations and improvements provided by users after using educational materials.

[0975] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[0976] User Registration

[0977] First, the user accesses the system's web page and enters the required information, such as name, email address, and password, into the new registration form. The information entered by the user is sent from the terminal to the server using the HTTPS protocol. The server stores the received registration information in a database such as MySQL and sends a registration completion notification to the user's email address. This process is carried out using PHP or Python scripts.

[0978] Request teaching materials

[0979] Next, the user logs into the system and fills out a request form for the desired teaching materials based on grade level and topic. The request is sent from the terminal to the server, and the server uses an emotion engine to evaluate the user's emotional state based on the received request. The emotion engine uses input speed, error rate, facial expression recognition data, etc.

[0980] Emotion recognition by emotion engine

[0981] The server collects emotional data from user input, usage, camera input, etc. This data is input into an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), which then makes an API call to evaluate the emotional data. As a result, the server conveys the user's emotional state to the AI.

[0982] Teaching material generation

[0983] Based on the received emotional data, the server issues instructions to a generative AI (e.g., GPT-4) to generate learning materials appropriate for the specified grade and topic. During this process, the difficulty and content of the learning materials are adjusted based on the user's emotional state. The generated learning materials are stored in a database and notified to the user. As a specific example, if the user is "tired," the AI ​​is instructed to increase the number of example questions to make the material easier to understand.

[0984] Example prompt sentence:

[0985] If the grade level is "8th grade," the topic is "linear equations," and the emotional state is "tired," then: "Create teaching materials for 8th grade linear equations with more examples that are easy to understand for users who are tired."

[0986] Teaching material distribution

[0987] When the user receives notification that the teaching materials are complete, they click a link to request a download of the materials. The device sends a download request including the user ID and teaching material ID to the server. The server retrieves the teaching material data from the database, generates a temporary download link, and sends it to the user's device. The user clicks the link to download the teaching material data.

[0988] Feedback collection

[0989] After using the learning materials, users enter their evaluation and suggestions for improvement in a feedback form. This feedback information is sent from the device to the server, which stores the information in a database. The feedback may also include emotional data from the learning process. The server analyzes the collected feedback and emotional data and reflects this in the next generation of learning materials, thereby continuously improving the quality of the learning materials and the user's learning experience.

[0990] The above is a specific embodiment of the system of the present invention. By providing learning materials optimized according to the user's emotional state and continuously improving the quality of the learning materials based on feedback and emotional data, more effective learning support is realized.

[0991] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0992] Specific processing steps

[0993] Step 1: User Registration

[0994] Input: Registration information such as user name, email address, and password

[0995] The terminal sends this information using the HTTPS protocol to be stored on the server.

[0996] The server stores the received registration information in a database.

[0997] Output: A notification email is sent to the user notifying them of successful registration.

[0998] Specific operation: The user enters information into a form on a web page and clicks the "Register" button. The device sends this information to the server, which stores it in a database using a PHP or Python script and sends a confirmation email via the SMTP protocol.

[0999] Step 2: Log in and complete the request form

[1000] Input: User login information (email address, password), grade and topic information of the requested teaching material

[1001] The server receives this and authenticates the user.

[1002] Output: The request is sent to the server.

[1003] Specific operation: The user enters authentication information on the login screen and clicks the "Login" button. Then, the user fills in details such as grade and topic in the request form and clicks the "Submit" button. The device then sends this information to the server.

[1004] Step 3: Emotion analysis using the emotion engine

[1005] Input: User request content, input speed, error rate, facial expression recognition data (using camera input)

[1006] The server passes this data to the emotion engine and makes an API call, which analyzes the emotional state and returns the results to the server.

[1007] Output: Emotional state data

[1008] Specific operation: The server collects input data, calls an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), and receives analysis results from the API.

[1009] Step 4: Generating teaching materials using generative AI models

[1010] Input: Request information, emotional state data

[1011] The server passes the prompt to a generative AI model (e.g., GPT-4) to generate learning materials based on the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the emotional data.

[1012] Output: Generated teaching materials

[1013] Specific operation: The server inputs a prompt into the AI ​​model and retrieves the generated teaching material data. An example of a prompt is: "Please create teaching materials for second-year junior high school students about linear equations with more easy-to-understand examples for users who are tired."

[1014] Step 5: Save and notify the material

[1015] Input: Generated teaching material data

[1016] The server stores this data in a database and notifies the user when the learning material is complete.

[1017] Output: Saving teaching material data, sending notification emails

[1018] Specific operation: The generated teaching materials are stored in a database and a notification email is sent to the user via the SMTP protocol.

[1019] Step 6: Request to download materials

[1020] Input: User ID, learning material ID

[1021] The terminal sends a request containing this information to the server.

[1022] The server retrieves the learning material data from the database and generates a download link.

[1023] Output: Generate and send a download link

[1024] Specific operation: The user clicks the link in the email and opens the learning material page in a browser. A request is sent from the device to the server, and the server generates a download link and sends it back to the device.

[1025] Step 7: Complete and submit the feedback form

[1026] Input: User feedback, emotional data during training

[1027] The terminal transmits this information to the server.

[1028] The server stores the received feedback in a database and periodically analyzes it.

[1029] Output: Save feedback data and analysis results

[1030] Specific operation: The user opens the feedback form and enters their opinions and thoughts. The device sends this to the server, which stores it in a database. The feedback and emotion data are then analyzed and reflected in the next generation of teaching materials.

[1031] Through the above processing steps, a system is realized that provides optimal learning materials that reflect the user's emotional state and feedback, thereby enabling more effective learning support.

[1032] (Application example 2)

[1033] 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."

[1034] While conventional online learning systems can provide learning materials based on a user's learning progress and level of understanding, they have limitations in providing learning materials that take into account the user's emotional state and psychological burden. This has led to problems such as reduced learning efficiency and satisfaction. Furthermore, there has been no established method for efficiently incorporating collected feedback to improve the quality of learning materials.

[1035] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1036] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing the feedback in a database, and means for adjusting the difficulty and content of the learning materials based on the user's emotional state using an emotion engine for analyzing the user's emotional data. This makes it possible to provide optimal learning materials according to the user's emotional state and improve learning efficiency and satisfaction. It is also possible to continuously improve the quality of the learning materials using the collected feedback and emotion data.

[1037] "User" refers to an individual who utilizes the system to request learning materials and study.

[1038] "Registration Information" refers to personal information such as name, email address, and password provided by a User when accessing the System.

[1039] "Database" refers to a system that systematically stores and manages data such as user registration information, teaching materials, and feedback.

[1040] "Teaching material request" refers to the act of requesting the system for the content of teaching materials needed based on the grade and topic specified by the user.

[1041] "Artificial intelligence" refers to a computer system that can learn from large amounts of data, recognize patterns, and make decisions like a human.

[1042] "Learning material generation" refers to the process by which artificial intelligence automatically creates learning materials based on user requests.

[1043] "Notification" refers to a communication means for informing the user that the educational material has been generated or that preparation for distribution has been completed.

[1044] "Download request" refers to a request made by a user to receive educational materials online.

[1045] "Feedback" refers to information such as evaluations and improvements provided by users after they have used the learning materials.

[1046] An "emotion engine" refers to software that analyzes a user's input speed, facial expression recognition data, etc., to evaluate the user's emotional state.

[1047] "Emotional data" refers to data that reflects the user's psychological state and emotions.

[1048] "Optimization" refers to the act of adjusting the difficulty and content of learning materials to improve users' learning efficiency and satisfaction.

[1049] "Quality improvement" refers to the process of continuously improving the content and structure of learning materials based on collected feedback and sentiment data.

[1050] MODE FOR CARRYING OUT THE INVENTION

[1051] The present invention provides a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. A specific embodiment of this system will be described.

[1052] System Configuration

[1053] Hardware

[1054] User devices such as smartphones, tablets, and personal computers

[1055] Camera (for facial expression recognition)

[1056] Server (data processing, storage, teaching material generation)

[1057] software

[1058] Emotion engine (e.g. Microsoft Azure Face API)

[1059] Generative AI (e.g. OpenAI GPT-3)

[1060] Database system (e.g. MySQL)

[1061] Communication interface (e.g. HTTP API)

[1062] What the program does

[1063] User Registration

[1064] A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form. The terminal sends the entered information to the server, which stores it in a database. A notification of registration completion is also sent to the user by email.

[1065] Request teaching materials

[1066] Users log in and request the learning materials they want based on their grade level and topic. The device sends the user's request to the server, which then uses an emotion engine to determine the user's emotion based on the received request.

[1067] Emotion recognition by emotion engine

[1068] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state. This evaluation includes input speed, error rate, and facial expression recognition data (using camera input). Based on the emotional state, the server issues instructions to the AI ​​to generate learning materials optimized for the user's emotions.

[1069] Teaching material generation

[1070] The server issues instructions to the generative AI, which generates learning materials according to the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data. For example, if the user is tired, the system will increase the number of example questions to make it easier to understand.

[1071] Teaching material distribution

[1072] The generated teaching materials are saved in a database and notified to the user. The user receives the notification that the teaching materials are complete and clicks a link to request a download of the materials. The device sends a download request to the server, and the server sends the teaching material data to the device. The user clicks the download link to download the teaching material data.

[1073] Feedback collection

[1074] After using the learning materials, the user opens a feedback form and enters feedback such as an evaluation and areas for improvement. The device sends the feedback information to the server, which then stores the received feedback in a database. The feedback may also include emotional data from the learning process. The collected feedback and emotional data are used to generate the next learning material.

[1075] Specific examples

[1076] Example 1: Request for math materials for 8th grade students

[1077] 1. User: A middle school student requests learning materials on "8th Grade Math - Linear Equations."

[1078] 2. Server: Evaluate the user's emotional state using the emotion engine and determine that the user is tired.

[1079] 3. Server: Based on the emotion data, the generative AI is instructed to generate teaching materials related to "linear equations." For example, if the user is tired, the server increases the number of example problems to make the material easier to understand.

[1080] 4. Example prompt for generative AI model:

[1081] "Please create teaching materials on linear equations for second-year junior high school students. Since the target users are feeling fatigued, please increase the number of examples and make the questions easier. Also, please use many illustrations and diagrams to improve comprehension."

[1082] 5. User: Receives and downloads the generated learning materials.

[1083] 6. User: Provide feedback after using the learning materials and also send emotional data about the learning experience.

[1084] This invention allows for the provision of learning materials that take into account the user's emotional state, significantly improving learning efficiency and satisfaction. Furthermore, the quality of the learning materials can be continuously improved based on the collected feedback and emotional data.

[1085] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1086] Step 1:

[1087] The user enters registration information

[1088] A user accesses the system and enters information such as name, email address, and password into the new registration form. The terminal sends this input data to the server. The server saves the received registration information in a database and sends a notification of registration completion to the user by email. Here, the input is "registration information" and the output is "saving to the database" and "sending a notification email of registration completion."

[1089] Step 2:

[1090] User requests learning materials

[1091] A user logs in and requests learning materials based on the desired grade and topic. The terminal sends the user's request data to the server. The server receives and analyzes this request. Here, the input is the "request data for grade and topic" and the output is "data analysis within the server."

[1092] Step 3:

[1093] Emotion recognition using an emotion engine

[1094] The server acquires emotional data such as the user's input speed, error rate, and facial expression data, and uses an emotion engine to evaluate the user's emotional state. The evaluation results are passed to the generative AI. The input is "emotional data," and the output is the "emotional state evaluation result."

[1095] Step 4:

[1096] Generative AI-based learning materials generation

[1097] Based on the evaluation results of the emotion engine, the server issues specific instructions to the generative AI to generate teaching materials. Based on this, the generative AI generates teaching materials appropriate for the grade and topic, adjusting the content according to the difficulty level and the user's level of understanding. Here, the input is "generation instructions and evaluation results," and the output is "generated teaching materials."

[1098] Step 5:

[1099] Saving and notifying materials

[1100] The server saves the generated teaching materials in a database and notifies the user that the teaching materials are complete. The user receives the notification and clicks a link to request download of the teaching materials. The inputs are "generated teaching materials" and "notification to user", and the outputs are "saving teaching materials in a database" and "generating a notification link".

[1101] Step 6:

[1102] Download materials

[1103] The user receives a notification that the teaching material is complete and clicks the link to make a download request. The terminal sends the request data to the server, and the server retrieves the teaching material data from the database and sends it to the user's terminal. The user then downloads and uses the teaching material data. The input is a "download request" and the output is "sending and downloading the teaching material data."

[1104] Step 7:

[1105] Gathering feedback

[1106] After using the learning materials, users enter their evaluations and suggestions for improvement through a feedback form. The device sends the feedback data to the server, which then stores the received feedback and emotion data in a database. This data is later used when generating new learning materials. The input is "user feedback data," and the output is "storage in the database and analysis."

[1107] This series of processing steps allows us to provide individually optimized learning materials that take into account the user's emotional data, improving learning efficiency and satisfaction. Furthermore, we can continuously improve the quality of the learning materials using feedback and emotional data.

[1108] 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.

[1109] 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.

[1110] 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.

[1111] [Third embodiment]

[1112] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1113] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1114] 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).

[1115] 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.

[1116] 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.

[1117] 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).

[1118] 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. 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.

[1119] 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.

[1120] 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.

[1121] 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.

[1122] 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.

[1123] 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."

[1124] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of the learning materials based on the feedback. Specific program processing and operation of this system are described below.

[1125] User Registration

[1126] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[1127] 2. The terminal sends the entered information to the server.

[1128] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[1129] Request teaching materials

[1130] 1. The user logs in and fills out a request form for the desired teaching materials based on the grade level and topic to be used.

[1131] 2. The terminal sends the user's request to the server.

[1132] 3. The server issues instructions to the artificial intelligence based on the received request and generates teaching materials based on the specified content.

[1133] Teaching material generation

[1134] 1. The server uses artificial intelligence to automatically generate teaching materials optimal for a specified grade and topic. For example, it creates teaching materials on linear equations for second-year junior high school students.

[1135] 2. The server saves the generated teaching materials in a database and notifies the user that the teaching materials are complete.

[1136] Teaching material distribution

[1137] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[1138] 2. The device sends a download request to the server.

[1139] 3. The server sends the educational material data to the terminal so that the user can download it.

[1140] Feedback collection

[1141] 1. After using the teaching materials, users enter feedback such as their experience and areas for improvement.

[1142] 2. The terminal sends the feedback information to the server.

[1143] 3. The server stores the feedback in a database and reflects it in the next generation of teaching materials.

[1144] Specific examples

[1145] Case 1: A request for math materials for eighth grade students

[1146] 1. User: Junior high school student A registers and logs in to the system.

[1147] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[1148] 3. Terminal: Sends the request to the server.

[1149] 4. Server: Based on the request, the AI ​​generates teaching materials on "linear equations."

[1150] 5. Server: Saves the generated teaching materials in a database and notifies Person A that the teaching materials are complete.

[1151] 6. User: Receive notifications and download materials.

[1152] 7. Device: Sends download request to server.

[1153] 8. Server: Sends the teaching material data to the terminal and Person A downloads it.

[1154] 9. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples."

[1155] 10. Device: Send feedback to the server.

[1156] 11. Server: The feedback is saved in the database and reflected in the next generation of teaching materials.

[1157] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality. This configuration maximizes learning effectiveness and provides efficient learning support.

[1158] The processing flow will be explained below.

[1159] User Registration

[1160] Step 1:

[1161] A user accesses the system, opens the registration form, and enters the required information, such as name, email address, and password.

[1162] Step 2:

[1163] The device sends the entered information to the server, where the data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[1164] Step 3:

[1165] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[1166] Step 4:

[1167] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[1168] Request teaching materials

[1169] Step 1:

[1170] The user logs in to the system and opens the materials request form, entering the grade level, topic, and desired materials.

[1171] Step 2:

[1172] The device sends the input request content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[1173] Step 3:

[1174] The server analyzes the received request and prepares to pass the request to the generative AI.

[1175] Teaching material generation

[1176] Step 1:

[1177] The server passes the request to the generative AI and instructs it to generate teaching materials appropriate for the specified grade and topic.

[1178] Step 2:

[1179] The generative AI on the server creates optimal teaching materials (e.g., explanations and practice problems for linear equations) based on past data and learning algorithms.

[1180] Step 3:

[1181] The server stores the generated teaching materials in a database, along with the metadata of the teaching materials (such as the creation date and related tags).

[1182] Step 4:

[1183] The server sends an email to the user notifying them that the educational material is ready.

[1184] Teaching material distribution

[1185] Step 1:

[1186] The user receives a notification email and clicks on the link to request the download of the materials.

[1187] Step 2:

[1188] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[1189] Step 3:

[1190] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[1191] Step 4:

[1192] The server sends the generated download link to the user's terminal.

[1193] Step 5:

[1194] The user clicks the download link to download the learning material data.

[1195] Feedback collection

[1196] Step 1:

[1197] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[1198] Step 2:

[1199] The terminal transmits the input feedback to the server.

[1200] Step 3:

[1201] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, etc.).

[1202] Step 4:

[1203] The server periodically analyzes the collected feedback and uses it to generate the next learning material, thereby continuously improving the quality of the learning material.

[1204] As described above, this system efficiently generates and distributes teaching materials that meet the individual needs of users, and by incorporating user feedback, it is possible to improve the quality of the teaching materials.

[1205] Example 1

[1206] 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."

[1207] Conventional online education systems have difficulty responding to individual learning needs because they are unable to generate learning materials quickly and accurately in response to user requests. It is also difficult to improve the quality of learning materials by incorporating user feedback, preventing maximum learning effectiveness.

[1208] 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.

[1209] In this invention, the server includes means for storing registration information received from users in a database, means for receiving learning material requests from users, means for generating learning materials based on the user requests using a generative AI model, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, and means for reflecting the collected feedback in the generation of the next learning material. This makes it possible to provide appropriate learning materials that meet the individual learning needs of users and to improve the quality of the learning materials by reflecting the feedback.

[1210] "User" refers to a person who uses the system to perform operations such as registration, requests, downloads, and feedback.

[1211] "Server" refers to the central processing unit that processes data received from users, stores it in a database, generates teaching materials through AI models, and notifies and distributes them to users.

[1212] "Database" refers to a system that systematically stores and manages data such as user registration information, request details, generated learning materials, and collected feedback.

[1213] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates optimal teaching materials based on user requests.

[1214] "Teaching materials" refers to learning materials and educational content created to meet the learning needs of users.

[1215] "Feedback" refers to the evaluation and suggestions for improvement provided by the user regarding the educational materials used.

[1216] A "request" refers to a request made by a user to the system regarding the content and format of the educational material desired by the user.

[1217] "Notification" refers to the act of a system conveying information to a user by means of email, screen display, or other means.

[1218] "Download Request" refers to a request made by a User to save generated educational materials to their own device.

[1219] "Storage" refers to the act of keeping data or information in a database or storage so that it can be accessed later.

[1220] The system of the present invention allows users to request individually optimized learning materials online and improve the quality of the learning materials based on the user's feedback. The system's main components are the user, a terminal, and a server.

[1221] User Registration

[1222] First, a user accesses the system and enters the required information such as name, email address, and password into the new registration form. The terminal then converts this input information into JSON format and sends it to the server as an HTTP POST request. The server parses the received data and saves it in a database (e.g., MySQL or PostgreSQL). After saving is complete, the server uses an email sending library (e.g., SMTP or SendGrid) to send a registration completion notification to the user.

[1223] Request teaching materials

[1224] After logging in to the system, the user enters the necessary information into a request form for teaching materials based on the desired grade and topic. The device then converts this information back into JSON format and sends it to the server as an HTTP POST request. The server parses the received request data, creates a prompt for the generative AI model (e.g., GPT-4), and sends the request. An example of a prompt is, "Please generate teaching materials related to linear equations in mathematics for second-year junior high school students."

[1225] Teaching material generation

[1226] The generative AI model generates optimal learning materials based on prompts received from the server. For example, it generates learning materials that include example problems and explanations for linear equations in mathematics for second-year junior high school students. The generated learning materials are saved in a database by the server, and once saved, the server sends a notification to the user that the learning materials are complete.

[1227] Teaching material distribution

[1228] When a user receives a notification that the teaching materials are complete, they click the link in the notification to access the materials download page. When the user clicks the "Download" button, the device sends a download request to the server. The server retrieves the teaching materials data from the database and sends it to the user's device as an HTTP response. This allows the user to download the teaching materials to their device.

[1229] Feedback collection

[1230] After using the learning materials, the user enters their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request. The server stores the received feedback data in a database and reflects it the next time learning materials are generated.

[1231] Specific examples

[1232] A junior high school student, Mr. A, registers and requests "teaching materials related to linear equations" for "second-year junior high school mathematics." The device sends the request to the server, which then sends a prompt to the generative AI model saying, "Please generate teaching materials related to linear equations." The generated teaching materials are saved in the database, and the user is notified that the teaching materials are complete. Mr. A receives the notification, downloads and uses the teaching materials, and then sends feedback saying, "It's easy to understand, but I'd like more example problems." The device sends the feedback to the server, which saves it in the database and reflects it in the next teaching material generation.

[1233] This system enables the rapid provision of individually optimized learning materials tailored to the user's learning needs, and also makes it possible to continuously improve the quality of the learning materials by utilizing user feedback.

[1234] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1235] Step 1: User Registration

[1236] A user accesses the system's new registration page and enters the required information, including name, email address, and password, into the form. The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1237] Input: User's name, email address, and password

[1238] Output: HTTP POST request to the server

[1239] Specific operation: The device converts the input content of the HTML form into JSON using JavaScript and sends a POST request to the server's API endpoint.

[1240] Step 2: Processing and database storage of registration information

[1241] The server parses the received JSON data, verifies its validity, and then stores the user information in a database (e.g., MySQL or PostgreSQL).

[1242] Input: JSON data sent from the terminal

[1243] Output: Save user information to database

[1244] What happens: The server validates the data and then saves it to the database using an SQL query.

[1245] Step 3: Sending a registration completion notice

[1246] The server sends a registration completion email to the user. Using an email sending library (e.g., SMTP or SendGrid), a registration completion notification is sent to the user's email address.

[1247] Input: The fact that registration information was saved, the user's email address

[1248] Output: Registration completion notification email sent to user

[1249] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[1250] Step 4: Complete and submit your materials request

[1251] A user logs in and enters the necessary information into a request form for the desired teaching materials based on grade level and topic. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1252] Input: Grade level, topic, and details of the desired teaching materials

[1253] Output: HTTP POST request to the server

[1254] Specific operation: The device converts the input content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[1255] Step 5: Process the request data and teach the AI ​​model

[1256] The server parses the received request data, checks the contents, and creates a prompt to the generative AI model (e.g., GPT-4) and sends the request.

[1257] Input: Request data sent from the terminal

[1258] Output: The prompt to send to the generative AI model

[1259] Specific operation: The server parses the request data, generates a prompt sentence, and sends it to the AI ​​model.

[1260] Step 6: Creating and saving teaching materials

[1261] The generative AI model generates teaching materials based on the prompts received from the server, which then receives the teaching material data and stores it in a database.

[1262] Input: The prompt sent to the generative AI model

[1263] Output: Teaching material data stored in the database

[1264] Specific operation: The AI ​​model generates teaching material data, the server receives it, and stores it in a database using an SQL query.

[1265] Step 7: Sending notification of completion of materials

[1266] The server notifies the user that the learning material is complete. An email containing a link to the completed learning material is sent to the user using the email sending library.

[1267] Input: Generated teaching material data, user email address

[1268] Output: Email to user notifying them of completion of the teaching material

[1269] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[1270] Step 8: Request download of materials

[1271] The user clicks the link in the completion notification email to access the download page. When the user clicks the "Download" button, the device sends a download request to the server.

[1272] Input: User download request

[1273] Output: HTTP GET request to the server

[1274] Specific operation: The device detects user operation and sends a GET request to the server's API endpoint.

[1275] Step 9: Submit the teaching materials data

[1276] The server retrieves the teaching material data from the database and sends it to the user's terminal as an HTTP response.

[1277] Input: Download request received from user

[1278] Output: Sending educational material data to the user's device

[1279] Specific operation: The server retrieves the teaching material data using an SQL query and sends it to the terminal as an HTTP response.

[1280] Step 10: Submitting feedback input

[1281] After using the learning materials, users enter their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request.

[1282] Input: User feedback

[1283] Output: HTTP POST request to the server

[1284] Specific operation: The terminal converts the feedback content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[1285] Step 11: Save and incorporate feedback

[1286] The server parses the received feedback data, stores it in a database, and instructs the AI ​​model to reflect that feedback the next time it generates teaching materials.

[1287] Input: Feedback data submitted by the user

[1288] Output: Save feedback to the database and instruct the AI ​​model to reflect the feedback

[1289] Specific operation: The server analyzes the feedback data, stores it in a database using an SQL query, and processes it so that it is reflected in the next prompt sentence for the AI ​​model.

[1290] These are the processing steps of the system. By generating individual learning materials based on user requests and incorporating feedback, learning materials optimized for learning needs are provided.

[1291] (Application example 1)

[1292] 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."

[1293] Conventional online learning systems take time for users to receive individually optimized learning materials, which does not sufficiently improve learning efficiency. Furthermore, they lack real-time learning support using smart devices and do not sufficiently consider user convenience. Therefore, there is a need for a method to optimize users' learning experience in real time and quickly respond to individual needs.

[1294] 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.

[1295] In this invention, the server includes means for storing registration information received from a user in a database, means for receiving a learning material request from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, means for providing optimized learning materials in real time using a smart device, and means for analyzing the user's voice commands or gesture inputs, thereby making it possible to provide individually optimized learning materials to the user in real time and improve learning efficiency.

[1296] The "means for storing registration information received from a user in a database" refers to a method or device for recording personal information and other registration information provided by a user in a database on the server side.

[1297] The "means for receiving a learning material request from a user" refers to an interface or method by which a user specifies the content and requirements of the learning material desired by the user to the system.

[1298] "Means for generating teaching materials based on user requests using artificial intelligence" refers to a method or device for creating teaching materials that are optimal for specified conditions using an artificial intelligence algorithm in response to a user's request for teaching materials.

[1299] The "means for storing the generated teaching materials in a database and notifying the user" refers to a means for recording the generated teaching materials in a database and notifying the user about it.

[1300] The "means for delivering educational materials when a user makes a download request" refers to a method or device for transmitting educational materials to a user's terminal when the user requests the download of the educational materials.

[1301] The "means for collecting user feedback and storing it in a database" refers to a method or device for collecting opinions and evaluations provided by users after use and recording them in a database.

[1302] "Means for providing optimized educational materials in real time using a smart device" refers to a method or apparatus for providing users with educational materials that are optimized on the spot through a smart device such as a smartphone or smart glasses.

[1303] "Means for analyzing user voice commands or gesture inputs" refers to a method or device for interpreting the content of user voice or gesture instructions and executing an action in response to them.

[1304] The system of the present invention allows users to quickly obtain individually optimized learning materials online and study them in real time through their smart devices. The components of this system and their detailed program processing are described below.

[1305] System configuration

[1306] 1. User Registration

[1307] Device: Smart device (e.g. smartphone, smart glasses)

[1308] Server: A central server for storing registration information (such as name, email address, and password) in a database.

[1309] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[1310] 2. Request for teaching materials

[1311] Terminal: An interface where users can make requests via voice commands or touch gestures.

[1312] Server: Receives the request and saves it in the database

[1313] Software: Natural Language Processing (NLP) engine (e.g., Google Cloud Natural Language API)

[1314] 3. Teaching material generation

[1315] Server: Generates educational materials using artificial intelligence based on user requests

[1316] Software: Generative AI models (e.g., OpenAI GPT-4)

[1317] 4. Teaching material distribution

[1318] Device: Receive notifications of educational material distribution and send download requests

[1319] Server: Deliver learning materials when a user makes a download request

[1320] Software: Cloud storage (e.g. Google Cloud Storage)

[1321] 5. Feedback Collection

[1322] On your device: Enter feedback using voice commands or touch gestures

[1323] Server: Receives feedback and stores it in a database

[1324] Software: Speech recognition engine, NLP engine

[1325] Program processing

[1326] User Registration

[1327] The user provides registration information by voice input using a smart device. This information is converted into text by a voice recognition engine and sent to the server. The server stores this registration information in a database and sends a notification to the user that registration is complete.

[1328] Request teaching materials

[1329] Users request learning materials using voice commands or touch gestures. The voice data is analyzed by an NLP engine, and the request is sent in text format to the server. The server then passes the request to an AI model to generate learning materials.

[1330] Teaching material generation

[1331] The server uses a generative AI model to generate optimal learning materials based on the user's request. For example, if a user requests "learning materials on linear equations for second-year junior high school mathematics," the AI ​​model will create the learning materials. The generated learning materials are stored in a database.

[1332] Teaching material distribution

[1333] Once the learning materials are generated, the user is notified. The user then sends a download request from their smart device, and the server sends the learning materials data to the device.

[1334] Feedback collection

[1335] After using the learning materials, users can input feedback using voice commands or touch gestures. The feedback is analyzed by a speech recognition engine and an NLP engine and sent to the server in text format. The server stores this in a database and reflects it in the next generation of learning materials.

[1336] Specific examples

[1337] Prompt Sentence Examples

[1338] Material Request:

[1339] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[1340] feedback:

[1341] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[1342] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality, thereby maximizing learning effectiveness and providing efficient learning support.

[1343] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1344] Step 1:

[1345] The user provides registration information using a smart device.

[1346] Specifically, the user uses voice input to input information such as name, email address, and password into the terminal.

[1347] The input data is audio data.

[1348] The device converts the voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API).

[1349] Step 2:

[1350] The terminal transmits the converted text data to the server.

[1351] The data to be transmitted is text data.

[1352] The server receives this text data and stores it in a database.

[1353] The server will send an email to the user notifying them of the completion of registration.

[1354] The output data is an email notifying the completion of registration.

[1355] Step 3:

[1356] Users can request educational materials using their smart devices.

[1357] Specifically, the user inputs a request for teaching materials according to grade level or topic using voice commands or touch gestures.

[1358] The input data is voice data or gesture data.

[1359] The device converts the voice data into text data using a speech recognition engine and analyzes the request using an NLP engine (e.g., Google Cloud Natural Language API).

[1360] The parsed text data is sent to the server.

[1361] Step 4:

[1362] The server receives the requested text data and generates optimal teaching materials using a generative AI model (e.g., OpenAI GPT-4).

[1363] The input data is the text data of the request.

[1364] The generated teaching materials are output in multiple data formats, including text, images, graphs, etc.

[1365] The server stores the generated teaching material data in a database and notifies the user that the teaching material has been completed.

[1366] Step 5:

[1367] The user receives a notification that the teaching material is complete and sends a download request using a smart device.

[1368] The input data is a download request sent from the terminal.

[1369] The terminal sends a request to the server, which provides a download link to the user.

[1370] The output data is a download link.

[1371] Step 6:

[1372] Users click on the download link from their smart device to obtain the learning materials.

[1373] The data to be input is the click operation of the user.

[1374] The server transmits the educational material data to the terminal, and the user is then able to use the educational material.

[1375] The output data is teaching material data.

[1376] Step 7:

[1377] Users provide feedback on the learning material using their smart devices.

[1378] Specifically, the user inputs feedback using voice commands or touch gestures.

[1379] The input data is voice data or gesture data.

[1380] The device converts the voice data into text data using a voice recognition engine, analyzes it using an NLP engine, and then sends it to the server.

[1381] The server stores the received feedback in a database and reflects it in the next generation of teaching materials.

[1382] Specific examples

[1383] Prompt Sentence Examples

[1384] Material Request:

[1385] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[1386] feedback:

[1387] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[1388] Through the above processing steps, users can obtain optimized learning materials in real time, and a system that can quickly respond to individual needs is realized.

[1389] 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.

[1390] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[1391] User Registration

[1392] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[1393] 2. The terminal sends the entered information to the server.

[1394] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[1395] Request teaching materials

[1396] 1. The user logs in and fills out a request form for the desired teaching materials based on grade level and topic.

[1397] 2. The terminal sends the user's request to the server.

[1398] 3. The server uses the emotion engine based on the received request to determine the user's emotion.

[1399] Emotion recognition by emotion engine

[1400] 1. The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[1401] 2. The server issues instructions to the AI ​​based on the user's emotional state and generates teaching materials optimized for the user's emotions.

[1402] Teaching material generation

[1403] 1. The server issues instructions to the generative AI to generate learning materials appropriate for the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data.

[1404] 2. The server stores the generated teaching materials in a database and notifies the user.

[1405] Teaching material distribution

[1406] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[1407] 2. The terminal sends a download request to the server. This request includes the user ID and the learning material ID.

[1408] 3. The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[1409] 4. The server sends the generated download link to the user's device.

[1410] 5. The user clicks the download link to download the teaching material data.

[1411] Feedback collection

[1412] 1. After using the learning materials, the user opens the feedback form and enters feedback such as an evaluation and areas for improvement.

[1413] 2. The terminal sends the feedback information to the server.

[1414] 3. The server stores the received feedback in a database, which may include emotional data during training.

[1415] 4. The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[1416] Specific examples

[1417] Case 1: A request for math materials for eighth grade students

[1418] 1. User: A junior high school student registers and logs into the system.

[1419] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[1420] 3. Terminal: Sends the request to the server.

[1421] 4. Server: Based on the request content, the emotion engine evaluates the user's emotional state.

[1422] 5. Server: Based on the emotional data, the AI ​​is instructed to generate educational materials on "linear equations." For example, if the user is tired, the AI ​​will increase the number of examples to make it easier to understand.

[1423] 6. Server: Stores the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[1424] 7. User: Receive notifications and download materials.

[1425] 8. Device: Sends download request to server.

[1426] 9. Server: Sends the teaching material data to the terminal and the user downloads it.

[1427] 10. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the study.

[1428] 11. Device: Send feedback to the server.

[1429] 12. Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[1430] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[1431] The processing flow will be explained below.

[1432] User Registration

[1433] Step 1:

[1434] A user accesses the system and enters the required information such as name, email address, and password into the new registration form.

[1435] Step 2:

[1436] The terminal sends the entered user information to the server. The data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[1437] Step 3:

[1438] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[1439] Step 4:

[1440] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[1441] Request teaching materials

[1442] Step 1:

[1443] Users log in to the system and fill out a request form for the teaching materials they want based on grade level and topic.

[1444] Step 2:

[1445] The terminal sends the user's desired content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[1446] Step 3:

[1447] The server analyzes the received request and prepares to pass the request to the generative AI.

[1448] Emotion recognition by emotion engine

[1449] Step 1:

[1450] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[1451] Step 2:

[1452] The server issues instructions to the AI ​​based on the user's emotional state and configures it to generate teaching materials optimized for the user's emotions.

[1453] Teaching material generation

[1454] Step 1:

[1455] The server issues instructions to the generative AI to generate teaching materials according to the specified grade and topic. For example, if it determines that the user is tired, it will adjust the difficulty level to a lower level.

[1456] Step 2:

[1457] The server stores the generated learning materials in a database, along with the learning materials' metadata (such as the creation date, associated tags, and emotional state).

[1458] Step 3:

[1459] The server sends an email to the user notifying them that the educational material is ready.

[1460] Teaching material distribution

[1461] Step 1:

[1462] The user receives a notification that the materials are complete and clicks on the link to request a download.

[1463] Step 2:

[1464] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[1465] Step 3:

[1466] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[1467] Step 4:

[1468] The server sends the generated download link to the user's terminal.

[1469] Step 5:

[1470] The user clicks the download link to download the learning material data.

[1471] Feedback collection

[1472] Step 1:

[1473] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[1474] Step 2:

[1475] The terminal transmits the input feedback to the server.

[1476] Step 3:

[1477] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, emotional state, etc.).

[1478] Step 4:

[1479] The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[1480] Specific examples

[1481] Case 1: A request for math materials for eighth grade students

[1482] Step 1:

[1483] User: A junior high school student registers and logs into the system.

[1484] Step 2:

[1485] User: Requests "teaching materials on linear equations" for "8th grade mathematics."

[1486] Step 3:

[1487] Terminal: Sends the request to the server.

[1488] Step 4:

[1489] Server: Based on the request content, the emotion engine evaluates the user's emotional state. For example, it detects if the user is showing signs of impatience or fatigue when making a request.

[1490] Step 5:

[1491] Server: Based on the emotional data, the AI ​​is instructed to generate teaching materials on "linear equations." If the user is tired, the AI ​​will provide more examples and more detailed explanations.

[1492] Step 6:

[1493] Server: Saves the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[1494] Step 7:

[1495] Users: Receive notifications and download learning materials.

[1496] Step 8:

[1497] Device: Sends a download request to the server.

[1498] Step 9:

[1499] Server: Sends educational material data to the terminal and users download it.

[1500] Step 10:

[1501] User: After using the learning materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the learning process.

[1502] Step 11:

[1503] Device: Send feedback to the server.

[1504] Step 12:

[1505] Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[1506] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[1507] Example 2

[1508] 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."

[1509] Conventional online learning systems do not provide learning materials that take into account the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to improve the quality of learning materials based on feedback, making it difficult to continuously improve the learning experience.

[1510] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1511] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for analyzing the user's emotions using an emotion engine, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, and means for collecting user feedback, storing it in a database, and analyzing it. This makes it possible to provide learning materials optimized according to the user's emotional state and to continuously improve the quality of the learning materials by utilizing the collected feedback and emotion data.

[1512] "Registration Information" refers to personal information that a User provides when accessing the System, including name, email address, password, etc.

[1513] A "material request" is a request made by a user to the system for material related to a particular grade or topic.

[1514] An "emotion engine" is a technology that analyzes a user's input data, usage status, facial expression recognition data, etc. to evaluate their emotional state.

[1515] "Artificial intelligence" is a type of computational technology that generates optimized learning materials based on the user's requests and emotional state.

[1516] The "database" is an information management system that centrally stores and manages data such as registration information, teaching materials, and feedback within the system.

[1517] "Feedback" refers to information about evaluations and improvements provided by users after using educational materials.

[1518] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[1519] User Registration

[1520] First, the user accesses the system's web page and enters the required information, such as name, email address, and password, into the new registration form. The information entered by the user is sent from the terminal to the server using the HTTPS protocol. The server stores the received registration information in a database such as MySQL and sends a registration completion notification to the user's email address. This process is carried out using PHP or Python scripts.

[1521] Request teaching materials

[1522] Next, the user logs into the system and fills out a request form for the desired teaching materials based on grade level and topic. The request is sent from the terminal to the server, and the server uses an emotion engine to evaluate the user's emotional state based on the received request. The emotion engine uses input speed, error rate, facial expression recognition data, etc.

[1523] Emotion recognition by emotion engine

[1524] The server collects emotional data from user input, usage, camera input, etc. This data is input into an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), which then makes an API call to evaluate the emotional data. As a result, the server conveys the user's emotional state to the AI.

[1525] Teaching material generation

[1526] Based on the received emotional data, the server issues instructions to a generative AI (e.g., GPT-4) to generate learning materials appropriate for the specified grade and topic. During this process, the difficulty and content of the learning materials are adjusted based on the user's emotional state. The generated learning materials are stored in a database and notified to the user. As a specific example, if the user is "tired," the AI ​​is instructed to increase the number of example questions to make the material easier to understand.

[1527] Example prompt sentence:

[1528] If the grade level is "8th grade," the topic is "linear equations," and the emotional state is "tired," then: "Create teaching materials for 8th grade linear equations with more examples that are easy to understand for users who are tired."

[1529] Teaching material distribution

[1530] When the user receives notification that the teaching materials are complete, they click a link to request a download of the materials. The device sends a download request including the user ID and teaching material ID to the server. The server retrieves the teaching material data from the database, generates a temporary download link, and sends it to the user's device. The user clicks the link to download the teaching material data.

[1531] Feedback collection

[1532] After using the learning materials, users enter their evaluation and suggestions for improvement in a feedback form. This feedback information is sent from the device to the server, which stores the information in a database. The feedback may also include emotional data from the learning process. The server analyzes the collected feedback and emotional data and reflects this in the next generation of learning materials, thereby continuously improving the quality of the learning materials and the user's learning experience.

[1533] The above is a specific embodiment of the system of the present invention. By providing learning materials optimized according to the user's emotional state and continuously improving the quality of the learning materials based on feedback and emotional data, more effective learning support is realized.

[1534] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1535] Specific processing steps

[1536] Step 1: User Registration

[1537] Input: Registration information such as user name, email address, and password

[1538] The terminal sends this information using the HTTPS protocol to be stored on the server.

[1539] The server stores the received registration information in a database.

[1540] Output: A notification email is sent to the user notifying them of successful registration.

[1541] Specific operation: The user enters information into a form on a web page and clicks the "Register" button. The device sends this information to the server, which stores it in a database using a PHP or Python script and sends a confirmation email via the SMTP protocol.

[1542] Step 2: Log in and complete the request form

[1543] Input: User login information (email address, password), grade and topic information of the requested teaching material

[1544] The server receives this and authenticates the user.

[1545] Output: The request is sent to the server.

[1546] Specific operation: The user enters authentication information on the login screen and clicks the "Login" button. Then, the user fills in details such as grade and topic in the request form and clicks the "Submit" button. The device then sends this information to the server.

[1547] Step 3: Emotion analysis using the emotion engine

[1548] Input: User request content, input speed, error rate, facial expression recognition data (using camera input)

[1549] The server passes this data to the emotion engine and makes an API call, which analyzes the emotional state and returns the results to the server.

[1550] Output: Emotional state data

[1551] Specific operation: The server collects input data, calls an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), and receives analysis results from the API.

[1552] Step 4: Generating teaching materials using generative AI models

[1553] Input: Request information, emotional state data

[1554] The server passes the prompt to a generative AI model (e.g., GPT-4) to generate learning materials based on the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the emotional data.

[1555] Output: Generated teaching materials

[1556] Specific operation: The server inputs a prompt into the AI ​​model and retrieves the generated teaching material data. An example of a prompt is: "Please create teaching materials for second-year junior high school students about linear equations with more easy-to-understand examples for users who are tired."

[1557] Step 5: Save and notify the material

[1558] Input: Generated teaching material data

[1559] The server stores this data in a database and notifies the user when the learning material is complete.

[1560] Output: Saving teaching material data, sending notification emails

[1561] Specific operation: The generated teaching materials are stored in a database and a notification email is sent to the user via the SMTP protocol.

[1562] Step 6: Request to download materials

[1563] Input: User ID, learning material ID

[1564] The terminal sends a request containing this information to the server.

[1565] The server retrieves the learning material data from the database and generates a download link.

[1566] Output: Generate and send a download link

[1567] Specific operation: The user clicks the link in the email and opens the learning material page in a browser. A request is sent from the device to the server, and the server generates a download link and sends it back to the device.

[1568] Step 7: Complete and submit the feedback form

[1569] Input: User feedback, emotional data during training

[1570] The terminal transmits this information to the server.

[1571] The server stores the received feedback in a database and periodically analyzes it.

[1572] Output: Save feedback data and analysis results

[1573] Specific operation: The user opens the feedback form and enters their opinions and thoughts. The device sends this to the server, which stores it in a database. The feedback and emotion data are then analyzed and reflected in the next generation of teaching materials.

[1574] Through the above processing steps, a system is realized that provides optimal learning materials that reflect the user's emotional state and feedback, thereby enabling more effective learning support.

[1575] (Application example 2)

[1576] 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."

[1577] While conventional online learning systems can provide learning materials based on a user's learning progress and level of understanding, they have limitations in providing learning materials that take into account the user's emotional state and psychological burden. This has led to problems such as reduced learning efficiency and satisfaction. Furthermore, there has been no established method for efficiently incorporating collected feedback to improve the quality of learning materials.

[1578] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1579] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing the feedback in a database, and means for adjusting the difficulty and content of the learning materials based on the user's emotional state using an emotion engine for analyzing the user's emotional data. This makes it possible to provide optimal learning materials according to the user's emotional state and improve learning efficiency and satisfaction. It is also possible to continuously improve the quality of the learning materials using the collected feedback and emotion data.

[1580] "User" refers to an individual who utilizes the system to request learning materials and study.

[1581] "Registration Information" refers to personal information such as name, email address, and password provided by a User when accessing the System.

[1582] "Database" refers to a system that systematically stores and manages data such as user registration information, teaching materials, and feedback.

[1583] "Teaching material request" refers to the act of requesting the system for the content of teaching materials needed based on the grade and topic specified by the user.

[1584] "Artificial intelligence" refers to a computer system that can learn from large amounts of data, recognize patterns, and make decisions like a human.

[1585] "Learning material generation" refers to the process by which artificial intelligence automatically creates learning materials based on user requests.

[1586] "Notification" refers to a communication means for informing the user that the educational material has been generated or that preparation for distribution has been completed.

[1587] "Download request" refers to a request made by a user to receive educational materials online.

[1588] "Feedback" refers to information such as evaluations and improvements provided by users after they have used the learning materials.

[1589] An "emotion engine" refers to software that analyzes a user's input speed, facial expression recognition data, etc., to evaluate the user's emotional state.

[1590] "Emotional data" refers to data that reflects the user's psychological state and emotions.

[1591] "Optimization" refers to the act of adjusting the difficulty and content of learning materials to improve users' learning efficiency and satisfaction.

[1592] "Quality improvement" refers to the process of continuously improving the content and structure of learning materials based on collected feedback and sentiment data.

[1593] MODE FOR CARRYING OUT THE INVENTION

[1594] The present invention provides a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. A specific embodiment of this system will be described.

[1595] System Configuration

[1596] Hardware

[1597] User devices such as smartphones, tablets, and personal computers

[1598] Camera (for facial expression recognition)

[1599] Server (data processing, storage, teaching material generation)

[1600] software

[1601] Emotion engine (e.g. Microsoft Azure Face API)

[1602] Generative AI (e.g. OpenAI GPT-3)

[1603] Database system (e.g. MySQL)

[1604] Communication interface (e.g. HTTP API)

[1605] What the program does

[1606] User Registration

[1607] A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form. The terminal sends the entered information to the server, which stores it in a database. A notification of registration completion is also sent to the user by email.

[1608] Request teaching materials

[1609] Users log in and request the learning materials they want based on their grade level and topic. The device sends the user's request to the server, which then uses an emotion engine to determine the user's emotion based on the received request.

[1610] Emotion recognition by emotion engine

[1611] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state. This evaluation includes input speed, error rate, and facial expression recognition data (using camera input). Based on the emotional state, the server issues instructions to the AI ​​to generate learning materials optimized for the user's emotions.

[1612] Teaching material generation

[1613] The server issues instructions to the generative AI, which generates learning materials according to the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data. For example, if the user is tired, the system will increase the number of example questions to make it easier to understand.

[1614] Teaching material distribution

[1615] The generated teaching materials are saved in a database and notified to the user. The user receives the notification that the teaching materials are complete and clicks a link to request a download of the materials. The device sends a download request to the server, and the server sends the teaching material data to the device. The user clicks the download link to download the teaching material data.

[1616] Feedback collection

[1617] After using the learning materials, the user opens a feedback form and enters feedback such as an evaluation and areas for improvement. The device sends the feedback information to the server, which then stores the received feedback in a database. The feedback may also include emotional data from the learning process. The collected feedback and emotional data are used to generate the next learning material.

[1618] Specific examples

[1619] Example 1: Request for math materials for 8th grade students

[1620] 1. User: A middle school student requests learning materials on "8th Grade Math - Linear Equations."

[1621] 2. Server: Evaluate the user's emotional state using the emotion engine and determine that the user is tired.

[1622] 3. Server: Based on the emotion data, the generative AI is instructed to generate teaching materials related to "linear equations." For example, if the user is tired, the server increases the number of example problems to make the material easier to understand.

[1623] 4. Example prompt for generative AI model:

[1624] "Please create teaching materials on linear equations for second-year junior high school students. Since the target users are feeling fatigued, please increase the number of examples and make the questions easier. Also, please use many illustrations and diagrams to improve comprehension."

[1625] 5. User: Receives and downloads the generated learning materials.

[1626] 6. User: Provide feedback after using the learning materials and also send emotional data about the learning experience.

[1627] This invention allows for the provision of learning materials that take into account the user's emotional state, significantly improving learning efficiency and satisfaction. Furthermore, the quality of the learning materials can be continuously improved based on the collected feedback and emotional data.

[1628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1629] Step 1:

[1630] The user enters registration information

[1631] A user accesses the system and enters information such as name, email address, and password into the new registration form. The terminal sends this input data to the server. The server saves the received registration information in a database and sends a notification of registration completion to the user by email. Here, the input is "registration information" and the output is "saving to the database" and "sending a notification email of registration completion."

[1632] Step 2:

[1633] User requests learning materials

[1634] A user logs in and requests learning materials based on the desired grade and topic. The terminal sends the user's request data to the server. The server receives and analyzes this request. Here, the input is the "request data for grade and topic" and the output is "data analysis within the server."

[1635] Step 3:

[1636] Emotion recognition using an emotion engine

[1637] The server acquires emotional data such as the user's input speed, error rate, and facial expression data, and uses an emotion engine to evaluate the user's emotional state. The evaluation results are passed to the generative AI. The input is "emotional data," and the output is the "emotional state evaluation result."

[1638] Step 4:

[1639] Generative AI-based learning materials generation

[1640] Based on the evaluation results of the emotion engine, the server issues specific instructions to the generative AI to generate teaching materials. Based on this, the generative AI generates teaching materials appropriate for the grade and topic, adjusting the content according to the difficulty level and the user's level of understanding. Here, the input is "generation instructions and evaluation results," and the output is "generated teaching materials."

[1641] Step 5:

[1642] Saving and notifying materials

[1643] The server saves the generated teaching materials in a database and notifies the user that the teaching materials are complete. The user receives the notification and clicks a link to request download of the teaching materials. The inputs are "generated teaching materials" and "notification to user", and the outputs are "saving teaching materials in a database" and "generating a notification link".

[1644] Step 6:

[1645] Download materials

[1646] The user receives a notification that the teaching material is complete and clicks the link to make a download request. The terminal sends the request data to the server, and the server retrieves the teaching material data from the database and sends it to the user's terminal. The user then downloads and uses the teaching material data. The input is a "download request" and the output is "sending and downloading the teaching material data."

[1647] Step 7:

[1648] Gathering feedback

[1649] After using the learning materials, users enter their evaluations and suggestions for improvement through a feedback form. The device sends the feedback data to the server, which then stores the received feedback and emotion data in a database. This data is later used when generating new learning materials. The input is "user feedback data," and the output is "storage in the database and analysis."

[1650] This series of processing steps allows us to provide individually optimized learning materials that take into account the user's emotional data, improving learning efficiency and satisfaction. Furthermore, we can continuously improve the quality of the learning materials using feedback and emotional data.

[1651] 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.

[1652] 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.

[1653] 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.

[1654] [Fourth embodiment]

[1655] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1656] 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.

[1657] 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).

[1658] 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.

[1659] 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.

[1660] 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).

[1661] 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. 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.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] 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."

[1668] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of the learning materials based on the feedback. Specific program processing and operation of this system are described below.

[1669] User Registration

[1670] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[1671] 2. The terminal sends the entered information to the server.

[1672] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[1673] Request teaching materials

[1674] 1. The user logs in and fills out a request form for the desired teaching materials based on the grade level and topic to be used.

[1675] 2. The terminal sends the user's request to the server.

[1676] 3. The server issues instructions to the artificial intelligence based on the received request and generates teaching materials based on the specified content.

[1677] Teaching material generation

[1678] 1. The server uses artificial intelligence to automatically generate teaching materials optimal for a specified grade and topic. For example, it creates teaching materials on linear equations for second-year junior high school students.

[1679] 2. The server saves the generated teaching materials in a database and notifies the user that the teaching materials are complete.

[1680] Teaching material distribution

[1681] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[1682] 2. The device sends a download request to the server.

[1683] 3. The server sends the educational material data to the terminal so that the user can download it.

[1684] Feedback collection

[1685] 1. After using the teaching materials, users enter feedback such as their experience and areas for improvement.

[1686] 2. The terminal sends the feedback information to the server.

[1687] 3. The server stores the feedback in a database and reflects it in the next generation of teaching materials.

[1688] Specific examples

[1689] Case 1: A request for math materials for eighth grade students

[1690] 1. User: Junior high school student A registers and logs in to the system.

[1691] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[1692] 3. Terminal: Sends the request to the server.

[1693] 4. Server: Based on the request, the AI ​​generates teaching materials on "linear equations."

[1694] 5. Server: Saves the generated teaching materials in a database and notifies Person A that the teaching materials are complete.

[1695] 6. User: Receive notifications and download materials.

[1696] 7. Device: Sends download request to server.

[1697] 8. Server: Sends the teaching material data to the terminal and Person A downloads it.

[1698] 9. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples."

[1699] 10. Device: Send feedback to the server.

[1700] 11. Server: The feedback is saved in the database and reflected in the next generation of teaching materials.

[1701] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality. This configuration maximizes learning effectiveness and provides efficient learning support.

[1702] The processing flow will be explained below.

[1703] User Registration

[1704] Step 1:

[1705] A user accesses the system, opens the registration form, and enters the required information, such as name, email address, and password.

[1706] Step 2:

[1707] The device sends the entered information to the server, where the data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[1708] Step 3:

[1709] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[1710] Step 4:

[1711] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[1712] Request teaching materials

[1713] Step 1:

[1714] The user logs in to the system and opens the materials request form, entering the grade level, topic, and desired materials.

[1715] Step 2:

[1716] The device sends the input request content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[1717] Step 3:

[1718] The server analyzes the received request and prepares to pass the request to the generative AI.

[1719] Teaching material generation

[1720] Step 1:

[1721] The server passes the request to the generative AI and instructs it to generate teaching materials appropriate for the specified grade and topic.

[1722] Step 2:

[1723] The generative AI on the server creates optimal teaching materials (e.g., explanations and practice problems for linear equations) based on past data and learning algorithms.

[1724] Step 3:

[1725] The server stores the generated teaching materials in a database, along with the metadata of the teaching materials (such as the creation date and related tags).

[1726] Step 4:

[1727] The server sends an email to the user notifying them that the educational material is ready.

[1728] Teaching material distribution

[1729] Step 1:

[1730] The user receives a notification email and clicks on the link to request the download of the materials.

[1731] Step 2:

[1732] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[1733] Step 3:

[1734] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[1735] Step 4:

[1736] The server sends the generated download link to the user's terminal.

[1737] Step 5:

[1738] The user clicks the download link to download the learning material data.

[1739] Feedback collection

[1740] Step 1:

[1741] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[1742] Step 2:

[1743] The terminal transmits the input feedback to the server.

[1744] Step 3:

[1745] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, etc.).

[1746] Step 4:

[1747] The server periodically analyzes the collected feedback and uses it to generate the next learning material, thereby continuously improving the quality of the learning material.

[1748] As described above, this system efficiently generates and distributes teaching materials that meet the individual needs of users, and by incorporating user feedback, it is possible to improve the quality of the teaching materials.

[1749] Example 1

[1750] 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."

[1751] Conventional online education systems have difficulty responding to individual learning needs because they are unable to generate learning materials quickly and accurately in response to user requests. It is also difficult to improve the quality of learning materials by incorporating user feedback, preventing maximum learning effectiveness.

[1752] 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.

[1753] In this invention, the server includes means for storing registration information received from users in a database, means for receiving learning material requests from users, means for generating learning materials based on the user requests using a generative AI model, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, and means for reflecting the collected feedback in the generation of the next learning material. This makes it possible to provide appropriate learning materials that meet the individual learning needs of users and to improve the quality of the learning materials by reflecting the feedback.

[1754] "User" refers to a person who uses the system to perform operations such as registration, requests, downloads, and feedback.

[1755] "Server" refers to the central processing unit that processes data received from users, stores it in a database, generates teaching materials through AI models, and notifies and distributes them to users.

[1756] "Database" refers to a system that systematically stores and manages data such as user registration information, request details, generated learning materials, and collected feedback.

[1757] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates optimal teaching materials based on user requests.

[1758] "Teaching materials" refers to learning materials and educational content created to meet the learning needs of users.

[1759] "Feedback" refers to the evaluation and suggestions for improvement provided by the user regarding the educational materials used.

[1760] A "request" refers to a request made by a user to the system regarding the content and format of the educational material desired by the user.

[1761] "Notification" refers to the act of a system conveying information to a user by means of email, screen display, or other means.

[1762] "Download Request" refers to a request made by a User to save generated educational materials to their own device.

[1763] "Storage" refers to the act of keeping data or information in a database or storage so that it can be accessed later.

[1764] The system of the present invention allows users to request individually optimized learning materials online and improve the quality of the learning materials based on the user's feedback. The system's main components are the user, a terminal, and a server.

[1765] User Registration

[1766] First, a user accesses the system and enters the required information such as name, email address, and password into the new registration form. The terminal then converts this input information into JSON format and sends it to the server as an HTTP POST request. The server parses the received data and saves it in a database (e.g., MySQL or PostgreSQL). After saving is complete, the server uses an email sending library (e.g., SMTP or SendGrid) to send a registration completion notification to the user.

[1767] Request teaching materials

[1768] After logging in to the system, the user enters the necessary information into a request form for teaching materials based on the desired grade and topic. The device then converts this information back into JSON format and sends it to the server as an HTTP POST request. The server parses the received request data, creates a prompt for the generative AI model (e.g., GPT-4), and sends the request. An example of a prompt is, "Please generate teaching materials related to linear equations in mathematics for second-year junior high school students."

[1769] Teaching material generation

[1770] The generative AI model generates optimal learning materials based on prompts received from the server. For example, it generates learning materials that include example problems and explanations for linear equations in mathematics for second-year junior high school students. The generated learning materials are saved in a database by the server, and once saved, the server sends a notification to the user that the learning materials are complete.

[1771] Teaching material distribution

[1772] When a user receives a notification that the teaching materials are complete, they click the link in the notification to access the materials download page. When the user clicks the "Download" button, the device sends a download request to the server. The server retrieves the teaching materials data from the database and sends it to the user's device as an HTTP response. This allows the user to download the teaching materials to their device.

[1773] Feedback collection

[1774] After using the learning materials, the user enters their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request. The server stores the received feedback data in a database and reflects it the next time learning materials are generated.

[1775] Specific examples

[1776] A junior high school student, Mr. A, registers and requests "teaching materials related to linear equations" for "second-year junior high school mathematics." The device sends the request to the server, which then sends a prompt to the generative AI model saying, "Please generate teaching materials related to linear equations." The generated teaching materials are saved in the database, and the user is notified that the teaching materials are complete. Mr. A receives the notification, downloads and uses the teaching materials, and then sends feedback saying, "It's easy to understand, but I'd like more example problems." The device sends the feedback to the server, which saves it in the database and reflects it in the next teaching material generation.

[1777] This system enables the rapid provision of individually optimized learning materials tailored to the user's learning needs, and also makes it possible to continuously improve the quality of the learning materials by utilizing user feedback.

[1778] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1779] Step 1: User Registration

[1780] A user accesses the system's new registration page and enters the required information, including name, email address, and password, into the form. The terminal converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1781] Input: User's name, email address, and password

[1782] Output: HTTP POST request to the server

[1783] Specific operation: The device converts the input content of the HTML form into JSON using JavaScript and sends a POST request to the server's API endpoint.

[1784] Step 2: Processing and database storage of registration information

[1785] The server parses the received JSON data, verifies its validity, and then stores the user information in a database (e.g., MySQL or PostgreSQL).

[1786] Input: JSON data sent from the terminal

[1787] Output: Save user information to database

[1788] What happens: The server validates the data and then saves it to the database using an SQL query.

[1789] Step 3: Sending a registration completion notice

[1790] The server sends a registration completion email to the user. Using an email sending library (e.g., SMTP or SendGrid), a registration completion notification is sent to the user's email address.

[1791] Input: The fact that registration information was saved, the user's email address

[1792] Output: Registration completion notification email sent to user

[1793] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[1794] Step 4: Complete and submit your materials request

[1795] A user logs in and enters the necessary information into a request form for the desired teaching materials based on grade level and topic. The device converts the input data into JSON format and sends it to the server as an HTTP POST request.

[1796] Input: Grade level, topic, and details of the desired teaching materials

[1797] Output: HTTP POST request to the server

[1798] Specific operation: The device converts the input content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[1799] Step 5: Process the request data and teach the AI ​​model

[1800] The server parses the received request data, checks the contents, and creates a prompt to the generative AI model (e.g., GPT-4) and sends the request.

[1801] Input: Request data sent from the terminal

[1802] Output: The prompt to send to the generative AI model

[1803] Specific operation: The server parses the request data, generates a prompt sentence, and sends it to the AI ​​model.

[1804] Step 6: Creating and saving teaching materials

[1805] The generative AI model generates teaching materials based on the prompts received from the server, which then receives the teaching material data and stores it in a database.

[1806] Input: The prompt sent to the generative AI model

[1807] Output: Teaching material data stored in the database

[1808] Specific operation: The AI ​​model generates teaching material data, the server receives it, and stores it in a database using an SQL query.

[1809] Step 7: Sending notification of completion of materials

[1810] The server notifies the user that the learning material is complete. An email containing a link to the completed learning material is sent to the user using the email sending library.

[1811] Input: Generated teaching material data, user email address

[1812] Output: Email to user notifying them of completion of the teaching material

[1813] Specific operation: The server uses the email sending library to generate a template email and send it to the user.

[1814] Step 8: Request download of materials

[1815] The user clicks the link in the completion notification email to access the download page. When the user clicks the "Download" button, the device sends a download request to the server.

[1816] Input: User download request

[1817] Output: HTTP GET request to the server

[1818] Specific operation: The device detects user operation and sends a GET request to the server's API endpoint.

[1819] Step 9: Submit the teaching materials data

[1820] The server retrieves the teaching material data from the database and sends it to the user's terminal as an HTTP response.

[1821] Input: Download request received from user

[1822] Output: Sending educational material data to the user's device

[1823] Specific operation: The server retrieves the teaching material data using an SQL query and sends it to the terminal as an HTTP response.

[1824] Step 10: Submitting feedback input

[1825] After using the learning materials, users enter their impressions and suggestions for improvement in a feedback form. The device converts the feedback data into JSON format and sends it to the server as an HTTP POST request.

[1826] Input: User feedback

[1827] Output: HTTP POST request to the server

[1828] Specific operation: The terminal converts the feedback content of the HTML form into JSON and sends a POST request to the server's API endpoint.

[1829] Step 11: Save and incorporate feedback

[1830] The server parses the received feedback data, stores it in a database, and instructs the AI ​​model to reflect that feedback the next time it generates teaching materials.

[1831] Input: Feedback data submitted by the user

[1832] Output: Save feedback to the database and instruct the AI ​​model to reflect the feedback

[1833] Specific operation: The server analyzes the feedback data, stores it in a database using an SQL query, and processes it so that it is reflected in the next prompt sentence for the AI ​​model.

[1834] These are the processing steps of the system. By generating individual learning materials based on user requests and incorporating feedback, learning materials optimized for learning needs are provided.

[1835] (Application example 1)

[1836] 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."

[1837] Conventional online learning systems take time for users to receive individually optimized learning materials, which does not sufficiently improve learning efficiency. Furthermore, they lack real-time learning support using smart devices and do not sufficiently consider user convenience. Therefore, there is a need for a method to optimize users' learning experience in real time and quickly respond to individual needs.

[1838] 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.

[1839] In this invention, the server includes means for storing registration information received from a user in a database, means for receiving a learning material request from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing it in a database, means for providing optimized learning materials in real time using a smart device, and means for analyzing the user's voice commands or gesture inputs, thereby making it possible to provide individually optimized learning materials to the user in real time and improve learning efficiency.

[1840] The "means for storing registration information received from a user in a database" refers to a method or device for recording personal information and other registration information provided by a user in a database on the server side.

[1841] The "means for receiving a learning material request from a user" refers to an interface or method by which a user specifies the content and requirements of the learning material desired by the user to the system.

[1842] "Means for generating teaching materials based on user requests using artificial intelligence" refers to a method or device for creating teaching materials that are optimal for specified conditions using an artificial intelligence algorithm in response to a user's request for teaching materials.

[1843] The "means for storing the generated teaching materials in a database and notifying the user" refers to a means for recording the generated teaching materials in a database and notifying the user about it.

[1844] The "means for delivering educational materials when a user makes a download request" refers to a method or device for transmitting educational materials to a user's terminal when the user requests the download of the educational materials.

[1845] The "means for collecting user feedback and storing it in a database" refers to a method or device for collecting opinions and evaluations provided by users after use and recording them in a database.

[1846] "Means for providing optimized educational materials in real time using a smart device" refers to a method or apparatus for providing users with educational materials that are optimized on the spot through a smart device such as a smartphone or smart glasses.

[1847] "Means for analyzing user voice commands or gesture inputs" refers to a method or device for interpreting the content of user voice or gesture instructions and executing an action in response to them.

[1848] The system of the present invention allows users to quickly obtain individually optimized learning materials online and study them in real time through their smart devices. The components of this system and their detailed program processing are described below.

[1849] System configuration

[1850] 1. User Registration

[1851] Device: Smart device (e.g. smartphone, smart glasses)

[1852] Server: A central server for storing registration information (such as name, email address, and password) in a database.

[1853] Software: Speech recognition engine (e.g. Google Cloud Speech-to-Text API)

[1854] 2. Request for teaching materials

[1855] Terminal: An interface where users can make requests via voice commands or touch gestures.

[1856] Server: Receives the request and saves it in the database

[1857] Software: Natural Language Processing (NLP) engine (e.g., Google Cloud Natural Language API)

[1858] 3. Teaching material generation

[1859] Server: Generates educational materials using artificial intelligence based on user requests

[1860] Software: Generative AI models (e.g., OpenAI GPT-4)

[1861] 4. Teaching material distribution

[1862] Device: Receive notifications of educational material distribution and send download requests

[1863] Server: Deliver learning materials when a user makes a download request

[1864] Software: Cloud storage (e.g. Google Cloud Storage)

[1865] 5. Feedback Collection

[1866] On your device: Enter feedback using voice commands or touch gestures

[1867] Server: Receives feedback and stores it in a database

[1868] Software: Speech recognition engine, NLP engine

[1869] Program processing

[1870] User Registration

[1871] The user provides registration information by voice input using a smart device. This information is converted into text by a voice recognition engine and sent to the server. The server stores this registration information in a database and sends a notification to the user that registration is complete.

[1872] Request teaching materials

[1873] Users request learning materials using voice commands or touch gestures. The voice data is analyzed by an NLP engine, and the request is sent in text format to the server. The server then passes the request to an AI model to generate learning materials.

[1874] Teaching material generation

[1875] The server uses a generative AI model to generate optimal learning materials based on the user's request. For example, if a user requests "learning materials on linear equations for second-year junior high school mathematics," the AI ​​model will create the learning materials. The generated learning materials are stored in a database.

[1876] Teaching material distribution

[1877] Once the learning materials are generated, the user is notified. The user then sends a download request from their smart device, and the server sends the learning materials data to the device.

[1878] Feedback collection

[1879] After using the learning materials, users can input feedback using voice commands or touch gestures. The feedback is analyzed by a speech recognition engine and an NLP engine and sent to the server in text format. The server stores this in a database and reflects it in the next generation of learning materials.

[1880] Specific examples

[1881] Prompt Sentence Examples

[1882] Material Request:

[1883] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[1884] feedback:

[1885] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[1886] This system quickly provides specific learning materials that meet the user's learning needs and utilizes user feedback to continuously improve its quality, thereby maximizing learning effectiveness and providing efficient learning support.

[1887] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1888] Step 1:

[1889] The user provides registration information using a smart device.

[1890] Specifically, the user uses voice input to input information such as name, email address, and password into the terminal.

[1891] The input data is audio data.

[1892] The device converts the voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API).

[1893] Step 2:

[1894] The terminal transmits the converted text data to the server.

[1895] The data to be transmitted is text data.

[1896] The server receives this text data and stores it in a database.

[1897] The server will send an email to the user notifying them of the completion of registration.

[1898] The output data is an email notifying the completion of registration.

[1899] Step 3:

[1900] Users can request educational materials using their smart devices.

[1901] Specifically, the user inputs a request for teaching materials according to grade level or topic using voice commands or touch gestures.

[1902] The input data is voice data or gesture data.

[1903] The device converts the voice data into text data using a speech recognition engine and analyzes the request using an NLP engine (e.g., Google Cloud Natural Language API).

[1904] The parsed text data is sent to the server.

[1905] Step 4:

[1906] The server receives the requested text data and generates optimal teaching materials using a generative AI model (e.g., OpenAI GPT-4).

[1907] The input data is the text data of the request.

[1908] The generated teaching materials are output in multiple data formats, including text, images, graphs, etc.

[1909] The server stores the generated teaching material data in a database and notifies the user that the teaching material has been completed.

[1910] Step 5:

[1911] The user receives a notification that the teaching material is complete and sends a download request using a smart device.

[1912] The input data is a download request sent from the terminal.

[1913] The terminal sends a request to the server, which provides a download link to the user.

[1914] The output data is a download link.

[1915] Step 6:

[1916] Users click on the download link from their smart device to obtain the learning materials.

[1917] The data to be input is the click operation of the user.

[1918] The server transmits the educational material data to the terminal, and the user is then able to use the educational material.

[1919] The output data is teaching material data.

[1920] Step 7:

[1921] Users provide feedback on the learning material using their smart devices.

[1922] Specifically, the user inputs feedback using voice commands or touch gestures.

[1923] The input data is voice data or gesture data.

[1924] The device converts the voice data into text data using a voice recognition engine, analyzes it using an NLP engine, and then sends it to the server.

[1925] The server stores the received feedback in a database and reflects it in the next generation of teaching materials.

[1926] Specific examples

[1927] Prompt Sentence Examples

[1928] Material Request:

[1929] Prompt: "I'd like to know more about how to solve math equations, can you give me some more examples?"

[1930] feedback:

[1931] Prompt: "The material was very easy to understand, but I'd like some more graph examples."

[1932] Through the above processing steps, users can obtain optimized learning materials in real time, and a system that can quickly respond to individual needs is realized.

[1933] 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.

[1934] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[1935] User Registration

[1936] 1. A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form.

[1937] 2. The terminal sends the entered information to the server.

[1938] 3. The server stores the received registration information in a database and also sends the user an email notifying them of the completion of registration.

[1939] Request teaching materials

[1940] 1. The user logs in and fills out a request form for the desired teaching materials based on grade level and topic.

[1941] 2. The terminal sends the user's request to the server.

[1942] 3. The server uses the emotion engine based on the received request to determine the user's emotion.

[1943] Emotion recognition by emotion engine

[1944] 1. The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[1945] 2. The server issues instructions to the AI ​​based on the user's emotional state and generates teaching materials optimized for the user's emotions.

[1946] Teaching material generation

[1947] 1. The server issues instructions to the generative AI to generate learning materials appropriate for the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data.

[1948] 2. The server stores the generated teaching materials in a database and notifies the user.

[1949] Teaching material distribution

[1950] 1. The user receives a notification that the materials are complete and clicks the link to request a download.

[1951] 2. The terminal sends a download request to the server. This request includes the user ID and the learning material ID.

[1952] 3. The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[1953] 4. The server sends the generated download link to the user's device.

[1954] 5. The user clicks the download link to download the teaching material data.

[1955] Feedback collection

[1956] 1. After using the learning materials, the user opens the feedback form and enters feedback such as an evaluation and areas for improvement.

[1957] 2. The terminal sends the feedback information to the server.

[1958] 3. The server stores the received feedback in a database, which may include emotional data during training.

[1959] 4. The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[1960] Specific examples

[1961] Case 1: A request for math materials for eighth grade students

[1962] 1. User: A junior high school student registers and logs into the system.

[1963] 2. User: Requests "teaching materials on linear equations" for "second year junior high school mathematics."

[1964] 3. Terminal: Sends the request to the server.

[1965] 4. Server: Based on the request content, the emotion engine evaluates the user's emotional state.

[1966] 5. Server: Based on the emotional data, the AI ​​is instructed to generate educational materials on "linear equations." For example, if the user is tired, the AI ​​will increase the number of examples to make it easier to understand.

[1967] 6. Server: Stores the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[1968] 7. User: Receive notifications and download materials.

[1969] 8. Device: Sends download request to server.

[1970] 9. Server: Sends the teaching material data to the terminal and the user downloads it.

[1971] 10. User: After using the teaching materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the study.

[1972] 11. Device: Send feedback to the server.

[1973] 12. Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[1974] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[1975] The processing flow will be explained below.

[1976] User Registration

[1977] Step 1:

[1978] A user accesses the system and enters the required information such as name, email address, and password into the new registration form.

[1979] Step 2:

[1980] The terminal sends the entered user information to the server. The data is transmitted securely using a secure communication protocol (e.g., HTTPS).

[1981] Step 3:

[1982] The server stores the received user information in a database, where the information is protected using appropriate encryption technology.

[1983] Step 4:

[1984] The server generates a notification of the completion of registration and sends a notification email to the specified email address.

[1985] Request teaching materials

[1986] Step 1:

[1987] Users log in to the system and fill out a request form for the teaching materials they want based on grade level and topic.

[1988] Step 2:

[1989] The terminal sends the user's desired content to the server. The content sent also includes the user ID, making it possible to identify which user made the request.

[1990] Step 3:

[1991] The server analyzes the received request and prepares to pass the request to the generative AI.

[1992] Emotion recognition by emotion engine

[1993] Step 1:

[1994] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state, including input speed, error rate, and facial expression recognition data (using camera input).

[1995] Step 2:

[1996] The server issues instructions to the AI ​​based on the user's emotional state and configures it to generate teaching materials optimized for the user's emotions.

[1997] Teaching material generation

[1998] Step 1:

[1999] The server issues instructions to the generative AI to generate teaching materials according to the specified grade and topic. For example, if it determines that the user is tired, it will adjust the difficulty level to a lower level.

[2000] Step 2:

[2001] The server stores the generated learning materials in a database, along with the learning materials' metadata (such as the creation date, associated tags, and emotional state).

[2002] Step 3:

[2003] The server sends an email to the user notifying them that the educational material is ready.

[2004] Teaching material distribution

[2005] Step 1:

[2006] The user receives a notification that the materials are complete and clicks on the link to request a download.

[2007] Step 2:

[2008] The terminal sends a download request to the server, which includes the user ID and the learning material ID.

[2009] Step 3:

[2010] The server retrieves the teaching material data corresponding to the teaching material ID from the database and generates a download link.

[2011] Step 4:

[2012] The server sends the generated download link to the user's terminal.

[2013] Step 5:

[2014] The user clicks the download link to download the learning material data.

[2015] Feedback collection

[2016] Step 1:

[2017] After using the learning materials, the user opens the feedback form in the system and enters feedback such as an evaluation and areas for improvement.

[2018] Step 2:

[2019] The terminal transmits the input feedback to the server.

[2020] Step 3:

[2021] The server stores the received feedback in a database, along with the feedback metadata (user ID, learning material ID, date and time, emotional state, etc.).

[2022] Step 4:

[2023] The server periodically analyzes the collected feedback and sentiment data and uses it to generate the next learning material, thereby continuously improving the quality of the learning material and the user's learning experience.

[2024] Specific examples

[2025] Case 1: A request for math materials for eighth grade students

[2026] Step 1:

[2027] User: A junior high school student registers and logs into the system.

[2028] Step 2:

[2029] User: Requests "teaching materials on linear equations" for "8th grade mathematics."

[2030] Step 3:

[2031] Terminal: Sends the request to the server.

[2032] Step 4:

[2033] Server: Based on the request content, the emotion engine evaluates the user's emotional state. For example, it detects if the user is showing signs of impatience or fatigue when making a request.

[2034] Step 5:

[2035] Server: Based on the emotional data, the AI ​​is instructed to generate teaching materials on "linear equations." If the user is tired, the AI ​​will provide more examples and more detailed explanations.

[2036] Step 6:

[2037] Server: Saves the generated teaching materials in a database and notifies the user when the teaching materials are complete.

[2038] Step 7:

[2039] Users: Receive notifications and download learning materials.

[2040] Step 8:

[2041] Device: Sends a download request to the server.

[2042] Step 9:

[2043] Server: Sends educational material data to the terminal and users download it.

[2044] Step 10:

[2045] User: After using the learning materials, the user enters feedback such as, "It's easy to understand, but I'd like more examples." The user also submits emotional data (e.g., how relaxed they were) during the learning process.

[2046] Step 11:

[2047] Device: Send feedback to the server.

[2048] Step 12:

[2049] Server: The feedback and emotion data are stored in a database and reflected in the next generation of teaching materials.

[2050] This system provides learning materials optimized according to the user's emotional state and continuously improves the quality of the materials based on collected feedback and emotional data, thereby achieving more effective learning support.

[2051] Example 2

[2052] 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."

[2053] Conventional online learning systems do not provide learning materials that take into account the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to improve the quality of learning materials based on feedback, making it difficult to continuously improve the learning experience.

[2054] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2055] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for analyzing the user's emotions using an emotion engine, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, and means for collecting user feedback, storing it in a database, and analyzing it. This makes it possible to provide learning materials optimized according to the user's emotional state and to continuously improve the quality of the learning materials by utilizing the collected feedback and emotion data.

[2056] "Registration Information" refers to personal information that a User provides when accessing the System, including name, email address, password, etc.

[2057] A "material request" is a request made by a user to the system for material related to a particular grade or topic.

[2058] An "emotion engine" is a technology that analyzes a user's input data, usage status, facial expression recognition data, etc. to evaluate their emotional state.

[2059] "Artificial intelligence" is a type of computational technology that generates optimized learning materials based on the user's requests and emotional state.

[2060] The "database" is an information management system that centrally stores and manages data such as registration information, teaching materials, and feedback within the system.

[2061] "Feedback" refers to information about evaluations and improvements provided by users after using educational materials.

[2062] The present invention is a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. Specific program processing and operation of this system are described below.

[2063] User Registration

[2064] First, the user accesses the system's web page and enters the required information, such as name, email address, and password, into the new registration form. The information entered by the user is sent from the terminal to the server using the HTTPS protocol. The server stores the received registration information in a database such as MySQL and sends a registration completion notification to the user's email address. This process is carried out using PHP or Python scripts.

[2065] Request teaching materials

[2066] Next, the user logs into the system and fills out a request form for the desired teaching materials based on grade level and topic. The request is sent from the terminal to the server, and the server uses an emotion engine to evaluate the user's emotional state based on the received request. The emotion engine uses input speed, error rate, facial expression recognition data, etc.

[2067] Emotion recognition by emotion engine

[2068] The server collects emotional data from user input, usage, camera input, etc. This data is input into an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), which then makes an API call to evaluate the emotional data. As a result, the server conveys the user's emotional state to the AI.

[2069] Teaching material generation

[2070] Based on the received emotional data, the server issues instructions to a generative AI (e.g., GPT-4) to generate learning materials appropriate for the specified grade and topic. During this process, the difficulty and content of the learning materials are adjusted based on the user's emotional state. The generated learning materials are stored in a database and notified to the user. As a specific example, if the user is "tired," the AI ​​is instructed to increase the number of example questions to make the material easier to understand.

[2071] Example prompt sentence:

[2072] If the grade level is "8th grade," the topic is "linear equations," and the emotional state is "tired," then: "Create teaching materials for 8th grade linear equations with more examples that are easy to understand for users who are tired."

[2073] Teaching material distribution

[2074] When the user receives notification that the teaching materials are complete, they click a link to request a download of the materials. The device sends a download request including the user ID and teaching material ID to the server. The server retrieves the teaching material data from the database, generates a temporary download link, and sends it to the user's device. The user clicks the link to download the teaching material data.

[2075] Feedback collection

[2076] After using the learning materials, users enter their evaluation and suggestions for improvement in a feedback form. This feedback information is sent from the device to the server, which stores the information in a database. The feedback may also include emotional data from the learning process. The server analyzes the collected feedback and emotional data and reflects this in the next generation of learning materials, thereby continuously improving the quality of the learning materials and the user's learning experience.

[2077] The above is a specific embodiment of the system of the present invention. By providing learning materials optimized according to the user's emotional state and continuously improving the quality of the learning materials based on feedback and emotional data, more effective learning support is realized.

[2078] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2079] Specific processing steps

[2080] Step 1: User Registration

[2081] Input: Registration information such as user name, email address, and password

[2082] The terminal sends this information using the HTTPS protocol to be stored on the server.

[2083] The server stores the received registration information in a database.

[2084] Output: A notification email is sent to the user notifying them of successful registration.

[2085] Specific operation: The user enters information into a form on a web page and clicks the "Register" button. The device sends this information to the server, which stores it in a database using a PHP or Python script and sends a confirmation email via the SMTP protocol.

[2086] Step 2: Log in and complete the request form

[2087] Input: User login information (email address, password), grade and topic information of the requested teaching material

[2088] The server receives this and authenticates the user.

[2089] Output: The request is sent to the server.

[2090] Specific operation: The user enters authentication information on the login screen and clicks the "Login" button. Then, the user fills in details such as grade and topic in the request form and clicks the "Submit" button. The device then sends this information to the server.

[2091] Step 3: Emotion analysis using the emotion engine

[2092] Input: User request content, input speed, error rate, facial expression recognition data (using camera input)

[2093] The server passes this data to the emotion engine and makes an API call, which analyzes the emotional state and returns the results to the server.

[2094] Output: Emotional state data

[2095] Specific operation: The server collects input data, calls an emotion engine (e.g., Microsoft Azure's Face API or IBM Watson's Emotion Analysis), and receives analysis results from the API.

[2096] Step 4: Generating teaching materials using generative AI models

[2097] Input: Request information, emotional state data

[2098] The server passes the prompt to a generative AI model (e.g., GPT-4) to generate learning materials based on the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the emotional data.

[2099] Output: Generated teaching materials

[2100] Specific operation: The server inputs a prompt into the AI ​​model and retrieves the generated teaching material data. An example of a prompt is: "Please create teaching materials for second-year junior high school students about linear equations with more easy-to-understand examples for users who are tired."

[2101] Step 5: Save and notify the material

[2102] Input: Generated teaching material data

[2103] The server stores this data in a database and notifies the user when the learning material is complete.

[2104] Output: Saving teaching material data, sending notification emails

[2105] Specific operation: The generated teaching materials are stored in a database and a notification email is sent to the user via the SMTP protocol.

[2106] Step 6: Request to download materials

[2107] Input: User ID, learning material ID

[2108] The terminal sends a request containing this information to the server.

[2109] The server retrieves the learning material data from the database and generates a download link.

[2110] Output: Generate and send a download link

[2111] Specific operation: The user clicks the link in the email and opens the learning material page in a browser. A request is sent from the device to the server, and the server generates a download link and sends it back to the device.

[2112] Step 7: Complete and submit the feedback form

[2113] Input: User feedback, emotional data during training

[2114] The terminal transmits this information to the server.

[2115] The server stores the received feedback in a database and periodically analyzes it.

[2116] Output: Save feedback data and analysis results

[2117] Specific operation: The user opens the feedback form and enters their opinions and thoughts. The device sends this to the server, which stores it in a database. The feedback and emotion data are then analyzed and reflected in the next generation of teaching materials.

[2118] Through the above processing steps, a system is realized that provides optimal learning materials that reflect the user's emotional state and feedback, thereby enabling more effective learning support.

[2119] (Application example 2)

[2120] 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."

[2121] While conventional online learning systems can provide learning materials based on a user's learning progress and level of understanding, they have limitations in providing learning materials that take into account the user's emotional state and psychological burden. This has led to problems such as reduced learning efficiency and satisfaction. Furthermore, there has been no established method for efficiently incorporating collected feedback to improve the quality of learning materials.

[2122] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2123] In this invention, the server includes means for storing registration information received from the user in a database, means for receiving learning material requests from the user, means for generating learning materials based on the user's request using artificial intelligence, means for storing the generated learning materials in a database and notifying the user, means for delivering the learning materials when the user makes a download request, means for collecting user feedback and storing the feedback in a database, and means for adjusting the difficulty and content of the learning materials based on the user's emotional state using an emotion engine for analyzing the user's emotional data. This makes it possible to provide optimal learning materials according to the user's emotional state and improve learning efficiency and satisfaction. It is also possible to continuously improve the quality of the learning materials using the collected feedback and emotion data.

[2124] "User" refers to an individual who utilizes the system to request learning materials and study.

[2125] "Registration Information" refers to personal information such as name, email address, and password provided by a User when accessing the System.

[2126] "Database" refers to a system that systematically stores and manages data such as user registration information, teaching materials, and feedback.

[2127] "Teaching material request" refers to the act of requesting the system for the content of teaching materials needed based on the grade and topic specified by the user.

[2128] "Artificial intelligence" refers to a computer system that can learn from large amounts of data, recognize patterns, and make decisions like a human.

[2129] "Learning material generation" refers to the process by which artificial intelligence automatically creates learning materials based on user requests.

[2130] "Notification" refers to a communication means for informing the user that the educational material has been generated or that preparation for distribution has been completed.

[2131] "Download request" refers to a request made by a user to receive educational materials online.

[2132] "Feedback" refers to information such as evaluations and improvements provided by users after they have used the learning materials.

[2133] An "emotion engine" refers to software that analyzes a user's input speed, facial expression recognition data, etc., to evaluate the user's emotional state.

[2134] "Emotional data" refers to data that reflects the user's psychological state and emotions.

[2135] "Optimization" refers to the act of adjusting the difficulty and content of learning materials to improve users' learning efficiency and satisfaction.

[2136] "Quality improvement" refers to the process of continuously improving the content and structure of learning materials based on collected feedback and sentiment data.

[2137] MODE FOR CARRYING OUT THE INVENTION

[2138] The present invention provides a system that allows users to request individually optimized learning materials online, provide feedback, and improve the quality of learning materials by recognizing and adjusting the user's emotions. A specific embodiment of this system will be described.

[2139] System Configuration

[2140] Hardware

[2141] User devices such as smartphones, tablets, and personal computers

[2142] Camera (for facial expression recognition)

[2143] Server (data processing, storage, teaching material generation)

[2144] software

[2145] Emotion engine (e.g. Microsoft Azure Face API)

[2146] Generative AI (e.g. OpenAI GPT-3)

[2147] Database system (e.g. MySQL)

[2148] Communication interface (e.g. HTTP API)

[2149] What the program does

[2150] User Registration

[2151] A user accesses the system and enters the required information (name, email address, password, etc.) into the new registration form. The terminal sends the entered information to the server, which stores it in a database. A notification of registration completion is also sent to the user by email.

[2152] Request teaching materials

[2153] Users log in and request the learning materials they want based on their grade level and topic. The device sends the user's request to the server, which then uses an emotion engine to determine the user's emotion based on the received request.

[2154] Emotion recognition by emotion engine

[2155] The server obtains emotional data from the user's input and usage, and uses an emotion engine to evaluate the user's emotional state. This evaluation includes input speed, error rate, and facial expression recognition data (using camera input). Based on the emotional state, the server issues instructions to the AI ​​to generate learning materials optimized for the user's emotions.

[2156] Teaching material generation

[2157] The server issues instructions to the generative AI, which generates learning materials according to the specified grade and topic. The difficulty and content of the learning materials are adjusted based on the user's emotional data. For example, if the user is tired, the system will increase the number of example questions to make it easier to understand.

[2158] Teaching material distribution

[2159] The generated teaching materials are saved in a database and notified to the user. The user receives the notification that the teaching materials are complete and clicks a link to request a download of the materials. The device sends a download request to the server, and the server sends the teaching material data to the device. The user clicks the download link to download the teaching material data.

[2160] Feedback collection

[2161] After using the learning materials, the user opens a feedback form and enters feedback such as an evaluation and areas for improvement. The device sends the feedback information to the server, which then stores the received feedback in a database. The feedback may also include emotional data from the learning process. The collected feedback and emotional data are used to generate the next learning material.

[2162] Specific examples

[2163] Example 1: Request for math materials for 8th grade students

[2164] 1. User: A middle school student requests learning materials on "8th Grade Math - Linear Equations."

[2165] 2. Server: Evaluate the user's emotional state using the emotion engine and determine that the user is tired.

[2166] 3. Server: Based on the emotion data, the generative AI is instructed to generate teaching materials related to "linear equations." For example, if the user is tired, the server increases the number of example problems to make the material easier to understand.

[2167] 4. Example prompt for generative AI model:

[2168] "Please create teaching materials on linear equations for second-year junior high school students. Since the target users are feeling fatigued, please increase the number of examples and make the questions easier. Also, please use many illustrations and diagrams to improve comprehension."

[2169] 5. User: Receives and downloads the generated learning materials.

[2170] 6. User: Provide feedback after using the learning materials and also send emotional data about the learning experience.

[2171] This invention allows for the provision of learning materials that take into account the user's emotional state, significantly improving learning efficiency and satisfaction. Furthermore, the quality of the learning materials can be continuously improved based on the collected feedback and emotional data.

[2172] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2173] Step 1:

[2174] The user enters registration information

[2175] A user accesses the system and enters information such as name, email address, and password into the new registration form. The terminal sends this input data to the server. The server saves the received registration information in a database and sends a notification of registration completion to the user by email. Here, the input is "registration information" and the output is "saving to the database" and "sending a notification e...

Claims

1. means for storing registration information received from users in a database; means for receiving educational material requests from users; means for generating educational materials based on user requests using artificial intelligence; A means for storing the generated teaching materials in a database and notifying the user; a means for delivering the educational materials when a user makes a download request; a means for collecting and storing user feedback in a database; A system including:

2. 2. The system according to claim 1, wherein the teaching materials generated based on the user's request are optimized for each grade and topic.

3. 10. The system of claim 1, wherein the system utilizes collected user feedback to continuously improve the quality of the generated educational materials.

Images