System

Abstract

A system is provided.SOLUTION: A system comprising: means for causing a generative artificial intelligence to learn a teacher's know-how; means for selecting a subject that a user wants to learn and a type of the teacher; means for generating a lesson plan corresponding to the generative artificial intelligence based on the user's selection; and means for displaying the generated lesson plan to the user.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 the traditional education system, there is a wide variation in the quality of teachers and teaching methods, making it difficult to provide a uniform, high-quality education. Students are also restricted in the time and place they want to study, making it difficult to provide a flexible learning environment. Furthermore, there is a limited number of instructors with excellent teaching skills, limiting opportunities to receive instruction from these instructors. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] By providing a means to teach generative artificial intelligence the know-how of teachers, the skills and knowledge of excellent teachers can be input into the AI ​​model, enabling the provision of uniform, high-quality education.

[0007] Additionally, providing a means for users to select the subjects and type of teacher they wish to study allows each student to receive an education customized to their needs.

[0008] In addition, by providing a means for generative artificial intelligence to generate corresponding lesson plans based on user selections, it is possible to quickly and accurately provide educational content that meets individual needs.

[0009] By providing a means for displaying the generated lesson plan to the user, an environment is created in which students can immediately learn the educational content they need.

[0010] This allows users to take lesson plans at any time, overcoming time constraints and providing a flexible learning environment.

[0011] Furthermore, the AI ​​model, which has the know-how of a variety of teachers, can select different types of teachers in response to user requests, thereby personalizing learning content and teaching methods and increasing opportunities for high-quality education.

[0012] "Teacher know-how" is information that indicates specific skills, knowledge, and experience related to education and teaching.

[0013] "Generative AI" refers to AI technology that has the ability to generate new information and content based on given data.

[0014] "User" refers to an individual who receives education using this system.

[0015] "Subjects to study" refers to a particular academic field in which the user desires education.

[0016] "Teacher type" refers to a classification that describes the characteristics of different instructors based on their teaching methods and styles.

[0017] A "lesson plan" refers to an educational plan that includes specific content and methods for learning.

[0018] "Means of learning" refers to the methods and processes by which generative AI learns the teacher's know-how.

[0019] "Means for selection" refers to the method or interface that allows a user to select the subject and type of teacher they wish to study.

[0020] "Means for generating" refers to the method by which the generative artificial intelligence creates lesson plans based on user selections.

[0021] "Means for displaying" refers to a method for visually presenting the generated lesson plan to the user. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the subject and teacher type they wish to study, and generates and provides a lesson plan based on the selection. An embodiment of this system is described in detail below.

[0044] Server Processing

[0045] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Specifically, the server creates customized lesson plans using know-how data according to the subject and teacher type selected by the user.

[0046] The server includes the following functions:

[0047] Importing know-how data and training the AI ​​model

[0048] Generate lesson plans based on user requests

[0049] Submitting the generated lesson plan

[0050] Terminal handling

[0051] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives the generated lesson plan from the server. The received lesson plan is converted into a format that can be displayed to the user and provided to the user.

[0052] The device includes the following features:

[0053] Providing a subject and teacher type selection interface

[0054] Sending user selection information to the server

[0055] Receive and view generated lesson plans

[0056] User Action

[0057] The user selects the subject and teacher type they wish to study on their device. Once the user has completed their selection, the information is sent by the device to the server, and a generated lesson plan is sent back to the device. The user can then use the lesson plan displayed on the device to continue their studies.

[0058] The specific steps for users are as follows:

[0059] 1. The user selects the subject and teacher type through the terminal interface.

[0060] 2. The user's selection information is sent from the terminal to the server.

[0061] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[0062] 4. The user studies the lesson plan displayed on the device.

[0063] Specific examples

[0064] Here is a concrete example of a logical math teacher type lesson plan:

[0065] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0066] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0067] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[0068] 4. The server sends the generated lesson plan back to the device.

[0069] 5. The device parses the generated lesson plan and displays it to the user.

[0070] 6. The user studies the specified content based on the lesson plan displayed on the device.

[0071] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[0075] Step 2:

[0076] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[0077] Step 3:

[0078] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[0079] Step 4:

[0080] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[0081] Step 5:

[0082] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[0083] Step 6:

[0084] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[0085] Step 7:

[0086] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[0087] Step 8:

[0088] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[0089] In this way, the present invention allows users to receive high-quality education tailored to their needs, and eliminates variations in teacher quality and teaching methods, enabling learning to be performed at a consistent educational level anywhere, anytime.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] Traditional education systems face challenges such as inconsistencies in teacher quality and teaching methods, making it difficult to provide a consistent, high-quality education. It is also difficult to generate customized lesson plans tailored to the subject and type of teacher a user wants to learn. Furthermore, users often lack access to the appropriate educational resources when they need them.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0094] In this invention, the server includes a means for acquiring teacher know-how and having the generative AI learn it, a means for the user to select the academic field they wish to study and the characteristics of the teacher, a means for the generative AI to generate a corresponding lesson plan based on the user's selection, and a means for displaying the generated lesson plan to the user. This allows the user to receive high-quality education at any time and obtain a lesson plan customized according to the academic field and the characteristics of the teacher.

[0095] "Teacher know-how" refers to information such as knowledge, skills, teaching methods, teaching materials, etc. accumulated by teachers in the field of education.

[0096] "Generative AI" refers to an AI system that has the ability to generate new information or content based on given data.

[0097] An "academic field" refers to an area in which a particular specialized knowledge or skill is systematized, or a single subject or theme.

[0098] "Teacher characteristics" refers to the teaching style and characteristics of a teacher, such as tendencies toward teaching methods such as being logical, intuitive, or practical.

[0099] A "learning plan" refers to a specific plan for learning, including the teaching materials to be used, lesson content, progress method, evaluation criteria, etc.

[0100] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the academic field they wish to study and the characteristics of the teacher, and generates a study plan based on the selection and provides it to the user. The details of this system are explained below.

[0101] Server Processing

[0102] The server first retrieves the know-how of multiple teachers from a database to provide high-quality education. This includes lecture materials, lesson videos, evaluation reports, etc. The retrieved know-how data is trained by a generative AI (such as OpenAI's GPT-4). In this training process, the following prompt sentences are used:

[0103] "Below are lecture materials from excellent math teachers. Learn their know-how."

[0104] Next, the server receives a request sent by the user via the terminal. The request includes the subject area the user wants to study and the characteristics of the teacher. Based on this information, the server uses generative artificial intelligence to generate an appropriate lesson plan. Specifically, the server generates a lesson plan using the following prompt sentence:

[0105] "User says they want to learn math. Create a lesson plan based on logical teacher types."

[0106] The generated learning plan is sent from the server to the device as JSON format data.

[0107] Terminal handling

[0108] The terminal functions as a user interface. The user selects the academic field and teacher characteristics they wish to study through the interface provided by the terminal. Once the selection is complete, the terminal transmits the information to the server. The lesson plan returned from the server is received by the terminal and converted into a format that can be displayed to the user.

[0109] User Action

[0110] The user selects the academic field and teacher characteristics they wish to study from the interface using their terminal. The selection information is sent to the server, and the generated learning plan is sent back to the terminal. The user can then proceed with their studies based on the learning plan displayed on the terminal.

[0111] Specific examples

[0112] For example, if a user wants a logical teacher-type lesson plan for math, the system works as follows:

[0113] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0114] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0115] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates a learning plan using generative artificial intelligence (for example, OpenAI's GPT-4).

[0116] 4. The server returns the generated learning plan to the device.

[0117] 5. The device analyzes the generated lesson plan and displays it to the user.

[0118] 6. The user studies the specified content based on the study plan displayed on the device.

[0119] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Server Processing Steps

[0122] Step 1: Acquire know-how data

[0123] To improve the quality of education, the server retrieves teacher know-how data (e.g., lecture materials, lesson videos, evaluation reports, etc.) from the database. The input is a search query, and the output is the corresponding know-how data.

[0124] Specific behavior:

[0125] The server uses SQL queries to filter and retrieve the required entries from the database.

[0126] Example: SELECT FROM Knowhow WHERE Subject = "Mathematics" AND TeacherType = "Logical"

[0127] Step 2: Training the AI ​​model

[0128] The server preprocesses the acquired know-how data and trains it on a generative AI (e.g., GPT-4). The input is the preprocessed know-how data, and the output is a trained AI model.

[0129] Specific behavior:

[0130] Know-how data is converted into text format and input into generative artificial intelligence through prompt sentences.

[0131] Example: Prompt: "Below is a lecture material from an excellent math teacher. Please learn this know-how."

[0132] Step 3: Receiving a user request

[0133] The server receives requests sent from users via their terminals. The requests include the subject area the user wants to study and the characteristics of the teacher. The input is the user's request information, and the output is the content of the request.

[0134] Specific behavior:

[0135] Receives the HTTP request and parses the request parameters (discipline and teacher characteristics).

[0136] Example: GET / generateLessonPlan?subject=Mathematics&teacherType=Logic

[0137] Step 4: Generate lesson plans

[0138] The server generates a learning plan based on the user's request using generative artificial intelligence. The input is the request information and a trained AI model, and the output is the learning plan.

[0139] Specific behavior:

[0140] Send prompts to GPT-4 to generate a learning plan.

[0141] Example: Prompt: "The user says they want to learn math. Create a lesson plan based on logical teacher types."

[0142] Step 5: Submit your lesson plan

[0143] The server sends the generated learning plan to the terminal as JSON format data. The input is the generated learning plan, and the output is an HTTP response to the terminal.

[0144] Specific behavior:

[0145] Send lesson plan data in JSON format as an HTTP response.

[0146] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[0147] Terminal processing steps

[0148] Step 1: Provide an interface

[0149] The terminal provides the user with an interface that allows them to select the subject they wish to study and the characteristics of the teacher. The input is the terminal configuration information, and the output is the interface display.

[0150] Specific behavior:

[0151] Create a select menu using HTML and CSS.

[0152] For example: "Choose the subject you would like to study.", "Choose the type of teacher."

[0153] Step 2: Sending User Selections

[0154] The terminal sends the user's selected academic field and teacher characteristics to the server. The input is the user's selection information, and the output is a request to the server.

[0155] Specific behavior:

[0156] The user's selection information is sent to the server using JavaScript AJAX.

[0157] Example: ajax.send("GET", " / generateLessonPlan?subject=Mathematics&teacherType=Logical")

[0158] Step 3: Receive your lesson plans

[0159] The terminal receives the generated learning plan from the server. The input is the HTTP response from the server, and the output is the learning plan data.

[0160] Specific behavior:

[0161] Receives the HTTP response from the server and parses the JSON format data.

[0162] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[0163] Step 4: View the lesson plan

[0164] The terminal displays the received lesson plan to the user. The input is the lesson plan data, and the output is the display on the user interface.

[0165] Specific behavior:

[0166] Use HTML and JavaScript to convert lesson plans into display formats.

[0167] For example: "Today's lesson plan: 1. Explain basic concepts, 2. Practice questions, 3. Application questions."

[0168] User processing steps

[0169] Step 1: Select subject and teacher type

[0170] The user selects the academic field they wish to study and the characteristics of the teacher through the terminal interface. The input is the user's selection, and the output is the input data to the terminal.

[0171] Specific behavior:

[0172] Select the discipline and teacher characteristics from the drop-down menus.

[0173] Examples: "mathematics", "logical"

[0174] Step 2: Start learning

[0175] The user proceeds with their studies based on the study plan displayed on the terminal. The input is the study plan displayed on the terminal, and the output is the user's study behavior.

[0176] Specific behavior:

[0177] Follow the displayed study plan, solve the problems and read the explanations.

[0178] For example, study based on "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions."

[0179] The above are the specific processing steps and operations in the system of the present invention.

[0180] (Application example 1)

[0181] 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."

[0182] Conventional educational systems have difficulty providing effective lesson plans based on the user's selected subject and teacher type, and are often restricted by location and time. Furthermore, typical online educational systems lack a sense of realism and interactivity, limiting learning effectiveness. Therefore, there is a demand for a system that allows users to take high-quality, interactive lessons in an immersive virtual space.

[0183] 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.

[0184] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for displaying the generated lesson plan to the user, and means for the user to take interactive lessons in a virtual space. This allows users to take high-quality, interactive lessons in a virtual space, providing a realistic learning experience without being restricted by location or time.

[0185] "Teacher know-how" refers to the specialized knowledge and teaching methods that educators possess, as well as the teaching techniques and methodologies they have acquired through their experience in the field of education.

[0186] "Generative AI" is a type of AI that uses algorithms and models to learn from large amounts of data and provide solutions to specific problems.

[0187] "Subjects that users want to study" refers to the fields or topics that users of the educational system wish to study.

[0188] "Teacher type" refers to categories of teachers with different teaching styles and teaching methods, and can be selected by the user.

[0189] A "lesson plan" is a document or program that contains details of the teaching plan or learning content to be followed by a learner, generated based on a specific subject and type of teacher.

[0190] A "virtual space" is a three-dimensional computer-generated virtual environment in which users can have an immersive, interactive experience.

[0191] "Interface" refers to the means or devices by which a user interacts with a system, and typically includes a graphical user interface (GUI).

[0192] "User request" is information that specifically indicates the learner's demands and wishes for the learning system.

[0193] A "server" is a computer system that receives requests, processes data, and provides appropriate information and services to clients.

[0194] The present invention is an educational system that uses generative artificial intelligence to learn teacher know-how, and generates and provides lesson plans based on a user's selection of the subject and teacher type they wish to study. Furthermore, this system allows users to take interactive lessons in a virtual space. Specific embodiments of each component are described below.

[0195] Server Processing

[0196] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on them. The generative AI used is OpenAI's GPT-3. This model is capable of learning from large amounts of educational data and generating lesson plans suited to specific subjects and teaching styles.

[0197] Examples of specific prompts are:

[0198] Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations.

[0199] The lesson plans generated by GPT-3 are then converted into a format for display in the virtual space. The server manages user requests and the generated lesson plans, and sends them to the device in the virtual space at the appropriate time.

[0200] Terminal handling

[0201] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits this information to the server and receives the generated lesson plan from the server. The received lesson plan is then converted into a format that is displayed to the user, allowing them to experience it interactively in a virtual space. For this reason, the device requires hardware with high-performance graphics and processing capabilities, such as the latest smartphones or head-mounted displays (HMDs).

[0202] User Action

[0203] The user selects the subject and teacher type they wish to study using their device. The user's learning request is then sent from the device to the server, and a generated lesson plan is sent back to the device. The user can then proceed with their learning in a virtual space based on the lesson plan. For example, if a user selects a chemistry experiment class, they can wear an HMD and learn while visualizing the actual chemistry experiment in the virtual space.

[0204] Example

[0205] Here is a concrete example of a chemistry experiment:

[0206] 1. The user selects the "Chemistry" and "Experimental" teacher types in the terminal interface.

[0207] 2. The terminal sends the user's selection information to the server.

[0208] 3. The server retrieves the teacher's know-how based on "chemistry" and "experimental" from the database and generates a lesson plan using GPT-3.

[0209] 4. The server sends the generated lesson plan to the device.

[0210] 5. The device analyzes the received lesson plan and displays it in the virtual space.

[0211] 6. Users use the HMD to take interactive lessons in a virtual space.

[0212] This system allows users to receive high-quality education in a virtual space with a sense of realism, significantly improving learning effectiveness.

[0213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0214] Step 1:

[0215] The user uses the device interface to select the subject and teacher type they wish to study, either by using a mouse or touch screen to select the subject and teacher type from drop-down menus, and the selection is entered into the device and sent to the server.

[0216] Step 2:

[0217] The device sends the user's selection information (subject and teacher type) to the server. Specifically, data about the selected subject and teacher type is sent to the server via a dedicated API endpoint. This data is sent in the form of a request.

[0218] Step 3:

[0219] The server receives a request sent by the user. The request includes the user's selected subject and teacher type. Based on this input, the server retrieves the corresponding teacher's know-how data from the database.

[0220] Step 4:

[0221] The server passes the acquired know-how data to a generative artificial intelligence (for example, OpenAI's GPT-3), which generates a lesson plan based on the user's selection. Specifically, it generates a prompt and sends a request to the GPT-3 model. An example prompt is "Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations." GPT-3 outputs the text data of the lesson plan based on this prompt.

[0222] Step 5:

[0223] The server receives the lesson plans from GPT-3, parses them, and formats them as structured data, which is then converted into a user-friendly form and ready to be sent to the device.

[0224] Step 6:

[0225] The server sends the generated lesson plan to the terminal, which sends the data in the form of a response containing a detailed lesson plan for the subject and type of teacher selected by the user.

[0226] Step 7:

[0227] The device then analyzes the received lesson plan and converts it into a format suitable for display in the virtual space, including the 3D objects and interactive elements used in the virtual space.

[0228] Step 8:

[0229] Users enter a virtual space using a head-mounted display (HMD). The converted lesson plan is displayed interactively within this virtual space. Through visual and physical movements, users can experience and learn the lesson content based on the lesson plan generated in the virtual space.

[0230] In this way, by executing each step consecutively, the user can interactively experience high-quality educational content in a virtual space.

[0231] 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.

[0232] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[0233] Server Processing

[0234] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state.

[0235] The server includes the following functions:

[0236] Importing know-how data and training the AI ​​model

[0237] Generate lesson plans based on user requests

[0238] Adjusting lesson plans using emotion engines

[0239] Submitting the generated lesson plan

[0240] Terminal handling

[0241] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[0242] The device includes the following features:

[0243] Providing a subject and teacher type selection interface

[0244] Sending user selection information to the server

[0245] Receive and view generated lesson plans

[0246] Emotion engine that analyzes facial expressions, voice, and behavior

[0247] User Action

[0248] The user selects the subject and type of teacher they wish to study on the device. Once the user completes their selection, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[0249] The specific steps for users are as follows:

[0250] 1. The user selects the subject and teacher type through the terminal interface.

[0251] 2. The user's selection information is sent from the terminal to the server.

[0252] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[0253] 4. The user proceeds with their studies based on the lesson plan displayed on the device.

[0254] 5. The device analyzes the user's facial expressions, voice, and behavior to recognize their emotional state.

[0255] 6. The server uses the emotion engine to adjust the lesson plan and provide it to the user.

[0256] Specific examples

[0257] Here's an example of taking a math lesson plan from a logical teacher and adjusting it using the emotion engine:

[0258] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0259] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0260] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[0261] 4. The server sends the generated lesson plan back to the device.

[0262] 5. The device parses the generated lesson plan and displays it to the user.

[0263] 6. The user studies the specified content based on the lesson plan displayed on the device.

[0264] 7. The device analyzes the user's facial expressions and voice and recognizes that the user is confused.

[0265] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[0266] 9. The user continues learning based on the adjusted lesson plan.

[0267] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[0268] The processing flow will be explained below.

[0269] Step 1:

[0270] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[0271] Step 2:

[0272] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[0273] Step 3:

[0274] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[0275] Step 4:

[0276] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[0277] Step 5:

[0278] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[0279] Step 6:

[0280] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[0281] Step 7:

[0282] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[0283] Step 8:

[0284] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[0285] Step 9:

[0286] The device analyzes the user's facial expressions, voice, and behavior to determine their emotional state. The device uses a camera and microphone to detect the user's emotional state in real time.

[0287] Step 10:

[0288] The terminal transmits the user's emotional state to the server, for example, if the user is confused, this information is conveyed to the server.

[0289] Step 11:

[0290] The server adjusts the lesson plan based on the received emotional information, using generative artificial intelligence to simplify or elaborate the content to make it easier for the user to understand.

[0291] Step 12:

[0292] The server then sends the adjusted lesson plan back to the user's terminal, and the user continues studying based on the adjusted content.

[0293] In this way, the system recognizes the user's emotional state in real time and adjusts the lesson plan accordingly, providing more effective and personalized education.

[0294] Example 2

[0295] 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."

[0296] Conventional educational systems have struggled to respond to individual users' learning needs and emotional states in a detailed manner. Furthermore, their reliance on fixed curricula and teacher methods did not necessarily maximize users' learning outcomes. Furthermore, they often failed to properly adjust teaching materials and explanations based on real-time feedback from users' emotional states. This often led to problems such as confusion and lack of understanding during learning, creating a need for a system that could maximize individual learning outcomes.

[0297] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0298] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for analyzing the user's facial expressions, voice, and behavior to determine their emotional state, and means for adjusting the lesson plan based on the emotional analysis results, thereby enabling the server to respond to the user's individual learning needs and fine-tune the lesson plan based on their emotional state in real time.

[0299] "Teacher know-how" refers to the specialized knowledge, skills, and information about teaching methods that educators possess.

[0300] "Generative AI" is an AI system that has the ability to automatically generate new information and content based on given data and instructions.

[0301] "User" refers to an individual or group who utilizes the System to receive educational content.

[0302] A "subject" is a specific academic field or topic that a user chooses to study.

[0303] "Teacher type" is an attribute that indicates a teacher's teaching style or approach, and includes classifications such as "logical" and "intuitive."

[0304] A "lesson plan" is a set of lesson plans or materials designed to achieve a specific educational goal.

[0305] "Emotional state" refers to the psychological and emotional state inferred from a user's facial expressions, voice, and behavior.

[0306] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions, voice, and behavioral data to determine their emotional state.

[0307] "Adjustment" is the process of changing the content and difficulty of an existing lesson plan depending on the user's learning situation and emotional state.

[0308] An "interface" is a piece of software or hardware that provides the means by which a user interacts with a system.

[0309] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[0310] Server Processing

[0311] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. An example of an AI model used is "GPT-4." The server also receives requests from users and generates lesson plans based on the requests. An example of a prompt is "Create a lesson plan for: Math with logical style." The server then uses an emotion engine that recognizes the user's emotions to adjust the lesson plan based on the user's emotional state. The emotion engine can be something like "Microsoft Azure Emotion API."

[0312] Terminal handling

[0313] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[0314] User Action

[0315] The user selects the subject and type of teacher they wish to study on their device. Once the selection is complete, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[0316] Specific examples

[0317] We will take a logical teacher-type lesson plan for mathematics and provide a concrete example of how it can be adjusted using an emotion engine.

[0318] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0319] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0320] 3. The server retrieves the teacher's know-how based on "mathematics" and "logical" from the database and generates a lesson plan using generative artificial intelligence. For example, it uses the prompt "Create a lesson plan for: Math with logical style."

[0321] 4. The server sends the generated lesson plan back to the device.

[0322] 5. The device parses the generated lesson plan and displays it to the user.

[0323] 6. The user studies the specified content based on the lesson plan displayed on the device.

[0324] 7. The device analyzes the user's facial expressions and voice to recognize when the user is confused. For example, it uses the Microsoft Azure Emotion API as its emotion engine.

[0325] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[0326] 9. The user continues learning based on the adjusted lesson plan.

[0327] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[0328] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0329] Program processing flow

[0330] Step 1: Import know-how data

[0331] The server retrieves the know-how of excellent teachers from a database. The input is a list of teacher IDs, and the output is a dataset of each teacher's teaching know-how. Specifically, it uses SQL queries to search and retrieve this data.

[0332] Specific operation:

[0333] Send a query to your SQL database: SELECT FROM teacher_knowhow WHERE teacher_id IN (1, 2, 3, ...)

[0334] Prepare to pass the educational know-how obtained from the database to the AI ​​model.

[0335] Step 2: Training the AI ​​model

[0336] The server trains the imported know-how data into a generative AI. The input is the know-how data, and the output is a trained AI model.

[0337] Specific operation:

[0338] Feed the data into the AI ​​model: ai_model.train(teacher_knowhow_data)

[0339] Verify that the learning is complete.

[0340] Step 3: Receiving a user request

[0341] The terminal receives the subject and teacher type selection information from the user and sends it to the server. The input is the user's selection information, and the output is the request data to the server.

[0342] Specific operation:

[0343] Display interface to receive user selection: "Display screen for user selection"

[0344] Send information to the server: "sendToServer(userSelection)"

[0345] Step 4: Generate lesson plans

[0346] The server generates a lesson plan by inputting prompts to the generative AI based on the user's selection information. The input is the selection information and the prompt sentence, and the output is the generated lesson plan.

[0347] Specific operation:

[0348] Create a prompt based on the user's selection: "Create a lesson plan for: Math with logical style."

[0349] Enter a prompt into the AI ​​model: "lesson_plan = ai_model.generate(prompt)"

[0350] Step 5: Emotion Engine Analysis

[0351] The device analyzes the user's facial expressions, voice, and behavior in real time to determine their emotional state. The input is the user's video feed and audio data, and the output is emotional data.

[0352] Specific operation:

[0353] Capture user facial expressions and voice in real time: "Get user video feed"

[0354] Analyze with emotion engine: "emotionData = analyzeEmotion(userVideoFeed)"

[0355] Step 6: Adjust your lesson plan

[0356] The server adjusts the lesson plan based on the emotion data received from the device. The input is the generated lesson plan and emotion data, and the output is the adjusted lesson plan.

[0357] Specific operation:

[0358] Receive emotional data: "Send data about your emotional state to the server"

[0359] Generate a new prompt if needed: "Adjust the lesson plan to simplify: {lesson_plan}"

[0360] Generate an adjusted lesson plan using the AI ​​model: "adjusted_lesson_plan = ai_model.generate(prompt)"

[0361] Step 7: Submit your lesson plan

[0362] The server sends the generated lesson plan to the terminal. The input is the adjusted lesson plan, and the output is the data sent to the terminal.

[0363] Specific operation:

[0364] Send the adjusted lesson plan to the device: "sendToClient(adjusted_lesson_plan)"

[0365] Step 8: View the lesson plan

[0366] The terminal displays the received lesson plan to the user. The input is the adjusted lesson plan and the output is the educational content displayed to the user.

[0367] Specific operation:

[0368] Receive lesson plan: "Receive adjusted_lesson_plan"

[0369] Show to user: "displayLessonPlan(adjusted_lesson_plan)"

[0370] Step 9: Feedback of the user's emotional state

[0371] The terminal continues to analyze the user's facial expressions, voice, and behavior, and sends emotional state feedback to the server. The input is updated emotional data, and the output is feedback data to the server.

[0372] Specific operation:

[0373] Continuous emotion analysis: "Continuously acquire emotionData"

[0374] Feedback of emotional state to the server: "sendToServer(updatedEmotionData)"

[0375] Step 10: View your adjusted lesson plan

[0376] The device updates and redisplays the lesson plan for the user based on the sentiment analysis results from the server. The input is the newly adjusted lesson plan, and the output is the updated educational content.

[0377] Specific operation:

[0378] Receive a new lesson plan: "Receive newLessonPlan"

[0379] Show it to the user again: "displayLessonPlan(newLessonPlan)"

[0380] (Application example 2)

[0381] 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."

[0382] Conventional educational and product recommendation systems do not adequately consider the individual needs and emotional state of users. This makes it difficult to provide optimal lesson plans and product recommendations for users, resulting in problems such as insufficient improvement of learning outcomes and insatiable purchase motivation. In particular, there is a lack of adaptive content provision according to emotional states, making it difficult to improve user satisfaction.

[0383] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, and means for the generative AI to generate a corresponding lesson plan based on the user's selection. This makes it possible to provide a personalized lesson plan based on the user's desired subject and type of teacher. The server also includes means for displaying the generated lesson plan to the user, means for incorporating an emotion engine that recognizes the user's emotional state, means for adjusting the lesson plan based on the emotion engine, means for inputting product categories and characteristics of interest, and means for recommending optimal products based on the input information and emotional state. This makes it possible to recommend optimal products and adjust lesson plans based on the user's emotional state and individual preferences, which is expected to improve user satisfaction.

[0384] "Teacher know-how" is a general term for the specialized knowledge, teaching skills, and educational methods that teachers have acquired through experience.

[0385] "Generative artificial intelligence" is a general term for artificial intelligence models that can generate new information and patterns based on massive amounts of data.

[0386] A "subject that a user wants to study" is a particular educational field or theme that a user selects for their own learning or knowledge improvement.

[0387] "Teacher type" refers to a teacher's characteristics such as teaching style, area of ​​expertise, and teaching method.

[0388] A "lesson plan" is a lesson plan that specifically lays out the learning content and teaching methods based on set educational objectives.

[0389] "Emotion engine" is a general term for technology that analyzes a user's facial expressions, voice, and behavior to recognize their emotional state in real time.

[0390] A "product category" refers to a group of products classified based on their type or attributes.

[0391] "Recommendation tools" is a general term for methods and techniques used to suggest optimal products and services based on a user's needs and emotional state.

[0392] "User's emotional state" is information that indicates the type and intensity of the emotion that the user is feeling at a particular moment.

[0393] The present invention provides an education and product recommendation system that uses generative artificial intelligence (AI) that learns teacher know-how, generates lesson plans tailored to users, and uses an emotion recognition engine. The following describes in detail an embodiment of the present invention.

[0394] Server Processing

[0395] To provide high-quality education, the server retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state. Furthermore, this system also has the function of receiving product category and characteristic information of interest and recommending the most suitable products based on that information. For this purpose, the server includes the following functions:

[0396] Importing know-how data and training the AI ​​model

[0397] Generate lesson plans based on user requests

[0398] Adjusting lesson plans using emotion engines

[0399] Sending generated lesson plans and product recommendations

[0400] Terminal handling

[0401] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study, and to input product categories and characteristics of interest. Once the user has completed their selection, the device transmits the information to the server, which then receives the generated lesson plans and product recommendations. The received information is converted into a format that is displayed to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state. To this end, the device includes the following functions:

[0402] Providing a subject and teacher type selection interface

[0403] Sending user selection information to the server

[0404] Receive and display generated lesson plans and product recommendations

[0405] Emotion engine that analyzes facial expressions, voice, and behavior

[0406] User Action

[0407] The user selects the subject they wish to study, the type of teacher, the product category, and the characteristics of their interest on the device. Once the user completes their selection, the device sends that information to the server, which then generates lesson plans and product recommendations, which are then sent back to the device. The user can use the information displayed on the device to further their studies or consider purchasing. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plans and product recommendations accordingly.

[0408] Software and Hardware

[0409] The hardware used is a smartphone (iOS or Android), smart glasses, or a head-mounted display (e.g., Google Glass). The software uses:

[0410] Emotion analysis: OpenCV, TensorFlow

[0411] AI models: Machine learning frameworks such as TensorFlow

[0412] Communication: requests library (Python)

[0413] Specific examples

[0414] For example, if a user wants to buy a fashion item, she can select "dress" and "elegant" through the app interface and smile at the camera. If the emotion engine recognizes her emotion as "joy," the AI ​​model will suggest the most suitable dress based on her preferences and emotions. In this way, the present invention can tailor optimal product recommendations and lesson plans to the user's emotional state and individual preferences.

[0415] Prompt Sentence Examples

[0416] "I would like to purchase some fashion items. I love dresses and elegant styles, and I am currently experiencing joy. Please recommend the best products for me."

[0417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0418] Step 1:

[0419] Through the terminal interface, the user selects the subject they wish to study, the type of teacher, the product category, and the characteristics they are interested in. By inputting this information, the user's individual needs are clarified. The input contents include the subject name, teacher style, product category, and characteristic information. For example, "Mathematics," "Logical," "Dress," "Elegant," etc.

[0420] Step 2:

[0421] The terminal receives the selection information from the user and sends it to the server. The terminal organizes the user's selection information, converts it into a specific format, and sends it to the server. This input data is necessary for processing within the server. Specific input data includes subject name, teaching style, product category, characteristic information, and user identification information.

[0422] Step 3:

[0423] Based on the received user information, the server uses generative AI to generate corresponding lesson plans and product recommendations. The server extracts relevant teacher know-how and product information from its database, inputs this data into an AI model, and generates appropriate lesson plans and product recommendations. As a result, a user-specific lesson plan and product list are generated and output.

[0424] Step 4:

[0425] The server transmits the generated lesson plan and product recommendation information to the terminal. The server then transmits the generated result data to the corresponding terminal based on the user identification information. The transmitted data includes the specific content of the lesson plan and a list of recommended products.

[0426] Step 5:

[0427] The terminal displays the received lesson plan and product recommendation information to the user. The terminal converts the data sent from the server into a visually easy-to-understand format and presents it to the user. This allows the user to check the generated educational content and recommended products.

[0428] Step 6:

[0429] The device analyzes facial expressions, voice, and behavior to recognize the user's emotional state. When the user provides facial expressions and voice through the device, the emotion engine analyzes these data in real time to determine the user's emotional state. This analysis is performed on the device, and the resulting emotional state information is output.

[0430] Step 7:

[0431] The server adjusts the generated lesson plans and product recommendations based on the emotional state sent from the device. Based on the emotional data obtained from the emotion engine, the server re-runs the AI ​​model to generate new lesson plans and product recommendations that correspond to the user's emotional state. This adjusted data is then sent back to the device.

[0432] Step 8:

[0433] The device then displays the adjusted lesson plan and product recommendations to the user again. Finally, the device displays educational content and product lists optimized for the user's emotional state, providing the user with an improved educational and purchasing experience.

[0434] This series of steps allows users to enjoy a personalized and optimal learning and purchasing experience.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Second embodiment]

[0439] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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."

[0451] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the subject and teacher type they wish to study, and generates and provides a lesson plan based on the selection. An embodiment of this system is described in detail below.

[0452] Server Processing

[0453] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Specifically, the server creates customized lesson plans using know-how data according to the subject and teacher type selected by the user.

[0454] The server includes the following functions:

[0455] Importing know-how data and training the AI ​​model

[0456] Generate lesson plans based on user requests

[0457] Submitting the generated lesson plan

[0458] Terminal handling

[0459] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives the generated lesson plan from the server. The received lesson plan is converted into a format that can be displayed to the user and provided to the user.

[0460] The device includes the following features:

[0461] Providing a subject and teacher type selection interface

[0462] Sending user selection information to the server

[0463] Receive and view generated lesson plans

[0464] User Action

[0465] The user selects the subject and teacher type they wish to study on their device. Once the user has completed their selection, the information is sent by the device to the server, and a generated lesson plan is sent back to the device. The user can then use the lesson plan displayed on the device to continue their studies.

[0466] The specific steps for users are as follows:

[0467] 1. The user selects the subject and teacher type through the terminal interface.

[0468] 2. The user's selection information is sent from the terminal to the server.

[0469] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[0470] 4. The user studies the lesson plan displayed on the device.

[0471] Specific examples

[0472] Here is a concrete example of a logical math teacher type lesson plan:

[0473] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0474] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0475] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[0476] 4. The server sends the generated lesson plan back to the device.

[0477] 5. The device parses the generated lesson plan and displays it to the user.

[0478] 6. The user studies the specified content based on the lesson plan displayed on the device.

[0479] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[0480] The processing flow will be explained below.

[0481] Step 1:

[0482] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[0483] Step 2:

[0484] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[0485] Step 3:

[0486] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[0487] Step 4:

[0488] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[0489] Step 5:

[0490] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[0491] Step 6:

[0492] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[0493] Step 7:

[0494] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[0495] Step 8:

[0496] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[0497] In this way, the present invention allows users to receive high-quality education tailored to their needs, and eliminates variations in teacher quality and teaching methods, enabling learning to be performed at a consistent educational level anywhere, anytime.

[0498] Example 1

[0499] 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."

[0500] Traditional education systems face challenges such as inconsistencies in teacher quality and teaching methods, making it difficult to provide a consistent, high-quality education. It is also difficult to generate customized lesson plans tailored to the subject and type of teacher a user wants to learn. Furthermore, users often lack access to the appropriate educational resources when they need them.

[0501] 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.

[0502] In this invention, the server includes a means for acquiring teacher know-how and having the generative AI learn it, a means for the user to select the academic field they wish to study and the characteristics of the teacher, a means for the generative AI to generate a corresponding lesson plan based on the user's selection, and a means for displaying the generated lesson plan to the user. This allows the user to receive high-quality education at any time and obtain a lesson plan customized according to the academic field and the characteristics of the teacher.

[0503] "Teacher know-how" refers to information such as knowledge, skills, teaching methods, teaching materials, etc. accumulated by teachers in the field of education.

[0504] "Generative AI" refers to an AI system that has the ability to generate new information or content based on given data.

[0505] An "academic field" refers to an area in which a particular specialized knowledge or skill is systematized, or a single subject or theme.

[0506] "Teacher characteristics" refers to the teaching style and characteristics of a teacher, such as tendencies toward teaching methods such as being logical, intuitive, or practical.

[0507] A "learning plan" refers to a specific plan for learning, including the teaching materials to be used, lesson content, progress method, evaluation criteria, etc.

[0508] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the academic field they wish to study and the characteristics of the teacher, and generates a study plan based on the selection and provides it to the user. The details of this system are explained below.

[0509] Server Processing

[0510] The server first retrieves the know-how of multiple teachers from a database to provide high-quality education. This includes lecture materials, lesson videos, evaluation reports, etc. The retrieved know-how data is trained by a generative AI (such as OpenAI's GPT-4). In this training process, the following prompt sentences are used:

[0511] "Below are lecture materials from excellent math teachers. Learn their know-how."

[0512] Next, the server receives a request sent by the user via the terminal. The request includes the subject area the user wants to study and the characteristics of the teacher. Based on this information, the server uses generative artificial intelligence to generate an appropriate lesson plan. Specifically, the server generates a lesson plan using the following prompt sentence:

[0513] "User says they want to learn math. Create a lesson plan based on logical teacher types."

[0514] The generated learning plan is sent from the server to the device as JSON format data.

[0515] Terminal handling

[0516] The terminal functions as a user interface. The user selects the academic field and teacher characteristics they wish to study through the interface provided by the terminal. Once the selection is complete, the terminal transmits the information to the server. The lesson plan returned from the server is received by the terminal and converted into a format that can be displayed to the user.

[0517] User Action

[0518] The user selects the academic field and teacher characteristics they wish to study from the interface using their terminal. The selection information is sent to the server, and the generated learning plan is sent back to the terminal. The user can then proceed with their studies based on the learning plan displayed on the terminal.

[0519] Specific examples

[0520] For example, if a user wants a logical teacher-type lesson plan for math, the system works as follows:

[0521] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0522] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0523] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates a learning plan using generative artificial intelligence (for example, OpenAI's GPT-4).

[0524] 4. The server returns the generated learning plan to the device.

[0525] 5. The device analyzes the generated lesson plan and displays it to the user.

[0526] 6. The user studies the specified content based on the study plan displayed on the device.

[0527] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[0528] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0529] Server Processing Steps

[0530] Step 1: Acquire know-how data

[0531] To improve the quality of education, the server retrieves teacher know-how data (e.g., lecture materials, lesson videos, evaluation reports, etc.) from the database. The input is a search query, and the output is the corresponding know-how data.

[0532] Specific behavior:

[0533] The server uses SQL queries to filter and retrieve the required entries from the database.

[0534] Example: SELECT FROM Knowhow WHERE Subject = "Mathematics" AND TeacherType = "Logical"

[0535] Step 2: Training the AI ​​model

[0536] The server preprocesses the acquired know-how data and trains it on a generative AI (e.g., GPT-4). The input is the preprocessed know-how data, and the output is a trained AI model.

[0537] Specific behavior:

[0538] Know-how data is converted into text format and input into generative artificial intelligence through prompt sentences.

[0539] Example: Prompt: "Below is a lecture material from an excellent math teacher. Please learn this know-how."

[0540] Step 3: Receiving a user request

[0541] The server receives requests sent from users via their terminals. The requests include the subject area the user wants to study and the characteristics of the teacher. The input is the user's request information, and the output is the content of the request.

[0542] Specific behavior:

[0543] Receives the HTTP request and parses the request parameters (discipline and teacher characteristics).

[0544] Example: GET / generateLessonPlan?subject=Mathematics&teacherType=Logic

[0545] Step 4: Generate lesson plans

[0546] The server generates a learning plan based on the user's request using generative artificial intelligence. The input is the request information and a trained AI model, and the output is the learning plan.

[0547] Specific behavior:

[0548] Send prompts to GPT-4 to generate a learning plan.

[0549] Example: Prompt: "The user says they want to learn math. Create a lesson plan based on logical teacher types."

[0550] Step 5: Submit your lesson plan

[0551] The server sends the generated learning plan to the terminal as JSON format data. The input is the generated learning plan, and the output is an HTTP response to the terminal.

[0552] Specific behavior:

[0553] Send lesson plan data in JSON format as an HTTP response.

[0554] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[0555] Terminal processing steps

[0556] Step 1: Provide an interface

[0557] The terminal provides the user with an interface that allows them to select the subject they wish to study and the characteristics of the teacher. The input is the terminal configuration information, and the output is the interface display.

[0558] Specific behavior:

[0559] Create a select menu using HTML and CSS.

[0560] For example: "Choose the subject you would like to study.", "Choose the type of teacher."

[0561] Step 2: Sending User Selections

[0562] The terminal sends the user's selected academic field and teacher characteristics to the server. The input is the user's selection information, and the output is a request to the server.

[0563] Specific behavior:

[0564] The user's selection information is sent to the server using JavaScript AJAX.

[0565] Example: ajax.send("GET", " / generateLessonPlan?subject=Mathematics&teacherType=Logical")

[0566] Step 3: Receive your lesson plans

[0567] The terminal receives the generated learning plan from the server. The input is the HTTP response from the server, and the output is the learning plan data.

[0568] Specific behavior:

[0569] Receives the HTTP response from the server and parses the JSON format data.

[0570] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[0571] Step 4: View the lesson plan

[0572] The terminal displays the received lesson plan to the user. The input is the lesson plan data, and the output is the display on the user interface.

[0573] Specific behavior:

[0574] Use HTML and JavaScript to convert lesson plans into display formats.

[0575] For example: "Today's lesson plan: 1. Explain basic concepts, 2. Practice questions, 3. Application questions."

[0576] User processing steps

[0577] Step 1: Select subject and teacher type

[0578] The user selects the academic field they wish to study and the characteristics of the teacher through the terminal interface. The input is the user's selection, and the output is the input data to the terminal.

[0579] Specific behavior:

[0580] Select the discipline and teacher characteristics from the drop-down menus.

[0581] Examples: "mathematics", "logical"

[0582] Step 2: Start learning

[0583] The user proceeds with their studies based on the study plan displayed on the terminal. The input is the study plan displayed on the terminal, and the output is the user's study behavior.

[0584] Specific behavior:

[0585] Follow the displayed study plan, solve the problems and read the explanations.

[0586] For example, study based on "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions."

[0587] The above are the specific processing steps and operations in the system of the present invention.

[0588] (Application example 1)

[0589] 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."

[0590] Conventional educational systems have difficulty providing effective lesson plans based on the user's selected subject and teacher type, and are often restricted by location and time. Furthermore, typical online educational systems lack a sense of realism and interactivity, limiting learning effectiveness. Therefore, there is a demand for a system that allows users to take high-quality, interactive lessons in an immersive virtual space.

[0591] 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.

[0592] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for displaying the generated lesson plan to the user, and means for the user to take interactive lessons in a virtual space. This allows users to take high-quality, interactive lessons in a virtual space, providing a realistic learning experience without being restricted by location or time.

[0593] "Teacher know-how" refers to the specialized knowledge and teaching methods that educators possess, as well as the teaching techniques and methodologies they have acquired through their experience in the field of education.

[0594] "Generative AI" is a type of AI that uses algorithms and models to learn from large amounts of data and provide solutions to specific problems.

[0595] "Subjects that users want to study" refers to the fields or topics that users of the educational system wish to study.

[0596] "Teacher type" refers to categories of teachers with different teaching styles and teaching methods, and can be selected by the user.

[0597] A "lesson plan" is a document or program that contains details of the teaching plan or learning content to be followed by a learner, generated based on a specific subject and type of teacher.

[0598] A "virtual space" is a three-dimensional computer-generated virtual environment in which users can have an immersive, interactive experience.

[0599] "Interface" refers to the means or devices by which a user interacts with a system, and typically includes a graphical user interface (GUI).

[0600] "User request" is information that specifically indicates the learner's demands and wishes for the learning system.

[0601] A "server" is a computer system that receives requests, processes data, and provides appropriate information and services to clients.

[0602] The present invention is an educational system that uses generative artificial intelligence to learn teacher know-how, and generates and provides lesson plans based on a user's selection of the subject and teacher type they wish to study. Furthermore, this system allows users to take interactive lessons in a virtual space. Specific embodiments of each component are described below.

[0603] Server Processing

[0604] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on them. The generative AI used is OpenAI's GPT-3. This model is capable of learning from large amounts of educational data and generating lesson plans suited to specific subjects and teaching styles.

[0605] Examples of specific prompts are:

[0606] Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations.

[0607] The lesson plans generated by GPT-3 are then converted into a format for display in the virtual space. The server manages user requests and the generated lesson plans, and sends them to the device in the virtual space at the appropriate time.

[0608] Terminal handling

[0609] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits this information to the server and receives the generated lesson plan from the server. The received lesson plan is then converted into a format that is displayed to the user, allowing them to experience it interactively in a virtual space. For this reason, the device requires hardware with high-performance graphics and processing capabilities, such as the latest smartphones or head-mounted displays (HMDs).

[0610] User Action

[0611] The user selects the subject and teacher type they wish to study using their device. The user's learning request is then sent from the device to the server, and a generated lesson plan is sent back to the device. The user can then proceed with their learning in a virtual space based on the lesson plan. For example, if a user selects a chemistry experiment class, they can wear an HMD and learn while visualizing the actual chemistry experiment in the virtual space.

[0612] Example

[0613] Here is a concrete example of a chemistry experiment:

[0614] 1. The user selects the "Chemistry" and "Experimental" teacher types in the terminal interface.

[0615] 2. The terminal sends the user's selection information to the server.

[0616] 3. The server retrieves the teacher's know-how based on "chemistry" and "experimental" from the database and generates a lesson plan using GPT-3.

[0617] 4. The server sends the generated lesson plan to the device.

[0618] 5. The device analyzes the received lesson plan and displays it in the virtual space.

[0619] 6. Users use the HMD to take interactive lessons in a virtual space.

[0620] This system allows users to receive high-quality education in a virtual space with a sense of realism, significantly improving learning effectiveness.

[0621] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0622] Step 1:

[0623] The user uses the device interface to select the subject and teacher type they wish to study, either by using a mouse or touch screen to select the subject and teacher type from drop-down menus, and the selection is entered into the device and sent to the server.

[0624] Step 2:

[0625] The device sends the user's selection information (subject and teacher type) to the server. Specifically, data about the selected subject and teacher type is sent to the server via a dedicated API endpoint. This data is sent in the form of a request.

[0626] Step 3:

[0627] The server receives a request sent by the user. The request includes the user's selected subject and teacher type. Based on this input, the server retrieves the corresponding teacher's know-how data from the database.

[0628] Step 4:

[0629] The server passes the acquired know-how data to a generative artificial intelligence (for example, OpenAI's GPT-3), which generates a lesson plan based on the user's selection. Specifically, it generates a prompt and sends a request to the GPT-3 model. An example prompt is "Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations." GPT-3 outputs the text data of the lesson plan based on this prompt.

[0630] Step 5:

[0631] The server receives the lesson plans from GPT-3, parses them, and formats them as structured data, which is then converted into a user-friendly form and ready to be sent to the device.

[0632] Step 6:

[0633] The server sends the generated lesson plan to the terminal, which sends the data in the form of a response containing a detailed lesson plan for the subject and type of teacher selected by the user.

[0634] Step 7:

[0635] The device then analyzes the received lesson plan and converts it into a format suitable for display in the virtual space, including the 3D objects and interactive elements used in the virtual space.

[0636] Step 8:

[0637] Users enter a virtual space using a head-mounted display (HMD). The converted lesson plan is displayed interactively within this virtual space. Through visual and physical movements, users can experience and learn the lesson content based on the lesson plan generated in the virtual space.

[0638] In this way, by executing each step consecutively, the user can interactively experience high-quality educational content in a virtual space.

[0639] 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.

[0640] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[0641] Server Processing

[0642] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state.

[0643] The server includes the following functions:

[0644] Importing know-how data and training the AI ​​model

[0645] Generate lesson plans based on user requests

[0646] Adjusting lesson plans using emotion engines

[0647] Submitting the generated lesson plan

[0648] Terminal handling

[0649] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[0650] The device includes the following features:

[0651] Providing a subject and teacher type selection interface

[0652] Sending user selection information to the server

[0653] Receive and view generated lesson plans

[0654] Emotion engine that analyzes facial expressions, voice, and behavior

[0655] User Action

[0656] The user selects the subject and type of teacher they wish to study on the device. Once the user completes their selection, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[0657] The specific steps for users are as follows:

[0658] 1. The user selects the subject and teacher type through the terminal interface.

[0659] 2. The user's selection information is sent from the terminal to the server.

[0660] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[0661] 4. The user proceeds with their studies based on the lesson plan displayed on the device.

[0662] 5. The device analyzes the user's facial expressions, voice, and behavior to recognize their emotional state.

[0663] 6. The server uses the emotion engine to adjust the lesson plan and provide it to the user.

[0664] Specific examples

[0665] Here's an example of taking a math lesson plan from a logical teacher and adjusting it using the emotion engine:

[0666] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0667] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0668] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[0669] 4. The server sends the generated lesson plan back to the device.

[0670] 5. The device parses the generated lesson plan and displays it to the user.

[0671] 6. The user studies the specified content based on the lesson plan displayed on the device.

[0672] 7. The device analyzes the user's facial expressions and voice and recognizes that the user is confused.

[0673] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[0674] 9. The user continues learning based on the adjusted lesson plan.

[0675] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[0676] The processing flow will be explained below.

[0677] Step 1:

[0678] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[0679] Step 2:

[0680] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[0681] Step 3:

[0682] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[0683] Step 4:

[0684] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[0685] Step 5:

[0686] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[0687] Step 6:

[0688] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[0689] Step 7:

[0690] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[0691] Step 8:

[0692] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[0693] Step 9:

[0694] The device analyzes the user's facial expressions, voice, and behavior to determine their emotional state. The device uses a camera and microphone to detect the user's emotional state in real time.

[0695] Step 10:

[0696] The terminal transmits the user's emotional state to the server, for example, if the user is confused, this information is conveyed to the server.

[0697] Step 11:

[0698] The server adjusts the lesson plan based on the received emotional information, using generative artificial intelligence to simplify or elaborate the content to make it easier for the user to understand.

[0699] Step 12:

[0700] The server then sends the adjusted lesson plan back to the user's terminal, and the user continues studying based on the adjusted content.

[0701] In this way, the system recognizes the user's emotional state in real time and adjusts the lesson plan accordingly, providing more effective and personalized education.

[0702] Example 2

[0703] 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."

[0704] Conventional educational systems have struggled to respond to individual users' learning needs and emotional states in a detailed manner. Furthermore, their reliance on fixed curricula and teacher methods did not necessarily maximize users' learning outcomes. Furthermore, they often failed to properly adjust teaching materials and explanations based on real-time feedback from users' emotional states. This often led to problems such as confusion and lack of understanding during learning, creating a need for a system that could maximize individual learning outcomes.

[0705] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0706] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for analyzing the user's facial expressions, voice, and behavior to determine their emotional state, and means for adjusting the lesson plan based on the emotional analysis results, thereby enabling the server to respond to the user's individual learning needs and fine-tune the lesson plan based on their emotional state in real time.

[0707] "Teacher know-how" refers to the specialized knowledge, skills, and information about teaching methods that educators possess.

[0708] "Generative AI" is an AI system that has the ability to automatically generate new information and content based on given data and instructions.

[0709] "User" refers to an individual or group who utilizes the System to receive educational content.

[0710] A "subject" is a specific academic field or topic that a user chooses to study.

[0711] "Teacher type" is an attribute that indicates a teacher's teaching style or approach, and includes classifications such as "logical" and "intuitive."

[0712] A "lesson plan" is a set of lesson plans or materials designed to achieve a specific educational goal.

[0713] "Emotional state" refers to the psychological and emotional state inferred from a user's facial expressions, voice, and behavior.

[0714] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions, voice, and behavioral data to determine their emotional state.

[0715] "Adjustment" is the process of changing the content and difficulty of an existing lesson plan depending on the user's learning situation and emotional state.

[0716] An "interface" is a piece of software or hardware that provides the means by which a user interacts with a system.

[0717] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[0718] Server Processing

[0719] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. An example of an AI model used is "GPT-4." The server also receives requests from users and generates lesson plans based on the requests. An example of a prompt is "Create a lesson plan for: Math with logical style." The server then uses an emotion engine that recognizes the user's emotions to adjust the lesson plan based on the user's emotional state. The emotion engine can be something like "Microsoft Azure Emotion API."

[0720] Terminal handling

[0721] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[0722] User Action

[0723] The user selects the subject and type of teacher they wish to study on their device. Once the selection is complete, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[0724] Specific examples

[0725] We will take a logical teacher-type lesson plan for mathematics and provide a concrete example of how it can be adjusted using an emotion engine.

[0726] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0727] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0728] 3. The server retrieves the teacher's know-how based on "mathematics" and "logical" from the database and generates a lesson plan using generative artificial intelligence. For example, it uses the prompt "Create a lesson plan for: Math with logical style."

[0729] 4. The server sends the generated lesson plan back to the device.

[0730] 5. The device parses the generated lesson plan and displays it to the user.

[0731] 6. The user studies the specified content based on the lesson plan displayed on the device.

[0732] 7. The device analyzes the user's facial expressions and voice to recognize when the user is confused. For example, it uses the Microsoft Azure Emotion API as its emotion engine.

[0733] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[0734] 9. The user continues learning based on the adjusted lesson plan.

[0735] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[0736] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0737] Program processing flow

[0738] Step 1: Import know-how data

[0739] The server retrieves the know-how of excellent teachers from a database. The input is a list of teacher IDs, and the output is a dataset of each teacher's teaching know-how. Specifically, it uses SQL queries to search and retrieve this data.

[0740] Specific operation:

[0741] Send a query to your SQL database: SELECT FROM teacher_knowhow WHERE teacher_id IN (1, 2, 3, ...)

[0742] Prepare to pass the educational know-how obtained from the database to the AI ​​model.

[0743] Step 2: Training the AI ​​model

[0744] The server trains the imported know-how data into a generative AI. The input is the know-how data, and the output is a trained AI model.

[0745] Specific operation:

[0746] Feed the data into the AI ​​model: ai_model.train(teacher_knowhow_data)

[0747] Verify that the learning is complete.

[0748] Step 3: Receiving a user request

[0749] The terminal receives the subject and teacher type selection information from the user and sends it to the server. The input is the user's selection information, and the output is the request data to the server.

[0750] Specific operation:

[0751] Display interface to receive user selection: "Display screen for user selection"

[0752] Send information to the server: "sendToServer(userSelection)"

[0753] Step 4: Generate lesson plans

[0754] The server generates a lesson plan by inputting prompts to the generative AI based on the user's selection information. The input is the selection information and the prompt sentence, and the output is the generated lesson plan.

[0755] Specific operation:

[0756] Create a prompt based on the user's selection: "Create a lesson plan for: Math with logical style."

[0757] Enter a prompt into the AI ​​model: "lesson_plan = ai_model.generate(prompt)"

[0758] Step 5: Emotion Engine Analysis

[0759] The device analyzes the user's facial expressions, voice, and behavior in real time to determine their emotional state. The input is the user's video feed and audio data, and the output is emotional data.

[0760] Specific operation:

[0761] Capture user facial expressions and voice in real time: "Get user video feed"

[0762] Analyze with emotion engine: "emotionData = analyzeEmotion(userVideoFeed)"

[0763] Step 6: Adjust your lesson plan

[0764] The server adjusts the lesson plan based on the emotion data received from the device. The input is the generated lesson plan and emotion data, and the output is the adjusted lesson plan.

[0765] Specific operation:

[0766] Receive emotional data: "Send data about your emotional state to the server"

[0767] Generate a new prompt if needed: "Adjust the lesson plan to simplify: {lesson_plan}"

[0768] Generate an adjusted lesson plan using the AI ​​model: "adjusted_lesson_plan = ai_model.generate(prompt)"

[0769] Step 7: Submit your lesson plan

[0770] The server sends the generated lesson plan to the terminal. The input is the adjusted lesson plan, and the output is the data sent to the terminal.

[0771] Specific operation:

[0772] Send the adjusted lesson plan to the device: "sendToClient(adjusted_lesson_plan)"

[0773] Step 8: View the lesson plan

[0774] The terminal displays the received lesson plan to the user. The input is the adjusted lesson plan and the output is the educational content displayed to the user.

[0775] Specific operation:

[0776] Receive lesson plan: "Receive adjusted_lesson_plan"

[0777] Show to user: "displayLessonPlan(adjusted_lesson_plan)"

[0778] Step 9: Feedback of the user's emotional state

[0779] The terminal continues to analyze the user's facial expressions, voice, and behavior, and sends emotional state feedback to the server. The input is updated emotional data, and the output is feedback data to the server.

[0780] Specific operation:

[0781] Continuous emotion analysis: "Continuously acquire emotionData"

[0782] Feedback of emotional state to the server: "sendToServer(updatedEmotionData)"

[0783] Step 10: View your adjusted lesson plan

[0784] The device updates and redisplays the lesson plan for the user based on the sentiment analysis results from the server. The input is the newly adjusted lesson plan, and the output is the updated educational content.

[0785] Specific operation:

[0786] Receive a new lesson plan: "Receive newLessonPlan"

[0787] Show it to the user again: "displayLessonPlan(newLessonPlan)"

[0788] (Application example 2)

[0789] 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."

[0790] Conventional educational and product recommendation systems do not adequately consider the individual needs and emotional state of users. This makes it difficult to provide optimal lesson plans and product recommendations for users, resulting in problems such as insufficient improvement of learning outcomes and insatiable purchase motivation. In particular, there is a lack of adaptive content provision according to emotional states, making it difficult to improve user satisfaction.

[0791] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, and means for the generative AI to generate a corresponding lesson plan based on the user's selection. This makes it possible to provide a personalized lesson plan based on the user's desired subject and type of teacher. The server also includes means for displaying the generated lesson plan to the user, means for incorporating an emotion engine that recognizes the user's emotional state, means for adjusting the lesson plan based on the emotion engine, means for inputting product categories and characteristics of interest, and means for recommending optimal products based on the input information and emotional state. This makes it possible to recommend optimal products and adjust lesson plans based on the user's emotional state and individual preferences, which is expected to improve user satisfaction.

[0792] "Teacher know-how" is a general term for the specialized knowledge, teaching skills, and educational methods that teachers have acquired through experience.

[0793] "Generative artificial intelligence" is a general term for artificial intelligence models that can generate new information and patterns based on massive amounts of data.

[0794] A "subject that a user wants to study" is a particular educational field or theme that a user selects for their own learning or knowledge improvement.

[0795] "Teacher type" refers to a teacher's characteristics such as teaching style, area of ​​expertise, and teaching method.

[0796] A "lesson plan" is a lesson plan that specifically lays out the learning content and teaching methods based on set educational objectives.

[0797] "Emotion engine" is a general term for technology that analyzes a user's facial expressions, voice, and behavior to recognize their emotional state in real time.

[0798] A "product category" refers to a group of products classified based on their type or attributes.

[0799] "Recommendation tools" is a general term for methods and techniques used to suggest optimal products and services based on a user's needs and emotional state.

[0800] "User's emotional state" is information that indicates the type and intensity of the emotion that the user is feeling at a particular moment.

[0801] The present invention provides an education and product recommendation system that uses generative artificial intelligence (AI) that learns teacher know-how, generates lesson plans tailored to users, and uses an emotion recognition engine. The following describes in detail an embodiment of the present invention.

[0802] Server Processing

[0803] To provide high-quality education, the server retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state. Furthermore, this system also has the function of receiving product category and characteristic information of interest and recommending the most suitable products based on that information. For this purpose, the server includes the following functions:

[0804] Importing know-how data and training the AI ​​model

[0805] Generate lesson plans based on user requests

[0806] Adjusting lesson plans using emotion engines

[0807] Sending generated lesson plans and product recommendations

[0808] Terminal handling

[0809] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study, and to input product categories and characteristics of interest. Once the user has completed their selection, the device transmits the information to the server, which then receives the generated lesson plans and product recommendations. The received information is converted into a format that is displayed to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state. To this end, the device includes the following functions:

[0810] Providing a subject and teacher type selection interface

[0811] Sending user selection information to the server

[0812] Receive and display generated lesson plans and product recommendations

[0813] Emotion engine that analyzes facial expressions, voice, and behavior

[0814] User Action

[0815] The user selects the subject they wish to study, the type of teacher, the product category, and the characteristics of their interest on the device. Once the user completes their selection, the device sends that information to the server, which then generates lesson plans and product recommendations, which are then sent back to the device. The user can use the information displayed on the device to further their studies or consider purchasing. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plans and product recommendations accordingly.

[0816] Software and Hardware

[0817] The hardware used is a smartphone (iOS or Android), smart glasses, or a head-mounted display (e.g., Google Glass). The software uses:

[0818] Emotion analysis: OpenCV, TensorFlow

[0819] AI models: Machine learning frameworks such as TensorFlow

[0820] Communication: requests library (Python)

[0821] Specific examples

[0822] For example, if a user wants to buy a fashion item, she can select "dress" and "elegant" through the app interface and smile at the camera. If the emotion engine recognizes her emotion as "joy," the AI ​​model will suggest the most suitable dress based on her preferences and emotions. In this way, the present invention can tailor optimal product recommendations and lesson plans to the user's emotional state and individual preferences.

[0823] Prompt Sentence Examples

[0824] "I would like to purchase some fashion items. I love dresses and elegant styles, and I am currently experiencing joy. Please recommend the best products for me."

[0825] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0826] Step 1:

[0827] Through the terminal interface, the user selects the subject they wish to study, the type of teacher, the product category, and the characteristics they are interested in. By inputting this information, the user's individual needs are clarified. The input contents include the subject name, teacher style, product category, and characteristic information. For example, "Mathematics," "Logical," "Dress," "Elegant," etc.

[0828] Step 2:

[0829] The terminal receives the selection information from the user and sends it to the server. The terminal organizes the user's selection information, converts it into a specific format, and sends it to the server. This input data is necessary for processing within the server. Specific input data includes subject name, teaching style, product category, characteristic information, and user identification information.

[0830] Step 3:

[0831] Based on the received user information, the server uses generative AI to generate corresponding lesson plans and product recommendations. The server extracts relevant teacher know-how and product information from its database, inputs this data into an AI model, and generates appropriate lesson plans and product recommendations. As a result, a user-specific lesson plan and product list are generated and output.

[0832] Step 4:

[0833] The server transmits the generated lesson plan and product recommendation information to the terminal. The server then transmits the generated result data to the corresponding terminal based on the user identification information. The transmitted data includes the specific content of the lesson plan and a list of recommended products.

[0834] Step 5:

[0835] The terminal displays the received lesson plan and product recommendation information to the user. The terminal converts the data sent from the server into a visually easy-to-understand format and presents it to the user. This allows the user to check the generated educational content and recommended products.

[0836] Step 6:

[0837] The device analyzes facial expressions, voice, and behavior to recognize the user's emotional state. When the user provides facial expressions and voice through the device, the emotion engine analyzes these data in real time to determine the user's emotional state. This analysis is performed on the device, and the resulting emotional state information is output.

[0838] Step 7:

[0839] The server adjusts the generated lesson plans and product recommendations based on the emotional state sent from the device. Based on the emotional data obtained from the emotion engine, the server re-runs the AI ​​model to generate new lesson plans and product recommendations that correspond to the user's emotional state. This adjusted data is then sent back to the device.

[0840] Step 8:

[0841] The device then displays the adjusted lesson plan and product recommendations to the user again. Finally, the device displays educational content and product lists optimized for the user's emotional state, providing the user with an improved educational and purchasing experience.

[0842] This series of steps allows users to enjoy a personalized and optimal learning and purchasing experience.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] [Third embodiment]

[0847] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0848] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0849] 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).

[0850] 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.

[0851] 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.

[0852] 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).

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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."

[0859] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the subject and teacher type they wish to study, and generates and provides a lesson plan based on the selection. An embodiment of this system is described in detail below.

[0860] Server Processing

[0861] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Specifically, the server creates customized lesson plans using know-how data according to the subject and teacher type selected by the user.

[0862] The server includes the following functions:

[0863] Importing know-how data and training the AI ​​model

[0864] Generate lesson plans based on user requests

[0865] Submitting the generated lesson plan

[0866] Terminal handling

[0867] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives the generated lesson plan from the server. The received lesson plan is converted into a format that can be displayed to the user and provided to the user.

[0868] The device includes the following features:

[0869] Providing a subject and teacher type selection interface

[0870] Sending user selection information to the server

[0871] Receive and view generated lesson plans

[0872] User Action

[0873] The user selects the subject and teacher type they wish to study on their device. Once the user has completed their selection, the information is sent by the device to the server, and a generated lesson plan is sent back to the device. The user can then use the lesson plan displayed on the device to continue their studies.

[0874] The specific steps for users are as follows:

[0875] 1. The user selects the subject and teacher type through the terminal interface.

[0876] 2. The user's selection information is sent from the terminal to the server.

[0877] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[0878] 4. The user studies the lesson plan displayed on the device.

[0879] Specific examples

[0880] Here is a concrete example of a logical math teacher type lesson plan:

[0881] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0882] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0883] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[0884] 4. The server sends the generated lesson plan back to the device.

[0885] 5. The device parses the generated lesson plan and displays it to the user.

[0886] 6. The user studies the specified content based on the lesson plan displayed on the device.

[0887] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[0888] The processing flow will be explained below.

[0889] Step 1:

[0890] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[0891] Step 2:

[0892] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[0893] Step 3:

[0894] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[0895] Step 4:

[0896] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[0897] Step 5:

[0898] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[0899] Step 6:

[0900] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[0901] Step 7:

[0902] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[0903] Step 8:

[0904] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[0905] In this way, the present invention allows users to receive high-quality education tailored to their needs, and eliminates variations in teacher quality and teaching methods, enabling learning to be performed at a consistent educational level anywhere, anytime.

[0906] Example 1

[0907] 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."

[0908] Traditional education systems face challenges such as inconsistencies in teacher quality and teaching methods, making it difficult to provide a consistent, high-quality education. It is also difficult to generate customized lesson plans tailored to the subject and type of teacher a user wants to learn. Furthermore, users often lack access to the appropriate educational resources when they need them.

[0909] 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.

[0910] In this invention, the server includes a means for acquiring teacher know-how and having the generative AI learn it, a means for the user to select the academic field they wish to study and the characteristics of the teacher, a means for the generative AI to generate a corresponding lesson plan based on the user's selection, and a means for displaying the generated lesson plan to the user. This allows the user to receive high-quality education at any time and obtain a lesson plan customized according to the academic field and the characteristics of the teacher.

[0911] "Teacher know-how" refers to information such as knowledge, skills, teaching methods, teaching materials, etc. accumulated by teachers in the field of education.

[0912] "Generative AI" refers to an AI system that has the ability to generate new information or content based on given data.

[0913] An "academic field" refers to an area in which a particular specialized knowledge or skill is systematized, or a single subject or theme.

[0914] "Teacher characteristics" refers to the teaching style and characteristics of a teacher, such as tendencies toward teaching methods such as being logical, intuitive, or practical.

[0915] A "learning plan" refers to a specific plan for learning, including the teaching materials to be used, lesson content, progress method, evaluation criteria, etc.

[0916] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the academic field they wish to study and the characteristics of the teacher, and generates a study plan based on the selection and provides it to the user. The details of this system are explained below.

[0917] Server Processing

[0918] The server first retrieves the know-how of multiple teachers from a database to provide high-quality education. This includes lecture materials, lesson videos, evaluation reports, etc. The retrieved know-how data is trained by a generative AI (such as OpenAI's GPT-4). In this training process, the following prompt sentences are used:

[0919] "Below are lecture materials from excellent math teachers. Learn their know-how."

[0920] Next, the server receives a request sent by the user via the terminal. The request includes the subject area the user wants to study and the characteristics of the teacher. Based on this information, the server uses generative artificial intelligence to generate an appropriate lesson plan. Specifically, the server generates a lesson plan using the following prompt sentence:

[0921] "User says they want to learn math. Create a lesson plan based on logical teacher types."

[0922] The generated learning plan is sent from the server to the device as JSON format data.

[0923] Terminal handling

[0924] The terminal functions as a user interface. The user selects the academic field and teacher characteristics they wish to study through the interface provided by the terminal. Once the selection is complete, the terminal transmits the information to the server. The lesson plan returned from the server is received by the terminal and converted into a format that can be displayed to the user.

[0925] User Action

[0926] The user selects the academic field and teacher characteristics they wish to study from the interface using their terminal. The selection information is sent to the server, and the generated learning plan is sent back to the terminal. The user can then proceed with their studies based on the learning plan displayed on the terminal.

[0927] Specific examples

[0928] For example, if a user wants a logical teacher-type lesson plan for math, the system works as follows:

[0929] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[0930] 2. The terminal receives the user's selection and transmits the selection information to the server.

[0931] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates a learning plan using generative artificial intelligence (for example, OpenAI's GPT-4).

[0932] 4. The server returns the generated learning plan to the device.

[0933] 5. The device analyzes the generated lesson plan and displays it to the user.

[0934] 6. The user studies the specified content based on the study plan displayed on the device.

[0935] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[0936] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0937] Server Processing Steps

[0938] Step 1: Acquire know-how data

[0939] To improve the quality of education, the server retrieves teacher know-how data (e.g., lecture materials, lesson videos, evaluation reports, etc.) from the database. The input is a search query, and the output is the corresponding know-how data.

[0940] Specific behavior:

[0941] The server uses SQL queries to filter and retrieve the required entries from the database.

[0942] Example: SELECT FROM Knowhow WHERE Subject = "Mathematics" AND TeacherType = "Logical"

[0943] Step 2: Training the AI ​​model

[0944] The server preprocesses the acquired know-how data and trains it on a generative AI (e.g., GPT-4). The input is the preprocessed know-how data, and the output is a trained AI model.

[0945] Specific behavior:

[0946] Know-how data is converted into text format and input into generative artificial intelligence through prompt sentences.

[0947] Example: Prompt: "Below is a lecture material from an excellent math teacher. Please learn this know-how."

[0948] Step 3: Receiving a user request

[0949] The server receives requests sent from users via their terminals. The requests include the subject area the user wants to study and the characteristics of the teacher. The input is the user's request information, and the output is the content of the request.

[0950] Specific behavior:

[0951] Receives the HTTP request and parses the request parameters (discipline and teacher characteristics).

[0952] Example: GET / generateLessonPlan?subject=Mathematics&teacherType=Logic

[0953] Step 4: Generate lesson plans

[0954] The server generates a learning plan based on the user's request using generative artificial intelligence. The input is the request information and a trained AI model, and the output is the learning plan.

[0955] Specific behavior:

[0956] Send prompts to GPT-4 to generate a learning plan.

[0957] Example: Prompt: "The user says they want to learn math. Create a lesson plan based on logical teacher types."

[0958] Step 5: Submit your lesson plan

[0959] The server sends the generated learning plan to the terminal as JSON format data. The input is the generated learning plan, and the output is an HTTP response to the terminal.

[0960] Specific behavior:

[0961] Send lesson plan data in JSON format as an HTTP response.

[0962] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[0963] Terminal processing steps

[0964] Step 1: Provide an interface

[0965] The terminal provides the user with an interface that allows them to select the subject they wish to study and the characteristics of the teacher. The input is the terminal configuration information, and the output is the interface display.

[0966] Specific behavior:

[0967] Create a select menu using HTML and CSS.

[0968] For example: "Choose the subject you would like to study.", "Choose the type of teacher."

[0969] Step 2: Sending User Selections

[0970] The terminal sends the user's selected academic field and teacher characteristics to the server. The input is the user's selection information, and the output is a request to the server.

[0971] Specific behavior:

[0972] The user's selection information is sent to the server using JavaScript AJAX.

[0973] Example: ajax.send("GET", " / generateLessonPlan?subject=Mathematics&teacherType=Logical")

[0974] Step 3: Receive your lesson plans

[0975] The terminal receives the generated learning plan from the server. The input is the HTTP response from the server, and the output is the learning plan data.

[0976] Specific behavior:

[0977] Receives the HTTP response from the server and parses the JSON format data.

[0978] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[0979] Step 4: View the lesson plan

[0980] The terminal displays the received lesson plan to the user. The input is the lesson plan data, and the output is the display on the user interface.

[0981] Specific behavior:

[0982] Use HTML and JavaScript to convert lesson plans into display formats.

[0983] For example: "Today's lesson plan: 1. Explain basic concepts, 2. Practice questions, 3. Application questions."

[0984] User processing steps

[0985] Step 1: Select subject and teacher type

[0986] The user selects the academic field they wish to study and the characteristics of the teacher through the terminal interface. The input is the user's selection, and the output is the input data to the terminal.

[0987] Specific behavior:

[0988] Select the discipline and teacher characteristics from the drop-down menus.

[0989] Examples: "mathematics", "logical"

[0990] Step 2: Start learning

[0991] The user proceeds with their studies based on the study plan displayed on the terminal. The input is the study plan displayed on the terminal, and the output is the user's study behavior.

[0992] Specific behavior:

[0993] Follow the displayed study plan, solve the problems and read the explanations.

[0994] For example, study based on "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions."

[0995] The above are the specific processing steps and operations in the system of the present invention.

[0996] (Application example 1)

[0997] 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."

[0998] Conventional educational systems have difficulty providing effective lesson plans based on the user's selected subject and teacher type, and are often restricted by location and time. Furthermore, typical online educational systems lack a sense of realism and interactivity, limiting learning effectiveness. Therefore, there is a demand for a system that allows users to take high-quality, interactive lessons in an immersive virtual space.

[0999] 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.

[1000] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for displaying the generated lesson plan to the user, and means for the user to take interactive lessons in a virtual space. This allows users to take high-quality, interactive lessons in a virtual space, providing a realistic learning experience without being restricted by location or time.

[1001] "Teacher know-how" refers to the specialized knowledge and teaching methods that educators possess, as well as the teaching techniques and methodologies they have acquired through their experience in the field of education.

[1002] "Generative AI" is a type of AI that uses algorithms and models to learn from large amounts of data and provide solutions to specific problems.

[1003] "Subjects that users want to study" refers to the fields or topics that users of the educational system wish to study.

[1004] "Teacher type" refers to categories of teachers with different teaching styles and teaching methods, and can be selected by the user.

[1005] A "lesson plan" is a document or program that contains details of the teaching plan or learning content to be followed by a learner, generated based on a specific subject and type of teacher.

[1006] A "virtual space" is a three-dimensional computer-generated virtual environment in which users can have an immersive, interactive experience.

[1007] "Interface" refers to the means or devices by which a user interacts with a system, and typically includes a graphical user interface (GUI).

[1008] "User request" is information that specifically indicates the learner's demands and wishes for the learning system.

[1009] A "server" is a computer system that receives requests, processes data, and provides appropriate information and services to clients.

[1010] The present invention is an educational system that uses generative artificial intelligence to learn teacher know-how, and generates and provides lesson plans based on a user's selection of the subject and teacher type they wish to study. Furthermore, this system allows users to take interactive lessons in a virtual space. Specific embodiments of each component are described below.

[1011] Server Processing

[1012] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on them. The generative AI used is OpenAI's GPT-3. This model is capable of learning from large amounts of educational data and generating lesson plans suited to specific subjects and teaching styles.

[1013] Examples of specific prompts are:

[1014] Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations.

[1015] The lesson plans generated by GPT-3 are then converted into a format for display in the virtual space. The server manages user requests and the generated lesson plans, and sends them to the device in the virtual space at the appropriate time.

[1016] Terminal handling

[1017] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits this information to the server and receives the generated lesson plan from the server. The received lesson plan is then converted into a format that is displayed to the user, allowing them to experience it interactively in a virtual space. For this reason, the device requires hardware with high-performance graphics and processing capabilities, such as the latest smartphones or head-mounted displays (HMDs).

[1018] User Action

[1019] The user selects the subject and teacher type they wish to study using their device. The user's learning request is then sent from the device to the server, and a generated lesson plan is sent back to the device. The user can then proceed with their learning in a virtual space based on the lesson plan. For example, if a user selects a chemistry experiment class, they can wear an HMD and learn while visualizing the actual chemistry experiment in the virtual space.

[1020] Example

[1021] Here is a concrete example of a chemistry experiment:

[1022] 1. The user selects the "Chemistry" and "Experimental" teacher types in the terminal interface.

[1023] 2. The terminal sends the user's selection information to the server.

[1024] 3. The server retrieves the teacher's know-how based on "chemistry" and "experimental" from the database and generates a lesson plan using GPT-3.

[1025] 4. The server sends the generated lesson plan to the device.

[1026] 5. The device analyzes the received lesson plan and displays it in the virtual space.

[1027] 6. Users use the HMD to take interactive lessons in a virtual space.

[1028] This system allows users to receive high-quality education in a virtual space with a sense of realism, significantly improving learning effectiveness.

[1029] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1030] Step 1:

[1031] The user uses the device interface to select the subject and teacher type they wish to study, either by using a mouse or touch screen to select the subject and teacher type from drop-down menus, and the selection is entered into the device and sent to the server.

[1032] Step 2:

[1033] The device sends the user's selection information (subject and teacher type) to the server. Specifically, data about the selected subject and teacher type is sent to the server via a dedicated API endpoint. This data is sent in the form of a request.

[1034] Step 3:

[1035] The server receives a request sent by the user. The request includes the user's selected subject and teacher type. Based on this input, the server retrieves the corresponding teacher's know-how data from the database.

[1036] Step 4:

[1037] The server passes the acquired know-how data to a generative artificial intelligence (for example, OpenAI's GPT-3), which generates a lesson plan based on the user's selection. Specifically, it generates a prompt and sends a request to the GPT-3 model. An example prompt is "Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations." GPT-3 outputs the text data of the lesson plan based on this prompt.

[1038] Step 5:

[1039] The server receives the lesson plans from GPT-3, parses them, and formats them as structured data, which is then converted into a user-friendly form and ready to be sent to the device.

[1040] Step 6:

[1041] The server sends the generated lesson plan to the terminal, which sends the data in the form of a response containing a detailed lesson plan for the subject and type of teacher selected by the user.

[1042] Step 7:

[1043] The device then analyzes the received lesson plan and converts it into a format suitable for display in the virtual space, including the 3D objects and interactive elements used in the virtual space.

[1044] Step 8:

[1045] Users enter a virtual space using a head-mounted display (HMD). The converted lesson plan is displayed interactively within this virtual space. Through visual and physical movements, users can experience and learn the lesson content based on the lesson plan generated in the virtual space.

[1046] In this way, by executing each step consecutively, the user can interactively experience high-quality educational content in a virtual space.

[1047] 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.

[1048] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[1049] Server Processing

[1050] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state.

[1051] The server includes the following functions:

[1052] Importing know-how data and training the AI ​​model

[1053] Generate lesson plans based on user requests

[1054] Adjusting lesson plans using emotion engines

[1055] Submitting the generated lesson plan

[1056] Terminal handling

[1057] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[1058] The device includes the following features:

[1059] Providing a subject and teacher type selection interface

[1060] Sending user selection information to the server

[1061] Receive and view generated lesson plans

[1062] Emotion engine that analyzes facial expressions, voice, and behavior

[1063] User Action

[1064] The user selects the subject and type of teacher they wish to study on the device. Once the user completes their selection, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[1065] The specific steps for users are as follows:

[1066] 1. The user selects the subject and teacher type through the terminal interface.

[1067] 2. The user's selection information is sent from the terminal to the server.

[1068] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[1069] 4. The user proceeds with their studies based on the lesson plan displayed on the device.

[1070] 5. The device analyzes the user's facial expressions, voice, and behavior to recognize their emotional state.

[1071] 6. The server uses the emotion engine to adjust the lesson plan and provide it to the user.

[1072] Specific examples

[1073] Here's an example of taking a math lesson plan from a logical teacher and adjusting it using the emotion engine:

[1074] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[1075] 2. The terminal receives the user's selection and transmits the selection information to the server.

[1076] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[1077] 4. The server sends the generated lesson plan back to the device.

[1078] 5. The device parses the generated lesson plan and displays it to the user.

[1079] 6. The user studies the specified content based on the lesson plan displayed on the device.

[1080] 7. The device analyzes the user's facial expressions and voice and recognizes that the user is confused.

[1081] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[1082] 9. The user continues learning based on the adjusted lesson plan.

[1083] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[1084] The processing flow will be explained below.

[1085] Step 1:

[1086] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[1087] Step 2:

[1088] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[1089] Step 3:

[1090] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[1091] Step 4:

[1092] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[1093] Step 5:

[1094] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[1095] Step 6:

[1096] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[1097] Step 7:

[1098] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[1099] Step 8:

[1100] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[1101] Step 9:

[1102] The device analyzes the user's facial expressions, voice, and behavior to determine their emotional state. The device uses a camera and microphone to detect the user's emotional state in real time.

[1103] Step 10:

[1104] The terminal transmits the user's emotional state to the server, for example, if the user is confused, this information is conveyed to the server.

[1105] Step 11:

[1106] The server adjusts the lesson plan based on the received emotional information, using generative artificial intelligence to simplify or elaborate the content to make it easier for the user to understand.

[1107] Step 12:

[1108] The server then sends the adjusted lesson plan back to the user's terminal, and the user continues studying based on the adjusted content.

[1109] In this way, the system recognizes the user's emotional state in real time and adjusts the lesson plan accordingly, providing more effective and personalized education.

[1110] Example 2

[1111] 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."

[1112] Conventional educational systems have struggled to respond to individual users' learning needs and emotional states in a detailed manner. Furthermore, their reliance on fixed curricula and teacher methods did not necessarily maximize users' learning outcomes. Furthermore, they often failed to properly adjust teaching materials and explanations based on real-time feedback from users' emotional states. This often led to problems such as confusion and lack of understanding during learning, creating a need for a system that could maximize individual learning outcomes.

[1113] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1114] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for analyzing the user's facial expressions, voice, and behavior to determine their emotional state, and means for adjusting the lesson plan based on the emotional analysis results, thereby enabling the server to respond to the user's individual learning needs and fine-tune the lesson plan based on their emotional state in real time.

[1115] "Teacher know-how" refers to the specialized knowledge, skills, and information about teaching methods that educators possess.

[1116] "Generative AI" is an AI system that has the ability to automatically generate new information and content based on given data and instructions.

[1117] "User" refers to an individual or group who utilizes the System to receive educational content.

[1118] A "subject" is a specific academic field or topic that a user chooses to study.

[1119] "Teacher type" is an attribute that indicates a teacher's teaching style or approach, and includes classifications such as "logical" and "intuitive."

[1120] A "lesson plan" is a set of lesson plans or materials designed to achieve a specific educational goal.

[1121] "Emotional state" refers to the psychological and emotional state inferred from a user's facial expressions, voice, and behavior.

[1122] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions, voice, and behavioral data to determine their emotional state.

[1123] "Adjustment" is the process of changing the content and difficulty of an existing lesson plan depending on the user's learning situation and emotional state.

[1124] An "interface" is a piece of software or hardware that provides the means by which a user interacts with a system.

[1125] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[1126] Server Processing

[1127] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. An example of an AI model used is "GPT-4." The server also receives requests from users and generates lesson plans based on the requests. An example of a prompt is "Create a lesson plan for: Math with logical style." The server then uses an emotion engine that recognizes the user's emotions to adjust the lesson plan based on the user's emotional state. The emotion engine can be something like "Microsoft Azure Emotion API."

[1128] Terminal handling

[1129] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[1130] User Action

[1131] The user selects the subject and type of teacher they wish to study on their device. Once the selection is complete, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[1132] Specific examples

[1133] We will take a logical teacher-type lesson plan for mathematics and provide a concrete example of how it can be adjusted using an emotion engine.

[1134] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[1135] 2. The terminal receives the user's selection and transmits the selection information to the server.

[1136] 3. The server retrieves the teacher's know-how based on "mathematics" and "logical" from the database and generates a lesson plan using generative artificial intelligence. For example, it uses the prompt "Create a lesson plan for: Math with logical style."

[1137] 4. The server sends the generated lesson plan back to the device.

[1138] 5. The device parses the generated lesson plan and displays it to the user.

[1139] 6. The user studies the specified content based on the lesson plan displayed on the device.

[1140] 7. The device analyzes the user's facial expressions and voice to recognize when the user is confused. For example, it uses the Microsoft Azure Emotion API as its emotion engine.

[1141] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[1142] 9. The user continues learning based on the adjusted lesson plan.

[1143] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[1144] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1145] Program processing flow

[1146] Step 1: Import know-how data

[1147] The server retrieves the know-how of excellent teachers from a database. The input is a list of teacher IDs, and the output is a dataset of each teacher's teaching know-how. Specifically, it uses SQL queries to search and retrieve this data.

[1148] Specific operation:

[1149] Send a query to your SQL database: SELECT FROM teacher_knowhow WHERE teacher_id IN (1, 2, 3, ...)

[1150] Prepare to pass the educational know-how obtained from the database to the AI ​​model.

[1151] Step 2: Training the AI ​​model

[1152] The server trains the imported know-how data into a generative AI. The input is the know-how data, and the output is a trained AI model.

[1153] Specific operation:

[1154] Feed the data into the AI ​​model: ai_model.train(teacher_knowhow_data)

[1155] Verify that the learning is complete.

[1156] Step 3: Receiving a user request

[1157] The terminal receives the subject and teacher type selection information from the user and sends it to the server. The input is the user's selection information, and the output is the request data to the server.

[1158] Specific operation:

[1159] Display interface to receive user selection: "Display screen for user selection"

[1160] Send information to the server: "sendToServer(userSelection)"

[1161] Step 4: Generate lesson plans

[1162] The server generates a lesson plan by inputting prompts to the generative AI based on the user's selection information. The input is the selection information and the prompt sentence, and the output is the generated lesson plan.

[1163] Specific operation:

[1164] Create a prompt based on the user's selection: "Create a lesson plan for: Math with logical style."

[1165] Enter a prompt into the AI ​​model: "lesson_plan = ai_model.generate(prompt)"

[1166] Step 5: Emotion Engine Analysis

[1167] The device analyzes the user's facial expressions, voice, and behavior in real time to determine their emotional state. The input is the user's video feed and audio data, and the output is emotional data.

[1168] Specific operation:

[1169] Capture user facial expressions and voice in real time: "Get user video feed"

[1170] Analyze with emotion engine: "emotionData = analyzeEmotion(userVideoFeed)"

[1171] Step 6: Adjust your lesson plan

[1172] The server adjusts the lesson plan based on the emotion data received from the device. The input is the generated lesson plan and emotion data, and the output is the adjusted lesson plan.

[1173] Specific operation:

[1174] Receive emotional data: "Send data about your emotional state to the server"

[1175] Generate a new prompt if needed: "Adjust the lesson plan to simplify: {lesson_plan}"

[1176] Generate an adjusted lesson plan using the AI ​​model: "adjusted_lesson_plan = ai_model.generate(prompt)"

[1177] Step 7: Submit your lesson plan

[1178] The server sends the generated lesson plan to the terminal. The input is the adjusted lesson plan, and the output is the data sent to the terminal.

[1179] Specific operation:

[1180] Send the adjusted lesson plan to the device: "sendToClient(adjusted_lesson_plan)"

[1181] Step 8: View the lesson plan

[1182] The terminal displays the received lesson plan to the user. The input is the adjusted lesson plan and the output is the educational content displayed to the user.

[1183] Specific operation:

[1184] Receive lesson plan: "Receive adjusted_lesson_plan"

[1185] Show to user: "displayLessonPlan(adjusted_lesson_plan)"

[1186] Step 9: Feedback of the user's emotional state

[1187] The terminal continues to analyze the user's facial expressions, voice, and behavior, and sends emotional state feedback to the server. The input is updated emotional data, and the output is feedback data to the server.

[1188] Specific operation:

[1189] Continuous emotion analysis: "Continuously acquire emotionData"

[1190] Feedback of emotional state to the server: "sendToServer(updatedEmotionData)"

[1191] Step 10: View your adjusted lesson plan

[1192] The device updates and redisplays the lesson plan for the user based on the sentiment analysis results from the server. The input is the newly adjusted lesson plan, and the output is the updated educational content.

[1193] Specific operation:

[1194] Receive a new lesson plan: "Receive newLessonPlan"

[1195] Show it to the user again: "displayLessonPlan(newLessonPlan)"

[1196] (Application example 2)

[1197] 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."

[1198] Conventional educational and product recommendation systems do not adequately consider the individual needs and emotional state of users. This makes it difficult to provide optimal lesson plans and product recommendations for users, resulting in problems such as insufficient improvement of learning outcomes and insatiable purchase motivation. In particular, there is a lack of adaptive content provision according to emotional states, making it difficult to improve user satisfaction.

[1199] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, and means for the generative AI to generate a corresponding lesson plan based on the user's selection. This makes it possible to provide a personalized lesson plan based on the user's desired subject and type of teacher. The server also includes means for displaying the generated lesson plan to the user, means for incorporating an emotion engine that recognizes the user's emotional state, means for adjusting the lesson plan based on the emotion engine, means for inputting product categories and characteristics of interest, and means for recommending optimal products based on the input information and emotional state. This makes it possible to recommend optimal products and adjust lesson plans based on the user's emotional state and individual preferences, which is expected to improve user satisfaction.

[1200] "Teacher know-how" is a general term for the specialized knowledge, teaching skills, and educational methods that teachers have acquired through experience.

[1201] "Generative artificial intelligence" is a general term for artificial intelligence models that can generate new information and patterns based on massive amounts of data.

[1202] A "subject that a user wants to study" is a particular educational field or theme that a user selects for their own learning or knowledge improvement.

[1203] "Teacher type" refers to a teacher's characteristics such as teaching style, area of ​​expertise, and teaching method.

[1204] A "lesson plan" is a lesson plan that specifically lays out the learning content and teaching methods based on set educational objectives.

[1205] "Emotion engine" is a general term for technology that analyzes a user's facial expressions, voice, and behavior to recognize their emotional state in real time.

[1206] A "product category" refers to a group of products classified based on their type or attributes.

[1207] "Recommendation tools" is a general term for methods and techniques used to suggest optimal products and services based on a user's needs and emotional state.

[1208] "User's emotional state" is information that indicates the type and intensity of the emotion that the user is feeling at a particular moment.

[1209] The present invention provides an education and product recommendation system that uses generative artificial intelligence (AI) that learns teacher know-how, generates lesson plans tailored to users, and uses an emotion recognition engine. The following describes in detail an embodiment of the present invention.

[1210] Server Processing

[1211] To provide high-quality education, the server retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state. Furthermore, this system also has the function of receiving product category and characteristic information of interest and recommending the most suitable products based on that information. For this purpose, the server includes the following functions:

[1212] Importing know-how data and training the AI ​​model

[1213] Generate lesson plans based on user requests

[1214] Adjusting lesson plans using emotion engines

[1215] Sending generated lesson plans and product recommendations

[1216] Terminal handling

[1217] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study, and to input product categories and characteristics of interest. Once the user has completed their selection, the device transmits the information to the server, which then receives the generated lesson plans and product recommendations. The received information is converted into a format that is displayed to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state. To this end, the device includes the following functions:

[1218] Providing a subject and teacher type selection interface

[1219] Sending user selection information to the server

[1220] Receive and display generated lesson plans and product recommendations

[1221] Emotion engine that analyzes facial expressions, voice, and behavior

[1222] User Action

[1223] The user selects the subject they wish to study, the type of teacher, the product category, and the characteristics of their interest on the device. Once the user completes their selection, the device sends that information to the server, which then generates lesson plans and product recommendations, which are then sent back to the device. The user can use the information displayed on the device to further their studies or consider purchasing. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plans and product recommendations accordingly.

[1224] Software and Hardware

[1225] The hardware used is a smartphone (iOS or Android), smart glasses, or a head-mounted display (e.g., Google Glass). The software uses:

[1226] Emotion analysis: OpenCV, TensorFlow

[1227] AI models: Machine learning frameworks such as TensorFlow

[1228] Communication: requests library (Python)

[1229] Specific examples

[1230] For example, if a user wants to buy a fashion item, she can select "dress" and "elegant" through the app interface and smile at the camera. If the emotion engine recognizes her emotion as "joy," the AI ​​model will suggest the most suitable dress based on her preferences and emotions. In this way, the present invention can tailor optimal product recommendations and lesson plans to the user's emotional state and individual preferences.

[1231] Prompt Sentence Examples

[1232] "I would like to purchase some fashion items. I love dresses and elegant styles, and I am currently experiencing joy. Please recommend the best products for me."

[1233] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1234] Step 1:

[1235] Through the terminal interface, the user selects the subject they wish to study, the type of teacher, the product category, and the characteristics they are interested in. By inputting this information, the user's individual needs are clarified. The input contents include the subject name, teacher style, product category, and characteristic information. For example, "Mathematics," "Logical," "Dress," "Elegant," etc.

[1236] Step 2:

[1237] The terminal receives the selection information from the user and sends it to the server. The terminal organizes the user's selection information, converts it into a specific format, and sends it to the server. This input data is necessary for processing within the server. Specific input data includes subject name, teaching style, product category, characteristic information, and user identification information.

[1238] Step 3:

[1239] Based on the received user information, the server uses generative AI to generate corresponding lesson plans and product recommendations. The server extracts relevant teacher know-how and product information from its database, inputs this data into an AI model, and generates appropriate lesson plans and product recommendations. As a result, a user-specific lesson plan and product list are generated and output.

[1240] Step 4:

[1241] The server transmits the generated lesson plan and product recommendation information to the terminal. The server then transmits the generated result data to the corresponding terminal based on the user identification information. The transmitted data includes the specific content of the lesson plan and a list of recommended products.

[1242] Step 5:

[1243] The terminal displays the received lesson plan and product recommendation information to the user. The terminal converts the data sent from the server into a visually easy-to-understand format and presents it to the user. This allows the user to check the generated educational content and recommended products.

[1244] Step 6:

[1245] The device analyzes facial expressions, voice, and behavior to recognize the user's emotional state. When the user provides facial expressions and voice through the device, the emotion engine analyzes these data in real time to determine the user's emotional state. This analysis is performed on the device, and the resulting emotional state information is output.

[1246] Step 7:

[1247] The server adjusts the generated lesson plans and product recommendations based on the emotional state sent from the device. Based on the emotional data obtained from the emotion engine, the server re-runs the AI ​​model to generate new lesson plans and product recommendations that correspond to the user's emotional state. This adjusted data is then sent back to the device.

[1248] Step 8:

[1249] The device then displays the adjusted lesson plan and product recommendations to the user again. Finally, the device displays educational content and product lists optimized for the user's emotional state, providing the user with an improved educational and purchasing experience.

[1250] This series of steps allows users to enjoy a personalized and optimal learning and purchasing experience.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] [Fourth embodiment]

[1255] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1256] 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.

[1257] 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).

[1258] 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.

[1259] 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.

[1260] 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).

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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."

[1268] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the subject and teacher type they wish to study, and generates and provides a lesson plan based on the selection. An embodiment of this system is described in detail below.

[1269] Server Processing

[1270] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Specifically, the server creates customized lesson plans using know-how data according to the subject and teacher type selected by the user.

[1271] The server includes the following functions:

[1272] Importing know-how data and training the AI ​​model

[1273] Generate lesson plans based on user requests

[1274] Submitting the generated lesson plan

[1275] Terminal handling

[1276] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives the generated lesson plan from the server. The received lesson plan is converted into a format that can be displayed to the user and provided to the user.

[1277] The device includes the following features:

[1278] Providing a subject and teacher type selection interface

[1279] Sending user selection information to the server

[1280] Receive and view generated lesson plans

[1281] User Action

[1282] The user selects the subject and teacher type they wish to study on their device. Once the user has completed their selection, the information is sent by the device to the server, and a generated lesson plan is sent back to the device. The user can then use the lesson plan displayed on the device to continue their studies.

[1283] The specific steps for users are as follows:

[1284] 1. The user selects the subject and teacher type through the terminal interface.

[1285] 2. The user's selection information is sent from the terminal to the server.

[1286] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[1287] 4. The user studies the lesson plan displayed on the device.

[1288] Specific examples

[1289] Here is a concrete example of a logical math teacher type lesson plan:

[1290] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[1291] 2. The terminal receives the user's selection and transmits the selection information to the server.

[1292] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[1293] 4. The server sends the generated lesson plan back to the device.

[1294] 5. The device parses the generated lesson plan and displays it to the user.

[1295] 6. The user studies the specified content based on the lesson plan displayed on the device.

[1296] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[1297] The processing flow will be explained below.

[1298] Step 1:

[1299] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[1300] Step 2:

[1301] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[1302] Step 3:

[1303] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[1304] Step 4:

[1305] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[1306] Step 5:

[1307] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[1308] Step 6:

[1309] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[1310] Step 7:

[1311] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[1312] Step 8:

[1313] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[1314] In this way, the present invention allows users to receive high-quality education tailored to their needs, and eliminates variations in teacher quality and teaching methods, enabling learning to be performed at a consistent educational level anywhere, anytime.

[1315] Example 1

[1316] 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."

[1317] Traditional education systems face challenges such as inconsistencies in teacher quality and teaching methods, making it difficult to provide a consistent, high-quality education. It is also difficult to generate customized lesson plans tailored to the subject and type of teacher a user wants to learn. Furthermore, users often lack access to the appropriate educational resources when they need them.

[1318] 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.

[1319] In this invention, the server includes a means for acquiring teacher know-how and having the generative AI learn it, a means for the user to select the academic field they wish to study and the characteristics of the teacher, a means for the generative AI to generate a corresponding lesson plan based on the user's selection, and a means for displaying the generated lesson plan to the user. This allows the user to receive high-quality education at any time and obtain a lesson plan customized according to the academic field and the characteristics of the teacher.

[1320] "Teacher know-how" refers to information such as knowledge, skills, teaching methods, teaching materials, etc. accumulated by teachers in the field of education.

[1321] "Generative AI" refers to an AI system that has the ability to generate new information or content based on given data.

[1322] An "academic field" refers to an area in which a particular specialized knowledge or skill is systematized, or a single subject or theme.

[1323] "Teacher characteristics" refers to the teaching style and characteristics of a teacher, such as tendencies toward teaching methods such as being logical, intuitive, or practical.

[1324] A "learning plan" refers to a specific plan for learning, including the teaching materials to be used, lesson content, progress method, evaluation criteria, etc.

[1325] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn the know-how of teachers, allows a user to select the academic field they wish to study and the characteristics of the teacher, and generates a study plan based on the selection and provides it to the user. The details of this system are explained below.

[1326] Server Processing

[1327] The server first retrieves the know-how of multiple teachers from a database to provide high-quality education. This includes lecture materials, lesson videos, evaluation reports, etc. The retrieved know-how data is trained by a generative AI (such as OpenAI's GPT-4). In this training process, the following prompt sentences are used:

[1328] "Below are lecture materials from excellent math teachers. Learn their know-how."

[1329] Next, the server receives a request sent by the user via the terminal. The request includes the subject area the user wants to study and the characteristics of the teacher. Based on this information, the server uses generative artificial intelligence to generate an appropriate lesson plan. Specifically, the server generates a lesson plan using the following prompt sentence:

[1330] "User says they want to learn math. Create a lesson plan based on logical teacher types."

[1331] The generated learning plan is sent from the server to the device as JSON format data.

[1332] Terminal handling

[1333] The terminal functions as a user interface. The user selects the academic field and teacher characteristics they wish to study through the interface provided by the terminal. Once the selection is complete, the terminal transmits the information to the server. The lesson plan returned from the server is received by the terminal and converted into a format that can be displayed to the user.

[1334] User Action

[1335] The user selects the academic field and teacher characteristics they wish to study from the interface using their terminal. The selection information is sent to the server, and the generated learning plan is sent back to the terminal. The user can then proceed with their studies based on the learning plan displayed on the terminal.

[1336] Specific examples

[1337] For example, if a user wants a logical teacher-type lesson plan for math, the system works as follows:

[1338] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[1339] 2. The terminal receives the user's selection and transmits the selection information to the server.

[1340] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates a learning plan using generative artificial intelligence (for example, OpenAI's GPT-4).

[1341] 4. The server returns the generated learning plan to the device.

[1342] 5. The device analyzes the generated lesson plan and displays it to the user.

[1343] 6. The user studies the specified content based on the study plan displayed on the device.

[1344] In this way, the present invention is a system that eliminates variations in teacher quality and teaching methods, allowing users to receive high-quality education anytime, anywhere.

[1345] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1346] Server Processing Steps

[1347] Step 1: Acquire know-how data

[1348] To improve the quality of education, the server retrieves teacher know-how data (e.g., lecture materials, lesson videos, evaluation reports, etc.) from the database. The input is a search query, and the output is the corresponding know-how data.

[1349] Specific behavior:

[1350] The server uses SQL queries to filter and retrieve the required entries from the database.

[1351] Example: SELECT FROM Knowhow WHERE Subject = "Mathematics" AND TeacherType = "Logical"

[1352] Step 2: Training the AI ​​model

[1353] The server preprocesses the acquired know-how data and trains it on a generative AI (e.g., GPT-4). The input is the preprocessed know-how data, and the output is a trained AI model.

[1354] Specific behavior:

[1355] Know-how data is converted into text format and input into generative artificial intelligence through prompt sentences.

[1356] Example: Prompt: "Below is a lecture material from an excellent math teacher. Please learn this know-how."

[1357] Step 3: Receiving a user request

[1358] The server receives requests sent from users via their terminals. The requests include the subject area the user wants to study and the characteristics of the teacher. The input is the user's request information, and the output is the content of the request.

[1359] Specific behavior:

[1360] Receives the HTTP request and parses the request parameters (discipline and teacher characteristics).

[1361] Example: GET / generateLessonPlan?subject=Mathematics&teacherType=Logic

[1362] Step 4: Generate lesson plans

[1363] The server generates a learning plan based on the user's request using generative artificial intelligence. The input is the request information and a trained AI model, and the output is the learning plan.

[1364] Specific behavior:

[1365] Send prompts to GPT-4 to generate a learning plan.

[1366] Example: Prompt: "The user says they want to learn math. Create a lesson plan based on logical teacher types."

[1367] Step 5: Submit your lesson plan

[1368] The server sends the generated learning plan to the terminal as JSON format data. The input is the generated learning plan, and the output is an HTTP response to the terminal.

[1369] Specific behavior:

[1370] Send lesson plan data in JSON format as an HTTP response.

[1371] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[1372] Terminal processing steps

[1373] Step 1: Provide an interface

[1374] The terminal provides the user with an interface that allows them to select the subject they wish to study and the characteristics of the teacher. The input is the terminal configuration information, and the output is the interface display.

[1375] Specific behavior:

[1376] Create a select menu using HTML and CSS.

[1377] For example: "Choose the subject you would like to study.", "Choose the type of teacher."

[1378] Step 2: Sending User Selections

[1379] The terminal sends the user's selected academic field and teacher characteristics to the server. The input is the user's selection information, and the output is a request to the server.

[1380] Specific behavior:

[1381] The user's selection information is sent to the server using JavaScript AJAX.

[1382] Example: ajax.send("GET", " / generateLessonPlan?subject=Mathematics&teacherType=Logical")

[1383] Step 3: Receive your lesson plans

[1384] The terminal receives the generated learning plan from the server. The input is the HTTP response from the server, and the output is the learning plan data.

[1385] Specific behavior:

[1386] Receives the HTTP response from the server and parses the JSON format data.

[1387] Example: {"lessonPlan": "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions"}

[1388] Step 4: View the lesson plan

[1389] The terminal displays the received lesson plan to the user. The input is the lesson plan data, and the output is the display on the user interface.

[1390] Specific behavior:

[1391] Use HTML and JavaScript to convert lesson plans into display formats.

[1392] For example: "Today's lesson plan: 1. Explain basic concepts, 2. Practice questions, 3. Application questions."

[1393] User processing steps

[1394] Step 1: Select subject and teacher type

[1395] The user selects the academic field they wish to study and the characteristics of the teacher through the terminal interface. The input is the user's selection, and the output is the input data to the terminal.

[1396] Specific behavior:

[1397] Select the discipline and teacher characteristics from the drop-down menus.

[1398] Examples: "mathematics", "logical"

[1399] Step 2: Start learning

[1400] The user proceeds with their studies based on the study plan displayed on the terminal. The input is the study plan displayed on the terminal, and the output is the user's study behavior.

[1401] Specific behavior:

[1402] Follow the displayed study plan, solve the problems and read the explanations.

[1403] For example, study based on "Today's lesson plan: 1. Explanation of basic concepts, 2. Practice questions, 3. Application questions."

[1404] The above are the specific processing steps and operations in the system of the present invention.

[1405] (Application example 1)

[1406] 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."

[1407] Conventional educational systems have difficulty providing effective lesson plans based on the user's selected subject and teacher type, and are often restricted by location and time. Furthermore, typical online educational systems lack a sense of realism and interactivity, limiting learning effectiveness. Therefore, there is a demand for a system that allows users to take high-quality, interactive lessons in an immersive virtual space.

[1408] 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.

[1409] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for displaying the generated lesson plan to the user, and means for the user to take interactive lessons in a virtual space. This allows users to take high-quality, interactive lessons in a virtual space, providing a realistic learning experience without being restricted by location or time.

[1410] "Teacher know-how" refers to the specialized knowledge and teaching methods that educators possess, as well as the teaching techniques and methodologies they have acquired through their experience in the field of education.

[1411] "Generative AI" is a type of AI that uses algorithms and models to learn from large amounts of data and provide solutions to specific problems.

[1412] "Subjects that users want to study" refers to the fields or topics that users of the educational system wish to study.

[1413] "Teacher type" refers to categories of teachers with different teaching styles and teaching methods, and can be selected by the user.

[1414] A "lesson plan" is a document or program that contains details of the teaching plan or learning content to be followed by a learner, generated based on a specific subject and type of teacher.

[1415] A "virtual space" is a three-dimensional computer-generated virtual environment in which users can have an immersive, interactive experience.

[1416] "Interface" refers to the means or devices by which a user interacts with a system, and typically includes a graphical user interface (GUI).

[1417] "User request" is information that specifically indicates the learner's demands and wishes for the learning system.

[1418] A "server" is a computer system that receives requests, processes data, and provides appropriate information and services to clients.

[1419] The present invention is an educational system that uses generative artificial intelligence to learn teacher know-how, and generates and provides lesson plans based on a user's selection of the subject and teacher type they wish to study. Furthermore, this system allows users to take interactive lessons in a virtual space. Specific embodiments of each component are described below.

[1420] Server Processing

[1421] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. This process inputs the teacher's skills and knowledge into the AI ​​model. The server also receives requests from users and generates lesson plans based on them. The generative AI used is OpenAI's GPT-3. This model is capable of learning from large amounts of educational data and generating lesson plans suited to specific subjects and teaching styles.

[1422] Examples of specific prompts are:

[1423] Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations.

[1424] The lesson plans generated by GPT-3 are then converted into a format for display in the virtual space. The server manages user requests and the generated lesson plans, and sends them to the device in the virtual space at the appropriate time.

[1425] Terminal handling

[1426] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits this information to the server and receives the generated lesson plan from the server. The received lesson plan is then converted into a format that is displayed to the user, allowing them to experience it interactively in a virtual space. For this reason, the device requires hardware with high-performance graphics and processing capabilities, such as the latest smartphones or head-mounted displays (HMDs).

[1427] User Action

[1428] The user selects the subject and teacher type they wish to study using their device. The user's learning request is then sent from the device to the server, and a generated lesson plan is sent back to the device. The user can then proceed with their learning in a virtual space based on the lesson plan. For example, if a user selects a chemistry experiment class, they can wear an HMD and learn while visualizing the actual chemistry experiment in the virtual space.

[1429] Example

[1430] Here is a concrete example of a chemistry experiment:

[1431] 1. The user selects the "Chemistry" and "Experimental" teacher types in the terminal interface.

[1432] 2. The terminal sends the user's selection information to the server.

[1433] 3. The server retrieves the teacher's know-how based on "chemistry" and "experimental" from the database and generates a lesson plan using GPT-3.

[1434] 4. The server sends the generated lesson plan to the device.

[1435] 5. The device analyzes the received lesson plan and displays it in the virtual space.

[1436] 6. Users use the HMD to take interactive lessons in a virtual space.

[1437] This system allows users to receive high-quality education in a virtual space with a sense of realism, significantly improving learning effectiveness.

[1438] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1439] Step 1:

[1440] The user uses the device interface to select the subject and teacher type they wish to study, either by using a mouse or touch screen to select the subject and teacher type from drop-down menus, and the selection is entered into the device and sent to the server.

[1441] Step 2:

[1442] The device sends the user's selection information (subject and teacher type) to the server. Specifically, data about the selected subject and teacher type is sent to the server via a dedicated API endpoint. This data is sent in the form of a request.

[1443] Step 3:

[1444] The server receives a request sent by the user. The request includes the user's selected subject and teacher type. Based on this input, the server retrieves the corresponding teacher's know-how data from the database.

[1445] Step 4:

[1446] The server passes the acquired know-how data to a generative artificial intelligence (for example, OpenAI's GPT-3), which generates a lesson plan based on the user's selection. Specifically, it generates a prompt and sends a request to the GPT-3 model. An example prompt is "Create a lesson plan for chemistry with an experimental teaching style. Focus on interactive experiments and visualizations." GPT-3 outputs the text data of the lesson plan based on this prompt.

[1447] Step 5:

[1448] The server receives the lesson plans from GPT-3, parses them, and formats them as structured data, which is then converted into a user-friendly form and ready to be sent to the device.

[1449] Step 6:

[1450] The server sends the generated lesson plan to the terminal, which sends the data in the form of a response containing a detailed lesson plan for the subject and type of teacher selected by the user.

[1451] Step 7:

[1452] The device then analyzes the received lesson plan and converts it into a format suitable for display in the virtual space, including the 3D objects and interactive elements used in the virtual space.

[1453] Step 8:

[1454] Users enter a virtual space using a head-mounted display (HMD). The converted lesson plan is displayed interactively within this virtual space. Through visual and physical movements, users can experience and learn the lesson content based on the lesson plan generated in the virtual space.

[1455] In this way, by executing each step consecutively, the user can interactively experience high-quality educational content in a virtual space.

[1456] 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.

[1457] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[1458] Server Processing

[1459] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state.

[1460] The server includes the following functions:

[1461] Importing know-how data and training the AI ​​model

[1462] Generate lesson plans based on user requests

[1463] Adjusting lesson plans using emotion engines

[1464] Submitting the generated lesson plan

[1465] Terminal handling

[1466] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[1467] The device includes the following features:

[1468] Providing a subject and teacher type selection interface

[1469] Sending user selection information to the server

[1470] Receive and view generated lesson plans

[1471] Emotion engine that analyzes facial expressions, voice, and behavior

[1472] User Action

[1473] The user selects the subject and type of teacher they wish to study on the device. Once the user completes their selection, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[1474] The specific steps for users are as follows:

[1475] 1. The user selects the subject and teacher type through the terminal interface.

[1476] 2. The user's selection information is sent from the terminal to the server.

[1477] 3. The server uses generative artificial intelligence to generate a lesson plan and sends it back to the device.

[1478] 4. The user proceeds with their studies based on the lesson plan displayed on the device.

[1479] 5. The device analyzes the user's facial expressions, voice, and behavior to recognize their emotional state.

[1480] 6. The server uses the emotion engine to adjust the lesson plan and provide it to the user.

[1481] Specific examples

[1482] Here's an example of taking a math lesson plan from a logical teacher and adjusting it using the emotion engine:

[1483] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[1484] 2. The terminal receives the user's selection and transmits the selection information to the server.

[1485] 3. The server retrieves the teacher's know-how based on "mathematics" and "logic" from a database and generates lesson plans using generative artificial intelligence.

[1486] 4. The server sends the generated lesson plan back to the device.

[1487] 5. The device parses the generated lesson plan and displays it to the user.

[1488] 6. The user studies the specified content based on the lesson plan displayed on the device.

[1489] 7. The device analyzes the user's facial expressions and voice and recognizes that the user is confused.

[1490] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[1491] 9. The user continues learning based on the adjusted lesson plan.

[1492] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[1493] The processing flow will be explained below.

[1494] Step 1:

[1495] The user accesses the terminal interface and selects the "subject they want to study" and the "type of teacher." For example, if the user selects "mathematics" and "logical," this information is entered into the terminal.

[1496] Step 2:

[1497] The terminal sends the information of the subject and teacher type selected by the user to the server as a request, which includes data on the selected subject and teacher type.

[1498] Step 3:

[1499] The server receives a request from the terminal, which includes the selection information "mathematics" and "logical."

[1500] Step 4:

[1501] The server retrieves "logical" teacher know-how data from the database, which represents the teacher's skills and knowledge for providing high-quality education.

[1502] Step 5:

[1503] The server inputs the acquired know-how data into a generative AI to generate a lesson plan for "Mathematics." The generative AI utilizes the teacher's know-how to create an optimal lesson plan for the user.

[1504] Step 6:

[1505] The server then sends the generated lesson plan to the user's device, which includes specific learning steps and content.

[1506] Step 7:

[1507] The terminal receives the lesson plan sent from the server and displays it to the user in an appropriate format, customized based on the subject and teacher type selected by the user.

[1508] Step 8:

[1509] The user progresses through their studies based on the lesson plan displayed on the device. The lesson plan shows specific learning content and procedures, and the user refers to it as they progress through their studies.

[1510] Step 9:

[1511] The device analyzes the user's facial expressions, voice, and behavior to determine their emotional state. The device uses a camera and microphone to detect the user's emotional state in real time.

[1512] Step 10:

[1513] The terminal transmits the user's emotional state to the server, for example, if the user is confused, this information is conveyed to the server.

[1514] Step 11:

[1515] The server adjusts the lesson plan based on the received emotional information, using generative artificial intelligence to simplify or elaborate the content to make it easier for the user to understand.

[1516] Step 12:

[1517] The server then sends the adjusted lesson plan back to the user's terminal, and the user continues studying based on the adjusted content.

[1518] In this way, the system recognizes the user's emotional state in real time and adjusts the lesson plan accordingly, providing more effective and personalized education.

[1519] Example 2

[1520] 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."

[1521] Conventional educational systems have struggled to respond to individual users' learning needs and emotional states in a detailed manner. Furthermore, their reliance on fixed curricula and teacher methods did not necessarily maximize users' learning outcomes. Furthermore, they often failed to properly adjust teaching materials and explanations based on real-time feedback from users' emotional states. This often led to problems such as confusion and lack of understanding during learning, creating a need for a system that could maximize individual learning outcomes.

[1522] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1523] In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, means for the generative AI to generate a corresponding lesson plan based on the user's selection, means for analyzing the user's facial expressions, voice, and behavior to determine their emotional state, and means for adjusting the lesson plan based on the emotional analysis results, thereby enabling the server to respond to the user's individual learning needs and fine-tune the lesson plan based on their emotional state in real time.

[1524] "Teacher know-how" refers to the specialized knowledge, skills, and information about teaching methods that educators possess.

[1525] "Generative AI" is an AI system that has the ability to automatically generate new information and content based on given data and instructions.

[1526] "User" refers to an individual or group who utilizes the System to receive educational content.

[1527] A "subject" is a specific academic field or topic that a user chooses to study.

[1528] "Teacher type" is an attribute that indicates a teacher's teaching style or approach, and includes classifications such as "logical" and "intuitive."

[1529] A "lesson plan" is a set of lesson plans or materials designed to achieve a specific educational goal.

[1530] "Emotional state" refers to the psychological and emotional state inferred from a user's facial expressions, voice, and behavior.

[1531] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions, voice, and behavioral data to determine their emotional state.

[1532] "Adjustment" is the process of changing the content and difficulty of an existing lesson plan depending on the user's learning situation and emotional state.

[1533] An "interface" is a piece of software or hardware that provides the means by which a user interacts with a system.

[1534] The present invention is an educational system that trains a generative artificial intelligence (AI) to learn teacher know-how, allows a user to select the subject and type of teacher they wish to study, and generates and provides a lesson plan based on that selection. Furthermore, the present invention also incorporates an emotion engine that recognizes the user's emotions, and has the function of adjusting the lesson plan based on the user's emotions. An embodiment of this system is described in detail below.

[1535] Server Processing

[1536] To provide high-quality education, the server first retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. An example of an AI model used is "GPT-4." The server also receives requests from users and generates lesson plans based on the requests. An example of a prompt is "Create a lesson plan for: Math with logical style." The server then uses an emotion engine that recognizes the user's emotions to adjust the lesson plan based on the user's emotional state. The emotion engine can be something like "Microsoft Azure Emotion API."

[1537] Terminal handling

[1538] The device acts as a user interface, providing a means for the user to select the subject and type of teacher they wish to study. Once the user has completed their selection, the device transmits that information to the server and receives a generated lesson plan from the server. The received lesson plan is converted into a format that is displayable to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state.

[1539] User Action

[1540] The user selects the subject and type of teacher they wish to study on their device. Once the selection is complete, the device sends the information to the server, and a generated lesson plan is sent back to the device. The user uses the lesson plan displayed on the device to progress with their studies. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plan accordingly.

[1541] Specific examples

[1542] We will take a logical teacher-type lesson plan for mathematics and provide a concrete example of how it can be adjusted using an emotion engine.

[1543] 1. The user selects "Mathematics" and "Logic" in the terminal interface.

[1544] 2. The terminal receives the user's selection and transmits the selection information to the server.

[1545] 3. The server retrieves the teacher's know-how based on "mathematics" and "logical" from the database and generates a lesson plan using generative artificial intelligence. For example, it uses the prompt "Create a lesson plan for: Math with logical style."

[1546] 4. The server sends the generated lesson plan back to the device.

[1547] 5. The device parses the generated lesson plan and displays it to the user.

[1548] 6. The user studies the specified content based on the lesson plan displayed on the device.

[1549] 7. The device analyzes the user's facial expressions and voice to recognize when the user is confused. For example, it uses the Microsoft Azure Emotion API as its emotion engine.

[1550] 8. The server adjusts the lesson plan through the emotion engine and simplifies the content for easy understanding by the user.

[1551] 9. The user continues learning based on the adjusted lesson plan.

[1552] Thus, the present invention is a system that recognizes a user's emotional state in real time and adjusts lesson plans accordingly, providing more effective and personalized education.

[1553] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1554] Program processing flow

[1555] Step 1: Import know-how data

[1556] The server retrieves the know-how of excellent teachers from a database. The input is a list of teacher IDs, and the output is a dataset of each teacher's teaching know-how. Specifically, it uses SQL queries to search and retrieve this data.

[1557] Specific operation:

[1558] Send a query to your SQL database: SELECT FROM teacher_knowhow WHERE teacher_id IN (1, 2, 3, ...)

[1559] Prepare to pass the educational know-how obtained from the database to the AI ​​model.

[1560] Step 2: Training the AI ​​model

[1561] The server trains the imported know-how data into a generative AI. The input is the know-how data, and the output is a trained AI model.

[1562] Specific operation:

[1563] Feed the data into the AI ​​model: ai_model.train(teacher_knowhow_data)

[1564] Verify that the learning is complete.

[1565] Step 3: Receiving a user request

[1566] The terminal receives the subject and teacher type selection information from the user and sends it to the server. The input is the user's selection information, and the output is the request data to the server.

[1567] Specific operation:

[1568] Display interface to receive user selection: "Display screen for user selection"

[1569] Send information to the server: "sendToServer(userSelection)"

[1570] Step 4: Generate lesson plans

[1571] The server generates a lesson plan by inputting prompts to the generative AI based on the user's selection information. The input is the selection information and the prompt sentence, and the output is the generated lesson plan.

[1572] Specific operation:

[1573] Create a prompt based on the user's selection: "Create a lesson plan for: Math with logical style."

[1574] Enter a prompt into the AI ​​model: "lesson_plan = ai_model.generate(prompt)"

[1575] Step 5: Emotion Engine Analysis

[1576] The device analyzes the user's facial expressions, voice, and behavior in real time to determine their emotional state. The input is the user's video feed and audio data, and the output is emotional data.

[1577] Specific operation:

[1578] Capture user facial expressions and voice in real time: "Get user video feed"

[1579] Analyze with emotion engine: "emotionData = analyzeEmotion(userVideoFeed)"

[1580] Step 6: Adjust your lesson plan

[1581] The server adjusts the lesson plan based on the emotion data received from the device. The input is the generated lesson plan and emotion data, and the output is the adjusted lesson plan.

[1582] Specific operation:

[1583] Receive emotional data: "Send data about your emotional state to the server"

[1584] Generate a new prompt if needed: "Adjust the lesson plan to simplify: {lesson_plan}"

[1585] Generate an adjusted lesson plan using the AI ​​model: "adjusted_lesson_plan = ai_model.generate(prompt)"

[1586] Step 7: Submit your lesson plan

[1587] The server sends the generated lesson plan to the terminal. The input is the adjusted lesson plan, and the output is the data sent to the terminal.

[1588] Specific operation:

[1589] Send the adjusted lesson plan to the device: "sendToClient(adjusted_lesson_plan)"

[1590] Step 8: View the lesson plan

[1591] The terminal displays the received lesson plan to the user. The input is the adjusted lesson plan and the output is the educational content displayed to the user.

[1592] Specific operation:

[1593] Receive lesson plan: "Receive adjusted_lesson_plan"

[1594] Show to user: "displayLessonPlan(adjusted_lesson_plan)"

[1595] Step 9: Feedback of the user's emotional state

[1596] The terminal continues to analyze the user's facial expressions, voice, and behavior, and sends emotional state feedback to the server. The input is updated emotional data, and the output is feedback data to the server.

[1597] Specific operation:

[1598] Continuous emotion analysis: "Continuously acquire emotionData"

[1599] Feedback of emotional state to the server: "sendToServer(updatedEmotionData)"

[1600] Step 10: View your adjusted lesson plan

[1601] The device updates and redisplays the lesson plan for the user based on the sentiment analysis results from the server. The input is the newly adjusted lesson plan, and the output is the updated educational content.

[1602] Specific operation:

[1603] Receive a new lesson plan: "Receive newLessonPlan"

[1604] Show it to the user again: "displayLessonPlan(newLessonPlan)"

[1605] (Application example 2)

[1606] 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."

[1607] Conventional educational and product recommendation systems do not adequately consider the individual needs and emotional state of users. This makes it difficult to provide optimal lesson plans and product recommendations for users, resulting in problems such as insufficient improvement of learning outcomes and insatiable purchase motivation. In particular, there is a lack of adaptive content provision according to emotional states, making it difficult to improve user satisfaction.

[1608] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for training a generative AI to learn teacher know-how, means for a user to select a subject and type of teacher they wish to study, and means for the generative AI to generate a corresponding lesson plan based on the user's selection. This makes it possible to provide a personalized lesson plan based on the user's desired subject and type of teacher. The server also includes means for displaying the generated lesson plan to the user, means for incorporating an emotion engine that recognizes the user's emotional state, means for adjusting the lesson plan based on the emotion engine, means for inputting product categories and characteristics of interest, and means for recommending optimal products based on the input information and emotional state. This makes it possible to recommend optimal products and adjust lesson plans based on the user's emotional state and individual preferences, which is expected to improve user satisfaction.

[1609] "Teacher know-how" is a general term for the specialized knowledge, teaching skills, and educational methods that teachers have acquired through experience.

[1610] "Generative artificial intelligence" is a general term for artificial intelligence models that can generate new information and patterns based on massive amounts of data.

[1611] A "subject that a user wants to study" is a particular educational field or theme that a user selects for their own learning or knowledge improvement.

[1612] "Teacher type" refers to a teacher's characteristics such as teaching style, area of ​​expertise, and teaching method.

[1613] A "lesson plan" is a lesson plan that specifically lays out the learning content and teaching methods based on set educational objectives.

[1614] "Emotion engine" is a general term for technology that analyzes a user's facial expressions, voice, and behavior to recognize their emotional state in real time.

[1615] A "product category" refers to a group of products classified based on their type or attributes.

[1616] "Recommendation tools" is a general term for methods and techniques used to suggest optimal products and services based on a user's needs and emotional state.

[1617] "User's emotional state" is information that indicates the type and intensity of the emotion that the user is feeling at a particular moment.

[1618] The present invention provides an education and product recommendation system that uses generative artificial intelligence (AI) that learns teacher know-how, generates lesson plans tailored to users, and uses an emotion recognition engine. The following describes in detail an embodiment of the present invention.

[1619] Server Processing

[1620] To provide high-quality education, the server retrieves the know-how of multiple excellent teachers from a database and trains the generative AI. Through this process, the teacher's skills and knowledge are input into the AI ​​model. The server also receives requests from users and generates lesson plans based on the requests. Furthermore, the server uses an emotion engine that recognizes the user's emotions to adjust the lesson plans based on the user's emotional state. Furthermore, this system also has the function of receiving product category and characteristic information of interest and recommending the most suitable products based on that information. For this purpose, the server includes the following functions:

[1621] Importing know-how data and training the AI ​​model

[1622] Generate lesson plans based on user requests

[1623] Adjusting lesson plans using emotion engines

[1624] Sending generated lesson plans and product recommendations

[1625] Terminal handling

[1626] The device acts as the user's interface, providing a means for the user to select the subject and type of teacher they wish to study, and to input product categories and characteristics of interest. Once the user has completed their selection, the device transmits the information to the server, which then receives the generated lesson plans and product recommendations. The received information is converted into a format that is displayed to the user and provided to the user. Additionally, the device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and behavior to determine their emotional state. To this end, the device includes the following functions:

[1627] Providing a subject and teacher type selection interface

[1628] Sending user selection information to the server

[1629] Receive and display generated lesson plans and product recommendations

[1630] Emotion engine that analyzes facial expressions, voice, and behavior

[1631] User Action

[1632] The user selects the subject they wish to study, the type of teacher, the product category, and the characteristics of their interest on the device. Once the user completes their selection, the device sends that information to the server, which then generates lesson plans and product recommendations, which are then sent back to the device. The user can use the information displayed on the device to further their studies or consider purchasing. Furthermore, the device recognizes the user's emotional state and adjusts the lesson plans and product recommendations accordingly.

[1633] Software and Hardware

[1634] The hardware used is a smartphone (iOS or Android), smart glasses, or a head-mounted display (e.g., Google Glass). The software uses:

[1635] Emotion analysis: OpenCV, TensorFlow

[1636] AI models: Machine learning frameworks such as TensorFlow

[1637] Communication: requests library (Python)

[1638] Specific examples

[1639] For example, if a user wants to buy a fashion item, she can select "dress" and "elegant" through the app interface and smile at the camera. If the emotion engine recognizes her emotion as "joy," the AI ​​model will suggest the most suitable dress based on her preferences and emotions. In this way, the present invention can tailor optimal product recommendations and lesson plans to the user's emotional state and individual preferences.

[1640] Prompt Sentence Examples

[1641] "I would like to purchase some fashion items. I love dresses and elegant styles, and I am currently experiencing joy. Please recommend the best products for me."

[1642] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1643] Step 1:

[1644] Through the terminal interface, the user selects the subject they wish to study, the type of teacher, the product category, and the characteristics they are interested in. By inputting this information, the user's individual needs are clarified. The input contents include the subject name, teacher style, product category, and characteristic information. For example, "Mathematics," "Logical," "Dress," "Elegant," etc.

[1645] Step 2:

[1646] The terminal receives the selection information from the user and sends it to the server. The terminal organizes the user's selection information, converts it into a specific format, and sends it to the server. This input data is necessary for processing within the server. Specific input data includes subject name, teaching style, product category, characteristic information, and user identification information.

[1647] Step 3:

[1648] Based on the received user information, the server uses generative AI to generate corresponding lesson plans and product recommendations. The server extracts relevant teacher know-how and product information from its database, inputs this data into an AI model, and generates appropriate lesson plans and product recommendations. As a result, a user-specific lesson plan and product list are generated and output.

[1649] Step 4:

[1650] The server transmits the generated lesson plan and product recommendation information to the terminal. The server then transmits the generated result data to the corresponding terminal based on the user identification information. The transmitted data includes the specific content of the lesson plan and a list of recommended products.

[1651] Step 5:

[1652] The terminal displays the received lesson plan and product recommendation information to the user. The terminal converts the data sent from the server into a visually easy-to-understand format and presents it to the user. This allows the user to check the generated educational content and recommended products.

[1653] Step 6:

[1654] The device analyzes facial expressions, voice, and behavior to recognize the user's emotional state. When the user provides facial expressions and voice through the device, the emotion engine analyzes these data in real time to determine the user's emotional state. This analysis is performed on the device, and the resulting emotional state information is output.

[1655] Step 7:

[1656] The server adjusts the generated lesson plans and product recommendations based on the emotional state sent from the device. Based on the emotional data obtained from the emotion engine, the server re-runs the AI ​​model to generate new lesson plans and product recommendations that correspond to the user's emotional state. This adjusted data is then sent back to the device.

[1657] Step 8:

[1658] The device then displays the adjusted lesson plan and product recommendations to the user again. Finally, the device displays educational content and product lists optimized for the user's emotional state, providing the user with an improved educational and purchasing experience.

[1659] This series of steps allows users to enjoy a personalized and optimal learning and purchasing experience.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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).

[1667] 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.

[1668] 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."

[1669] 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.

[1670] 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).

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] 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.

[1680] 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.

[1681] The following is further disclosed regarding the above embodiment.

[1682] (Claim 1)

[1683] A means to teach generative AI the know-how of teachers,

[1684] a means for the user to select the subject and type of teacher they wish to study;

[1685] means for generating a corresponding lesson plan based on the user's selection;

[1686] means for displaying the generated lesson plan to a user;

[1687] A system including:

[1688] (Claim 2)

[1689] 10. The system of claim 1, further comprising means for allowing a user to take the lesson plan at any time.

[1690] (Claim 3)

[1691] 2. The system according to claim 1, further comprising means for enabling selection of types of teachers with different know-how based on a request from a user.

[1692] "Example 1"

[1693] (Claim 1)

[1694] A means to acquire the know-how of teachers and have generative AI learn it,

[1695] a means for the user to select the subject area and teacher characteristics they wish to study;

[1696] A means for generating a corresponding learning plan by a generative artificial intelligence based on the user's selection;

[1697] means for displaying the generated lesson plan to the user;

[1698] A system including:

[1699] (Claim 2)

[1700] 10. The system of claim 1, further comprising means for allowing a user to take the lesson plan at any time.

[1701] (Claim 3)

[1702] 2. The system according to claim 1, further comprising means for enabling selection of characteristics of teachers having different know-how based on a request from a user.

[1703] "Application Example 1"

[1704] (Claim 1)

[1705] A means to teach generative AI the know-how of teachers,

[1706] a means for the user to select the subject and type of teacher they wish to study;

[1707] means for generating a corresponding lesson plan based on the user's selection;

[1708] means for displaying the generated lesson plan to a user;

[1709] A means for users to take classes interactively in a virtual space;

[1710] A system including:

[1711] (Claim 2)

[1712] 10. The system of claim 1, further comprising means for allowing a user to take the lesson plan at any time.

[1713] (Claim 3)

[1714] 2. The system according to claim 1, further comprising means for enabling selection of types of teachers with different know-how based on a request from a user.

[1715] "Example 2: Combining Emotion Engines"

[1716] (Claim 1)

[1717] A means to teach generative AI the know-how of teachers,

[1718] a means for the user to select the subject and type of teacher they wish to study;

[1719] means for generating a corresponding lesson plan based on the user's selection;

[1720] means for displaying the generated lesson plan to a user;

[1721] means for analyzing a user's facial expressions, voice, and behavior to determine their emotional state;

[1722] a means for adjusting lesson plans based on the results of the sentiment analysis;

[1723] A system including:

[1724] (Claim 2)

[1725] 10. The system of claim 1, further comprising means for allowing a user to take the lesson plan at any time.

[1726] (Claim 3)

[1727] 2. The system according to claim 1, further comprising means for enabling selection of types of teachers with different know-how based on a request from a user.

[1728] "Application example 2 when combining emotion engines"

[1729] (Claim 1)

[1730] A means to teach generative AI the know-how of teachers,

[1731] a means for the user to select the subject and type of teacher they wish to study;

[1732] means for generating a corresponding lesson plan based on the user's selection;

[1733] means for displaying the generated lesson plan to a user;

[1734] means for implementing an emotion engine that recognizes the user's emotional state;

[1735] means for adjusting a lesson plan based on said emotion engine;

[1736] A means to input product categories and characteristics of interest;

[1737] means for recommending optimal products based on the input information and emotional state;

[1738] A system including:

[1739] (Claim 2)

[1740] 10. The system of claim 1, further comprising means for allowing a user to take the lesson plan at any time.

[1741] (Claim 3)

[1742] 2. The system according to claim 1, further comprising means for enabling selection of types of teachers with different know-how based on a request from a user. [Explanation of symbols]

[1743] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to teach generative AI the know-how of teachers, a means for the user to select the subject and type of teacher they wish to study; means for generating a corresponding lesson plan based on the user's selection; means for displaying the generated lesson plan to a user; A system including:

2. 10. The system of claim 1, further comprising means for allowing a user to take said lesson plan at any time.

3. 2. The system according to claim 1, further comprising means for enabling selection of types of teachers having different know-how based on a request from a user.

Images