System

Abstract

A system is provided.SOLUTION: An online tutoring system for providing learning assistance to a student using a generative AI model, the system comprising: means for receiving a learning request of the student; means for generating learning content using the generative AI model; means for providing the generated learning content to the student; means for monitoring learning progress of the student; means for generating feedback; and means for providing the generated feedback to the student.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 recent years, educational disparities have been recognized as a social problem. These disparities arise from the fact that some students are unable to receive high-quality learning support due to geographical or economic constraints. In particular, students from rural areas or economically disadvantaged families are placed in an unfair situation in terms of learning opportunities. To address these issues, there is a need for methods to provide low-cost, high-quality educational support. [Means for solving the problem]

[0005] The present invention relates to an online tutoring system that uses a generative AI model to provide learning support to students. The system includes a means for receiving a student's learning request, a means for generating learning content using a generative AI model, a means for providing the generated learning content to the student, a means for monitoring the student's learning progress, a means for analyzing the student's learning progress data and generating feedback, and a means for providing the generated feedback to the student. The system also includes a means for authenticating students and is accessible via the Internet, regardless of geographical location. This overcomes economic and geographical constraints, allowing many students to receive high-quality learning support equitably.

[0006] "Generative AI models" refer to artificial intelligence algorithms and machine learning models used to provide learning support to students.

[0007] An "online tutoring system" refers to a system that provides remote learning support via the Internet.

[0008] A "learning request" is a request by a student for assistance with a specific learning topic or subject.

[0009] "Learning content" refers to educational materials such as teaching materials, exercises, and explanatory materials generated by generative AI models.

[0010] "Learning progress" refers to the level of understanding and progress a student achieves through learning activities.

[0011] "Monitoring" refers to the continuous observation and recording of students' learning activities.

[0012] "Analysis" refers to the process of analyzing collected data and drawing specific conclusions or feedback.

[0013] "Feedback" refers to advice and evaluations provided to students based on the analysis results.

[0014] "Authentication" refers to the process of verifying that a user is legitimate when accessing a system. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention relates to an online tutoring system using a generative AI model, which includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, and means for providing the generated feedback to the student.

[0037] System program processing

[0038] The system does the following:

[0039] 1. User Registration

[0040] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[0041] The terminal sends this information to the server via an HTTP POST request.

[0042] The server verifies the information received and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the device.

[0043] The terminal displays a registration complete message to the user.

[0044] 2. Login and Authentication

[0045] The user enters their email address and password on the login page.

[0046] The terminal transmits this information to the server.

[0047] The server performs authentication against the database, and if there is a match, generates an authentication token and returns it to the terminal.

[0048] The device stores the token and remains logged in.

[0049] 3. Start of learning support

[0050] A user requests learning support (e.g., they want to understand a math equation better).

[0051] The terminal transmits the request contents to the server.

[0052] The server uses a generative AI model to generate learning content (e.g., explanations of equations, practice problems) in response to requests.

[0053] The generation AI generates learning materials and questions and returns them to the server.

[0054] The server transmits the generated learning content to the terminal, which displays it to the user.

[0055] 4. Progress monitoring and feedback

[0056] The user solves the practice problems and sends the results (correct or incorrect and time) from the terminal to the server.

[0057] The server analyzes this data and evaluates the user's learning status and level of understanding.

[0058] The server generates feedback using a generative AI model and returns the feedback to the device.

[0059] The terminal displays this feedback to the user.

[0060] Specific examples

[0061] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[0062] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[0063] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[0064] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[0065] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[0066] 5. Hanako Yamada solves the exercises and sends the results from her device to the server. The server analyzes this data and evaluates the user's level of understanding. It generates feedback and returns it to the device. The device displays the feedback to Hanako Yamada.

[0067] In this way, online tutoring systems utilizing generative AI can overcome geographical and economic constraints and provide comprehensive, high-quality learning support.

[0068] The processing flow will be explained below.

[0069] Program processing steps

[0070] Registering Users

[0071] Step 1:

[0072] When a user first accesses the system, a registration form is displayed.

[0073] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[0074] Step 2:

[0075] The terminal sends the entered information to the server via an HTTP POST request.

[0076] Step 3:

[0077] The server validates the information received (checks for required fields, verifies format, etc.).

[0078] Step 4:

[0079] After verification, the server stores the user data in a database and generates a unique user ID.

[0080] Step 5:

[0081] The server returns a registration completion message and the user ID to the terminal.

[0082] Step 6:

[0083] The terminal displays a registration completion message to the user.

[0084] Login and Authentication

[0085] Step 1:

[0086] The user visits the login page and enters their email address and password.

[0087] Step 2:

[0088] The device sends the entered login information to the server via an HTTP POST request.

[0089] Step 3:

[0090] The server checks the user information (email address and password) in its database.

[0091] Step 4:

[0092] If there is a match, the server generates an authentication token and returns it to the terminal.

[0093] Step 5:

[0094] The terminal stores the token and logs the user in.

[0095] Start of learning support

[0096] Step 1:

[0097] A user makes a learning support request (e.g., "8th grade math equations").

[0098] Step 2:

[0099] The terminal sends the request contents to the server using an HTTP POST request.

[0100] Step 3:

[0101] The server checks the request and requests the generative AI model to generate learning content.

[0102] Step 4:

[0103] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[0104] Step 5:

[0105] The generation AI returns the generated learning content to the server.

[0106] Step 6:

[0107] The server transmits the generated learning content to the terminal.

[0108] Step 7:

[0109] The terminal displays the learning content to the user.

[0110] Progress monitoring and feedback

[0111] Step 1:

[0112] The user solves the exercises.

[0113] Step 2:

[0114] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[0115] Step 3:

[0116] The device sends these results to the server via an HTTP POST request.

[0117] Step 4:

[0118] The server analyzes the received data and evaluates the user's learning progress.

[0119] Step 5:

[0120] The server uses the generative AI model to generate feedback to provide to the user.

[0121] Step 6:

[0122] The server transmits the generated feedback to the terminal.

[0123] Step 7:

[0124] The terminal displays the received feedback to the user.

[0125] Example 1

[0126] 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."

[0127] Conventional online tutoring systems have limited ability to respond to individual learning needs, making it difficult to provide appropriate feedback based on students' progress and level of understanding. Furthermore, regional restrictions limit the amount of learning support available. Therefore, there is a need for a system that can respond to individual user needs, monitor progress, and provide appropriate feedback.

[0128] 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.

[0129] In this invention, the server includes: a means for displaying a registration form when a user first accesses the system; a means for receiving and transmitting information entered by the user; a means for verifying the received information, saving it in a database, and generating a unique user ID; a means for authenticating the email address and password entered by the user and generating an authentication token; a means for receiving a user's learning request; a means for generating learning content based on prompts using a generative AI model; a means for providing the generated learning content to the user; a means for monitoring the user's progress and collecting data; a means for analyzing the collected data and generating feedback; and a means for providing the generated feedback to the user. This enables support tailored to the user's individual learning needs, provides appropriate feedback based on the student's progress and level of understanding, and realizes comprehensive learning support that transcends regional constraints.

[0130] "User" refers to an individual who uses this system to receive learning support.

[0131] The "registration form" is an interface for users to enter necessary information when they access the site for the first time.

[0132] The "server" is a central system that manages information from users, runs generative AI models, and connects with databases.

[0133] "Terminal" refers to a device that a user directly operates to input information and receive learning content and feedback.

[0134] A "database" is a system for storing user information, learning content, progress data, etc.

[0135] An "authentication token" is a code generated to authenticate a user's login status and enable the maintenance of a session.

[0136] A "learning request" is a request issued by a user seeking specific learning content or support.

[0137] A "generative AI model" is an algorithm or system that uses machine learning technology to automatically generate learning content and feedback in response to user requests.

[0138] A "prompt" is an instruction given to a generative AI model when generating learning content or feedback.

[0139] "Learning content" refers to educational materials such as explanatory materials and practice questions generated by a generative AI model.

[0140] "Progress data" is information relating to the learning progress and level of understanding that is collected while the user is receiving learning support.

[0141] "Feedback" is information containing learning improvement points and advice generated by the AI ​​model based on progress data.

[0142] This invention relates to an online tutoring system that uses a generative AI model, and provides a specific method for users to receive assistance tailored to their individual learning needs. This system includes a personal computer (terminal), a web server (server), a database, HTTP communication, and a generative AI model (e.g., OpenAI's GPT model), and is implemented as follows:

[0143] Registering Users

[0144] When a user accesses the system for the first time, a registration form is displayed. The user enters their name, email address, password, age, grade, desired subjects, etc. This information is collected by the terminal and sent to the server using an HTTP POST request. The server verifies the received information and stores it in a database (e.g., MySQL). Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user saying "Registration complete."

[0145] Login and Authentication

[0146] The user enters their email address and password on the login page. This information is sent via the device to the server, which checks it against the user information in its database. If it matches, it generates an authentication token (e.g., JSON Web Token, JWT) and returns it to the device. The device stores the token and displays a "Login successful" message to the user.

[0147] Start of learning support

[0148] When a user clicks the "Request Learning Support" button on the dashboard, the device sends the request to the server. The server sends an appropriate prompt to a generative AI model (e.g., OpenAI GPT-4), which then generates learning content (e.g., explanatory materials, practice questions). The generated learning content is sent to the device via the server, and the device displays it to the user.

[0149] Example prompts include:

[0150] "Generate math equation practice problems for eighth graders."

[0151] Progress monitoring and feedback

[0152] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. This data is sent from the device to a server, which analyzes the data. For example, the user's correct answer rate and answer time are calculated. Feedback is generated using a generative AI model and returned from the server to the device. The device displays the feedback to the user.

[0153] This system provides support tailored to each user's individual learning needs, allowing them to receive high-quality learning support without being restricted by geographical location.

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1: Registering a user

[0156] When a user accesses the system for the first time, a registration form is displayed in which they enter their name, email address, password, age, grade, desired subjects, etc.

[0157] The device collects this information and sends it to the server using an HTTP POST request, along with the input data (name, email address, password, age, grade, and desired subjects).

[0158] The server verifies the received information (checks the format of the email address and the strength of the password), and if the verification is successful, it saves the new user information in a database (e.g. MySQL). After saving it in the database, the server generates a unique user ID and returns it to the terminal. The output is the user ID and a success message.

[0159] The terminal displays the message "Registration Complete" to the user, thereby completing the user's registration.

[0160] Step 2: Login and Authentication

[0161] The user enters their email address and password on the login page. The data entered is the email address and password.

[0162] The device sends this information to the server using an HTTP POST request.

[0163] The server checks the user information in its database against the entered information. If the check results match, it generates an authentication token (e.g., JSON Web Token, JWT). The output is the authentication token. If the check results do not match, it generates an error message.

[0164] The server returns an authentication token to the device, which stores it in local storage, allowing session management. The device displays a successful login message to the user and redirects them to the dashboard or home page.

[0165] Step 3: Start learning support

[0166] The user clicks the "Request Learning Support" button on the dashboard. At this time, the user's request (learning content request) becomes the input data.

[0167] The device sends the request content to the server using an HTTP POST request.

[0168] The server generates an appropriate prompt for the generative AI model (e.g., OpenAI GPT-4). This prompt is a sentence such as "Please generate practice problems and explanations for math equations for eighth-grade students." Sending this prompt to the generative AI corresponds to data processing and data calculation.

[0169] The generative AI model generates learning content (e.g., explanatory materials, practice questions) based on the prompts. The output is the generated learning content.

[0170] The generation AI returns the generated learning content to the server, and the server sends the content to the device.

[0171] The terminal displays the learning content to the user.

[0172] Step 4: Progress monitoring and feedback

[0173] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. These results become input data.

[0174] The device sends the results to the server using an HTTP POST request.

[0175] The server analyzes the received data. For example, it calculates the percentage of correct answers and tallys up the answering time. This corresponds to data processing and data calculation.

[0176] Based on this, the server evaluates the user's learning status and level of understanding. Based on the evaluation results, a generative AI model is used to generate feedback. The output is the generated feedback. Specific examples include "advice on how to solve equations" and "additional practice problems."

[0177] The server sends the feedback to the terminal, which displays the feedback to the user.

[0178] (Application example 1)

[0179] 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."

[0180] In today's educational environment, it is difficult for learners in remote locations to receive high-quality learning support, especially in the absence of an environment where individualized instruction can be provided in real time. Furthermore, there is a lack of systems that can efficiently monitor learning progress in virtual classroom environments and provide appropriate feedback in real time. Furthermore, there is a need for a means to provide an interactive educational environment without attending a physical classroom.

[0181] 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.

[0182] In this invention, the server includes means for receiving a learning request from a learner, means for generating learning content using a generative AI model, means for providing the generated learning content to the learner, means for monitoring the learner's progress data in real time during learning activities in a virtual environment, means for providing an interactive virtual classroom environment, and means for allowing the learner to participate in the virtual classroom using a head-mounted display or VR device, thereby enabling real-time monitoring of learning progress and provision of individualized instruction.

[0183] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate appropriate answers or content for specific tasks or questions.

[0184] "Student" means an individual who receives education or learning support through this system.

[0185] A "learning need" is a request by a learner for support or instruction on a particular learning content or topic.

[0186] "Learning content" refers to educational materials such as teaching materials and workbooks that are generated by a generative AI model based on the learner's learning requirements.

[0187] "Progress data" refers to data such as the grades and response times a learner obtains through learning activities.

[0188] "Feedback" refers to information such as advice and comments to learners that is generated by analyzing the learner's progress data.

[0189] A "virtual environment" is a system that uses virtual reality technology to provide an interactive learning environment similar to a physical classroom.

[0190] A "virtual classroom" is a virtual classroom in which learners can participate remotely using head-mounted displays or VR devices.

[0191] "Interactive" refers to the ability of learners to interact with the system in real time.

[0192] A "head-mounted display" is a device worn on the head that displays visual information and is used to provide a VR experience.

[0193] A "VR device" is a hardware device that allows you to experience virtual reality.

[0194] This invention relates to an online tutoring system that uses generative AI models to provide learning support to learners. This system allows learners to access the system via the Internet and receive real-time learning support in a virtual classroom environment.

[0195] Specifically, the system includes the following hardware and software configuration:

[0196] Server: Flask (Python framework), SQLite (database), TensorFlow (generative AI model), Pandas (data analysis)

[0197] Devices: Smartphones, tablets, and head-mounted displays (e.g., Oculus Rift, HTC Vive) used by learners

[0198] Communication method: Internet connection (Wi-Fi or mobile network)

[0199] Program processing

[0200] 1. User Registration:

[0201] When a user first accesses the system, they are presented with a user registration form where they enter their name, email address, password, age, grade, and desired subjects. The device sends this information to the server via an HTTPS request, which then verifies it and stores it in a database.

[0202] 2. Login and Authentication:

[0203] The user logs in by entering their email address and password. The device sends this to the server, which then authenticates it in the database, generates a JWT (JSON Web Token), and returns it to the device as a token. This token is used to maintain the logged-in state.

[0204] 3. Learning support begins:

[0205] When a user requests learning support (e.g., "I want to learn the equations of motion in physics"), the device sends the request to the server. The generative AI model generates learning content based on the user's request, and the server provides it to the device.

[0206] 4. Progress monitoring and feedback:

[0207] As users study in the virtual classroom and attempt practice problems, their results (e.g., percentage of correct answers and time required to answer) are sent from their devices to the server. The server analyzes the progress data, generates feedback that evaluates the learner's level of understanding, and returns it to the device.

[0208] 5. Virtual Classroom:

[0209] Learners can use head-mounted displays to participate in virtual classrooms and take interactive lessons in real time. Progress data during learning activities is monitored in real time, and timely feedback is provided.

[0210] Examples of concrete examples and prompts

[0211] Specific examples

[0212] User: High school student A

[0213] Learning content: Physics equations of motion

[0214] scenario:

[0215] 1. Learner A launches the Virtual Classroom app on their smartphone and registers on their first visit.

[0216] 2. Enter your name, email address, password, grade, and desired subject (physics) to complete registration.

[0217] 3. Log in and request to learn about "Equations of Motion."

[0218] 4. The generative AI model generates learning content on the equation of motion and provides it to Learner A.

[0219] 5. Learner A solves the practice problems and sends the results to the server.

[0220] 6. The server analyzes the data and provides feedback to Learner A based on their level of understanding.

[0221] Prompt Sentence Examples

[0222] User name: Student A, Grade: 2nd year high school student, Subject: Physics

[0223] "Generate educational content related to the equations of motion."

[0224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0225] Step 1:

[0226] When a user accesses the system for the first time, a user registration form is displayed. The user enters their name, email address, password, age, grade level, and desired subjects. The entered information is sent to the server using an HTTPS request on the terminal. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user indicating that registration is complete.

[0227] Step 2:

[0228] The user enters their email address and password on the login page. The device sends this information to the server. The server performs authentication in the database, and if the email address and password match, it generates a JWT (JSON Web Token) and returns it to the device. The device saves the token and maintains the logged-in state. The input data is the email address and password, and the output data is an authentication token.

[0229] Step 3:

[0230] A user requests learning support. For example, they might request, "I want to learn the equations of motion in physics." The device sends this request to the server. The server uses a generative AI model to generate learning content that corresponds to the request. The generative AI model uses pre-trained data to automatically generate learning materials based on the prompt sentence. The generated learning content is sent from the server to the device, which displays it to the user. The input data is the learning request, and the output data is the learning content.

[0231] Step 4:

[0232] Users study the learning content provided in the virtual classroom. Learners can participate in the virtual classroom using VR devices such as head-mounted displays. When learners solve practice problems, the results (correct answer rate and answer time) are sent from their devices to the server. The input data are the answers to the practice problems, and the output data are progress data for analysis.

[0233] Step 5:

[0234] The server analyzes the received progress data. Using data analysis tools such as Pandas, it evaluates the progress data and generates feedback based on the generative AI model. The generated feedback is sent from the server to the terminal, which displays the feedback to the user. The input data is the progress data to be analyzed, and the output data is the generated feedback.

[0235] Step 6:

[0236] The learner uses the generated feedback to further study. The server then uses the generative AI model again to provide learning content based on the learner's new requests and challenges. This process is repeated until the user has sufficiently deepened their understanding. The input data is feedback, and the output data is the regenerated learning content.

[0237] 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.

[0238] This invention combines an emotion engine with an online tutoring system that utilizes generative AI models to provide more effective learning support to students. The system recognizes users' emotions and adjusts learning content and feedback based on those emotions, enabling a personalized learning experience.

[0239] System program processing

[0240] The system does the following:

[0241] 1. User Registration

[0242] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[0243] The device sends this information to the server via an HTTP POST request.

[0244] The server verifies the received information, stores it in a database, and once registration is complete, generates a unique user ID and returns it to the device.

[0245] The terminal displays a registration complete message to the user.

[0246] 2. Login and Authentication

[0247] The user enters their email address and password on the login page.

[0248] The terminal transmits this information to the server.

[0249] The server checks the user information (email address and password) in its database.

[0250] If there is a match, the server generates an authentication token and returns it to the terminal.

[0251] The terminal stores the token and logs the user in.

[0252] 3. Start of learning support

[0253] A user makes a learning support request (e.g., "8th grade math equations").

[0254] The terminal sends the request contents to the server using an HTTP POST request.

[0255] The server checks the request and requests the generative AI model to generate learning content.

[0256] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[0257] The generation AI returns the generated learning content to the server.

[0258] The server transmits the generated learning content to the terminal.

[0259] The terminal displays the learning content to the user.

[0260] 4. Operation of the Emotion Engine

[0261] The device captures the user's facial expressions and voice through a camera and microphone.

[0262] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[0263] The device transmits the recognized emotion data to the server.

[0264] 5. Progress monitoring and feedback

[0265] The user solves the practice problems and enters the results (correct or incorrect and time) into the terminal.

[0266] The device sends these results to the server via an HTTP POST request.

[0267] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[0268] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[0269] The server transmits the generated feedback to the terminal.

[0270] The terminal displays the received feedback to the user.

[0271] Specific examples

[0272] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[0273] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[0274] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[0275] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[0276] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[0277] 5. While Hanako Yamada is working on the exercises, the device captures her facial expressions and voice through a camera and microphone. The emotion engine analyzes this data and recognizes that she is confused.

[0278] 6. Hanako Yamada completes the exercise and enters her results into her device. The device sends these results to the server, which analyzes the progress and emotion data it receives to assess her level of understanding. Using a generative AI model, the server generates feedback with detailed explanations to alleviate her confusion and sends it to the device.

[0279] 7. The device displays the received feedback to Hanako Yamada to support her learning.

[0280] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[0281] The processing flow will be explained below.

[0282] Program processing steps

[0283] Registering Users

[0284] Step 1:

[0285] When a user first accesses the system, a registration form is displayed.

[0286] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[0287] Step 2:

[0288] The terminal sends the entered information to the server via an HTTP POST request.

[0289] Step 3:

[0290] The server validates the information received (checks for required fields, verifies format, etc.).

[0291] Step 4:

[0292] After verification, the server stores the user data in a database and generates a unique user ID.

[0293] Step 5:

[0294] The server returns a registration completion message and the user ID to the terminal.

[0295] Step 6:

[0296] The terminal displays a registration completion message to the user.

[0297] Login and Authentication

[0298] Step 1:

[0299] The user visits the login page and enters their email address and password.

[0300] Step 2:

[0301] The device sends the entered login information to the server via an HTTP POST request.

[0302] Step 3:

[0303] The server checks the user information (email address and hashed password) in its database.

[0304] Step 4:

[0305] If there is a match, the server generates an authentication token and returns it to the terminal.

[0306] Step 5:

[0307] The terminal stores the token and logs the user in.

[0308] Start of learning support

[0309] Step 1:

[0310] A user makes a learning support request (e.g., "8th grade math equations").

[0311] Step 2:

[0312] The terminal sends the request contents to the server using an HTTP POST request.

[0313] Step 3:

[0314] The server checks the request and requests the generative AI model to generate learning content.

[0315] Step 4:

[0316] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[0317] Step 5:

[0318] The generation AI returns the generated learning content to the server.

[0319] Step 6:

[0320] The server transmits the generated learning content to the terminal.

[0321] Step 7:

[0322] The terminal displays the learning content to the user.

[0323] Emotion Engine Operation

[0324] Step 1:

[0325] The device captures the user's facial expressions and voice through a camera and microphone.

[0326] Step 2:

[0327] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[0328] Step 3:

[0329] The device sends the recognized emotion data to the server via an HTTP POST request.

[0330] Progress monitoring and feedback

[0331] Step 1:

[0332] The user solves the exercises.

[0333] Step 2:

[0334] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[0335] Step 3:

[0336] The device sends the result data to the server via an HTTP POST request.

[0337] Step 4:

[0338] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[0339] Step 5:

[0340] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[0341] Step 6:

[0342] The server sends the generated feedback to the device via an HTTP POST request.

[0343] Step 7:

[0344] The terminal displays the received feedback to the user.

[0345] Example 2

[0346] 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."

[0347] In online learning systems, general learning support that ignores students' emotional states is insufficient to provide an effective learning experience. For example, if a student is confused, appropriate feedback and support may not be provided. Therefore, it is necessary to recognize students' emotional states in real time and adjust learning content and feedback based on their emotional states.

[0348] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for capturing the student's facial expressions and voice, means for analyzing the captured data to recognize the student's emotions, means for receiving and storing the recognized emotion data, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and emotion data and generating feedback, and means for providing the generated feedback to the student. This enables effective learning support tailored based on the student's emotional state.

[0349] The "means for receiving student learning requests" is an input interface for students to request the learning content and support they desire.

[0350] "Means for generating learning content using generative AI models" refers to a function that utilizes generative AI to automatically create learning materials and workbooks based on student requests.

[0351] "Means for providing generated learning content to students" refers to the function for sending the generated learning materials and question sets to students' devices and displaying them.

[0352] "Means for capturing student facial expressions and voices" refers to devices or functions that use cameras and microphones to record and record students' facial expressions and voices.

[0353] The "means for analyzing captured data to recognize student emotions" refers to algorithms or software for analyzing the acquired facial and voice data and determining the student's emotional state.

[0354] The "means for receiving and storing recognized emotion data" is a function for transmitting analyzed emotion data to a server and storing it in a database.

[0355] "Means for monitoring student learning progress" refers to a function for tracking and recording the progress of students as they study, whether their answers are correct or incorrect, and the time it takes to answer.

[0356] The "means for analyzing students' learning progress data and emotional data and generating feedback" refers to algorithms or software for generating feedback based on the acquired progress data and emotional data according to the students' level of understanding and emotional state.

[0357] The "means for providing the generated feedback to the student" is a function for transmitting the generated feedback to the student's terminal and displaying it.

[0358] This invention is an online tutoring system that uses a generative AI model to recognize a student's emotional state and adjust learning content and feedback based on that state to provide a personalized learning experience. The system operates through a series of processes, including user registration, login and authentication, initiation of learning support, operation of the emotion engine, and progress monitoring and feedback.

[0359] Hardware and software used

[0360] Device: A computer or smartphone used by a student. A device is equipped with a camera and microphone.

[0361] Server: Responsible for the backend processing of the entire system, including user authentication, database management, sending requests to the AI ​​model, and managing generated content.

[0362] Generative AI model: An AI that generates learning content based on student requests. Examples of generative models include GPT (Generative Pre-trained Transformer).

[0363] Emotion engine: An algorithm that analyzes students' facial and vocal data to determine their emotional state. This engine uses a deep learning model.

[0364] System program processing

[0365] 1. User Registration

[0366] When a user accesses the system for the first time, a registration form is displayed on the terminal. The user enters basic information such as name, email address, password, age, grade, and desired subjects. The terminal sends this information to the server via an HTTP POST request. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The user sees a message on the screen saying "Registration complete."

[0367] 2. Login and Authentication

[0368] The user enters their email address and password on the login page, and the device sends this to the server. The server accesses a database to verify that the email address and password combination is correct. If they match, the server generates an authentication token and returns it to the device. The device stores the token, and the user is logged in.

[0369] 3. Start of learning support

[0370] When a user requests learning support, for example, they send a request to learn "mathematical equations for second-year junior high school students." The device sends this content to the server via an HTTP POST request. The server analyzes the request and asks the generative AI model to generate learning content. The generative AI model generates learning content (e.g., explanations and practice problems for equations) based on the prompt and returns it to the server. The server then sends the content to the device and displays it to the user.

[0371] 4. Operation of the Emotion Engine

[0372] The device uses a camera and microphone to capture students' facial expressions and voices in real time. The emotion engine analyzes this data and recognizes the student's emotional state. The device then transmits the recognized emotion data to the server, which stores the received emotion data and uses it for subsequent feedback.

[0373] 5. Progress monitoring and feedback

[0374] When a user solves the provided practice problems, they enter the results (correct / incorrect answers, response time) into their device. The device then sends these results to the server, which combines progress data and emotional data to evaluate the user's level of understanding. The server then uses a generative AI model to generate feedback based on the user's level of understanding and emotional state. The generated feedback is sent to the device and displayed to the user.

[0375] Examples of concrete examples and prompts

[0376] Specific examples

[0377] Username: Yamada Taro

[0378] Age: 14

[0379] Grade: 2nd year of junior high school

[0380] Subject: Mathematics (Equations)

[0381] Request: I want to learn math equations for second-year junior high school students.

[0382] Prompt Sentence Examples

[0383] Username: Yamada Taro

[0384] Grade: 2nd year of junior high school

[0385] Subject: Mathematics

[0386] What you'll learn: Generate materials and exercises to deepen your understanding of equations

[0387] Emotional state: Confused

[0388] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[0389] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0390] Step 1: Registering a user

[0391] Input: The user enters registration information into the terminal, including name, email address, password, age, grade, and desired subjects.

[0392] Specific operation: The user accesses the system and enters the required information into the displayed registration form. The terminal sends this information to the server via an HTTP POST request.

[0393] Data processing / data calculation: The server validates the information it receives, for example, checking that the email address is formatted correctly or that the password meets requirements.

[0394] Output: After verification, the server saves the data in the database, generates a unique user ID and returns it to the terminal, which displays a message to the user saying "Registration completed."

[0395] Step 2: Login and Authentication

[0396] Input: The user enters their email address and password on the login page.

[0397] Specific operation: The device sends this information to the server via an HTTP POST request.

[0398] Data processing / data calculation: The server accesses the database and checks whether the email address and password combination sent is correct. If they match, it generates an authentication token.

[0399] Output: The server returns an authentication token to the device, which stores the token and logs the user in.

[0400] Step 3: Start learning support

[0401] Input: The user types the request "I want to learn eighth grade math equations" into the terminal.

[0402] Specific operation: The device sends the request content to the server via an HTTP POST request.

[0403] Data processing / data calculation: The server analyzes the received request content, generates a prompt sentence, and sends it to the generative AI model.

[0404] Example: "User name: Yamada Taro, Grade: 8th grade, Subject: Mathematics, Learning content: Please generate materials and practice problems to deepen my understanding of equations, Emotional state: Confused."

[0405] Output: The generative AI model generates learning content (explanatory materials, practice questions) and returns it to the server, which sends it to the device, which displays the content to the user.

[0406] Step 4: Emotion Engine in Action

[0407] Input: The user's facial expressions and voice are captured by the camera and microphone.

[0408] Specific operation: The device captures the user's video and audio in real time.

[0409] Data processing / data calculation: The emotion engine analyzes this data and recognizes the user's emotions (happiness, sadness, confusion, etc.).

[0410] Output: The recognized emotion data is sent from the device to the server, where it is stored.

[0411] Step 5: Progress monitoring and feedback

[0412] Input: The user solves the exercises and enters the results (correct / incorrect and answer time) into the terminal.

[0413] Specific operation: The device sends the results of the exercise to the server via an HTTP POST request.

[0414] Data processing / data calculation: The server integrates the progress data and emotion data to evaluate the user's level of understanding and learning status. It uses a generative AI model to generate feedback tailored to the user.

[0415] For example, adjustments are made, such as adding more detailed explanations for confused users.

[0416] Output: The server sends the generated feedback to the device, which displays it to the user.

[0417] The above is the flow of processing in the program for this system, and details of the specific operations, data processing, and data calculations in each processing step.

[0418] (Application example 2)

[0419] 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."

[0420] Conventional online tutoring systems provide learning content and monitor progress according to students' learning needs, but they are unable to adjust feedback based on the student's emotional state. As a result, support for students' understanding and motivation may be insufficient. Furthermore, customer support in virtual stores faces the challenge of providing optimal support based on the customer's emotions.

[0421] 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.

[0422] In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, means for providing the generated feedback to the student, means for collecting information using a camera or microphone to analyze the student's emotional state, and means for adjusting the learning content and feedback based on the collected emotional data. This enables individually optimized learning support based on the student's emotional state, improving learning effectiveness and enabling customer support in the virtual store to be provided in response to customer emotions.

[0423] A "generative AI model" is an artificial intelligence model that adaptively learns based on input data and automatically generates the necessary information and content.

[0424] An "online tutoring system" is a computer system that provides learning support to students via the Internet.

[0425] "Learning needs" are requests for content or skills that students want to learn.

[0426] "Learning content" is a general term for teaching materials, resources, practice questions, etc. that students use to study.

[0427] "Learning progress" is data that shows what students are learning and their progress.

[0428] "Feedback" refers to information such as comments and advice provided regarding a student's learning situation and progress.

[0429] "Emotional state" refers to the psychological state of students or customers that can be analyzed from their facial expressions and voices.

[0430] "Cameras and microphones" are devices that capture video and audio.

[0431] "Emotion data" refers to data relating to an emotional state obtained from facial expressions, voice, etc.

[0432] "Individual optimization" means providing support that is optimized according to the characteristics and conditions of each student or customer.

[0433] The online tutoring system of this invention combines a generative AI model and an emotion engine to provide individually optimized learning support. A specific embodiment of this system will be described.

[0434] First, students must register to receive learning support. They access the system from a device (e.g., a PC or smartphone) and enter information such as their name, email address, password, and desired subjects. The device then sends this information to the server via an HTTP POST request. The server stores the received information in a database, and once registration is complete, generates a unique user ID and returns it to the device. The device then displays a message indicating registration is complete.

[0435] Next, the student enters their email address and password on the login page to authenticate. The device sends this information to the server, which checks the user information in the database. If authentication is successful, the server generates an authentication token and returns it to the device. The device saves the token and logs the user in.

[0436] When a student requests learning support, for example, "Study math equations for second-year junior high school students," the device sends this request to the server via an HTTP POST request. The server passes the request to a generative AI model, which generates the necessary learning content. The server then sends the generated learning content to the device, which then displays it.

[0437] Cameras and microphones are used to understand students' emotional states during learning. The devices capture students' facial expressions and voices in real time and analyze them using an emotion engine. This analysis data is sent from the device to the server, and the student's emotional state is reflected in the feedback. For example, if a student is confused, the server generates a more detailed explanation and sends it to the device. This allows students to receive individually optimized feedback.

[0438] The main software components of this system include a server-side generative AI model, user authentication, a database, and an emotion engine analysis API. The hardware required is a PC or smartphone equipped with a camera and microphone.

[0439] As a concrete example, let's consider the system's operation when a user named "Yamada Hanako" is studying mathematics for a second-year junior high school student. She accesses the system for the first time and completes registration after entering the necessary information. Next, she logs in and requests to study "equations." The system generates optimal learning content and displays it on the device. While studying, her emotional state is analyzed in real time using the camera and microphone, and feedback is adjusted as necessary.

[0440] Example prompt sentence:

[0441] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[0442] Login: "ichiro@example.com, password123"

[0443] Learning Request: "Explain quadratic equations"

[0444] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[0445] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on quadratic equations"

[0446] As described above, this invention is a system that provides learning support tailored to the emotional state of each student by linking a generative AI model with an emotion engine.

[0447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0448] Step 1:

[0449] Customer Registration

[0450] Terminal: When a customer first accesses the virtual store, they enter information such as their name, email address, password, and preferred product category. The entered information is sent to the server via an HTTP POST request. (Input) Customer information (Output) Send request to server.

[0451] Server: Stores the received customer information in a database, and after registration is complete generates a unique customer ID and returns it to the terminal. The terminal displays a registration completion message. (Input) Customer information (Data processing) Data verification and ID generation (Output) Registration completion message.

[0452] Step 2:

[0453] Login and Authentication

[0454] Terminal: The customer enters their email address and password on the login page and sends them to the server in an HTTP POST request. (Input) Authentication information (Output) Request sent to the server.

[0455] Server: Checks customer information in the database, and if authentication is successful, generates an authentication token and returns it to the terminal. The terminal saves the token and logs the customer in. (Input) Authentication information (Data processing work) Data verification and token generation (Output) Authentication token.

[0456] Step 3:

[0457] Customer Support Requests

[0458] Terminal: A customer asks a question about a product or requests support (e.g., "Tell me more about your new product"). The terminal sends this request to the server via an HTTP POST request. (Input) Customer request (Output) Request sent to the server.

[0459] Server: The request content is passed to the generation AI model, which generates the necessary support information. The server receives the generated support information and sends it to the terminal. (Input) Customer request (Data calculation) Support information generation (Output) Support information.

[0460] Step 4:

[0461] Emotion Engine Operation

[0462] Device: Captures customer facial expressions and voices in real time using a camera and microphone. Sends the captured data to the emotion engine API. (Input) Customer facial and voice data. (Output) Sends data to the emotion engine.

[0463] Emotion engine: Analyzes facial and voice data to recognize emotional states (e.g., joy, confusion, dissatisfaction, etc.). (Input) Facial and voice data (Data calculation) Emotion analysis (Output) Emotion data.

[0464] Step 5:

[0465] Response adjustment and feedback

[0466] Server: Based on the received emotion data, the generative AI model readjusts the support content and generates appropriate feedback. The generated feedback is sent to the device. (Input) Emotion data (Data calculation) Adjustment of support content (Output) Feedback.

[0467] Terminal: Displays the received feedback information to the customer. For example, if confusion is detected, a more detailed explanation is displayed. (Input) Feedback information (Output) Feedback display.

[0468] Example prompt sentence:

[0469] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[0470] Login: "ichiro@example.com, password123"

[0471] Customer Support Request: "Explain the details of the new smartphone"

[0472] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[0473] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on the new smartphone"

[0474] As described above, by appropriately processing input data at each step and utilizing a generative AI model and emotion engine, the system is able to provide optimal support tailored to the emotional state of each individual customer.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] [Second embodiment]

[0479] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0480] 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.

[0481] 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).

[0482] 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.

[0483] 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.

[0484] 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).

[0485] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0486] 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.

[0487] 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.

[0488] 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.

[0489] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0490] 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."

[0491] The present invention relates to an online tutoring system using a generative AI model, which includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, and means for providing the generated feedback to the student.

[0492] System program processing

[0493] The system does the following:

[0494] 1. User Registration

[0495] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[0496] The terminal sends this information to the server via an HTTP POST request.

[0497] The server verifies the information received and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the device.

[0498] The terminal displays a registration complete message to the user.

[0499] 2. Login and Authentication

[0500] The user enters their email address and password on the login page.

[0501] The terminal transmits this information to the server.

[0502] The server performs authentication against the database, and if there is a match, generates an authentication token and returns it to the terminal.

[0503] The device stores the token and remains logged in.

[0504] 3. Start of learning support

[0505] A user requests learning support (e.g., they want to understand a math equation better).

[0506] The terminal transmits the request contents to the server.

[0507] The server uses a generative AI model to generate learning content (e.g., explanations of equations, practice problems) in response to requests.

[0508] The generation AI generates learning materials and questions and returns them to the server.

[0509] The server transmits the generated learning content to the terminal, which displays it to the user.

[0510] 4. Progress monitoring and feedback

[0511] The user solves the practice problems and sends the results (correct or incorrect and time) from the terminal to the server.

[0512] The server analyzes this data and evaluates the user's learning status and level of understanding.

[0513] The server generates feedback using a generative AI model and returns the feedback to the device.

[0514] The terminal displays this feedback to the user.

[0515] Specific examples

[0516] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[0517] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[0518] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[0519] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[0520] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[0521] 5. Hanako Yamada solves the exercises and sends the results from her device to the server. The server analyzes this data and evaluates the user's level of understanding. It generates feedback and returns it to the device. The device displays the feedback to Hanako Yamada.

[0522] In this way, online tutoring systems utilizing generative AI can overcome geographical and economic constraints and provide comprehensive, high-quality learning support.

[0523] The processing flow will be explained below.

[0524] Program processing steps

[0525] Registering Users

[0526] Step 1:

[0527] When a user first accesses the system, a registration form is displayed.

[0528] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[0529] Step 2:

[0530] The terminal sends the entered information to the server via an HTTP POST request.

[0531] Step 3:

[0532] The server validates the information received (checks for required fields, verifies format, etc.).

[0533] Step 4:

[0534] After verification, the server stores the user data in a database and generates a unique user ID.

[0535] Step 5:

[0536] The server returns a registration completion message and the user ID to the terminal.

[0537] Step 6:

[0538] The terminal displays a registration completion message to the user.

[0539] Login and Authentication

[0540] Step 1:

[0541] The user visits the login page and enters their email address and password.

[0542] Step 2:

[0543] The device sends the entered login information to the server via an HTTP POST request.

[0544] Step 3:

[0545] The server checks the user information (email address and password) in its database.

[0546] Step 4:

[0547] If there is a match, the server generates an authentication token and returns it to the terminal.

[0548] Step 5:

[0549] The terminal stores the token and logs the user in.

[0550] Start of learning support

[0551] Step 1:

[0552] A user makes a learning support request (e.g., "8th grade math equations").

[0553] Step 2:

[0554] The terminal sends the request contents to the server using an HTTP POST request.

[0555] Step 3:

[0556] The server checks the request and requests the generative AI model to generate learning content.

[0557] Step 4:

[0558] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[0559] Step 5:

[0560] The generation AI returns the generated learning content to the server.

[0561] Step 6:

[0562] The server transmits the generated learning content to the terminal.

[0563] Step 7:

[0564] The terminal displays the learning content to the user.

[0565] Progress monitoring and feedback

[0566] Step 1:

[0567] The user solves the exercises.

[0568] Step 2:

[0569] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[0570] Step 3:

[0571] The device sends these results to the server via an HTTP POST request.

[0572] Step 4:

[0573] The server analyzes the received data and evaluates the user's learning progress.

[0574] Step 5:

[0575] The server uses the generative AI model to generate feedback to provide to the user.

[0576] Step 6:

[0577] The server transmits the generated feedback to the terminal.

[0578] Step 7:

[0579] The terminal displays the received feedback to the user.

[0580] Example 1

[0581] 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."

[0582] Conventional online tutoring systems have limited ability to respond to individual learning needs, making it difficult to provide appropriate feedback based on students' progress and level of understanding. Furthermore, regional restrictions limit the amount of learning support available. Therefore, there is a need for a system that can respond to individual user needs, monitor progress, and provide appropriate feedback.

[0583] 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.

[0584] In this invention, the server includes: a means for displaying a registration form when a user first accesses the system; a means for receiving and transmitting information entered by the user; a means for verifying the received information, saving it in a database, and generating a unique user ID; a means for authenticating the email address and password entered by the user and generating an authentication token; a means for receiving a user's learning request; a means for generating learning content based on prompts using a generative AI model; a means for providing the generated learning content to the user; a means for monitoring the user's progress and collecting data; a means for analyzing the collected data and generating feedback; and a means for providing the generated feedback to the user. This enables support tailored to the user's individual learning needs, provides appropriate feedback based on the student's progress and level of understanding, and realizes comprehensive learning support that transcends regional constraints.

[0585] "User" refers to an individual who uses this system to receive learning support.

[0586] The "registration form" is an interface for users to enter necessary information when they access the site for the first time.

[0587] The "server" is a central system that manages information from users, runs generative AI models, and connects with databases.

[0588] "Terminal" refers to a device that a user directly operates to input information and receive learning content and feedback.

[0589] A "database" is a system for storing user information, learning content, progress data, etc.

[0590] An "authentication token" is a code generated to authenticate a user's login status and enable the maintenance of a session.

[0591] A "learning request" is a request issued by a user seeking specific learning content or support.

[0592] A "generative AI model" is an algorithm or system that uses machine learning technology to automatically generate learning content and feedback in response to user requests.

[0593] A "prompt" is an instruction given to a generative AI model when generating learning content or feedback.

[0594] "Learning content" refers to educational materials such as explanatory materials and practice questions generated by a generative AI model.

[0595] "Progress data" is information relating to the learning progress and level of understanding that is collected while the user is receiving learning support.

[0596] "Feedback" is information containing learning improvement points and advice generated by the AI ​​model based on progress data.

[0597] This invention relates to an online tutoring system that uses a generative AI model, and provides a specific method for users to receive assistance tailored to their individual learning needs. This system includes a personal computer (terminal), a web server (server), a database, HTTP communication, and a generative AI model (e.g., OpenAI's GPT model), and is implemented as follows:

[0598] Registering Users

[0599] When a user accesses the system for the first time, a registration form is displayed. The user enters their name, email address, password, age, grade, desired subjects, etc. This information is collected by the terminal and sent to the server using an HTTP POST request. The server verifies the received information and stores it in a database (e.g., MySQL). Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user saying "Registration complete."

[0600] Login and Authentication

[0601] The user enters their email address and password on the login page. This information is sent via the device to the server, which checks it against the user information in its database. If it matches, it generates an authentication token (e.g., JSON Web Token, JWT) and returns it to the device. The device stores the token and displays a "Login successful" message to the user.

[0602] Start of learning support

[0603] When a user clicks the "Request Learning Support" button on the dashboard, the device sends the request to the server. The server sends an appropriate prompt to a generative AI model (e.g., OpenAI GPT-4), which then generates learning content (e.g., explanatory materials, practice questions). The generated learning content is sent to the device via the server, and the device displays it to the user.

[0604] Example prompts include:

[0605] "Generate math equation practice problems for eighth graders."

[0606] Progress monitoring and feedback

[0607] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. This data is sent from the device to a server, which analyzes the data. For example, the user's correct answer rate and answer time are calculated. Feedback is generated using a generative AI model and returned from the server to the device. The device displays the feedback to the user.

[0608] This system provides support tailored to each user's individual learning needs, allowing them to receive high-quality learning support without being restricted by geographical location.

[0609] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0610] Step 1: Registering a user

[0611] When a user accesses the system for the first time, a registration form is displayed in which they enter their name, email address, password, age, grade, desired subjects, etc.

[0612] The device collects this information and sends it to the server using an HTTP POST request, along with the input data (name, email address, password, age, grade, and desired subjects).

[0613] The server verifies the received information (checks the format of the email address and the strength of the password), and if the verification is successful, it saves the new user information in a database (e.g. MySQL). After saving it in the database, the server generates a unique user ID and returns it to the terminal. The output is the user ID and a success message.

[0614] The terminal displays the message "Registration Complete" to the user, thereby completing the user's registration.

[0615] Step 2: Login and Authentication

[0616] The user enters their email address and password on the login page. The data entered is the email address and password.

[0617] The device sends this information to the server using an HTTP POST request.

[0618] The server checks the user information in its database against the entered information. If the check results match, it generates an authentication token (e.g., JSON Web Token, JWT). The output is the authentication token. If the check results do not match, it generates an error message.

[0619] The server returns an authentication token to the device, which stores it in local storage, allowing session management. The device displays a successful login message to the user and redirects them to the dashboard or home page.

[0620] Step 3: Start learning support

[0621] The user clicks the "Request Learning Support" button on the dashboard. At this time, the user's request (learning content request) becomes the input data.

[0622] The device sends the request content to the server using an HTTP POST request.

[0623] The server generates an appropriate prompt for the generative AI model (e.g., OpenAI GPT-4). This prompt is a sentence such as "Please generate practice problems and explanations for math equations for eighth-grade students." Sending this prompt to the generative AI corresponds to data processing and data calculation.

[0624] The generative AI model generates learning content (e.g., explanatory materials, practice questions) based on the prompts. The output is the generated learning content.

[0625] The generation AI returns the generated learning content to the server, and the server sends the content to the device.

[0626] The terminal displays the learning content to the user.

[0627] Step 4: Progress monitoring and feedback

[0628] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. These results become input data.

[0629] The device sends the results to the server using an HTTP POST request.

[0630] The server analyzes the received data. For example, it calculates the percentage of correct answers and tallys up the answering time. This corresponds to data processing and data calculation.

[0631] Based on this, the server evaluates the user's learning status and level of understanding. Based on the evaluation results, a generative AI model is used to generate feedback. The output is the generated feedback. Specific examples include "advice on how to solve equations" and "additional practice problems."

[0632] The server sends the feedback to the terminal, which displays the feedback to the user.

[0633] (Application example 1)

[0634] 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."

[0635] In today's educational environment, it is difficult for learners in remote locations to receive high-quality learning support, especially in the absence of an environment where individualized instruction can be provided in real time. Furthermore, there is a lack of systems that can efficiently monitor learning progress in virtual classroom environments and provide appropriate feedback in real time. Furthermore, there is a need for a means to provide an interactive educational environment without attending a physical classroom.

[0636] 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.

[0637] In this invention, the server includes means for receiving a learning request from a learner, means for generating learning content using a generative AI model, means for providing the generated learning content to the learner, means for monitoring the learner's progress data in real time during learning activities in a virtual environment, means for providing an interactive virtual classroom environment, and means for allowing the learner to participate in the virtual classroom using a head-mounted display or VR device, thereby enabling real-time monitoring of learning progress and provision of individualized instruction.

[0638] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate appropriate answers or content for specific tasks or questions.

[0639] "Student" means an individual who receives education or learning support through this system.

[0640] A "learning need" is a request by a learner for support or instruction on a particular learning content or topic.

[0641] "Learning content" refers to educational materials such as teaching materials and workbooks that are generated by a generative AI model based on the learner's learning requirements.

[0642] "Progress data" refers to data such as the grades and response times a learner obtains through learning activities.

[0643] "Feedback" refers to information such as advice and comments to learners that is generated by analyzing the learner's progress data.

[0644] A "virtual environment" is a system that uses virtual reality technology to provide an interactive learning environment similar to a physical classroom.

[0645] A "virtual classroom" is a virtual classroom in which learners can participate remotely using head-mounted displays or VR devices.

[0646] "Interactive" refers to the ability of learners to interact with the system in real time.

[0647] A "head-mounted display" is a device worn on the head that displays visual information and is used to provide a VR experience.

[0648] A "VR device" is a hardware device that allows you to experience virtual reality.

[0649] This invention relates to an online tutoring system that uses generative AI models to provide learning support to learners. This system allows learners to access the system via the Internet and receive real-time learning support in a virtual classroom environment.

[0650] Specifically, the system includes the following hardware and software configuration:

[0651] Server: Flask (Python framework), SQLite (database), TensorFlow (generative AI model), Pandas (data analysis)

[0652] Devices: Smartphones, tablets, and head-mounted displays (e.g., Oculus Rift, HTC Vive) used by learners

[0653] Communication method: Internet connection (Wi-Fi or mobile network)

[0654] Program processing

[0655] 1. User Registration:

[0656] When a user first accesses the system, they are presented with a user registration form where they enter their name, email address, password, age, grade, and desired subjects. The device sends this information to the server via an HTTPS request, which then verifies it and stores it in a database.

[0657] 2. Login and Authentication:

[0658] The user logs in by entering their email address and password. The device sends this to the server, which then authenticates it in the database, generates a JWT (JSON Web Token), and returns it to the device as a token. This token is used to maintain the logged-in state.

[0659] 3. Learning support begins:

[0660] When a user requests learning support (e.g., "I want to learn the equations of motion in physics"), the device sends the request to the server. The generative AI model generates learning content based on the user's request, and the server provides it to the device.

[0661] 4. Progress monitoring and feedback:

[0662] As users study in the virtual classroom and attempt practice problems, their results (e.g., percentage of correct answers and time required to answer) are sent from their devices to the server. The server analyzes the progress data, generates feedback that evaluates the learner's level of understanding, and returns it to the device.

[0663] 5. Virtual Classroom:

[0664] Learners can use head-mounted displays to participate in virtual classrooms and take interactive lessons in real time. Progress data during learning activities is monitored in real time, and timely feedback is provided.

[0665] Examples of concrete examples and prompts

[0666] Specific examples

[0667] User: High school student A

[0668] Learning content: Physics equations of motion

[0669] scenario:

[0670] 1. Learner A launches the Virtual Classroom app on their smartphone and registers on their first visit.

[0671] 2. Enter your name, email address, password, grade, and desired subject (physics) to complete registration.

[0672] 3. Log in and request to learn about "Equations of Motion."

[0673] 4. The generative AI model generates learning content on the equation of motion and provides it to Learner A.

[0674] 5. Learner A solves the practice problems and sends the results to the server.

[0675] 6. The server analyzes the data and provides feedback to Learner A based on their level of understanding.

[0676] Prompt Sentence Examples

[0677] User name: Student A, Grade: 2nd year high school student, Subject: Physics

[0678] "Generate educational content related to the equations of motion."

[0679] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0680] Step 1:

[0681] When a user accesses the system for the first time, a user registration form is displayed. The user enters their name, email address, password, age, grade level, and desired subjects. The entered information is sent to the server using an HTTPS request on the terminal. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user indicating that registration is complete.

[0682] Step 2:

[0683] The user enters their email address and password on the login page. The device sends this information to the server. The server performs authentication in the database, and if the email address and password match, it generates a JWT (JSON Web Token) and returns it to the device. The device saves the token and maintains the logged-in state. The input data is the email address and password, and the output data is an authentication token.

[0684] Step 3:

[0685] A user requests learning support. For example, they might request, "I want to learn the equations of motion in physics." The device sends this request to the server. The server uses a generative AI model to generate learning content that corresponds to the request. The generative AI model uses pre-trained data to automatically generate learning materials based on the prompt sentence. The generated learning content is sent from the server to the device, which displays it to the user. The input data is the learning request, and the output data is the learning content.

[0686] Step 4:

[0687] Users study the learning content provided in the virtual classroom. Learners can participate in the virtual classroom using VR devices such as head-mounted displays. When learners solve practice problems, the results (correct answer rate and answer time) are sent from their devices to the server. The input data are the answers to the practice problems, and the output data are progress data for analysis.

[0688] Step 5:

[0689] The server analyzes the received progress data. Using data analysis tools such as Pandas, it evaluates the progress data and generates feedback based on the generative AI model. The generated feedback is sent from the server to the terminal, which displays the feedback to the user. The input data is the progress data to be analyzed, and the output data is the generated feedback.

[0690] Step 6:

[0691] The learner uses the generated feedback to further study. The server then uses the generative AI model again to provide learning content based on the learner's new requests and challenges. This process is repeated until the user has sufficiently deepened their understanding. The input data is feedback, and the output data is the regenerated learning content.

[0692] 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.

[0693] This invention combines an emotion engine with an online tutoring system that utilizes generative AI models to provide more effective learning support to students. The system recognizes users' emotions and adjusts learning content and feedback based on those emotions, enabling a personalized learning experience.

[0694] System program processing

[0695] The system does the following:

[0696] 1. User Registration

[0697] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[0698] The device sends this information to the server via an HTTP POST request.

[0699] The server verifies the received information, stores it in a database, and once registration is complete, generates a unique user ID and returns it to the device.

[0700] The terminal displays a registration complete message to the user.

[0701] 2. Login and Authentication

[0702] The user enters their email address and password on the login page.

[0703] The terminal transmits this information to the server.

[0704] The server checks the user information (email address and password) in its database.

[0705] If there is a match, the server generates an authentication token and returns it to the terminal.

[0706] The terminal stores the token and logs the user in.

[0707] 3. Start of learning support

[0708] A user makes a learning support request (e.g., "8th grade math equations").

[0709] The terminal sends the request contents to the server using an HTTP POST request.

[0710] The server checks the request and requests the generative AI model to generate learning content.

[0711] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[0712] The generation AI returns the generated learning content to the server.

[0713] The server transmits the generated learning content to the terminal.

[0714] The terminal displays the learning content to the user.

[0715] 4. Operation of the Emotion Engine

[0716] The device captures the user's facial expressions and voice through a camera and microphone.

[0717] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[0718] The device transmits the recognized emotion data to the server.

[0719] 5. Progress monitoring and feedback

[0720] The user solves the practice problems and enters the results (correct or incorrect and time) into the terminal.

[0721] The device sends these results to the server via an HTTP POST request.

[0722] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[0723] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[0724] The server transmits the generated feedback to the terminal.

[0725] The terminal displays the received feedback to the user.

[0726] Specific examples

[0727] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[0728] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[0729] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[0730] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[0731] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[0732] 5. While Hanako Yamada is working on the exercises, the device captures her facial expressions and voice through a camera and microphone. The emotion engine analyzes this data and recognizes that she is confused.

[0733] 6. Hanako Yamada completes the exercise and enters her results into her device. The device sends these results to the server, which analyzes the progress and emotion data it receives to assess her level of understanding. Using a generative AI model, the server generates feedback with detailed explanations to alleviate her confusion and sends it to the device.

[0734] 7. The device displays the received feedback to Hanako Yamada to support her learning.

[0735] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[0736] The processing flow will be explained below.

[0737] Program processing steps

[0738] Registering Users

[0739] Step 1:

[0740] When a user first accesses the system, a registration form is displayed.

[0741] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[0742] Step 2:

[0743] The terminal sends the entered information to the server via an HTTP POST request.

[0744] Step 3:

[0745] The server validates the information received (checks for required fields, verifies format, etc.).

[0746] Step 4:

[0747] After verification, the server stores the user data in a database and generates a unique user ID.

[0748] Step 5:

[0749] The server returns a registration completion message and the user ID to the terminal.

[0750] Step 6:

[0751] The terminal displays a registration completion message to the user.

[0752] Login and Authentication

[0753] Step 1:

[0754] The user visits the login page and enters their email address and password.

[0755] Step 2:

[0756] The device sends the entered login information to the server via an HTTP POST request.

[0757] Step 3:

[0758] The server checks the user information (email address and hashed password) in its database.

[0759] Step 4:

[0760] If there is a match, the server generates an authentication token and returns it to the terminal.

[0761] Step 5:

[0762] The terminal stores the token and logs the user in.

[0763] Start of learning support

[0764] Step 1:

[0765] A user makes a learning support request (e.g., "8th grade math equations").

[0766] Step 2:

[0767] The terminal sends the request contents to the server using an HTTP POST request.

[0768] Step 3:

[0769] The server checks the request and requests the generative AI model to generate learning content.

[0770] Step 4:

[0771] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[0772] Step 5:

[0773] The generation AI returns the generated learning content to the server.

[0774] Step 6:

[0775] The server transmits the generated learning content to the terminal.

[0776] Step 7:

[0777] The terminal displays the learning content to the user.

[0778] Emotion Engine Operation

[0779] Step 1:

[0780] The device captures the user's facial expressions and voice through a camera and microphone.

[0781] Step 2:

[0782] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[0783] Step 3:

[0784] The device sends the recognized emotion data to the server via an HTTP POST request.

[0785] Progress monitoring and feedback

[0786] Step 1:

[0787] The user solves the exercises.

[0788] Step 2:

[0789] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[0790] Step 3:

[0791] The device sends the result data to the server via an HTTP POST request.

[0792] Step 4:

[0793] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[0794] Step 5:

[0795] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[0796] Step 6:

[0797] The server sends the generated feedback to the device via an HTTP POST request.

[0798] Step 7:

[0799] The terminal displays the received feedback to the user.

[0800] Example 2

[0801] 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."

[0802] In online learning systems, general learning support that ignores students' emotional states is insufficient to provide an effective learning experience. For example, if a student is confused, appropriate feedback and support may not be provided. Therefore, it is necessary to recognize students' emotional states in real time and adjust learning content and feedback based on their emotional states.

[0803] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for capturing the student's facial expressions and voice, means for analyzing the captured data to recognize the student's emotions, means for receiving and storing the recognized emotion data, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and emotion data and generating feedback, and means for providing the generated feedback to the student. This enables effective learning support tailored based on the student's emotional state.

[0804] The "means for receiving student learning requests" is an input interface for students to request the learning content and support they desire.

[0805] "Means for generating learning content using generative AI models" refers to a function that utilizes generative AI to automatically create learning materials and workbooks based on student requests.

[0806] "Means for providing generated learning content to students" refers to the function for sending the generated learning materials and question sets to students' devices and displaying them.

[0807] "Means for capturing student facial expressions and voices" refers to devices or functions that use cameras and microphones to record and record students' facial expressions and voices.

[0808] The "means for analyzing captured data to recognize student emotions" refers to algorithms or software for analyzing the acquired facial and voice data and determining the student's emotional state.

[0809] The "means for receiving and storing recognized emotion data" is a function for transmitting analyzed emotion data to a server and storing it in a database.

[0810] "Means for monitoring student learning progress" refers to a function for tracking and recording the progress of students as they study, whether their answers are correct or incorrect, and the time it takes to answer.

[0811] The "means for analyzing students' learning progress data and emotional data and generating feedback" refers to algorithms or software for generating feedback based on the acquired progress data and emotional data according to the students' level of understanding and emotional state.

[0812] The "means for providing the generated feedback to the student" is a function for transmitting the generated feedback to the student's terminal and displaying it.

[0813] This invention is an online tutoring system that uses a generative AI model to recognize a student's emotional state and adjust learning content and feedback based on that state to provide a personalized learning experience. The system operates through a series of processes, including user registration, login and authentication, initiation of learning support, operation of the emotion engine, and progress monitoring and feedback.

[0814] Hardware and software used

[0815] Device: A computer or smartphone used by a student. A device is equipped with a camera and microphone.

[0816] Server: Responsible for the backend processing of the entire system, including user authentication, database management, sending requests to the AI ​​model, and managing generated content.

[0817] Generative AI model: An AI that generates learning content based on student requests. Examples of generative models include GPT (Generative Pre-trained Transformer).

[0818] Emotion engine: An algorithm that analyzes students' facial and vocal data to determine their emotional state. This engine uses a deep learning model.

[0819] System program processing

[0820] 1. User Registration

[0821] When a user accesses the system for the first time, a registration form is displayed on the terminal. The user enters basic information such as name, email address, password, age, grade, and desired subjects. The terminal sends this information to the server via an HTTP POST request. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The user sees a message on the screen saying "Registration complete."

[0822] 2. Login and Authentication

[0823] The user enters their email address and password on the login page, and the device sends this to the server. The server accesses a database to verify that the email address and password combination is correct. If they match, the server generates an authentication token and returns it to the device. The device stores the token, and the user is logged in.

[0824] 3. Start of learning support

[0825] When a user requests learning support, for example, they send a request to learn "mathematical equations for second-year junior high school students." The device sends this content to the server via an HTTP POST request. The server analyzes the request and asks the generative AI model to generate learning content. The generative AI model generates learning content (e.g., explanations and practice problems for equations) based on the prompt and returns it to the server. The server then sends the content to the device and displays it to the user.

[0826] 4. Operation of the Emotion Engine

[0827] The device uses a camera and microphone to capture students' facial expressions and voices in real time. The emotion engine analyzes this data and recognizes the student's emotional state. The device then transmits the recognized emotion data to the server, which stores the received emotion data and uses it for subsequent feedback.

[0828] 5. Progress monitoring and feedback

[0829] When a user solves the provided practice problems, they enter the results (correct / incorrect answers, response time) into their device. The device then sends these results to the server, which combines progress data and emotional data to evaluate the user's level of understanding. The server then uses a generative AI model to generate feedback based on the user's level of understanding and emotional state. The generated feedback is sent to the device and displayed to the user.

[0830] Examples of concrete examples and prompts

[0831] Specific examples

[0832] Username: Yamada Taro

[0833] Age: 14

[0834] Grade: 2nd year of junior high school

[0835] Subject: Mathematics (Equations)

[0836] Request: I want to learn math equations for second-year junior high school students.

[0837] Prompt Sentence Examples

[0838] Username: Yamada Taro

[0839] Grade: 2nd year of junior high school

[0840] Subject: Mathematics

[0841] What you'll learn: Generate materials and exercises to deepen your understanding of equations

[0842] Emotional state: Confused

[0843] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[0844] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0845] Step 1: Registering a user

[0846] Input: The user enters registration information into the terminal, including name, email address, password, age, grade, and desired subjects.

[0847] Specific operation: The user accesses the system and enters the required information into the displayed registration form. The terminal sends this information to the server via an HTTP POST request.

[0848] Data processing / data calculation: The server validates the information it receives, for example, checking that the email address is formatted correctly or that the password meets requirements.

[0849] Output: After verification, the server saves the data in the database, generates a unique user ID and returns it to the terminal, which displays a message to the user saying "Registration completed."

[0850] Step 2: Login and Authentication

[0851] Input: The user enters their email address and password on the login page.

[0852] Specific operation: The device sends this information to the server via an HTTP POST request.

[0853] Data processing / data calculation: The server accesses the database and checks whether the email address and password combination sent is correct. If they match, it generates an authentication token.

[0854] Output: The server returns an authentication token to the device, which stores the token and logs the user in.

[0855] Step 3: Start learning support

[0856] Input: The user types the request "I want to learn eighth grade math equations" into the terminal.

[0857] Specific operation: The device sends the request content to the server via an HTTP POST request.

[0858] Data processing / data calculation: The server analyzes the received request content, generates a prompt sentence, and sends it to the generative AI model.

[0859] Example: "User name: Yamada Taro, Grade: 8th grade, Subject: Mathematics, Learning content: Please generate materials and practice problems to deepen my understanding of equations, Emotional state: Confused."

[0860] Output: The generative AI model generates learning content (explanatory materials, practice questions) and returns it to the server, which sends it to the device, which displays the content to the user.

[0861] Step 4: Emotion Engine in Action

[0862] Input: The user's facial expressions and voice are captured by the camera and microphone.

[0863] Specific operation: The device captures the user's video and audio in real time.

[0864] Data processing / data calculation: The emotion engine analyzes this data and recognizes the user's emotions (happiness, sadness, confusion, etc.).

[0865] Output: The recognized emotion data is sent from the device to the server, where it is stored.

[0866] Step 5: Progress monitoring and feedback

[0867] Input: The user solves the exercises and enters the results (correct / incorrect and answer time) into the terminal.

[0868] Specific operation: The device sends the results of the exercise to the server via an HTTP POST request.

[0869] Data processing / data calculation: The server integrates the progress data and emotion data to evaluate the user's level of understanding and learning status. It uses a generative AI model to generate feedback tailored to the user.

[0870] For example, adjustments are made, such as adding more detailed explanations for confused users.

[0871] Output: The server sends the generated feedback to the device, which displays it to the user.

[0872] The above is the flow of processing in the program for this system, and details of the specific operations, data processing, and data calculations in each processing step.

[0873] (Application example 2)

[0874] 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."

[0875] Conventional online tutoring systems provide learning content and monitor progress according to students' learning needs, but they are unable to adjust feedback based on the student's emotional state. As a result, support for students' understanding and motivation may be insufficient. Furthermore, customer support in virtual stores faces the challenge of providing optimal support based on the customer's emotions.

[0876] 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.

[0877] In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, means for providing the generated feedback to the student, means for collecting information using a camera or microphone to analyze the student's emotional state, and means for adjusting the learning content and feedback based on the collected emotional data. This enables individually optimized learning support based on the student's emotional state, improving learning effectiveness and enabling customer support in the virtual store to be provided in response to customer emotions.

[0878] A "generative AI model" is an artificial intelligence model that adaptively learns based on input data and automatically generates the necessary information and content.

[0879] An "online tutoring system" is a computer system that provides learning support to students via the Internet.

[0880] "Learning needs" are requests for content or skills that students want to learn.

[0881] "Learning content" is a general term for teaching materials, resources, practice questions, etc. that students use to study.

[0882] "Learning progress" is data that shows what students are learning and their progress.

[0883] "Feedback" refers to information such as comments and advice provided regarding a student's learning situation and progress.

[0884] "Emotional state" refers to the psychological state of students or customers that can be analyzed from their facial expressions and voices.

[0885] "Cameras and microphones" are devices that capture video and audio.

[0886] "Emotion data" refers to data relating to an emotional state obtained from facial expressions, voice, etc.

[0887] "Individual optimization" means providing support that is optimized according to the characteristics and conditions of each student or customer.

[0888] The online tutoring system of this invention combines a generative AI model and an emotion engine to provide individually optimized learning support. A specific embodiment of this system will be described.

[0889] First, students must register to receive learning support. They access the system from a device (e.g., a PC or smartphone) and enter information such as their name, email address, password, and desired subjects. The device then sends this information to the server via an HTTP POST request. The server stores the received information in a database, and once registration is complete, generates a unique user ID and returns it to the device. The device then displays a message indicating registration is complete.

[0890] Next, the student enters their email address and password on the login page to authenticate. The device sends this information to the server, which checks the user information in the database. If authentication is successful, the server generates an authentication token and returns it to the device. The device saves the token and logs the user in.

[0891] When a student requests learning support, for example, "Study math equations for second-year junior high school students," the device sends this request to the server via an HTTP POST request. The server passes the request to a generative AI model, which generates the necessary learning content. The server then sends the generated learning content to the device, which then displays it.

[0892] Cameras and microphones are used to understand students' emotional states during learning. The devices capture students' facial expressions and voices in real time and analyze them using an emotion engine. This analysis data is sent from the device to the server, and the student's emotional state is reflected in the feedback. For example, if a student is confused, the server generates a more detailed explanation and sends it to the device. This allows students to receive individually optimized feedback.

[0893] The main software components of this system include a server-side generative AI model, user authentication, a database, and an emotion engine analysis API. The hardware required is a PC or smartphone equipped with a camera and microphone.

[0894] As a concrete example, let's consider the system's operation when a user named "Yamada Hanako" is studying mathematics for a second-year junior high school student. She accesses the system for the first time and completes registration after entering the necessary information. Next, she logs in and requests to study "equations." The system generates optimal learning content and displays it on the device. While studying, her emotional state is analyzed in real time using the camera and microphone, and feedback is adjusted as necessary.

[0895] Example prompt sentence:

[0896] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[0897] Login: "ichiro@example.com, password123"

[0898] Learning Request: "Explain quadratic equations"

[0899] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[0900] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on quadratic equations"

[0901] As described above, this invention is a system that provides learning support tailored to the emotional state of each student by linking a generative AI model with an emotion engine.

[0902] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0903] Step 1:

[0904] Customer Registration

[0905] Terminal: When a customer first accesses the virtual store, they enter information such as their name, email address, password, and preferred product category. The entered information is sent to the server via an HTTP POST request. (Input) Customer information (Output) Send request to server.

[0906] Server: Stores the received customer information in a database, and after registration is complete generates a unique customer ID and returns it to the terminal. The terminal displays a registration completion message. (Input) Customer information (Data processing) Data verification and ID generation (Output) Registration completion message.

[0907] Step 2:

[0908] Login and Authentication

[0909] Terminal: The customer enters their email address and password on the login page and sends them to the server in an HTTP POST request. (Input) Authentication information (Output) Request sent to the server.

[0910] Server: Checks customer information in the database, and if authentication is successful, generates an authentication token and returns it to the terminal. The terminal saves the token and logs the customer in. (Input) Authentication information (Data processing work) Data verification and token generation (Output) Authentication token.

[0911] Step 3:

[0912] Customer Support Requests

[0913] Terminal: A customer asks a question about a product or requests support (e.g., "Tell me more about your new product"). The terminal sends this request to the server via an HTTP POST request. (Input) Customer request (Output) Request sent to the server.

[0914] Server: The request content is passed to the generation AI model, which generates the necessary support information. The server receives the generated support information and sends it to the terminal. (Input) Customer request (Data calculation) Support information generation (Output) Support information.

[0915] Step 4:

[0916] Emotion Engine Operation

[0917] Device: Captures customer facial expressions and voices in real time using a camera and microphone. Sends the captured data to the emotion engine API. (Input) Customer facial and voice data. (Output) Sends data to the emotion engine.

[0918] Emotion engine: Analyzes facial and voice data to recognize emotional states (e.g., joy, confusion, dissatisfaction, etc.). (Input) Facial and voice data (Data calculation) Emotion analysis (Output) Emotion data.

[0919] Step 5:

[0920] Response adjustment and feedback

[0921] Server: Based on the received emotion data, the generative AI model readjusts the support content and generates appropriate feedback. The generated feedback is sent to the device. (Input) Emotion data (Data calculation) Adjustment of support content (Output) Feedback.

[0922] Terminal: Displays the received feedback information to the customer. For example, if confusion is detected, a more detailed explanation is displayed. (Input) Feedback information (Output) Feedback display.

[0923] Example prompt sentence:

[0924] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[0925] Login: "ichiro@example.com, password123"

[0926] Customer Support Request: "Explain the details of the new smartphone"

[0927] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[0928] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on the new smartphone"

[0929] As described above, by appropriately processing input data at each step and utilizing a generative AI model and emotion engine, the system is able to provide optimal support tailored to the emotional state of each individual customer.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] [Third embodiment]

[0934] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0935] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0936] 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).

[0937] 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.

[0938] 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.

[0939] 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).

[0940] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0941] 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.

[0942] 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.

[0943] 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.

[0944] 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.

[0945] 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."

[0946] The present invention relates to an online tutoring system using a generative AI model, which includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, and means for providing the generated feedback to the student.

[0947] System program processing

[0948] The system does the following:

[0949] 1. User Registration

[0950] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[0951] The terminal sends this information to the server via an HTTP POST request.

[0952] The server verifies the information received and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the device.

[0953] The terminal displays a registration complete message to the user.

[0954] 2. Login and Authentication

[0955] The user enters their email address and password on the login page.

[0956] The terminal transmits this information to the server.

[0957] The server performs authentication against the database, and if there is a match, generates an authentication token and returns it to the terminal.

[0958] The device stores the token and remains logged in.

[0959] 3. Start of learning support

[0960] A user requests learning support (e.g., they want to understand a math equation better).

[0961] The terminal transmits the request contents to the server.

[0962] The server uses a generative AI model to generate learning content (e.g., explanations of equations, practice problems) in response to requests.

[0963] The generation AI generates learning materials and questions and returns them to the server.

[0964] The server transmits the generated learning content to the terminal, which displays it to the user.

[0965] 4. Progress monitoring and feedback

[0966] The user solves the practice problems and sends the results (correct or incorrect and time) from the terminal to the server.

[0967] The server analyzes this data and evaluates the user's learning status and level of understanding.

[0968] The server generates feedback using a generative AI model and returns the feedback to the device.

[0969] The terminal displays this feedback to the user.

[0970] Specific examples

[0971] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[0972] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[0973] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[0974] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[0975] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[0976] 5. Hanako Yamada solves the exercises and sends the results from her device to the server. The server analyzes this data and evaluates the user's level of understanding. It generates feedback and returns it to the device. The device displays the feedback to Hanako Yamada.

[0977] In this way, online tutoring systems utilizing generative AI can overcome geographical and economic constraints and provide comprehensive, high-quality learning support.

[0978] The processing flow will be explained below.

[0979] Program processing steps

[0980] Registering Users

[0981] Step 1:

[0982] When a user first accesses the system, a registration form is displayed.

[0983] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[0984] Step 2:

[0985] The terminal sends the entered information to the server via an HTTP POST request.

[0986] Step 3:

[0987] The server validates the information received (checks for required fields, verifies format, etc.).

[0988] Step 4:

[0989] After verification, the server stores the user data in a database and generates a unique user ID.

[0990] Step 5:

[0991] The server returns a registration completion message and the user ID to the terminal.

[0992] Step 6:

[0993] The terminal displays a registration completion message to the user.

[0994] Login and Authentication

[0995] Step 1:

[0996] The user visits the login page and enters their email address and password.

[0997] Step 2:

[0998] The device sends the entered login information to the server via an HTTP POST request.

[0999] Step 3:

[1000] The server checks the user information (email address and password) in its database.

[1001] Step 4:

[1002] If there is a match, the server generates an authentication token and returns it to the terminal.

[1003] Step 5:

[1004] The terminal stores the token and logs the user in.

[1005] Start of learning support

[1006] Step 1:

[1007] A user makes a learning support request (e.g., "8th grade math equations").

[1008] Step 2:

[1009] The terminal sends the request contents to the server using an HTTP POST request.

[1010] Step 3:

[1011] The server checks the request and requests the generative AI model to generate learning content.

[1012] Step 4:

[1013] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[1014] Step 5:

[1015] The generation AI returns the generated learning content to the server.

[1016] Step 6:

[1017] The server transmits the generated learning content to the terminal.

[1018] Step 7:

[1019] The terminal displays the learning content to the user.

[1020] Progress monitoring and feedback

[1021] Step 1:

[1022] The user solves the exercises.

[1023] Step 2:

[1024] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[1025] Step 3:

[1026] The device sends these results to the server via an HTTP POST request.

[1027] Step 4:

[1028] The server analyzes the received data and evaluates the user's learning progress.

[1029] Step 5:

[1030] The server uses the generative AI model to generate feedback to provide to the user.

[1031] Step 6:

[1032] The server transmits the generated feedback to the terminal.

[1033] Step 7:

[1034] The terminal displays the received feedback to the user.

[1035] Example 1

[1036] 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."

[1037] Conventional online tutoring systems have limited ability to respond to individual learning needs, making it difficult to provide appropriate feedback based on students' progress and level of understanding. Furthermore, regional restrictions limit the amount of learning support available. Therefore, there is a need for a system that can respond to individual user needs, monitor progress, and provide appropriate feedback.

[1038] 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.

[1039] In this invention, the server includes: a means for displaying a registration form when a user first accesses the system; a means for receiving and transmitting information entered by the user; a means for verifying the received information, saving it in a database, and generating a unique user ID; a means for authenticating the email address and password entered by the user and generating an authentication token; a means for receiving a user's learning request; a means for generating learning content based on prompts using a generative AI model; a means for providing the generated learning content to the user; a means for monitoring the user's progress and collecting data; a means for analyzing the collected data and generating feedback; and a means for providing the generated feedback to the user. This enables support tailored to the user's individual learning needs, provides appropriate feedback based on the student's progress and level of understanding, and realizes comprehensive learning support that transcends regional constraints.

[1040] "User" refers to an individual who uses this system to receive learning support.

[1041] The "registration form" is an interface for users to enter necessary information when they access the site for the first time.

[1042] The "server" is a central system that manages information from users, runs generative AI models, and connects with databases.

[1043] "Terminal" refers to a device that a user directly operates to input information and receive learning content and feedback.

[1044] A "database" is a system for storing user information, learning content, progress data, etc.

[1045] An "authentication token" is a code generated to authenticate a user's login status and enable the maintenance of a session.

[1046] A "learning request" is a request issued by a user seeking specific learning content or support.

[1047] A "generative AI model" is an algorithm or system that uses machine learning technology to automatically generate learning content and feedback in response to user requests.

[1048] A "prompt" is an instruction given to a generative AI model when generating learning content or feedback.

[1049] "Learning content" refers to educational materials such as explanatory materials and practice questions generated by a generative AI model.

[1050] "Progress data" is information relating to the learning progress and level of understanding that is collected while the user is receiving learning support.

[1051] "Feedback" is information containing learning improvement points and advice generated by the AI ​​model based on progress data.

[1052] This invention relates to an online tutoring system that uses a generative AI model, and provides a specific method for users to receive assistance tailored to their individual learning needs. This system includes a personal computer (terminal), a web server (server), a database, HTTP communication, and a generative AI model (e.g., OpenAI's GPT model), and is implemented as follows:

[1053] Registering Users

[1054] When a user accesses the system for the first time, a registration form is displayed. The user enters their name, email address, password, age, grade, desired subjects, etc. This information is collected by the terminal and sent to the server using an HTTP POST request. The server verifies the received information and stores it in a database (e.g., MySQL). Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user saying "Registration complete."

[1055] Login and Authentication

[1056] The user enters their email address and password on the login page. This information is sent via the device to the server, which checks it against the user information in its database. If it matches, it generates an authentication token (e.g., JSON Web Token, JWT) and returns it to the device. The device stores the token and displays a "Login successful" message to the user.

[1057] Start of learning support

[1058] When a user clicks the "Request Learning Support" button on the dashboard, the device sends the request to the server. The server sends an appropriate prompt to a generative AI model (e.g., OpenAI GPT-4), which then generates learning content (e.g., explanatory materials, practice questions). The generated learning content is sent to the device via the server, and the device displays it to the user.

[1059] Example prompts include:

[1060] "Generate math equation practice problems for eighth graders."

[1061] Progress monitoring and feedback

[1062] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. This data is sent from the device to a server, which analyzes the data. For example, the user's correct answer rate and answer time are calculated. Feedback is generated using a generative AI model and returned from the server to the device. The device displays the feedback to the user.

[1063] This system provides support tailored to each user's individual learning needs, allowing them to receive high-quality learning support without being restricted by geographical location.

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

[1065] Step 1: Registering a user

[1066] When a user accesses the system for the first time, a registration form is displayed in which they enter their name, email address, password, age, grade, desired subjects, etc.

[1067] The device collects this information and sends it to the server using an HTTP POST request, along with the input data (name, email address, password, age, grade, and desired subjects).

[1068] The server verifies the received information (checks the format of the email address and the strength of the password), and if the verification is successful, it saves the new user information in a database (e.g. MySQL). After saving it in the database, the server generates a unique user ID and returns it to the terminal. The output is the user ID and a success message.

[1069] The terminal displays the message "Registration Complete" to the user, thereby completing the user's registration.

[1070] Step 2: Login and Authentication

[1071] The user enters their email address and password on the login page. The data entered is the email address and password.

[1072] The device sends this information to the server using an HTTP POST request.

[1073] The server checks the user information in its database against the entered information. If the check results match, it generates an authentication token (e.g., JSON Web Token, JWT). The output is the authentication token. If the check results do not match, it generates an error message.

[1074] The server returns an authentication token to the device, which stores it in local storage, allowing session management. The device displays a successful login message to the user and redirects them to the dashboard or home page.

[1075] Step 3: Start learning support

[1076] The user clicks the "Request Learning Support" button on the dashboard. At this time, the user's request (learning content request) becomes the input data.

[1077] The device sends the request content to the server using an HTTP POST request.

[1078] The server generates an appropriate prompt for the generative AI model (e.g., OpenAI GPT-4). This prompt is a sentence such as "Please generate practice problems and explanations for math equations for eighth-grade students." Sending this prompt to the generative AI corresponds to data processing and data calculation.

[1079] The generative AI model generates learning content (e.g., explanatory materials, practice questions) based on the prompts. The output is the generated learning content.

[1080] The generation AI returns the generated learning content to the server, and the server sends the content to the device.

[1081] The terminal displays the learning content to the user.

[1082] Step 4: Progress monitoring and feedback

[1083] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. These results become input data.

[1084] The device sends the results to the server using an HTTP POST request.

[1085] The server analyzes the received data. For example, it calculates the percentage of correct answers and tallys up the answering time. This corresponds to data processing and data calculation.

[1086] Based on this, the server evaluates the user's learning status and level of understanding. Based on the evaluation results, a generative AI model is used to generate feedback. The output is the generated feedback. Specific examples include "advice on how to solve equations" and "additional practice problems."

[1087] The server sends the feedback to the terminal, which displays the feedback to the user.

[1088] (Application example 1)

[1089] 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."

[1090] In today's educational environment, it is difficult for learners in remote locations to receive high-quality learning support, especially in the absence of an environment where individualized instruction can be provided in real time. Furthermore, there is a lack of systems that can efficiently monitor learning progress in virtual classroom environments and provide appropriate feedback in real time. Furthermore, there is a need for a means to provide an interactive educational environment without attending a physical classroom.

[1091] 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.

[1092] In this invention, the server includes means for receiving a learning request from a learner, means for generating learning content using a generative AI model, means for providing the generated learning content to the learner, means for monitoring the learner's progress data in real time during learning activities in a virtual environment, means for providing an interactive virtual classroom environment, and means for allowing the learner to participate in the virtual classroom using a head-mounted display or VR device, thereby enabling real-time monitoring of learning progress and provision of individualized instruction.

[1093] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate appropriate answers or content for specific tasks or questions.

[1094] "Student" means an individual who receives education or learning support through this system.

[1095] A "learning need" is a request by a learner for support or instruction on a particular learning content or topic.

[1096] "Learning content" refers to educational materials such as teaching materials and workbooks that are generated by a generative AI model based on the learner's learning requirements.

[1097] "Progress data" refers to data such as the grades and response times a learner obtains through learning activities.

[1098] "Feedback" refers to information such as advice and comments to learners that is generated by analyzing the learner's progress data.

[1099] A "virtual environment" is a system that uses virtual reality technology to provide an interactive learning environment similar to a physical classroom.

[1100] A "virtual classroom" is a virtual classroom in which learners can participate remotely using head-mounted displays or VR devices.

[1101] "Interactive" refers to the ability of learners to interact with the system in real time.

[1102] A "head-mounted display" is a device worn on the head that displays visual information and is used to provide a VR experience.

[1103] A "VR device" is a hardware device that allows you to experience virtual reality.

[1104] This invention relates to an online tutoring system that uses generative AI models to provide learning support to learners. This system allows learners to access the system via the Internet and receive real-time learning support in a virtual classroom environment.

[1105] Specifically, the system includes the following hardware and software configuration:

[1106] Server: Flask (Python framework), SQLite (database), TensorFlow (generative AI model), Pandas (data analysis)

[1107] Devices: Smartphones, tablets, and head-mounted displays (e.g., Oculus Rift, HTC Vive) used by learners

[1108] Communication method: Internet connection (Wi-Fi or mobile network)

[1109] Program processing

[1110] 1. User Registration:

[1111] When a user first accesses the system, they are presented with a user registration form where they enter their name, email address, password, age, grade, and desired subjects. The device sends this information to the server via an HTTPS request, which then verifies it and stores it in a database.

[1112] 2. Login and Authentication:

[1113] The user logs in by entering their email address and password. The device sends this to the server, which then authenticates it in the database, generates a JWT (JSON Web Token), and returns it to the device as a token. This token is used to maintain the logged-in state.

[1114] 3. Learning support begins:

[1115] When a user requests learning support (e.g., "I want to learn the equations of motion in physics"), the device sends the request to the server. The generative AI model generates learning content based on the user's request, and the server provides it to the device.

[1116] 4. Progress monitoring and feedback:

[1117] As users study in the virtual classroom and attempt practice problems, their results (e.g., percentage of correct answers and time required to answer) are sent from their devices to the server. The server analyzes the progress data, generates feedback that evaluates the learner's level of understanding, and returns it to the device.

[1118] 5. Virtual Classroom:

[1119] Learners can use head-mounted displays to participate in virtual classrooms and take interactive lessons in real time. Progress data during learning activities is monitored in real time, and timely feedback is provided.

[1120] Examples of concrete examples and prompts

[1121] Specific examples

[1122] User: High school student A

[1123] Learning content: Physics equations of motion

[1124] scenario:

[1125] 1. Learner A launches the Virtual Classroom app on their smartphone and registers on their first visit.

[1126] 2. Enter your name, email address, password, grade, and desired subject (physics) to complete registration.

[1127] 3. Log in and request to learn about "Equations of Motion."

[1128] 4. The generative AI model generates learning content on the equation of motion and provides it to Learner A.

[1129] 5. Learner A solves the practice problems and sends the results to the server.

[1130] 6. The server analyzes the data and provides feedback to Learner A based on their level of understanding.

[1131] Prompt Sentence Examples

[1132] User name: Student A, Grade: 2nd year high school student, Subject: Physics

[1133] "Generate educational content related to the equations of motion."

[1134] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1135] Step 1:

[1136] When a user accesses the system for the first time, a user registration form is displayed. The user enters their name, email address, password, age, grade level, and desired subjects. The entered information is sent to the server using an HTTPS request on the terminal. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user indicating that registration is complete.

[1137] Step 2:

[1138] The user enters their email address and password on the login page. The device sends this information to the server. The server performs authentication in the database, and if the email address and password match, it generates a JWT (JSON Web Token) and returns it to the device. The device saves the token and maintains the logged-in state. The input data is the email address and password, and the output data is an authentication token.

[1139] Step 3:

[1140] A user requests learning support. For example, they might request, "I want to learn the equations of motion in physics." The device sends this request to the server. The server uses a generative AI model to generate learning content that corresponds to the request. The generative AI model uses pre-trained data to automatically generate learning materials based on the prompt sentence. The generated learning content is sent from the server to the device, which displays it to the user. The input data is the learning request, and the output data is the learning content.

[1141] Step 4:

[1142] Users study the learning content provided in the virtual classroom. Learners can participate in the virtual classroom using VR devices such as head-mounted displays. When learners solve practice problems, the results (correct answer rate and answer time) are sent from their devices to the server. The input data are the answers to the practice problems, and the output data are progress data for analysis.

[1143] Step 5:

[1144] The server analyzes the received progress data. Using data analysis tools such as Pandas, it evaluates the progress data and generates feedback based on the generative AI model. The generated feedback is sent from the server to the terminal, which displays the feedback to the user. The input data is the progress data to be analyzed, and the output data is the generated feedback.

[1145] Step 6:

[1146] The learner uses the generated feedback to further study. The server then uses the generative AI model again to provide learning content based on the learner's new requests and challenges. This process is repeated until the user has sufficiently deepened their understanding. The input data is feedback, and the output data is the regenerated learning content.

[1147] 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.

[1148] This invention combines an emotion engine with an online tutoring system that utilizes generative AI models to provide more effective learning support to students. The system recognizes users' emotions and adjusts learning content and feedback based on those emotions, enabling a personalized learning experience.

[1149] System program processing

[1150] The system does the following:

[1151] 1. User Registration

[1152] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[1153] The device sends this information to the server via an HTTP POST request.

[1154] The server verifies the received information, stores it in a database, and once registration is complete, generates a unique user ID and returns it to the device.

[1155] The terminal displays a registration complete message to the user.

[1156] 2. Login and Authentication

[1157] The user enters their email address and password on the login page.

[1158] The terminal transmits this information to the server.

[1159] The server checks the user information (email address and password) in its database.

[1160] If there is a match, the server generates an authentication token and returns it to the terminal.

[1161] The terminal stores the token and logs the user in.

[1162] 3. Start of learning support

[1163] A user makes a learning support request (e.g., "8th grade math equations").

[1164] The terminal sends the request contents to the server using an HTTP POST request.

[1165] The server checks the request and requests the generative AI model to generate learning content.

[1166] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[1167] The generation AI returns the generated learning content to the server.

[1168] The server transmits the generated learning content to the terminal.

[1169] The terminal displays the learning content to the user.

[1170] 4. Operation of the Emotion Engine

[1171] The device captures the user's facial expressions and voice through a camera and microphone.

[1172] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[1173] The device transmits the recognized emotion data to the server.

[1174] 5. Progress monitoring and feedback

[1175] The user solves the practice problems and enters the results (correct or incorrect and time) into the terminal.

[1176] The device sends these results to the server via an HTTP POST request.

[1177] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[1178] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[1179] The server transmits the generated feedback to the terminal.

[1180] The terminal displays the received feedback to the user.

[1181] Specific examples

[1182] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[1183] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[1184] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[1185] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[1186] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[1187] 5. While Hanako Yamada is working on the exercises, the device captures her facial expressions and voice through a camera and microphone. The emotion engine analyzes this data and recognizes that she is confused.

[1188] 6. Hanako Yamada completes the exercise and enters her results into her device. The device sends these results to the server, which analyzes the progress and emotion data it receives to assess her level of understanding. Using a generative AI model, the server generates feedback with detailed explanations to alleviate her confusion and sends it to the device.

[1189] 7. The device displays the received feedback to Hanako Yamada to support her learning.

[1190] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[1191] The processing flow will be explained below.

[1192] Program processing steps

[1193] Registering Users

[1194] Step 1:

[1195] When a user first accesses the system, a registration form is displayed.

[1196] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[1197] Step 2:

[1198] The terminal sends the entered information to the server via an HTTP POST request.

[1199] Step 3:

[1200] The server validates the information received (checks for required fields, verifies format, etc.).

[1201] Step 4:

[1202] After verification, the server stores the user data in a database and generates a unique user ID.

[1203] Step 5:

[1204] The server returns a registration completion message and the user ID to the terminal.

[1205] Step 6:

[1206] The terminal displays a registration completion message to the user.

[1207] Login and Authentication

[1208] Step 1:

[1209] The user visits the login page and enters their email address and password.

[1210] Step 2:

[1211] The device sends the entered login information to the server via an HTTP POST request.

[1212] Step 3:

[1213] The server checks the user information (email address and hashed password) in its database.

[1214] Step 4:

[1215] If there is a match, the server generates an authentication token and returns it to the terminal.

[1216] Step 5:

[1217] The terminal stores the token and logs the user in.

[1218] Start of learning support

[1219] Step 1:

[1220] A user makes a learning support request (e.g., "8th grade math equations").

[1221] Step 2:

[1222] The terminal sends the request contents to the server using an HTTP POST request.

[1223] Step 3:

[1224] The server checks the request and requests the generative AI model to generate learning content.

[1225] Step 4:

[1226] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[1227] Step 5:

[1228] The generation AI returns the generated learning content to the server.

[1229] Step 6:

[1230] The server transmits the generated learning content to the terminal.

[1231] Step 7:

[1232] The terminal displays the learning content to the user.

[1233] Emotion Engine Operation

[1234] Step 1:

[1235] The device captures the user's facial expressions and voice through a camera and microphone.

[1236] Step 2:

[1237] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[1238] Step 3:

[1239] The device sends the recognized emotion data to the server via an HTTP POST request.

[1240] Progress monitoring and feedback

[1241] Step 1:

[1242] The user solves the exercises.

[1243] Step 2:

[1244] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[1245] Step 3:

[1246] The device sends the result data to the server via an HTTP POST request.

[1247] Step 4:

[1248] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[1249] Step 5:

[1250] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[1251] Step 6:

[1252] The server sends the generated feedback to the device via an HTTP POST request.

[1253] Step 7:

[1254] The terminal displays the received feedback to the user.

[1255] Example 2

[1256] 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."

[1257] In online learning systems, general learning support that ignores students' emotional states is insufficient to provide an effective learning experience. For example, if a student is confused, appropriate feedback and support may not be provided. Therefore, it is necessary to recognize students' emotional states in real time and adjust learning content and feedback based on their emotional states.

[1258] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for capturing the student's facial expressions and voice, means for analyzing the captured data to recognize the student's emotions, means for receiving and storing the recognized emotion data, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and emotion data and generating feedback, and means for providing the generated feedback to the student. This enables effective learning support tailored based on the student's emotional state.

[1259] The "means for receiving student learning requests" is an input interface for students to request the learning content and support they desire.

[1260] "Means for generating learning content using generative AI models" refers to a function that utilizes generative AI to automatically create learning materials and workbooks based on student requests.

[1261] "Means for providing generated learning content to students" refers to the function for sending the generated learning materials and question sets to students' devices and displaying them.

[1262] "Means for capturing student facial expressions and voices" refers to devices or functions that use cameras and microphones to record and record students' facial expressions and voices.

[1263] The "means for analyzing captured data to recognize student emotions" refers to algorithms or software for analyzing the acquired facial and voice data and determining the student's emotional state.

[1264] The "means for receiving and storing recognized emotion data" is a function for transmitting analyzed emotion data to a server and storing it in a database.

[1265] "Means for monitoring student learning progress" refers to a function for tracking and recording the progress of students as they study, whether their answers are correct or incorrect, and the time it takes to answer.

[1266] The "means for analyzing students' learning progress data and emotional data and generating feedback" refers to algorithms or software for generating feedback based on the acquired progress data and emotional data according to the students' level of understanding and emotional state.

[1267] The "means for providing the generated feedback to the student" is a function for transmitting the generated feedback to the student's terminal and displaying it.

[1268] This invention is an online tutoring system that uses a generative AI model to recognize a student's emotional state and adjust learning content and feedback based on that state to provide a personalized learning experience. The system operates through a series of processes, including user registration, login and authentication, initiation of learning support, operation of the emotion engine, and progress monitoring and feedback.

[1269] Hardware and software used

[1270] Device: A computer or smartphone used by a student. A device is equipped with a camera and microphone.

[1271] Server: Responsible for the backend processing of the entire system, including user authentication, database management, sending requests to the AI ​​model, and managing generated content.

[1272] Generative AI model: An AI that generates learning content based on student requests. Examples of generative models include GPT (Generative Pre-trained Transformer).

[1273] Emotion engine: An algorithm that analyzes students' facial and vocal data to determine their emotional state. This engine uses a deep learning model.

[1274] System program processing

[1275] 1. User Registration

[1276] When a user accesses the system for the first time, a registration form is displayed on the terminal. The user enters basic information such as name, email address, password, age, grade, and desired subjects. The terminal sends this information to the server via an HTTP POST request. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The user sees a message on the screen saying "Registration complete."

[1277] 2. Login and Authentication

[1278] The user enters their email address and password on the login page, and the device sends this to the server. The server accesses a database to verify that the email address and password combination is correct. If they match, the server generates an authentication token and returns it to the device. The device stores the token, and the user is logged in.

[1279] 3. Start of learning support

[1280] When a user requests learning support, for example, they send a request to learn "mathematical equations for second-year junior high school students." The device sends this content to the server via an HTTP POST request. The server analyzes the request and asks the generative AI model to generate learning content. The generative AI model generates learning content (e.g., explanations and practice problems for equations) based on the prompt and returns it to the server. The server then sends the content to the device and displays it to the user.

[1281] 4. Operation of the Emotion Engine

[1282] The device uses a camera and microphone to capture students' facial expressions and voices in real time. The emotion engine analyzes this data and recognizes the student's emotional state. The device then transmits the recognized emotion data to the server, which stores the received emotion data and uses it for subsequent feedback.

[1283] 5. Progress monitoring and feedback

[1284] When a user solves the provided practice problems, they enter the results (correct / incorrect answers, response time) into their device. The device then sends these results to the server, which combines progress data and emotional data to evaluate the user's level of understanding. The server then uses a generative AI model to generate feedback based on the user's level of understanding and emotional state. The generated feedback is sent to the device and displayed to the user.

[1285] Examples of concrete examples and prompts

[1286] Specific examples

[1287] Username: Yamada Taro

[1288] Age: 14

[1289] Grade: 2nd year of junior high school

[1290] Subject: Mathematics (Equations)

[1291] Request: I want to learn math equations for second-year junior high school students.

[1292] Prompt Sentence Examples

[1293] Username: Yamada Taro

[1294] Grade: 2nd year of junior high school

[1295] Subject: Mathematics

[1296] What you'll learn: Generate materials and exercises to deepen your understanding of equations

[1297] Emotional state: Confused

[1298] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[1299] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1300] Step 1: Registering a user

[1301] Input: The user enters registration information into the terminal, including name, email address, password, age, grade, and desired subjects.

[1302] Specific operation: The user accesses the system and enters the required information into the displayed registration form. The terminal sends this information to the server via an HTTP POST request.

[1303] Data processing / data calculation: The server validates the information it receives, for example, checking that the email address is formatted correctly or that the password meets requirements.

[1304] Output: After verification, the server saves the data in the database, generates a unique user ID and returns it to the terminal, which displays a message to the user saying "Registration completed."

[1305] Step 2: Login and Authentication

[1306] Input: The user enters their email address and password on the login page.

[1307] Specific operation: The device sends this information to the server via an HTTP POST request.

[1308] Data processing / data calculation: The server accesses the database and checks whether the email address and password combination sent is correct. If they match, it generates an authentication token.

[1309] Output: The server returns an authentication token to the device, which stores the token and logs the user in.

[1310] Step 3: Start learning support

[1311] Input: The user types the request "I want to learn eighth grade math equations" into the terminal.

[1312] Specific operation: The device sends the request content to the server via an HTTP POST request.

[1313] Data processing / data calculation: The server analyzes the received request content, generates a prompt sentence, and sends it to the generative AI model.

[1314] Example: "User name: Yamada Taro, Grade: 8th grade, Subject: Mathematics, Learning content: Please generate materials and practice problems to deepen my understanding of equations, Emotional state: Confused."

[1315] Output: The generative AI model generates learning content (explanatory materials, practice questions) and returns it to the server, which sends it to the device, which displays the content to the user.

[1316] Step 4: Emotion Engine in Action

[1317] Input: The user's facial expressions and voice are captured by the camera and microphone.

[1318] Specific operation: The device captures the user's video and audio in real time.

[1319] Data processing / data calculation: The emotion engine analyzes this data and recognizes the user's emotions (happiness, sadness, confusion, etc.).

[1320] Output: The recognized emotion data is sent from the device to the server, where it is stored.

[1321] Step 5: Progress monitoring and feedback

[1322] Input: The user solves the exercises and enters the results (correct / incorrect and answer time) into the terminal.

[1323] Specific operation: The device sends the results of the exercise to the server via an HTTP POST request.

[1324] Data processing / data calculation: The server integrates the progress data and emotion data to evaluate the user's level of understanding and learning status. It uses a generative AI model to generate feedback tailored to the user.

[1325] For example, adjustments are made, such as adding more detailed explanations for confused users.

[1326] Output: The server sends the generated feedback to the device, which displays it to the user.

[1327] The above is the flow of processing in the program for this system, and details of the specific operations, data processing, and data calculations in each processing step.

[1328] (Application example 2)

[1329] 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."

[1330] Conventional online tutoring systems provide learning content and monitor progress according to students' learning needs, but they are unable to adjust feedback based on the student's emotional state. As a result, support for students' understanding and motivation may be insufficient. Furthermore, customer support in virtual stores faces the challenge of providing optimal support based on the customer's emotions.

[1331] 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.

[1332] In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, means for providing the generated feedback to the student, means for collecting information using a camera or microphone to analyze the student's emotional state, and means for adjusting the learning content and feedback based on the collected emotional data. This enables individually optimized learning support based on the student's emotional state, improving learning effectiveness and enabling customer support in the virtual store to be provided in response to customer emotions.

[1333] A "generative AI model" is an artificial intelligence model that adaptively learns based on input data and automatically generates the necessary information and content.

[1334] An "online tutoring system" is a computer system that provides learning support to students via the Internet.

[1335] "Learning needs" are requests for content or skills that students want to learn.

[1336] "Learning content" is a general term for teaching materials, resources, practice questions, etc. that students use to study.

[1337] "Learning progress" is data that shows what students are learning and their progress.

[1338] "Feedback" refers to information such as comments and advice provided regarding a student's learning situation and progress.

[1339] "Emotional state" refers to the psychological state of students or customers that can be analyzed from their facial expressions and voices.

[1340] "Cameras and microphones" are devices that capture video and audio.

[1341] "Emotion data" refers to data relating to an emotional state obtained from facial expressions, voice, etc.

[1342] "Individual optimization" means providing support that is optimized according to the characteristics and conditions of each student or customer.

[1343] The online tutoring system of this invention combines a generative AI model and an emotion engine to provide individually optimized learning support. A specific embodiment of this system will be described.

[1344] First, students must register to receive learning support. They access the system from a device (e.g., a PC or smartphone) and enter information such as their name, email address, password, and desired subjects. The device then sends this information to the server via an HTTP POST request. The server stores the received information in a database, and once registration is complete, generates a unique user ID and returns it to the device. The device then displays a message indicating registration is complete.

[1345] Next, the student enters their email address and password on the login page to authenticate. The device sends this information to the server, which checks the user information in the database. If authentication is successful, the server generates an authentication token and returns it to the device. The device saves the token and logs the user in.

[1346] When a student requests learning support, for example, "Study math equations for second-year junior high school students," the device sends this request to the server via an HTTP POST request. The server passes the request to a generative AI model, which generates the necessary learning content. The server then sends the generated learning content to the device, which then displays it.

[1347] Cameras and microphones are used to understand students' emotional states during learning. The devices capture students' facial expressions and voices in real time and analyze them using an emotion engine. This analysis data is sent from the device to the server, and the student's emotional state is reflected in the feedback. For example, if a student is confused, the server generates a more detailed explanation and sends it to the device. This allows students to receive individually optimized feedback.

[1348] The main software components of this system include a server-side generative AI model, user authentication, a database, and an emotion engine analysis API. The hardware required is a PC or smartphone equipped with a camera and microphone.

[1349] As a concrete example, let's consider the system's operation when a user named "Yamada Hanako" is studying mathematics for a second-year junior high school student. She accesses the system for the first time and completes registration after entering the necessary information. Next, she logs in and requests to study "equations." The system generates optimal learning content and displays it on the device. While studying, her emotional state is analyzed in real time using the camera and microphone, and feedback is adjusted as necessary.

[1350] Example prompt sentence:

[1351] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[1352] Login: "ichiro@example.com, password123"

[1353] Learning Request: "Explain quadratic equations"

[1354] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[1355] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on quadratic equations"

[1356] As described above, this invention is a system that provides learning support tailored to the emotional state of each student by linking a generative AI model with an emotion engine.

[1357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1358] Step 1:

[1359] Customer Registration

[1360] Terminal: When a customer first accesses the virtual store, they enter information such as their name, email address, password, and preferred product category. The entered information is sent to the server via an HTTP POST request. (Input) Customer information (Output) Send request to server.

[1361] Server: Stores the received customer information in a database, and after registration is complete generates a unique customer ID and returns it to the terminal. The terminal displays a registration completion message. (Input) Customer information (Data processing) Data verification and ID generation (Output) Registration completion message.

[1362] Step 2:

[1363] Login and Authentication

[1364] Terminal: The customer enters their email address and password on the login page and sends them to the server in an HTTP POST request. (Input) Authentication information (Output) Request sent to the server.

[1365] Server: Checks customer information in the database, and if authentication is successful, generates an authentication token and returns it to the terminal. The terminal saves the token and logs the customer in. (Input) Authentication information (Data processing work) Data verification and token generation (Output) Authentication token.

[1366] Step 3:

[1367] Customer Support Requests

[1368] Terminal: A customer asks a question about a product or requests support (e.g., "Tell me more about your new product"). The terminal sends this request to the server via an HTTP POST request. (Input) Customer request (Output) Request sent to the server.

[1369] Server: The request content is passed to the generation AI model, which generates the necessary support information. The server receives the generated support information and sends it to the terminal. (Input) Customer request (Data calculation) Support information generation (Output) Support information.

[1370] Step 4:

[1371] Emotion Engine Operation

[1372] Device: Captures customer facial expressions and voices in real time using a camera and microphone. Sends the captured data to the emotion engine API. (Input) Customer facial and voice data. (Output) Sends data to the emotion engine.

[1373] Emotion engine: Analyzes facial and voice data to recognize emotional states (e.g., joy, confusion, dissatisfaction, etc.). (Input) Facial and voice data (Data calculation) Emotion analysis (Output) Emotion data.

[1374] Step 5:

[1375] Response adjustment and feedback

[1376] Server: Based on the received emotion data, the generative AI model readjusts the support content and generates appropriate feedback. The generated feedback is sent to the device. (Input) Emotion data (Data calculation) Adjustment of support content (Output) Feedback.

[1377] Terminal: Displays the received feedback information to the customer. For example, if confusion is detected, a more detailed explanation is displayed. (Input) Feedback information (Output) Feedback display.

[1378] Example prompt sentence:

[1379] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[1380] Login: "ichiro@example.com, password123"

[1381] Customer Support Request: "Explain the details of the new smartphone"

[1382] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[1383] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on the new smartphone"

[1384] As described above, by appropriately processing input data at each step and utilizing a generative AI model and emotion engine, the system is able to provide optimal support tailored to the emotional state of each individual customer.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] [Fourth embodiment]

[1389] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1390] 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.

[1391] 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).

[1392] 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.

[1393] 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.

[1394] 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).

[1395] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1396] 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.

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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."

[1402] The present invention relates to an online tutoring system using a generative AI model, which includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, and means for providing the generated feedback to the student.

[1403] System program processing

[1404] The system does the following:

[1405] 1. User Registration

[1406] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[1407] The terminal sends this information to the server via an HTTP POST request.

[1408] The server verifies the information received and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the device.

[1409] The terminal displays a registration complete message to the user.

[1410] 2. Login and Authentication

[1411] The user enters their email address and password on the login page.

[1412] The terminal transmits this information to the server.

[1413] The server performs authentication against the database, and if there is a match, generates an authentication token and returns it to the terminal.

[1414] The device stores the token and remains logged in.

[1415] 3. Start of learning support

[1416] A user requests learning support (e.g., they want to understand a math equation better).

[1417] The terminal transmits the request contents to the server.

[1418] The server uses a generative AI model to generate learning content (e.g., explanations of equations, practice problems) in response to requests.

[1419] The generation AI generates learning materials and questions and returns them to the server.

[1420] The server transmits the generated learning content to the terminal, which displays it to the user.

[1421] 4. Progress monitoring and feedback

[1422] The user solves the practice problems and sends the results (correct or incorrect and time) from the terminal to the server.

[1423] The server analyzes this data and evaluates the user's learning status and level of understanding.

[1424] The server generates feedback using a generative AI model and returns the feedback to the device.

[1425] The terminal displays this feedback to the user.

[1426] Specific examples

[1427] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[1428] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[1429] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[1430] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[1431] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[1432] 5. Hanako Yamada solves the exercises and sends the results from her device to the server. The server analyzes this data and evaluates the user's level of understanding. It generates feedback and returns it to the device. The device displays the feedback to Hanako Yamada.

[1433] In this way, online tutoring systems utilizing generative AI can overcome geographical and economic constraints and provide comprehensive, high-quality learning support.

[1434] The processing flow will be explained below.

[1435] Program processing steps

[1436] Registering Users

[1437] Step 1:

[1438] When a user first accesses the system, a registration form is displayed.

[1439] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[1440] Step 2:

[1441] The terminal sends the entered information to the server via an HTTP POST request.

[1442] Step 3:

[1443] The server validates the information received (checks for required fields, verifies format, etc.).

[1444] Step 4:

[1445] After verification, the server stores the user data in a database and generates a unique user ID.

[1446] Step 5:

[1447] The server returns a registration completion message and the user ID to the terminal.

[1448] Step 6:

[1449] The terminal displays a registration completion message to the user.

[1450] Login and Authentication

[1451] Step 1:

[1452] The user visits the login page and enters their email address and password.

[1453] Step 2:

[1454] The device sends the entered login information to the server via an HTTP POST request.

[1455] Step 3:

[1456] The server checks the user information (email address and password) in its database.

[1457] Step 4:

[1458] If there is a match, the server generates an authentication token and returns it to the terminal.

[1459] Step 5:

[1460] The terminal stores the token and logs the user in.

[1461] Start of learning support

[1462] Step 1:

[1463] A user makes a learning support request (e.g., "8th grade math equations").

[1464] Step 2:

[1465] The terminal sends the request contents to the server using an HTTP POST request.

[1466] Step 3:

[1467] The server checks the request and requests the generative AI model to generate learning content.

[1468] Step 4:

[1469] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[1470] Step 5:

[1471] The generation AI returns the generated learning content to the server.

[1472] Step 6:

[1473] The server transmits the generated learning content to the terminal.

[1474] Step 7:

[1475] The terminal displays the learning content to the user.

[1476] Progress monitoring and feedback

[1477] Step 1:

[1478] The user solves the exercises.

[1479] Step 2:

[1480] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[1481] Step 3:

[1482] The device sends these results to the server via an HTTP POST request.

[1483] Step 4:

[1484] The server analyzes the received data and evaluates the user's learning progress.

[1485] Step 5:

[1486] The server uses the generative AI model to generate feedback to provide to the user.

[1487] Step 6:

[1488] The server transmits the generated feedback to the terminal.

[1489] Step 7:

[1490] The terminal displays the received feedback to the user.

[1491] Example 1

[1492] 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."

[1493] Conventional online tutoring systems have limited ability to respond to individual learning needs, making it difficult to provide appropriate feedback based on students' progress and level of understanding. Furthermore, regional restrictions limit the amount of learning support available. Therefore, there is a need for a system that can respond to individual user needs, monitor progress, and provide appropriate feedback.

[1494] 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.

[1495] In this invention, the server includes: a means for displaying a registration form when a user first accesses the system; a means for receiving and transmitting information entered by the user; a means for verifying the received information, saving it in a database, and generating a unique user ID; a means for authenticating the email address and password entered by the user and generating an authentication token; a means for receiving a user's learning request; a means for generating learning content based on prompts using a generative AI model; a means for providing the generated learning content to the user; a means for monitoring the user's progress and collecting data; a means for analyzing the collected data and generating feedback; and a means for providing the generated feedback to the user. This enables support tailored to the user's individual learning needs, provides appropriate feedback based on the student's progress and level of understanding, and realizes comprehensive learning support that transcends regional constraints.

[1496] "User" refers to an individual who uses this system to receive learning support.

[1497] The "registration form" is an interface for users to enter necessary information when they access the site for the first time.

[1498] The "server" is a central system that manages information from users, runs generative AI models, and connects with databases.

[1499] "Terminal" refers to a device that a user directly operates to input information and receive learning content and feedback.

[1500] A "database" is a system for storing user information, learning content, progress data, etc.

[1501] An "authentication token" is a code generated to authenticate a user's login status and enable the maintenance of a session.

[1502] A "learning request" is a request issued by a user seeking specific learning content or support.

[1503] A "generative AI model" is an algorithm or system that uses machine learning technology to automatically generate learning content and feedback in response to user requests.

[1504] A "prompt" is an instruction given to a generative AI model when generating learning content or feedback.

[1505] "Learning content" refers to educational materials such as explanatory materials and practice questions generated by a generative AI model.

[1506] "Progress data" is information relating to the learning progress and level of understanding that is collected while the user is receiving learning support.

[1507] "Feedback" is information containing learning improvement points and advice generated by the AI ​​model based on progress data.

[1508] This invention relates to an online tutoring system that uses a generative AI model, and provides a specific method for users to receive assistance tailored to their individual learning needs. This system includes a personal computer (terminal), a web server (server), a database, HTTP communication, and a generative AI model (e.g., OpenAI's GPT model), and is implemented as follows:

[1509] Registering Users

[1510] When a user accesses the system for the first time, a registration form is displayed. The user enters their name, email address, password, age, grade, desired subjects, etc. This information is collected by the terminal and sent to the server using an HTTP POST request. The server verifies the received information and stores it in a database (e.g., MySQL). Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user saying "Registration complete."

[1511] Login and Authentication

[1512] The user enters their email address and password on the login page. This information is sent via the device to the server, which checks it against the user information in its database. If it matches, it generates an authentication token (e.g., JSON Web Token, JWT) and returns it to the device. The device stores the token and displays a "Login successful" message to the user.

[1513] Start of learning support

[1514] When a user clicks the "Request Learning Support" button on the dashboard, the device sends the request to the server. The server sends an appropriate prompt to a generative AI model (e.g., OpenAI GPT-4), which then generates learning content (e.g., explanatory materials, practice questions). The generated learning content is sent to the device via the server, and the device displays it to the user.

[1515] Example prompts include:

[1516] "Generate math equation practice problems for eighth graders."

[1517] Progress monitoring and feedback

[1518] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. This data is sent from the device to a server, which analyzes the data. For example, the user's correct answer rate and answer time are calculated. Feedback is generated using a generative AI model and returned from the server to the device. The device displays the feedback to the user.

[1519] This system provides support tailored to each user's individual learning needs, allowing them to receive high-quality learning support without being restricted by geographical location.

[1520] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1521] Step 1: Registering a user

[1522] When a user accesses the system for the first time, a registration form is displayed in which they enter their name, email address, password, age, grade, desired subjects, etc.

[1523] The device collects this information and sends it to the server using an HTTP POST request, along with the input data (name, email address, password, age, grade, and desired subjects).

[1524] The server verifies the received information (checks the format of the email address and the strength of the password), and if the verification is successful, it saves the new user information in a database (e.g. MySQL). After saving it in the database, the server generates a unique user ID and returns it to the terminal. The output is the user ID and a success message.

[1525] The terminal displays the message "Registration Complete" to the user, thereby completing the user's registration.

[1526] Step 2: Login and Authentication

[1527] The user enters their email address and password on the login page. The data entered is the email address and password.

[1528] The device sends this information to the server using an HTTP POST request.

[1529] The server checks the user information in its database against the entered information. If the check results match, it generates an authentication token (e.g., JSON Web Token, JWT). The output is the authentication token. If the check results do not match, it generates an error message.

[1530] The server returns an authentication token to the device, which stores it in local storage, allowing session management. The device displays a successful login message to the user and redirects them to the dashboard or home page.

[1531] Step 3: Start learning support

[1532] The user clicks the "Request Learning Support" button on the dashboard. At this time, the user's request (learning content request) becomes the input data.

[1533] The device sends the request content to the server using an HTTP POST request.

[1534] The server generates an appropriate prompt for the generative AI model (e.g., OpenAI GPT-4). This prompt is a sentence such as "Please generate practice problems and explanations for math equations for eighth-grade students." Sending this prompt to the generative AI corresponds to data processing and data calculation.

[1535] The generative AI model generates learning content (e.g., explanatory materials, practice questions) based on the prompts. The output is the generated learning content.

[1536] The generation AI returns the generated learning content to the server, and the server sends the content to the device.

[1537] The terminal displays the learning content to the user.

[1538] Step 4: Progress monitoring and feedback

[1539] When a user solves a practice problem, the results (correct answers and answer time) are saved on the device. These results become input data.

[1540] The device sends the results to the server using an HTTP POST request.

[1541] The server analyzes the received data. For example, it calculates the percentage of correct answers and tallys up the answering time. This corresponds to data processing and data calculation.

[1542] Based on this, the server evaluates the user's learning status and level of understanding. Based on the evaluation results, a generative AI model is used to generate feedback. The output is the generated feedback. Specific examples include "advice on how to solve equations" and "additional practice problems."

[1543] The server sends the feedback to the terminal, which displays the feedback to the user.

[1544] (Application example 1)

[1545] 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."

[1546] In today's educational environment, it is difficult for learners in remote locations to receive high-quality learning support, especially in the absence of an environment where individualized instruction can be provided in real time. Furthermore, there is a lack of systems that can efficiently monitor learning progress in virtual classroom environments and provide appropriate feedback in real time. Furthermore, there is a need for a means to provide an interactive educational environment without attending a physical classroom.

[1547] 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.

[1548] In this invention, the server includes means for receiving a learning request from a learner, means for generating learning content using a generative AI model, means for providing the generated learning content to the learner, means for monitoring the learner's progress data in real time during learning activities in a virtual environment, means for providing an interactive virtual classroom environment, and means for allowing the learner to participate in the virtual classroom using a head-mounted display or VR device, thereby enabling real-time monitoring of learning progress and provision of individualized instruction.

[1549] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate appropriate answers or content for specific tasks or questions.

[1550] "Student" means an individual who receives education or learning support through this system.

[1551] A "learning need" is a request by a learner for support or instruction on a particular learning content or topic.

[1552] "Learning content" refers to educational materials such as teaching materials and workbooks that are generated by a generative AI model based on the learner's learning requirements.

[1553] "Progress data" refers to data such as the grades and response times a learner obtains through learning activities.

[1554] "Feedback" refers to information such as advice and comments to learners that is generated by analyzing the learner's progress data.

[1555] A "virtual environment" is a system that uses virtual reality technology to provide an interactive learning environment similar to a physical classroom.

[1556] A "virtual classroom" is a virtual classroom in which learners can participate remotely using head-mounted displays or VR devices.

[1557] "Interactive" refers to the ability of learners to interact with the system in real time.

[1558] A "head-mounted display" is a device worn on the head that displays visual information and is used to provide a VR experience.

[1559] A "VR device" is a hardware device that allows you to experience virtual reality.

[1560] This invention relates to an online tutoring system that uses generative AI models to provide learning support to learners. This system allows learners to access the system via the Internet and receive real-time learning support in a virtual classroom environment.

[1561] Specifically, the system includes the following hardware and software configuration:

[1562] Server: Flask (Python framework), SQLite (database), TensorFlow (generative AI model), Pandas (data analysis)

[1563] Devices: Smartphones, tablets, and head-mounted displays (e.g., Oculus Rift, HTC Vive) used by learners

[1564] Communication method: Internet connection (Wi-Fi or mobile network)

[1565] Program processing

[1566] 1. User Registration:

[1567] When a user first accesses the system, they are presented with a user registration form where they enter their name, email address, password, age, grade, and desired subjects. The device sends this information to the server via an HTTPS request, which then verifies it and stores it in a database.

[1568] 2. Login and Authentication:

[1569] The user logs in by entering their email address and password. The device sends this to the server, which then authenticates it in the database, generates a JWT (JSON Web Token), and returns it to the device as a token. This token is used to maintain the logged-in state.

[1570] 3. Learning support begins:

[1571] When a user requests learning support (e.g., "I want to learn the equations of motion in physics"), the device sends the request to the server. The generative AI model generates learning content based on the user's request, and the server provides it to the device.

[1572] 4. Progress monitoring and feedback:

[1573] As users study in the virtual classroom and attempt practice problems, their results (e.g., percentage of correct answers and time required to answer) are sent from their devices to the server. The server analyzes the progress data, generates feedback that evaluates the learner's level of understanding, and returns it to the device.

[1574] 5. Virtual Classroom:

[1575] Learners can use head-mounted displays to participate in virtual classrooms and take interactive lessons in real time. Progress data during learning activities is monitored in real time, and timely feedback is provided.

[1576] Examples of concrete examples and prompts

[1577] Specific examples

[1578] User: High school student A

[1579] Learning content: Physics equations of motion

[1580] scenario:

[1581] 1. Learner A launches the Virtual Classroom app on their smartphone and registers on their first visit.

[1582] 2. Enter your name, email address, password, grade, and desired subject (physics) to complete registration.

[1583] 3. Log in and request to learn about "Equations of Motion."

[1584] 4. The generative AI model generates learning content on the equation of motion and provides it to Learner A.

[1585] 5. Learner A solves the practice problems and sends the results to the server.

[1586] 6. The server analyzes the data and provides feedback to Learner A based on their level of understanding.

[1587] Prompt Sentence Examples

[1588] User name: Student A, Grade: 2nd year high school student, Subject: Physics

[1589] "Generate educational content related to the equations of motion."

[1590] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1591] Step 1:

[1592] When a user accesses the system for the first time, a user registration form is displayed. The user enters their name, email address, password, age, grade level, and desired subjects. The entered information is sent to the server using an HTTPS request on the terminal. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The terminal displays a message to the user indicating that registration is complete.

[1593] Step 2:

[1594] The user enters their email address and password on the login page. The device sends this information to the server. The server performs authentication in the database, and if the email address and password match, it generates a JWT (JSON Web Token) and returns it to the device. The device saves the token and maintains the logged-in state. The input data is the email address and password, and the output data is an authentication token.

[1595] Step 3:

[1596] A user requests learning support. For example, they might request, "I want to learn the equations of motion in physics." The device sends this request to the server. The server uses a generative AI model to generate learning content that corresponds to the request. The generative AI model uses pre-trained data to automatically generate learning materials based on the prompt sentence. The generated learning content is sent from the server to the device, which displays it to the user. The input data is the learning request, and the output data is the learning content.

[1597] Step 4:

[1598] Users study the learning content provided in the virtual classroom. Learners can participate in the virtual classroom using VR devices such as head-mounted displays. When learners solve practice problems, the results (correct answer rate and answer time) are sent from their devices to the server. The input data are the answers to the practice problems, and the output data are progress data for analysis.

[1599] Step 5:

[1600] The server analyzes the received progress data. Using data analysis tools such as Pandas, it evaluates the progress data and generates feedback based on the generative AI model. The generated feedback is sent from the server to the terminal, which displays the feedback to the user. The input data is the progress data to be analyzed, and the output data is the generated feedback.

[1601] Step 6:

[1602] The learner uses the generated feedback to further study. The server then uses the generative AI model again to provide learning content based on the learner's new requests and challenges. This process is repeated until the user has sufficiently deepened their understanding. The input data is feedback, and the output data is the regenerated learning content.

[1603] 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.

[1604] This invention combines an emotion engine with an online tutoring system that utilizes generative AI models to provide more effective learning support to students. The system recognizes users' emotions and adjusts learning content and feedback based on those emotions, enabling a personalized learning experience.

[1605] System program processing

[1606] The system does the following:

[1607] 1. User Registration

[1608] When a user first accesses the system, they are presented with a registration form where they enter their name, email address, password, age, grade, and desired subjects.

[1609] The device sends this information to the server via an HTTP POST request.

[1610] The server verifies the received information, stores it in a database, and once registration is complete, generates a unique user ID and returns it to the device.

[1611] The terminal displays a registration complete message to the user.

[1612] 2. Login and Authentication

[1613] The user enters their email address and password on the login page.

[1614] The terminal transmits this information to the server.

[1615] The server checks the user information (email address and password) in its database.

[1616] If there is a match, the server generates an authentication token and returns it to the terminal.

[1617] The terminal stores the token and logs the user in.

[1618] 3. Start of learning support

[1619] A user makes a learning support request (e.g., "8th grade math equations").

[1620] The terminal sends the request contents to the server using an HTTP POST request.

[1621] The server checks the request and requests the generative AI model to generate learning content.

[1622] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[1623] The generation AI returns the generated learning content to the server.

[1624] The server transmits the generated learning content to the terminal.

[1625] The terminal displays the learning content to the user.

[1626] 4. Operation of the Emotion Engine

[1627] The device captures the user's facial expressions and voice through a camera and microphone.

[1628] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[1629] The device transmits the recognized emotion data to the server.

[1630] 5. Progress monitoring and feedback

[1631] The user solves the practice problems and enters the results (correct or incorrect and time) into the terminal.

[1632] The device sends these results to the server via an HTTP POST request.

[1633] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[1634] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[1635] The server transmits the generated feedback to the terminal.

[1636] The terminal displays the received feedback to the user.

[1637] Specific examples

[1638] User name: Yamada Hanako, Grade: 2nd year of junior high school, Subject: Mathematics

[1639] 1. Hanako Yamada accesses the system from her home computer (terminal) and enters the necessary information in the registration form. After entering the information, the terminal sends this information to the server.

[1640] 2. The server verifies the received information and stores it in the database. Once registration is complete, it generates a unique user ID and returns it to the terminal. The terminal then displays the message "Registration completed" to Hanako Yamada.

[1641] 3. Hanako Yamada enters her email address and password on the login page, and the device sends this to the server. The server authenticates it in the database, generates an authentication token, and returns it to the device. The device saves the token and maintains the logged-in state.

[1642] 4. When Hanako Yamada requests to deepen her understanding of "equations," her device sends this request to the server. The server uses the generative AI model to generate learning content related to equations and provides it to her device. The device then displays materials and practice problems for Hanako Yamada.

[1643] 5. While Hanako Yamada is working on the exercises, the device captures her facial expressions and voice through a camera and microphone. The emotion engine analyzes this data and recognizes that she is confused.

[1644] 6. Hanako Yamada completes the exercise and enters her results into her device. The device sends these results to the server, which analyzes the progress and emotion data it receives to assess her level of understanding. Using a generative AI model, the server generates feedback with detailed explanations to alleviate her confusion and sends it to the device.

[1645] 7. The device displays the received feedback to Hanako Yamada to support her learning.

[1646] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[1647] The processing flow will be explained below.

[1648] Program processing steps

[1649] Registering Users

[1650] Step 1:

[1651] When a user first accesses the system, a registration form is displayed.

[1652] Users enter their name, email address, password, age, grade, desired subjects to study, etc.

[1653] Step 2:

[1654] The terminal sends the entered information to the server via an HTTP POST request.

[1655] Step 3:

[1656] The server validates the information received (checks for required fields, verifies format, etc.).

[1657] Step 4:

[1658] After verification, the server stores the user data in a database and generates a unique user ID.

[1659] Step 5:

[1660] The server returns a registration completion message and the user ID to the terminal.

[1661] Step 6:

[1662] The terminal displays a registration completion message to the user.

[1663] Login and Authentication

[1664] Step 1:

[1665] The user visits the login page and enters their email address and password.

[1666] Step 2:

[1667] The device sends the entered login information to the server via an HTTP POST request.

[1668] Step 3:

[1669] The server checks the user information (email address and hashed password) in its database.

[1670] Step 4:

[1671] If there is a match, the server generates an authentication token and returns it to the terminal.

[1672] Step 5:

[1673] The terminal stores the token and logs the user in.

[1674] Start of learning support

[1675] Step 1:

[1676] A user makes a learning support request (e.g., "8th grade math equations").

[1677] Step 2:

[1678] The terminal sends the request contents to the server using an HTTP POST request.

[1679] Step 3:

[1680] The server checks the request and requests the generative AI model to generate learning content.

[1681] Step 4:

[1682] Generative AI generates learning content (e.g., explanatory materials, practice questions) based on requests.

[1683] Step 5:

[1684] The generation AI returns the generated learning content to the server.

[1685] Step 6:

[1686] The server transmits the generated learning content to the terminal.

[1687] Step 7:

[1688] The terminal displays the learning content to the user.

[1689] Emotion Engine Operation

[1690] Step 1:

[1691] The device captures the user's facial expressions and voice through a camera and microphone.

[1692] Step 2:

[1693] The emotion engine analyzes this data and recognizes the user's emotional state (e.g., joy, sadness, confusion, etc.).

[1694] Step 3:

[1695] The device sends the recognized emotion data to the server via an HTTP POST request.

[1696] Progress monitoring and feedback

[1697] Step 1:

[1698] The user solves the exercises.

[1699] Step 2:

[1700] The user enters the results of the practice questions they have solved (correct answers, time taken, etc.) into the terminal.

[1701] Step 3:

[1702] The device sends the result data to the server via an HTTP POST request.

[1703] Step 4:

[1704] The server analyzes the received progress data and emotion data to evaluate the user's learning status and level of understanding.

[1705] Step 5:

[1706] The server uses the generative AI model to generate feedback to provide to the user, taking into account emotional data and adjusting the feedback content (e.g., adding more detailed explanations if the user is confused).

[1707] Step 6:

[1708] The server sends the generated feedback to the device via an HTTP POST request.

[1709] Step 7:

[1710] The terminal displays the received feedback to the user.

[1711] Example 2

[1712] 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."

[1713] In online learning systems, general learning support that ignores students' emotional states is insufficient to provide an effective learning experience. For example, if a student is confused, appropriate feedback and support may not be provided. Therefore, it is necessary to recognize students' emotional states in real time and adjust learning content and feedback based on their emotional states.

[1714] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for capturing the student's facial expressions and voice, means for analyzing the captured data to recognize the student's emotions, means for receiving and storing the recognized emotion data, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and emotion data and generating feedback, and means for providing the generated feedback to the student. This enables effective learning support tailored based on the student's emotional state.

[1715] The "means for receiving student learning requests" is an input interface for students to request the learning content and support they desire.

[1716] "Means for generating learning content using generative AI models" refers to a function that utilizes generative AI to automatically create learning materials and workbooks based on student requests.

[1717] "Means for providing generated learning content to students" refers to the function for sending the generated learning materials and question sets to students' devices and displaying them.

[1718] "Means for capturing student facial expressions and voices" refers to devices or functions that use cameras and microphones to record and record students' facial expressions and voices.

[1719] The "means for analyzing captured data to recognize student emotions" refers to algorithms or software for analyzing the acquired facial and voice data and determining the student's emotional state.

[1720] The "means for receiving and storing recognized emotion data" is a function for transmitting analyzed emotion data to a server and storing it in a database.

[1721] "Means for monitoring student learning progress" refers to a function for tracking and recording the progress of students as they study, whether their answers are correct or incorrect, and the time it takes to answer.

[1722] The "means for analyzing students' learning progress data and emotional data and generating feedback" refers to algorithms or software for generating feedback based on the acquired progress data and emotional data according to the students' level of understanding and emotional state.

[1723] The "means for providing the generated feedback to the student" is a function for transmitting the generated feedback to the student's terminal and displaying it.

[1724] This invention is an online tutoring system that uses a generative AI model to recognize a student's emotional state and adjust learning content and feedback based on that state to provide a personalized learning experience. The system operates through a series of processes, including user registration, login and authentication, initiation of learning support, operation of the emotion engine, and progress monitoring and feedback.

[1725] Hardware and software used

[1726] Device: A computer or smartphone used by a student. A device is equipped with a camera and microphone.

[1727] Server: Responsible for the backend processing of the entire system, including user authentication, database management, sending requests to the AI ​​model, and managing generated content.

[1728] Generative AI model: An AI that generates learning content based on student requests. Examples of generative models include GPT (Generative Pre-trained Transformer).

[1729] Emotion engine: An algorithm that analyzes students' facial and vocal data to determine their emotional state. This engine uses a deep learning model.

[1730] System program processing

[1731] 1. User Registration

[1732] When a user accesses the system for the first time, a registration form is displayed on the terminal. The user enters basic information such as name, email address, password, age, grade, and desired subjects. The terminal sends this information to the server via an HTTP POST request. The server verifies the received information and stores it in a database. Once registration is complete, a unique user ID is generated and returned to the terminal. The user sees a message on the screen saying "Registration complete."

[1733] 2. Login and Authentication

[1734] The user enters their email address and password on the login page, and the device sends this to the server. The server accesses a database to verify that the email address and password combination is correct. If they match, the server generates an authentication token and returns it to the device. The device stores the token, and the user is logged in.

[1735] 3. Start of learning support

[1736] When a user requests learning support, for example, they send a request to learn "mathematical equations for second-year junior high school students." The device sends this content to the server via an HTTP POST request. The server analyzes the request and asks the generative AI model to generate learning content. The generative AI model generates learning content (e.g., explanations and practice problems for equations) based on the prompt and returns it to the server. The server then sends the content to the device and displays it to the user.

[1737] 4. Operation of the Emotion Engine

[1738] The device uses a camera and microphone to capture students' facial expressions and voices in real time. The emotion engine analyzes this data and recognizes the student's emotional state. The device then transmits the recognized emotion data to the server, which stores the received emotion data and uses it for subsequent feedback.

[1739] 5. Progress monitoring and feedback

[1740] When a user solves the provided practice problems, they enter the results (correct / incorrect answers, response time) into their device. The device then sends these results to the server, which combines progress data and emotional data to evaluate the user's level of understanding. The server then uses a generative AI model to generate feedback based on the user's level of understanding and emotional state. The generated feedback is sent to the device and displayed to the user.

[1741] Examples of concrete examples and prompts

[1742] Specific examples

[1743] Username: Yamada Taro

[1744] Age: 14

[1745] Grade: 2nd year of junior high school

[1746] Subject: Mathematics (Equations)

[1747] Request: I want to learn math equations for second-year junior high school students.

[1748] Prompt Sentence Examples

[1749] Username: Yamada Taro

[1750] Grade: 2nd year of junior high school

[1751] Subject: Mathematics

[1752] What you'll learn: Generate materials and exercises to deepen your understanding of equations

[1753] Emotional state: Confused

[1754] In this way, an online tutoring system that combines a generative AI model and an emotion engine can provide individually optimized, high-quality learning support.

[1755] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1756] Step 1: Registering a user

[1757] Input: The user enters registration information into the terminal, including name, email address, password, age, grade, and desired subjects.

[1758] Specific operation: The user accesses the system and enters the required information into the displayed registration form. The terminal sends this information to the server via an HTTP POST request.

[1759] Data processing / data calculation: The server validates the information it receives, for example, checking that the email address is formatted correctly or that the password meets requirements.

[1760] Output: After verification, the server saves the data in the database, generates a unique user ID and returns it to the terminal, which displays a message to the user saying "Registration completed."

[1761] Step 2: Login and Authentication

[1762] Input: The user enters their email address and password on the login page.

[1763] Specific operation: The device sends this information to the server via an HTTP POST request.

[1764] Data processing / data calculation: The server accesses the database and checks whether the email address and password combination sent is correct. If they match, it generates an authentication token.

[1765] Output: The server returns an authentication token to the device, which stores the token and logs the user in.

[1766] Step 3: Start learning support

[1767] Input: The user types the request "I want to learn eighth grade math equations" into the terminal.

[1768] Specific operation: The device sends the request content to the server via an HTTP POST request.

[1769] Data processing / data calculation: The server analyzes the received request content, generates a prompt sentence, and sends it to the generative AI model.

[1770] Example: "User name: Yamada Taro, Grade: 8th grade, Subject: Mathematics, Learning content: Please generate materials and practice problems to deepen my understanding of equations, Emotional state: Confused."

[1771] Output: The generative AI model generates learning content (explanatory materials, practice questions) and returns it to the server, which sends it to the device, which displays the content to the user.

[1772] Step 4: Emotion Engine in Action

[1773] Input: The user's facial expressions and voice are captured by the camera and microphone.

[1774] Specific operation: The device captures the user's video and audio in real time.

[1775] Data processing / data calculation: The emotion engine analyzes this data and recognizes the user's emotions (happiness, sadness, confusion, etc.).

[1776] Output: The recognized emotion data is sent from the device to the server, where it is stored.

[1777] Step 5: Progress monitoring and feedback

[1778] Input: The user solves the exercises and enters the results (correct / incorrect and answer time) into the terminal.

[1779] Specific operation: The device sends the results of the exercise to the server via an HTTP POST request.

[1780] Data processing / data calculation: The server integrates the progress data and emotion data to evaluate the user's level of understanding and learning status. It uses a generative AI model to generate feedback tailored to the user.

[1781] For example, adjustments are made, such as adding more detailed explanations for confused users.

[1782] Output: The server sends the generated feedback to the device, which displays it to the user.

[1783] The above is the flow of processing in the program for this system, and details of the specific operations, data processing, and data calculations in each processing step.

[1784] (Application example 2)

[1785] 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."

[1786] Conventional online tutoring systems provide learning content and monitor progress according to students' learning needs, but they are unable to adjust feedback based on the student's emotional state. As a result, support for students' understanding and motivation may be insufficient. Furthermore, customer support in virtual stores faces the challenge of providing optimal support based on the customer's emotions.

[1787] 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.

[1788] In this invention, the server includes means for receiving a student's learning request, means for generating learning content using a generative AI model, means for providing the generated learning content to the student, means for monitoring the student's learning progress, means for analyzing the student's learning progress data and generating feedback, means for providing the generated feedback to the student, means for collecting information using a camera or microphone to analyze the student's emotional state, and means for adjusting the learning content and feedback based on the collected emotional data. This enables individually optimized learning support based on the student's emotional state, improving learning effectiveness and enabling customer support in the virtual store to be provided in response to customer emotions.

[1789] A "generative AI model" is an artificial intelligence model that adaptively learns based on input data and automatically generates the necessary information and content.

[1790] An "online tutoring system" is a computer system that provides learning support to students via the Internet.

[1791] "Learning needs" are requests for content or skills that students want to learn.

[1792] "Learning content" is a general term for teaching materials, resources, practice questions, etc. that students use to study.

[1793] "Learning progress" is data that shows what students are learning and their progress.

[1794] "Feedback" refers to information such as comments and advice provided regarding a student's learning situation and progress.

[1795] "Emotional state" refers to the psychological state of students or customers that can be analyzed from their facial expressions and voices.

[1796] "Cameras and microphones" are devices that capture video and audio.

[1797] "Emotion data" refers to data relating to an emotional state obtained from facial expressions, voice, etc.

[1798] "Individual optimization" means providing support that is optimized according to the characteristics and conditions of each student or customer.

[1799] The online tutoring system of this invention combines a generative AI model and an emotion engine to provide individually optimized learning support. A specific embodiment of this system will be described.

[1800] First, students must register to receive learning support. They access the system from a device (e.g., a PC or smartphone) and enter information such as their name, email address, password, and desired subjects. The device then sends this information to the server via an HTTP POST request. The server stores the received information in a database, and once registration is complete, generates a unique user ID and returns it to the device. The device then displays a message indicating registration is complete.

[1801] Next, the student enters their email address and password on the login page to authenticate. The device sends this information to the server, which checks the user information in the database. If authentication is successful, the server generates an authentication token and returns it to the device. The device saves the token and logs the user in.

[1802] When a student requests learning support, for example, "Study math equations for second-year junior high school students," the device sends this request to the server via an HTTP POST request. The server passes the request to a generative AI model, which generates the necessary learning content. The server then sends the generated learning content to the device, which then displays it.

[1803] Cameras and microphones are used to understand students' emotional states during learning. The devices capture students' facial expressions and voices in real time and analyze them using an emotion engine. This analysis data is sent from the device to the server, and the student's emotional state is reflected in the feedback. For example, if a student is confused, the server generates a more detailed explanation and sends it to the device. This allows students to receive individually optimized feedback.

[1804] The main software components of this system include a server-side generative AI model, user authentication, a database, and an emotion engine analysis API. The hardware required is a PC or smartphone equipped with a camera and microphone.

[1805] As a concrete example, let's consider the system's operation when a user named "Yamada Hanako" is studying mathematics for a second-year junior high school student. She accesses the system for the first time and completes registration after entering the necessary information. Next, she logs in and requests to study "equations." The system generates optimal learning content and displays it on the device. While studying, her emotional state is analyzed in real time using the camera and microphone, and feedback is adjusted as necessary.

[1806] Example prompt sentence:

[1807] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[1808] Login: "ichiro@example.com, password123"

[1809] Learning Request: "Explain quadratic equations"

[1810] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[1811] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on quadratic equations"

[1812] As described above, this invention is a system that provides learning support tailored to the emotional state of each student by linking a generative AI model with an emotion engine.

[1813] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1814] Step 1:

[1815] Customer Registration

[1816] Terminal: When a customer first accesses the virtual store, they enter information such as their name, email address, password, and preferred product category. The entered information is sent to the server via an HTTP POST request. (Input) Customer information (Output) Send request to server.

[1817] Server: Stores the received customer information in a database, and after registration is complete generates a unique customer ID and returns it to the terminal. The terminal displays a registration completion message. (Input) Customer information (Data processing) Data verification and ID generation (Output) Registration completion message.

[1818] Step 2:

[1819] Login and Authentication

[1820] Terminal: The customer enters their email address and password on the login page and sends them to the server in an HTTP POST request. (Input) Authentication information (Output) Request sent to the server.

[1821] Server: Checks customer information in the database, and if authentication is successful, generates an authentication token and returns it to the terminal. The terminal saves the token and logs the customer in. (Input) Authentication information (Data processing work) Data verification and token generation (Output) Authentication token.

[1822] Step 3:

[1823] Customer Support Requests

[1824] Terminal: A customer asks a question about a product or requests support (e.g., "Tell me more about your new product"). The terminal sends this request to the server via an HTTP POST request. (Input) Customer request (Output) Request sent to the server.

[1825] Server: The request content is passed to the generation AI model, which generates the necessary support information. The server receives the generated support information and sends it to the terminal. (Input) Customer request (Data calculation) Support information generation (Output) Support information.

[1826] Step 4:

[1827] Emotion Engine Operation

[1828] Device: Captures customer facial expressions and voices in real time using a camera and microphone. Sends the captured data to the emotion engine API. (Input) Customer facial and voice data. (Output) Sends data to the emotion engine.

[1829] Emotion engine: Analyzes facial and voice data to recognize emotional states (e.g., joy, confusion, dissatisfaction, etc.). (Input) Facial and voice data (Data calculation) Emotion analysis (Output) Emotion data.

[1830] Step 5:

[1831] Response adjustment and feedback

[1832] Server: Based on the received emotion data, the generative AI model readjusts the support content and generates appropriate feedback. The generated feedback is sent to the device. (Input) Emotion data (Data calculation) Adjustment of support content (Output) Feedback.

[1833] Terminal: Displays the received feedback information to the customer. For example, if confusion is detected, a more detailed explanation is displayed. (Input) Feedback information (Output) Feedback display.

[1834] Example prompt sentence:

[1835] Register: "Suzuki Ichiro, email@example.com, password123, interest: electronics"

[1836] Login: "ichiro@example.com, password123"

[1837] Customer Support Request: "Explain the details of the new smartphone"

[1838] Emotion recognition: "image: customer_face.jpg, audio: customer_voice.wav"

[1839] Feedback adjustment: "Emotion detected: confusion, provide additional explanation on the new smartphone"

[1840] As described above, by appropriately processing input data at each step and utilizing a generative AI model and emotion engine, the system is able to provide optimal support tailored to the emotional state of each individual customer.

[1841] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1842] 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.

[1843] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1844] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1845] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1846] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1847] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1848] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1849] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1850] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1851] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1852] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1853] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1854] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1855] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1856] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1857] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1858] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1859] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1860] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1861] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1862] The following is further disclosed regarding the above embodiment.

[1863] (Claim 1)

[1864] An online tutoring system that uses a generative AI model to provide learning support to students,

[1865] a means of receiving students' learning requirements;

[1866] A means for generating learning content using a generative AI model;

[1867] a means for providing the generated learning content to students;

[1868] a means of monitoring students' learning progress;

[1869] a means of analyzing student learning progress data and generating feedback;

[1870] a means of providing the generated feedback to students;

[1871] A system including:

[1872] (Claim 2)

[1873] 10. The system of claim 1, further comprising means for authenticating the student.

[1874] (Claim 3)

[1875] 10. The system of claim 1, which is accessible via the Internet without geographical restrictions.

[1876] "Example 1"

[1877] (Claim 1)

[1878] a means for displaying a registration form when a user first accesses the system and receiving and transmitting information entered by the user;

[1879] A means of validating the received information, storing it in a database, and generating a unique user ID;

[1880] A means for authenticating the email address and password entered by the user and generating an authentication token;

[1881] means for receiving a user's learning request;

[1882] a means for generating learning content based on the prompt sentence using a generative AI model;

[1883] a means for providing the generated learning content to a user;

[1884] a means for monitoring the user's progress and collecting data;

[1885] a means of analyzing the collected data and generating feedback;

[1886] means for providing the generated feedback to a user;

[1887] A system including:

[1888] (Claim 2)

[1889] 10. The system of claim 1, further comprising means for authenticating a user.

[1890] (Claim 3)

[1891] 10. The system of claim 1, which is accessible via the Internet without geographical restrictions.

[1892] "Application Example 1"

[1893] (Claim 1)

[1894] An online tutoring system that uses a generative AI model to provide learning support to learners,

[1895] A means for receiving learning requests from learners;

[1896] A means for generating learning content using a generative AI model;

[1897] a means for providing the generated learning content to the learner;

[1898] a means of monitoring learners' learning progress;

[1899] means for analyzing learner progress data and generating feedback;

[1900] a means of providing the generated feedback to the learner;

[1901] A means for monitoring learner progress data in real time during learning activities in the virtual environment; and

[1902] a means for providing an interactive virtual classroom environment;

[1903] A means for learners to participate in a virtual classroom via a head-mounted display or VR device;

[1904] A system including:

[1905] (Claim 2)

[1906] 10. The system of claim 1, further comprising means for authenticating the learner.

[1907] (Claim 3)

[1908] 10. The system of claim 1, which is accessible via the Internet without geographical restrictions.

[1909] "Example 2: Combining Emotion Engines"

[1910] (Claim 1)

[1911] a means of receiving students' learning requirements;

[1912] A means for generating learning content using a generative AI model;

[1913] a means for providing the generated learning content to students;

[1914] A means of capturing students' facial expressions and voices,

[1915] a means of analyzing the captured data to recognize student emotions;

[1916] means for receiving and storing the recognized emotion data;

[1917] a means of monitoring students' learning progress;

[1918] a means for analyzing the student's learning progress data and emotion data and generating feedback;

[1919] a means of providing the generated feedback to students;

[1920] A system including:

[1921] (Claim 2)

[1922] 10. The system of claim 1, further comprising means for authenticating the student.

[1923] (Claim 3)

[1924] 10. The system of claim 1, which is accessible via the Internet without geographical restrictions.

[1925] "Application example 2 when combining emotion engines"

[1926] (Claim 1)

[1927] An online tutoring system that uses a generative AI model to provide learning support to students,

[1928] a means of receiving students' learning requirements;

[1929] A means for generating learning content using a generative AI model;

[1930] a means for providing the generated learning content to students;

[1931] a means of monitoring students' learning progress;

[1932] a means of analyzing student learning progress data and generating feedback;

[1933] a means of providing the generated feedback to students;

[1934] A means of collecting information using cameras and microphones to analyze students' emotional states;

[1935] a means of tailoring learning content and feedback based on collected emotional data;

[1936] A system including:

[1937] (Claim 2)

[1938] 10. The system of claim 1, further comprising means for authenticating the student.

[1939] (Claim 3)

[1940] 10. The system of claim 1, which is accessible via the Internet without geographical restrictions. [Explanation of symbols]

[1941] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. An online tutoring system that uses a generative AI model to provide learning support to students, a means of receiving students' learning requirements; A means for generating learning content using a generative AI model; a means for providing the generated learning content to students; a means of monitoring students' learning progress; a means of analyzing student learning progress data and generating feedback; a means of providing the generated feedback to students; A system including:

2. The system of claim 1 further comprising means for authenticating the student.

3. 10. The system of claim 1, which is accessible via the Internet without geographical restrictions.

Images