System

Abstract

A system is provided.SOLUTION: A system, comprising: means for optimizing educational content based on a learning style and a learning pace of a learner using an artificial intelligence model; means for selecting appropriate educational content based on the learning style and the learning pace; and means for providing the selected educational content to the learner.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] The traditional one-size-fits-all approach to education has limited effectiveness because it is unable to fully accommodate the learning styles and pace of individual learners. Furthermore, there is insufficient collaboration with educational institutions, making it difficult to provide content that is adapted to regional educational regulations. As a result, learners' learning efficiency is not improving. [Means for solving the problem]

[0005] The present invention provides a means for optimizing educational content based on a learner's learning style and pace using an artificial intelligence model, and a means for selecting appropriate educational content based on the learning style and pace. It also includes a means for providing the selected educational content to the learner. The present invention is characterized by emphasizing partnerships with educational institutions and adapting the provided content to regional educational regulations. This makes it possible to provide learners with an effective and personalized learning experience and improve learning efficiency.

[0006] An "artificial intelligence model" is an algorithm that analyzes learner data and selects appropriate educational content.

[0007] A "learning style" is a characteristic that describes how an individual learner learns most effectively. Examples include visual, auditory, and tactile learning styles.

[0008] "Learning pace" refers to the speed at which a learner feels comfortable learning. Examples include fast, normal, and slow paces.

[0009] "Educational content" refers to the learning materials and resources used by learners, including, for example, lessons, videos, quizzes, and textbooks.

[0010] "Optimization" refers to adjusting something to bring out the best performance under given conditions.

[0011] "Educational institution" refers to an organization that provides education, such as a school, university, or college.

[0012] A "partnership" refers to the collaboration of two or more organizations for a common purpose.

[0013] "Region-specific education regulations" refers to education laws, regulations, and guidelines established by a particular region or country. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] 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.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] 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.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] 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.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for each learner's learning style and pace.

[0036] System configuration

[0037] server

[0038] 1. The server stores the learner's information in a database.

[0039] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace.

[0040] 3. The server trains the AI ​​model and generates optimal educational content using the learner's historical data and real-time learning data.

[0041] 4. The server provides personalized educational content when accessed by the learner.

[0042] User

[0043] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[0044] 2. Learners input their learning style (e.g., visual, auditory) and learning pace (e.g., fast, normal, slow).

[0045] 3. Learners submit requests for desired educational content (e.g., math, science).

[0046] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[0047] Terminal

[0048] 1. The terminal receives input information from the learner and sends it to the server.

[0049] 2. The terminal displays the personalized educational content sent from the server.

[0050] Explanation of program processing

[0051] 1. Initialize the server:

[0052] The server loads learning content, such as math and science lessons, and trains the AI ​​model.

[0053] 2. Learner Registration:

[0054] Users (learners) register their learning style and pace with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[0055] 3. Learning content requests:

[0056] When a user logs into the learning platform and requests specific educational content, the server selects the most appropriate educational content to suit the user's learning style and pace.

[0057] 4. Providing personalized learning content:

[0058] The server uses the AI ​​model to generate optimized educational content and sends it back to the user, who then displays it on their device.

[0059] Specific examples

[0060] For example, if a user requests "Math" content, the server verifies that the user's learning style is registered as "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model to search for math lessons that are suitable for a visual and fast-paced learning style. The server then selects an appropriate lesson (e.g., "Math: Lesson 1") and sends it to the user's device. The user can then efficiently progress through this lesson.

[0061] In this way, this platform can provide educational content optimized to the needs of each individual learner, improving learning efficiency.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model.

[0065] Step 2:

[0066] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[0067] Step 3:

[0068] The server trains the AI ​​model, which contains algorithms for selecting the most appropriate educational content based on learner data.

[0069] Step 4:

[0070] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[0071] Step 5:

[0072] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[0073] Step 6:

[0074] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[0075] Step 7:

[0076] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[0077] Step 8:

[0078] The server generates personalized educational content selected by the AI ​​model and sends it to the device.

[0079] Step 9:

[0080] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[0081] Step 10:

[0082] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model, enabling more effective personalization.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] Conventional educational systems have the problem of being unable to provide educational content optimized for each learner's learning style and pace. This reduces learners' learning efficiency and makes it difficult to maintain their interest and motivation. Furthermore, there is a lack of a mechanism for instantly providing the educational content requested by learners, making it impossible to provide a fast and appropriate learning experience. Furthermore, the cost and effort required to deal with the technical complexity of individually optimizing educational content is also a major issue.

[0086] 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.

[0087] In this invention, the server includes means for loading educational data and training a generative AI model to classify optimal learning styles and paces, means for a learner to input and save their learning style and learning pace from a terminal, and means for selecting and providing personalized educational content using the generative AI model when a learner requests specific educational content, thereby enabling educational content optimized for the individual needs of each learner to be provided quickly and appropriately.

[0088] A "server" is a device that stores learner information, loads educational data, trains generative AI models, and provides personalized educational content requested by learners.

[0089] A "generative AI model" is a model that uses artificial intelligence technology to optimize educational content and select appropriate content based on the learner's learning style and pace.

[0090] "Learning style" refers to the way in which a learner absorbs knowledge most efficiently, such as visual or auditory.

[0091] "Learning pace" refers to the speed at which a learner can most efficiently progress through their studies, such as fast, normal, or slow.

[0092] "Educational content" is a general term for the teaching materials and lessons that learners use to learn, and is provided in the form of video, audio, text, etc.

[0093] A "terminal" is a device used by a learner to access the server, log in, request content, and view received content.

[0094] A "database" is a system for efficiently storing and managing data such as learner information, learning style, and pace.

[0095] "Classification" means organizing educational content based on collected data according to the learner's learning style and pace and dividing it into appropriate categories.

[0096] The present invention is an educational system that provides personalized educational content based on the learner's learning style and pace. This system is mainly composed of a server, a terminal, and a user. The specific configuration and operation are described below.

[0097] server

[0098] The server loads educational data from Amazon S3 and uses the training data to build a generative AI model (e.g., using TensorFlow). The server stores learner information (learning style and pace) in a MySQL database. The server also categorizes the educational content requested by the learner and selects and provides the appropriate content.

[0099] Loading training data and training the AI ​​model

[0100] The server downloads educational content from Amazon S3, for example, contained in a folder called "math_lessons," locally, and uses TensorFlow to train a generative AI model that determines the optimal learning style and pace based on past learning data.

[0101] User Roles

[0102] Users (learners) access the platform using their terminals and log in. After logging in, users input and set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow). This information is stored in a database by the server.

[0103] Educational Content Requests

[0104] The user selects the desired educational content (e.g., mathematics, science) from the platform menu, clicks the request button, and the device sends the request to the server in HTTPS format.

[0105] Response from the server

[0106] The server receives the learner's request and uses a trained generative AI model to select the most appropriate educational content, which is then sent back to the device.

[0107] Device behavior

[0108] The device receives the response sent from the server and displays appropriate educational content, for example, playing video educational content for visual and fast-paced learners.

[0109] Specific operation example

[0110] For example, if a user requests "Math" content, the server uses an AI model to determine that the user has a visual, fast-paced learning style. The content "interactive_math_lesson_1.mp4" is selected and sent from the server to the device. The device then displays this video to the user, helping them learn more efficiently.

[0111] Prompt Sentence Examples

[0112] For example, a user can request on a learning platform, "Can you provide me with fast-paced visual lessons in math?" and the server can select and provide the most appropriate content.

[0113] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1: Initialize the server

[0116] Server behavior:

[0117] When the server is powered on, it boots up an OS (e.g., Ubuntu). The server loads educational content from Amazon S3 and downloads training data locally. Specifically, all content in the "math_lessons" folder stored in Amazon S3 is downloaded. Next, the server uses TensorFlow to train a generative AI model. The training data includes data on past learning history and learning style. The server uses this data to generate a model that classifies learning style and pace.

[0118] Input: Educational content, past learning history data

[0119] Data processing & calculation: Download data and train AI models

[0120] Output: A trained generative AI model

[0121] Step 2: Enroll learners

[0122] User Action:

[0123] Users use their devices to access the platform's login page and enter their authentication information (username, password) to log in. After logging in, users are taken to a dashboard screen where they can set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow).

[0124] Server behavior:

[0125] The server receives the learning style and pace sent by the learner and stores them in a MySQL database. Specifically, it stores the data in the corresponding columns in the table that stores user information.

[0126] Input: Learner style and pace information

[0127] Data processing and calculation: Receiving data and saving it to the database

[0128] Output: Saved learner information

[0129] Step 3: Request learning content

[0130] User Action:

[0131] The user selects a specific educational content (e.g., mathematics) from the platform's menu and submits a request for the educational content by clicking a request button, which sends the request to the server.

[0132] Terminal behavior:

[0133] The device sends the learner's request to the server as an HTTPS request, for example, calling the endpoint " / request-content?subject=math".

[0134] Input: User request for educational content

[0135] Data processing & calculation: Sending a request

[0136] Output: Request data to the server

[0137] Step 4: Select and deliver personalized learning content

[0138] Server behavior:

[0139] The server receives the learner's request. The request data also includes the learner's learning style and pace. Based on the saved learning style and pace information, the server uses a generative AI model to select the most suitable educational content. For example, it determines that the content "interactive_math_lesson_1.mp4" is most suitable for a "visual" and "fast-paced" learner. Based on this selection result, the server generates a response including the content ID and password and sends it to the device.

[0140] Input: Request data from user, learning style and pace information

[0141] Data processing & calculation: Content selection and response generation using AI models

[0142] Output: Response data for selected educational content

[0143] Step 5: Display educational content

[0144] Terminal behavior:

[0145] The device receives the response from the server and displays the corresponding educational content by launching a video player and streaming a file such as "interactive_math_lesson_1.mp4."

[0146] Input: Response data from the server

[0147] Data processing & calculation: Response analysis, content display

[0148] Output: The educational content displayed to the learner

[0149] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[0150] (Application example 1)

[0151] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0152] With conventional education platforms, it was difficult to provide educational content that was optimized for each learner's individual learning style and pace.In addition, when it came to training workers on factory floors, there was a lack of technology to provide training methods that were suited to each worker, making it difficult to efficiently improve their skills and ensure safe work.

[0153] 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.

[0154] In this invention, the server includes means for optimizing educational content based on the learning style and learning pace of a learner using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace, means for providing the selected educational content to the learner, and means including a factory robot for providing optimal training content based on the learning style and learning pace of a worker, thereby enabling the provision of optimal educational and training content according to the individual needs of the learner and worker.

[0155] An "artificial intelligence model" refers to an algorithm that uses large amounts of data to learn patterns and make predictions and classifications.

[0156] "Learning style" refers to the way in which a learner most effectively perceives information, and can include visual, auditory, tactile, etc.

[0157] "Learning pace" refers to the speed at which a learner absorbs and comprehends information, and can include fast, normal, or slow.

[0158] "Educational content" refers to information and materials provided to learners, including text, video, audio, illustrations, etc.

[0159] "Optimization means" refers to the process of using artificial intelligence models and algorithms to select educational content with the optimal format and content that suits the learner's learning style and pace.

[0160] "Means of selection" refers to a method or system for extracting from multiple educational contents the one that best suits the learner's requirements.

[0161] "Means of delivery" refers to the means for delivering the selected educational content to learners, including delivery via the Internet and downloads.

[0162] A "factory robot" is a mechanical device designed to perform various tasks within a factory, and is capable of providing training content to workers.

[0163] The present invention is a system for providing educational content optimized to the individual needs of learners and factory workers. Specific embodiments of this system will be described below.

[0164] Hardware and Software Configuration

[0165] The server has the following responsibilities:

[0166] 1. Database: Stores information about learners and workers. Specifically, a database such as MySQL is used.

[0167] 2. Loading educational content: Loading and categorizing pre-prepared educational content.

[0168] 3. Training artificial intelligence models: Using software such as TensorFlow, AI models are trained using historical and real-time data from learners and workers.

[0169] 4. Generate and deliver optimal content: Generate optimal educational content based on the learning style and pace of learners and workers, and deliver personalized content.

[0170] Terminals are devices that students and workers use to communicate with the server, and can be PCs, smartphones, tablets, or factory robots.

[0171] Processing Details

[0172] The server receives input from learners and workers and uses the AI ​​model to generate optimized educational content based on that information. Specifically, if visual learning is effective, content that is easy to understand visually will be generated, and for workers who learn at a fast pace, short sessions will be selected to enable efficient learning.

[0173] Learners and workers input their own learning style and pace from their devices and select the educational content they want. This information is sent to the server, which then generates optimized educational content and distributes it to the devices.

[0174] Specific operations

[0175] For learners

[0176] 1. Learners access the platform using their devices and log in.

[0177] 2. Learners input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[0178] 3. Learners request the educational content they want (math, science, etc.).

[0179] For example, if a visual, fast-paced learner requests "Math" content, the following will happen:

[0180] The server uses AI models to select visual, fast-paced math lessons.

[0181] Generate content that includes visually easy-to-understand heat maps, diagrams, and short video clips.

[0182] The generated content is provided to the learner's device to advance their learning.

[0183] For workers

[0184] 1. The worker logs in using the factory robot's interface.

[0185] 2. Workers input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[0186] 3. Workers request the training content they desire (e.g., safe operations, quality control, etc.).

[0187] For example, if a fast visual learner requests "Quality Control Training," the following happens:

[0188] The robot receives visual, fast-paced, quality-controlled training content from the server.

[0189] The robot displays heat maps and diagrams that are easy for workers to understand visually, guiding them to important checkpoints.

[0190] Workers will follow the robot's instructions as they go through the training.

[0191] Example prompts to input to the generative AI model

[0192] "Provide optimal quality control training content for factory workers who are fast-paced visual learners."

[0193] "We will provide training on safe operation using audio guidance. Please also explain in detail the precautions to take."

[0194] In this way, the system of the present invention can generate and provide optimal education and training content tailored to the individual needs of learners and workers, thereby enabling efficient and effective education and training.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The server stores information about learners and workers in a database, including their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow), forming the basis for providing educational content optimized to the individual needs of each learner and worker.

[0198] Step 2:

[0199] The server loads pre-prepared educational content and categorizes it according to each learning style and pace. Specifically, it categorizes lessons such as math and science into visually and aurally easy-to-understand content, and stores each content in a database. This prepares the content for efficient delivery.

[0200] Step 3:

[0201] The server collects historical data and real-time learning data from learners and workers to train the AI ​​model. Using software such as TensorFlow, the model is trained to generate optimal educational content based on the characteristics of learners and workers. This AI model functions as an algorithm that processes the data and makes predictions and classifications.

[0202] Step 4:

[0203] Learners and workers access the platform and log in using a device (such as a PC, smartphone, or factory robot). The device receives the user's input information and sends it to the server. The server then imports the received learning style and pace information into a database and uses it to generate personalized content.

[0204] Step 5:

[0205] Learners and workers submit requests for the educational content they desire (mathematics, science, safe operations, quality control, etc.). The request is sent from the device to the server, which uses an AI model to generate the optimal educational content based on the request, learning style, and pace.

[0206] Step 6:

[0207] The server uses the AI ​​model to generate optimized educational content and transmit it to the device. Specifically, it selects training content that is easy to understand visually, including heat maps, diagrams, and audio guidance, and outputs the results.

[0208] Step 7:

[0209] The terminal receives the personalized educational content sent from the server and displays it to the learner and worker, allowing the learner and worker to progress with their studies using the optimized content.

[0210] In this way, it is possible to provide individualized and optimal education and training to learners and workers through each step.

[0211] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0212] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for a learner's learning style, learning pace, and emotions. A specific embodiment of this system is described below.

[0213] System configuration

[0214] server

[0215] 1. The server is responsible for storing learner information in a database.

[0216] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace, and also obtains emotional information using an emotion engine.

[0217] 3. The server trains the AI ​​model and emotion engine, and generates optimal educational content using the learner's historical data, real-time learning data, and emotion data.

[0218] 4. The server provides personalized educational content when accessed by the learner.

[0219] User

[0220] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[0221] 2. Learners input or provide learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and real-time emotional information (e.g., happy, sad, excited).

[0222] 3. Learners submit requests for desired educational content (e.g., math, science).

[0223] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[0224] Terminal

[0225] 1. The terminal receives input information and real-time emotional information from the learner and transmits it to the server.

[0226] 2. The terminal displays the personalized educational content sent from the server.

[0227] Explanation of program processing

[0228] 1. Initialize the server:

[0229] The server loads learning content and trains the AI ​​model and emotion engine, including lessons in math and science, catering to multiple learning styles, including visual and auditory.

[0230] 2. Learner Registration:

[0231] Users (learners) register their learning style and pace, as well as initial emotional data, with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[0232] 3. Learning content requests:

[0233] A user logs into a learning platform and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[0234] 4. Acquiring learners' emotional information:

[0235] The server uses an emotion engine to recognize the learner's emotional information in real time, thereby understanding the learner's emotional state during learning.

[0236] 5. Providing personalized learning content:

[0237] The server takes into account the learner's learning style and pace, as well as emotional information, and uses an AI model and emotional engine to generate optimized educational content, which is then sent to the device.

[0238] 6. Display of educational content:

[0239] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their studies.

[0240] Specific examples

[0241] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[0242] In this way, this platform can provide educational content optimized to the needs of individual learners, improving learning efficiency. By combining it with an emotion engine, it is possible to provide a more highly personalized learning experience.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model and emotion engine.

[0246] Step 2:

[0247] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[0248] Step 3:

[0249] The server trains the AI ​​model and emotion engine. The AI ​​model contains algorithms for selecting optimal educational content based on learner data. The emotion engine collects and analyzes user emotion data in real time.

[0250] Step 4:

[0251] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[0252] Step 5:

[0253] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[0254] Step 6:

[0255] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[0256] Step 7:

[0257] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[0258] Step 8:

[0259] The server uses an emotion engine to recognize the user's emotional information in real time, for example, by analyzing the user's facial expressions and tone of voice through the user's webcam and microphone.

[0260] Step 9:

[0261] The server further optimizes the educational content selected by the AI ​​model based on the acquired emotional information, thereby adjusting the content format and difficulty level according to the user's emotional state.

[0262] Step 10:

[0263] The server generates optimized and personalized educational content and transmits it to the terminal.

[0264] Step 11:

[0265] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[0266] Step 12:

[0267] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model and emotion engine, enabling more effective personalization.

[0268] Example 2

[0269] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0270] The present invention aims to solve the problem that it is difficult for conventional educational platforms to provide educational content that is tailored to the learner's learning style and pace, as well as to provide individually optimized educational content that takes into account real-time emotional data during learning. Specifically, there is a need to grasp the learner's emotional state in real time and dynamically adjust educational content accordingly.

[0271] 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.

[0272] In this invention, the server includes: means for optimizing educational content based on a learner's learning style, learning pace, and emotional data using an artificial intelligence model; means for selecting appropriate educational content based on the learning style, learning pace, and emotional data; means having an emotion engine for acquiring and analyzing the learner's emotional data in real time; and means for providing the selected educational content to the learner. This not only provides optimal educational content tailored to the learner's learning style and pace, but also enables a more highly personalized learning experience that responds to the learner's emotional state during learning.

[0273] An "artificial intelligence model" is a computer program that analyzes data and learns patterns to make predictions and decisions.

[0274] "Learning style" refers to the method or approach that a learner uses to most effectively comprehend and acquire information, such as visual learning or auditory learning.

[0275] "Learning pace" refers to how quickly a learner can digest and understand educational content, and can be categorized as fast, normal, or slow.

[0276] "Educational Content" includes teaching materials and resources designed to teach a particular academic subject or skill, such as mathematics lessons or science experiment guides.

[0277] "Emotional data" is information that indicates the learner's current emotional state, including happiness, sadness, excitement, etc.

[0278] An "emotion engine" is software or a system that analyzes and recognizes a learner's real-time emotional state.

[0279] "Optimization" refers to adjusting a system or process to maximize performance or efficiency in order to achieve a specific purpose.

[0280] "Selection" is the act of selecting the most appropriate option from multiple choices or options.

[0281] "Provision" refers to the act of the system providing the necessary information or services to the user.

[0282] This invention is an educational platform that utilizes artificial intelligence (AI) models to provide educational content optimized for a learner's learning style, learning pace, and emotional data. This platform is composed of a server, a terminal, and a user.

[0283] Server Features

[0284] 1. Training the AI ​​model and emotion engine

[0285] The server uses artificial intelligence models to learn from learner data and optimize educational content. It also uses an emotion engine to analyze learner emotion data in real time. The main software used includes AI models such as TensorFlow and PyTorch, and emotion engines such as Affectiva and IBM Watson Emotion Analysis.

[0286] 2. Loading and optimizing learning content

[0287] The server loads pre-prepared learning content, including lessons in subjects like math and science, and caters to visual and auditory learning styles, allowing the server to optimize educational content based on learning style, learning pace, and emotional data.

[0288] 3. Data storage and content provision

[0289] The server stores learners' learning style, learning pace, and initial emotional data in a database and uses it to provide personalized learning experiences. This is done using cloud data services such as Amazon Web Services (AWS). The server then transmits optimized educational content to the device, where it can be accessed by the user.

[0290] Device Features

[0291] The device (PC or smartphone) receives learner input information and emotional data collected in real time and sends it to the server. The device also plays a role in displaying personalized educational content sent from the server to the user.

[0292] User operations

[0293] Users (learners) access the platform using their devices and log in. They input their learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data (e.g., happy, sad, excited). They then submit a request for the educational content they desire (e.g., math, science). The server processes this request and provides optimized content.

[0294] Specific examples

[0295] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[0296] Prompt Sentence Examples

[0297] Learning style: "I'm a visual learner."

[0298] Learning pace: "I like to learn at a fast pace."

[0299] Emotional information: "I feel excited right now."

[0300] In this way, the platform of the present invention can provide educational content tailored to the individual needs of learners, greatly improving learning efficiency.

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Specific flow of program processing

[0303] Step 1: Initialize the server

[0304] The server loads learning content (e.g., math and science lessons). This includes content for multiple learning styles, such as visual and auditory learning. The hardware used is a cloud server, and the software is a database management system. The input is a set of files containing educational content prepared in advance, and the output is information indicating that the learning data has been loaded.

[0305] Specific behavior:

[0306] The server downloads the educational content from the cloud storage.

[0307] Load content into a database and categorize it by style.

[0308] Step 2: Training the AI ​​model and emotion engine

[0309] The server trains the AI ​​model and emotion engine using the learner's historical data and pre-prepared data. The software used is TensorFlow, PyTorch, Affectiva, and IBM Watson Emotion Analysis. The input is past learning data and emotion data, and the output is the trained model.

[0310] Specific behavior:

[0311] Cleanse historical and sentiment data and prepare it for machine learning.

[0312] Run the training process for the AI ​​model and emotion engine to set optimal parameters.

[0313] Step 3: Enroll learners

[0314] Users access the platform using their devices and create an account or log in. The input is the user's learning style, learning pace, and initial emotional data, and the output is a learner profile stored in a database.

[0315] Specific behavior:

[0316] The user inputs learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data from the terminal.

[0317] The server stores this information in a database.

[0318] Step 4: Request learning content

[0319] A user requests a specific educational content (e.g., mathematics). The request is sent from the device and processed by the server. The input is the user's content request, and the output is a confirmation that the request was received.

[0320] Specific behavior:

[0321] The user selects a particular educational content from the terminal and sends a request to the server.

[0322] The server receives the request and begins searching for the appropriate content.

[0323] Step 5: Obtaining learners' emotional information

[0324] The server uses an emotion engine to obtain the learner's emotional data in real time. The input is the user's current emotional information (e.g., facial recognition data, voice data), and the output is the analyzed emotional data.

[0325] Specific behavior:

[0326] The server receives emotional state data (facial recognition, voice analysis, etc.) sent from the user's device.

[0327] The emotion engine analyzes the data and identifies the emotional state (e.g., excitement, sadness).

[0328] Step 6: Deliver personalized learning content

[0329] The server takes into account the learning style and pace, as well as the acquired emotional data, to generate optimal educational content. The input is the learner profile stored on the server and real-time emotional data, and the output is optimized educational content.

[0330] Specific behavior:

[0331] The server uses AI models to generate optimal learning content, taking into account learning style, learning pace, and emotional data.

[0332] The content is sent to the terminal and made available to the user.

[0333] Step 7: Display educational content

[0334] The terminal receives the educational content sent from the server and displays it to the user. The input is the educational content sent from the server, and the output is the learning material displayed to the user.

[0335] Specific behavior:

[0336] The terminal receives the educational content transmitted from the server.

[0337] The content is displayed on the screen and users can begin learning.

[0338] In this way, the program's series of processes is meticulously planned to provide educational content optimized to the individual needs of each learner.

[0339] (Application example 2)

[0340] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0341] Traditional educational platforms face the challenge of providing customized educational content that responds to learners' individual learning styles, pace, and real-time emotional states. This makes it difficult to maintain learners' interest and maximize learning efficiency. Furthermore, there is a lack of systems for providing appropriate content to accommodate different learning styles, such as visual and auditory, which can lead to a decline in learning quality.

[0342] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for optimizing educational content based on the learner's learning style and learning pace using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace and real-time emotional data, means for providing the selected educational content to the learner, and means for displaying the optimized educational content on a smart device. This makes it possible to provide educational content optimized to the individual needs of the learner and maximize learning efficiency and interest.

[0343] An "artificial intelligence model" is an algorithm or statistical model that analyzes learner data and selects and generates optimal educational content.

[0344] "Learning style" is a term that refers to the methods or ways in which learners most effectively understand and absorb information.

[0345] "Learning pace" refers to the speed or rhythm at which a learner progresses through learning content.

[0346] "Educational content" refers to materials and information that include learning materials, lessons, exercises, and other learning subjects provided to learners.

[0347] "Real-time emotional data" refers to data capturing the learner's emotional state in real time, including, for example, joy, excitement, or sadness during learning.

[0348] "Smart devices" are electronic devices with internet connectivity that are used by learners, such as computers, smartphones, and smart glasses.

[0349] "Optimize" means to adjust or improve something to be best suited to a specific purpose.

[0350] "To select" means to decide and select a specific object from among many candidates or possibilities.

[0351] "Providing" refers to imparting and distributing necessary information and teaching materials to learners.

[0352] "Display" means to visually show information on the screen of an electronic device or the like.

[0353] A "system" is a complex consisting of multiple elements that interact and cooperate to achieve a specific function or purpose.

[0354] The present invention provides an educational platform that provides educational content optimized to the individual needs of learners. Specific embodiments for carrying out the present invention will be described below.

[0355] System Overview

[0356] The system of the present invention utilizes an artificial intelligence model to optimize educational content based on the learner's learning style, learning pace, and real-time emotional data, and provides it via smart devices. The main components of the system are a server, a terminal (smart device), and a user.

[0357] Hardware and Software Configuration

[0358] Hardware:

[0359] 1. Server: A high-performance computer server

[0360] 2. Smart Devices: Electronic devices with internet connectivity such as smart glasses, smartphones, tablets, etc.

[0361] software:

[0362] 1. Artificial intelligence model: Algorithms using machine learning frameworks such as TensorFlow

[0363] 2. Emotion recognition engine: Emotion analysis software such as EmotionEngine

[0364] 3. Content Management: Database System

[0365] 4. User Profile Management: UserProfile System

[0366] 5. Smart Device API: SmartGlassesAPI, etc.

[0367] Data processing and calculation

[0368] server:

[0369] 1. Initialization: The server loads learning content and trains the AI ​​model and emotion engine. The learning content includes lessons for math and science, for example, and includes content that supports multiple learning styles, such as visual and auditory.

[0370] 2. Acquiring learner information: The server stores the learner's learning style, learning pace, and real-time emotional data in a database, and generates optimal educational content based on this information.

[0371] Terminal (smart device):

[0372] 1. Information collection: The device collects learners' actions and reactions in real time and sends them to the server. This includes data from cameras, sensors, microphones, etc.

[0373] 2. Content display: The terminal displays the optimized educational content sent from the server and provides it to the learner.

[0374] Specific processing examples:

[0375] For example, if a learner is studying "Mathematics" through smart glasses and the emotion engine recognizes the "Excited" state, the server will determine that the learner's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the learner's excited state. The server then selects an appropriate lesson (e.g., "Mathematics: Lesson 3") and sends it to the user's device.

[0376] Example prompt sentence:

[0377] User learning style: Visual

[0378] User learning pace: Fast

[0379] Real-time emotions: excitement

[0380] Requested educational content: Mathematics

[0381] In this way, the system can provide educational content optimized to the needs of each individual learner, maximizing learning efficiency and interest.

[0382] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0383] Step 1:

[0384] Initialize the server:

[0385] The server loads the learning content and trains the artificial intelligence model and emotion engine. Specifically, the server retrieves educational content (e.g., math and science lessons) from the database and uses it as training data for the AI ​​model using a machine learning framework such as TensorFlow. It also trains the emotion recognition model using EmotionEngine. The inputs are the learning content and the initial data for the AI ​​model and emotion engine, and the outputs are the trained AI model and emotion recognition model.

[0386] Step 2:

[0387] User profile settings:

[0388] Users log in to the system and register their learning style, learning pace, initial emotional data, etc. This information is sent to the server via their terminal, and the server stores this information in a database. The input is the learning style, learning pace, and emotional data provided by the user from their terminal, and the output is the user profile information stored in the database.

[0389] Step 3:

[0390] Educational Content Request:

[0391] A user uses a device to request a specific educational content (e.g., mathematics). This request is sent to a server. The input is the content request from the user, and the output is the request data to the server.

[0392] Step 4:

[0393] Acquiring emotional information:

[0394] The server uses the EmotionEngine to obtain the learner's emotional information in real time. It uses the device's camera and microphone to analyze the learner's facial expressions and tone of voice to generate emotional data. The input is real-time camera feed and audio data, and the output is the emotion recognition results.

[0395] Step 5:

[0396] Generate personalized learning content:

[0397] The server generates optimal educational content based on learning style, learning pace, and real-time emotional data. It uses an AI model based on machine learning frameworks such as TensorFlow to analyze this data and select the most appropriate lessons and materials. The input is stored user profile information and real-time emotional data, and the output is optimized educational content.

[0398] Step 6:

[0399] Educational content provided by:

[0400] The server sends the generated optimized educational content to the smart device, which then displays it. The input is the educational content sent from the server, and the output is the learning material displayed on the device.

[0401] Specifically, when a learner requests "math" content through smart glasses, the emotion engine recognizes the "excitement" state. For a learner whose learning style is identified as "visual" and whose learning pace is "fast," the server selects math lessons that correspond to the excitement state appropriate for a visual and fast pace and displays them on the smart glasses.

[0402] Example prompt sentence:

[0403] User learning style: Visual

[0404] User learning pace: Fast

[0405] Real-time emotions: excitement

[0406] Requested educational content: Mathematics

[0407] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 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.

[0413] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] 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.

[0415] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0417] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0418] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0419] 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.

[0420] 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.

[0421] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0422] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0423] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for each learner's learning style and pace.

[0424] System configuration

[0425] server

[0426] 1. The server stores the learner's information in a database.

[0427] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace.

[0428] 3. The server trains the AI ​​model and generates optimal educational content using the learner's historical data and real-time learning data.

[0429] 4. The server provides personalized educational content when accessed by the learner.

[0430] User

[0431] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[0432] 2. Learners input their learning style (e.g., visual, auditory) and learning pace (e.g., fast, normal, slow).

[0433] 3. Learners submit requests for desired educational content (e.g., math, science).

[0434] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[0435] Terminal

[0436] 1. The terminal receives input information from the learner and sends it to the server.

[0437] 2. The terminal displays the personalized educational content sent from the server.

[0438] Explanation of program processing

[0439] 1. Initialize the server:

[0440] The server loads learning content, such as math and science lessons, and trains the AI ​​model.

[0441] 2. Learner Registration:

[0442] Users (learners) register their learning style and pace with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[0443] 3. Learning content requests:

[0444] When a user logs into the learning platform and requests specific educational content, the server selects the most appropriate educational content to suit the user's learning style and pace.

[0445] 4. Providing personalized learning content:

[0446] The server uses the AI ​​model to generate optimized educational content and sends it back to the user, who then displays it on their device.

[0447] Specific examples

[0448] For example, if a user requests "Math" content, the server verifies that the user's learning style is registered as "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model to search for math lessons that are suitable for a visual and fast-paced learning style. The server then selects an appropriate lesson (e.g., "Math: Lesson 1") and sends it to the user's device. The user can then efficiently progress through this lesson.

[0449] In this way, this platform can provide educational content optimized to the needs of each individual learner, improving learning efficiency.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model.

[0453] Step 2:

[0454] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[0455] Step 3:

[0456] The server trains the AI ​​model, which contains algorithms for selecting the most appropriate educational content based on learner data.

[0457] Step 4:

[0458] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[0459] Step 5:

[0460] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[0461] Step 6:

[0462] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[0463] Step 7:

[0464] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[0465] Step 8:

[0466] The server generates personalized educational content selected by the AI ​​model and sends it to the device.

[0467] Step 9:

[0468] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[0469] Step 10:

[0470] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model, enabling more effective personalization.

[0471] Example 1

[0472] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] Conventional educational systems have the problem of being unable to provide educational content optimized for each learner's learning style and pace. This reduces learners' learning efficiency and makes it difficult to maintain their interest and motivation. Furthermore, there is a lack of a mechanism for instantly providing the educational content requested by learners, making it impossible to provide a fast and appropriate learning experience. Furthermore, the cost and effort required to deal with the technical complexity of individually optimizing educational content is also a major issue.

[0474] 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.

[0475] In this invention, the server includes means for loading educational data and training a generative AI model to classify optimal learning styles and paces, means for a learner to input and save their learning style and learning pace from a terminal, and means for selecting and providing personalized educational content using the generative AI model when a learner requests specific educational content, thereby enabling educational content optimized for the individual needs of each learner to be provided quickly and appropriately.

[0476] A "server" is a device that stores learner information, loads educational data, trains generative AI models, and provides personalized educational content requested by learners.

[0477] A "generative AI model" is a model that uses artificial intelligence technology to optimize educational content and select appropriate content based on the learner's learning style and pace.

[0478] "Learning style" refers to the way in which a learner absorbs knowledge most efficiently, such as visual or auditory.

[0479] "Learning pace" refers to the speed at which a learner can most efficiently progress through their studies, such as fast, normal, or slow.

[0480] "Educational content" is a general term for the teaching materials and lessons that learners use to learn, and is provided in the form of video, audio, text, etc.

[0481] A "terminal" is a device used by a learner to access the server, log in, request content, and view received content.

[0482] A "database" is a system for efficiently storing and managing data such as learner information, learning style, and pace.

[0483] "Classification" means organizing educational content based on collected data according to the learner's learning style and pace and dividing it into appropriate categories.

[0484] The present invention is an educational system that provides personalized educational content based on the learner's learning style and pace. This system is mainly composed of a server, a terminal, and a user. The specific configuration and operation are described below.

[0485] server

[0486] The server loads educational data from Amazon S3 and uses the training data to build a generative AI model (e.g., using TensorFlow). The server stores learner information (learning style and pace) in a MySQL database. The server also categorizes the educational content requested by the learner and selects and provides the appropriate content.

[0487] Loading training data and training the AI ​​model

[0488] The server downloads educational content from Amazon S3, for example, contained in a folder called "math_lessons," locally, and uses TensorFlow to train a generative AI model that determines the optimal learning style and pace based on past learning data.

[0489] User Roles

[0490] Users (learners) access the platform using their terminals and log in. After logging in, users input and set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow). This information is stored in a database by the server.

[0491] Educational Content Requests

[0492] The user selects the desired educational content (e.g., mathematics, science) from the platform menu, clicks the request button, and the device sends the request to the server in HTTPS format.

[0493] Response from the server

[0494] The server receives the learner's request and uses a trained generative AI model to select the most appropriate educational content, which is then sent back to the device.

[0495] Device behavior

[0496] The device receives the response sent from the server and displays appropriate educational content, for example, playing video educational content for visual and fast-paced learners.

[0497] Specific operation example

[0498] For example, if a user requests "Math" content, the server uses an AI model to determine that the user has a visual, fast-paced learning style. The content "interactive_math_lesson_1.mp4" is selected and sent from the server to the device. The device then displays this video to the user, helping them learn more efficiently.

[0499] Prompt Sentence Examples

[0500] For example, a user can request on a learning platform, "Can you provide me with fast-paced visual lessons in math?" and the server can select and provide the most appropriate content.

[0501] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[0502] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0503] Step 1: Initialize the server

[0504] Server behavior:

[0505] When the server is powered on, it boots up an OS (e.g., Ubuntu). The server loads educational content from Amazon S3 and downloads training data locally. Specifically, all content in the "math_lessons" folder stored in Amazon S3 is downloaded. Next, the server uses TensorFlow to train a generative AI model. The training data includes data on past learning history and learning style. The server uses this data to generate a model that classifies learning style and pace.

[0506] Input: Educational content, past learning history data

[0507] Data processing & calculation: Download data and train AI models

[0508] Output: A trained generative AI model

[0509] Step 2: Enroll learners

[0510] User Action:

[0511] Users use their devices to access the platform's login page and enter their authentication information (username, password) to log in. After logging in, users are taken to a dashboard screen where they can set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow).

[0512] Server behavior:

[0513] The server receives the learning style and pace sent by the learner and stores them in a MySQL database. Specifically, it stores the data in the corresponding columns in the table that stores user information.

[0514] Input: Learner style and pace information

[0515] Data processing and calculation: Receiving data and saving it to the database

[0516] Output: Saved learner information

[0517] Step 3: Request learning content

[0518] User Action:

[0519] The user selects a specific educational content (e.g., mathematics) from the platform's menu and submits a request for the educational content by clicking a request button, which sends the request to the server.

[0520] Terminal behavior:

[0521] The device sends the learner's request to the server as an HTTPS request, for example, calling the endpoint " / request-content?subject=math".

[0522] Input: User request for educational content

[0523] Data processing & calculation: Sending a request

[0524] Output: Request data to the server

[0525] Step 4: Select and deliver personalized learning content

[0526] Server behavior:

[0527] The server receives the learner's request. The request data also includes the learner's learning style and pace. Based on the saved learning style and pace information, the server uses a generative AI model to select the most suitable educational content. For example, it determines that the content "interactive_math_lesson_1.mp4" is most suitable for a "visual" and "fast-paced" learner. Based on this selection result, the server generates a response including the content ID and password and sends it to the device.

[0528] Input: Request data from user, learning style and pace information

[0529] Data processing & calculation: Content selection and response generation using AI models

[0530] Output: Response data for selected educational content

[0531] Step 5: Display educational content

[0532] Terminal behavior:

[0533] The device receives the response from the server and displays the corresponding educational content by launching a video player and streaming a file such as "interactive_math_lesson_1.mp4."

[0534] Input: Response data from the server

[0535] Data processing & calculation: Response analysis, content display

[0536] Output: The educational content displayed to the learner

[0537] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[0538] (Application example 1)

[0539] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0540] With conventional education platforms, it was difficult to provide educational content that was optimized for each learner's individual learning style and pace.In addition, when it came to training workers on factory floors, there was a lack of technology to provide training methods that were suited to each worker, making it difficult to efficiently improve their skills and ensure safe work.

[0541] 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.

[0542] In this invention, the server includes means for optimizing educational content based on the learning style and learning pace of a learner using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace, means for providing the selected educational content to the learner, and means including a factory robot for providing optimal training content based on the learning style and learning pace of a worker, thereby enabling the provision of optimal educational and training content according to the individual needs of the learner and worker.

[0543] An "artificial intelligence model" refers to an algorithm that uses large amounts of data to learn patterns and make predictions and classifications.

[0544] "Learning style" refers to the way in which a learner most effectively perceives information, and can include visual, auditory, tactile, etc.

[0545] "Learning pace" refers to the speed at which a learner absorbs and comprehends information, and can include fast, normal, or slow.

[0546] "Educational content" refers to information and materials provided to learners, including text, video, audio, illustrations, etc.

[0547] "Optimization means" refers to the process of using artificial intelligence models and algorithms to select educational content with the optimal format and content that suits the learner's learning style and pace.

[0548] "Means of selection" refers to a method or system for extracting from multiple educational contents the one that best suits the learner's requirements.

[0549] "Means of delivery" refers to the means for delivering the selected educational content to learners, including delivery via the Internet and downloads.

[0550] A "factory robot" is a mechanical device designed to perform various tasks within a factory, and is capable of providing training content to workers.

[0551] The present invention is a system for providing educational content optimized to the individual needs of learners and factory workers. Specific embodiments of this system will be described below.

[0552] Hardware and Software Configuration

[0553] The server has the following responsibilities:

[0554] 1. Database: Stores information about learners and workers. Specifically, a database such as MySQL is used.

[0555] 2. Loading educational content: Loading and categorizing pre-prepared educational content.

[0556] 3. Training artificial intelligence models: Using software such as TensorFlow, AI models are trained using historical and real-time data from learners and workers.

[0557] 4. Generate and deliver optimal content: Generate optimal educational content based on the learning style and pace of learners and workers, and deliver personalized content.

[0558] Terminals are devices that students and workers use to communicate with the server, and can be PCs, smartphones, tablets, or factory robots.

[0559] Processing Details

[0560] The server receives input from learners and workers and uses the AI ​​model to generate optimized educational content based on that information. Specifically, if visual learning is effective, content that is easy to understand visually will be generated, and for workers who learn at a fast pace, short sessions will be selected to enable efficient learning.

[0561] Learners and workers input their own learning style and pace from their devices and select the educational content they want. This information is sent to the server, which then generates optimized educational content and distributes it to the devices.

[0562] Specific operations

[0563] For learners

[0564] 1. Learners access the platform using their devices and log in.

[0565] 2. Learners input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[0566] 3. Learners request the educational content they want (math, science, etc.).

[0567] For example, if a visual, fast-paced learner requests "Math" content, the following will happen:

[0568] The server uses AI models to select visual, fast-paced math lessons.

[0569] Generate content that includes visually easy-to-understand heat maps, diagrams, and short video clips.

[0570] The generated content is provided to the learner's device to advance their learning.

[0571] For workers

[0572] 1. The worker logs in using the factory robot's interface.

[0573] 2. Workers input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[0574] 3. Workers request the training content they desire (e.g., safe operations, quality control, etc.).

[0575] For example, if a fast visual learner requests "Quality Control Training," the following happens:

[0576] The robot receives visual, fast-paced, quality-controlled training content from the server.

[0577] The robot displays heat maps and diagrams that are easy for workers to understand visually, guiding them to important checkpoints.

[0578] Workers will follow the robot's instructions as they go through the training.

[0579] Example prompts to input to the generative AI model

[0580] "Provide optimal quality control training content for factory workers who are fast-paced visual learners."

[0581] "We will provide training on safe operation using audio guidance. Please also explain in detail the precautions to take."

[0582] In this way, the system of the present invention can generate and provide optimal education and training content tailored to the individual needs of learners and workers, thereby enabling efficient and effective education and training.

[0583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0584] Step 1:

[0585] The server stores information about learners and workers in a database, including their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow), forming the basis for providing educational content optimized to the individual needs of each learner and worker.

[0586] Step 2:

[0587] The server loads pre-prepared educational content and categorizes it according to each learning style and pace. Specifically, it categorizes lessons such as math and science into visually and aurally easy-to-understand content, and stores each content in a database. This prepares the content for efficient delivery.

[0588] Step 3:

[0589] The server collects historical data and real-time learning data from learners and workers to train the AI ​​model. Using software such as TensorFlow, the model is trained to generate optimal educational content based on the characteristics of learners and workers. This AI model functions as an algorithm that processes the data and makes predictions and classifications.

[0590] Step 4:

[0591] Learners and workers access the platform and log in using a device (such as a PC, smartphone, or factory robot). The device receives the user's input information and sends it to the server. The server then imports the received learning style and pace information into a database and uses it to generate personalized content.

[0592] Step 5:

[0593] Learners and workers submit requests for the educational content they desire (mathematics, science, safe operations, quality control, etc.). The request is sent from the device to the server, which uses an AI model to generate the optimal educational content based on the request, learning style, and pace.

[0594] Step 6:

[0595] The server uses the AI ​​model to generate optimized educational content and transmit it to the device. Specifically, it selects training content that is easy to understand visually, including heat maps, diagrams, and audio guidance, and outputs the results.

[0596] Step 7:

[0597] The terminal receives the personalized educational content sent from the server and displays it to the learner and worker, allowing the learner and worker to progress with their studies using the optimized content.

[0598] In this way, it is possible to provide individualized and optimal education and training to learners and workers through each step.

[0599] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0600] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for a learner's learning style, learning pace, and emotions. A specific embodiment of this system is described below.

[0601] System configuration

[0602] server

[0603] 1. The server is responsible for storing learner information in a database.

[0604] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace, and also obtains emotional information using an emotion engine.

[0605] 3. The server trains the AI ​​model and emotion engine, and generates optimal educational content using the learner's historical data, real-time learning data, and emotion data.

[0606] 4. The server provides personalized educational content when accessed by the learner.

[0607] User

[0608] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[0609] 2. Learners input or provide learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and real-time emotional information (e.g., happy, sad, excited).

[0610] 3. Learners submit requests for desired educational content (e.g., math, science).

[0611] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[0612] Terminal

[0613] 1. The terminal receives input information and real-time emotional information from the learner and transmits it to the server.

[0614] 2. The terminal displays the personalized educational content sent from the server.

[0615] Explanation of program processing

[0616] 1. Initialize the server:

[0617] The server loads learning content and trains the AI ​​model and emotion engine, including lessons in math and science, catering to multiple learning styles, including visual and auditory.

[0618] 2. Learner Registration:

[0619] Users (learners) register their learning style and pace, as well as initial emotional data, with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[0620] 3. Learning content requests:

[0621] A user logs into a learning platform and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[0622] 4. Acquiring learners' emotional information:

[0623] The server uses an emotion engine to recognize the learner's emotional information in real time, thereby understanding the learner's emotional state during learning.

[0624] 5. Providing personalized learning content:

[0625] The server takes into account the learner's learning style and pace, as well as emotional information, and uses an AI model and emotional engine to generate optimized educational content, which is then sent to the device.

[0626] 6. Display of educational content:

[0627] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their studies.

[0628] Specific examples

[0629] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[0630] In this way, this platform can provide educational content optimized to the needs of individual learners, improving learning efficiency. By combining it with an emotion engine, it is possible to provide a more highly personalized learning experience.

[0631] The processing flow will be explained below.

[0632] Step 1:

[0633] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model and emotion engine.

[0634] Step 2:

[0635] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[0636] Step 3:

[0637] The server trains the AI ​​model and emotion engine. The AI ​​model contains algorithms for selecting optimal educational content based on learner data. The emotion engine collects and analyzes user emotion data in real time.

[0638] Step 4:

[0639] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[0640] Step 5:

[0641] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[0642] Step 6:

[0643] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[0644] Step 7:

[0645] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[0646] Step 8:

[0647] The server uses an emotion engine to recognize the user's emotional information in real time, for example, by analyzing the user's facial expressions and tone of voice through the user's webcam and microphone.

[0648] Step 9:

[0649] The server further optimizes the educational content selected by the AI ​​model based on the acquired emotional information, thereby adjusting the content format and difficulty level according to the user's emotional state.

[0650] Step 10:

[0651] The server generates optimized and personalized educational content and transmits it to the terminal.

[0652] Step 11:

[0653] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[0654] Step 12:

[0655] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model and emotion engine, enabling more effective personalization.

[0656] Example 2

[0657] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0658] The present invention aims to solve the problem that it is difficult for conventional educational platforms to provide educational content that is tailored to the learner's learning style and pace, as well as to provide individually optimized educational content that takes into account real-time emotional data during learning. Specifically, there is a need to grasp the learner's emotional state in real time and dynamically adjust educational content accordingly.

[0659] 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.

[0660] In this invention, the server includes: means for optimizing educational content based on a learner's learning style, learning pace, and emotional data using an artificial intelligence model; means for selecting appropriate educational content based on the learning style, learning pace, and emotional data; means having an emotion engine for acquiring and analyzing the learner's emotional data in real time; and means for providing the selected educational content to the learner. This not only provides optimal educational content tailored to the learner's learning style and pace, but also enables a more highly personalized learning experience that responds to the learner's emotional state during learning.

[0661] An "artificial intelligence model" is a computer program that analyzes data and learns patterns to make predictions and decisions.

[0662] "Learning style" refers to the method or approach that a learner uses to most effectively comprehend and acquire information, such as visual learning or auditory learning.

[0663] "Learning pace" refers to how quickly a learner can digest and understand educational content, and can be categorized as fast, normal, or slow.

[0664] "Educational Content" includes teaching materials and resources designed to teach a particular academic subject or skill, such as mathematics lessons or science experiment guides.

[0665] "Emotional data" is information that indicates the learner's current emotional state, including happiness, sadness, excitement, etc.

[0666] An "emotion engine" is software or a system that analyzes and recognizes a learner's real-time emotional state.

[0667] "Optimization" refers to adjusting a system or process to maximize performance or efficiency in order to achieve a specific purpose.

[0668] "Selection" is the act of selecting the most appropriate option from multiple choices or options.

[0669] "Provision" refers to the act of the system providing the necessary information or services to the user.

[0670] This invention is an educational platform that utilizes artificial intelligence (AI) models to provide educational content optimized for a learner's learning style, learning pace, and emotional data. This platform is composed of a server, a terminal, and a user.

[0671] Server Features

[0672] 1. Training the AI ​​model and emotion engine

[0673] The server uses artificial intelligence models to learn from learner data and optimize educational content. It also uses an emotion engine to analyze learner emotion data in real time. The main software used includes AI models such as TensorFlow and PyTorch, and emotion engines such as Affectiva and IBM Watson Emotion Analysis.

[0674] 2. Loading and optimizing learning content

[0675] The server loads pre-prepared learning content, including lessons in subjects like math and science, and caters to visual and auditory learning styles, allowing the server to optimize educational content based on learning style, learning pace, and emotional data.

[0676] 3. Data storage and content provision

[0677] The server stores learners' learning style, learning pace, and initial emotional data in a database and uses it to provide personalized learning experiences. This is done using cloud data services such as Amazon Web Services (AWS). The server then transmits optimized educational content to the device, where it can be accessed by the user.

[0678] Device Features

[0679] The device (PC or smartphone) receives learner input information and emotional data collected in real time and sends it to the server. The device also plays a role in displaying personalized educational content sent from the server to the user.

[0680] User operations

[0681] Users (learners) access the platform using their devices and log in. They input their learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data (e.g., happy, sad, excited). They then submit a request for the educational content they desire (e.g., math, science). The server processes this request and provides optimized content.

[0682] Specific examples

[0683] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[0684] Prompt Sentence Examples

[0685] Learning style: "I'm a visual learner."

[0686] Learning pace: "I like to learn at a fast pace."

[0687] Emotional information: "I feel excited right now."

[0688] In this way, the platform of the present invention can provide educational content tailored to the individual needs of learners, greatly improving learning efficiency.

[0689] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0690] Specific flow of program processing

[0691] Step 1: Initialize the server

[0692] The server loads learning content (e.g., math and science lessons). This includes content for multiple learning styles, such as visual and auditory learning. The hardware used is a cloud server, and the software is a database management system. The input is a set of files containing educational content prepared in advance, and the output is information indicating that the learning data has been loaded.

[0693] Specific behavior:

[0694] The server downloads the educational content from the cloud storage.

[0695] Load content into a database and categorize it by style.

[0696] Step 2: Training the AI ​​model and emotion engine

[0697] The server trains the AI ​​model and emotion engine using the learner's historical data and pre-prepared data. The software used is TensorFlow, PyTorch, Affectiva, and IBM Watson Emotion Analysis. The input is past learning data and emotion data, and the output is the trained model.

[0698] Specific behavior:

[0699] Cleanse historical and sentiment data and prepare it for machine learning.

[0700] Run the training process for the AI ​​model and emotion engine to set optimal parameters.

[0701] Step 3: Enroll learners

[0702] Users access the platform using their devices and create an account or log in. The input is the user's learning style, learning pace, and initial emotional data, and the output is a learner profile stored in a database.

[0703] Specific behavior:

[0704] The user inputs learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data from the terminal.

[0705] The server stores this information in a database.

[0706] Step 4: Request learning content

[0707] A user requests a specific educational content (e.g., mathematics). The request is sent from the device and processed by the server. The input is the user's content request, and the output is a confirmation that the request was received.

[0708] Specific behavior:

[0709] The user selects a particular educational content from the terminal and sends a request to the server.

[0710] The server receives the request and begins searching for the appropriate content.

[0711] Step 5: Obtaining learners' emotional information

[0712] The server uses an emotion engine to obtain the learner's emotional data in real time. The input is the user's current emotional information (e.g., facial recognition data, voice data), and the output is the analyzed emotional data.

[0713] Specific behavior:

[0714] The server receives emotional state data (facial recognition, voice analysis, etc.) sent from the user's device.

[0715] The emotion engine analyzes the data and identifies the emotional state (e.g., excitement, sadness).

[0716] Step 6: Deliver personalized learning content

[0717] The server takes into account the learning style and pace, as well as the acquired emotional data, to generate optimal educational content. The input is the learner profile stored on the server and real-time emotional data, and the output is optimized educational content.

[0718] Specific behavior:

[0719] The server uses AI models to generate optimal learning content, taking into account learning style, learning pace, and emotional data.

[0720] The content is sent to the terminal and made available to the user.

[0721] Step 7: Display educational content

[0722] The terminal receives the educational content sent from the server and displays it to the user. The input is the educational content sent from the server, and the output is the learning material displayed to the user.

[0723] Specific behavior:

[0724] The terminal receives the educational content transmitted from the server.

[0725] The content is displayed on the screen and users can begin learning.

[0726] In this way, the program's series of processes is meticulously planned to provide educational content optimized to the individual needs of each learner.

[0727] (Application example 2)

[0728] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0729] Traditional educational platforms face the challenge of providing customized educational content that responds to learners' individual learning styles, pace, and real-time emotional states. This makes it difficult to maintain learners' interest and maximize learning efficiency. Furthermore, there is a lack of systems for providing appropriate content to accommodate different learning styles, such as visual and auditory, which can lead to a decline in learning quality.

[0730] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for optimizing educational content based on the learner's learning style and learning pace using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace and real-time emotional data, means for providing the selected educational content to the learner, and means for displaying the optimized educational content on a smart device. This makes it possible to provide educational content optimized to the individual needs of the learner and maximize learning efficiency and interest.

[0731] An "artificial intelligence model" is an algorithm or statistical model that analyzes learner data and selects and generates optimal educational content.

[0732] "Learning style" is a term that refers to the methods or ways in which learners most effectively understand and absorb information.

[0733] "Learning pace" refers to the speed or rhythm at which a learner progresses through learning content.

[0734] "Educational content" refers to materials and information that include learning materials, lessons, exercises, and other learning subjects provided to learners.

[0735] "Real-time emotional data" refers to data capturing the learner's emotional state in real time, including, for example, joy, excitement, or sadness during learning.

[0736] "Smart devices" are electronic devices with internet connectivity that are used by learners, such as computers, smartphones, and smart glasses.

[0737] "Optimize" means to adjust or improve something to be best suited to a specific purpose.

[0738] "To select" means to decide and select a specific object from among many candidates or possibilities.

[0739] "Providing" refers to imparting and distributing necessary information and teaching materials to learners.

[0740] "Display" means to visually show information on the screen of an electronic device or the like.

[0741] A "system" is a complex consisting of multiple elements that interact and cooperate to achieve a specific function or purpose.

[0742] The present invention provides an educational platform that provides educational content optimized to the individual needs of learners. Specific embodiments for carrying out the present invention will be described below.

[0743] System Overview

[0744] The system of the present invention utilizes an artificial intelligence model to optimize educational content based on the learner's learning style, learning pace, and real-time emotional data, and provides it via smart devices. The main components of the system are a server, a terminal (smart device), and a user.

[0745] Hardware and Software Configuration

[0746] Hardware:

[0747] 1. Server: A high-performance computer server

[0748] 2. Smart Devices: Electronic devices with internet connectivity such as smart glasses, smartphones, tablets, etc.

[0749] software:

[0750] 1. Artificial intelligence model: Algorithms using machine learning frameworks such as TensorFlow

[0751] 2. Emotion recognition engine: Emotion analysis software such as EmotionEngine

[0752] 3. Content Management: Database System

[0753] 4. User Profile Management: UserProfile System

[0754] 5. Smart Device API: SmartGlassesAPI, etc.

[0755] Data processing and calculation

[0756] server:

[0757] 1. Initialization: The server loads learning content and trains the AI ​​model and emotion engine. The learning content includes lessons for math and science, for example, and includes content that supports multiple learning styles, such as visual and auditory.

[0758] 2. Acquiring learner information: The server stores the learner's learning style, learning pace, and real-time emotional data in a database, and generates optimal educational content based on this information.

[0759] Terminal (smart device):

[0760] 1. Information collection: The device collects learners' actions and reactions in real time and sends them to the server. This includes data from cameras, sensors, microphones, etc.

[0761] 2. Content display: The terminal displays the optimized educational content sent from the server and provides it to the learner.

[0762] Specific processing examples:

[0763] For example, if a learner is studying "Mathematics" through smart glasses and the emotion engine recognizes the "Excited" state, the server will determine that the learner's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the learner's excited state. The server then selects an appropriate lesson (e.g., "Mathematics: Lesson 3") and sends it to the user's device.

[0764] Example prompt sentence:

[0765] User learning style: Visual

[0766] User learning pace: Fast

[0767] Real-time emotions: excitement

[0768] Requested educational content: Mathematics

[0769] In this way, the system can provide educational content optimized to the needs of each individual learner, maximizing learning efficiency and interest.

[0770] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0771] Step 1:

[0772] Initialize the server:

[0773] The server loads the learning content and trains the artificial intelligence model and emotion engine. Specifically, the server retrieves educational content (e.g., math and science lessons) from the database and uses it as training data for the AI ​​model using a machine learning framework such as TensorFlow. It also trains the emotion recognition model using EmotionEngine. The inputs are the learning content and the initial data for the AI ​​model and emotion engine, and the outputs are the trained AI model and emotion recognition model.

[0774] Step 2:

[0775] User profile settings:

[0776] Users log in to the system and register their learning style, learning pace, initial emotional data, etc. This information is sent to the server via their terminal, and the server stores this information in a database. The input is the learning style, learning pace, and emotional data provided by the user from their terminal, and the output is the user profile information stored in the database.

[0777] Step 3:

[0778] Educational Content Request:

[0779] A user uses a device to request a specific educational content (e.g., mathematics). This request is sent to a server. The input is the content request from the user, and the output is the request data to the server.

[0780] Step 4:

[0781] Acquiring emotional information:

[0782] The server uses the EmotionEngine to obtain the learner's emotional information in real time. It uses the device's camera and microphone to analyze the learner's facial expressions and tone of voice to generate emotional data. The input is real-time camera feed and audio data, and the output is the emotion recognition results.

[0783] Step 5:

[0784] Generate personalized learning content:

[0785] The server generates optimal educational content based on learning style, learning pace, and real-time emotional data. It uses an AI model based on machine learning frameworks such as TensorFlow to analyze this data and select the most appropriate lessons and materials. The input is stored user profile information and real-time emotional data, and the output is optimized educational content.

[0786] Step 6:

[0787] Educational content provided by:

[0788] The server sends the generated optimized educational content to the smart device, which then displays it. The input is the educational content sent from the server, and the output is the learning material displayed on the device.

[0789] Specifically, when a learner requests "math" content through smart glasses, the emotion engine recognizes the "excitement" state. For a learner whose learning style is identified as "visual" and whose learning pace is "fast," the server selects math lessons that correspond to the excitement state appropriate for a visual and fast pace and displays them on the smart glasses.

[0790] Example prompt sentence:

[0791] User learning style: Visual

[0792] User learning pace: Fast

[0793] Real-time emotions: excitement

[0794] Requested educational content: Mathematics

[0795] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0796] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0797] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0798] [Third embodiment]

[0799] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0800] 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.

[0801] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0802] 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.

[0803] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0804] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0805] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0806] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0807] 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.

[0808] 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.

[0809] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0810] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0811] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for each learner's learning style and pace.

[0812] System configuration

[0813] server

[0814] 1. The server stores the learner's information in a database.

[0815] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace.

[0816] 3. The server trains the AI ​​model and generates optimal educational content using the learner's historical data and real-time learning data.

[0817] 4. The server provides personalized educational content when accessed by the learner.

[0818] User

[0819] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[0820] 2. Learners input their learning style (e.g., visual, auditory) and learning pace (e.g., fast, normal, slow).

[0821] 3. Learners submit requests for desired educational content (e.g., math, science).

[0822] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[0823] Terminal

[0824] 1. The terminal receives input information from the learner and sends it to the server.

[0825] 2. The terminal displays the personalized educational content sent from the server.

[0826] Explanation of program processing

[0827] 1. Initialize the server:

[0828] The server loads learning content, such as math and science lessons, and trains the AI ​​model.

[0829] 2. Learner Registration:

[0830] Users (learners) register their learning style and pace with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[0831] 3. Learning content requests:

[0832] When a user logs into the learning platform and requests specific educational content, the server selects the most appropriate educational content to suit the user's learning style and pace.

[0833] 4. Providing personalized learning content:

[0834] The server uses the AI ​​model to generate optimized educational content and sends it back to the user, who then displays it on their device.

[0835] Specific examples

[0836] For example, if a user requests "Math" content, the server verifies that the user's learning style is registered as "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model to search for math lessons that are suitable for a visual and fast-paced learning style. The server then selects an appropriate lesson (e.g., "Math: Lesson 1") and sends it to the user's device. The user can then efficiently progress through this lesson.

[0837] In this way, this platform can provide educational content optimized to the needs of each individual learner, improving learning efficiency.

[0838] The processing flow will be explained below.

[0839] Step 1:

[0840] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model.

[0841] Step 2:

[0842] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[0843] Step 3:

[0844] The server trains the AI ​​model, which contains algorithms for selecting the most appropriate educational content based on learner data.

[0845] Step 4:

[0846] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[0847] Step 5:

[0848] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[0849] Step 6:

[0850] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[0851] Step 7:

[0852] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[0853] Step 8:

[0854] The server generates personalized educational content selected by the AI ​​model and sends it to the device.

[0855] Step 9:

[0856] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[0857] Step 10:

[0858] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model, enabling more effective personalization.

[0859] Example 1

[0860] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0861] Conventional educational systems have the problem of being unable to provide educational content optimized for each learner's learning style and pace. This reduces learners' learning efficiency and makes it difficult to maintain their interest and motivation. Furthermore, there is a lack of a mechanism for instantly providing the educational content requested by learners, making it impossible to provide a fast and appropriate learning experience. Furthermore, the cost and effort required to deal with the technical complexity of individually optimizing educational content is also a major issue.

[0862] 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.

[0863] In this invention, the server includes means for loading educational data and training a generative AI model to classify optimal learning styles and paces, means for a learner to input and save their learning style and learning pace from a terminal, and means for selecting and providing personalized educational content using the generative AI model when a learner requests specific educational content, thereby enabling educational content optimized for the individual needs of each learner to be provided quickly and appropriately.

[0864] A "server" is a device that stores learner information, loads educational data, trains generative AI models, and provides personalized educational content requested by learners.

[0865] A "generative AI model" is a model that uses artificial intelligence technology to optimize educational content and select appropriate content based on the learner's learning style and pace.

[0866] "Learning style" refers to the way in which a learner absorbs knowledge most efficiently, such as visual or auditory.

[0867] "Learning pace" refers to the speed at which a learner can most efficiently progress through their studies, such as fast, normal, or slow.

[0868] "Educational content" is a general term for the teaching materials and lessons that learners use to learn, and is provided in the form of video, audio, text, etc.

[0869] A "terminal" is a device used by a learner to access the server, log in, request content, and view received content.

[0870] A "database" is a system for efficiently storing and managing data such as learner information, learning style, and pace.

[0871] "Classification" means organizing educational content based on collected data according to the learner's learning style and pace and dividing it into appropriate categories.

[0872] The present invention is an educational system that provides personalized educational content based on the learner's learning style and pace. This system is mainly composed of a server, a terminal, and a user. The specific configuration and operation are described below.

[0873] server

[0874] The server loads educational data from Amazon S3 and uses the training data to build a generative AI model (e.g., using TensorFlow). The server stores learner information (learning style and pace) in a MySQL database. The server also categorizes the educational content requested by the learner and selects and provides the appropriate content.

[0875] Loading training data and training the AI ​​model

[0876] The server downloads educational content from Amazon S3, for example, contained in a folder called "math_lessons," locally, and uses TensorFlow to train a generative AI model that determines the optimal learning style and pace based on past learning data.

[0877] User Roles

[0878] Users (learners) access the platform using their terminals and log in. After logging in, users input and set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow). This information is stored in a database by the server.

[0879] Educational Content Requests

[0880] The user selects the desired educational content (e.g., mathematics, science) from the platform menu, clicks the request button, and the device sends the request to the server in HTTPS format.

[0881] Response from the server

[0882] The server receives the learner's request and uses a trained generative AI model to select the most appropriate educational content, which is then sent back to the device.

[0883] Device behavior

[0884] The device receives the response sent from the server and displays appropriate educational content, for example, playing video educational content for visual and fast-paced learners.

[0885] Specific operation example

[0886] For example, if a user requests "Math" content, the server uses an AI model to determine that the user has a visual, fast-paced learning style. The content "interactive_math_lesson_1.mp4" is selected and sent from the server to the device. The device then displays this video to the user, helping them learn more efficiently.

[0887] Prompt Sentence Examples

[0888] For example, a user can request on a learning platform, "Can you provide me with fast-paced visual lessons in math?" and the server can select and provide the most appropriate content.

[0889] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[0890] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0891] Step 1: Initialize the server

[0892] Server behavior:

[0893] When the server is powered on, it boots up an OS (e.g., Ubuntu). The server loads educational content from Amazon S3 and downloads training data locally. Specifically, all content in the "math_lessons" folder stored in Amazon S3 is downloaded. Next, the server uses TensorFlow to train a generative AI model. The training data includes data on past learning history and learning style. The server uses this data to generate a model that classifies learning style and pace.

[0894] Input: Educational content, past learning history data

[0895] Data processing & calculation: Download data and train AI models

[0896] Output: A trained generative AI model

[0897] Step 2: Enroll learners

[0898] User Action:

[0899] Users use their devices to access the platform's login page and enter their authentication information (username, password) to log in. After logging in, users are taken to a dashboard screen where they can set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow).

[0900] Server behavior:

[0901] The server receives the learning style and pace sent by the learner and stores them in a MySQL database. Specifically, it stores the data in the corresponding columns in the table that stores user information.

[0902] Input: Learner style and pace information

[0903] Data processing and calculation: Receiving data and saving it to the database

[0904] Output: Saved learner information

[0905] Step 3: Request learning content

[0906] User Action:

[0907] The user selects a specific educational content (e.g., mathematics) from the platform's menu and submits a request for the educational content by clicking a request button, which sends the request to the server.

[0908] Terminal behavior:

[0909] The device sends the learner's request to the server as an HTTPS request, for example, calling the endpoint " / request-content?subject=math".

[0910] Input: User request for educational content

[0911] Data processing & calculation: Sending a request

[0912] Output: Request data to the server

[0913] Step 4: Select and deliver personalized learning content

[0914] Server behavior:

[0915] The server receives the learner's request. The request data also includes the learner's learning style and pace. Based on the saved learning style and pace information, the server uses a generative AI model to select the most suitable educational content. For example, it determines that the content "interactive_math_lesson_1.mp4" is most suitable for a "visual" and "fast-paced" learner. Based on this selection result, the server generates a response including the content ID and password and sends it to the device.

[0916] Input: Request data from user, learning style and pace information

[0917] Data processing & calculation: Content selection and response generation using AI models

[0918] Output: Response data for selected educational content

[0919] Step 5: Display educational content

[0920] Terminal behavior:

[0921] The device receives the response from the server and displays the corresponding educational content by launching a video player and streaming a file such as "interactive_math_lesson_1.mp4."

[0922] Input: Response data from the server

[0923] Data processing & calculation: Response analysis, content display

[0924] Output: The educational content displayed to the learner

[0925] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[0926] (Application example 1)

[0927] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0928] With conventional education platforms, it was difficult to provide educational content that was optimized for each learner's individual learning style and pace.In addition, when it came to training workers on factory floors, there was a lack of technology to provide training methods that were suited to each worker, making it difficult to efficiently improve their skills and ensure safe work.

[0929] 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.

[0930] In this invention, the server includes means for optimizing educational content based on the learning style and learning pace of a learner using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace, means for providing the selected educational content to the learner, and means including a factory robot for providing optimal training content based on the learning style and learning pace of a worker, thereby enabling the provision of optimal educational and training content according to the individual needs of the learner and worker.

[0931] An "artificial intelligence model" refers to an algorithm that uses large amounts of data to learn patterns and make predictions and classifications.

[0932] "Learning style" refers to the way in which a learner most effectively perceives information, and can include visual, auditory, tactile, etc.

[0933] "Learning pace" refers to the speed at which a learner absorbs and comprehends information, and can include fast, normal, or slow.

[0934] "Educational content" refers to information and materials provided to learners, including text, video, audio, illustrations, etc.

[0935] "Optimization means" refers to the process of using artificial intelligence models and algorithms to select educational content with the optimal format and content that suits the learner's learning style and pace.

[0936] "Means of selection" refers to a method or system for extracting from multiple educational contents the one that best suits the learner's requirements.

[0937] "Means of delivery" refers to the means for delivering the selected educational content to learners, including delivery via the Internet and downloads.

[0938] A "factory robot" is a mechanical device designed to perform various tasks within a factory, and is capable of providing training content to workers.

[0939] The present invention is a system for providing educational content optimized to the individual needs of learners and factory workers. Specific embodiments of this system will be described below.

[0940] Hardware and Software Configuration

[0941] The server has the following responsibilities:

[0942] 1. Database: Stores information about learners and workers. Specifically, a database such as MySQL is used.

[0943] 2. Loading educational content: Loading and categorizing pre-prepared educational content.

[0944] 3. Training artificial intelligence models: Using software such as TensorFlow, AI models are trained using historical and real-time data from learners and workers.

[0945] 4. Generate and deliver optimal content: Generate optimal educational content based on the learning style and pace of learners and workers, and deliver personalized content.

[0946] Terminals are devices that students and workers use to communicate with the server, and can be PCs, smartphones, tablets, or factory robots.

[0947] Processing Details

[0948] The server receives input from learners and workers and uses the AI ​​model to generate optimized educational content based on that information. Specifically, if visual learning is effective, content that is easy to understand visually will be generated, and for workers who learn at a fast pace, short sessions will be selected to enable efficient learning.

[0949] Learners and workers input their own learning style and pace from their devices and select the educational content they want. This information is sent to the server, which then generates optimized educational content and distributes it to the devices.

[0950] Specific operations

[0951] For learners

[0952] 1. Learners access the platform using their devices and log in.

[0953] 2. Learners input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[0954] 3. Learners request the educational content they want (math, science, etc.).

[0955] For example, if a visual, fast-paced learner requests "Math" content, the following will happen:

[0956] The server uses AI models to select visual, fast-paced math lessons.

[0957] Generate content that includes visually easy-to-understand heat maps, diagrams, and short video clips.

[0958] The generated content is provided to the learner's device to advance their learning.

[0959] For workers

[0960] 1. The worker logs in using the factory robot's interface.

[0961] 2. Workers input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[0962] 3. Workers request the training content they desire (e.g., safe operations, quality control, etc.).

[0963] For example, if a fast visual learner requests "Quality Control Training," the following happens:

[0964] The robot receives visual, fast-paced, quality-controlled training content from the server.

[0965] The robot displays heat maps and diagrams that are easy for workers to understand visually, guiding them to important checkpoints.

[0966] Workers will follow the robot's instructions as they go through the training.

[0967] Example prompts to input to the generative AI model

[0968] "Provide optimal quality control training content for factory workers who are fast-paced visual learners."

[0969] "We will provide training on safe operation using audio guidance. Please also explain in detail the precautions to take."

[0970] In this way, the system of the present invention can generate and provide optimal education and training content tailored to the individual needs of learners and workers, thereby enabling efficient and effective education and training.

[0971] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0972] Step 1:

[0973] The server stores information about learners and workers in a database, including their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow), forming the basis for providing educational content optimized to the individual needs of each learner and worker.

[0974] Step 2:

[0975] The server loads pre-prepared educational content and categorizes it according to each learning style and pace. Specifically, it categorizes lessons such as math and science into visually and aurally easy-to-understand content, and stores each content in a database. This prepares the content for efficient delivery.

[0976] Step 3:

[0977] The server collects historical data and real-time learning data from learners and workers to train the AI ​​model. Using software such as TensorFlow, the model is trained to generate optimal educational content based on the characteristics of learners and workers. This AI model functions as an algorithm that processes the data and makes predictions and classifications.

[0978] Step 4:

[0979] Learners and workers access the platform and log in using a device (such as a PC, smartphone, or factory robot). The device receives the user's input information and sends it to the server. The server then imports the received learning style and pace information into a database and uses it to generate personalized content.

[0980] Step 5:

[0981] Learners and workers submit requests for the educational content they desire (mathematics, science, safe operations, quality control, etc.). The request is sent from the device to the server, which uses an AI model to generate the optimal educational content based on the request, learning style, and pace.

[0982] Step 6:

[0983] The server uses the AI ​​model to generate optimized educational content and transmit it to the device. Specifically, it selects training content that is easy to understand visually, including heat maps, diagrams, and audio guidance, and outputs the results.

[0984] Step 7:

[0985] The terminal receives the personalized educational content sent from the server and displays it to the learner and worker, allowing the learner and worker to progress with their studies using the optimized content.

[0986] In this way, it is possible to provide individualized and optimal education and training to learners and workers through each step.

[0987] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0988] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for a learner's learning style, learning pace, and emotions. A specific embodiment of this system is described below.

[0989] System configuration

[0990] server

[0991] 1. The server is responsible for storing learner information in a database.

[0992] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace, and also obtains emotional information using an emotion engine.

[0993] 3. The server trains the AI ​​model and emotion engine, and generates optimal educational content using the learner's historical data, real-time learning data, and emotion data.

[0994] 4. The server provides personalized educational content when accessed by the learner.

[0995] User

[0996] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[0997] 2. Learners input or provide learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and real-time emotional information (e.g., happy, sad, excited).

[0998] 3. Learners submit requests for desired educational content (e.g., math, science).

[0999] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[1000] Terminal

[1001] 1. The terminal receives input information and real-time emotional information from the learner and transmits it to the server.

[1002] 2. The terminal displays the personalized educational content sent from the server.

[1003] Explanation of program processing

[1004] 1. Initialize the server:

[1005] The server loads learning content and trains the AI ​​model and emotion engine, including lessons in math and science, catering to multiple learning styles, including visual and auditory.

[1006] 2. Learner Registration:

[1007] Users (learners) register their learning style and pace, as well as initial emotional data, with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[1008] 3. Learning content requests:

[1009] A user logs into a learning platform and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[1010] 4. Acquiring learners' emotional information:

[1011] The server uses an emotion engine to recognize the learner's emotional information in real time, thereby understanding the learner's emotional state during learning.

[1012] 5. Providing personalized learning content:

[1013] The server takes into account the learner's learning style and pace, as well as emotional information, and uses an AI model and emotional engine to generate optimized educational content, which is then sent to the device.

[1014] 6. Display of educational content:

[1015] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their studies.

[1016] Specific examples

[1017] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[1018] In this way, this platform can provide educational content optimized to the needs of individual learners, improving learning efficiency. By combining it with an emotion engine, it is possible to provide a more highly personalized learning experience.

[1019] The processing flow will be explained below.

[1020] Step 1:

[1021] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model and emotion engine.

[1022] Step 2:

[1023] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[1024] Step 3:

[1025] The server trains the AI ​​model and emotion engine. The AI ​​model contains algorithms for selecting optimal educational content based on learner data. The emotion engine collects and analyzes user emotion data in real time.

[1026] Step 4:

[1027] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[1028] Step 5:

[1029] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[1030] Step 6:

[1031] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[1032] Step 7:

[1033] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[1034] Step 8:

[1035] The server uses an emotion engine to recognize the user's emotional information in real time, for example, by analyzing the user's facial expressions and tone of voice through the user's webcam and microphone.

[1036] Step 9:

[1037] The server further optimizes the educational content selected by the AI ​​model based on the acquired emotional information, thereby adjusting the content format and difficulty level according to the user's emotional state.

[1038] Step 10:

[1039] The server generates optimized and personalized educational content and transmits it to the terminal.

[1040] Step 11:

[1041] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[1042] Step 12:

[1043] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model and emotion engine, enabling more effective personalization.

[1044] Example 2

[1045] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1046] The present invention aims to solve the problem that it is difficult for conventional educational platforms to provide educational content that is tailored to the learner's learning style and pace, as well as to provide individually optimized educational content that takes into account real-time emotional data during learning. Specifically, there is a need to grasp the learner's emotional state in real time and dynamically adjust educational content accordingly.

[1047] 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.

[1048] In this invention, the server includes: means for optimizing educational content based on a learner's learning style, learning pace, and emotional data using an artificial intelligence model; means for selecting appropriate educational content based on the learning style, learning pace, and emotional data; means having an emotion engine for acquiring and analyzing the learner's emotional data in real time; and means for providing the selected educational content to the learner. This not only provides optimal educational content tailored to the learner's learning style and pace, but also enables a more highly personalized learning experience that responds to the learner's emotional state during learning.

[1049] An "artificial intelligence model" is a computer program that analyzes data and learns patterns to make predictions and decisions.

[1050] "Learning style" refers to the method or approach that a learner uses to most effectively comprehend and acquire information, such as visual learning or auditory learning.

[1051] "Learning pace" refers to how quickly a learner can digest and understand educational content, and can be categorized as fast, normal, or slow.

[1052] "Educational Content" includes teaching materials and resources designed to teach a particular academic subject or skill, such as mathematics lessons or science experiment guides.

[1053] "Emotional data" is information that indicates the learner's current emotional state, including happiness, sadness, excitement, etc.

[1054] An "emotion engine" is software or a system that analyzes and recognizes a learner's real-time emotional state.

[1055] "Optimization" refers to adjusting a system or process to maximize performance or efficiency in order to achieve a specific purpose.

[1056] "Selection" is the act of selecting the most appropriate option from multiple choices or options.

[1057] "Provision" refers to the act of the system providing the necessary information or services to the user.

[1058] This invention is an educational platform that utilizes artificial intelligence (AI) models to provide educational content optimized for a learner's learning style, learning pace, and emotional data. This platform is composed of a server, a terminal, and a user.

[1059] Server Features

[1060] 1. Training the AI ​​model and emotion engine

[1061] The server uses artificial intelligence models to learn from learner data and optimize educational content. It also uses an emotion engine to analyze learner emotion data in real time. The main software used includes AI models such as TensorFlow and PyTorch, and emotion engines such as Affectiva and IBM Watson Emotion Analysis.

[1062] 2. Loading and optimizing learning content

[1063] The server loads pre-prepared learning content, including lessons in subjects like math and science, and caters to visual and auditory learning styles, allowing the server to optimize educational content based on learning style, learning pace, and emotional data.

[1064] 3. Data storage and content provision

[1065] The server stores learners' learning style, learning pace, and initial emotional data in a database and uses it to provide personalized learning experiences. This is done using cloud data services such as Amazon Web Services (AWS). The server then transmits optimized educational content to the device, where it can be accessed by the user.

[1066] Device Features

[1067] The device (PC or smartphone) receives learner input information and emotional data collected in real time and sends it to the server. The device also plays a role in displaying personalized educational content sent from the server to the user.

[1068] User operations

[1069] Users (learners) access the platform using their devices and log in. They input their learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data (e.g., happy, sad, excited). They then submit a request for the educational content they desire (e.g., math, science). The server processes this request and provides optimized content.

[1070] Specific examples

[1071] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[1072] Prompt Sentence Examples

[1073] Learning style: "I'm a visual learner."

[1074] Learning pace: "I like to learn at a fast pace."

[1075] Emotional information: "I feel excited right now."

[1076] In this way, the platform of the present invention can provide educational content tailored to the individual needs of learners, greatly improving learning efficiency.

[1077] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1078] Specific flow of program processing

[1079] Step 1: Initialize the server

[1080] The server loads learning content (e.g., math and science lessons). This includes content for multiple learning styles, such as visual and auditory learning. The hardware used is a cloud server, and the software is a database management system. The input is a set of files containing educational content prepared in advance, and the output is information indicating that the learning data has been loaded.

[1081] Specific behavior:

[1082] The server downloads the educational content from the cloud storage.

[1083] Load content into a database and categorize it by style.

[1084] Step 2: Training the AI ​​model and emotion engine

[1085] The server trains the AI ​​model and emotion engine using the learner's historical data and pre-prepared data. The software used is TensorFlow, PyTorch, Affectiva, and IBM Watson Emotion Analysis. The input is past learning data and emotion data, and the output is the trained model.

[1086] Specific behavior:

[1087] Cleanse historical and sentiment data and prepare it for machine learning.

[1088] Run the training process for the AI ​​model and emotion engine to set optimal parameters.

[1089] Step 3: Enroll learners

[1090] Users access the platform using their devices and create an account or log in. The input is the user's learning style, learning pace, and initial emotional data, and the output is a learner profile stored in a database.

[1091] Specific behavior:

[1092] The user inputs learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data from the terminal.

[1093] The server stores this information in a database.

[1094] Step 4: Request learning content

[1095] A user requests a specific educational content (e.g., mathematics). The request is sent from the device and processed by the server. The input is the user's content request, and the output is a confirmation that the request was received.

[1096] Specific behavior:

[1097] The user selects a particular educational content from the terminal and sends a request to the server.

[1098] The server receives the request and begins searching for the appropriate content.

[1099] Step 5: Obtaining learners' emotional information

[1100] The server uses an emotion engine to obtain the learner's emotional data in real time. The input is the user's current emotional information (e.g., facial recognition data, voice data), and the output is the analyzed emotional data.

[1101] Specific behavior:

[1102] The server receives emotional state data (facial recognition, voice analysis, etc.) sent from the user's device.

[1103] The emotion engine analyzes the data and identifies the emotional state (e.g., excitement, sadness).

[1104] Step 6: Deliver personalized learning content

[1105] The server takes into account the learning style and pace, as well as the acquired emotional data, to generate optimal educational content. The input is the learner profile stored on the server and real-time emotional data, and the output is optimized educational content.

[1106] Specific behavior:

[1107] The server uses AI models to generate optimal learning content, taking into account learning style, learning pace, and emotional data.

[1108] The content is sent to the terminal and made available to the user.

[1109] Step 7: Display educational content

[1110] The terminal receives the educational content sent from the server and displays it to the user. The input is the educational content sent from the server, and the output is the learning material displayed to the user.

[1111] Specific behavior:

[1112] The terminal receives the educational content transmitted from the server.

[1113] The content is displayed on the screen and users can begin learning.

[1114] In this way, the program's series of processes is meticulously planned to provide educational content optimized to the individual needs of each learner.

[1115] (Application example 2)

[1116] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1117] Traditional educational platforms face the challenge of providing customized educational content that responds to learners' individual learning styles, pace, and real-time emotional states. This makes it difficult to maintain learners' interest and maximize learning efficiency. Furthermore, there is a lack of systems for providing appropriate content to accommodate different learning styles, such as visual and auditory, which can lead to a decline in learning quality.

[1118] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for optimizing educational content based on the learner's learning style and learning pace using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace and real-time emotional data, means for providing the selected educational content to the learner, and means for displaying the optimized educational content on a smart device. This makes it possible to provide educational content optimized to the individual needs of the learner and maximize learning efficiency and interest.

[1119] An "artificial intelligence model" is an algorithm or statistical model that analyzes learner data and selects and generates optimal educational content.

[1120] "Learning style" is a term that refers to the methods or ways in which learners most effectively understand and absorb information.

[1121] "Learning pace" refers to the speed or rhythm at which a learner progresses through learning content.

[1122] "Educational content" refers to materials and information that include learning materials, lessons, exercises, and other learning subjects provided to learners.

[1123] "Real-time emotional data" refers to data capturing the learner's emotional state in real time, including, for example, joy, excitement, or sadness during learning.

[1124] "Smart devices" are electronic devices with internet connectivity that are used by learners, such as computers, smartphones, and smart glasses.

[1125] "Optimize" means to adjust or improve something to be best suited to a specific purpose.

[1126] "To select" means to decide and select a specific object from among many candidates or possibilities.

[1127] "Providing" refers to imparting and distributing necessary information and teaching materials to learners.

[1128] "Display" means to visually show information on the screen of an electronic device or the like.

[1129] A "system" is a complex consisting of multiple elements that interact and cooperate to achieve a specific function or purpose.

[1130] The present invention provides an educational platform that provides educational content optimized to the individual needs of learners. Specific embodiments for carrying out the present invention will be described below.

[1131] System Overview

[1132] The system of the present invention utilizes an artificial intelligence model to optimize educational content based on the learner's learning style, learning pace, and real-time emotional data, and provides it via smart devices. The main components of the system are a server, a terminal (smart device), and a user.

[1133] Hardware and Software Configuration

[1134] Hardware:

[1135] 1. Server: A high-performance computer server

[1136] 2. Smart Devices: Electronic devices with internet connectivity such as smart glasses, smartphones, tablets, etc.

[1137] software:

[1138] 1. Artificial intelligence model: Algorithms using machine learning frameworks such as TensorFlow

[1139] 2. Emotion recognition engine: Emotion analysis software such as EmotionEngine

[1140] 3. Content Management: Database System

[1141] 4. User Profile Management: UserProfile System

[1142] 5. Smart Device API: SmartGlassesAPI, etc.

[1143] Data processing and calculation

[1144] server:

[1145] 1. Initialization: The server loads learning content and trains the AI ​​model and emotion engine. The learning content includes lessons for math and science, for example, and includes content that supports multiple learning styles, such as visual and auditory.

[1146] 2. Acquiring learner information: The server stores the learner's learning style, learning pace, and real-time emotional data in a database, and generates optimal educational content based on this information.

[1147] Terminal (smart device):

[1148] 1. Information collection: The device collects learners' actions and reactions in real time and sends them to the server. This includes data from cameras, sensors, microphones, etc.

[1149] 2. Content display: The terminal displays the optimized educational content sent from the server and provides it to the learner.

[1150] Specific processing examples:

[1151] For example, if a learner is studying "Mathematics" through smart glasses and the emotion engine recognizes the "Excited" state, the server will determine that the learner's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the learner's excited state. The server then selects an appropriate lesson (e.g., "Mathematics: Lesson 3") and sends it to the user's device.

[1152] Example prompt sentence:

[1153] User learning style: Visual

[1154] User learning pace: Fast

[1155] Real-time emotions: excitement

[1156] Requested educational content: Mathematics

[1157] In this way, the system can provide educational content optimized to the needs of each individual learner, maximizing learning efficiency and interest.

[1158] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1159] Step 1:

[1160] Initialize the server:

[1161] The server loads the learning content and trains the artificial intelligence model and emotion engine. Specifically, the server retrieves educational content (e.g., math and science lessons) from the database and uses it as training data for the AI ​​model using a machine learning framework such as TensorFlow. It also trains the emotion recognition model using EmotionEngine. The inputs are the learning content and the initial data for the AI ​​model and emotion engine, and the outputs are the trained AI model and emotion recognition model.

[1162] Step 2:

[1163] User profile settings:

[1164] Users log in to the system and register their learning style, learning pace, initial emotional data, etc. This information is sent to the server via their terminal, and the server stores this information in a database. The input is the learning style, learning pace, and emotional data provided by the user from their terminal, and the output is the user profile information stored in the database.

[1165] Step 3:

[1166] Educational Content Request:

[1167] A user uses a device to request a specific educational content (e.g., mathematics). This request is sent to a server. The input is the content request from the user, and the output is the request data to the server.

[1168] Step 4:

[1169] Acquiring emotional information:

[1170] The server uses the EmotionEngine to obtain the learner's emotional information in real time. It uses the device's camera and microphone to analyze the learner's facial expressions and tone of voice to generate emotional data. The input is real-time camera feed and audio data, and the output is the emotion recognition results.

[1171] Step 5:

[1172] Generate personalized learning content:

[1173] The server generates optimal educational content based on learning style, learning pace, and real-time emotional data. It uses an AI model based on machine learning frameworks such as TensorFlow to analyze this data and select the most appropriate lessons and materials. The input is stored user profile information and real-time emotional data, and the output is optimized educational content.

[1174] Step 6:

[1175] Educational content provided by:

[1176] The server sends the generated optimized educational content to the smart device, which then displays it. The input is the educational content sent from the server, and the output is the learning material displayed on the device.

[1177] Specifically, when a learner requests "math" content through smart glasses, the emotion engine recognizes the "excitement" state. For a learner whose learning style is identified as "visual" and whose learning pace is "fast," the server selects math lessons that correspond to the excitement state appropriate for a visual and fast pace and displays them on the smart glasses.

[1178] Example prompt sentence:

[1179] User learning style: Visual

[1180] User learning pace: Fast

[1181] Real-time emotions: excitement

[1182] Requested educational content: Mathematics

[1183] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1184] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1185] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1186] [Fourth embodiment]

[1187] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1188] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1189] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1190] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1191] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1192] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1193] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1194] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1195] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1196] 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.

[1197] 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.

[1198] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1199] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1200] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for each learner's learning style and pace.

[1201] System configuration

[1202] server

[1203] 1. The server stores the learner's information in a database.

[1204] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace.

[1205] 3. The server trains the AI ​​model and generates optimal educational content using the learner's historical data and real-time learning data.

[1206] 4. The server provides personalized educational content when accessed by the learner.

[1207] User

[1208] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[1209] 2. Learners input their learning style (e.g., visual, auditory) and learning pace (e.g., fast, normal, slow).

[1210] 3. Learners submit requests for desired educational content (e.g., math, science).

[1211] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[1212] Terminal

[1213] 1. The terminal receives input information from the learner and sends it to the server.

[1214] 2. The terminal displays the personalized educational content sent from the server.

[1215] Explanation of program processing

[1216] 1. Initialize the server:

[1217] The server loads learning content, such as math and science lessons, and trains the AI ​​model.

[1218] 2. Learner Registration:

[1219] Users (learners) register their learning style and pace with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[1220] 3. Learning content requests:

[1221] When a user logs into the learning platform and requests specific educational content, the server selects the most appropriate educational content to suit the user's learning style and pace.

[1222] 4. Providing personalized learning content:

[1223] The server uses the AI ​​model to generate optimized educational content and sends it back to the user, who then displays it on their device.

[1224] Specific examples

[1225] For example, if a user requests "Math" content, the server verifies that the user's learning style is registered as "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model to search for math lessons that are suitable for a visual and fast-paced learning style. The server then selects an appropriate lesson (e.g., "Math: Lesson 1") and sends it to the user's device. The user can then efficiently progress through this lesson.

[1226] In this way, this platform can provide educational content optimized to the needs of each individual learner, improving learning efficiency.

[1227] The processing flow will be explained below.

[1228] Step 1:

[1229] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model.

[1230] Step 2:

[1231] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[1232] Step 3:

[1233] The server trains the AI ​​model, which contains algorithms for selecting the most appropriate educational content based on learner data.

[1234] Step 4:

[1235] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[1236] Step 5:

[1237] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[1238] Step 6:

[1239] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[1240] Step 7:

[1241] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[1242] Step 8:

[1243] The server generates personalized educational content selected by the AI ​​model and sends it to the device.

[1244] Step 9:

[1245] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[1246] Step 10:

[1247] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model, enabling more effective personalization.

[1248] Example 1

[1249] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1250] Conventional educational systems have the problem of being unable to provide educational content optimized for each learner's learning style and pace. This reduces learners' learning efficiency and makes it difficult to maintain their interest and motivation. Furthermore, there is a lack of a mechanism for instantly providing the educational content requested by learners, making it impossible to provide a fast and appropriate learning experience. Furthermore, the cost and effort required to deal with the technical complexity of individually optimizing educational content is also a major issue.

[1251] 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.

[1252] In this invention, the server includes means for loading educational data and training a generative AI model to classify optimal learning styles and paces, means for a learner to input and save their learning style and learning pace from a terminal, and means for selecting and providing personalized educational content using the generative AI model when a learner requests specific educational content, thereby enabling educational content optimized for the individual needs of each learner to be provided quickly and appropriately.

[1253] A "server" is a device that stores learner information, loads educational data, trains generative AI models, and provides personalized educational content requested by learners.

[1254] A "generative AI model" is a model that uses artificial intelligence technology to optimize educational content and select appropriate content based on the learner's learning style and pace.

[1255] "Learning style" refers to the way in which a learner absorbs knowledge most efficiently, such as visual or auditory.

[1256] "Learning pace" refers to the speed at which a learner can most efficiently progress through their studies, such as fast, normal, or slow.

[1257] "Educational content" is a general term for the teaching materials and lessons that learners use to learn, and is provided in the form of video, audio, text, etc.

[1258] A "terminal" is a device used by a learner to access the server, log in, request content, and view received content.

[1259] A "database" is a system for efficiently storing and managing data such as learner information, learning style, and pace.

[1260] "Classification" means organizing educational content based on collected data according to the learner's learning style and pace and dividing it into appropriate categories.

[1261] The present invention is an educational system that provides personalized educational content based on the learner's learning style and pace. This system is mainly composed of a server, a terminal, and a user. The specific configuration and operation are described below.

[1262] server

[1263] The server loads educational data from Amazon S3 and uses the training data to build a generative AI model (e.g., using TensorFlow). The server stores learner information (learning style and pace) in a MySQL database. The server also categorizes the educational content requested by the learner and selects and provides the appropriate content.

[1264] Loading training data and training the AI ​​model

[1265] The server downloads educational content from Amazon S3, for example, contained in a folder called "math_lessons," locally, and uses TensorFlow to train a generative AI model that determines the optimal learning style and pace based on past learning data.

[1266] User Roles

[1267] Users (learners) access the platform using their terminals and log in. After logging in, users input and set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow). This information is stored in a database by the server.

[1268] Educational Content Requests

[1269] The user selects the desired educational content (e.g., mathematics, science) from the platform menu, clicks the request button, and the device sends the request to the server in HTTPS format.

[1270] Response from the server

[1271] The server receives the learner's request and uses a trained generative AI model to select the most appropriate educational content, which is then sent back to the device.

[1272] Device behavior

[1273] The device receives the response sent from the server and displays appropriate educational content, for example, playing video educational content for visual and fast-paced learners.

[1274] Specific operation example

[1275] For example, if a user requests "Math" content, the server uses an AI model to determine that the user has a visual, fast-paced learning style. The content "interactive_math_lesson_1.mp4" is selected and sent from the server to the device. The device then displays this video to the user, helping them learn more efficiently.

[1276] Prompt Sentence Examples

[1277] For example, a user can request on a learning platform, "Can you provide me with fast-paced visual lessons in math?" and the server can select and provide the most appropriate content.

[1278] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[1279] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1280] Step 1: Initialize the server

[1281] Server behavior:

[1282] When the server is powered on, it boots up an OS (e.g., Ubuntu). The server loads educational content from Amazon S3 and downloads training data locally. Specifically, all content in the "math_lessons" folder stored in Amazon S3 is downloaded. Next, the server uses TensorFlow to train a generative AI model. The training data includes data on past learning history and learning style. The server uses this data to generate a model that classifies learning style and pace.

[1283] Input: Educational content, past learning history data

[1284] Data processing & calculation: Download data and train AI models

[1285] Output: A trained generative AI model

[1286] Step 2: Enroll learners

[1287] User Action:

[1288] Users use their devices to access the platform's login page and enter their authentication information (username, password) to log in. After logging in, users are taken to a dashboard screen where they can set their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow).

[1289] Server behavior:

[1290] The server receives the learning style and pace sent by the learner and stores them in a MySQL database. Specifically, it stores the data in the corresponding columns in the table that stores user information.

[1291] Input: Learner style and pace information

[1292] Data processing and calculation: Receiving data and saving it to the database

[1293] Output: Saved learner information

[1294] Step 3: Request learning content

[1295] User Action:

[1296] The user selects a specific educational content (e.g., mathematics) from the platform's menu and submits a request for the educational content by clicking a request button, which sends the request to the server.

[1297] Terminal behavior:

[1298] The device sends the learner's request to the server as an HTTPS request, for example, calling the endpoint " / request-content?subject=math".

[1299] Input: User request for educational content

[1300] Data processing & calculation: Sending a request

[1301] Output: Request data to the server

[1302] Step 4: Select and deliver personalized learning content

[1303] Server behavior:

[1304] The server receives the learner's request. The request data also includes the learner's learning style and pace. Based on the saved learning style and pace information, the server uses a generative AI model to select the most suitable educational content. For example, it determines that the content "interactive_math_lesson_1.mp4" is most suitable for a "visual" and "fast-paced" learner. Based on this selection result, the server generates a response including the content ID and password and sends it to the device.

[1305] Input: Request data from user, learning style and pace information

[1306] Data processing & calculation: Content selection and response generation using AI models

[1307] Output: Response data for selected educational content

[1308] Step 5: Display educational content

[1309] Terminal behavior:

[1310] The device receives the response from the server and displays the corresponding educational content by launching a video player and streaming a file such as "interactive_math_lesson_1.mp4."

[1311] Input: Response data from the server

[1312] Data processing & calculation: Response analysis, content display

[1313] Output: The educational content displayed to the learner

[1314] This makes it possible to quickly and appropriately provide educational content that is optimized to the needs of each individual learner.

[1315] (Application example 1)

[1316] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1317] With conventional education platforms, it was difficult to provide educational content that was optimized for each learner's individual learning style and pace.In addition, when it came to training workers on factory floors, there was a lack of technology to provide training methods that were suited to each worker, making it difficult to efficiently improve their skills and ensure safe work.

[1318] 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.

[1319] In this invention, the server includes means for optimizing educational content based on the learning style and learning pace of a learner using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace, means for providing the selected educational content to the learner, and means including a factory robot for providing optimal training content based on the learning style and learning pace of a worker, thereby enabling the provision of optimal educational and training content according to the individual needs of the learner and worker.

[1320] An "artificial intelligence model" refers to an algorithm that uses large amounts of data to learn patterns and make predictions and classifications.

[1321] "Learning style" refers to the way in which a learner most effectively perceives information, and can include visual, auditory, tactile, etc.

[1322] "Learning pace" refers to the speed at which a learner absorbs and comprehends information, and can include fast, normal, or slow.

[1323] "Educational content" refers to information and materials provided to learners, including text, video, audio, illustrations, etc.

[1324] "Optimization means" refers to the process of using artificial intelligence models and algorithms to select educational content with the optimal format and content that suits the learner's learning style and pace.

[1325] "Means of selection" refers to a method or system for extracting from multiple educational contents the one that best suits the learner's requirements.

[1326] "Means of delivery" refers to the means for delivering the selected educational content to learners, including delivery via the Internet and downloads.

[1327] A "factory robot" is a mechanical device designed to perform various tasks within a factory, and is capable of providing training content to workers.

[1328] The present invention is a system for providing educational content optimized to the individual needs of learners and factory workers. Specific embodiments of this system will be described below.

[1329] Hardware and Software Configuration

[1330] The server has the following responsibilities:

[1331] 1. Database: Stores information about learners and workers. Specifically, a database such as MySQL is used.

[1332] 2. Loading educational content: Loading and categorizing pre-prepared educational content.

[1333] 3. Training artificial intelligence models: Using software such as TensorFlow, AI models are trained using historical and real-time data from learners and workers.

[1334] 4. Generate and deliver optimal content: Generate optimal educational content based on the learning style and pace of learners and workers, and deliver personalized content.

[1335] Terminals are devices that students and workers use to communicate with the server, and can be PCs, smartphones, tablets, or factory robots.

[1336] Processing Details

[1337] The server receives input from learners and workers and uses the AI ​​model to generate optimized educational content based on that information. Specifically, if visual learning is effective, content that is easy to understand visually will be generated, and for workers who learn at a fast pace, short sessions will be selected to enable efficient learning.

[1338] Learners and workers input their own learning style and pace from their devices and select the educational content they want. This information is sent to the server, which then generates optimized educational content and distributes it to the devices.

[1339] Specific operations

[1340] For learners

[1341] 1. Learners access the platform using their devices and log in.

[1342] 2. Learners input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[1343] 3. Learners request the educational content they want (math, science, etc.).

[1344] For example, if a visual, fast-paced learner requests "Math" content, the following will happen:

[1345] The server uses AI models to select visual, fast-paced math lessons.

[1346] Generate content that includes visually easy-to-understand heat maps, diagrams, and short video clips.

[1347] The generated content is provided to the learner's device to advance their learning.

[1348] For workers

[1349] 1. The worker logs in using the factory robot's interface.

[1350] 2. Workers input their learning style (visual, auditory, etc.) and pace (fast, normal, slow).

[1351] 3. Workers request the training content they desire (e.g., safe operations, quality control, etc.).

[1352] For example, if a fast visual learner requests "Quality Control Training," the following happens:

[1353] The robot receives visual, fast-paced, quality-controlled training content from the server.

[1354] The robot displays heat maps and diagrams that are easy for workers to understand visually, guiding them to important checkpoints.

[1355] Workers will follow the robot's instructions as they go through the training.

[1356] Example prompts to input to the generative AI model

[1357] "Provide optimal quality control training content for factory workers who are fast-paced visual learners."

[1358] "We will provide training on safe operation using audio guidance. Please also explain in detail the precautions to take."

[1359] In this way, the system of the present invention can generate and provide optimal education and training content tailored to the individual needs of learners and workers, thereby enabling efficient and effective education and training.

[1360] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1361] Step 1:

[1362] The server stores information about learners and workers in a database, including their learning style (visual, auditory, etc.) and learning pace (fast, normal, slow), forming the basis for providing educational content optimized to the individual needs of each learner and worker.

[1363] Step 2:

[1364] The server loads pre-prepared educational content and categorizes it according to each learning style and pace. Specifically, it categorizes lessons such as math and science into visually and aurally easy-to-understand content, and stores each content in a database. This prepares the content for efficient delivery.

[1365] Step 3:

[1366] The server collects historical data and real-time learning data from learners and workers to train the AI ​​model. Using software such as TensorFlow, the model is trained to generate optimal educational content based on the characteristics of learners and workers. This AI model functions as an algorithm that processes the data and makes predictions and classifications.

[1367] Step 4:

[1368] Learners and workers access the platform and log in using a device (such as a PC, smartphone, or factory robot). The device receives the user's input information and sends it to the server. The server then imports the received learning style and pace information into a database and uses it to generate personalized content.

[1369] Step 5:

[1370] Learners and workers submit requests for the educational content they desire (mathematics, science, safe operations, quality control, etc.). The request is sent from the device to the server, which uses an AI model to generate the optimal educational content based on the request, learning style, and pace.

[1371] Step 6:

[1372] The server uses the AI ​​model to generate optimized educational content and transmit it to the device. Specifically, it selects training content that is easy to understand visually, including heat maps, diagrams, and audio guidance, and outputs the results.

[1373] Step 7:

[1374] The terminal receives the personalized educational content sent from the server and displays it to the learner and worker, allowing the learner and worker to progress with their studies using the optimized content.

[1375] In this way, it is possible to provide individualized and optimal education and training to learners and workers through each step.

[1376] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1377] The present invention is an educational platform that utilizes artificial intelligence (AI) to provide educational content optimized for a learner's learning style, learning pace, and emotions. A specific embodiment of this system is described below.

[1378] System configuration

[1379] server

[1380] 1. The server is responsible for storing learner information in a database.

[1381] 2. The server loads pre-prepared educational content and categorizes it according to each learning style and pace, and also obtains emotional information using an emotion engine.

[1382] 3. The server trains the AI ​​model and emotion engine, and generates optimal educational content using the learner's historical data, real-time learning data, and emotion data.

[1383] 4. The server provides personalized educational content when accessed by the learner.

[1384] User

[1385] 1. Learners access the platform using a device (PC, smartphone, etc.) and log in.

[1386] 2. Learners input or provide learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and real-time emotional information (e.g., happy, sad, excited).

[1387] 3. Learners submit requests for desired educational content (e.g., math, science).

[1388] 4. The learner receives the personalized educational content provided by the server and proceeds with their learning.

[1389] Terminal

[1390] 1. The terminal receives input information and real-time emotional information from the learner and transmits it to the server.

[1391] 2. The terminal displays the personalized educational content sent from the server.

[1392] Explanation of program processing

[1393] 1. Initialize the server:

[1394] The server loads learning content and trains the AI ​​model and emotion engine, including lessons in math and science, catering to multiple learning styles, including visual and auditory.

[1395] 2. Learner Registration:

[1396] Users (learners) register their learning style and pace, as well as initial emotional data, with the server, which stores this information in a database and uses it to provide a personalized learning experience.

[1397] 3. Learning content requests:

[1398] A user logs into a learning platform and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[1399] 4. Acquiring learners' emotional information:

[1400] The server uses an emotion engine to recognize the learner's emotional information in real time, thereby understanding the learner's emotional state during learning.

[1401] 5. Providing personalized learning content:

[1402] The server takes into account the learner's learning style and pace, as well as emotional information, and uses an AI model and emotional engine to generate optimized educational content, which is then sent to the device.

[1403] 6. Display of educational content:

[1404] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their studies.

[1405] Specific examples

[1406] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[1407] In this way, this platform can provide educational content optimized to the needs of individual learners, improving learning efficiency. By combining it with an emotion engine, it is possible to provide a more highly personalized learning experience.

[1408] The processing flow will be explained below.

[1409] Step 1:

[1410] The server starts and instantiates the class "LearnSphere", which loads the learning content as an initial setting and prepares to train the AI ​​model and emotion engine.

[1411] Step 2:

[1412] The server loads pre-prepared educational content, including lessons in, for example, math and science, that caters to multiple learning styles, including visual and auditory.

[1413] Step 3:

[1414] The server trains the AI ​​model and emotion engine. The AI ​​model contains algorithms for selecting optimal educational content based on learner data. The emotion engine collects and analyzes user emotion data in real time.

[1415] Step 4:

[1416] A user accesses the platform from a device and enters their learning style (e.g., visual) and learning pace (e.g., fast) on the sign-up page.

[1417] Step 5:

[1418] The terminal sends the user's input information to the server, which receives it and stores it in a database along with the learner's ID.

[1419] Step 6:

[1420] A user logs in from a terminal and requests a specific educational content (e.g., mathematics). This request is sent to the server.

[1421] Step 7:

[1422] The server retrieves information about the user's learning style and pace from a database, then uses this information to select the most suitable educational content using an AI model.

[1423] Step 8:

[1424] The server uses an emotion engine to recognize the user's emotional information in real time, for example, by analyzing the user's facial expressions and tone of voice through the user's webcam and microphone.

[1425] Step 9:

[1426] The server further optimizes the educational content selected by the AI ​​model based on the acquired emotional information, thereby adjusting the content format and difficulty level according to the user's emotional state.

[1427] Step 10:

[1428] The server generates optimized and personalized educational content and transmits it to the terminal.

[1429] Step 11:

[1430] The terminal receives the educational content sent from the server and displays it to the user, who then uses the content to advance their learning.

[1431] Step 12:

[1432] After a learner has finished consuming educational content, the server collects the data and uses it to improve the AI ​​model and emotion engine, enabling more effective personalization.

[1433] Example 2

[1434] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1435] The present invention aims to solve the problem that it is difficult for conventional educational platforms to provide educational content that is tailored to the learner's learning style and pace, as well as to provide individually optimized educational content that takes into account real-time emotional data during learning. Specifically, there is a need to grasp the learner's emotional state in real time and dynamically adjust educational content accordingly.

[1436] 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.

[1437] In this invention, the server includes: means for optimizing educational content based on a learner's learning style, learning pace, and emotional data using an artificial intelligence model; means for selecting appropriate educational content based on the learning style, learning pace, and emotional data; means having an emotion engine for acquiring and analyzing the learner's emotional data in real time; and means for providing the selected educational content to the learner. This not only provides optimal educational content tailored to the learner's learning style and pace, but also enables a more highly personalized learning experience that responds to the learner's emotional state during learning.

[1438] An "artificial intelligence model" is a computer program that analyzes data and learns patterns to make predictions and decisions.

[1439] "Learning style" refers to the method or approach that a learner uses to most effectively comprehend and acquire information, such as visual learning or auditory learning.

[1440] "Learning pace" refers to how quickly a learner can digest and understand educational content, and can be categorized as fast, normal, or slow.

[1441] "Educational Content" includes teaching materials and resources designed to teach a particular academic subject or skill, such as mathematics lessons or science experiment guides.

[1442] "Emotional data" is information that indicates the learner's current emotional state, including happiness, sadness, excitement, etc.

[1443] An "emotion engine" is software or a system that analyzes and recognizes a learner's real-time emotional state.

[1444] "Optimization" refers to adjusting a system or process to maximize performance or efficiency in order to achieve a specific purpose.

[1445] "Selection" is the act of selecting the most appropriate option from multiple choices or options.

[1446] "Provision" refers to the act of the system providing the necessary information or services to the user.

[1447] This invention is an educational platform that utilizes artificial intelligence (AI) models to provide educational content optimized for a learner's learning style, learning pace, and emotional data. This platform is composed of a server, a terminal, and a user.

[1448] Server Features

[1449] 1. Training the AI ​​model and emotion engine

[1450] The server uses artificial intelligence models to learn from learner data and optimize educational content. It also uses an emotion engine to analyze learner emotion data in real time. The main software used includes AI models such as TensorFlow and PyTorch, and emotion engines such as Affectiva and IBM Watson Emotion Analysis.

[1451] 2. Loading and optimizing learning content

[1452] The server loads pre-prepared learning content, including lessons in subjects like math and science, and caters to visual and auditory learning styles, allowing the server to optimize educational content based on learning style, learning pace, and emotional data.

[1453] 3. Data storage and content provision

[1454] The server stores learners' learning style, learning pace, and initial emotional data in a database and uses it to provide personalized learning experiences. This is done using cloud data services such as Amazon Web Services (AWS). The server then transmits optimized educational content to the device, where it can be accessed by the user.

[1455] Device Features

[1456] The device (PC or smartphone) receives learner input information and emotional data collected in real time and sends it to the server. The device also plays a role in displaying personalized educational content sent from the server to the user.

[1457] User operations

[1458] Users (learners) access the platform using their devices and log in. They input their learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data (e.g., happy, sad, excited). They then submit a request for the educational content they desire (e.g., math, science). The server processes this request and provides optimized content.

[1459] Specific examples

[1460] For example, if a user requests "Math" content and the emotion engine recognizes the "Excited" state, the server determines that the user's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the user's excited state. As a result, an appropriate lesson (e.g., "Math: Lesson 3") is selected and sent to the user's device. The user can efficiently progress through this lesson.

[1461] Prompt Sentence Examples

[1462] Learning style: "I'm a visual learner."

[1463] Learning pace: "I like to learn at a fast pace."

[1464] Emotional information: "I feel excited right now."

[1465] In this way, the platform of the present invention can provide educational content tailored to the individual needs of learners, greatly improving learning efficiency.

[1466] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1467] Specific flow of program processing

[1468] Step 1: Initialize the server

[1469] The server loads learning content (e.g., math and science lessons). This includes content for multiple learning styles, such as visual and auditory learning. The hardware used is a cloud server, and the software is a database management system. The input is a set of files containing educational content prepared in advance, and the output is information indicating that the learning data has been loaded.

[1470] Specific behavior:

[1471] The server downloads the educational content from the cloud storage.

[1472] Load content into a database and categorize it by style.

[1473] Step 2: Training the AI ​​model and emotion engine

[1474] The server trains the AI ​​model and emotion engine using the learner's historical data and pre-prepared data. The software used is TensorFlow, PyTorch, Affectiva, and IBM Watson Emotion Analysis. The input is past learning data and emotion data, and the output is the trained model.

[1475] Specific behavior:

[1476] Cleanse historical and sentiment data and prepare it for machine learning.

[1477] Run the training process for the AI ​​model and emotion engine to set optimal parameters.

[1478] Step 3: Enroll learners

[1479] Users access the platform using their devices and create an account or log in. The input is the user's learning style, learning pace, and initial emotional data, and the output is a learner profile stored in a database.

[1480] Specific behavior:

[1481] The user inputs learning style (e.g., visual, auditory), learning pace (e.g., fast, normal, slow), and initial emotional data from the terminal.

[1482] The server stores this information in a database.

[1483] Step 4: Request learning content

[1484] A user requests a specific educational content (e.g., mathematics). The request is sent from the device and processed by the server. The input is the user's content request, and the output is a confirmation that the request was received.

[1485] Specific behavior:

[1486] The user selects a particular educational content from the terminal and sends a request to the server.

[1487] The server receives the request and begins searching for the appropriate content.

[1488] Step 5: Obtaining learners' emotional information

[1489] The server uses an emotion engine to obtain the learner's emotional data in real time. The input is the user's current emotional information (e.g., facial recognition data, voice data), and the output is the analyzed emotional data.

[1490] Specific behavior:

[1491] The server receives emotional state data (facial recognition, voice analysis, etc.) sent from the user's device.

[1492] The emotion engine analyzes the data and identifies the emotional state (e.g., excitement, sadness).

[1493] Step 6: Deliver personalized learning content

[1494] The server takes into account the learning style and pace, as well as the acquired emotional data, to generate optimal educational content. The input is the learner profile stored on the server and real-time emotional data, and the output is optimized educational content.

[1495] Specific behavior:

[1496] The server uses AI models to generate optimal learning content, taking into account learning style, learning pace, and emotional data.

[1497] The content is sent to the terminal and made available to the user.

[1498] Step 7: Display educational content

[1499] The terminal receives the educational content sent from the server and displays it to the user. The input is the educational content sent from the server, and the output is the learning material displayed to the user.

[1500] Specific behavior:

[1501] The terminal receives the educational content transmitted from the server.

[1502] The content is displayed on the screen and users can begin learning.

[1503] In this way, the program's series of processes is meticulously planned to provide educational content optimized to the individual needs of each learner.

[1504] (Application example 2)

[1505] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1506] Traditional educational platforms face the challenge of providing customized educational content that responds to learners' individual learning styles, pace, and real-time emotional states. This makes it difficult to maintain learners' interest and maximize learning efficiency. Furthermore, there is a lack of systems for providing appropriate content to accommodate different learning styles, such as visual and auditory, which can lead to a decline in learning quality.

[1507] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for optimizing educational content based on the learner's learning style and learning pace using an artificial intelligence model, means for selecting appropriate educational content based on the learning style and learning pace and real-time emotional data, means for providing the selected educational content to the learner, and means for displaying the optimized educational content on a smart device. This makes it possible to provide educational content optimized to the individual needs of the learner and maximize learning efficiency and interest.

[1508] An "artificial intelligence model" is an algorithm or statistical model that analyzes learner data and selects and generates optimal educational content.

[1509] "Learning style" is a term that refers to the methods or ways in which learners most effectively understand and absorb information.

[1510] "Learning pace" refers to the speed or rhythm at which a learner progresses through learning content.

[1511] "Educational content" refers to materials and information that include learning materials, lessons, exercises, and other learning subjects provided to learners.

[1512] "Real-time emotional data" refers to data capturing the learner's emotional state in real time, including, for example, joy, excitement, or sadness during learning.

[1513] "Smart devices" are electronic devices with internet connectivity that are used by learners, such as computers, smartphones, and smart glasses.

[1514] "Optimize" means to adjust or improve something to be best suited to a specific purpose.

[1515] "To select" means to decide and select a specific object from among many candidates or possibilities.

[1516] "Providing" refers to imparting and distributing necessary information and teaching materials to learners.

[1517] "Display" means to visually show information on the screen of an electronic device or the like.

[1518] A "system" is a complex consisting of multiple elements that interact and cooperate to achieve a specific function or purpose.

[1519] The present invention provides an educational platform that provides educational content optimized to the individual needs of learners. Specific embodiments for carrying out the present invention will be described below.

[1520] System Overview

[1521] The system of the present invention utilizes an artificial intelligence model to optimize educational content based on the learner's learning style, learning pace, and real-time emotional data, and provides it via smart devices. The main components of the system are a server, a terminal (smart device), and a user.

[1522] Hardware and Software Configuration

[1523] Hardware:

[1524] 1. Server: A high-performance computer server

[1525] 2. Smart Devices: Electronic devices with internet connectivity such as smart glasses, smartphones, tablets, etc.

[1526] software:

[1527] 1. Artificial intelligence model: Algorithms using machine learning frameworks such as TensorFlow

[1528] 2. Emotion recognition engine: Emotion analysis software such as EmotionEngine

[1529] 3. Content Management: Database System

[1530] 4. User Profile Management: UserProfile System

[1531] 5. Smart Device API: SmartGlassesAPI, etc.

[1532] Data processing and calculation

[1533] server:

[1534] 1. Initialization: The server loads learning content and trains the AI ​​model and emotion engine. The learning content includes lessons for math and science, for example, and includes content that supports multiple learning styles, such as visual and auditory.

[1535] 2. Acquiring learner information: The server stores the learner's learning style, learning pace, and real-time emotional data in a database, and generates optimal educational content based on this information.

[1536] Terminal (smart device):

[1537] 1. Information collection: The device collects learners' actions and reactions in real time and sends them to the server. This includes data from cameras, sensors, microphones, etc.

[1538] 2. Content display: The terminal displays the optimized educational content sent from the server and provides it to the learner.

[1539] Specific processing examples:

[1540] For example, if a learner is studying "Mathematics" through smart glasses and the emotion engine recognizes the "Excited" state, the server will determine that the learner's learning style is "visual" and their learning pace is registered as "fast." The server then uses the AI ​​model and emotion engine to search for math lessons that are suitable for a visual, fast-paced learning style and match the learner's excited state. The server then selects an appropriate lesson (e.g., "Mathematics: Lesson 3") and sends it to the user's device.

[1541] Example prompt sentence:

[1542] User learning style: Visual

[1543] User learning pace: Fast

[1544] Real-time emotions: excitement

[1545] Requested educational content: Mathematics

[1546] In this way, the system can provide educational content optimized to the needs of each individual learner, maximizing learning efficiency and interest.

[1547] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1548] Step 1:

[1549] Initialize the server:

[1550] The server loads the learning content and trains the artificial intelligence model and emotion engine. Specifically, the server retrieves educational content (e.g., math and science lessons) from the database and uses it as training data for the AI ​​model using a machine learning framework such as TensorFlow. It also trains the emotion recognition model using EmotionEngine. The inputs are the learning content and the initial data for the AI ​​model and emotion engine, and the outputs are the trained AI model and emotion recognition model.

[1551] Step 2:

[1552] User profile settings:

[1553] Users log in to the system and register their learning style, learning pace, initial emotional data, etc. This information is sent to the server via their terminal, and the server stores this information in a database. The input is the learning style, learning pace, and emotional data provided by the user from their terminal, and the output is the user profile information stored in the database.

[1554] Step 3:

[1555] Educational Content Request:

[1556] A user uses a device to request a specific educational content (e.g., mathematics). This request is sent to a server. The input is the content request from the user, and the output is the request data to the server.

[1557] Step 4:

[1558] Acquiring emotional information:

[1559] The server uses the EmotionEngine to obtain the learner's emotional information in real time. It uses the device's camera and microphone to analyze the learner's facial expressions and tone of voice to generate emotional data. The input is real-time camera feed and audio data, and the output is the emotion recognition results.

[1560] Step 5:

[1561] Generate personalized learning content:

[1562] The server generates optimal educational content based on learning style, learning pace, and real-time emotional data. It uses an AI model based on machine learning frameworks such as TensorFlow to analyze this data and select the most appropriate lessons and materials. The input is stored user profile information and real-time emotional data, and the output is optimized educational content.

[1563] Step 6:

[1564] Educational content provided by:

[1565] The server sends the generated optimized educational content to the smart device, which then displays it. The input is the educational content sent from the server, and the output is the learning material displayed on the device.

[1566] Specifically, when a learner requests "math" content through smart glasses, the emotion engine recognizes the "excitement" state. For a learner whose learning style is identified as "visual" and whose learning pace is "fast," the server selects math lessons that correspond to the excitement state appropriate for a visual and fast pace and displays them on the smart glasses.

[1567] Example prompt sentence:

[1568] User learning style: Visual

[1569] User learning pace: Fast

[1570] Real-time emotions: excitement

[1571] Requested educational content: Mathematics

[1572] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1573] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1574] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1575] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1576] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1577] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1578] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1579] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1580] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1581] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1582] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1583] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1584] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1585] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1586] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1587] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1588] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1589] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1590] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1591] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1592] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1593] The following is further disclosed regarding the above embodiment.

[1594] (Claim 1)

[1595] A means of optimizing educational content based on a learner's learning style and pace using artificial intelligence models;

[1596] means for selecting appropriate educational content based on said learning style and learning pace;

[1597] means for providing the selected educational content to a learner;

[1598] A system including:

[1599] (Claim 2)

[1600] 10. The system of claim 1, comprising content provided in partnership with an educational institution.

[1601] (Claim 3)

[1602] 10. The system of claim 1, wherein the educational content is adapted to local educational regulations.

[1603] "Example 1"

[1604] (Claim 1)

[1605] A means for the server to load educational data and train a generative AI model to classify optimal learning styles and paces;

[1606] A means for a learner to input and save their learning style and pace from a terminal;

[1607] a means for using a generative AI model to select and deliver personalized educational content when a learner requests specific educational content;

[1608] A system including:

[1609] (Claim 2)

[1610] 10. The system of claim 1, wherein the educational content is provided through a partnership with an educational institution or the like.

[1611] (Claim 3)

[1612] 10. The system of claim 1, wherein the educational content is adapted to local educational regulations.

[1613] "Application Example 1"

[1614] (Claim 1)

[1615] A means of optimizing educational content based on a learner's learning style and pace using artificial intelligence models;

[1616] means for selecting appropriate educational content based on said learning style and learning pace;

[1617] means for providing the selected educational content to a learner;

[1618] a factory robot that provides optimal training content based on the worker's learning style and pace;

[1619] A system including:

[1620] (Claim 2)

[1621] 10. The system of claim 1, comprising content provided in partnership with an educational institution.

[1622] (Claim 3)

[1623] 10. The system of claim 1, wherein the educational content is adapted to local educational regulations.

[1624] "Example 2: Combining Emotion Engines"

[1625] (Claim 1)

[1626] A means of optimizing educational content based on learners' learning style and pace, as well as emotional data, using artificial intelligence models;

[1627] means for selecting appropriate educational content based on said learning style, learning pace and emotional data;

[1628] A means having an emotion engine that acquires and analyzes learner emotion data in real time;

[1629] means for providing the selected educational content to a learner;

[1630] A system including:

[1631] (Claim 2)

[1632] 10. The system of claim 1, comprising content provided in partnership with an educational institution.

[1633] (Claim 3)

[1634] 10. The system of claim 1, wherein the educational content is adapted to local educational regulations.

[1635] "Application example 2 when combining emotion engines"

[1636] (Claim 1)

[1637] A means of optimizing educational content based on a learner's learning style and pace using artificial intelligence models;

[1638] means for selecting appropriate educational content based on said learning style and learning pace and real-time emotional data;

[1639] means for providing the selected educational content to a learner;

[1640] A means for displaying the optimized educational content by a smart device;

[1641] A system including:

[1642] (Claim 2)

[1643] 10. The system of claim 1, comprising content provided in partnership with an educational institution.

[1644] (Claim 3)

[1645] 10. The system of claim 1, wherein the educational content is adapted to local educational regulations. [Explanation of symbols]

[1646] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of optimizing educational content based on a learner's learning style and pace using artificial intelligence models; means for selecting appropriate educational content based on said learning style and learning pace; means for providing the selected educational content to a learner; A system including:

2. 10. The system of claim 1, including content provided in partnership with an educational institution.

3. The system of claim 1 , wherein the educational content is adapted to local educational regulations.

Images