System

Abstract

To provide a system.SOLUTION: A system, which is an education platform that utilizes a generative AI, includes: means for providing education content that meets individual leaning needs; means in which at least one of a student and a teacher communicates with the generative AI; means for providing customized learning experience; means for collecting feedback from at least one of the student and the teacher; means for generating, based on the collected feedback, a prompt text for an instruction to generate optimal education content; means for inputting the prompt text to the generative AI to generate optimal education content; and means for distributing the generated education content.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Traditional educational platforms have difficulty providing educational content tailored to the needs of individual learners and customizing the learning experience. In addition, there is a demand for students and teachers to communicate directly with AI to provide a more effective learning experience. [Means for solving the problem]

[0005] We provide an educational platform that utilizes generative AI. This platform provides educational content tailored to the needs of individual learners and allows students and teachers to communicate directly with the AI ​​to provide a customized learning experience. Furthermore, the generative AI optimizes the learning experience based on feedback from students and teachers. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the embodiment 2 of the second embodiment in the case where an emotion engine is combined. [Figure 20] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the embodiment 3 of the form example 3 in the case where an emotion engine is combined. [Figure 22] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] As one embodiment of the present invention, an educational platform that utilizes generative AI is provided. This platform is equipped with an interface that allows students and teachers to communicate directly with the AI. Specifically, students and teachers input their learning needs and questions into the AI, and the AI ​​generates educational content based on them. For example, if a student inputs "I don't understand fraction addition," the AI ​​generates educational materials related to fraction addition and provides them to the student.

[0029] "Example 2"

[0030] In addition, generative AI optimizes the learning experience based on feedback from students and teachers. Specifically, it collects feedback from students and teachers and adjusts the AI's educational content generation algorithm based on that feedback. For example, if a student gives feedback that a certain material is easy to understand, the AI ​​will learn the style of that material and reflect it in future material generation.

[0031] "Example 3"

[0032] In addition, the educational platform of the present invention provides educational content tailored to the needs of individual learners. Specifically, it analyzes the student's learning history and level of understanding, and generates personalized educational content based on that. For example, if the AI ​​detects that a student is struggling with fraction addition, the AI ​​will generate teaching materials focused on fraction addition and provide them to the student.

[0033] The process flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Students and teachers log in to the education platform.

[0036] Step 2: Students or teachers input their learning needs or questions into the AI. For example, they could say, "I don't understand how to add fractions."

[0037] Step 3: The AI ​​generates educational content based on the input information. Specifically, it generates teaching materials on fraction addition.

[0038] Step 4: The generated learning materials are provided to students, who use them to further their learning.

[0039] "Example 2"

[0040] Step 1: Students and teachers use the educational platform to advance their learning.

[0041] Step 2: Feedback from students and teachers is sent to the AI. For example, a student may give feedback that a particular material is easy to understand.

[0042] Step 3: The AI ​​will adjust its educational content generation algorithm based on the collected feedback. Specifically, it will learn the style of the teaching materials based on the feedback from students and reflect it in future teaching material generation.

[0043] "Example 3"

[0044] Step 1: Students use the educational platform to progress with their studies.

[0045] Step 2: AI analyzes students' learning history and level of understanding.

[0046] Step 3: The AI ​​generates personalized educational content based on the analysis results. For example, if it detects that a student is struggling with fraction addition, the AI ​​will generate instructional materials focused on fraction addition.

[0047] Step 4: The generated learning materials are provided to students, who use them to further their learning.

[0048] Example 1

[0049] Next, a description will be given of Example 1 of the embodiment 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".

[0050] Conventional educational platforms were difficult to customize to meet individual learning needs, making it difficult to quickly provide the specific educational content that students and teachers wanted. In addition, there was a lack of a mechanism for optimizing the generated educational content based on user feedback, which led to problems with insufficient learning effectiveness.

[0051] 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.

[0052] In this invention, the server includes a means for performing user authentication, a means for receiving user input, a means for generating a prompt sentence, a means for sending a request to the generative AI model, a means for receiving and storing the generated content, and a means for providing the stored content to the user, thereby enabling the rapid provision of educational content that meets individual learning needs and the optimization of the learning experience based on user feedback.

[0053] "User authentication" is the process of verifying that a user has valid authority when accessing a system.

[0054] "User input" refers to information or requests that a user provides to the system, including, in particular, learning needs and questions.

[0055] A "prompt" is a textual request that instructs a generative AI model to generate specific educational content.

[0056] A "generative AI model" is an artificial intelligence algorithm or system that automatically generates educational content based on user input.

[0057] "Means for sending a request" refers to a communication means by which the server sends a prompt sentence to the generative AI model.

[0058] "Generated content" refers to educational materials or teaching materials that a generative AI model generates based on a prompt.

[0059] "Means for storing" refers to a function for storing the generated content in a database or storage.

[0060] The "means of providing" refers to the functionality for displaying and making accessible the stored content to the user.

[0061] The present invention relates to an educational platform that utilizes a generative AI model, and is a system that provides educational content that meets individual learning needs. A specific embodiment of this system will be described below.

[0062] Server Roles

[0063] The server authenticates users, receives user input, generates prompts, sends requests to the generative AI model, receives and stores the generated content, and serves the content.

[0064] 1. User Authentication

[0065] The server receives login information when a user accesses the educational platform. It refers to a database (e.g., MySQL (registered trademark)) and authenticates the user. If authentication is successful, it grants access rights to the user.

[0066] 2. Receiving User Input

[0067] The server receives learning needs and questions that the user inputs into the interface, for example, the user inputs "I don't understand adding fractions."

[0068] 3. Prompt generation

[0069] The server analyzes the received user input and generates a prompt to send to the generative AI model. Specifically, it creates a prompt such as "Please generate teaching materials on fraction addition."

[0070] 4. Sending a request to the generative AI model

[0071] The server sends the generated prompt sentence to a generative AI model (e.g., GPT-4 (registered trademark) from OpenAI (registered trademark)). The generative AI model generates educational content based on the prompt sentence.

[0072] 5. Receiving and storing generated content

[0073] The server receives the educational content returned by the generative AI model and stores the received content in a database.

[0074] 6. Content Provision

[0075] The server transmits the stored educational content to the user's terminal.

[0076] Terminal Roles

[0077] The terminal is a device that allows users to access the educational platform, input their learning needs and questions, and display the generated educational content. Specifically, this applies to PCs, tablets, smartphones, etc.

[0078] 1. Access and Login

[0079] The terminal displays an interface for the user to access the educational platform. The user enters login information, which the terminal transmits to the server.

[0080] 2. Submitting User Input

[0081] The device sends to the server learning needs and questions that users enter into the interface, for example, "I don't understand adding fractions."

[0082] 3. Display of Content

[0083] The terminal displays the educational content received from the server to the user, for example, teaching materials on adding fractions.

[0084] User Roles

[0085] Users (students and teachers) use their terminals to access the educational platform, input their learning needs and questions, and study using the provided educational content.

[0086] 1. Log in

[0087] The user enters a username and password into the terminal interface and clicks the login button.

[0088] 2. Input your learning needs

[0089] Users enter their learning needs or questions into the interface, for example, "I don't understand adding fractions."

[0090] 3. Use of Content

[0091] The user learns using educational content displayed on the device, for example by reading material and solving problems about adding fractions.

[0092] Examples

[0093] A specific example will be described in which a user (student) inputs "I don't understand addition of fractions."

[0094] 1. The terminal sends this input to the server.

[0095] 2. The server analyzes the input and sends a prompt to the generative AI model saying, "I would like you to generate teaching materials on adding fractions."

[0096] 3. The generative AI model (GPT-4) generates teaching materials on adding fractions.

[0097] 4. The server transmits the generated teaching materials to the terminal.

[0098] 5. The terminal displays the educational material to the user.

[0099] Examples of prompt statements

[0100] "Generate educational materials on fraction addition for students who don't understand fraction addition."

[0101] In this way, the server, terminal, and user each play their respective roles, and an educational platform that utilizes generative AI models functions.

[0102] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0103] Step 1:

[0104] User Authentication

[0105] The server receives login information (username and password) when a user accesses the educational platform. The server runs a SQL query against a database (e.g. MySQL) to authenticate the user. If authentication is successful, the server grants the user access.

[0106] Input: Username, Password

[0107] Output: Authentication result (success / failure)

[0108] Step 2:

[0109] Receiving User Input

[0110] The server receives the learning needs and questions that the user inputs into the interface. For example, the user might input, "I don't understand adding fractions." The server analyzes this input and takes the next step.

[0111] Input: Learning need or question (e.g., "I don't understand adding fractions")

[0112] Output: Parsed user input

[0113] Step 3:

[0114] Generate prompt statement

[0115] The server analyzes the received user input and generates a prompt to send to the generative AI model. Specifically, it creates a prompt such as "Please generate teaching materials on fraction addition."

[0116] Input: Parsed user input

[0117] Output: Prompt (e.g. "Please generate teaching materials on adding fractions")

[0118] Step 4:

[0119] Sending requests to generative AI models

[0120] The server sends the generated prompt sentence to a generative AI model (e.g., OpenAI's GPT-4). The server sends an HTTP request to the API endpoint of the generative AI model, and the generative AI model generates educational content based on the prompt sentence.

[0121] Input: Prompt statement

[0122] Output: A request to the generative AI model

[0123] Step 5:

[0124] Receiving and storing generated content

[0125] The server receives the educational content returned by the generative AI model and executes SQL queries to store the received content in a database.

[0126] Input: Response from generative AI model (educational content)

[0127] Output: Saved educational content

[0128] Step 6:

[0129] Content provision

[0130] The server transmits the stored educational content to the user's terminal as an HTTP response, and the terminal displays it to the user.

[0131] Input: Saved Educational Content

[0132] Output: Sending educational content to user devices

[0133] Step 7:

[0134] View content

[0135] The terminal displays the educational content received from the server to the user. Specifically, the educational content is visually displayed using HTML and CSS.

[0136] Input: Educational content from the server

[0137] Output: The educational content displayed to the user

[0138] Step 8:

[0139] Use of Content

[0140] The user learns using educational content displayed on the device, for example by reading material and solving problems about adding fractions.

[0141] Input: Displayed educational content

[0142] Output: User learning outcomes

[0143] (Application example 1)

[0144] Next, a description will be given of Application Example 1 of Form 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."

[0145] Conventional educational platforms lacked the customization required to meet individual learning needs, making it difficult to provide educational content in real time. In addition, there was a lack of a way for on-site staff working in brick-and-mortar stores to instantly receive the necessary educational content, which hindered the improvement of work efficiency and customer service skills.

[0146] 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.

[0147] In this invention, the server is an educational platform that utilizes generative AI and includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, and a means for receiving educational content in real time through a smart device. This makes it possible to provide educational content customized to individual learning needs, and allows staff working in the field, such as in a brick-and-mortar store, to receive the necessary educational content in real time, thereby improving work efficiency and customer service skills.

[0148] "Generative AI" is an artificial intelligence technology that automatically generates new content and data based on input information.

[0149] An "educational platform" is an online system that provides educational content and enables learners and educators to communicate with each other.

[0150] "Individual learning needs" are the educational requirements of each learner based on their specific learning goals and levels of understanding.

[0151] "Educational content" refers to teaching materials and information that students use to learn, and includes formats such as text, images, and videos.

[0152] A "means of communication" is an interface that allows learners and educators to interact with generative AI and exchange information.

[0153] A "customized learning experience" is an educational experience that is optimized based on a learner's individual needs and feedback.

[0154] A "smart device" is an electronic device that has Internet connectivity and enables users to obtain and operate information.

[0155] "Means of receiving educational content in real time" refers to a system that allows learners to instantly obtain the educational content they need.

[0156] A system for implementing this invention is an educational platform that utilizes generative AI and includes means for providing educational content tailored to individual learning needs, means for students and teachers to communicate with the generative AI, means for providing a customized learning experience, and means for receiving educational content in real time via a smart device.

[0157] The server uses a generative AI model to generate educational content based on user input. Specifically, when a user inputs a prompt such as "Please tell me the features of a new product" through a smart device (e.g., smart glasses), the server sends the prompt to the generative AI model. The generative AI model generates appropriate educational content based on the prompt and returns the result to the server.

[0158] The server then transmits the generated educational content to the smart device, enabling users to receive the content in real time, enabling store staff to instantly acquire knowledge about new products and improve their work efficiency and customer service skills.

[0159] The hardware used is smart glasses (e.g., Google® Glass®, Vuzix Blade). The software uses a generative AI model (e.g., GPT-3®) to generate educational content through the OpenAI API. The program is implemented in Python and manages communication between the server and the smart device.

[0160] As a concrete example, when a new product arrives at a brick-and-mortar store, a staff member can type into the smart glasses, "Please tell me about the features of the new product." Based on this prompt, the generative AI model generates a detailed description and selling points, which are then displayed on the staff member's glasses.

[0161] Example prompt:

[0162] Please tell us the features of your new product.

[0163] In this way, it is possible to provide customized educational content tailored to individual learning needs, allowing staff working in physical stores and other locations to receive the educational content they need in real time, improving their work efficiency and customer service skills.

[0164] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] The user inputs a prompt sentence through a smart device (e.g., smart glasses).

[0167] Input: The user types into the smart glasses, "Please tell me the features of the new product" by voice or text.

[0168] Output: The smart glasses send the entered prompt text to the server.

[0169] Step 2:

[0170] The server sends the received prompt text to the generative AI model.

[0171] Input: The prompt text sent from the smart glasses.

[0172] Output: A request to send a prompt to the generative AI model.

[0173] Specific operation: The server receives the prompt text and sends a request to the generative AI model using the OpenAI API.

[0174] Step 3:

[0175] A generative AI model generates educational content based on the prompt text.

[0176] Input: The prompt text sent by the server.

[0177] Output: The generated educational content.

[0178] How it works: A generative AI model (e.g. GPT-3) analyzes the prompt and generates appropriate educational content.

[0179] Step 4:

[0180] The server receives the generated educational content and transmits it to the smart device.

[0181] Input: Educational content returned from a generative AI model.

[0182] Output: Educational content sent to smart devices.

[0183] Specific operation: The server receives the generated educational content and converts it into a data format for transmission to the smart glasses.

[0184] Step 5:

[0185] The smart device displays the received educational content to the user.

[0186] Input: Educational content sent from the server.

[0187] Output: Educational content displayed on the smart glasses display.

[0188] Specific operation: The smart glasses analyze the received educational content and display it in the user's field of vision.

[0189] In this way, users can receive the educational content they need in real time.

[0190] Example 2

[0191] Next, a second embodiment of the second embodiment will be described. 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."

[0192] Traditional educational platforms are not sufficiently customized to address the individual learning needs of students and teachers, and they lack the means to effectively use feedback to optimize the learning experience, limiting the quality and effectiveness of educational content.

[0193] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting feedback from students and teachers, a means for analyzing the collected feedback, and a means for adjusting the algorithm of the generative AI model based on the analysis result. This makes it possible to automatically generate educational content by effectively utilizing the feedback and provide a customized learning experience that meets individual learning needs.

[0194] "Feedback" refers to information such as impressions, evaluations, and level of understanding provided by students and teachers regarding educational content.

[0195] "Analysis" refers to the process of understanding the content of collected feedback using natural language processing techniques and extracting important information.

[0196] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to automatically generate educational content.

[0197] "Algorithm adjustment" is the process of changing the parameters and behavior of the generative AI model based on the analysis results in order to generate more effective educational content.

[0198] "Educational content" refers to teaching materials and resources used by students and teachers for learning and teaching.

[0199] "Collection methods" refers to the interfaces and systems used to gather feedback from students and teachers.

[0200] "Delivery means" refers to the interface or system for delivering the generated educational content to students and teachers.

[0201] This invention is a system that provides educational content tailored to individual learning needs by collecting and analyzing feedback from students and teachers and adjusting the algorithms of the generative AI model based on the results.

[0202] Hardware and Software Used

[0203] server:

[0204] The server collects and analyzes feedback, adjusts the algorithms of the generative AI model, and generates and provides new educational content.

[0205] The server uses a database to store the feedback and generated educational content.

[0206] The server analyzes the feedback using natural language processing technologies such as Google Cloud Natural Language API or IBM Watson® Natural Language Understanding.

[0207] The server uses OpenAI's GPT-4 and Google's BERT as generative AI models.

[0208] Device:

[0209] The terminal provides an interface for students and teachers to enter feedback.

[0210] The terminal provides an interface for providing the generated educational content to students and teachers.

[0211] User:

[0212] Users (students and teachers) input feedback through the terminals and access the generated educational content.

[0213] Explanation of program processing

[0214] Collecting feedback:

[0215] The server collects feedback from students and teachers via their terminals. For example, a user may enter feedback such as "This teaching material has many diagrams and is easy to understand" using a web form or a mobile application.

[0216] Feedback Analysis:

[0217] The server analyzes the collected feedback using natural language processing technology. For example, it uses the Google Cloud Natural Language API to extract keywords such as "There are many diagrams, so it is easy to understand" from the feedback text.

[0218] Algorithm adjustments:

[0219] The server adjusts the algorithm of the generative AI model based on the analysis results. For example, it changes the parameters of the generative AI model (OpenAI's GPT-4) based on the analysis results and reflects them in future teaching material generation.

[0220] Creating new materials:

[0221] The server uses the tuned algorithm to generate new educational content. For example, the following prompt is input to the generative AI model:

[0222] "Please generate the following mathematics teaching materials. Feedback from students indicates that teaching materials with many diagrams are easier to understand. Please create teaching materials that include the following: how to calculate the area of ​​a triangle, examples and explanations, and lots of diagrams."

[0223] Materials provided by:

[0224] The server provides the generated educational content to students and teachers through terminals, which display links that allow users to access new learning materials.

[0225] Examples

[0226] For example, a user (student) gives feedback about a particular mathematics teaching material, saying, "This teaching material has many diagrams and is easy to understand." The server collects this feedback and uses NLP technology to extract the information that "it has many diagrams and is easy to understand." The server then adjusts the algorithm of the generative AI model so that it uses more diagrams when generating future mathematics teaching materials. New teaching materials are generated and provided to students via their terminals.

[0227] In this way, generative AI models can optimize the learning experience based on student and teacher feedback, providing educational content tailored to individual learning needs.

[0228] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0229] Step 1: Gather feedback

[0230] The server provides a web form and / or a mobile application for collecting feedback.

[0231] The terminal displays an interface for the user to input feedback.

[0232] Users (students and teachers) input their thoughts and evaluations on specific learning materials as feedback.

[0233] Input: Feedback entered by the user (e.g., "This material had many diagrams and was easy to understand").

[0234] Output: Collected feedback data.

[0235] Specific operation: The terminal displays a text box for the user to input feedback, and the server stores the input feedback in a database.

[0236] Step 2: Analyzing feedback

[0237] The server analyzes the collected feedback using natural language processing (NLP) technology.

[0238] The server analyzes the feedback content using the Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0239] Input: Collected feedback data.

[0240] Output: Analysis results (e.g., keyword "There are many diagrams, making it easy to understand").

[0241] What it does: The server sends the feedback text to the API, which extracts important keywords and phrases, and stores the analysis results in a database.

[0242] Step 3: Adjusting the algorithm

[0243] The server adjusts the algorithm of the generative AI model based on the analysis results.

[0244] The server learns the style and structure of learning materials that are rated as easy to understand and reflects this in future learning material generation.

[0245] Input: Analysis results.

[0246] Output: Tuned generative AI model parameters.

[0247] Specific operation: The server changes the parameters of the generative AI model (e.g., OpenAI's GPT-4) based on the analysis results and saves the adjusted model.

[0248] Step 4: Generate new materials

[0249] The server generates new educational content using the tuned algorithm.

[0250] The server stores the generated teaching materials in a database.

[0251] Input: Tuned generative AI model parameters.

[0252] Output:New educational content.

[0253] Specific operation: The server inputs the prompt sentence, "Please generate the following mathematics teaching materials. According to feedback from students, teaching materials with many diagrams are rated as easier to understand. Please create teaching materials that include the following content: how to calculate the area of ​​a triangle, example problems and explanations, and make extensive use of diagrams," into the generative AI model and saves the generated teaching materials in the database.

[0254] Step 5: Provide materials

[0255] The server provides the generated teaching materials to students and teachers via their terminals.

[0256] The terminal provides an interface through which the user can access new educational material.

[0257] Enter: new educational content.

[0258] Output: A link to the educational material that users can access.

[0259] Specific operation: The server sends the URL of the generated educational material to the terminal, and the terminal displays a link that allows the user to access the educational material.

[0260] (Application example 2)

[0261] Next, a description will be given of Application Example 2 of Form 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."

[0262] Conventional educational platforms have had difficulty effectively utilizing feedback from students and teachers to optimize the learning experience. In addition, there was a lack of systems that automatically generated and appropriately delivered educational content tailored to individual learning needs. As a result, problems arose in which students' understanding and learning efficiency declined.

[0263] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for collecting feedback from students and teachers, a means for generating a prompt sentence based on the collected feedback, a means for inputting the prompt sentence into the generative AI model and generating optimal educational content, and a means for delivering the generated educational content. This makes it possible to effectively utilize feedback from students and teachers and automatically generate and deliver optimal educational content according to individual learning needs.

[0264] "Generative AI" is a system that uses artificial intelligence technology to generate new content and data.

[0265] An "educational platform" is an online system that provides educational content and enables learners and educators to communicate with each other.

[0266] "Individual learning needs" are the educational requirements of each student based on his or her specific learning goals and levels of understanding.

[0267] "Educational content" refers to teaching materials and information that students use to learn, and includes formats such as text, video, and audio.

[0268] "Feedback" is any opinion or evaluation provided by a student or teacher that is useful in improving the learning experience or educational content.

[0269] A "prompt sentence" is an input sentence that causes a generative AI to generate a specific output.

[0270] A "generative AI model" is a model that has the specific algorithms and structure of generative AI, and generates new content based on input data.

[0271] "Delivery" refers to the act of providing the generated educational content to students.

[0272] The system for implementing this invention mainly comprises three elements: a server, a terminal, and a user. The specific roles and processes of each element are explained below.

[0273] server

[0274] The server plays a central role in the educational platform that utilizes generative AI. The server includes the following means:

[0275] 1. Means for providing educational content tailored to individual learning needs: The server analyzes students' learning history and performance data and selects educational content that best suits their individual learning needs.

[0276] 2. A means for students and teachers to communicate with the generative AI: The server provides a chatbot and interactive interface that allows students and teachers to interact directly with the generative AI.

[0277] 3. A means to provide a customized learning experience: The server uses the collected data to suggest the optimal learning path for each student.

[0278] 4. Means of collecting feedback from students and teachers: The server provides feedback forms and surveys within the application to collect feedback from students and teachers.

[0279] 5. Means for generating prompt sentences based on collected feedback: The server analyzes the collected feedback and generates prompt sentences to input into the generative AI model.

[0280] 6. A means for inputting a prompt sentence into a generative AI model and generating optimal educational content: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and generates optimal educational content.

[0281] 7. Means for distributing the generated educational content: The server distributes the generated educational content to the student's terminal.

[0282] Terminal

[0283] A device is a device used by a student or teacher, such as a smartphone, tablet, or computer. A device has the following capabilities:

[0284] 1. Display of educational content: The terminal displays the educational content delivered from the server.

[0285] 2. Entering feedback: The terminal provides an interface for students and teachers to enter feedback.

[0286] 3. Interaction with generative AI: The device provides an interface that allows interaction with the generative AI.

[0287] User

[0288] Users are students and teachers with the following roles:

[0289] 1. Use of educational content: The user studies the educational content provided through the terminal.

[0290] 2. Providing Feedback: Users provide feedback on their learning experience and educational content.

[0291] 3. Interacting with generative AI: The user interacts with the generative AI to convey questions and requests.

[0292] Examples

[0293] For example, if Student A uses a mathematics textbook and provides feedback such as "This textbook was very easy to understand," the server collects this feedback and generates the following prompt:

[0294] Use the feedback below to generate the best educational content.

[0295] Student ID: 1, Material ID: 101, Feedback: This material was very easy to understand.

[0296] The server inputs this prompt sentence into the generative AI model to generate new educational content, which is then distributed to Student A's device.

[0297] In this way, a system is realized in which servers, terminals, and users work together to generate and distribute optimal educational content based on feedback.

[0298] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0299] Step 1:

[0300] The server collects feedback from students and teachers. Specifically, it collects opinions and evaluations from users using feedback forms and questionnaires provided through their terminals. The input is the feedback data entered by the users, and the output is the feedback data stored in the server.

[0301] Step 2:

[0302] The server analyzes the collected feedback data. Specifically, it analyzes the content of the feedback using natural language processing technology and extracts important keywords and evaluation points. The input is the collected feedback data, and the output is the analyzed feedback information.

[0303] Step 3:

[0304] The server generates a prompt sentence based on the parsed feedback information. Specifically, it uses an algorithm that automatically generates a prompt sentence that reflects the content of the feedback. The input is the parsed feedback information, and the output is the generated prompt sentence.

[0305] Step 4:

[0306] The server inputs the generated prompt sentence into the generative AI model. Specifically, the server sends the prompt sentence to the generative AI model (e.g., OpenAI's GPT-3) and has it generate optimal educational content. The input is the generated prompt sentence, and the output is the educational content returned from the generative AI model.

[0307] Step 5:

[0308] The server distributes the generated educational content to the student's device. Specifically, it converts the generated educational content into an appropriate format and sends it to the student's device. The input is the educational content returned from the generative AI model, and the output is the educational content displayed on the student's device.

[0309] Step 6:

[0310] The terminal displays the distributed educational content. Specifically, the educational content received from the server is displayed on the screen so that the student can study. The input is the educational content distributed from the server, and the output is the educational content displayed on the terminal screen.

[0311] Step 7:

[0312] The user studies the displayed educational content and provides feedback. Specifically, the user enters his / her opinion or evaluation of the studied content into a feedback form and transmits it to the server. The input is the feedback entered by the user, and the output is the feedback data transmitted to the server.

[0313] In this way, a system is realized in which servers, terminals, and users work together to generate and distribute optimal educational content based on feedback.

[0314] Example 3

[0315] Next, a third embodiment of the third embodiment will be described. 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."

[0316] With conventional educational platforms, it was difficult to provide educational content tailored to the needs of individual learners. In addition, there was a lack of a mechanism to accurately grasp the learner's level of understanding and provide appropriate learning materials based on that. This resulted in a decrease in the learner's learning efficiency, and there was an issue that effective learning could not be achieved.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0318] In this invention, the server includes a means for collecting learning history data, a means for saving the collected learning history data, a means for analyzing the saved learning history data, a means for generating personalized educational content based on the analysis results, a means for providing the generated educational content, and a means for feeding back the learning results, thereby making it possible to provide educational content tailored to the needs of individual learners.

[0319] "Learning History Data" means a record of all learning activities conducted by a Student on the Learning Platform.

[0320] The "means for storing" is a function for storing the collected learning history data in a storage device such as a database.

[0321] "Means of analysis" refers to a function that analyzes saved learning history data and evaluates students' level of understanding and learning progress.

[0322] "Means for generation" is a function for creating personalized educational content based on the analysis results.

[0323] The "means of providing" refers to the function of transmitting the generated educational content to the student's terminal and displaying it.

[0324] "Means of feedback" is a function that collects the results of students' learning and sends them to a server to be used for the next learning.

[0325] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new content or information based on input data.

[0326] A "prompt" is text that is used to input specific instructions or questions to a generative AI model.

[0327] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0328] The present invention relates to an educational platform that provides educational content tailored to the needs of individual learners. A specific embodiment of this system will be described below.

[0329] 1. Program Generation

[0330] The server generates the program for the educational platform. This program analyzes students' learning history and comprehension levels and provides personalized educational content. The hardware used includes the server, database, and student devices (tablets and PCs). The software uses a generative AI model (for example, OpenAI's GPT-4).

[0331] 2. Program Processing Explanation

[0332] The server collects students' learning history data and stores it in a database. The server then uses a generative AI model to analyze the students' learning history and comprehension. This analysis includes information such as what problems the students have tackled in the past, which problems they struggled with, and how well they have understood the material.

[0333] The server generates personalized educational content based on the analysis results. For example, if it detects that a student is struggling with fraction addition, the server generates instructional materials focused on fraction addition. The instructional materials can be in the form of text, images, videos, etc.

[0334] The terminal (e.g., a tablet or PC used by a student) receives the personalized educational content sent from the server and displays it to the student. The student studies the teaching materials provided through the terminal.

[0335] 3. Examples of concrete examples and prompts

[0336] As a concrete example, consider a case where Student A is struggling with fraction addition. The server analyzes Student A's learning history and detects that Student A has a low level of understanding regarding fraction addition. The server then uses a generative AI model to generate teaching materials focused on fraction addition. The teaching materials include everything from basic concepts to applied problems of fraction addition.

[0337] Here is an example of a prompt to be input to the generative AI model:

[0338] "After analyzing Student A's learning history, we found that he is struggling with fraction addition. Please generate teaching materials that cover everything from basic concepts to applied problems related to fraction addition."

[0339] By inputting this prompt sentence into the generative AI model, personalized educational content is generated. The server sends this content to the terminal and provides it to Student A.

[0340] As described above, the present invention is capable of providing educational content optimized for each learner by combining the means for collecting, storing, and analyzing learning history data, and for generating, providing, and providing feedback on content. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0341] Step 1: Collect learning history data

[0342] The server records all learning activities that students perform on the learning platform. Specifically, it collects information in real time, such as the problems students solve, the videos they watch, and the materials they read. The input is the students' learning activities, and the output is the collected learning history data.

[0343] Step 2: Save learning history data

[0344] The server stores the collected learning history data in a database. Specifically, it creates an individual database entry for each student and stores the collected data. The input is the collected learning history data, and the output is the data stored in the database.

[0345] Step 3: Analyze learning history data

[0346] The server inputs the saved learning history data into the generative AI model and analyzes the student's level of understanding. Specifically, the server inputs a prompt statement to the generative AI model saying, "Analyze the student's learning history and identify weak areas." The input is the saved learning history data and the prompt statement, and the output is the analysis result regarding the student's level of understanding.

[0347] Step 4: Generate personalized educational content

[0348] Based on the analysis results, the server inputs a prompt sentence into the generative AI model to generate personalized educational content. Specifically, the prompt sentence is "Please generate teaching materials that include everything from basic concepts to applied problems regarding fraction addition." The input is the analysis results and the prompt sentence, and the output is the generated educational content.

[0349] Step 5: Provide educational content

[0350] The server transmits the generated educational content to the student's terminal. The terminal displays the received educational content to the student. Specifically, the educational material is displayed on a tablet or PC so that the student can study. The input is the generated educational content, and the output is the educational material displayed on the terminal.

[0351] Step 6: Feedback on learning results

[0352] The user (student) studies the teaching materials provided through the terminal and solves the practice problems. The answer is sent to the server, and the server updates the learning history data again. Specifically, the correct answer rate and answer time of the problem solved by the student are recorded and saved in a database. The input is the student's answer, and the output is the updated learning history data.

[0353] (Application example 3)

[0354] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0355] Conventional educational platforms have difficulty in providing educational content tailored to the needs of individual learners, and there has been a lack of personalized education, particularly in the area of ​​maintenance work for technicians. In addition, efficient learning has been difficult because educational content is not provided that takes into account the technician's past maintenance history or level of understanding.

[0356] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0357] In this invention, the server is an educational platform that utilizes generative AI and includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, and a means for analyzing the maintenance history and level of understanding of a technician and generating personalized maintenance educational content based thereon. This makes it possible to provide personalized educational content based on the technician's past maintenance history and level of understanding.

[0358] "Generative AI" is a system that uses artificial intelligence technology to analyze data and automatically generate new content and information.

[0359] An "educational platform" is a system that provides an online or offline educational environment for use by learners and educators.

[0360] "Individual learning needs" are the educational requirements of each learner based on their specific learning goals and levels of understanding.

[0361] "Educational content" refers to teaching materials and information that students use to learn, including text, video, and interactive materials.

[0362] "Means of communication" are the methods and tools that learners and educators use to interact with and exchange information with generative AI.

[0363] A "customized learning experience" is an educational experience that is tailored to a learner's individual needs and level of understanding.

[0364] "Technician" refers to a professional who has specific skills and techniques and performs maintenance work, etc.

[0365] "Maintenance history" is a record of past maintenance work performed by a technician.

[0366] "Understanding" refers to the degree to which a learner or technician has understood a particular piece of knowledge or skill.

[0367] "Individualized maintenance training content" refers to training materials that are specially created based on a technician's maintenance history and level of understanding.

[0368] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server provides an educational platform that utilizes generative AI and generates educational content tailored to individual learning needs. The terminal is a device that allows the user to communicate with the server and receive the generated educational content. The user is an engineer or a learner, and uses the educational content through the terminal.

[0369] Server Processing

[0370] The server operates using the following hardware and software:

[0371] Hardware: A server machine with a powerful processor, sufficient memory, and storage.

[0372] Software: Python, Pandas, Scikit-learn, Transformers (Hugging Face)

[0373] The server first loads technician maintenance history data from a CSV file, then uses Scikit-learn's KMeans clustering algorithm to analyze technician maintenance history and classify it into clusters, which allows technicians to be divided into specific groups based on their past work history and error rates.

[0374] Then, we use the Transformers library to generate personalized maintenance training content for each cluster using the GPT-3 model. Specifically, we generate appropriate prompt sentences for each cluster and input them into the GPT-3 model to generate training content.

[0375] Terminal handling

[0376] The terminal is a device through which the user communicates with the server and receives the generated educational content. The terminal may be a PC, a tablet, a smartphone, etc. The terminal displays the educational content transmitted from the server and provides an interface for the user to study the content.

[0377] User Actions

[0378] The user accesses the server through the terminal and receives personalized educational content based on his / her maintenance history and level of understanding. The user studies the provided educational content and sends feedback to the server as necessary. This feedback is taken into consideration when the server generates the next educational content.

[0379] Examples

[0380] For example, if Technician A has a high error rate in maintenance tasks in the past, that technician will be classified into a specific cluster. For this cluster, the GPT-3 model will generate educational content focusing on "specific steps to reduce error rates" and "common troubleshooting methods."

[0381] Examples of prompt statements

[0382] Create maintenance training content for technicians who belong to Cluster 2, which contains many technicians with high error rates. Focus on specific steps to reduce the error rate and common troubleshooting methods.

[0383] In this way, it is possible to provide individualized educational content based on the technician's past maintenance history and level of understanding.

[0384] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0385] Step 1:

[0386] The server reads the technician's maintenance history data from a CSV file. The input is a CSV file that records the technician's maintenance history, and the output is the maintenance history data in data frame format. Specifically, the server reads the CSV file using the Pandas library and converts it into a data frame.

[0387] Step 2:

[0388] The server clusters technicians based on the maintenance history data it has loaded. The input is the maintenance history data in data frame format, and the output is a label indicating the cluster to which each technician belongs. Specifically, the server uses Scikit-learn's KMeans clustering algorithm to classify technicians into multiple clusters.

[0389] Step 3:

[0390] The server creates a prompt sentence for generating personalized educational content for each cluster. The input is the label of each cluster, and the output is a prompt sentence for each cluster. In concrete terms, the server generates an appropriate prompt sentence based on the characteristics of each cluster.

[0391] Step 4:

[0392] The server inputs the generated prompt sentence into the GPT-3 model to generate personalized educational content. The input is the prompt sentence, and the output is the personalized educational content. In specific operation, the server uses the Transformers library to input the prompt sentence into the GPT-3 model and obtain the generated educational content.

[0393] Step 5:

[0394] The server transmits the generated educational content to the terminal. The input is the personalized educational content, and the output is the educational content transmitted to the terminal. In a specific operation, the server transmits the educational content to the terminal via a network.

[0395] Step 6:

[0396] The terminal displays the received educational content to the user. The input is the educational content sent from the server, and the output is the educational content displayed in a format viewable by the user. In specific operations, the terminal converts the received data into an appropriate format and displays it on the user interface.

[0397] Step 7:

[0398] The user studies the displayed educational content and sends feedback to the server as necessary. The input is the user's feedback, and the output is the feedback sent to the server. In concrete terms, the user inputs feedback through the terminal and sends the feedback to the server by pressing a send button.

[0399] Step 8:

[0400] The server optimizes the next educational content based on the received feedback. The input is the user's feedback, and the output is the optimized educational content. Specifically, the server analyzes the feedback data and adjusts the next educational content using a generative AI model.

[0401] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0402] "Example 1"

[0403] In one embodiment of the present invention, the generative AI includes an emotion engine that recognizes the user's emotions. The emotion engine infers emotions from the user's facial expressions, tone of voice, text input, etc. For example, if a student shows a confused facial expression, raises the tone of their voice, or types "I don't know" in the text input, the emotion engine determines that the student is confused.

[0404] "Example 2"

[0405] After the emotion engine recognizes emotions, the generative AI can automatically generate educational content based on those emotions. For example, if a student feels confused, the AI ​​can provide simpler learning materials or detailed explanations to help students understand better.

[0406] "Example 3"

[0407] In addition, the emotion engine optimizes the learning experience based on the student's emotional changes. For example, if a student is confused at first, but shows a relieved expression after reading the provided material, the emotion engine will determine that the material was effective. This information can be used to generate future learning materials.

[0408] The process flow of each embodiment will be described below.

[0409] "Example 1"

[0410] Step 1: The generative AI collects information from the user's facial expressions, tone of voice, text input, etc.

[0411] Step 2: Send the collected information to the emotion engine.

[0412] Step 3: The emotion engine infers the user's emotion from the collected information.

[0413] "Example 2"

[0414] Step 1: After the emotion engine recognizes the emotion, it sends that information to the generative AI.

[0415] Step 2: The generative AI automatically generates educational content based on the received emotional information.

[0416] Step 3: The generated educational content is provided to the user.

[0417] "Example 3"

[0418] Step 1: The user consumes the provided educational content.

[0419] Step 2: The emotion engine again recognizes the change in the user's emotion.

[0420] Step 3: The emotion engine sends the emotion change information to the generative AI.

[0421] Step 4: The generative AI optimizes the learning experience based on the received emotional change information.

[0422] Example 1

[0423] Next, a description will be given of Example 1 of the embodiment 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".

[0424] Conventional educational platforms have difficulty responding to individual learning needs and failing to provide feedback that takes into account the user's emotions. As a result, it is difficult for students and teachers to effectively advance their learning. Furthermore, there is a need for the generated educational content to be optimized according to the user's level of understanding and emotions.

[0425] 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.

[0426] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a sentiment analysis means for recognizing the user's sentiment, a means for generating a prompt sentence based on the user's input data, and a means for providing the generated educational content and the result of the sentiment analysis to the user. This makes it possible to provide optimal educational content according to the user's learning needs and provide feedback according to the user's sentiment.

[0427] "Generative AI" is an artificial intelligence technology that automatically generates content based on user input data.

[0428] An "educational platform" is an online system for students and teachers to conduct learning and educational activities.

[0429] "Learning needs" are the requirements or requirements that students or teachers have regarding specific learning objectives or learning content.

[0430] "Educational content" refers to teaching materials or information provided for the purpose of learning or education.

[0431] "Means of communication" refers to the interface or method by which a user interacts with and exchanges information with a generative AI.

[0432] A "customized learning experience" is a learning process or content that is optimized to a user's individual learning needs and progress.

[0433] "Emotion analysis means" is a technology that estimates emotions from a user's facial expressions, tone of voice, text input, etc.

[0434] A "prompt sentence" is an input sentence that instructs a generative AI to generate specific content.

[0435] "Feedback" is a response or evaluation provided to a user's action or input.

[0436] This invention relates to an educational platform that utilizes generative AI, and is a system that can provide educational content tailored to individual learning needs and provide feedback that takes into account the user's emotions.

[0437] The server uses a generative AI model (e.g., a general natural language processing model) to generate educational content based on user input data. Specifically, when a user inputs their learning needs or questions, the server analyzes the content and generates an appropriate prompt sentence. The generated prompt sentence is input into the generative AI model, which generates educational content.

[0438] In addition, the server uses emotion analysis means (e.g., a general emotion recognition API) to analyze the user's emotions. It estimates the user's emotions from their facial expressions, tone of voice, text input, etc., and determines whether the user is confused or not. This makes it possible to provide feedback according to the user's emotions.

[0439] The terminal transmits the data entered by the user to the server, and displays the educational content and the results of the sentiment analysis received from the server to the user. The user can study the displayed educational material and ask additional questions if necessary.

[0440] As a concrete example, consider the case where a student says, "I don't understand adding fractions." In this case, the server will input the following prompt to the generative AI model:

[0441] "My students say they don't understand how fractions are added. Please generate some easy-to-understand teaching materials on fraction addition."

[0442] Based on this prompt, the generative AI model generates teaching materials on fraction addition. For example, it might generate content like, "To understand fraction addition, you must first align the denominators. For example, when calculating 1 / 2 + 1 / 3, if you align the denominators to 6, it becomes 3 / 6 + 2 / 6, and the result is 5 / 6."

[0443] And if the sentiment analysis tool detects that a student is confused, the server can provide additional support messages, such as "If you need help, feel free to ask us anytime."

[0444] In this way, an educational platform that utilizes generative AI can provide optimal educational content tailored to the user's learning needs and provide feedback based on the user's emotions.

[0445] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0446] Step 1:

[0447] Users use the terminal to input their learning needs and questions.

[0448] Input: The user's learning need or question (e.g., "I don't understand adding fractions")

[0449] Output: Data entered into the terminal

[0450] Step 2:

[0451] The terminal transmits the user's input data to the server.

[0452] Input: Data entered into the terminal.

[0453] Output: Data sent to the server

[0454] Step 3:

[0455] The server analyzes the received user input data and generates a prompt sentence for the generative AI model.

[0456] Input: Data sent to the server

[0457] Data processing: Analyzes user input data and generates prompts

[0458] Output: Generated prompt (e.g. "Students say they don't understand fraction addition. Please generate easy-to-understand teaching materials on fraction addition.")

[0459] Step 4:

[0460] The server inputs prompt sentences into the generative AI model and generates educational content.

[0461] Input: Generated prompt text

[0462] Data Computation: A generative AI model generates educational content based on prompts

[0463] Output: Generated educational content (e.g., "To understand fraction addition, you must first align the denominators. For example, when calculating 1 / 2 + 1 / 3, if you align the denominators to 6, the result becomes 3 / 6 + 2 / 6, which is 5 / 6.")

[0464] Step 5:

[0465] The server uses the emotion analysis means to analyze the emotion of the user.

[0466] Input: User facial expressions, tone of voice, text input, etc.

[0467] Data calculation: Sentiment analysis method estimates user's emotions

[0468] Output: Sentiment analysis results (e.g., user is confused)

[0469] Step 6:

[0470] The server transmits the generated educational content and the results of sentiment analysis to the terminal.

[0471] Input: Generated educational content, sentiment analysis results

[0472] Output: Data sent to the terminal

[0473] Step 7:

[0474] The terminal displays the educational content and the results of the emotion analysis received from the server to the user.

[0475] Input: Data sent to the terminal

[0476] Output: Educational content and feedback displayed to the user (e.g., "To understand fraction addition, you must first align the denominators. For example, when calculating 1 / 2 + 1 / 3, if you align the denominators to 6, the result becomes 3 / 6 + 2 / 6, which is 5 / 6." and "If you have any questions, please feel free to ask us.")

[0477] Step 8:

[0478] The user studies the presented material and asks follow-up questions as needed.

[0479] Input: User's follow-up question (e.g., "Can you give me more examples of adding fractions?")

[0480] Output: Additional questions typed into the terminal

[0481] The above is the specific processing flow of the program of this system.

[0482] (Application example 1)

[0483] Next, a description will be given of Application Example 1 of Form 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."

[0484] Conventional educational platforms have the problem that it is difficult to respond to individual learning needs and cannot provide educational content that takes into account the emotions of users. In particular, when educating and training factory workers on-site, it is necessary to properly recognize the confusion and stress of workers and provide guidance accordingly.

[0485] 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. In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for recognizing the user's emotions using an emotion engine, and a means for adjusting the educational content based on the user's emotions. This makes it possible to provide appropriate educational content based on emotions in response to the individual learning needs of the user.

[0486] "Generative AI" is artificial intelligence that generates new content and information based on user input.

[0487] An "educational platform" is a system that provides educational content and enables learners and educators to communicate with each other.

[0488] "Individual learning needs" are requirements based on each learner's specific learning goals and levels of understanding.

[0489] "Educational content" refers to teaching materials and information that students use to learn.

[0490] A "means of communication" is an interface that allows users to interact with generative AI.

[0491] A "customized learning experience" is a learning process that is tailored to each individual learner's needs and progress.

[0492] An "emotion engine" is a technology that estimates emotions from a user's facial expressions, tone of voice, text input, etc.

[0493] The "means for adjusting educational content based on the user's emotions" is a function for changing the educational content provided in accordance with the user's emotions recognized by the emotion engine.

[0494] As an embodiment of the present invention, a system that provides an educational platform that utilizes generative AI is constructed. A specific embodiment of the system is described below.

[0495] System Configuration

[0496] The system consists of the following main components:

[0497] 1. Server: Hosts the generative AI model and runs the educational content generation and emotion engine.

[0498] 2. Terminal: Provides an interface for communicating with generative AI on devices used by students and teachers (smartphones, tablets, PCs, etc.).

[0499] 3. Camera and microphone: Devices for capturing the user's facial expressions and voice and inputting them into the emotion engine.

[0500] Program Processing

[0501] The server performs data processing and calculation using the following software and hardware:

[0502] Generative AI model: Uses OpenAI APIs to generate educational content based on user input.

[0503] Emotion engine: Facial expression recognition is performed using OpenCV, and speech recognition is performed using the SpeechRecognition library.

[0504] Database: Used to store users' learning history and feedback and to optimize the learning experience.

[0505] Processing flow

[0506] 1. User input: The user inputs their learning needs or questions through a terminal. For example, they input a question such as, "I don't know how to set up this machine."

[0507] 2. Emotion Recognition: The camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine recognizes the user's emotions, for example detecting confused facial expressions and tone of voice.

[0508] 3. Prompt generation: Based on the recognized emotions and user input, generate a prompt to send to the generative AI model, for example, "The worker is confused. Please provide detailed guidance for the following question: I don't know how to configure this machine."

[0509] 4. Educational content generation: The generative AI model generates appropriate educational content based on the prompts and provides it to the user.

[0510] Examples

[0511] For example, if a factory worker types "I don't know how to set up this machine" into the terminal, the emotion engine will use the camera and microphone to recognize the worker's confused facial expression and tone of voice. As a result, a prompt will be generated for the generative AI model saying "The worker is confused. Please provide detailed guidance for the following question: I don't know how to set up this machine." Based on this prompt, the generative AI model will generate detailed setup instructions and provide them to the worker.

[0512] In this way, it is possible to provide appropriate educational content based on emotions, in response to the individual learning needs of the user.

[0513] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0514] Step 1:

[0515] The user inputs their learning needs and questions through the terminal. For example, they input a question such as, "I don't know how to set up this machine." The input data is sent to the server in text format.

[0516] Step 2:

[0517] The device's camera and microphone are used to capture the user's facial expressions and voice. The captured image and voice data are then sent to the server.

[0518] Step 3:

[0519] The server analyzes the received image data using OpenCV and recognizes the user's emotions from their facial expressions. For example, it detects confused expressions. The input is image data, and the output is the estimation result of the emotion.

[0520] Step 4:

[0521] The server converts the received voice data into text using the SpeechRecognition library. For example, the voice saying "I don't know how to set up this machine" is converted into text. The input is voice data, and the output is text data.

[0522] Step 5:

[0523] The server generates a prompt to be sent to the generative AI model based on the recognized emotion and the user's text input. For example, it generates a prompt such as "The worker is confused. Please provide detailed guidance for the following question: I don't know how to configure this machine." The input is the emotion estimation result and text data, and the output is the prompt sentence.

[0524] Step 6:

[0525] The server uses a generative AI model to generate educational content based on the generated prompt, e.g., detailed setup instructions. The input is the prompt text, and the output is the educational content.

[0526] Step 7:

[0527] The server transmits the generated educational content to the terminal and provides it to the user. The user browses the generated educational content through the terminal and proceeds with learning or work. The input is the educational content, and the output is the user's learning experience.

[0528] Example 2

[0529] Next, a second embodiment of the second embodiment will be described. 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."

[0530] Conventional educational platforms have difficulty providing educational content that meets individual learning needs, and have been unable to effectively utilize feedback from students and teachers. It has also been difficult to recognize students' emotional states in real time and provide appropriate educational content based on that. This has led to issues with the inability to sufficiently improve learning outcomes.

[0531] 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.

[0532] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for collecting feedback from students and teachers, a means for analyzing the collected feedback, a means for recognizing the emotions of students, and a means for automatically generating educational content based on the recognized emotions. This makes it possible to provide educational content tailored to individual learning needs, effectively utilize feedback from students and teachers, and provide appropriate educational content according to the emotional state of students.

[0533] "Generative AI" is a system that automatically generates educational content using artificial intelligence technology.

[0534] An "educational platform" is an online system for providing educational content intended for use by students and teachers.

[0535] "Individual learning needs" refers to the specific learning requirements and goals that each student and teacher has.

[0536] "Educational content" refers to teaching materials and resources provided for learning.

[0537] "Feedback" refers to opinions and evaluations provided by students and teachers on educational content.

[0538] "Emotion recognition" is a technology that identifies a student's emotional state from their facial expressions, voice, etc.

[0539] A "customized learning experience" refers to a learning experience that is tailored to individual learning needs and emotional states.

[0540] A "server" is a computer system that is the central part of an educational platform and processes and stores data.

[0541] "Terminal" refers to a device (PC, tablet, smartphone, etc.) used by students and teachers to access the educational platform.

[0542] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0543] The present invention relates to an educational platform that utilizes generative AI, and is a system that provides educational content tailored to individual learning needs. A specific embodiment of this system will be described below.

[0544] Hardware and Software Used

[0545] Hardware: Servers, terminals (PCs, tablets, smartphones)

[0546] Software: Generative AI models, emotion engines, feedback collection systems

[0547] System Configuration

[0548] 1. Feedback Collection System

[0549] Users (students and teachers) provide feedback on educational content.

[0550] The terminal collects this feedback and sends it to the server.

[0551] 2. Feedback Analysis System

[0552] The server analyzes the collected feedback.

[0553] The generative AI model adjusts its educational content generation algorithm based on the feedback.

[0554] For example, if a student provides feedback such as "this material is easy to understand," the AI ​​will learn the style of that material and reflect it in the creation of future material.

[0555] 3. Emotion Recognition System

[0556] The device recognizes students' emotions through their facial expressions and voice.

[0557] The emotion engine analyzes this data to identify the student's emotional state.

[0558] For example, if the emotion engine detects that a student is confused, it sends that information to the generative AI model.

[0559] 4. Educational Content Generation System

[0560] The generative AI model automatically generates educational content appropriate to the student's emotional state based on information from the emotion engine.

[0561] For example, if a student is identified as confused, the AI ​​will provide easier learning materials or more detailed explanations.

[0562] The terminal displays the generated educational content to the student.

[0563] Examples

[0564] Examples of feedback collection

[0565] The user (student) gives feedback such as "This math material was very easy to understand."

[0566] The terminal sends this feedback to the server.

[0567] Feedback analysis examples

[0568] The server analyzes student feedback and extracts positive evaluations such as "easy to understand."

[0569] The generative AI model uses this positive feedback to adjust its future teaching material generation algorithms.

[0570] Examples of emotion recognition

[0571] The user (student) is faced with a difficult problem and looks confused.

[0572] The device uses a camera and microphone to transmit these facial expressions and voices to the emotion engine.

[0573] The emotion engine recognizes that the student is confused.

[0574] Examples of educational content creation

[0575] The generative AI model takes the information from the emotion engine and generates simpler learning materials to aid student understanding.

[0576] The terminal displays the generated new teaching material to the student.

[0577] Examples of prompt statements

[0578] “If a student gives feedback that a particular material is easy to understand, explain how you can learn from that style of material and incorporate it into your future material production.”

[0579] “Explain how the generative AI model can generate easier learning materials if the sentiment engine recognizes that a student is confused.”

[0580] The above is a specific embodiment for carrying out the present invention.

[0581] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0582] Step 1:

[0583] Collecting feedback

[0584] Users (students and teachers) provide feedback on educational content.

[0585] Specific action: A student types a comment on an online learning platform, such as "This material was easy to understand."

[0586] The terminal collects this feedback and sends it to the server.

[0587] Input: Feedback comments from students and teachers

[0588] Data processing: Collect feedback comments as text data

[0589] Output: Feedback data sent to the server.

[0590] Step 2:

[0591] Feedback Analysis

[0592] The server analyzes the collected feedback.

[0593] Specific Behavior: The server runs the feedback data through a text analysis algorithm to determine whether the feedback is positive or negative.

[0594] Input: Feedback data

[0595] Data processing: Classifying feedback using text analysis algorithms

[0596] Output: Categorized feedback data

[0597] The generative AI model adjusts its educational content generation algorithm based on the feedback.

[0598] Specific actions: For example, learn the style of teaching materials that receive the most positive feedback and reflect this in the creation of future teaching materials.

[0599] Input: Categorized feedback data

[0600] Data processing: Adjusting the educational content generation algorithm

[0601] Output: A tuned educational content generation algorithm.

[0602] Step 3:

[0603] Emotion recognition

[0604] The device recognizes students' emotions through their facial expressions and voice.

[0605] Specific operation: The device's camera and microphone capture the student's facial expressions and voice in real time and send them to the emotion engine.

[0606] Input: Student facial expression and voice data

[0607] Data processing: facial expression and voice data capture

[0608] Output: Data sent to the emotion engine

[0609] The emotion engine analyzes this data to identify the student's emotional state.

[0610] Specific behavior: The emotion engine analyzes the student's facial expression data and determines that the student is "confused."

[0611] Input: facial expression data and voice data

[0612] Data processing: Identifying emotional states through sentiment analysis algorithms

[0613] Output: Identified emotional state data

[0614] Step 4:

[0615] Educational content generation

[0616] The generative AI model automatically generates educational content appropriate to the student's emotional state based on information from the emotion engine.

[0617] How it works: When the emotion engine tells the model that the user is confused, the generative AI model generates new content that includes simpler teaching materials and more detailed explanations.

[0618] Input: Identified emotional state data

[0619] Data processing: Generating new content using educational content generation algorithms

[0620] Output: Generated educational content

[0621] The terminal displays the generated educational content to the student.

[0622] Specific action: The new teaching material is displayed on the device screen and the student can view it.

[0623] Input: Generated educational content

[0624] Data processing: Display of educational content

[0625] Output: Educational content presented to students

[0626] The above are the specific processing steps of the program of this system.

[0627] (Application example 2)

[0628] Next, a description will be given of Application Example 2 of Form 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."

[0629] Conventional educational platforms have the problem that it is difficult to respond to the individual learning needs of students and cannot provide educational content that takes into account the emotional state of students. In particular, it is necessary to provide appropriate educational content at the right time when students are confused or have not yet fully understood.

[0630] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0631] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for recognizing students' emotions using an emotion engine, and a means for automatically generating educational content based on the recognized emotions. This makes it possible to recognize students' emotional states in real time and provide optimal educational content based on the emotional states.

[0632] "Generative AI" is an artificial intelligence technology that automatically generates educational content based on the feedback and learning needs of students and teachers.

[0633] An "educational platform" is a system for providing educational content intended for use by students and teachers.

[0634] "Individual learning needs" refers to the specific learning requirements and goals that each student has.

[0635] "Educational content" refers to teaching materials and information provided for learning.

[0636] "Means of communication" refers to the methods and interfaces that students and teachers use to exchange information with generative AI.

[0637] A "customized learning experience" refers to a learning experience that is tailored based on a student's individual learning needs and feedback.

[0638] An "emotion engine" refers to technologies and algorithms that are used to recognize a student's emotional state.

[0639] "Means for recognizing emotions" refers to a method or apparatus for detecting a student's emotional state using an emotion engine.

[0640] "Means of automatic generation" refers to the methods and algorithms by which a generative AI automatically creates educational content based on information obtained from the emotion engine.

[0641] As an embodiment of the present invention, a system for installing an emotion recognition educational assistant application on a smartphone or a head-mounted display will be described.

[0642] The server uses generative AI to provide educational content tailored to individual learning needs. Specifically, it provides an interface for students and teachers to communicate with the generative AI and provide a customized learning experience. It also uses an emotion engine to recognize students' emotions and automatically generate educational content based on those emotions.

[0643] This system uses the following hardware and software:

[0644] Hardware: Camera on a smartphone or head-mounted display

[0645] Software: OpenCV (image processing library), Keras (deep learning library), TextGenerationAI (generative AI model)

[0646] The server acquires images from the camera and performs image processing using OpenCV. Specifically, the images are converted to grayscale and input into the emotion recognition model. The emotion recognition model is built using Keras and predicts the student's emotions. Based on the predicted emotions, appropriate educational content is generated using TextGenerationAI.

[0647] For example, if a student is in a math class and the emotion recognition model detects "confusion" from the student's facial expression, it will send the following prompt to the generative AI model:

[0648] Example prompt:

[0649] Provide a simpler explanation for solving quadratic equations.

[0650] Based on this prompt, the generative AI model can then generate a simpler explanation to provide to the student, such as "Here's a step-by-step guide on how to use the formula to solve quadratic equations."

[0651] In this way, the server can recognize the students' emotional state in real time and provide them with optimal educational content based on it, thus improving their comprehension and optimizing their learning experience.

[0652] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0653] Step 1:

[0654] The server acquires video from the device's camera. The input is real-time video from the camera, and the output is the acquired video frames. Specifically, the server transmits the video captured by the camera to the server frame by frame.

[0655] Step 2:

[0656] The server converts the acquired video frames to grayscale using OpenCV. The input is a color video frame, and the output is a grayscale video frame. Specifically, the server converts a color image to a grayscale image using OpenCV functions.

[0657] Step 3:

[0658] The server inputs the grayscale converted video frames into an emotion recognition model using Keras. The input is a grayscale video frame, and the output is the emotion recognition result. In concrete terms, the grayscale image is input into the emotion recognition model, and the emotion prediction result is obtained.

[0659] Step 4:

[0660] The server generates an appropriate prompt sentence based on the emotion recognition result. The input is the emotion recognition result, and the output is the prompt sentence. As a specific operation, if the emotion is "confusion", the server generates the prompt sentence "Provide a simpler explanation for solving quadratic equations."

[0661] Step 5:

[0662] The server sends the generated prompt sentence to TextGenerationAI to generate educational content. The input is the prompt sentence, and the output is the generated educational content. Specifically, the server calls the TextGenerationAI API and generates educational content based on the prompt sentence.

[0663] Step 6:

[0664] The server transmits the generated educational content to the terminal and provides it to the user. The input is the generated educational content, and the output is the educational content displayed to the user. In concrete terms, the server transmits the generated educational content to the terminal and displays it on the user's screen.

[0665] Example 3

[0666] Next, a third embodiment of the third embodiment will be described. 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."

[0667] With conventional educational platforms, it was difficult to provide educational content tailored to the needs of individual learners, resulting in insufficient learning outcomes. It was also difficult to grasp students' emotions and levels of understanding in real time and optimize the learning experience based on that. This led to issues such as a decline in students' motivation to learn and poor learning outcomes.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0669] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for collecting learning history data of students, a means for analyzing the learning history data, a means for generating personalized educational content, a means for providing educational content, a means for monitoring the emotions of students, and a means for analyzing and feeding back the emotion data. This makes it possible to provide educational content tailored to the needs of individual learners, maximizing the learning effect. In addition, since the emotions and comprehension of students can be grasped in real time and the learning experience can be optimized based on the emotions and comprehension, it is possible to improve the motivation of students to learn and improve the learning results.

[0670] "Generative AI" is a system that generates data using artificial intelligence technology.

[0671] An "educational platform" is a system that provides educational content and enables learners and educators to communicate with each other.

[0672] "Individual learning needs" refers to the specific learning requirements and goals that each learner has.

[0673] "Educational content" refers to teaching materials and information that students use to learn.

[0674] "Means of communication" refers to the methods and tools that learners and educators use to exchange information with generative AI.

[0675] A "customized learning experience" refers to a learning process that is tailored to a learner's individual needs and progress.

[0676] "Learning history data" refers to information regarding a learner's past learning activities and achievements.

[0677] "Analytical means" refers to the methods and tools used to analyze collected data and extract meaningful information.

[0678] "Personalized educational content" refers to instructional materials created based on a learner's specific needs and level of understanding.

[0679] "Means of delivery" refers to the methods and tools used to deliver the generated educational content to learners.

[0680] "Emotion monitoring measures" refer to methods and tools for observing and recording learners' emotional states in real time.

[0681] "Emotional Data" refers to information regarding a learner's emotional state.

[0682] "Feedback measures" refer to methods and tools for improving a system or learning process based on collected data.

[0683] The present invention relates to an educational platform that utilizes generative AI, and is a system that provides educational content tailored to individual learning needs. A specific embodiment of this system will be described below.

[0684] The server first collects the students' learning history data, including past test results, study time, browsing history of teaching materials, etc. The server obtains this information from a database (e.g., MySQL or PostgreSQL).

[0685] The server then analyzes the collected learning history data using an AI model (e.g., TENSORFLOW® or PyTorch). This analysis identifies areas in which the student is struggling. For example, it may be discovered that the student is struggling with adding fractions.

[0686] The server generates personalized educational content based on the analysis results. Using a generative AI model (e.g., OpenAI's GPT-4), it creates teaching materials by inputting prompt sentences such as the following:

[0687] Example prompt:

[0688] "Student A is having difficulty with adding fractions. Please generate teaching materials that cover the basics of adding fractions, as well as advanced applications."

[0689] The generated teaching materials are sent from the server to the student's device (e.g., tablet or PC). The device displays the received teaching materials to the student.

[0690] In addition, the device uses a built-in camera and microphone to monitor the student's facial expressions and tone of voice in real time. An emotion engine (e.g., Microsoft® Azure® Emotion API) is used to analyze the student's emotional state. If the student shows a relieved expression after reading the material, the emotion engine determines that the material was effective.

[0691] The server analyzes the emotion data sent from the emotion engine. This information is fed back to future teaching material generation. For example, if a student shows a relieved expression, the server determines that the teaching material was effective and reflects this information in the next teaching material generation.

[0692] As a concrete example, consider a case where a user (Student A) is struggling with adding fractions. The server retrieves Student A's past test results and study time from the database and analyzes them using an AI model. Based on the analysis results, the server inputs the following prompt sentence into the generative AI model:

[0693] Example prompt:

[0694] "Student A is having difficulty with adding fractions. Please generate teaching materials that cover the basics of adding fractions, as well as advanced applications."

[0695] The generated teaching materials are sent from the server to Student A's device. The device displays the teaching materials to Student A and monitors Student A's facial expressions with a built-in camera. If the emotion engine analyzes Student A's facial expressions and detects a relieved expression, the server determines that the teaching materials were effective and reflects this information in the next generation of teaching materials.

[0696] The above is a specific embodiment of this educational platform. The flow of the specific process in the third embodiment will be described with reference to FIG.

[0697] Step 1:

[0698] The server collects students' learning history data. As input, it retrieves information such as past test results, study time, and browsing history of teaching materials from a database (e.g., MySQL or PostgreSQL). As output, it centralizes these data and creates a dataset for analysis.

[0699] Step 2:

[0700] The server analyzes the collected learning history data using an AI model (e.g., TensorFlow or PyTorch). The dataset created in step 1 is used as input. Data processing involves preprocessing the data (filling in missing values, normalization, etc.) and inputting it into the AI ​​model. The output is an analysis result that identifies which areas the student is struggling with.

[0701] Step 3:

[0702] The server generates personalized educational content based on the analysis results. As input, it uses the analysis results obtained in step 2. It inputs the following prompt sentence into a generative AI model (e.g., OpenAI's GPT-4) to create teaching materials. As output, it generates personalized educational content.

[0703] Example prompt:

[0704] "Student A is having difficulty with adding fractions. Please generate teaching materials that cover the basics of adding fractions, as well as advanced applications."

[0705] Step 4:

[0706] The server sends the generated educational content to the terminal. As input, it uses the educational content generated in step 3. As output, it obtains the educational content sent to the terminal. The terminal displays the received educational material to the student.

[0707] Step 5:

[0708] The device monitors the student's facial expressions and tone of voice in real time using the built-in camera and microphone. As input, it obtains the student's facial expression and voice data. It analyzes these data using an emotion engine (e.g., Microsoft Azure's Emotion API). As output, it obtains the student's emotional state.

[0709] Step 6:

[0710] The server analyzes the emotion data sent from the emotion engine. As input, it uses the emotion data obtained in step 5. As data processing, it analyzes the emotion data and evaluates the effectiveness of the teaching materials. As output, it obtains an evaluation result regarding the effectiveness of the teaching materials. This information is fed back to the generation of future teaching materials.

[0711] Specifically, for example, if Student A is struggling with adding fractions, the server retrieves Student A's past test results and study time from the database and analyzes them using the AI ​​model. Based on the analysis results, the server inputs prompt sentences into the generative AI model and generates personalized learning materials. The generated learning materials are sent from the server to Student A's device, and the device displays the learning materials to Student A. The device monitors Student A's facial expressions with a built-in camera, and the emotion engine analyzes the expressions. If the server detects a relieved expression, it determines that the learning materials were effective and reflects this information in the next learning material generation.

[0712] (Application example 3)

[0713] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0714] With conventional education platforms, it was difficult to provide educational content tailored to the needs of individual learners, and it was not possible to optimize the learning experience by grasping the learner's emotions and level of understanding in real time. Furthermore, in factories and other workplaces, there was a problem that personalized education based on the worker's skill level and work history was not provided, and efficient education was not possible.

[0715] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0716] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for analyzing the work history and skill level of a worker to generate personalized educational content, and a means for analyzing the facial expressions and movements of a worker to optimize the learning experience. This makes it possible to provide optimized educational content in real time to individual learners and workers.

[0717] "Generative AI" is a system that uses artificial intelligence technology to analyze data and automatically generate new information and content.

[0718] An "educational platform" is an online or offline system that provides educational content and learning tools for use by learners and educators.

[0719] "Individual learning needs" refers to the educational requirements of each learner based on their specific learning goals, levels of understanding and interests.

[0720] "Educational content" is a general term for teaching materials, information, assignments, etc. that students use to study.

[0721] A "means of communication" is the interface or method by which a user interacts with a system and exchanges information.

[0722] A "customized learning experience" is a learning process or materials that are tailored to a learner's individual needs and progress.

[0723] "Work history" refers to records and data of work that a worker has performed in the past.

[0724] "Skill level" is an index showing the degree of proficiency of a worker's techniques and knowledge.

[0725] "Means of analyzing facial expressions and movements" refers to technologies and algorithms that use cameras and sensors to detect and analyze a worker's facial expressions and movements.

[0726] "Means for optimizing the learning experience" are methods and techniques for adjusting the educational content and learning process provided based on the learner's or worker's level of understanding and emotions.

[0727] The present invention provides an educational platform that utilizes generative AI, and is a system that provides educational content tailored to individual learning needs. Specific embodiments for implementing the present invention will be described below.

[0728] System Configuration

[0729] This system consists of three main components: a server, a terminal, and a user.

[0730] server

[0731] The server has the following functions:

[0732] 1. Means of providing educational content tailored to individual learning needs: The server stores the learner's learning history and skill level in a database and generates personalized educational content based on that.

[0733] 2. Means of communication with the generative AI: The server uses the generative AI model to analyze input and feedback from users and provide appropriate educational content.

[0734] 3. A means to provide a customized learning experience: The server adjusts the learning process in real time based on the learner's progress and understanding.

[0735] 4. Means for analyzing workers' work history and skill level: The server stores the work history and skill level of factory workers in a database and generates personalized educational content based on that.

[0736] 5. Means for analyzing the worker's facial expressions and movements: The server uses cameras and sensors to capture the worker's facial expressions and movements and analyzes them using an emotion engine.

[0737] 6. Means for optimizing learning experience: The server optimizes the learning experience of the learner or worker based on the analysis results of the emotion engine.

[0738] Terminal

[0739] The terminal is a device through which the user receives the educational content. Specifically, the terminal includes a smartphone, a tablet, a personal computer, etc. The terminal displays the educational content transmitted from the server and transmits the user's input and feedback to the server.

[0740] User

[0741] The users are students or factory workers who receive educational content through their terminals and proceed with their learning. The users operate their terminals to send feedback to the server and optimize their learning experience.

[0742] Hardware and Software Used

[0743] Hardware: Cameras (to capture the worker's facial expressions), sensors (to capture their movements)

[0744] Software: OpenCV (for image processing), TensorFlow (for emotion engine models)

[0745] Data processing and calculation

[0746] The server performs the following data processing and calculations.

[0747] 1. Database management of learning history and skill level: The learning history and skill level of learners and workers are stored in a database, and the data is retrieved as needed.

[0748] 2. Facial Expression Analysis: Preprocess facial expression images captured by the camera and analyze them with the emotion engine. Specifically, we convert the images to grayscale using OpenCV and predict emotions using the TensorFlow model.

[0749] 3. Educational content generation: Generate personalized educational content using generative AI models based on learning history and skill level.

[0750] 4. Optimizing the learning experience: Adjust the educational content and learning process in real time based on the analysis results of the emotion engine.

[0751] Examples

[0752] For example, if a factory worker is struggling with a particular task and facial expressions captured by the camera indicate confusion, the server will generate educational content focused on that task and send it to the device. The worker can then receive the educational content through the device and progress with their learning.

[0753] Examples of prompt statements

[0754] "Create a program that uses the learning history and facial expression data of factory workers to generate personalized educational content and optimize the learning experience. Specifically, analyze the facial expressions of workers and, if they are confused, provide educational content focused on the specific task."

[0755] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0756] Step 1:

[0757] The server stores the learning history and skill levels of learners and workers in a database.

[0758] Input: Learner and worker learning history data, skill level data

[0759] Data processing: Converting data into a format for saving to a database

[0760] Output: Learning history and skill level data stored in a database

[0761] Specific operation: The server receives the learning history and skill level data entered by the user and stores it in a database.

[0762] Step 2:

[0763] The server acquires the facial expression image of the worker captured by the camera.

[0764] Input: Facial expression image captured by the camera

[0765] Data processing: Convert the image to grayscale and adjust the size

[0766] Output: Preprocessed facial expression images

[0767] Specific operation: The server receives the facial expression image sent from the camera, converts it to grayscale using OpenCV, and adjusts the size.

[0768] Step 3:

[0769] The server analyzes the pre-processed facial expression images with an emotion engine.

[0770] Input: Preprocessed facial expression images

[0771] Data computation: Predicting emotions using an emotion engine (TensorFlow model)

[0772] Output: Emotion label (e.g. confusion, relief, etc.)

[0773] Specific operation: The server inputs the preprocessed facial expression images into the TensorFlow model to predict emotions.

[0774] Step 4:

[0775] The server generates personalized educational content based on learning history and skill level.

[0776] Input: Learning history data, skill level data

[0777] Data Computation: Generating educational content using generative AI models

[0778] Output: personalized educational content

[0779] Specific operation: The server retrieves learning history and skill level data from the database and generates personalized educational content using a generative AI model.

[0780] Step 5:

[0781] The server optimizes the learning experience based on the emotion engine's analysis results.

[0782] Input: emotion labels, personalized educational content

[0783] Data Computing: Tailoring Educational Content Based on Sentiment Labels

[0784] Output: Optimized educational content

[0785] Specific Behavior: The server generates and optimizes educational content focused on a specific task when the emotion label indicates “confusion.”

[0786] Step 6:

[0787] The terminal displays the optimized educational content to the user.

[0788] Input: Optimized educational content

[0789] Data processing: Converting educational content into a display format

[0790] Output: Educational content displayed on the device

[0791] Specific operation: The terminal receives the optimized educational content sent from the server and displays it to the user.

[0792] Step 7:

[0793] Users receive educational content through their terminals and progress with their studies.

[0794] Input: Educational content displayed on the device

[0795] Data Computing: Understanding Educational Content and Advancing Learning

[0796] Output: Learning progress data, feedback

[0797] Specific operation: The user looks at the educational content displayed on the terminal, progresses with their studies, and sends feedback to the server if necessary.

[0798] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0799] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0800] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0801] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0802] [Second embodiment]

[0803] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0804] 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.

[0805] 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 wide area network (WAN) and / or a local area network (LAN).

[0806] 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.

[0807] 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 the voice according to instructions from the processor 46.

[0808] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0809] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0810] Fig. 4 shows an example of 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.

[0811] 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.

[0812] 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.

[0813] In the smart glasses 214, the reception output process is performed by the processor 46. The storage 50 stores a reception output program 60. The processor 46

[0814] The processor 46 reads out a reception output program 60 from the memory 50, and executes the read reception output program 60 on the RAM 48. The processor 46 operates as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48, thereby realizing the reception output process.

[0815] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0816] "Example 1"

[0817] As one embodiment of the present invention, an educational platform that utilizes generative AI is provided. This platform is equipped with an interface that allows students and teachers to communicate directly with the AI. Specifically, students and teachers input their learning needs and questions into the AI, and the AI ​​generates educational content based on them. For example, if a student inputs "I don't understand fraction addition," the AI ​​generates educational materials related to fraction addition and provides them to the student.

[0818] "Example 2"

[0819] In addition, generative AI optimizes the learning experience based on feedback from students and teachers. Specifically, it collects feedback from students and teachers and adjusts the AI's educational content generation algorithm based on that feedback. For example, if a student gives feedback that a certain material is easy to understand, the AI ​​will learn the style of that material and reflect it in future material generation.

[0820] "Example 3"

[0821] In addition, the educational platform of the present invention provides educational content tailored to the needs of individual learners. Specifically, it analyzes the student's learning history and level of understanding, and generates personalized educational content based on that. For example, if the AI ​​detects that a student is struggling with fraction addition, the AI ​​will generate teaching materials focused on fraction addition and provide them to the student.

[0822] The process flow of each embodiment will be described below.

[0823] "Example 1"

[0824] Step 1: Students and teachers log in to the education platform.

[0825] Step 2: Students or teachers input their learning needs or questions into the AI. For example, they could say, "I don't understand how to add fractions."

[0826] Step 3: The AI ​​generates educational content based on the input information. Specifically, it generates teaching materials on fraction addition.

[0827] Step 4: The generated learning materials are provided to students, who use them to further their learning.

[0828] "Example 2"

[0829] Step 1: Students and teachers use the educational platform to advance their learning.

[0830] Step 2: Feedback from students and teachers is sent to the AI. For example, a student may give feedback that a particular material is easy to understand.

[0831] Step 3: The AI ​​will adjust its educational content generation algorithm based on the collected feedback. Specifically, it will learn the style of the teaching materials based on the feedback from students and reflect it in future teaching material generation.

[0832] "Example 3"

[0833] Step 1: Students use the educational platform to progress with their studies.

[0834] Step 2: AI analyzes students' learning history and level of understanding.

[0835] Step 3: The AI ​​generates personalized educational content based on the analysis results. For example, if it detects that a student is struggling with fraction addition, the AI ​​will generate instructional materials focused on fraction addition.

[0836] Step 4: The generated learning materials are provided to students, who use them to further their learning.

[0837] Example 1

[0838] Next, a description will be given of Example 1 of Form 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".

[0839] Conventional educational platforms were difficult to customize to meet individual learning needs, making it difficult to quickly provide the specific educational content that students and teachers wanted. In addition, there was a lack of a mechanism for optimizing the generated educational content based on user feedback, which led to problems with insufficient learning effectiveness.

[0840] 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.

[0841] In this invention, the server includes a means for performing user authentication, a means for receiving user input, a means for generating a prompt sentence, a means for sending a request to the generative AI model, a means for receiving and storing the generated content, and a means for providing the stored content to the user, thereby enabling the rapid provision of educational content that meets individual learning needs and the optimization of the learning experience based on user feedback.

[0842] "User authentication" is the process of verifying that a user has valid authority when accessing a system.

[0843] "User input" refers to information or requests that a user provides to the system, including, in particular, learning needs and questions.

[0844] A "prompt" is a textual request that instructs a generative AI model to generate specific educational content.

[0845] A "generative AI model" is an artificial intelligence algorithm or system that automatically generates educational content based on user input.

[0846] "Means for sending a request" refers to a communication means by which the server sends a prompt sentence to the generative AI model.

[0847] "Generated content" refers to educational materials or teaching materials that a generative AI model generates based on a prompt.

[0848] "Means for storing" refers to a function for storing the generated content in a database or storage.

[0849] The "means of providing" refers to the functionality for displaying and making accessible the stored content to the user.

[0850] The present invention relates to an educational platform that utilizes a generative AI model, and is a system that provides educational content that meets individual learning needs. A specific embodiment of this system will be described below.

[0851] Server Roles

[0852] The server authenticates users, receives user input, generates prompts, sends requests to the generative AI model, receives and stores the generated content, and serves the content.

[0853] 1. User Authentication

[0854] When a user accesses the educational platform, the server receives login information. It references a database (e.g., MySQL) and authenticates the user. If authentication is successful, it grants the user access rights.

[0855] 2. Receiving User Input

[0856] The server receives learning needs and questions that the user inputs into the interface, for example, the user inputs "I don't understand adding fractions."

[0857] 3. Prompt generation

[0858] The server analyzes the received user input and generates a prompt to send to the generative AI model. Specifically, it creates a prompt such as "Please generate teaching materials on fraction addition."

[0859] 4. Sending a request to the generative AI model

[0860] The server sends the generated prompt sentence to a generative AI model (e.g., OpenAI's GPT-4), which generates educational content based on the prompt sentence.

[0861] 5. Receiving and storing generated content

[0862] The server receives the educational content returned by the generative AI model and stores the received content in a database.

[0863] 6. Content Provision

[0864] The server transmits the stored educational content to the user's terminal.

[0865] Terminal Roles

[0866] The terminal is a device that allows users to access the educational platform, input their learning needs and questions, and display the generated educational content. Specifically, this applies to PCs, tablets, smartphones, etc.

[0867] 1. Access and Login

[0868] The terminal displays an interface for the user to access the educational platform. The user enters login information, which the terminal transmits to the server.

[0869] 2. Submitting User Input

[0870] The device sends to the server learning needs and questions that users enter into the interface, for example, "I don't understand adding fractions."

[0871] 3. Display of Content

[0872] The terminal displays the educational content received from the server to the user, for example, teaching materials on adding fractions.

[0873] User Roles

[0874] Users (students and teachers) use their terminals to access the educational platform, input their learning needs and questions, and study using the provided educational content.

[0875] 1. Log in

[0876] The user enters a username and password into the terminal interface and clicks the login button.

[0877] 2. Input your learning needs

[0878] Users enter their learning needs or questions into the interface, for example, "I don't understand adding fractions."

[0879] 3. Use of Content

[0880] The user learns using educational content displayed on the device, for example by reading material and solving problems about adding fractions.

[0881] Examples

[0882] A specific example will be described in which a user (student) inputs "I don't understand addition of fractions."

[0883] 1. The terminal sends this input to the server.

[0884] 2. The server analyzes the input and sends a prompt to the generative AI model saying, "I would like you to generate teaching materials on adding fractions."

[0885] 3. The generative AI model (GPT-4) generates teaching materials on adding fractions.

[0886] 4. The server transmits the generated teaching materials to the terminal.

[0887] 5. The terminal displays the educational material to the user.

[0888] Examples of prompt statements

[0889] "Generate educational materials on fraction addition for students who don't understand fraction addition."

[0890] In this way, the server, terminal, and user each play their respective roles, and an educational platform that utilizes generative AI models functions.

[0891] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0892] Step 1:

[0893] User Authentication

[0894] The server receives login information (username and password) when a user accesses the educational platform. The server runs a SQL query against a database (e.g. MySQL) to authenticate the user. If authentication is successful, the server grants the user access.

[0895] Input: Username, Password

[0896] Output: Authentication result (success / failure)

[0897] Step 2:

[0898] Receiving User Input

[0899] The server receives the learning needs and questions that the user inputs into the interface. For example, the user might input, "I don't understand adding fractions." The server analyzes this input and takes the next step.

[0900] Input: Learning need or question (e.g., "I don't understand adding fractions")

[0901] Output: Parsed user input

[0902] Step 3:

[0903] Generate prompt statement

[0904] The server analyzes the received user input and generates a prompt to send to the generative AI model. Specifically, it creates a prompt such as "Please generate teaching materials on fraction addition."

[0905] Input: Parsed user input

[0906] Output: Prompt (e.g. "Please generate teaching materials on adding fractions")

[0907] Step 4:

[0908] Sending requests to generative AI models

[0909] The server sends the generated prompt sentence to a generative AI model (e.g., OpenAI's GPT-4). The server sends an HTTP request to the API endpoint of the generative AI model, and the generative AI model generates educational content based on the prompt sentence.

[0910] Input: Prompt statement

[0911] Output: A request to the generative AI model

[0912] Step 5:

[0913] Receiving and storing generated content

[0914] The server receives the educational content returned by the generative AI model and executes SQL queries to store the received content in a database.

[0915] Input: Response from generative AI model (educational content)

[0916] Output: Saved educational content

[0917] Step 6:

[0918] Content provision

[0919] The server transmits the stored educational content to the user's terminal as an HTTP response, and the terminal displays it to the user.

[0920] Input: Saved Educational Content

[0921] Output: Sending educational content to user devices

[0922] Step 7:

[0923] View content

[0924] The terminal displays the educational content received from the server to the user. Specifically, the educational content is visually displayed using HTML and CSS.

[0925] Input: Educational content from the server

[0926] Output: The educational content displayed to the user

[0927] Step 8:

[0928] Use of Content

[0929] The user learns using educational content displayed on the device, for example by reading material and solving problems about adding fractions.

[0930] Input: Displayed educational content

[0931] Output: User learning outcomes

[0932] (Application example 1)

[0933] Next, a description will be given of Application Example 1 of Form 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".

[0934] Conventional educational platforms lacked the customization required to meet individual learning needs, making it difficult to provide educational content in real time. In addition, there was a lack of a way for on-site staff working in brick-and-mortar stores to instantly receive the necessary educational content, which hindered the improvement of work efficiency and customer service skills.

[0935] 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.

[0936] In this invention, the server is an educational platform that utilizes generative AI and includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, and a means for receiving educational content in real time through a smart device. This makes it possible to provide educational content customized to individual learning needs, and allows staff working in the field, such as in a brick-and-mortar store, to receive the necessary educational content in real time, thereby improving work efficiency and customer service skills.

[0937] "Generative AI" is an artificial intelligence technology that automatically generates new content and data based on input information.

[0938] An "educational platform" is an online system that provides educational content and enables learners and educators to communicate with each other.

[0939] "Individual learning needs" are the educational requirements of each learner based on their specific learning goals and levels of understanding.

[0940] "Educational content" refers to teaching materials and information that students use to learn, and includes formats such as text, images, and videos.

[0941] A "means of communication" is an interface that allows learners and educators to interact with generative AI and exchange information.

[0942] A "customized learning experience" is an educational experience that is optimized based on a learner's individual needs and feedback.

[0943] A "smart device" is an electronic device that has Internet connectivity and enables users to obtain and operate information.

[0944] "Means of receiving educational content in real time" refers to a system that allows learners to instantly obtain the educational content they need.

[0945] A system for implementing this invention is an educational platform that utilizes generative AI and includes means for providing educational content tailored to individual learning needs, means for students and teachers to communicate with the generative AI, means for providing a customized learning experience, and means for receiving educational content in real time via a smart device.

[0946] The server uses a generative AI model to generate educational content based on user input. Specifically, when a user inputs a prompt such as "Please tell me the features of a new product" through a smart device (e.g., smart glasses), the server sends the prompt to the generative AI model. The generative AI model generates appropriate educational content based on the prompt and returns the result to the server.

[0947] The server then transmits the generated educational content to the smart device, allowing the user to receive the content in real time, enabling store staff to instantly acquire knowledge about new products and improve their work efficiency and customer service skills.

[0948] The hardware used is smart glasses (e.g., Google Glass, Vuzix Blade). The software uses a generative AI model (e.g., GPT-3) to generate educational content through the OpenAI API. The program is implemented in Python and manages communication between the server and the smart device.

[0949] As a concrete example, when a new product arrives at a brick-and-mortar store, a staff member can type into the smart glasses, "Please tell me about the features of the new product." Based on this prompt, the generative AI model generates a detailed description and selling points, which are then displayed on the staff member's glasses.

[0950] Example prompt:

[0951] Please tell us the features of your new product.

[0952] In this way, it is possible to provide customized educational content tailored to individual learning needs, allowing staff working in physical stores and other locations to receive the educational content they need in real time, improving their work efficiency and customer service skills.

[0953] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0954] Step 1:

[0955] The user inputs a prompt sentence through a smart device (e.g., smart glasses).

[0956] Input: The user types into the smart glasses, "Please tell me the features of the new product" by voice or text.

[0957] Output: The smart glasses send the entered prompt text to the server.

[0958] Step 2:

[0959] The server sends the received prompt text to the generative AI model.

[0960] Input: The prompt text sent from the smart glasses.

[0961] Output: A request to send a prompt to the generative AI model.

[0962] Specific operation: The server receives the prompt text and sends a request to the generative AI model using the OpenAI API.

[0963] Step 3:

[0964] A generative AI model generates educational content based on the prompt text.

[0965] Input: The prompt text sent by the server.

[0966] Output: The generated educational content.

[0967] How it works: A generative AI model (e.g. GPT-3) analyzes the prompt and generates appropriate educational content.

[0968] Step 4:

[0969] The server receives the generated educational content and transmits it to the smart device.

[0970] Input: Educational content returned from a generative AI model.

[0971] Output: Educational content sent to smart devices.

[0972] Specific operation: The server receives the generated educational content and converts it into a data format for transmission to the smart glasses.

[0973] Step 5:

[0974] The smart device displays the received educational content to the user.

[0975] Input: Educational content sent from the server.

[0976] Output: Educational content displayed on the smart glasses display.

[0977] Specific operation: The smart glasses analyze the received educational content and display it in the user's field of vision.

[0978] In this way, users can receive the educational content they need in real time.

[0979] Example 2

[0980] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0981] Traditional educational platforms are not sufficiently customized to address the individual learning needs of students and teachers, and they lack the means to effectively use feedback to optimize the learning experience, limiting the quality and effectiveness of educational content.

[0982] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting feedback from students and teachers, a means for analyzing the collected feedback, and a means for adjusting the algorithm of the generative AI model based on the analysis result. This makes it possible to automatically generate educational content by effectively utilizing the feedback and provide a customized learning experience that meets individual learning needs.

[0983] "Feedback" refers to information such as impressions, evaluations, and level of understanding provided by students and teachers regarding educational content.

[0984] "Analysis" refers to the process of understanding the content of collected feedback using natural language processing techniques and extracting important information.

[0985] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to automatically generate educational content.

[0986] "Algorithm adjustment" is the process of changing the parameters and behavior of the generative AI model based on the analysis results in order to generate more effective educational content.

[0987] "Educational content" refers to teaching materials and resources used by students and teachers for learning and teaching.

[0988] "Collection methods" refers to the interfaces and systems used to gather feedback from students and teachers.

[0989] "Delivery means" refers to the interface or system for delivering the generated educational content to students and teachers.

[0990] This invention is a system that provides educational content tailored to individual learning needs by collecting and analyzing feedback from students and teachers and adjusting the algorithms of the generative AI model based on the results.

[0991] Hardware and Software Used

[0992] server:

[0993] The server collects and analyzes feedback, adjusts the algorithms of the generative AI model, and generates and provides new educational content.

[0994] The server uses a database to store the feedback and generated educational content.

[0995] The server analyzes the feedback using natural language processing technologies such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0996] The server uses OpenAI's GPT-4 and Google's BERT as generative AI models.

[0997] Device:

[0998] The terminal provides an interface for students and teachers to enter feedback.

[0999] The terminal provides an interface for providing the generated educational content to students and teachers.

[1000] User:

[1001] Users (students and teachers) input feedback through the terminals and access the generated educational content.

[1002] Explanation of program processing

[1003] Collecting feedback:

[1004] The server collects feedback from students and teachers via their terminals. For example, a user may enter feedback such as "This teaching material has many diagrams and is easy to understand" using a web form or a mobile application.

[1005] Feedback Analysis:

[1006] The server analyzes the collected feedback using natural language processing technology. For example, it uses the Google Cloud Natural Language API to extract keywords such as "There are many diagrams, so it is easy to understand" from the feedback text.

[1007] Algorithm adjustments:

[1008] The server adjusts the algorithm of the generative AI model based on the analysis results. For example, it changes the parameters of the generative AI model (OpenAI's GPT-4) based on the analysis results and reflects them in future teaching material generation.

[1009] Creating new materials:

[1010] The server uses the tuned algorithm to generate new educational content. For example, the following prompt is input to the generative AI model:

[1011] "Please generate the following mathematics teaching materials. Feedback from students indicates that teaching materials with many diagrams are easier to understand. Please create teaching materials that include the following: how to calculate the area of ​​a triangle, examples and explanations, and lots of diagrams."

[1012] Materials provided by:

[1013] The server provides the generated educational content to students and teachers through terminals, which display links that allow users to access new learning materials.

[1014] Examples

[1015] For example, a user (student) gives feedback about a particular mathematics teaching material, saying, "This teaching material has many diagrams and is easy to understand." The server collects this feedback and uses NLP technology to extract the information that "it has many diagrams and is easy to understand." The server then adjusts the algorithm of the generative AI model so that it uses more diagrams when generating future mathematics teaching materials. New teaching materials are generated and provided to students via their terminals.

[1016] In this way, generative AI models can optimize the learning experience based on student and teacher feedback, providing educational content tailored to individual learning needs.

[1017] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1018] Step 1: Gather feedback

[1019] The server provides a web form and / or a mobile application for collecting feedback.

[1020] The terminal displays an interface for the user to input feedback.

[1021] Users (students and teachers) input their thoughts and evaluations on specific learning materials as feedback.

[1022] Input: Feedback entered by the user (e.g., "This material had many diagrams and was easy to understand").

[1023] Output: Collected feedback data.

[1024] Specific operation: The terminal displays a text box for the user to input feedback, and the server stores the input feedback in a database.

[1025] Step 2: Analyzing feedback

[1026] The server analyzes the collected feedback using natural language processing (NLP) technology.

[1027] The server analyzes the feedback content using the Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1028] Input: Collected feedback data.

[1029] Output: Analysis results (e.g., keyword "There are many diagrams, making it easy to understand").

[1030] What it does: The server sends the feedback text to the API, which extracts important keywords and phrases, and stores the analysis results in a database.

[1031] Step 3: Adjusting the algorithm

[1032] The server adjusts the algorithm of the generative AI model based on the analysis results.

[1033] The server learns the style and structure of learning materials that are rated as easy to understand and reflects this in future learning material generation.

[1034] Input: Analysis results.

[1035] Output: Tuned generative AI model parameters.

[1036] Specific operation: The server changes the parameters of the generative AI model (e.g., OpenAI's GPT-4) based on the analysis results and saves the adjusted model.

[1037] Step 4: Generate new materials

[1038] The server generates new educational content using the tuned algorithm.

[1039] The server stores the generated teaching materials in a database.

[1040] Input: Tuned generative AI model parameters.

[1041] Output:New educational content.

[1042] Specific operation: The server inputs the prompt sentence, "Please generate the following mathematics teaching materials. According to feedback from students, teaching materials with many diagrams are rated as easier to understand. Please create teaching materials that include the following content: how to calculate the area of ​​a triangle, example problems and explanations, and make extensive use of diagrams," into the generative AI model and saves the generated teaching materials in the database.

[1043] Step 5: Provide materials

[1044] The server provides the generated teaching materials to students and teachers via their terminals.

[1045] The terminal provides an interface through which the user can access new educational material.

[1046] Enter: new educational content.

[1047] Output: A link to the educational material that users can access.

[1048] Specific operation: The server sends the URL of the generated educational material to the terminal, and the terminal displays a link that allows the user to access the educational material.

[1049] (Application example 2)

[1050] Next, a description will be given of Application Example 2 of Form 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".

[1051] Conventional educational platforms have had difficulty effectively utilizing feedback from students and teachers to optimize the learning experience. In addition, there was a lack of systems that automatically generated and appropriately delivered educational content tailored to individual learning needs. As a result, problems arose in which students' understanding and learning efficiency declined.

[1052] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for collecting feedback from students and teachers, a means for generating a prompt sentence based on the collected feedback, a means for inputting the prompt sentence into the generative AI model and generating optimal educational content, and a means for delivering the generated educational content. This makes it possible to effectively utilize feedback from students and teachers and automatically generate and deliver optimal educational content according to individual learning needs.

[1053] "Generative AI" is a system that uses artificial intelligence technology to generate new content and data.

[1054] An "educational platform" is an online system that provides educational content and enables learners and educators to communicate with each other.

[1055] "Individual learning needs" are the educational requirements of each student based on his or her specific learning goals and levels of understanding.

[1056] "Educational content" refers to teaching materials and information that students use to learn, and includes formats such as text, video, and audio.

[1057] "Feedback" is any opinion or evaluation provided by a student or teacher that is useful in improving the learning experience or educational content.

[1058] A "prompt sentence" is an input sentence that causes a generative AI to generate a specific output.

[1059] A "generative AI model" is a model that has the specific algorithms and structure of generative AI, and generates new content based on input data.

[1060] "Delivery" refers to the act of providing the generated educational content to students.

[1061] The system for implementing this invention mainly comprises three elements: a server, a terminal, and a user. The specific roles and processes of each element are explained below.

[1062] server

[1063] The server plays a central role in the educational platform that utilizes generative AI. The server includes the following means:

[1064] 1. Means for providing educational content tailored to individual learning needs: The server analyzes students' learning history and performance data and selects educational content that best suits their individual learning needs.

[1065] 2. A means for students and teachers to communicate with the generative AI: The server provides a chatbot and interactive interface that allows students and teachers to interact directly with the generative AI.

[1066] 3. A means to provide a customized learning experience: The server uses the collected data to suggest the optimal learning path for each student.

[1067] 4. Means of collecting feedback from students and teachers: The server provides feedback forms and surveys within the application to collect feedback from students and teachers.

[1068] 5. Means for generating prompt sentences based on collected feedback: The server analyzes the collected feedback and generates prompt sentences to input into the generative AI model.

[1069] 6. A means for inputting a prompt sentence into a generative AI model and generating optimal educational content: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and generates optimal educational content.

[1070] 7. Means for distributing the generated educational content: The server distributes the generated educational content to the student's terminal.

[1071] Terminal

[1072] A device is a device used by a student or teacher, such as a smartphone, tablet, or computer. A device has the following capabilities:

[1073] 1. Display of educational content: The terminal displays the educational content delivered from the server.

[1074] 2. Entering feedback: The terminal provides an interface for students and teachers to enter feedback.

[1075] 3. Interaction with generative AI: The device provides an interface that allows interaction with the generative AI.

[1076] User

[1077] Users are students and teachers with the following roles:

[1078] 1. Use of educational content: The user studies the educational content provided through the terminal.

[1079] 2. Providing Feedback: Users provide feedback on their learning experience and educational content.

[1080] 3. Interacting with generative AI: The user interacts with the generative AI to convey questions and requests.

[1081] Examples

[1082] For example, if Student A uses a mathematics textbook and provides feedback such as "This textbook was very easy to understand," the server collects this feedback and generates the following prompt:

[1083] Use the feedback below to generate the best educational content.

[1084] Student ID: 1, Material ID: 101, Feedback: This material was very easy to understand.

[1085] The server inputs this prompt sentence into the generative AI model to generate new educational content, which is then distributed to Student A's device.

[1086] In this way, a system is realized in which servers, terminals, and users work together to generate and distribute optimal educational content based on feedback.

[1087] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1088] Step 1:

[1089] The server collects feedback from students and teachers. Specifically, it collects opinions and evaluations from users using feedback forms and questionnaires provided through their terminals. The input is the feedback data entered by the users, and the output is the feedback data stored in the server.

[1090] Step 2:

[1091] The server analyzes the collected feedback data. Specifically, it analyzes the content of the feedback using natural language processing technology and extracts important keywords and evaluation points. The input is the collected feedback data, and the output is the analyzed feedback information.

[1092] Step 3:

[1093] The server generates a prompt sentence based on the parsed feedback information. Specifically, it uses an algorithm that automatically generates a prompt sentence that reflects the content of the feedback. The input is the parsed feedback information, and the output is the generated prompt sentence.

[1094] Step 4:

[1095] The server inputs the generated prompt sentence into the generative AI model. Specifically, the server sends the prompt sentence to the generative AI model (e.g., OpenAI's GPT-3) and has it generate optimal educational content. The input is the generated prompt sentence, and the output is the educational content returned from the generative AI model.

[1096] Step 5:

[1097] The server distributes the generated educational content to the student's device. Specifically, it converts the generated educational content into an appropriate format and sends it to the student's device. The input is the educational content returned from the generative AI model, and the output is the educational content displayed on the student's device.

[1098] Step 6:

[1099] The terminal displays the distributed educational content. Specifically, the educational content received from the server is displayed on the screen so that the student can study. The input is the educational content distributed from the server, and the output is the educational content displayed on the terminal screen.

[1100] Step 7:

[1101] The user studies the displayed educational content and provides feedback. Specifically, the user enters his / her opinion or evaluation of the studied content into a feedback form and transmits it to the server. The input is the feedback entered by the user, and the output is the feedback data transmitted to the server.

[1102] In this way, a system is realized in which servers, terminals, and users work together to generate and distribute optimal educational content based on feedback.

[1103] Example 3

[1104] Next, a third embodiment of the third embodiment will be described. 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".

[1105] With conventional educational platforms, it was difficult to provide educational content tailored to the needs of individual learners. In addition, there was a lack of a mechanism to accurately grasp the learner's level of understanding and provide appropriate learning materials based on that. This resulted in a decrease in the learner's learning efficiency, and there was an issue that effective learning could not be achieved.

[1106] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1107] In this invention, the server includes a means for collecting learning history data, a means for saving the collected learning history data, a means for analyzing the saved learning history data, a means for generating personalized educational content based on the analysis results, a means for providing the generated educational content, and a means for feeding back the learning results, thereby making it possible to provide educational content tailored to the needs of individual learners.

[1108] "Learning History Data" means a record of all learning activities conducted by a Student on the Learning Platform.

[1109] The "means for storing" is a function for storing the collected learning history data in a storage device such as a database.

[1110] "Means of analysis" refers to a function that analyzes saved learning history data and evaluates students' level of understanding and learning progress.

[1111] "Means for generation" is a function for creating personalized educational content based on the analysis results.

[1112] "Means of providing" refers to the function of transmitting the generated educational content to students' terminals and displaying it.

[1113] "Means of feedback" is a function that collects the results of students' learning and sends them to a server to be used for the next learning.

[1114] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new content or information based on input data.

[1115] A "prompt" is text that is used to input specific instructions or questions to a generative AI model.

[1116] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1117] The present invention relates to an educational platform that provides educational content tailored to the needs of individual learners. A specific embodiment of this system will be described below.

[1118] 1. Program Generation

[1119] The server generates the program for the educational platform. This program analyzes students' learning history and comprehension levels and provides personalized educational content. The hardware used includes the server, database, and student devices (tablets and PCs). The software uses a generative AI model (for example, OpenAI's GPT-4).

[1120] 2. Program Processing Explanation

[1121] The server collects students' learning history data and stores it in a database. The server then uses a generative AI model to analyze the students' learning history and comprehension. This analysis includes information such as what problems the students have tackled in the past, which problems they struggled with, and how well they have understood the material.

[1122] The server generates personalized educational content based on the analysis results. For example, if it detects that a student is struggling with fraction addition, the server generates instructional materials focused on fraction addition. The instructional materials can be in the form of text, images, videos, etc.

[1123] The terminal (e.g., a tablet or PC used by a student) receives the personalized educational content sent from the server and displays it to the student. The student studies the teaching materials provided through the terminal.

[1124] 3. Examples of concrete examples and prompts

[1125] As a concrete example, consider a case where Student A is struggling with fraction addition. The server analyzes Student A's learning history and detects that Student A has a low level of understanding regarding fraction addition. The server then uses a generative AI model to generate teaching materials focused on fraction addition. The teaching materials include everything from basic concepts to applied problems of fraction addition.

[1126] Here is an example of a prompt to be input to the generative AI model:

[1127] "After analyzing Student A's learning history, we found that he is struggling with fraction addition. Please generate teaching materials that cover everything from basic concepts to applied problems related to fraction addition."

[1128] By inputting this prompt sentence into the generative AI model, personalized educational content is generated. The server sends this content to the terminal and provides it to Student A.

[1129] As described above, the present invention is capable of providing educational content optimized for each learner by combining the means for collecting, storing, and analyzing learning history data, and for generating, providing, and providing feedback on content. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1130] Step 1: Collect learning history data

[1131] The server records all learning activities that students perform on the learning platform. Specifically, it collects information in real time, such as the problems students solve, the videos they watch, and the materials they read. The input is the students' learning activities, and the output is the collected learning history data.

[1132] Step 2: Save learning history data

[1133] The server stores the collected learning history data in a database. Specifically, it creates an individual database entry for each student and stores the collected data. The input is the collected learning history data, and the output is the data stored in the database.

[1134] Step 3: Analyze learning history data

[1135] The server inputs the saved learning history data into the generative AI model and analyzes the student's level of understanding. Specifically, the server inputs a prompt statement to the generative AI model saying, "Analyze the student's learning history and identify weak areas." The input is the saved learning history data and the prompt statement, and the output is the analysis result regarding the student's level of understanding.

[1136] Step 4: Generate personalized educational content

[1137] Based on the analysis results, the server inputs a prompt sentence into the generative AI model to generate personalized educational content. Specifically, the prompt sentence is "Please generate teaching materials that include everything from basic concepts to applied problems regarding fraction addition." The input is the analysis results and the prompt sentence, and the output is the generated educational content.

[1138] Step 5: Provide educational content

[1139] The server transmits the generated educational content to the student's terminal. The terminal displays the received educational content to the student. Specifically, the educational material is displayed on a tablet or PC so that the student can study. The input is the generated educational content, and the output is the educational material displayed on the terminal.

[1140] Step 6: Feedback on learning results

[1141] The user (student) studies the teaching materials provided through the terminal and solves the practice problems. The answer is sent to the server, and the server updates the learning history data again. Specifically, the correct answer rate and answer time of the problem solved by the student are recorded and saved in a database. The input is the student's answer, and the output is the updated learning history data.

[1142] (Application example 3)

[1143] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1144] Conventional educational platforms have difficulty in providing educational content tailored to the needs of individual learners, and there has been a lack of personalized education, particularly in the area of ​​maintenance work for technicians. In addition, efficient learning has been difficult because educational content is not provided that takes into account the technician's past maintenance history or level of understanding.

[1145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1146] In this invention, the server is an educational platform that utilizes generative AI and includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, and a means for analyzing the maintenance history and level of understanding of a technician and generating personalized maintenance educational content based thereon. This makes it possible to provide personalized educational content based on the technician's past maintenance history and level of understanding.

[1147] "Generative AI" is a system that uses artificial intelligence technology to analyze data and automatically generate new content and information.

[1148] An "educational platform" is a system that provides an online or offline educational environment for use by learners and educators.

[1149] "Individual learning needs" are the educational requirements of each learner based on their specific learning goals and levels of understanding.

[1150] "Educational content" refers to teaching materials and information that students use to learn, including text, video, and interactive materials.

[1151] "Means of communication" are the methods and tools that learners and educators use to interact with and exchange information with generative AI.

[1152] A "customized learning experience" is an educational experience that is tailored to a learner's individual needs and level of understanding.

[1153] "Technician" refers to a professional who has specific skills and techniques and performs maintenance work, etc.

[1154] "Maintenance history" is a record of past maintenance work performed by a technician.

[1155] "Understanding" refers to the degree to which a learner or technician has understood a particular piece of knowledge or skill.

[1156] "Individualized maintenance training content" refers to training materials that are specially created based on a technician's maintenance history and level of understanding.

[1157] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server provides an educational platform that utilizes generative AI and generates educational content tailored to individual learning needs. The terminal is a device that allows the user to communicate with the server and receive the generated educational content. The user is an engineer or a learner, and uses the educational content through the terminal.

[1158] Server Processing

[1159] The server operates using the following hardware and software:

[1160] Hardware: A server machine with a powerful processor, sufficient memory, and storage.

[1161] Software: Python, Pandas, Scikit-learn, Transformers (Hugging Face)

[1162] The server first loads technician maintenance history data from a CSV file, then uses Scikit-learn's KMeans clustering algorithm to analyze technician maintenance history and classify it into clusters, which allows technicians to be divided into specific groups based on their past work history and error rates.

[1163] Then, we use the Transformers library to generate personalized maintenance training content for each cluster using the GPT-3 model. Specifically, we generate appropriate prompt sentences for each cluster and input them into the GPT-3 model to generate training content.

[1164] Terminal handling

[1165] The terminal is a device through which the user communicates with the server and receives the generated educational content. The terminal may be a PC, a tablet, a smartphone, etc. The terminal displays the educational content transmitted from the server and provides an interface for the user to study the content.

[1166] User Actions

[1167] The user accesses the server through the terminal and receives personalized educational content based on his / her maintenance history and level of understanding. The user studies the provided educational content and sends feedback to the server as necessary. This feedback is taken into consideration when the server generates the next educational content.

[1168] Examples

[1169] For example, if Technician A has a high error rate in maintenance tasks in the past, that technician will be classified into a specific cluster. For this cluster, the GPT-3 model will generate educational content focusing on "specific steps to reduce error rates" and "common troubleshooting methods."

[1170] Examples of prompt statements

[1171] Create maintenance training content for technicians who belong to Cluster 2, which contains many technicians with high error rates. Focus on specific steps to reduce the error rate and common troubleshooting methods.

[1172] In this way, it is possible to provide individualized educational content based on the technician's past maintenance history and level of understanding.

[1173] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1174] Step 1:

[1175] The server reads the technician's maintenance history data from a CSV file. The input is a CSV file that records the technician's maintenance history, and the output is the maintenance history data in data frame format. Specifically, the server reads the CSV file using the Pandas library and converts it into a data frame.

[1176] Step 2:

[1177] The server clusters technicians based on the maintenance history data it has loaded. The input is the maintenance history data in data frame format, and the output is a label indicating the cluster to which each technician belongs. Specifically, the server uses Scikit-learn's KMeans clustering algorithm to classify technicians into multiple clusters.

[1178] Step 3:

[1179] The server creates a prompt sentence for generating personalized educational content for each cluster. The input is the label of each cluster, and the output is a prompt sentence for each cluster. In concrete terms, the server generates an appropriate prompt sentence based on the characteristics of each cluster.

[1180] Step 4:

[1181] The server inputs the generated prompt sentence into the GPT-3 model to generate personalized educational content. The input is the prompt sentence, and the output is the personalized educational content. In specific operation, the server uses the Transformers library to input the prompt sentence into the GPT-3 model and obtain the generated educational content.

[1182] Step 5:

[1183] The server transmits the generated educational content to the terminal. The input is the personalized educational content, and the output is the educational content transmitted to the terminal. In a specific operation, the server transmits the educational content to the terminal via a network.

[1184] Step 6:

[1185] The terminal displays the received educational content to the user. The input is the educational content sent from the server, and the output is the educational content displayed in a format viewable by the user. In specific operations, the terminal converts the received data into an appropriate format and displays it on the user interface.

[1186] Step 7:

[1187] The user studies the displayed educational content and sends feedback to the server as necessary. The input is the user's feedback, and the output is the feedback sent to the server. In concrete terms, the user inputs feedback through the terminal and sends the feedback to the server by pressing a send button.

[1188] Step 8:

[1189] The server optimizes the next educational content based on the received feedback. The input is the user's feedback, and the output is the optimized educational content. Specifically, the server analyzes the feedback data and adjusts the next educational content using a generative AI model.

[1190] In addition, 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.

[1191] "Example 1"

[1192] In one embodiment of the present invention, the generative AI includes an emotion engine that recognizes the user's emotions. The emotion engine infers emotions from the user's facial expressions, tone of voice, text input, etc. For example, if a student shows a confused facial expression, raises the tone of their voice, or types "I don't know" in the text input, the emotion engine determines that the student is confused.

[1193] "Example 2"

[1194] After the emotion engine recognizes emotions, the generative AI can automatically generate educational content based on those emotions. For example, if a student feels confused, the AI ​​can provide simpler learning materials or detailed explanations to help students understand better.

[1195] "Example 3"

[1196] In addition, the emotion engine optimizes the learning experience based on the student's emotional changes. For example, if a student is confused at first, but shows a relieved expression after reading the provided material, the emotion engine will determine that the material was effective. This information can be used to generate future learning materials.

[1197] The process flow of each embodiment will be described below.

[1198] "Example 1"

[1199] Step 1: The generative AI collects information from the user's facial expressions, tone of voice, text input, etc.

[1200] Step 2: Send the collected information to the emotion engine.

[1201] Step 3: The emotion engine infers the user's emotion from the collected information.

[1202] "Example 2"

[1203] Step 1: After the emotion engine recognizes the emotion, it sends that information to the generative AI.

[1204] Step 2: The generative AI automatically generates educational content based on the received emotional information.

[1205] Step 3: The generated educational content is provided to the user.

[1206] "Example 3"

[1207] Step 1: The user consumes the provided educational content.

[1208] Step 2: The emotion engine again recognizes the change in the user's emotion.

[1209] Step 3: The emotion engine sends the emotion change information to the generative AI.

[1210] Step 4: The generative AI optimizes the learning experience based on the received emotional change information.

[1211] Example 1

[1212] Next, a description will be given of Example 1 of Form 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".

[1213] Conventional educational platforms have difficulty responding to individual learning needs and failing to provide feedback that takes into account the user's emotions. As a result, it is difficult for students and teachers to effectively advance their learning. Furthermore, there is a need for the generated educational content to be optimized according to the user's level of understanding and emotions.

[1214] 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.

[1215] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a sentiment analysis means for recognizing the user's sentiment, a means for generating a prompt sentence based on the user's input data, and a means for providing the generated educational content and the result of the sentiment analysis to the user. This makes it possible to provide optimal educational content according to the user's learning needs and provide feedback according to the user's sentiment.

[1216] "Generative AI" is an artificial intelligence technology that automatically generates content based on user input data.

[1217] An "educational platform" is an online system for students and teachers to conduct learning and educational activities.

[1218] "Learning needs" are the requirements or requirements that students or teachers have regarding specific learning objectives or learning content.

[1219] "Educational content" refers to teaching materials or information provided for the purpose of learning or education.

[1220] "Means of communication" refers to the interface or method by which a user interacts with and exchanges information with a generative AI.

[1221] A "customized learning experience" is a learning process or content that is optimized to a user's individual learning needs and progress.

[1222] "Emotion analysis means" is a technology that estimates emotions from a user's facial expressions, tone of voice, text input, etc.

[1223] A "prompt sentence" is an input sentence that instructs a generative AI to generate specific content.

[1224] "Feedback" is a response or evaluation provided to a user's action or input.

[1225] This invention relates to an educational platform that utilizes generative AI, and is a system that can provide educational content tailored to individual learning needs and provide feedback that takes into account the user's emotions.

[1226] The server uses a generative AI model (e.g., a general natural language processing model) to generate educational content based on user input data. Specifically, when a user inputs their learning needs or questions, the server analyzes the content and generates an appropriate prompt sentence. The generated prompt sentence is input into the generative AI model, which generates educational content.

[1227] In addition, the server uses emotion analysis means (e.g., a general emotion recognition API) to analyze the user's emotions. It estimates the user's emotions from their facial expressions, tone of voice, text input, etc., and determines whether the user is confused or not. This makes it possible to provide feedback according to the user's emotions.

[1228] The terminal transmits the data entered by the user to the server, and displays the educational content and the results of the sentiment analysis received from the server to the user. The user can study the displayed educational material and ask additional questions if necessary.

[1229] As a concrete example, consider the case where a student says, "I don't understand adding fractions." In this case, the server will input the following prompt to the generative AI model:

[1230] "My students say they don't understand how fractions are added. Please generate some easy-to-understand teaching materials on fraction addition."

[1231] Based on this prompt, the generative AI model generates teaching materials on fraction addition. For example, it might generate content like, "To understand fraction addition, you must first align the denominators. For example, when calculating 1 / 2 + 1 / 3, if you align the denominators to 6, it becomes 3 / 6 + 2 / 6, and the result is 5 / 6."

[1232] And if the sentiment analysis tool detects that a student is confused, the server can provide additional support messages, such as "If you need help, feel free to ask us anytime."

[1233] In this way, an educational platform that utilizes generative AI can provide optimal educational content tailored to the user's learning needs and provide feedback based on the user's emotions.

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

[1235] Step 1:

[1236] Users use the terminal to input their learning needs and questions.

[1237] Input: The user's learning need or question (e.g., "I don't understand adding fractions")

[1238] Output: Data entered into the terminal

[1239] Step 2:

[1240] The terminal transmits the user's input data to the server.

[1241] Input: Data entered into the terminal.

[1242] Output: Data sent to the server

[1243] Step 3:

[1244] The server analyzes the received user input data and generates a prompt sentence for the generative AI model.

[1245] Input: Data sent to the server

[1246] Data processing: Analyzes user input data and generates prompts

[1247] Output: Generated prompt (e.g. "Students say they don't understand fraction addition. Please generate easy-to-understand teaching materials on fraction addition.")

[1248] Step 4:

[1249] The server inputs prompt sentences into the generative AI model and generates educational content.

[1250] Input: Generated prompt text

[1251] Data Computation: A generative AI model generates educational content based on prompts

[1252] Output: Generated educational content (e.g., "To understand fraction addition, you must first align the denominators. For example, when calculating 1 / 2 + 1 / 3, if you align the denominators to 6, the result becomes 3 / 6 + 2 / 6, which is 5 / 6.")

[1253] Step 5:

[1254] The server uses the emotion analysis means to analyze the emotion of the user.

[1255] Input: User facial expressions, tone of voice, text input, etc.

[1256] Data calculation: Sentiment analysis method estimates user's emotions

[1257] Output: Sentiment analysis results (e.g., user is confused)

[1258] Step 6:

[1259] The server transmits the generated educational content and the results of sentiment analysis to the terminal.

[1260] Input: Generated educational content, sentiment analysis results

[1261] Output: Data sent to the terminal

[1262] Step 7:

[1263] The terminal displays the educational content and the results of the emotion analysis received from the server to the user.

[1264] Input: Data sent to the terminal

[1265] Output: Educational content and feedback displayed to the user (e.g., "To understand fraction addition, you must first align the denominators. For example, when calculating 1 / 2 + 1 / 3, if you align the denominators to 6, the result becomes 3 / 6 + 2 / 6, which is 5 / 6." and "If you have any questions, please feel free to ask us.")

[1266] Step 8:

[1267] The user studies the presented material and asks follow-up questions as needed.

[1268] Input: User's follow-up question (e.g., "Can you give me more examples of adding fractions?")

[1269] Output: Additional questions typed into the terminal

[1270] The above is the specific processing flow of the program of this system.

[1271] (Application example 1)

[1272] Next, a description will be given of Application Example 1 of Form 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".

[1273] Conventional educational platforms have the problem that it is difficult to respond to individual learning needs and cannot provide educational content that takes into account the emotions of users. In particular, when educating and training factory workers on-site, it is necessary to properly recognize the confusion and stress of workers and provide guidance accordingly.

[1274] 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. In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for recognizing the user's emotions using an emotion engine, and a means for adjusting the educational content based on the user's emotions. This makes it possible to provide appropriate educational content based on emotions in response to the individual learning needs of the user.

[1275] "Generative AI" is artificial intelligence that generates new content and information based on user input.

[1276] An "educational platform" is a system that provides educational content and enables learners and educators to communicate with each other.

[1277] "Individual learning needs" are requirements based on each learner's specific learning goals and levels of understanding.

[1278] "Educational content" refers to teaching materials and information that students use to learn.

[1279] A "means of communication" is an interface that allows users to interact with generative AI.

[1280] A "customized learning experience" is a learning process that is tailored to each individual learner's needs and progress.

[1281] An "emotion engine" is a technology that estimates emotions from a user's facial expressions, tone of voice, text input, etc.

[1282] The "means for adjusting educational content based on the user's emotions" is a function for changing the educational content provided in accordance with the user's emotions recognized by the emotion engine.

[1283] As an embodiment of the present invention, a system that provides an educational platform that utilizes generative AI is constructed. A specific embodiment of the system is described below.

[1284] System Configuration

[1285] The system consists of the following main components:

[1286] 1. Server: Hosts the generative AI model and runs the educational content generation and emotion engine.

[1287] 2. Terminal: Provides an interface for communicating with generative AI on devices used by students and teachers (smartphones, tablets, PCs, etc.).

[1288] 3. Camera and microphone: Devices for capturing the user's facial expressions and voice and inputting them into the emotion engine.

[1289] Program Processing

[1290] The server performs data processing and calculation using the following software and hardware:

[1291] Generative AI model: Uses OpenAI APIs to generate educational content based on user input.

[1292] Emotion engine: Facial expression recognition is performed using OpenCV, and speech recognition is performed using the SpeechRecognition library.

[1293] Database: Used to store users' learning history and feedback and to optimize the learning experience.

[1294] Processing flow

[1295] 1. User input: The user inputs their learning needs or questions through a terminal. For example, they input a question such as, "I don't know how to set up this machine."

[1296] 2. Emotion Recognition: The camera and microphone are used to capture the user's facial expressions and voice, and the emotion engine recognizes the user's emotions, for example detecting confused facial expressions and tone of voice.

[1297] 3. Prompt generation: Based on the recognized emotions and user input, generate a prompt to send to the generative AI model, for example, "The worker is confused. Please provide detailed guidance for the following question: I don't know how to configure this machine."

[1298] 4. Educational content generation: The generative AI model generates appropriate educational content based on the prompts and provides it to the user.

[1299] Examples

[1300] For example, if a factory worker types "I don't know how to set up this machine" into the terminal, the emotion engine will use the camera and microphone to recognize the worker's confused facial expression and tone of voice. As a result, a prompt will be generated for the generative AI model saying "The worker is confused. Please provide detailed guidance for the following question: I don't know how to set up this machine." Based on this prompt, the generative AI model will generate detailed setup instructions and provide them to the worker.

[1301] In this way, it is possible to provide appropriate educational content based on emotions, in response to the individual learning needs of the user.

[1302] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1303] Step 1:

[1304] The user inputs their learning needs and questions through the terminal. For example, they input a question such as, "I don't know how to set up this machine." The input data is sent to the server in text format.

[1305] Step 2:

[1306] The device's camera and microphone are used to capture the user's facial expressions and voice. The captured image and voice data are then sent to the server.

[1307] Step 3:

[1308] The server analyzes the received image data using OpenCV and recognizes the user's emotions from their facial expressions. For example, it detects confused expressions. The input is image data, and the output is the estimation result of the emotion.

[1309] Step 4:

[1310] The server converts the received voice data into text using the SpeechRecognition library. For example, the voice saying "I don't know how to set up this machine" is converted into text. The input is voice data, and the output is text data.

[1311] Step 5:

[1312] The server generates a prompt to be sent to the generative AI model based on the recognized emotion and the user's text input. For example, it generates a prompt such as "The worker is confused. Please provide detailed guidance for the following question: I don't know how to configure this machine." The input is the emotion estimation result and text data, and the output is the prompt sentence.

[1313] Step 6:

[1314] The server uses a generative AI model to generate educational content based on the generated prompt, e.g., detailed setup instructions. The input is the prompt text, and the output is the educational content.

[1315] Step 7:

[1316] The server transmits the generated educational content to the terminal and provides it to the user. The user browses the generated educational content through the terminal and proceeds with learning or work. The input is the educational content, and the output is the user's learning experience.

[1317] Example 2

[1318] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1319] Conventional educational platforms have difficulty providing educational content that meets individual learning needs, and have been unable to effectively utilize feedback from students and teachers. It has also been difficult to recognize students' emotional states in real time and provide appropriate educational content based on that. This has led to issues with the inability to sufficiently improve learning outcomes.

[1320] 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.

[1321] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for collecting feedback from students and teachers, a means for analyzing the collected feedback, a means for recognizing the emotions of students, and a means for automatically generating educational content based on the recognized emotions. This makes it possible to provide educational content tailored to individual learning needs, effectively utilize feedback from students and teachers, and provide appropriate educational content according to the emotional state of students.

[1322] "Generative AI" is a system that automatically generates educational content using artificial intelligence technology.

[1323] An "educational platform" is an online system for providing educational content intended for use by students and teachers.

[1324] "Individual learning needs" refers to the specific learning requirements and goals that each student and teacher has.

[1325] "Educational content" refers to teaching materials and resources provided for learning.

[1326] "Feedback" refers to opinions and evaluations provided by students and teachers on educational content.

[1327] "Emotion recognition" is a technology that identifies a student's emotional state from their facial expressions, voice, etc.

[1328] A "customized learning experience" refers to a learning experience that is tailored to individual learning needs and emotional states.

[1329] A "server" is a computer system that is the central part of an educational platform and processes and stores data.

[1330] "Terminal" refers to a device (PC, tablet, smartphone, etc.) used by students and teachers to access the educational platform.

[1331] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1332] The present invention relates to an educational platform that utilizes generative AI, and is a system that provides educational content tailored to individual learning needs. A specific embodiment of this system will be described below.

[1333] Hardware and Software Used

[1334] Hardware: Servers, terminals (PCs, tablets, smartphones)

[1335] Software: Generative AI models, emotion engines, feedback collection systems

[1336] System Configuration

[1337] 1. Feedback Collection System

[1338] Users (students and teachers) provide feedback on educational content.

[1339] The terminal collects this feedback and sends it to the server.

[1340] 2. Feedback Analysis System

[1341] The server analyzes the collected feedback.

[1342] The generative AI model adjusts its educational content generation algorithm based on the feedback.

[1343] For example, if a student provides feedback such as "this material is easy to understand," the AI ​​will learn the style of that material and reflect it in the creation of future material.

[1344] 3. Emotion Recognition System

[1345] The device recognizes students' emotions through their facial expressions and voice.

[1346] The emotion engine analyzes this data to identify the student's emotional state.

[1347] For example, if the emotion engine detects that a student is confused, it sends that information to the generative AI model.

[1348] 4. Educational Content Generation System

[1349] The generative AI model automatically generates educational content appropriate to the student's emotional state based on information from the emotion engine.

[1350] For example, if a student is identified as confused, the AI ​​will provide easier learning materials or more detailed explanations.

[1351] The terminal displays the generated educational content to the student.

[1352] Examples

[1353] Examples of feedback collection

[1354] The user (student) gives feedback such as "This math material was very easy to understand."

[1355] The terminal sends this feedback to the server.

[1356] Examples of feedback analysis

[1357] The server analyzes student feedback and extracts positive evaluations such as "easy to understand."

[1358] The generative AI model uses this positive feedback to adjust its future teaching material generation algorithms.

[1359] Examples of emotion recognition

[1360] The user (student) is faced with a difficult problem and looks confused.

[1361] The device uses a camera and microphone to transmit these facial expressions and voices to the emotion engine.

[1362] The emotion engine recognizes that the student is confused.

[1363] Examples of educational content creation

[1364] The generative AI model takes the information from the emotion engine and generates simpler learning materials to aid student understanding.

[1365] The terminal displays the generated new teaching material to the student.

[1366] Examples of prompt statements

[1367] “If a student gives feedback that a particular material is easy to understand, explain how you can learn from that style of material and incorporate it into your future material production.”

[1368] “Explain how the generative AI model can generate easier learning materials if the sentiment engine recognizes that a student is confused.”

[1369] The above is a specific embodiment for carrying out the present invention.

[1370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1371] Step 1:

[1372] Collecting feedback

[1373] Users (students and teachers) provide feedback on educational content.

[1374] Specific action: A student types a comment on an online learning platform, such as "This material was easy to understand."

[1375] The terminal collects this feedback and sends it to the server.

[1376] Input: Feedback comments from students and teachers

[1377] Data processing: Collect feedback comments as text data

[1378] Output: Feedback data sent to the server.

[1379] Step 2:

[1380] Feedback Analysis

[1381] The server analyzes the collected feedback.

[1382] Specific Behavior: The server runs the feedback data through a text analysis algorithm to determine whether the feedback is positive or negative.

[1383] Input: Feedback data

[1384] Data processing: Classifying feedback using text analysis algorithms

[1385] Output: Categorized feedback data

[1386] The generative AI model adjusts its educational content generation algorithm based on the feedback.

[1387] Specific actions: For example, learn the style of teaching materials that receive the most positive feedback and reflect this in the creation of future teaching materials.

[1388] Input: Categorized feedback data

[1389] Data processing: Adjusting the educational content generation algorithm

[1390] Output: A tuned educational content generation algorithm.

[1391] Step 3:

[1392] Emotion recognition

[1393] The device recognizes students' emotions through their facial expressions and voice.

[1394] Specific operation: The device's camera and microphone capture the student's facial expressions and voice in real time and send them to the emotion engine.

[1395] Input: Student facial expression and voice data

[1396] Data processing: facial expression and voice data capture

[1397] Output: Data sent to the emotion engine

[1398] The emotion engine analyzes this data to identify the student's emotional state.

[1399] Specific behavior: The emotion engine analyzes the student's facial expression data and determines that the student is "confused."

[1400] Input: facial expression data and voice data

[1401] Data processing: Identifying emotional states through sentiment analysis algorithms

[1402] Output: Identified emotional state data

[1403] Step 4:

[1404] Educational content generation

[1405] The generative AI model automatically generates educational content appropriate to the student's emotional state based on information from the emotion engine.

[1406] How it works: When the emotion engine tells the model that the user is confused, the generative AI model generates new content that includes simpler teaching materials and more detailed explanations.

[1407] Input: Identified emotional state data

[1408] Data processing: Generating new content using educational content generation algorithms

[1409] Output: Generated educational content

[1410] The terminal displays the generated educational content to the student.

[1411] Specific action: The new teaching material is displayed on the device screen and the student can view it.

[1412] Input: Generated educational content

[1413] Data processing: Display of educational content

[1414] Output: Educational content presented to students

[1415] The above are the specific processing steps of the program of this system.

[1416] (Application example 2)

[1417] Next, a description will be given of Application Example 2 of Form 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".

[1418] Conventional educational platforms have the problem that it is difficult to respond to the individual learning needs of students and cannot provide educational content that takes into account the emotional state of students. In particular, it is necessary to provide appropriate educational content at the right time when students are confused or have not yet fully understood.

[1419] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1420] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for recognizing students' emotions using an emotion engine, and a means for automatically generating educational content based on the recognized emotions. This makes it possible to recognize students' emotional states in real time and provide optimal educational content based on the emotional states.

[1421] "Generative AI" is an artificial intelligence technology that automatically generates educational content based on the feedback and learning needs of students and teachers.

[1422] An "educational platform" is a system for providing educational content intended for use by students and teachers.

[1423] "Individual learning needs" refers to the specific learning requirements and goals that each student has.

[1424] "Educational content" refers to teaching materials and information provided for learning.

[1425] "Means of communication" refers to the methods and interfaces that students and teachers use to exchange information with generative AI.

[1426] A "customized learning experience" refers to a learning experience that is tailored based on a student's individual learning needs and feedback.

[1427] An "emotion engine" refers to technologies and algorithms that are used to recognize a student's emotional state.

[1428] "Means for recognizing emotions" refers to a method or apparatus for detecting a student's emotional state using an emotion engine.

[1429] "Means of automatic generation" refers to the methods and algorithms by which a generative AI automatically creates educational content based on information obtained from the emotion engine.

[1430] As an embodiment of the present invention, a system for installing an emotion recognition educational assistant application on a smartphone or a head-mounted display will be described.

[1431] The server uses generative AI to provide educational content tailored to individual learning needs. Specifically, it provides an interface for students and teachers to communicate with the generative AI and provide a customized learning experience. It also uses an emotion engine to recognize students' emotions and automatically generate educational content based on those emotions.

[1432] This system uses the following hardware and software:

[1433] Hardware: Camera on a smartphone or head-mounted display

[1434] Software: OpenCV (image processing library), Keras (deep learning library), TextGenerationAI (generative AI model)

[1435] The server acquires images from the camera and performs image processing using OpenCV. Specifically, the images are converted to grayscale and input into the emotion recognition model. The emotion recognition model is built using Keras and predicts the student's emotions. Based on the predicted emotions, appropriate educational content is generated using TextGenerationAI.

[1436] For example, if a student is in a math class and the emotion recognition model detects "confusion" from the student's facial expression, it will send the following prompt to the generative AI model:

[1437] Example prompt:

[1438] Provide a simpler explanation for solving quadratic equations.

[1439] Based on this prompt, the generative AI model can then generate a simpler explanation to provide to the student, such as "Here's a step-by-step guide on how to use the formula to solve quadratic equations."

[1440] In this way, the server can recognize the students' emotional state in real time and provide them with optimal educational content based on it, thus improving their comprehension and optimizing their learning experience.

[1441] The flow of the identification process in the application example 2 will be described with reference to FIG.

[1442] Step 1:

[1443] The server acquires video from the device's camera. The input is real-time video from the camera, and the output is the acquired video frames. Specifically, the server transmits the video captured by the camera to the server frame by frame.

[1444] Step 2:

[1445] The server converts the acquired video frames to grayscale using OpenCV. The input is a color video frame, and the output is a grayscale video frame. Specifically, the server converts a color image to a grayscale image using OpenCV functions.

[1446] Step 3:

[1447] The server inputs the grayscale converted video frames into an emotion recognition model using Keras. The input is a grayscale video frame, and the output is the emotion recognition result. In concrete terms, the grayscale image is input into the emotion recognition model, and the emotion prediction result is obtained.

[1448] Step 4:

[1449] The server generates an appropriate prompt sentence based on the emotion recognition result. The input is the emotion recognition result, and the output is the prompt sentence. As a specific operation, if the emotion is "confusion", the server generates the prompt sentence "Provide a simpler explanation for solving quadratic equations."

[1450] Step 5:

[1451] The server sends the generated prompt sentence to TextGenerationAI to generate educational content. The input is the prompt sentence, and the output is the generated educational content. Specifically, the server calls the TextGenerationAI API and generates educational content based on the prompt sentence.

[1452] Step 6:

[1453] The server transmits the generated educational content to the terminal and provides it to the user. The input is the generated educational content, and the output is the educational content displayed to the user. In concrete terms, the server transmits the generated educational content to the terminal and displays it on the user's screen.

[1454] Example 3

[1455] Next, a third embodiment of the third embodiment will be described. 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".

[1456] With conventional educational platforms, it was difficult to provide educational content tailored to the needs of individual learners, resulting in insufficient learning outcomes. It was also difficult to grasp students' emotions and levels of understanding in real time and optimize the learning experience based on that. This led to issues such as a decline in students' motivation to learn and poor learning outcomes.

[1457] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1458] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for collecting learning history data of students, a means for analyzing the learning history data, a means for generating personalized educational content, a means for providing educational content, a means for monitoring the emotions of students, and a means for analyzing and feeding back the emotion data. This makes it possible to provide educational content tailored to the needs of individual learners, maximizing the learning effect. In addition, since the emotions and comprehension of students can be grasped in real time and the learning experience can be optimized based on the emotions and comprehension, it is possible to improve the motivation of students to learn and improve the learning results.

[1459] "Generative AI" is a system that generates data using artificial intelligence technology.

[1460] An "educational platform" is a system that provides educational content and enables learners and educators to communicate with each other.

[1461] "Individual learning needs" refers to the specific learning requirements and goals that each learner has.

[1462] "Educational content" refers to teaching materials and information that students use to learn.

[1463] "Means of communication" refers to the methods and tools that learners and educators use to exchange information with generative AI.

[1464] A "customized learning experience" refers to a learning process that is tailored to a learner's individual needs and progress.

[1465] "Learning history data" refers to information regarding a learner's past learning activities and achievements.

[1466] "Analytical means" refers to the methods and tools used to analyze collected data and extract meaningful information.

[1467] "Personalized educational content" refers to instructional materials created based on a learner's specific needs and level of understanding.

[1468] "Means of delivery" refers to the methods and tools used to deliver the generated educational content to learners.

[1469] "Emotion monitoring measures" refer to methods and tools for observing and recording learners' emotional states in real time.

[1470] "Emotional Data" refers to information regarding a learner's emotional state.

[1471] "Feedback measures" refer to methods and tools for improving a system or learning process based on collected data.

[1472] The present invention relates to an educational platform that utilizes generative AI, and is a system that provides educational content tailored to individual learning needs. A specific embodiment of this system will be described below.

[1473] The server first collects the students' learning history data, including past test results, study time, browsing history of teaching materials, etc. The server obtains this information from a database (e.g., MySQL or PostgreSQL).

[1474] The server then analyzes the collected learning history data using AI models (e.g., TensorFlow or PyTorch). This analysis identifies areas in which students struggle. For example, it may be discovered that a student struggles with adding fractions.

[1475] The server generates personalized educational content based on the analysis results. Using a generative AI model (e.g., OpenAI's GPT-4), it creates teaching materials by inputting prompt sentences such as the following:

[1476] Example prompt:

[1477] "Student A is having difficulty with adding fractions. Please generate teaching materials that cover the basics of adding fractions, as well as advanced applications."

[1478] The generated teaching materials are sent from the server to the student's device (e.g., tablet or PC). The device displays the received teaching materials to the student.

[1479] In addition, the device uses the built-in camera and microphone to monitor the student's facial expressions and tone of voice in real time. An emotion engine (for example, Microsoft Azure's Emotion API) is used to analyze the student's emotional state. If the student shows a relieved expression after reading the material, the emotion engine determines that the material was effective.

[1480] The server analyzes the emotion data sent from the emotion engine. This information is fed back to future teaching material generation. For example, if a student shows a relieved expression, the server determines that the teaching material was effective and reflects this information in the next teaching material generation.

[1481] As a concrete example, consider a case where a user (Student A) is struggling with adding fractions. The server retrieves Student A's past test results and study time from the database and analyzes them using an AI model. Based on the analysis results, the server inputs the following prompt sentence into the generative AI model:

[1482] Example prompt:

[1483] "Student A is having difficulty with adding fractions. Please generate teaching materials that cover the basics of adding fractions, as well as advanced applications."

[1484] The generated teaching materials are sent from the server to Student A's device. The device displays the teaching materials to Student A and monitors Student A's facial expressions with a built-in camera. If the emotion engine analyzes Student A's facial expressions and detects a relieved expression, the server determines that the teaching materials were effective and reflects this information in the next generation of teaching materials.

[1485] The above is a specific embodiment of this educational platform. The flow of the specific process in the third embodiment will be described with reference to FIG.

[1486] Step 1:

[1487] The server collects students' learning history data. As input, it retrieves information such as past test results, study time, and browsing history of teaching materials from a database (e.g., MySQL or PostgreSQL). As output, it centralizes these data and creates a dataset for analysis.

[1488] Step 2:

[1489] The server analyzes the collected learning history data using an AI model (e.g., TensorFlow or PyTorch). The dataset created in step 1 is used as input. Data processing involves preprocessing the data (filling in missing values, normalization, etc.) and inputting it into the AI ​​model. The output is an analysis result that identifies which areas the student is struggling with.

[1490] Step 3:

[1491] The server generates personalized educational content based on the analysis results. As input, it uses the analysis results obtained in step 2. It inputs the following prompt sentence into a generative AI model (e.g., OpenAI's GPT-4) to create teaching materials. As output, it generates personalized educational content.

[1492] Example prompt:

[1493] "Student A is having difficulty with adding fractions. Please generate teaching materials that cover the basics of adding fractions, as well as advanced applications."

[1494] Step 4:

[1495] The server sends the generated educational content to the terminal. As input, it uses the educational content generated in step 3. As output, it obtains the educational content sent to the terminal. The terminal displays the received educational material to the student.

[1496] Step 5:

[1497] The device monitors the student's facial expressions and tone of voice in real time using the built-in camera and microphone. As input, it obtains the student's facial expression and voice data. It uses an emotion engine (e.g., Microsoft Azure's Emotion API) to analyze these data. As output, it obtains the student's emotional state.

[1498] Step 6:

[1499] The server analyzes the emotion data sent from the emotion engine. As input, it uses the emotion data obtained in step 5. As data processing, it analyzes the emotion data and evaluates the effectiveness of the teaching materials. As output, it obtains an evaluation result regarding the effectiveness of the teaching materials. This information is fed back to the generation of future teaching materials.

[1500] Specifically, for example, if Student A is struggling with adding fractions, the server retrieves Student A's past test results and study time from the database and analyzes them using the AI ​​model. Based on the analysis results, the server inputs prompt sentences into the generative AI model and generates personalized learning materials. The generated learning materials are sent from the server to Student A's device, and the device displays the learning materials to Student A. The device monitors Student A's facial expressions with a built-in camera, and the emotion engine analyzes the expressions. If the server detects a relieved expression, it determines that the learning materials were effective and reflects this information in the next learning material generation.

[1501] (Application example 3)

[1502] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1503] With conventional education platforms, it was difficult to provide educational content tailored to the needs of individual learners, and it was not possible to optimize the learning experience by grasping the learner's emotions and level of understanding in real time. Furthermore, in factories and other workplaces, there was a problem that personalized education based on the worker's skill level and work history was not provided, and efficient education was not possible.

[1504] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1505] In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for analyzing the work history and skill level of a worker to generate personalized educational content, and a means for analyzing the facial expressions and movements of a worker to optimize the learning experience. This makes it possible to provide optimized educational content in real time to individual learners and workers.

[1506] "Generative AI" is a system that uses artificial intelligence technology to analyze data and automatically generate new information and content.

[1507] An "educational platform" is an online or offline system that provides educational content and learning tools for use by learners and educators.

[1508] "Individual learning needs" refers to the educational requirements of each learner based on their specific learning goals, levels of understanding and interests.

[1509] "Educational content" is a general term for teaching materials, information, assignments, etc. that students use to study.

[1510] A "means of communication" is the interface or method by which a user interacts with a system and exchanges information.

[1511] A "customized learning experience" is a learning process or materials that are tailored to a learner's individual needs and progress.

[1512] "Work history" refers to records and data of work that a worker has performed in the past.

[1513] "Skill level" is an index showing the degree of proficiency of a worker's techniques and knowledge.

[1514] "Means of analyzing facial expressions and movements" refers to technologies and algorithms that use cameras and sensors to detect and analyze a worker's facial expressions and movements.

[1515] "Means for optimizing the learning experience" are methods and techniques for adjusting the educational content and learning process provided based on the learner's or worker's level of understanding and emotions.

[1516] The present invention provides an educational platform that utilizes generative AI, and is a system that provides educational content tailored to individual learning needs. Specific embodiments for implementing the present invention will be described below.

[1517] System Configuration

[1518] This system consists of three main components: a server, a terminal, and a user.

[1519] server

[1520] The server has the following functions:

[1521] 1. Means of providing educational content tailored to individual learning needs: The server stores the learner's learning history and skill level in a database and generates personalized educational content based on that.

[1522] 2. Means of communication with the generative AI: The server uses the generative AI model to analyze input and feedback from users and provide appropriate educational content.

[1523] 3. A means to provide a customized learning experience: The server adjusts the learning process in real time based on the learner's progress and understanding.

[1524] 4. Means for analyzing workers' work history and skill level: The server stores the work history and skill level of factory workers in a database and generates personalized educational content based on that.

[1525] 5. Means for analyzing the worker's facial expressions and movements: The server uses cameras and sensors to capture the worker's facial expressions and movements and analyzes them using an emotion engine.

[1526] 6. Means for optimizing learning experience: The server optimizes the learning experience of the learner or worker based on the analysis results of the emotion engine.

[1527] Terminal

[1528] The terminal is a device through which the user receives the educational content. Specifically, the terminal includes a smartphone, a tablet, a personal computer, etc. The terminal displays the educational content transmitted from the server and transmits the user's input and feedback to the server.

[1529] User

[1530] The users are students or factory workers who receive educational content through their terminals and proceed with their learning. The users operate their terminals to send feedback to the server and optimize their learning experience.

[1531] Hardware and Software Used

[1532] Hardware: Cameras (to capture the worker's facial expressions), sensors (to capture their movements)

[1533] Software: OpenCV (for image processing), TensorFlow (for emotion engine models)

[1534] Data processing and calculation

[1535] The server performs the following data processing and calculations.

[1536] 1. Database management of learning history and skill level: The learning history and skill level of learners and workers are stored in a database, and the data is retrieved as needed.

[1537] 2. Facial Expression Analysis: Preprocess facial expression images captured by the camera and analyze them with the emotion engine. Specifically, we convert the images to grayscale using OpenCV and predict emotions using the TensorFlow model.

[1538] 3. Educational content generation: Generate personalized educational content using generative AI models based on learning history and skill level.

[1539] 4. Optimizing the learning experience: Adjust the educational content and learning process in real time based on the analysis results of the emotion engine.

[1540] Examples

[1541] For example, if a factory worker is struggling with a particular task and facial expressions captured by the camera indicate confusion, the server will generate educational content focused on that task and send it to the device. The worker can then receive the educational content through the device and progress with their learning.

[1542] Examples of prompt statements

[1543] "Create a program that uses the learning history and facial expression data of factory workers to generate personalized educational content and optimize the learning experience. Specifically, analyze the facial expressions of workers and, if they are confused, provide educational content focused on the specific task."

[1544] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1545] Step 1:

[1546] The server stores the learning history and skill levels of learners and workers in a database.

[1547] Input: Learner and worker learning history data, skill level data

[1548] Data processing: Converting data into a format for saving to a database

[1549] Output: Learning history and skill level data stored in a database

[1550] Specific operation: The server receives the learning history and skill level data entered by the user and stores it in a database.

[1551] Step 2:

[1552] The server acquires the facial expression image of the worker captured by the camera.

[1553] Input: Facial expression image captured by the camera

[1554] Data processing: Convert the image to grayscale and adjust the size

[1555] Output: Preprocessed facial expression images

[1556] Specific operation: The server receives the facial expression image sent from the camera, converts it to grayscale using OpenCV, and adjusts the size.

[1557] Step 3:

[1558] The server analyzes the pre-processed facial expression images with an emotion engine.

[1559] Input: Preprocessed facial expression images

[1560] Data computation: Predicting emotions using an emotion engine (TensorFlow model)

[1561] Output: Emotion label (e.g. confusion, relief, etc.)

[1562] Specific operation: The server inputs the preprocessed facial expression images into the TensorFlow model to predict emotions.

[1563] Step 4:

[1564] The server generates personalized educational content based on learning history and skill level.

[1565] Input: Learning history data, skill level data

[1566] Data Computation: Generating educational content using generative AI models

[1567] Output: personalized educational content

[1568] Specific operation: The server retrieves learning history and skill level data from the database and generates personalized educational content using a generative AI model.

[1569] Step 5:

[1570] The server optimizes the learning experience based on the emotion engine's analysis results.

[1571] Input: emotion labels, personalized educational content

[1572] Data Computing: Tailoring Educational Content Based on Sentiment Labels

[1573] Output: Optimized educational content

[1574] Specific Behavior: The server generates and optimizes educational content focused on a specific task when the emotion label indicates “confusion.”

[1575] Step 6:

[1576] The terminal displays the optimized educational content to the user.

[1577] Input: Optimized educational content

[1578] Data processing: Converting educational content into a display format

[1579] Output: Educational content displayed on the device

[1580] Specific operation: The terminal receives the optimized educational content sent from the server and displays it to the user.

[1581] Step 7:

[1582] Users receive educational content through their terminals and progress with their studies.

[1583] Input: Educational content displayed on the device

[1584] Data Computing: Understanding Educational Content and Advancing Learning

[1585] Output: Learning progress data, feedback

[1586] Specific operation: The user looks at the educational content displayed on the terminal, progresses with their studies, and sends feedback to the server if necessary.

[1587] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1588] 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> ) and other generative AIs. Data generation model 58 is

[1589] , obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is 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.

[1590] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1591] 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 smart glasses 214.

[1592] [Third embodiment]

[1593] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1594] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1595] 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 wide area network (WAN) and / or a local area network (LAN).

[1596] 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.

[1597] 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 the voice according to instructions from the processor 46.

[1598] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1599] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1600] Fig. 6 shows an example of 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.

[1601] 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.

[1602] 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.

[1603] In the headset type terminal 314, 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.

[1604] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1605] "Example 1"

[1606] As one embodiment of the present invention, an educational platform that utilizes generative AI is provided. This platform is equipped with an interface that allows students and teachers to communicate directly with the AI. Specifically, students and teachers input their learning needs and questions into the AI, and the AI ​​generates educational content based on them. For example, if a student inputs "I don't understand fraction addition," the AI ​​generates educational materials related to fraction addition and provides them to the student.

[1607] "Example 2"

[1608] In addition, generative AI optimizes the learning experience based on feedback from students and teachers. Specifically, it collects feedback from students and teachers and adjusts the AI's educational content generation algorithm based on that feedback. For example, if a student gives feedback that a certain material is easy to understand, the AI ​​will learn the style of that material and reflect it in future material generation.

[1609] "Example 3"

[1610] In addition, the educational platform of the present invention provides educational content tailored to the needs of individual learners. Specifically, it analyzes the student's learning history and level of understanding, and generates personalized educational content based on that. For example, if the AI ​​detects that a student is struggling with fraction addition, the AI ​​will generate teaching materials focused on fraction addition and provide them to the student.

[1611] The process flow of each embodiment will be described below.

[1612] "Example 1"

[1613] Step 1: Students and teachers log in to the education platform.

[1614] Step 2: Students or teachers input their learning needs or questions into the AI. For example, they could say, "I don't understand how to add fractions."

[1615] Step 3: The AI ​​generates educational content based on the input information. Specifically, it generates teaching materials on fraction addition.

[1616] Step 4: The generated learning materials are provided to students, who use them to further their learning.

[1617] "Example 2"

[1618] Step 1: Students and teachers use the educational platform to advance their learning.

[1619] Step 2: Feedback from students and teachers is sent to the AI. For example, a student may give feedback that a particular material is easy to understand.

[1620] Step 3: The AI ​​will adjust its educational content generation algorithm based on the collected feedback. Specifically, it will learn the style of the teaching materials based on the feedback from students and reflect it in future teaching material generation.

[1621] "Example 3"

[1622] Step 1: Students use the educational platform to progress with their studies.

[1623] Step 2: AI analyzes students' learning history and level of understanding.

[1624] Step 3: The AI ​​generates personalized educational content based on the analysis results. For example, if it detects that a student is struggling with fraction addition, the AI ​​will generate instructional materials focused on fraction addition.

[1625] Step 4: The generated learning materials are provided to students, who use them to further their learning.

[1626] Example 1

[1627] Next, a description will be given of Example 1 of the embodiment 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".

[1628] Conventional educational platforms were difficult to customize to meet individual learning needs, making it difficult to quickly provide the specific educational content that students and teachers wanted. In addition, there was a lack of a mechanism for optimizing the generated educational content based on user feedback, which led to problems with insufficient learning effectiveness.

[1629] 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.

[1630] In this invention, the server includes a means for performing user authentication, a means for receiving user input, a means for generating a prompt sentence, a means for sending a request to the generative AI model, a means for receiving and storing the generated content, and a means for providing the stored content to the user, thereby enabling the rapid provision of educational content that meets individual learning needs and the optimization of the learning experience based on user feedback.

[1631] "User authentication" is the process of verifying that a user has valid authority when accessing a system.

[1632] "User input" refers to information or requests that a user provides to the system, including, in particular, learning needs and questions.

[1633] A "prompt" is a textual request that instructs a generative AI model to generate specific educational content.

[1634] A "generative AI model" is an artificial intelligence algorithm or system that automatically generates educational content based on user input.

[1635] "Means for sending a request" refers to a communication means by which the server sends a prompt sentence to the generative AI model.

[1636] "Generated content" refers to educational materials or teaching materials that a generative AI model generates based on a prompt.

[1637] "Means for storing" refers to a function for storing the generated content in a database or storage.

[1638] The "means of providing" refers to the functionality for displaying and making accessible the stored content to the user.

[1639] The present invention relates to an educational platform that utilizes a generative AI model, and is a system that provides educational content that meets individual learning needs. A specific embodiment of this system will be described below.

[1640] Server Roles

[1641] The server authenticates users, receives user input, generates prompts, sends requests to the generative AI model, receives and stores the generated content, and serves the content.

[1642] 1. User Authentication

[1643] When a user accesses the educational platform, the server receives login information. It references a database (e.g., MySQL) and authenticates the user. If authentication is successful, it grants the user access rights.

[1644] 2. Receiving User Input

[1645] The server receives learning needs and questions that the user inputs into the interface, for example, the user inputs "I don't understand adding fractions."

[1646] 3. Prompt generation

[1647] The server analyzes the received user input and generates a prompt to send to the generative AI model. Specifically, it creates a prompt such as "Please generate teaching materials on fraction addition."

[1648] 4. Sending a request to the generative AI model

[1649] The server sends the generated prompt sentence to a generative AI model (e.g., OpenAI's GPT-4), which generates educational content based on the prompt sentence.

[1650] 5. Receiving and storing generated content

[1651] The server receives the educational content returned by the generative AI model and stores the received content in a database.

[1652] 6. Content Provision

[1653] The server transmits the stored educational content to the user's terminal.

[1654] Terminal Roles

[1655] The terminal is a device that allows users to access the educational platform, input their learning needs and questions, and display the generated educational content. Specifically, this applies to PCs, tablets, smartphones, etc.

[1656] 1. Access and Login

[1657] The terminal displays an interface for the user to access the educational platform. The user enters login information, which the terminal transmits to the server.

[1658] 2. Submitting User Input

[1659] The device sends to the server learning needs and questions that users enter into the interface, for example, "I don't understand adding fractions."

[1660] 3. Display of Content

[1661] The terminal displays the educational content received from the server to the user, for example, teaching materials on adding fractions.

[1662] User Roles

[1663] Users (students and teachers) use their terminals to access the educational platform, input their learning needs and questions, and study using the provided educational content.

[1664] 1. Log in

[1665] The user enters a username and password into the terminal interface and clicks the login button.

[1666] 2. Input your learning needs

[1667] Users enter their learning needs or questions into the interface, for example, "I don't understand adding fractions."

[1668] 3. Use of Content

[1669] The user learns using educational content displayed on the device, for example by reading material and solving problems about adding fractions.

[1670] Examples

[1671] A specific example will be described in which a user (student) inputs "I don't understand addition of fractions."

[1672] 1. The terminal sends this input to the server.

[1673] 2. The server analyzes the input and sends a prompt to the generative AI model saying, "I would like you to generate teaching materials on adding fractions."

[1674] 3. The generative AI model (GPT-4) generates teaching materials on adding fractions.

[1675] 4. The server transmits the generated teaching materials to the terminal.

[1676] 5. The terminal displays the educational material to the user.

[1677] Examples of prompt statements

[1678] "Generate educational materials on fraction addition for students who don't understand fraction addition."

[1679] In this way, the server, terminal, and user each play their respective roles, and an educational platform that utilizes generative AI models functions.

[1680] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1681] Step 1:

[1682] User Authentication

[1683] The server receives login information (username and password) when a user accesses the educational platform. The server runs a SQL query against a database (e.g. MySQL) to authenticate the user. If authentication is successful, the server grants the user access.

[1684] Input: Username, Password

[1685] Output: Authentication result (success / failure)

[1686] Step 2:

[1687] Receiving User Input

[1688] The server receives the learning needs and questions that the user inputs into the interface. For example, the user might input, "I don't understand adding fractions." The server analyzes this input and takes the next step.

[1689] Input: Learning need or question (e.g., "I don't understand adding fractions")

[1690] Output: Parsed user input

[1691] Step 3:

[1692] Generate prompt statement

[1693] The server analyzes the received user input and generates a prompt to send to the generative AI model. Specifically, it creates a prompt such as "Please generate teaching materials on fraction addition."

[1694] Input: Parsed user input

[1695] Output: Prompt (e.g. "Please generate teaching materials on adding fractions")

[1696] Step 4:

[1697] Sending requests to generative AI models

[1698] The server sends the generated prompt sentence to a generative AI model (e.g., OpenAI's GPT-4). The server sends an HTTP request to the API endpoint of the generative AI model, and the generative AI model generates educational content based on the prompt sentence.

[1699] Input: Prompt statement

[1700] Output: A request to the generative AI model

[1701] Step 5:

[1702] Receiving and storing generated content

[1703] The server receives the educational content returned by the generative AI model and executes SQL queries to store the received content in a database.

[1704] Input: Response from generative AI model (educational content)

[1705] Output: Saved educational content

[1706] Step 6:

[1707] Content provision

[1708] The server transmits the stored educational content to the user's terminal as an HTTP response, and the terminal displays it to the user.

[1709] Input: Saved Educational Content

[1710] Output: Sending educational content to user devices

[1711] Step 7:

[1712] View content

[1713] The terminal displays the educational content received from the server to the user. Specifically, the educational content is visually displayed using HTML and CSS.

[1714] Input: Educational content from the server

[1715] Output: The educational content displayed to the user

[1716] Step 8:

[1717] Use of Content

[1718] The user learns using educational content displayed on the device, for example by reading material and solving problems about adding fractions.

[1719] Input: Displayed educational content

[1720] Output: User learning outcomes

[1721] (Application example 1)

[1722] Next, a description will be given of Application Example 1 of Form 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".

[1723] Conventional educational platforms lacked the customization required to meet individual learning needs, making it difficult to provide educational content in real time. In addition, there was a lack of a way for on-site staff working in brick-and-mortar stores to instantly receive the necessary educational content, which hindered the improvement of work efficiency and customer service skills.

[1724] 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.

[1725] In this invention, the server is an educational platform that utilizes generative AI and includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, and a means for receiving educational content in real time through a smart device. This makes it possible to provide educational content customized to individual learning needs, and allows staff working in the field, such as in a brick-and-mortar store, to receive the necessary educational content in real time, thereby improving work efficiency and customer service skills.

[1726] "Generative AI" is an artificial intelligence technology that automatically generates new content and data based on input information.

[1727] An "educational platform" is an online system that provides educational content and enables learners and educators to communicate with each other.

[1728] "Individual learning needs" are the educational requirements of each learner based on their specific learning goals and levels of understanding.

[1729] "Educational content" refers to teaching materials and information that students use to learn, and includes formats such as text, images, and videos.

[1730] A "means of communication" is an interface that allows learners and educators to interact with generative AI and exchange information.

[1731] A "customized learning experience" is an educational experience that is optimized based on a learner's individual needs and feedback.

[1732] A "smart device" is an electronic device that has Internet connectivity and enables users to obtain and operate information.

[1733] "Means of receiving educational content in real time" refers to a system that allows learners to instantly obtain the educational content they need.

[1734] A system for implementing this invention is an educational platform that utilizes generative AI and includes means for providing educational content tailored to individual learning needs, means for students and teachers to communicate with the generative AI, means for providing a customized learning experience, and means for receiving educational content in real time via a smart device.

[1735] The server uses a generative AI model to generate educational content based on user input. Specifically, when a user inputs a prompt such as "Please tell me the features of a new product" through a smart device (e.g., smart glasses), the server sends the prompt to the generative AI model. The generative AI model generates appropriate educational content based on the prompt and returns the result to the server.

[1736] The server then transmits the generated educational content to the smart device, enabling users to receive the content in real time, enabling store staff to instantly acquire knowledge about new products and improve their work efficiency and customer service skills.

[1737] The hardware used is smart glasses (e.g., Google Glass, Vuzix Blade). The software uses a generative AI model (e.g., GPT-3) to generate educational content through the OpenAI API. The program is implemented in Python and manages communication between the server and the smart device.

[1738] As a concrete example, when a new product arrives at a brick-and-mortar store, a staff member can type into the smart glasses, "Please tell me about the features of the new product." Based on this prompt, the generative AI model generates a detailed description and selling points, which are then displayed on the staff member's glasses.

[1739] Example prompt:

[1740] Please tell us the features of your new product.

[1741] In this way, it becomes possible to provide customized educational content tailored to individual learning needs, allowing staff working in physical stores and other locations to receive the educational content they need in real time, improving their work efficiency and customer service skills.

[1742] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1743] Step 1:

[1744] The user inputs a prompt sentence through a smart device (e.g., smart glasses).

[1745] Input: The user types into the smart glasses, "Please tell me the features of the new product" by voice or text.

[1746] Output: The smart glasses send the entered prompt text to the server.

[1747] Step 2:

[1748] The server sends the received prompt text to the generative AI model.

[1749] Input: The prompt text sent from the smart glasses.

[1750] Output: A request to send a prompt to the generative AI model.

[1751] Specific operation: The server receives the prompt text and sends a request to the generative AI model using the OpenAI API.

[1752] Step 3:

[1753] A generative AI model generates educational content based on the prompt text.

[1754] Input: The prompt text sent by the server.

[1755] Output: The generated educational content.

[1756] How it works: A generative AI model (e.g. GPT-3) analyzes the prompt and generates appropriate educational content.

[1757] Step 4:

[1758] The server receives the generated educational content and transmits it to the smart device.

[1759] Input: Educational content returned from a generative AI model.

[1760] Output: Educational content sent to smart devices.

[1761] Specific operation: The server receives the generated educational content and converts it into a data format for transmission to the smart glasses.

[1762] Step 5:

[1763] The smart device displays the received educational content to the user.

[1764] Input: Educational content sent from the server.

[1765] Output: Educational content displayed on the smart glasses display.

[1766] Specific operation: The smart glasses analyze the received educational content and display it in the user's field of vision.

[1767] In this way, users can receive the educational content they need in real time.

[1768] Example 2

[1769] Next, a second embodiment of the second form will be described. 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".

[1770] Traditional educational platforms are not sufficiently customized to address the individual learning needs of students and teachers, and they lack the means to effectively use feedback to optimize the learning experience, limiting the quality and effectiveness of educational content.

[1771] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting feedback from students and teachers, a means for analyzing the collected feedback, and a means for adjusting the algorithm of the generative AI model based on the analysis result. This makes it possible to automatically generate educational content by effectively utilizing the feedback and provide a customized learning experience that meets individual learning needs.

[1772] "Feedback" refers to information such as impressions, evaluations, and level of understanding provided by students and teachers regarding educational content.

[1773] "Analysis" refers to the process of understanding the content of collected feedback using natural language processing techniques and extracting important information.

[1774] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to automatically generate educational content.

[1775] "Algorithm adjustment" is the process of changing the parameters and behavior of the generative AI model based on the analysis results in order to generate more effective educational content.

[1776] "Educational content" refers to teaching materials and resources used by students and teachers for learning and teaching.

[1777] "Collection methods" refers to the interfaces and systems used to gather feedback from students and teachers.

[1778] "Delivery means" refers to the interface or system for delivering the generated educational content to students and teachers.

[1779] This invention is a system that provides educational content tailored to individual learning needs by collecting and analyzing feedback from students and teachers and adjusting the algorithms of the generative AI model based on the results.

[1780] Hardware and Software Used

[1781] server:

[1782] The server collects and analyzes feedback, adjusts the algorithms of the generative AI model, and generates and provides new educational content.

[1783] The server uses a database to store the feedback and generated educational content.

[1784] The server analyzes the feedback using natural language processing technologies such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1785] The server uses OpenAI's GPT-4 and Google's BERT as generative AI models.

[1786] Device:

[1787] The terminal provides an interface for students and teachers to enter feedback.

[1788] The terminal provides an interface for providing the generated educational content to students and teachers.

[1789] User:

[1790] Users (students and teachers) input feedback through the terminals and access the generated educational content.

[1791] Explanation of program processing

[1792] Collecting feedback:

[1793] The server collects feedback from students and teachers via their terminals. For example, a user may enter feedback such as "This teaching material has many diagrams and is easy to understand" using a web form or a mobile application.

[1794] Feedback Analysis:

[1795] The server analyzes the collected feedback using natural language processing technology. For example, it uses the Google Cloud Natural Language API to extract keywords such as "There are many diagrams, so it is easy to understand" from the feedback text.

[1796] Algorithm adjustments:

[1797] The server adjusts the algorithm of the generative AI model based on the analysis results. For example, it changes the parameters of the generative AI model (OpenAI's GPT-4) based on the analysis results and reflects them in future teaching material generation.

[1798] Creating new materials:

[1799] The server uses the tuned algorithm to generate new educational content. For example, the following prompt is input to the generative AI model:

[1800] "Please generate the following mathematics teaching materials. Feedback from students indicates that teaching materials with many diagrams are easier to understand. Please create teaching materials that include the following: how to calculate the area of ​​a triangle, examples and explanations, and lots of diagrams."

[1801] Materials provided by:

[1802] The server provides the generated educational content to students and teachers through terminals, which display links that allow users to access new learning materials.

[1803] Examples

[1804] For example, a user (student) gives feedback about a particular mathematics teaching material, saying, "This teaching material has many diagrams and is easy to understand." The server collects this feedback and uses NLP technology to extract the information that "it has many diagrams and is easy to understand." The server then adjusts the algorithm of the generative AI model so that it uses more diagrams when generating future mathematics teaching materials. New teaching materials are generated and provided to students via their terminals.

[1805] In this way, generative AI models can optimize the learning experience based on student and teacher feedback, providing educational content tailored to individual learning needs.

[1806] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1807] Step 1: Gather feedback

[1808] The server provides a web form and / or a mobile application for collecting feedback.

[1809] The terminal displays an interface for the user to input feedback.

[1810] Users (students and teachers) input their thoughts and evaluations on specific learning materials as feedback.

[1811] Input: Feedback entered by the user (e.g., "This material had many diagrams and was easy to understand").

[1812] Output: Collected feedback data.

[1813] Specific operation: The terminal displays a text box for the user to input feedback, and the server stores the input feedback in a database.

[1814] Step 2: Analyzing feedback

[1815] The server analyzes the collected feedback using natural language processing (NLP) technology.

[1816] The server analyzes the feedback content using the Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1817] Input: Collected feedback data.

[1818] Output: Analysis results (e.g., keyword "There are many diagrams, making it easy to understand").

[1819] What it does: The server sends the feedback text to the API, which extracts important keywords and phrases, and stores the analysis results in a database.

[1820] Step 3: Adjusting the algorithm

[1821] The server adjusts the algorithm of the generative AI model based on the analysis results.

[1822] The server learns the style and structure of learning materials that are rated as easy to understand and reflects this in future learning material generation.

[1823] Input: Analysis results.

[1824] Output: Tuned generative AI model parameters.

[1825] Specific operation: The server changes the parameters of the generative AI model (e.g., OpenAI's GPT-4) based on the analysis results and saves the adjusted model.

[1826] Step 4: Generate new materials

[1827] The server generates new educational content using the tuned algorithm.

[1828] The server stores the generated teaching materials in a database.

[1829] Input: Tuned generative AI model parameters.

[1830] Output:New educational content.

[1831] Specific operation: The server inputs the prompt sentence, "Please generate the following mathematics teaching materials. According to feedback from students, teaching materials with many diagrams are rated as easier to understand. Please create teaching materials that include the following content: how to calculate the area of ​​a triangle, example problems and explanations, and make extensive use of diagrams," into the generative AI model and saves the generated teaching materials in the database.

[1832] Step 5: Provide materials

[1833] The server provides the generated teaching materials to students and teachers via their terminals.

[1834] The terminal provides an interface through which the user can access new educational material.

[1835] Enter: new educational content.

[1836] Output: A link to the educational material that users can access.

[1837] Specific operation: The server sends the URL of the generated educational material to the terminal, and the terminal displays a link that allows the user to access the educational material.

[1838] (Application example 2)

[1839] Next, a description will be given of Application Example 2 of Form 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".

[1840] Conventional educational platforms have had difficulty effectively utilizing feedback from students and teachers to optimize the learning experience. In addition, there was a lack of systems that automatically generated and appropriately delivered educational content tailored to individual learning needs. As a result, problems arose in which students' understanding and learning efficiency declined.

[1841] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, a means for collecting feedback from students and teachers, a means for generating a prompt sentence based on the collected feedback, a means for inputting the prompt sentence into the generative AI model and generating optimal educational content, and a means for delivering the generated educational content. This makes it possible to effectively utilize feedback from students and teachers and automatically generate and deliver optimal educational content according to individual learning needs.

[1842] "Generative AI" is a system that uses artificial intelligence technology to generate new content and data.

[1843] An "educational platform" is an online system that provides educational content and enables learners and educators to communicate with each other.

[1844] "Individual learning needs" are the educational requirements of each student based on his or her specific learning goals and levels of understanding.

[1845] "Educational content" refers to teaching materials and information that students use to learn, and includes formats such as text, video, and audio.

[1846] "Feedback" is any opinion or evaluation provided by a student or teacher that is useful in improving the learning experience or educational content.

[1847] A "prompt sentence" is an input sentence that causes a generative AI to generate a specific output.

[1848] A "generative AI model" is a model that has the specific algorithms and structures of generative AI, and generates new content based on input data.

[1849] "Delivery" refers to the act of providing the generated educational content to students.

[1850] The system for implementing this invention mainly comprises three elements: a server, a terminal, and a user. The specific roles and processes of each element are explained below.

[1851] server

[1852] The server plays a central role in the educational platform that utilizes generative AI. The server includes the following means:

[1853] 1. Means for providing educational content tailored to individual learning needs: The server analyzes students' learning history and performance data and selects educational content that best suits their individual learning needs.

[1854] 2. A means for students and teachers to communicate with the generative AI: The server provides a chatbot and interactive interface that allows students and teachers to interact directly with the generative AI.

[1855] 3. A means to provide a customized learning experience: The server uses the collected data to suggest the optimal learning path for each student.

[1856] 4. Means of collecting feedback from students and teachers: The server provides feedback forms and surveys within the application to collect feedback from students and teachers.

[1857] 5. Means for generating prompt sentences based on collected feedback: The server analyzes the collected feedback and generates prompt sentences to input into the generative AI model.

[1858] 6. A means for inputting a prompt sentence into a generative AI model and generating optimal educational content: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and generates optimal educational content.

[1859] 7. Means for distributing the generated educational content: The server distributes the generated educational content to the student's terminal.

[1860] Terminal

[1861] A device is a device used by a student or teacher, such as a smartphone, tablet, or computer. A device has the following capabilities:

[1862] 1. Display of educational content: The terminal displays the educational content delivered from the server.

[1863] 2. Entering feedback: The terminal provides an interface for students and teachers to enter feedback.

[1864] 3. Interaction with generative AI: The device provides an interface that allows interaction with the generative AI.

[1865] User

[1866] Users are students and teachers with the following roles:

[1867] 1. Use of educational content: The user studies the educational content provided through the terminal.

[1868] 2. Providing Feedback: Users provide feedback on their learning experience and educational content.

[1869] 3. Interacting with generative AI: The user interacts with the generative AI to convey questions and requests.

[1870] Examples

[1871] For example, if Student A uses a mathematics textbook and provides feedback such as "This textbook was very easy to understand," the server collects this feedback and generates the following prompt:

[1872] Use the feedback below to generate the best educational content.

[1873] Student ID: 1, Material ID: 101, Feedback: This material was very easy to understand.

[1874] The server inputs this prompt sentence into the generative AI model to generate new educational content, which is then distributed to Student A's device.

[1875] In this way, a system is realized in which servers, terminals, and users work together to generate and distribute optimal educational content based on feedback.

[1876] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1877] Step 1:

[1878] The server collects feedback from students and teachers. Specifically, it collects opinions and evaluations from users using feedback forms and questionnaires provided through their terminals. The input is the feedback data entered by the users, and the output is the feedback data stored in the server.

[1879] Step 2:

[1880] The server analyzes the collected feedback data. Specifically, it analyzes the content of the feedback using natural language processing technology and extracts important keywords and evaluation points. The input is the collected feedback data, and the output is the analyzed feedback information.

[1881] Step 3:

[1882] The server generates a prompt sentence based on the parsed feedback information. Specifically, it uses an algorithm that automatically generates a prompt sentence that reflects the content of the feedback. The input is the parsed feedback information, and the output is the generated prompt sentence.

[1883] Step 4:

[1884] The server inputs the generated prompt sentence into the generative AI model. Specifically, the server sends the prompt sentence to the generative AI model (e.g., OpenAI's GPT-3) and has it generate optimal educational content. The input is the generated prompt sentence, and the output is the educational content returned from the generative AI model.

[1885] Step 5:

[1886] The server distributes the generated educational content to the student's device. Specifically, it converts the generated educational content into an appropriate format and sends it to the student's device. The input is the educational content returned from the generative AI model, and the output is the educational content displayed on the student's device.

[1887] Step 6:

[1888] The terminal displays the distributed educational content. Specifically, the educational content received from the server is displayed on the screen so that the student can study. The input is the educational content distributed from the server, and the output is the educational content displayed on the terminal screen.

[1889] Step 7:

[1890] The user studies the displayed educational content and provides feedback. Specifically, the user enters his / her opinion or evaluation of the studied content into a feedback form and transmits it to the server. The input is the feedback entered by the user, and the output is the feedback data transmitted to the server.

[1891] In this way, a system is realized in which servers, terminals, and users work together to generate and distribute optimal educational content based on feedback.

[1892] Example 3

[1893] Next, a third embodiment of the third embodiment will be described. 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".

[1894] With conventional educational platforms, it was difficult to provide educational content tailored to the needs of individual learners. In addition, there was a lack of a mechanism to accurately grasp the learner's level of understanding and provide appropriate learning materials based on that. This resulted in a decrease in the learner's learning efficiency, and there was an issue that effective learning could not be achieved.

[1895] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1896] In this invention, the server includes a means for collecting learning history data, a means for saving the collected learning history data, a means for analyzing the saved learning history data, a means for generating personalized educational content based on the analysis results, a means for providing the generated educational content, and a means for feeding back the learning results, thereby making it possible to provide educational content tailored to the needs of individual learners.

[1897] "Learning History Data" means a record of all learning activities conducted by a Student on the Learning Platform.

[1898] The "means for storing" is a function for storing the collected learning history data in a storage device such as a database.

[1899] "Means of analysis" refers to a function that analyzes saved learning history data and evaluates students' level of understanding and learning progress.

[1900] "Means for generation" is a function for creating personalized educational content based on the analysis results.

[1901] The "means of providing" refers to the function of transmitting the generated educational content to the student's terminal and displaying it.

[1902] "Means of feedback" is a function that collects the results of students' learning and sends them to a server to be used for the next learning.

[1903] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new content or information based on input data.

[1904] A "prompt" is text that is used to input specific instructions or questions to a generative AI model.

[1905] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1906] The present invention relates to an educational platform that provides educational content tailored to the needs of individual learners. A specific embodiment of this system will be described below.

[1907] 1. Program Generation

[1908] The server generates the program for the educational platform. This program analyzes students' learning history and comprehension levels and provides personalized educational content. The hardware used includes the server, database, and student devices (tablets and PCs). The software uses a generative AI model (for example, OpenAI's GPT-4).

[1909] 2. Program Processing Explanation

[1910] The server collects students' learning history data and stores it in a database. The server then uses a generative AI model to analyze the students' learning history and comprehension. This analysis includes information such as what problems the students have tackled in the past, which problems they struggled with, and how well they have understood the material.

[1911] The server generates personalized educational content based on the analysis results. For example, if it detects that a student is struggling with fraction addition, the server generates instructional materials focused on fraction addition. The instructional materials can be in the form of text, images, videos, etc.

[1912] The terminal (e.g., a tablet or PC used by a student) receives the personalized educational content sent from the server and displays it to the student. The student studies the teaching materials provided through the terminal.

[1913] 3. Examples of concrete examples and prompts

[1914] As a concrete example, consider a case where Student A is struggling with fraction addition. The server analyzes Student A's learning history and detects that Student A has a low level of understanding regarding fraction addition. The server then uses a generative AI model to generate teaching materials focused on fraction addition. The teaching materials include everything from basic concepts to applied problems of fraction addition.

[1915] Here is an example of a prompt to be input to the generative AI model:

[1916] "After analyzing Student A's learning history, we found that he is struggling with fraction addition. Please generate teaching materials that cover everything from basic concepts to applied problems related to fraction addition."

[1917] By inputting this prompt sentence into the generative AI model, personalized educational content is generated. The server sends this content to the terminal and provides it to Student A.

[1918] As described above, the present invention is capable of providing educational content optimized for each learner by combining the means for collecting, storing, and analyzing learning history data, and for generating, providing, and providing feedback on content. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1919] Step 1: Collect learning history data

[1920] The server records all learning activities that students perform on the learning platform. Specifically, it collects information in real time, such as the problems students solve, the videos they watch, and the materials they read. The input is the students' learning activities, and the output is the collected learning history data.

[1921] Step 2: Save learning history data

[1922] The server stores the collected learning history data in a database. Specifically, it creates an individual database entry for each student and stores the collected data. The input is the collected learning history data, and the output is the data stored in the database.

[1923] Step 3: Analyze learning history data

[1924] The server inputs the saved learning history data into the generative AI model and analyzes the student's level of understanding. Specifically, the server inputs a prompt statement to the generative AI model saying, "Analyze the student's learning history and identify weak areas." The input is the saved learning history data and the prompt statement, and the output is the analysis result regarding the student's level of understanding.

[1925] Step 4: Generate personalized educational content

[1926] Based on the analysis results, the server inputs a prompt sentence into the generative AI model to generate personalized educational content. Specifically, the prompt sentence is "Please generate teaching materials that include everything from basic concepts to applied problems regarding fraction addition." The input is the analysis results and the prompt sentence, and the output is the generated educational content.

[1927] Step 5: Provide educational content

[1928] The server transmits the generated educational content to the student's terminal. The terminal displays the received educational content to the student. Specifically, the educational material is displayed on a tablet or PC so that the student can study. The input is the generated educational content, and the output is the educational material displayed on the terminal.

[1929] Step 6: Feedback on learning results

[1930] The user (student) studies the teaching materials provided through the terminal and solves the practice problems. The answer is sent to the server, and the server updates the learning history data again. Specifically, the correct answer rate and answer time of the problem solved by the student are recorded and saved in a database. The input is the student's answer, and the output is the updated learning history data.

[1931] (Application example 3)

[1932] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1933] Conventional educational platforms have difficulty in providing educational content tailored to the needs of individual learners, and there has been a lack of personalized education, particularly in the area of ​​maintenance work for technicians. In addition, efficient learning has been difficult because educational content is not provided that takes into account the technician's past maintenance history or level of understanding.

[1934] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1935] In this invention, the server is an educational platform that utilizes generative AI and includes a means for providing educational content tailored to individual learning needs, a means for students and teachers to communicate with the generative AI, a means for providing a customized learning experience, and a means for analyzing the maintenance history and level of understanding of a technician and generating personalized maintenance educational content based thereon. This makes it possible to provide personalized educational content based on the technician's past maintenance history and level of understanding.

[1936] "Generative AI" is a system that uses artificial intelligence technology to analyze data and automatically generate new content and information.

[1937] An "educational platform" is a system that provides an online or offline educational environment for use by learners and educators.

[1938] "Individual learning needs" are the educational requirements of each learner based on their specific learning goals and levels of understanding.

[1939] "Educational content" refers to teaching materials and information that students use to learn, including text, video, and interactive materials.

[1940] "Means of communication" are the methods and tools that learners and educators use to interact with and exchange information with generative AI.

[1941] A "customized learning experience" is an educational experience that is tailored to a learner's individual needs and level of understanding.

[1942] "Technician" refers to a professional who has specific skills and techniques and performs maintenance work, etc.

[1943] "Maintenance history" is a record of past maintenance work performed by a technician.

[1944] "Understanding" refers to the degree to which a learner or technician has understood a particular piece of knowledge or skill.

[1945] "Individualized maintenance training content" refers to training materials that are specially created based on a technician's maintenance history and level of understanding.

[1946] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server provides an educational platform that utilizes generative AI and generates educational content tailored to individual learning needs. The terminal is a device that allows the user to communicate with the server and receive the generated educational content. The user is an engineer or a learner, and uses the educational content through the terminal.

[1947] Server Processing

[1948] The server operates using the following hardware and software:

[1949] Hardware: A server machine with a powerful processor, sufficient memory, and storage.

[1950] Software: Python, Pandas, Scikit-learn, Transformers (Hugging Face)

[1951] The server first loads technician maintenance history data from a CSV file, then uses Scikit-learn's KMeans clustering algorithm to analyze technician maintenance histor...

Claims

1. An educational platform utilizing generative AI, which provides educational content tailored to individual learning needs; A means for at least one of the student and teacher to communicate with the generative AI; A means to provide a customized learning experience; and means for collecting feedback from students and / or teachers; A means for generating a prompt sentence instructing the generation of optimal educational content based on the collected feedback; A means for inputting the prompt sentence into the generating AI and generating optimal educational content; A means for delivering the generated educational content; A system including:

2. The system of claim 1 , wherein the generative AI automatically generates educational content based on learning needs of at least one of students and teachers.

3. 10. The system of claim 1, wherein the generative AI optimizes the learning experience based on feedback from students and / or teachers.

Images