system

Abstract

Provide a system. The method includes: storing data in a database that provides learning content; a means for constructing a generated learning content model based on the stored data; means for generating customized learning content based on user input information; a means for collecting user feedback and test results to optimize the learning content model; A system including:

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] Currently, individualized instruction can only be provided in limited environments, making it difficult to address the learning needs of each student. Furthermore, there is a lack of systems that can provide customized learning content based on each student's learning pace and level of understanding. As a result, the quality of education and students' learning efficiency decline, posing a serious problem, especially in areas with limited educational resources. To address these issues, the present invention aims to provide a system that uses generative AI to efficiently and effectively provide personalized learning content. [Means for solving the problem]

[0005] The present invention employs the following means: First, a system is provided that includes a means for storing data in a database that provides learning content, a means for constructing a learning content model based on the stored data, a means for generating customized learning content based on user input information, and a means for collecting feedback and test results from users and optimizing the learning content model. This system makes it possible to provide learning content optimized for each user, improving the user's learning efficiency and satisfaction.

[0006] "Learning content" refers to teaching materials and resources used for educational purposes, and includes various formats such as text, visuals, and videos.

[0007] A "database" refers to an information storage system that systematically organizes and stores information so that it can be easily searched and retrieved.

[0008] "Generated learning content model" refers to a model that the generative AI learns from stored learning content and generates and optimizes content based on user needs.

[0009] "User input information" refers to information entered by the user, such as the subjects they wish to study, their level of proficiency, and their learning style.

[0010] "Customized learning content" refers to learning materials optimized for users, created by generative AI based on user input.

[0011] "Feedback" refers to information such as users' impressions, evaluations, and level of understanding after using learning content.

[0012] "Test results" refers to the scores and evaluations of tests taken by users using learning content.

[0013] "Optimize" refers to the process by which the system improves and adjusts learning content and learning content models based on feedback and test results.

[0014] "User device" refers to the computer device, such as a PC, tablet, or smartphone, that a user uses to view and interact with the learning content. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. Specific embodiments of the system are described below.

[0037] Overview of program processing

[0038] This system consists of three main components: a server, a device, and a user. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users input information based on their own learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content through feedback and test results.

[0039] Natural language explanation of program processing

[0040] Server Processing

[0041] 1. Registering content in the database

[0042] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[0043] 2. Building a learning content model

[0044] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[0045] 3. Creating customized learning content

[0046] The server receives information sent by the user, such as the subjects they wish to study, their level of proficiency, and their learning style, and the AI ​​then generates customized learning content based on that information. This content is then sent to the device.

[0047] 4. Feedback and optimization

[0048] As users progress through their learning, they send feedback and proficiency test results to the server, which receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[0049] Terminal handling

[0050] 1. Accepting user input

[0051] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style, and sends this information to the server.

[0052] 2. Viewing learning content

[0053] The customized learning content received from the server is displayed on the device, and the displayed content is provided in the form of videos and interactive questions.

[0054] 3. Submitting feedback and test results

[0055] The terminal provides an interface for collecting user-provided feedback and proficiency test results and transmitting them to a server.

[0056] User Action

[0057] 1. Enter your information

[0058] Users input information into the device such as the subject they wish to study, their level of proficiency, and their learning style, for example, "math," "beginner," and "visual learning."

[0059] 2. Use of learning content

[0060] Students learn with customized learning content displayed on their device, including visual videos and interactive exercises to teach the basics of factoring.

[0061] 3. Providing Feedback

[0062] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[0063] Specific examples

[0064] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[0065] 1. User Input

[0066] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server.

[0067] 2. Providing learning content

[0068] Based on the information entered by Mr. A, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations with diagrams and animations is provided.

[0069] 3. Learning progression and feedback

[0070] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of comprehension and feedback into the device and takes a proficiency test. Result information such as "Comprehension: 80%" and "Test result: 85 points" is sent to the server via the device.

[0071] 4. Content optimization

[0072] Based on the feedback and test results received, the server retrains the generative AI to further optimize the learning content it provides next time.

[0073] By repeating this process, learning content optimized for each user can be provided, enabling efficient learning.

[0074] The processing flow will be explained below.

[0075] Step 1: Registering content in the database

[0076] The server receives data provided by learning content providers and stores it in a database, along with metadata such as subject, difficulty level, and format.

[0077] Step 2: Building a learning content model

[0078] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[0079] Step 3: Accepting User Input

[0080] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[0081] Step 4: Generate customized learning content

[0082] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, and learning style information. The generated content is optimized in terms of format and content to meet the user's needs.

[0083] Step 5: View learning content

[0084] The terminal receives the customized learning content sent from the server and displays it to the user, who can then use the provided content to continue their learning.

[0085] Step 6: Gather feedback and test results

[0086] After the user has used the learning content, the device collects feedback from the user and the results of the proficiency test, and sends this to the server. The feedback includes information about the user's level of understanding and satisfaction.

[0087] Step 7: Optimize based on feedback

[0088] The server analyzes the collected feedback and test result data and feeds it back to the generation AI, which uses this data to retrain its model and reflect it in the next generation of learning content. This process ensures that the learning content is continuously optimized.

[0089] In this way, each step works together as a series of steps, creating a system that efficiently provides learning content optimized for each user.

[0090] Example 1

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

[0092] Providing customized learning content that meets the needs of individual learners has been difficult. In particular, there is a need for an effective method for efficiently generating and continuously optimizing learning content that accommodates different learning styles and proficiency levels. Furthermore, there is a lack of mechanisms for optimizing content using feedback and test results, making it difficult to ensure an efficient learning process for learners.

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

[0094] In this invention, the server includes a storage means for storing data, a means for constructing a generative learning content model based on the stored data, a means for using a generative AI model to generate customized learning content based on user input information, and a means for collecting user feedback and test results and optimizing the learning content model, thereby enabling efficient provision of customized learning content tailored to the needs of individual learners and utilizing feedback to continuously optimize the content.

[0095] A "storage means" is a device or system for storing data.

[0096] "Learning content" refers to information and teaching materials for use by learners, including text, videos, images, etc.

[0097] A "learning content model" is an algorithm or data structure built to generate and manage learning content.

[0098] A "generative AI model" is a function or program that uses artificial intelligence technology to generate content that meets user needs.

[0099] "User" refers to the learner or educator who uses this system.

[0100] "Input information" refers to data such as the subjects the user wishes to study, skill level, learning style, etc., that the user provides to the system.

[0101] "Feedback" refers to opinions and evaluations of learning content provided by learners.

[0102] "Test results" refers to the scores and evaluations of tests taken by learners to measure their proficiency.

[0103] "Device" refers to a device or terminal that displays learning content and accepts user input.

[0104] "Optimization" is the process of improving learning content and its generative models based on feedback and test results.

[0105] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. This system is mainly composed of three elements: a server, a terminal, and a user. Specific embodiments of the present invention are described below.

[0106] The server is responsible for managing learning content, building models using generative AI, and managing the database. The server receives data provided by learning content providers and stores it in a database. The stored data includes, for example, text, videos, and images, along with metadata such as subject, difficulty level, and format. As a specific example of use, a learning content model is built using OpenAI's (registered trademark) GPT-4 (registered trademark) model. This model is trained to accommodate a variety of learning styles and difficulty levels.

[0107] The server then uses a generative AI model to generate customized learning content based on the user's input. The information input by the user includes the desired subject, proficiency level, learning style, and so on. For example, if a user inputs prompts such as "Mathematics," "Beginner," and "Visual Learning," the server generates customized learning content based on that information. The generative AI model then uses that information to generate optimal learning content, such as a video that explains how to solve linear equations using diagrams and animations, and sends it to the device.

[0108] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The device also displays customized learning content sent from the server. The displayed content is provided in the form of, for example, videos or interactive questions. Users can use this content to advance their studies.

[0109] Furthermore, the device is equipped with an interface that allows the device to collect feedback and proficiency test results after the user has used the learning content and send them to the server. For example, the user can enter specific feedback and test results, such as "Understanding: 80%" and "Test result: 85 points," and send them to the server. Based on this information, the server retrains the generative AI and optimizes the learning content model. This allows the next learning content to be further improved and better suited to the needs of each learner.

[0110] As a concrete example, when a first-year high school student named "A" uses this system to improve his or her math grades, the following series of operations takes place: A enters "Math," "Beginner," and "Visual" style into his or her device in the school's computer lab and sends that information to the server. Based on A's input, the server uses the generative AI to generate beginner-level visual learning content and sends it to the device. A watches and studies the provided visual videos, enters comprehension ratings and feedback, takes a proficiency test, and sends the results to the server. Based on this feedback and test results, the server retrains the generative AI to further optimize the learning content it provides next time.

[0111] In this way, the system can provide learning content optimized for each user and support efficient learning.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1:

[0114] Registering content in the database

[0115] Server Processing

[0116] Input: Data provided by learning content providers (text, videos, images, etc.).

[0117] Specific operation: The server receives the provided learning content data.

[0118] Data processing: Formatting the received data along with metadata (subject, level, format, etc.).

[0119] Output: Save the formatted data to the database.

[0120] Specific operation: The server writes the formatted data to the database.

[0121] Step 2:

[0122] Building a learning content model

[0123] Server Processing

[0124] Input: Learning content data stored in the database.

[0125] Specific operation: The server retrieves the stored learning content data from the database.

[0126] Data computation: Training a generative AI model (e.g., OpenAI's GPT-4) based on the acquired data.

[0127] Output: A trained learning content model.

[0128] Specific operation: The server stores the trained generative AI model.

[0129] Step 3:

[0130] Entering user information

[0131] User Action

[0132] Input: Information such as subjects you wish to study, your proficiency level, and your learning style.

[0133] Specific operation: The user inputs desired information into the terminal interface.

[0134] Output: Sends user input information to the server.

[0135] Terminal handling

[0136] Specific operation: The terminal transfers the entered information to the server.

[0137] Step 4:

[0138] Generate customized learning content

[0139] Server Processing

[0140] Input: User submitted information about desired subjects, proficiency level, and learning style.

[0141] Specific operation: The server analyzes the received user information.

[0142] Data calculation: Generate customized learning content using a generative AI model based on analyzed user information.

[0143] Output: Customized learning content (e.g., a video explaining how to solve linear equations with diagrams and animations).

[0144] Specific operation: Send the generated learning content to the device.

[0145] Step 5:

[0146] View learning content

[0147] Terminal handling

[0148] Input: Customized learning content sent from the server.

[0149] Specific operation: The device displays the received learning content.

[0150] Output: The customized learning content that is displayed to the user.

[0151] What it does: Videos and interactive content appear on the screen.

[0152] Step 6:

[0153] Submitting feedback and test results

[0154] User Action

[0155] Input: Feedback and proficiency test results.

[0156] Specific actions: The user enters feedback and test results into the device interface.

[0157] Output: Sends feedback and proficiency test results to the server.

[0158] Terminal handling

[0159] Specific operation: The device transfers the collected information to the server.

[0160] Server Processing

[0161] Input: User-submitted feedback and test results.

[0162] What happens: The server stores the feedback and test results in a database.

[0163] Step 7:

[0164] Content Optimization

[0165] Server Processing

[0166] Input: Feedback and test results stored in the database.

[0167] Specific Actions: The server retrieves the stored feedback and test results.

[0168] Data computation: Retraining generative AI models based on feedback and testing results, and optimizing learning content models.

[0169] Output: Optimized learning content model.

[0170] Specific action: The next learning content provided will be more accurate.

[0171] (Application example 1)

[0172] 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."

[0173] In conventional learning systems, because each user has different learning needs, it is difficult to achieve efficient learning with uniform learning content. Customizing learning content also requires a huge amount of time and effort, making it unrealistic. Furthermore, because content is not optimized in real time based on the user's learning progress, there is a problem in that learning effectiveness is not fully realized.

[0174] 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.

[0175] In this invention, the server includes means for storing data in a database that provides learning content, means for constructing a generated learning content model based on the stored data, means for generating customized learning content based on user input information, means for collecting user feedback and test results and optimizing the learning content model, means for generating learning content using the generative AI model, and means for displaying the generated customized learning content on a smartphone or head-mounted display. This allows for efficient generation of learning content customized for each user and real-time content optimization.

[0176] A "database" is an information management system for systematically storing and managing learning content.

[0177] A "generated learning content model" is a model for representing learning content that is constructed using generative AI based on stored data.

[0178] "Customized learning content" means learning materials generated based on user input in a format appropriate for specific learning needs and proficiency levels.

[0179] "Feedback" refers to information provided by users after learning about their level of understanding and satisfaction.

[0180] "Test results" are the results of a test used to assess the level of comprehension of learning content.

[0181] A "generative AI model" is a computational model that uses artificial intelligence to generate new learning content.

[0182] A "smartphone" is a portable device that combines advanced computing and connectivity capabilities with the functionality of a mobile phone.

[0183] A "head-mounted display" is a device that is worn on the user's head to display a screen.

[0184] "Device" means an electronic device that allows a user to access and interact with learning content.

[0185] To specifically illustrate the embodiment of the present invention, the roles and processes of the server, terminal, and user are described in detail below, along with specific examples and prompts.

[0186] Server Processing

[0187] The server manages learning content, builds generative AI models, generates customized learning content, and optimizes feedback and test results. Here, we explain the specific process flow.

[0188] 1. Providing learning content and managing the database

[0189] The server processes the data and stores it in a database that provides learning content. When content is registered in the database, metadata about the content (subject, difficulty level, format, etc.) is also stored.

[0190] 2. Building a generative AI model

[0191] The server uses the stored data to build a learning content model using generative AI. This AI model utilizes natural language generation models such as OpenAI's GPT-3 (registered trademark). The model is trained to accommodate a variety of learning styles and difficulty levels.

[0192] 3. Creating customized learning content

[0193] The AI ​​generates customized learning content based on information such as the user's desired subject, proficiency level, and learning style. For example, the user can enter a prompt such as "Create an interactive learning content for intermediate level math."

[0194] 4. Gather feedback and test results and optimize

[0195] As users learn, they provide feedback and test results, which are then sent to the server, which then collects and stores the data in a database.The generative AI uses this feedback data to retrain and optimize the learning content model.

[0196] Terminal handling

[0197] The terminal receives input from the user, displays customized learning content, and collects feedback.

[0198] 1. Accepting user input

[0199] The terminal provides an interface for users to input their desired subjects, proficiency level, and learning style, which is then sent to the server.

[0200] 2. Displaying customized learning content

[0201] The system displays customized learning content received from the server, which may be presented in video, text, interactive formats, etc.

[0202] 3. Submitting feedback and test results

[0203] The terminal provides an interface for collecting and transmitting user-provided feedback and proficiency test results to a server.

[0204] User Action

[0205] Users input information, access customized learning content, and provide feedback through an interface provided by the terminal.

[0206] 1. Enter your information

[0207] Users input information such as the subject they wish to study, their level of proficiency, and their learning style into the terminal. For example, they input details such as "mathematics," "intermediate," and "interactive learning."

[0208] 2. Use of learning content

[0209] The device will display customized learning content, such as interactive math problems at an intermediate level, to help students progress through their studies.

[0210] 3. Providing Feedback

[0211] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[0212] Examples and prompts

[0213] For example, if a high school student uses this system to improve their math grades, the following process will occur:

[0214] 1. User Input

[0215] "Mathematics," "Intermediate," and "Interactive" styles are entered into the terminal, and the information is sent to the server.

[0216] 2. Providing learning content

[0217] The server uses a generative AI based on the user's input information to generate "interactive intermediate level math problems" and deliver them to the device.

[0218] 3. Learning progression and feedback

[0219] The user proceeds with the study using the provided interactive learning content, and then inputs feedback and test results, which are then transmitted to the server.

[0220] The above process provides a customized and efficient learning environment for each user. The system can improve the user's learning experience by using a generative AI model to generate new learning content based on prompts.

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] User input acceptance

[0224] The device provides an interface for users to input their desired subject, proficiency level, and learning style. The user inputs this information (e.g., "Mathematics," "Intermediate," "Interactive"), and the device sends it to the server. Specifically, the input data is packaged in JSON format and sent to the server's API endpoint.

[0225] Input: Subjects you wish to study, level of proficiency, learning style

[0226] Output: Request data to the server

[0227] Processing: Packaging input data on the device and sending it to the server

[0228] Step 2:

[0229] Generate customized learning content

[0230] The server generates learning content using a generative AI model (e.g., GPT-3) based on the information received from the user. At this time, a prompt sentence is passed to the generative AI model (e.g., "Create an interactive learning content for intermediate level math."). The generative AI model generates customized learning content based on the prompt and returns the data to the server.

[0231] Input: User input information, prompt text

[0232] Output: Customized learning content

[0233] Processing: Content generation using generative AI models

[0234] Step 3:

[0235] Providing learning content

[0236] The server then transmits the generated customized learning content to the user's device, which interprets the received data and displays it in a user interface, such as displaying generated interactive questions or videos for the user to view.

[0237] Input: Customized learning content

[0238] Output: Display content on the user's device

[0239] Processing: Sending data from the server to the device and displaying it on the device

[0240] Step 4:

[0241] Progressing learning and collecting feedback

[0242] The user uses the provided learning content to progress through the learning process. After completing the learning, the device collects feedback from the user regarding their level of understanding and satisfaction. The user enters evaluation data, which the device then sends to the server.

[0243] Input: User learning feedback

[0244] Output: Feedback data to the server

[0245] Processing: Collecting feedback on the device and sending it to the server

[0246] Step 5:

[0247] Feedback analysis and model optimization

[0248] The server analyzes the received feedback and test results, and uses this data to retrain the generative AI model and optimize the learning content model, for example, updating new learning content to be more effective based on the feedback data.

[0249] Input: User feedback and test results

[0250] Output: Optimized learning content model

[0251] Processing: Analyzing feedback data and retraining the generated AI model

[0252] Through each of the above steps, customized learning content is provided to users, and a continuously optimized system is realized.

[0253] 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.

[0254] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[0255] Overview of program processing

[0256] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[0257] Natural language explanation of program processing

[0258] Server Processing

[0259] 1. Registering content in the database

[0260] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[0261] 2. Building a learning content model

[0262] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[0263] 3. Creating customized learning content

[0264] The server uses generative AI to generate customized learning content based on the user's desired study subjects, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[0265] 4. Feedback and optimization

[0266] As the user progresses with their learning, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[0267] Terminal handling

[0268] 1. Accepting user input

[0269] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[0270] 2. Viewing learning content

[0271] The terminal receives the customized learning content and content corresponding to the user's emotions sent from the server and displays them to the user, who can then use them to advance their learning.

[0272] 3. Submitting feedback and test results

[0273] The device provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server, where emotion information collected by the emotion engine is also sent.

[0274] User Action

[0275] 1. Enter your information

[0276] The user inputs information into the device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[0277] 2. Use of learning content

[0278] The device displays customized learning content and emotionally relevant content to guide students through their learning, such as visual videos and interactive puzzles to teach the basics of factoring.

[0279] 3. Providing Feedback

[0280] After using the learning content, users enter feedback on their level of understanding and satisfaction through their device and send it to the server. They also take the provided proficiency test and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[0281] Specific examples

[0282] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[0283] 1. User Input

[0284] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes Person A's facial expressions and voice to obtain emotional information.

[0285] 2. Providing learning content

[0286] Based on A's input and emotional information, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, it could provide a video that uses diagrams and animations to explain how to solve linear equations. If the emotion engine detects stress or confusion while A is learning, the server will immediately provide support materials and hints.

[0287] 3. Learning progression and feedback

[0288] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of his or her level of understanding and feedback into the device and takes a proficiency test. Result information such as "Understanding: 80%" and "Test result: 85 points" is sent to the server via the device. Emotion data collected by the emotion engine is also sent to the server.

[0289] 4. Content optimization

[0290] Based on the feedback, test results, and emotional information received, the server retrains the generative AI to further optimize the learning content it provides next time.

[0291] By repeating this process, learning content optimized for each user is provided, enabling efficient learning, and by utilizing emotional information, the user's learning experience is further improved.

[0292] The processing flow will be explained below.

[0293] Step 1: Registering content in the database

[0294] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are also stored.

[0295] Step 2: Building a learning content model

[0296] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[0297] Step 3: Accepting User Input

[0298] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[0299] Step 4: Emotion Engine Activation and Analysis

[0300] The device activates an emotion engine to monitor the user's facial expressions and voice in real time. The emotion engine analyzes the data and recognizes the user's emotional state (e.g., joy, confusion, concentration). The recognized emotion data is sent to the server.

[0301] Step 5: Generate customized learning content

[0302] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[0303] Step 6: View learning content

[0304] The terminal receives the customized learning content sent from the server and displays it to the user, for example, visual learning content for beginners' level mathematics.

[0305] Step 7: Gather feedback and test results

[0306] After the user uses the learning content, the device collects feedback and proficiency test results from the user and sends them to the server. The emotion engine also continuously monitors the user's emotional state during learning and sends this data to the server.

[0307] Step 8: Optimize based on feedback

[0308] The server analyzes the collected feedback and test result data, as well as the emotional data from the emotion engine, and feeds it back to the generative AI, which uses this data to retrain its model and optimize the learning content model. Through this process, the learning content is continuously optimized.

[0309] In this way, each step works together as a series of steps to efficiently provide learning content optimized for each user and create a personalized learning experience that takes into account the user's emotional state.

[0310] Example 2

[0311] 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."

[0312] Conventional learning systems have difficulty providing content customized to users' learning needs and emotional state, preventing them from providing an efficient learning experience. Furthermore, there are limited means to optimize learning content using user feedback and test results. Therefore, there is a need to provide optimal learning content for each individual user and maximize learning effectiveness.

[0313] 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.

[0314] In this invention, the server includes means for storing data in a database that provides digital data, means for creating a digital model constructed based on the stored data, means for generating customized digital content based on user input information and emotion data, and means for collecting feedback and test results from users and optimizing the digital model, thereby enabling the provision of learning content optimized for each user and continuous content optimization.

[0315] "Digital data" refers to information or content stored in electronic form.

[0316] A "database" refers to a system for efficiently storing, managing, and accessing large amounts of digital data.

[0317] "Digital model" refers to a product or representative form constructed from specific digital data according to certain conditions or methods.

[0318] "User" means an individual end user who uses the System to receive and use Learning Content.

[0319] "Input information" refers to data provided by a user to the system, including desired subjects, proficiency level, and learning style.

[0320] "Emotional data" refers to information that expresses a user's emotional state in numerical or categorical terms.

[0321] "Customized digital content" refers to digital data that is individually tailored and generated based on user input and emotional data.

[0322] "Feedback" refers to the evaluations, opinions, and information about understanding that users provide to the system.

[0323] "Test results" refers to the results of an assessment conducted to measure the level of proficiency and understanding of the learning content.

[0324] "Device" means the device used by a User to access the System and receive Digital Content.

[0325] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[0326] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[0327] Server Processing

[0328] The server receives digital data provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved. The server then uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and difficulty levels. The server then uses generative AI to generate customized digital content based on the user's desired study subject, proficiency level, and learning style, as well as emotional information provided by the emotion engine. The generated content is optimized with a format and content that meets the user's needs. As the user progresses with their studies, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is then retrained based on the feedback data, optimizing the digital model.

[0329] Terminal handling

[0330] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information and sends this data to the server. The device receives customized digital content and content based on the user's emotions sent from the server and displays it to the user. The user can use this content to advance their studies. The device also provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server. The emotional information collected by the emotion engine is also sent to the server.

[0331] User Action

[0332] Users input information into their device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice. The user progresses through the study using customized digital content displayed on the device and content tailored to the user's emotions. For example, visual videos and interactive problems are provided to teach the basics of factorization. After using the learning content, the user inputs feedback regarding their level of understanding and satisfaction through the device and sends it to the server. The user also takes the provided proficiency test and sends the results to the server. Emotional data during the study is also sent to the server via the emotion engine.

[0333] As a concrete example, when a first-year high school student uses this system to improve their math grades, the following process takes place: The user enters "math," "beginner," and "visual" styles into their device in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to obtain emotional information. Based on the user's input and emotional information, the server uses generative AI to generate practical, beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations using diagrams and animations might be provided. If the emotion engine detects stress or confusion during the user's learning, the server immediately provides support materials and hints. After the user watches the provided visual video and studies, they enter a comprehension assessment and feedback and take a proficiency test. The results and emotional data are sent to the server, which then retrains the generative AI based on the received information to further optimize the learning content provided next time.

[0334] An example prompt is, "Generate visual content for beginner level mathematics aimed at first-year high school students. The user's emotional information suggests stress, so please include easy-to-understand illustrations and animations."

[0335] In this way, the present invention not only provides learning content customized for each user, enabling efficient learning, but also improves the quality of the learning experience by utilizing the user's emotional information.

[0336] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0337] Step 1:

[0338] Enter user information

[0339] The user uses the device to input the subject they wish to study, their level of proficiency, and their learning style. The device receives this input information and sends it to the server. Specifically, if the user inputs "math," "beginner," and "visual learning," the information is sent to the server.

[0340] Input: Subject you wish to study, proficiency level, learning style

[0341] Output: Data sent to the server

[0342] Step 2:

[0343] Emotion data acquisition using emotion engine

[0344] The device activates an emotion engine that analyzes the user's facial expressions and voice in real time. The emotion engine acquires the user's emotional state (e.g., stress, joy, confusion) and transmits the emotional data to the server.

[0345] Input: User's facial expression, voice

[0346] Output: Emotion data

[0347] Step 3:

[0348] Collection of learning content data and database registration

[0349] The server receives digital data such as text, videos, and images provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are included. The server then manages the digital data.

[0350] Input: Digital data, metadata

[0351] Output: Registration to database completed

[0352] Step 4:

[0353] Building a learning content model

[0354] The server uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and levels of difficulty. Generative AI uses large amounts of data for machine learning.

[0355] Input: Digital data in a database

[0356] Output: Learning content model

[0357] Step 5:

[0358] Generate customized learning content

[0359] The server uses the user's desired study subject, proficiency level, learning style, and emotional information provided by the emotion engine to generate customized digital content using generative AI. For example, it generates a video that explains how to solve linear equations using diagrams and animations. The generated content is then sent to the user's device.

[0360] Input: Learning preference information, emotion data, learning content model

[0361] Output: Customized digital content

[0362] Step 6:

[0363] View learning content

[0364] The device receives the customized digital content sent from the server and displays it to the user, who can then use it to further their learning. For example, the device may play an interactive visual video.

[0365] Input: Customized digital content from the server

[0366] Output: View learning content

[0367] Step 7:

[0368] Getting feedback and test results

[0369] After learning, the device collects feedback from the user and the results of the proficiency test, and sends this feedback and test results to the server.

[0370] Input: User feedback, test results

[0371] Output: Data sent to the server

[0372] Step 8:

[0373] Content Optimization

[0374] The server retrains the generative AI based on the received feedback, test results, and emotional data, optimizing the digital model to improve the accuracy and adaptability of the learning content provided next time, for example, by improving the learning materials to reduce stress for the user.

[0375] Input: Feedback, test results, sentiment data

[0376] Output: Optimized digital content model

[0377] (Application example 2)

[0378] 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."

[0379] In modern virtual stores, users often lack sufficient information to understand the characteristics and usage of products they are considering purchasing, and the information provided is often uniform, making it difficult to address the diverse needs and emotional states of users. Therefore, to increase users' purchasing motivation and product understanding, it is necessary to provide product information and tutorials customized for each individual user. However, providing such personalized information efficiently has been difficult using conventional methods.

[0380] 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 storing data in a database that provides learning content, means for constructing a learning content model based on the stored data, means for generating customized learning content based on user input information and emotional information, means for collecting user feedback, emotional data, and purchase history and optimizing the learning content model, and means for displaying the generated customized product information and tutorials on the terminal. This makes it possible to provide product information and tutorials tailored to the individual needs and emotional state of each user in a virtual store, thereby improving the user's purchasing motivation and product understanding.

[0381] "Learning Content" refers to teaching materials and resources used by users to acquire specific knowledge or skills.

[0382] A "database" is a system for storing and managing learning content and related data.

[0383] A "generated learning content model" is a model built using generative AI based on stored data to accommodate various learning styles and levels of difficulty.

[0384] "User input information" refers to information such as the subject desired to study, proficiency level, learning style, product category, characteristics, and usage method.

[0385] "Emotional information" is data related to the emotional state of the user analyzed from facial expressions, voice, etc.

[0386] "Customized learning content" refers to personalized learning materials and information generated based on user input and emotional information.

[0387] "Feedback" refers to evaluations and opinions regarding learning content and product information provided by users.

[0388] "Purchase history" is a record of products that a user has purchased in the past.

[0389] "Optimizing" means retraining the generative AI based on the collected data to improve its learning content model and the information it provides.

[0390] "Product information" refers to information about the characteristics, usage, reviews, etc. of products offered in the virtual store.

[0391] "Tutorials" are interactive guides or videos that explain the use or features of a product.

[0392] A "terminal" is a device that allows a user to input information and display customized content.

[0393] The present invention is a system for providing users with personalized product information and tutorials in a virtual store. This system utilizes a database that provides learning content, a generative AI model, and an emotion engine to generate and display optimal information based on the user's input information and emotion information. Specific embodiments of the system are described below.

[0394] Server Processing

[0395] 1. Registering content in the database

[0396] The server receives data such as product information, reviews, and tutorial videos provided by the virtual store and registers them in a database, including metadata such as product category, characteristics, and usage instructions.

[0397] 2. Building a learning content model

[0398] Using the stored data, generative AI is used to build learning content models that are trained to accommodate different shopping styles and product categories.

[0399] 3. Generating customized learning content

[0400] The server uses generative AI to generate customized learning content based on the user's input information (e.g., product category, characteristics, and usage) and the emotional information provided by the emotion engine, taking into account the user's past purchase history and emotional data.

[0401] 4. Feedback and optimization

[0402] Users browse product information and send their post-purchase feedback and sentiment data to the server. The server receives this data and stores it in a database. The AI ​​is retrained based on the feedback data and optimizes the learning content model.

[0403] Terminal handling

[0404] 1. Accepting user input

[0405] The terminal provides an interface for users to input the products and categories they are interested in. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[0406] 2. Viewing learning content

[0407] The terminal receives customized product information and tutorials sent from the server and displays them to the user, who can use this information to deepen their understanding of the product and consider purchasing it.

[0408] 3. Submitting feedback and ratings

[0409] The device provides an interface to collect feedback and ratings provided by users and send them to the server, where emotion information collected by the emotion engine is also sent.

[0410] User Action

[0411] 1. Enter your information

[0412] Users input the category and characteristics of the product they wish to purchase into the device. For example, they input information such as "electronic device," "smartphone," or "for beginners." During the learning process, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[0413] 2. Use of learning content

[0414] By viewing customized product information and tutorials displayed on the device, users can learn about the product's features and how to use it. For example, a video explaining how to set up a smartphone is provided.

[0415] 3. Providing Feedback

[0416] After using the learning content, users enter feedback on their level of understanding and satisfaction through their devices and send it to the server. They also rate the products provided and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[0417] Specific examples

[0418] For example, suppose a user is considering purchasing the latest smartphone and wants to learn how to use it. In this case, the user enters "electronic device," "smartphone," and "for beginners" into the device, and the emotion engine acquires emotional information from facial expressions and voice. Based on this information, the server uses generative AI to generate a customized visual tutorial explaining how to set up the smartphone and sends it to the device. After the user watches this tutorial and deepens their understanding of the product, they send feedback via the device saying, "This tutorial video was very helpful." Emotional data generated by the emotion engine is also sent to the server.

[0419] Prompt Sentence Examples

[0420] "Welcome to SmartShop Tutor. If you want to learn how to use the latest smartphone, what information do you want? For example, 'How to set it up for beginners' or 'How to best use apps'?"

[0421] "We'll provide you with a customized smartphone tutorial based on your interests to help you make your purchase decision."

[0422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0423] Step 1: Registering content in the database

[0424] The server receives product information (category, characteristics, usage, reviews, tutorial videos, etc.) provided by the virtual store and stores it in a database. At this time, product metadata is also registered. Specifically, the server obtains data from the product provider and stores it in the appropriate fields of the database. The input is product information data, and the output is the product information data stored in the database.

[0425] Step 2: Building a generative AI model

[0426] The server uses a generative AI to build a learning content model based on the product information data stored in the database. This model is trained to flexibly respond to the differences associated with each product. Specifically, the server retrieves data from the database, inputs it into the generative AI, and performs training. The input is the product information data retrieved from the database, and the output is the constructed learning content model.

[0427] Step 3: Accepting User Input

[0428] The terminal provides an interface for users to input information such as the category, characteristics, and usage of the product they are considering purchasing. It also uses an emotion engine to analyze the user's facial expressions and voice to obtain emotional information. Specifically, the terminal receives input information through the user interface and runs the emotion engine to analyze the voice and facial expression data. The input is the user's input information and emotional data, and the output is the user's input information and emotional data sent to the server.

[0429] Step 4: Generate customized learning content

[0430] The server uses generative AI to generate customized learning content based on the input information and emotional information sent by the user. This generation also takes into account the user's past purchase history and emotional data. Specifically, the server inputs the user's acquired data into a model to generate optimized learning content. The input is the user's input information and emotional data, and the output is customized learning content.

[0431] Step 5: View learning content

[0432] The terminal receives customized product information and tutorials sent from the server and displays them to the user. Specifically, the terminal receives data from the server and displays it on the display. The input is the learning content sent from the server, and the output is the customized learning content displayed on the terminal display.

[0433] Step 6: Submit your feedback and rating

[0434] The device collects feedback and evaluations provided by users and sends them to the server. It also sends emotional information acquired by the emotion engine to the server. Specifically, the device collects feedback data through the user interface and sends it together with emotional data. The input is the user's feedback data and emotional data, and the output is the feedback data and emotional data sent to the server.

[0435] Step 7: Feedback and optimization

[0436] The server stores the received feedback, emotional data, and purchase history in a database, and uses this information to retrain and optimize the generative AI model. Specifically, the server stores the collected data in a database and inputs it into the generative AI for retraining. The input is user feedback data, emotional data, and purchase history, and the output is an optimized learning content model.

[0437] 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.

[0438] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0439] 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.

[0440] [Second embodiment]

[0441] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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."

[0453] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. Specific embodiments of the system are described below.

[0454] Overview of program processing

[0455] This system consists of three main components: a server, a device, and a user. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users input information based on their own learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content through feedback and test results.

[0456] Natural language explanation of program processing

[0457] Server Processing

[0458] 1. Registering content in the database

[0459] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[0460] 2. Building a learning content model

[0461] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[0462] 3. Creating customized learning content

[0463] The server receives information sent by the user, such as the subjects they wish to study, their level of proficiency, and their learning style, and the AI ​​then generates customized learning content based on that information. This content is then sent to the device.

[0464] 4. Feedback and optimization

[0465] As users progress through their learning, they send feedback and proficiency test results to the server, which receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[0466] Terminal handling

[0467] 1. Accepting user input

[0468] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style, and sends this information to the server.

[0469] 2. Viewing learning content

[0470] The customized learning content received from the server is displayed on the device, and the displayed content is provided in the form of videos and interactive questions.

[0471] 3. Submitting feedback and test results

[0472] The terminal provides an interface for collecting user-provided feedback and proficiency test results and transmitting them to a server.

[0473] User Action

[0474] 1. Enter your information

[0475] Users input information into the device such as the subject they wish to study, their level of proficiency, and their learning style, for example, "math," "beginner," and "visual learning."

[0476] 2. Use of learning content

[0477] Students learn with customized learning content displayed on their device, including visual videos and interactive exercises to teach the basics of factoring.

[0478] 3. Providing Feedback

[0479] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[0480] Specific examples

[0481] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[0482] 1. User Input

[0483] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server.

[0484] 2. Providing learning content

[0485] Based on the information entered by Mr. A, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations with diagrams and animations is provided.

[0486] 3. Learning progression and feedback

[0487] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of comprehension and feedback into the device and takes a proficiency test. Result information such as "Comprehension: 80%" and "Test result: 85 points" is sent to the server via the device.

[0488] 4. Content optimization

[0489] Based on the feedback and test results received, the server retrains the generative AI to further optimize the learning content it provides next time.

[0490] By repeating this process, learning content optimized for each user can be provided, enabling efficient learning.

[0491] The processing flow will be explained below.

[0492] Step 1: Registering content in the database

[0493] The server receives data provided by learning content providers and stores it in a database, along with metadata such as subject, difficulty level, and format.

[0494] Step 2: Building a learning content model

[0495] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[0496] Step 3: Accepting User Input

[0497] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[0498] Step 4: Generate customized learning content

[0499] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, and learning style information. The generated content is optimized in terms of format and content to meet the user's needs.

[0500] Step 5: View learning content

[0501] The terminal receives the customized learning content sent from the server and displays it to the user, who can then use the provided content to continue their learning.

[0502] Step 6: Gather feedback and test results

[0503] After the user has used the learning content, the device collects feedback from the user and the results of the proficiency test, and sends this to the server. The feedback includes information about the user's level of understanding and satisfaction.

[0504] Step 7: Optimize based on feedback

[0505] The server analyzes the collected feedback and test result data and feeds it back to the generation AI, which uses this data to retrain its model and reflect it in the next generation of learning content. This process ensures that the learning content is continuously optimized.

[0506] In this way, each step works together as a series of steps, creating a system that efficiently provides learning content optimized for each user.

[0507] Example 1

[0508] 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."

[0509] Providing customized learning content that meets the needs of individual learners has been difficult. In particular, there is a need for an effective method for efficiently generating and continuously optimizing learning content that accommodates different learning styles and proficiency levels. Furthermore, there is a lack of mechanisms for optimizing content using feedback and test results, making it difficult to ensure an efficient learning process for learners.

[0510] 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.

[0511] In this invention, the server includes a storage means for storing data, a means for constructing a generative learning content model based on the stored data, a means for using a generative AI model to generate customized learning content based on user input information, and a means for collecting user feedback and test results and optimizing the learning content model, thereby enabling efficient provision of customized learning content tailored to the needs of individual learners and utilizing feedback to continuously optimize the content.

[0512] A "storage means" is a device or system for storing data.

[0513] "Learning content" refers to information and teaching materials for use by learners, including text, videos, images, etc.

[0514] A "learning content model" is an algorithm or data structure built to generate and manage learning content.

[0515] A "generative AI model" is a function or program that uses artificial intelligence technology to generate content that meets user needs.

[0516] "User" refers to the learner or educator who uses this system.

[0517] "Input information" refers to data such as the subjects the user wishes to study, skill level, learning style, etc., that the user provides to the system.

[0518] "Feedback" refers to opinions and evaluations of learning content provided by learners.

[0519] "Test results" refers to the scores and evaluations of tests taken by learners to measure their proficiency.

[0520] "Device" refers to a device or terminal that displays learning content and accepts user input.

[0521] "Optimization" is the process of improving learning content and its generative models based on feedback and test results.

[0522] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. This system is mainly composed of three elements: a server, a terminal, and a user. Specific embodiments of the present invention are described below.

[0523] The server is responsible for managing learning content, building models using generative AI, and managing the database. The server receives data provided by learning content providers and stores it in a database. The stored data includes, for example, text, videos, and images, along with metadata such as subject, difficulty level, and format. As a specific example of use, a learning content model is built using OpenAI's GPT-4 model. This model is trained to accommodate a variety of learning styles and difficulty levels.

[0524] The server then uses a generative AI model to generate customized learning content based on the user's input. The information input by the user includes the desired subject, proficiency level, learning style, and so on. For example, if a user inputs prompts such as "Mathematics," "Beginner," and "Visual Learning," the server generates customized learning content based on that information. The generative AI model then uses that information to generate optimal learning content, such as a video that explains how to solve linear equations using diagrams and animations, and sends it to the device.

[0525] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The device also displays customized learning content sent from the server. The displayed content is provided in the form of, for example, videos or interactive questions. Users can use this content to advance their studies.

[0526] Furthermore, the device is equipped with an interface that allows the device to collect feedback and proficiency test results after the user has used the learning content and send them to the server. For example, the user can enter specific feedback and test results, such as "Understanding: 80%" and "Test result: 85 points," and send them to the server. Based on this information, the server retrains the generative AI and optimizes the learning content model. This allows the next learning content to be further improved and better suited to the needs of each learner.

[0527] As a concrete example, when a first-year high school student named "A" uses this system to improve his or her math grades, the following series of operations takes place: A enters "Math," "Beginner," and "Visual" style into his or her device in the school's computer lab and sends that information to the server. Based on A's input, the server uses the generative AI to generate beginner-level visual learning content and sends it to the device. A watches and studies the provided visual videos, enters comprehension ratings and feedback, takes a proficiency test, and sends the results to the server. Based on this feedback and test results, the server retrains the generative AI to further optimize the learning content it provides next time.

[0528] In this way, the system can provide learning content optimized for each user and support efficient learning.

[0529] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0530] Step 1:

[0531] Registering content in the database

[0532] Server Processing

[0533] Input: Data provided by learning content providers (text, videos, images, etc.).

[0534] Specific operation: The server receives the provided learning content data.

[0535] Data processing: Formatting the received data along with metadata (subject, level, format, etc.).

[0536] Output: Save the formatted data to the database.

[0537] Specific operation: The server writes the formatted data to the database.

[0538] Step 2:

[0539] Building a learning content model

[0540] Server Processing

[0541] Input: Learning content data stored in the database.

[0542] Specific operation: The server retrieves the stored learning content data from the database.

[0543] Data computation: Training a generative AI model (e.g., OpenAI's GPT-4) based on the acquired data.

[0544] Output: A trained learning content model.

[0545] Specific operation: The server stores the trained generative AI model.

[0546] Step 3:

[0547] Entering user information

[0548] User Action

[0549] Input: Information such as subjects you wish to study, your proficiency level, and your learning style.

[0550] Specific operation: The user inputs desired information into the terminal interface.

[0551] Output: Sends user input information to the server.

[0552] Terminal handling

[0553] Specific operation: The terminal transfers the entered information to the server.

[0554] Step 4:

[0555] Generate customized learning content

[0556] Server Processing

[0557] Input: User submitted information about desired subjects, proficiency level, and learning style.

[0558] Specific operation: The server analyzes the received user information.

[0559] Data calculation: Generate customized learning content using a generative AI model based on analyzed user information.

[0560] Output: Customized learning content (e.g., a video explaining how to solve linear equations with diagrams and animations).

[0561] Specific operation: Send the generated learning content to the device.

[0562] Step 5:

[0563] View learning content

[0564] Terminal handling

[0565] Input: Customized learning content sent from the server.

[0566] Specific operation: The device displays the received learning content.

[0567] Output: The customized learning content that is displayed to the user.

[0568] What it does: Videos and interactive content appear on the screen.

[0569] Step 6:

[0570] Submitting feedback and test results

[0571] User Action

[0572] Input: Feedback and proficiency test results.

[0573] Specific actions: The user enters feedback and test results into the device interface.

[0574] Output: Sends feedback and proficiency test results to the server.

[0575] Terminal handling

[0576] Specific operation: The device transfers the collected information to the server.

[0577] Server Processing

[0578] Input: User-submitted feedback and test results.

[0579] What happens: The server stores the feedback and test results in a database.

[0580] Step 7:

[0581] Content Optimization

[0582] Server Processing

[0583] Input: Feedback and test results stored in the database.

[0584] Specific Actions: The server retrieves the stored feedback and test results.

[0585] Data computation: Retraining generative AI models based on feedback and testing results, and optimizing learning content models.

[0586] Output: Optimized learning content model.

[0587] Specific action: The next learning content provided will be more accurate.

[0588] (Application example 1)

[0589] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0590] In conventional learning systems, because each user has different learning needs, it is difficult to achieve efficient learning with uniform learning content. Customizing learning content also requires a huge amount of time and effort, making it unrealistic. Furthermore, because content is not optimized in real time based on the user's learning progress, there is a problem in that learning effectiveness is not fully realized.

[0591] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0592] In this invention, the server includes means for storing data in a database that provides learning content, means for constructing a generated learning content model based on the stored data, means for generating customized learning content based on user input information, means for collecting user feedback and test results and optimizing the learning content model, means for generating learning content using the generative AI model, and means for displaying the generated customized learning content on a smartphone or head-mounted display. This allows for efficient generation of learning content customized for each user and real-time content optimization.

[0593] A "database" is an information management system for systematically storing and managing learning content.

[0594] A "generated learning content model" is a model for representing learning content that is constructed using generative AI based on stored data.

[0595] "Customized learning content" means learning materials generated based on user input in a format appropriate for specific learning needs and proficiency levels.

[0596] "Feedback" refers to information provided by users after learning about their level of understanding and satisfaction.

[0597] "Test results" are the results of a test used to assess the level of comprehension of learning content.

[0598] A "generative AI model" is a computational model that uses artificial intelligence to generate new learning content.

[0599] A "smartphone" is a portable device that combines advanced computing and connectivity capabilities with the functionality of a mobile phone.

[0600] A "head-mounted display" is a device that is worn on the user's head to display a screen.

[0601] "Device" means an electronic device that allows a user to access and interact with learning content.

[0602] To specifically illustrate the embodiment of the present invention, the roles and processes of the server, terminal, and user are described in detail below, along with specific examples and prompts.

[0603] Server Processing

[0604] The server manages learning content, builds generative AI models, generates customized learning content, and optimizes feedback and test results. Here, we explain the specific process flow.

[0605] 1. Providing learning content and managing the database

[0606] The server processes the data and stores it in a database that provides learning content. When content is registered in the database, metadata about the content (subject, difficulty level, format, etc.) is also stored.

[0607] 2. Building a generative AI model

[0608] The server uses the stored data to build learning content models using generative AI, which uses natural language generation models such as OpenAI's GPT-3, and is trained to accommodate a variety of learning styles and levels of difficulty.

[0609] 3. Creating customized learning content

[0610] The AI ​​generates customized learning content based on information such as the user's desired subject, proficiency level, and learning style. For example, the user can enter a prompt such as "Create an interactive learning content for intermediate level math."

[0611] 4. Gather feedback and test results and optimize

[0612] As users learn, they provide feedback and test results, which are then sent to the server, which then collects and stores the data in a database.The generative AI uses this feedback data to retrain and optimize the learning content model.

[0613] Terminal handling

[0614] The terminal receives input from the user, displays customized learning content, and collects feedback.

[0615] 1. Accepting user input

[0616] The terminal provides an interface for users to input their desired subjects, proficiency level, and learning style, which is then sent to the server.

[0617] 2. Displaying customized learning content

[0618] The system displays customized learning content received from the server, which may be presented in video, text, interactive formats, etc.

[0619] 3. Submitting feedback and test results

[0620] The terminal provides an interface for collecting and transmitting user-provided feedback and proficiency test results to a server.

[0621] User Action

[0622] Users input information, access customized learning content, and provide feedback through an interface provided by the terminal.

[0623] 1. Enter your information

[0624] Users input information such as the subject they wish to study, their level of proficiency, and their learning style into the terminal. For example, they input details such as "mathematics," "intermediate," and "interactive learning."

[0625] 2. Use of learning content

[0626] The device will display customized learning content, such as interactive math problems at an intermediate level, to help students progress through their studies.

[0627] 3. Providing Feedback

[0628] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[0629] Examples and prompts

[0630] For example, if a high school student uses this system to improve their math grades, the following process will occur:

[0631] 1. User Input

[0632] "Mathematics," "Intermediate," and "Interactive" styles are entered into the terminal, and the information is sent to the server.

[0633] 2. Providing learning content

[0634] The server uses a generative AI based on the user's input information to generate "interactive intermediate level math problems" and deliver them to the device.

[0635] 3. Learning progression and feedback

[0636] The user proceeds with the study using the provided interactive learning content, and then inputs feedback and test results, which are then transmitted to the server.

[0637] The above process provides a customized and efficient learning environment for each user. The system can improve the user's learning experience by using a generative AI model to generate new learning content based on prompts.

[0638] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0639] Step 1:

[0640] User input acceptance

[0641] The device provides an interface for users to input their desired subject, proficiency level, and learning style. The user inputs this information (e.g., "Mathematics," "Intermediate," "Interactive"), and the device sends it to the server. Specifically, the input data is packaged in JSON format and sent to the server's API endpoint.

[0642] Input: Subjects you wish to study, level of proficiency, learning style

[0643] Output: Request data to the server

[0644] Processing: Packaging input data on the device and sending it to the server

[0645] Step 2:

[0646] Generate customized learning content

[0647] The server generates learning content using a generative AI model (e.g., GPT-3) based on the information received from the user. At this time, a prompt sentence is passed to the generative AI model (e.g., "Create an interactive learning content for intermediate level math."). The generative AI model generates customized learning content based on the prompt and returns the data to the server.

[0648] Input: User input information, prompt text

[0649] Output: Customized learning content

[0650] Processing: Content generation using generative AI models

[0651] Step 3:

[0652] Providing learning content

[0653] The server then transmits the generated customized learning content to the user's device, which interprets the received data and displays it in a user interface, such as displaying generated interactive questions or videos for the user to view.

[0654] Input: Customized learning content

[0655] Output: Display content on the user's device

[0656] Processing: Sending data from the server to the device and displaying it on the device

[0657] Step 4:

[0658] Progressing learning and collecting feedback

[0659] The user uses the provided learning content to progress through the learning process. After completing the learning, the device collects feedback from the user regarding their level of understanding and satisfaction. The user enters evaluation data, which the device then sends to the server.

[0660] Input: User learning feedback

[0661] Output: Feedback data to the server

[0662] Processing: Collecting feedback on the device and sending it to the server

[0663] Step 5:

[0664] Feedback analysis and model optimization

[0665] The server analyzes the received feedback and test results, and uses this data to retrain the generative AI model and optimize the learning content model, for example, updating new learning content to be more effective based on the feedback data.

[0666] Input: User feedback and test results

[0667] Output: Optimized learning content model

[0668] Processing: Analyzing feedback data and retraining the generated AI model

[0669] Through each of the above steps, customized learning content is provided to users, and a continuously optimized system is realized.

[0670] 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.

[0671] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[0672] Overview of program processing

[0673] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[0674] Natural language explanation of program processing

[0675] Server Processing

[0676] 1. Registering content in the database

[0677] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[0678] 2. Building a learning content model

[0679] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[0680] 3. Creating customized learning content

[0681] The server uses generative AI to generate customized learning content based on the user's desired study subjects, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[0682] 4. Feedback and optimization

[0683] As the user progresses with their learning, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[0684] Terminal handling

[0685] 1. Accepting user input

[0686] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[0687] 2. Viewing learning content

[0688] The terminal receives the customized learning content and content corresponding to the user's emotions sent from the server and displays them to the user, who can then use them to advance their learning.

[0689] 3. Submitting feedback and test results

[0690] The device provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server, where emotion information collected by the emotion engine is also sent.

[0691] User Action

[0692] 1. Enter your information

[0693] The user inputs information into the device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[0694] 2. Use of learning content

[0695] The device displays customized learning content and emotionally relevant content to guide students through their learning, such as visual videos and interactive puzzles to teach the basics of factoring.

[0696] 3. Providing Feedback

[0697] After using the learning content, users enter feedback on their level of understanding and satisfaction through their device and send it to the server. They also take the provided proficiency test and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[0698] Specific examples

[0699] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[0700] 1. User Input

[0701] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes Person A's facial expressions and voice to obtain emotional information.

[0702] 2. Providing learning content

[0703] Based on A's input and emotional information, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, it could provide a video that uses diagrams and animations to explain how to solve linear equations. If the emotion engine detects stress or confusion while A is learning, the server will immediately provide support materials and hints.

[0704] 3. Learning progression and feedback

[0705] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of his or her level of understanding and feedback into the device and takes a proficiency test. Result information such as "Understanding: 80%" and "Test result: 85 points" is sent to the server via the device. Emotion data collected by the emotion engine is also sent to the server.

[0706] 4. Content optimization

[0707] Based on the feedback, test results, and emotional information received, the server retrains the generative AI to further optimize the learning content it provides next time.

[0708] By repeating this process, learning content optimized for each user is provided, enabling efficient learning, and by utilizing emotional information, the user's learning experience is further improved.

[0709] The processing flow will be explained below.

[0710] Step 1: Registering content in the database

[0711] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are also stored.

[0712] Step 2: Building a learning content model

[0713] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[0714] Step 3: Accepting User Input

[0715] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[0716] Step 4: Emotion Engine Activation and Analysis

[0717] The device activates an emotion engine to monitor the user's facial expressions and voice in real time. The emotion engine analyzes the data and recognizes the user's emotional state (e.g., joy, confusion, concentration). The recognized emotion data is sent to the server.

[0718] Step 5: Generate customized learning content

[0719] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[0720] Step 6: View learning content

[0721] The terminal receives the customized learning content sent from the server and displays it to the user, for example, visual learning content for beginners' level mathematics.

[0722] Step 7: Gather feedback and test results

[0723] After the user uses the learning content, the device collects feedback and proficiency test results from the user and sends them to the server. The emotion engine also continuously monitors the user's emotional state during learning and sends this data to the server.

[0724] Step 8: Optimize based on feedback

[0725] The server analyzes the collected feedback and test result data, as well as the emotional data from the emotion engine, and feeds it back to the generative AI, which uses this data to retrain its model and optimize the learning content model. Through this process, the learning content is continuously optimized.

[0726] In this way, each step works together as a series of steps to efficiently provide learning content optimized for each user and create a personalized learning experience that takes into account the user's emotional state.

[0727] Example 2

[0728] 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."

[0729] Conventional learning systems have difficulty providing content customized to users' learning needs and emotional state, preventing them from providing an efficient learning experience. Furthermore, there are limited means to optimize learning content using user feedback and test results. Therefore, there is a need to provide optimal learning content for each individual user and maximize learning effectiveness.

[0730] 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.

[0731] In this invention, the server includes means for storing data in a database that provides digital data, means for creating a digital model constructed based on the stored data, means for generating customized digital content based on user input information and emotion data, and means for collecting feedback and test results from users and optimizing the digital model, thereby enabling the provision of learning content optimized for each user and continuous content optimization.

[0732] "Digital data" refers to information or content stored in electronic form.

[0733] A "database" refers to a system for efficiently storing, managing, and accessing large amounts of digital data.

[0734] "Digital model" refers to a product or representative form constructed from specific digital data according to certain conditions or methods.

[0735] "User" means an individual end user who uses the System to receive and use Learning Content.

[0736] "Input information" refers to data provided by a user to the system, including desired subjects, proficiency level, and learning style.

[0737] "Emotional data" refers to information that expresses a user's emotional state in numerical or categorical terms.

[0738] "Customized digital content" refers to digital data that is individually tailored and generated based on user input and emotional data.

[0739] "Feedback" refers to the evaluations, opinions, and information about understanding that users provide to the system.

[0740] "Test results" refers to the results of an assessment conducted to measure the level of proficiency and understanding of the learning content.

[0741] "Device" means the device used by a User to access the System and receive Digital Content.

[0742] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[0743] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[0744] Server Processing

[0745] The server receives digital data provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved. The server then uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and difficulty levels. The server then uses generative AI to generate customized digital content based on the user's desired study subject, proficiency level, and learning style, as well as emotional information provided by the emotion engine. The generated content is optimized with a format and content that meets the user's needs. As the user progresses with their studies, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is then retrained based on the feedback data, optimizing the digital model.

[0746] Terminal handling

[0747] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information and sends this data to the server. The device receives customized digital content and content based on the user's emotions sent from the server and displays it to the user. The user can use this content to advance their studies. The device also provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server. The emotional information collected by the emotion engine is also sent to the server.

[0748] User Action

[0749] Users input information into their device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice. The user progresses through the study using customized digital content displayed on the device and content tailored to the user's emotions. For example, visual videos and interactive problems are provided to teach the basics of factorization. After using the learning content, the user inputs feedback regarding their level of understanding and satisfaction through the device and sends it to the server. The user also takes the provided proficiency test and sends the results to the server. Emotional data during the study is also sent to the server via the emotion engine.

[0750] As a concrete example, when a first-year high school student uses this system to improve their math grades, the following process takes place: The user enters "math," "beginner," and "visual" styles into their device in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to obtain emotional information. Based on the user's input and emotional information, the server uses generative AI to generate practical, beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations using diagrams and animations might be provided. If the emotion engine detects stress or confusion during the user's learning, the server immediately provides support materials and hints. After the user watches the provided visual video and studies, they enter a comprehension assessment and feedback and take a proficiency test. The results and emotional data are sent to the server, which then retrains the generative AI based on the received information to further optimize the learning content provided next time.

[0751] An example prompt is, "Generate visual content for beginner level mathematics aimed at first-year high school students. The user's emotional information suggests stress, so please include easy-to-understand illustrations and animations."

[0752] In this way, the present invention not only provides learning content customized for each user, enabling efficient learning, but also improves the quality of the learning experience by utilizing the user's emotional information.

[0753] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0754] Step 1:

[0755] Enter user information

[0756] The user uses the device to input the subject they wish to study, their level of proficiency, and their learning style. The device receives this input information and sends it to the server. Specifically, if the user inputs "math," "beginner," and "visual learning," the information is sent to the server.

[0757] Input: Subject you wish to study, proficiency level, learning style

[0758] Output: Data sent to the server

[0759] Step 2:

[0760] Emotion data acquisition using emotion engine

[0761] The device activates an emotion engine that analyzes the user's facial expressions and voice in real time. The emotion engine acquires the user's emotional state (e.g., stress, joy, confusion) and transmits the emotional data to the server.

[0762] Input: User's facial expression, voice

[0763] Output: Emotion data

[0764] Step 3:

[0765] Collection of learning content data and database registration

[0766] The server receives digital data such as text, videos, and images provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are included. The server then manages the digital data.

[0767] Input: Digital data, metadata

[0768] Output: Registration to database completed

[0769] Step 4:

[0770] Building a learning content model

[0771] The server uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and levels of difficulty. Generative AI uses large amounts of data for machine learning.

[0772] Input: Digital data in a database

[0773] Output: Learning content model

[0774] Step 5:

[0775] Generate customized learning content

[0776] The server uses the user's desired study subject, proficiency level, learning style, and emotional information provided by the emotion engine to generate customized digital content using generative AI. For example, it generates a video that explains how to solve linear equations using diagrams and animations. The generated content is then sent to the user's device.

[0777] Input: Learning preference information, emotion data, learning content model

[0778] Output: Customized digital content

[0779] Step 6:

[0780] View learning content

[0781] The device receives the customized digital content sent from the server and displays it to the user, who can then use it to further their learning. For example, the device may play an interactive visual video.

[0782] Input: Customized digital content from the server

[0783] Output: View learning content

[0784] Step 7:

[0785] Getting feedback and test results

[0786] After learning, the device collects feedback from the user and the results of the proficiency test, and sends this feedback and test results to the server.

[0787] Input: User feedback, test results

[0788] Output: Data sent to the server

[0789] Step 8:

[0790] Content Optimization

[0791] The server retrains the generative AI based on the received feedback, test results, and emotional data, optimizing the digital model to improve the accuracy and adaptability of the learning content provided next time, for example, by improving the learning materials to reduce stress for the user.

[0792] Input: Feedback, test results, sentiment data

[0793] Output: Optimized digital content model

[0794] (Application example 2)

[0795] 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."

[0796] In modern virtual stores, users often lack sufficient information to understand the characteristics and usage of products they are considering purchasing, and the information provided is often uniform, making it difficult to address the diverse needs and emotional states of users. Therefore, to increase users' purchasing motivation and product understanding, it is necessary to provide product information and tutorials customized for each individual user. However, providing such personalized information efficiently has been difficult using conventional methods.

[0797] 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 storing data in a database that provides learning content, means for constructing a learning content model based on the stored data, means for generating customized learning content based on user input information and emotional information, means for collecting user feedback, emotional data, and purchase history and optimizing the learning content model, and means for displaying the generated customized product information and tutorials on the terminal. This makes it possible to provide product information and tutorials tailored to the individual needs and emotional state of each user in a virtual store, thereby improving the user's purchasing motivation and product understanding.

[0798] "Learning Content" refers to teaching materials and resources used by users to acquire specific knowledge or skills.

[0799] A "database" is a system for storing and managing learning content and related data.

[0800] A "generated learning content model" is a model built using generative AI based on stored data to accommodate various learning styles and levels of difficulty.

[0801] "User input information" refers to information such as the subject desired to study, proficiency level, learning style, product category, characteristics, and usage method.

[0802] "Emotional information" is data related to the emotional state of the user analyzed from facial expressions, voice, etc.

[0803] "Customized learning content" refers to personalized learning materials and information generated based on user input and emotional information.

[0804] "Feedback" refers to evaluations and opinions regarding learning content and product information provided by users.

[0805] "Purchase history" is a record of products that a user has purchased in the past.

[0806] "Optimizing" means retraining the generative AI based on the collected data to improve its learning content model and the information it provides.

[0807] "Product information" refers to information about the characteristics, usage, reviews, etc. of products offered in the virtual store.

[0808] "Tutorials" are interactive guides or videos that explain the use or features of a product.

[0809] A "terminal" is a device that allows a user to input information and display customized content.

[0810] The present invention is a system for providing users with personalized product information and tutorials in a virtual store. This system utilizes a database that provides learning content, a generative AI model, and an emotion engine to generate and display optimal information based on the user's input information and emotion information. Specific embodiments of the system are described below.

[0811] Server Processing

[0812] 1. Registering content in the database

[0813] The server receives data such as product information, reviews, and tutorial videos provided by the virtual store and registers them in a database, including metadata such as product category, characteristics, and usage instructions.

[0814] 2. Building a learning content model

[0815] Using the stored data, generative AI is used to build learning content models that are trained to accommodate different shopping styles and product categories.

[0816] 3. Generating customized learning content

[0817] The server uses generative AI to generate customized learning content based on the user's input information (e.g., product category, characteristics, and usage) and the emotional information provided by the emotion engine, taking into account the user's past purchase history and emotional data.

[0818] 4. Feedback and optimization

[0819] Users browse product information and send their post-purchase feedback and sentiment data to the server. The server receives this data and stores it in a database. The AI ​​is retrained based on the feedback data and optimizes the learning content model.

[0820] Terminal handling

[0821] 1. Accepting user input

[0822] The terminal provides an interface for users to input the products and categories they are interested in. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[0823] 2. Viewing learning content

[0824] The terminal receives customized product information and tutorials sent from the server and displays them to the user, who can use this information to deepen their understanding of the product and consider purchasing it.

[0825] 3. Submitting feedback and ratings

[0826] The device provides an interface to collect feedback and ratings provided by users and send them to the server, where emotion information collected by the emotion engine is also sent.

[0827] User Action

[0828] 1. Enter your information

[0829] Users input the category and characteristics of the product they wish to purchase into the device. For example, they input information such as "electronic device," "smartphone," or "for beginners." During the learning process, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[0830] 2. Use of learning content

[0831] By viewing customized product information and tutorials displayed on the device, users can learn about the product's features and how to use it. For example, a video explaining how to set up a smartphone is provided.

[0832] 3. Providing Feedback

[0833] After using the learning content, users enter feedback on their level of understanding and satisfaction through their devices and send it to the server. They also rate the products provided and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[0834] Specific examples

[0835] For example, suppose a user is considering purchasing the latest smartphone and wants to learn how to use it. In this case, the user enters "electronic device," "smartphone," and "for beginners" into the device, and the emotion engine acquires emotional information from facial expressions and voice. Based on this information, the server uses generative AI to generate a customized visual tutorial explaining how to set up the smartphone and sends it to the device. After the user watches this tutorial and deepens their understanding of the product, they send feedback via the device saying, "This tutorial video was very helpful." Emotional data generated by the emotion engine is also sent to the server.

[0836] Prompt Sentence Examples

[0837] "Welcome to SmartShop Tutor. If you want to learn how to use the latest smartphone, what information do you want? For example, 'How to set it up for beginners' or 'How to best use apps'?"

[0838] "We'll provide you with a customized smartphone tutorial based on your interests to help you make your purchase decision."

[0839] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0840] Step 1: Registering content in the database

[0841] The server receives product information (category, characteristics, usage, reviews, tutorial videos, etc.) provided by the virtual store and stores it in a database. At this time, product metadata is also registered. Specifically, the server obtains data from the product provider and stores it in the appropriate fields of the database. The input is product information data, and the output is the product information data stored in the database.

[0842] Step 2: Building a generative AI model

[0843] The server uses a generative AI to build a learning content model based on the product information data stored in the database. This model is trained to flexibly respond to the differences associated with each product. Specifically, the server retrieves data from the database, inputs it into the generative AI, and performs training. The input is the product information data retrieved from the database, and the output is the constructed learning content model.

[0844] Step 3: Accepting User Input

[0845] The terminal provides an interface for users to input information such as the category, characteristics, and usage of the product they are considering purchasing. It also uses an emotion engine to analyze the user's facial expressions and voice to obtain emotional information. Specifically, the terminal receives input information through the user interface and runs the emotion engine to analyze the voice and facial expression data. The input is the user's input information and emotional data, and the output is the user's input information and emotional data sent to the server.

[0846] Step 4: Generate customized learning content

[0847] The server uses generative AI to generate customized learning content based on the input information and emotional information sent by the user. This generation also takes into account the user's past purchase history and emotional data. Specifically, the server inputs the user's acquired data into a model to generate optimized learning content. The input is the user's input information and emotional data, and the output is customized learning content.

[0848] Step 5: View learning content

[0849] The terminal receives customized product information and tutorials sent from the server and displays them to the user. Specifically, the terminal receives data from the server and displays it on the display. The input is the learning content sent from the server, and the output is the customized learning content displayed on the terminal display.

[0850] Step 6: Submit your feedback and rating

[0851] The device collects feedback and evaluations provided by users and sends them to the server. It also sends emotional information acquired by the emotion engine to the server. Specifically, the device collects feedback data through the user interface and sends it together with emotional data. The input is the user's feedback data and emotional data, and the output is the feedback data and emotional data sent to the server.

[0852] Step 7: Feedback and optimization

[0853] The server stores the received feedback, emotional data, and purchase history in a database, and uses this information to retrain and optimize the generative AI model. Specifically, the server stores the collected data in a database and inputs it into the generative AI for retraining. The input is user feedback data, emotional data, and purchase history, and the output is an optimized learning content model.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] [Third embodiment]

[0858] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0859] 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.

[0860] 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).

[0861] 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.

[0862] 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.

[0863] 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).

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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."

[0870] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. Specific embodiments of the system are described below.

[0871] Overview of program processing

[0872] This system consists of three main components: a server, a device, and a user. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users input information based on their own learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content through feedback and test results.

[0873] Natural language explanation of program processing

[0874] Server Processing

[0875] 1. Registering content in the database

[0876] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[0877] 2. Building a learning content model

[0878] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[0879] 3. Creating customized learning content

[0880] The server receives information sent by the user, such as the subjects they wish to study, their level of proficiency, and their learning style, and the AI ​​then generates customized learning content based on that information. This content is then sent to the device.

[0881] 4. Feedback and optimization

[0882] As users progress through their learning, they send feedback and proficiency test results to the server, which receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[0883] Terminal handling

[0884] 1. Accepting user input

[0885] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style, and sends this information to the server.

[0886] 2. Viewing learning content

[0887] The customized learning content received from the server is displayed on the device, and the displayed content is provided in the form of videos and interactive questions.

[0888] 3. Submitting feedback and test results

[0889] The terminal provides an interface for collecting user-provided feedback and proficiency test results and transmitting them to a server.

[0890] User Action

[0891] 1. Enter your information

[0892] Users input information into the device such as the subject they wish to study, their level of proficiency, and their learning style, for example, "math," "beginner," and "visual learning."

[0893] 2. Use of learning content

[0894] Students learn with customized learning content displayed on their device, including visual videos and interactive exercises to teach the basics of factoring.

[0895] 3. Providing Feedback

[0896] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[0897] Specific examples

[0898] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[0899] 1. User Input

[0900] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server.

[0901] 2. Providing learning content

[0902] Based on the information entered by Mr. A, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations with diagrams and animations is provided.

[0903] 3. Learning progression and feedback

[0904] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of comprehension and feedback into the device and takes a proficiency test. Result information such as "Comprehension: 80%" and "Test result: 85 points" is sent to the server via the device.

[0905] 4. Content optimization

[0906] Based on the feedback and test results received, the server retrains the generative AI to further optimize the learning content it provides next time.

[0907] By repeating this process, learning content optimized for each user can be provided, enabling efficient learning.

[0908] The processing flow will be explained below.

[0909] Step 1: Registering content in the database

[0910] The server receives data provided by learning content providers and stores it in a database, along with metadata such as subject, difficulty level, and format.

[0911] Step 2: Building a learning content model

[0912] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[0913] Step 3: Accepting User Input

[0914] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[0915] Step 4: Generate customized learning content

[0916] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, and learning style information. The generated content is optimized in terms of format and content to meet the user's needs.

[0917] Step 5: View learning content

[0918] The terminal receives the customized learning content sent from the server and displays it to the user, who can then use the provided content to continue their learning.

[0919] Step 6: Gather feedback and test results

[0920] After the user has used the learning content, the device collects feedback from the user and the results of the proficiency test, and sends this to the server. The feedback includes information about the user's level of understanding and satisfaction.

[0921] Step 7: Optimize based on feedback

[0922] The server analyzes the collected feedback and test result data and feeds it back to the generation AI, which uses this data to retrain its model and reflect it in the next generation of learning content. This process ensures that the learning content is continuously optimized.

[0923] In this way, each step works together as a series of steps, creating a system that efficiently provides learning content optimized for each user.

[0924] Example 1

[0925] 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."

[0926] Providing customized learning content that meets the needs of individual learners has been difficult. In particular, there is a need for an effective method for efficiently generating and continuously optimizing learning content that accommodates different learning styles and proficiency levels. Furthermore, there is a lack of mechanisms for optimizing content using feedback and test results, making it difficult to ensure an efficient learning process for learners.

[0927] 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.

[0928] In this invention, the server includes a storage means for storing data, a means for constructing a generative learning content model based on the stored data, a means for using a generative AI model to generate customized learning content based on user input information, and a means for collecting user feedback and test results and optimizing the learning content model, thereby enabling efficient provision of customized learning content tailored to the needs of individual learners and utilizing feedback to continuously optimize the content.

[0929] A "storage means" is a device or system for storing data.

[0930] "Learning content" refers to information and teaching materials for use by learners, including text, videos, images, etc.

[0931] A "learning content model" is an algorithm or data structure built to generate and manage learning content.

[0932] A "generative AI model" is a function or program that uses artificial intelligence technology to generate content that meets user needs.

[0933] "User" refers to the learner or educator who uses this system.

[0934] "Input information" refers to data such as the subjects the user wishes to study, skill level, learning style, etc., that the user provides to the system.

[0935] "Feedback" refers to opinions and evaluations of learning content provided by learners.

[0936] "Test results" refers to the scores and evaluations of tests taken by learners to measure their proficiency.

[0937] "Device" refers to a device or terminal that displays learning content and accepts user input.

[0938] "Optimization" is the process of improving learning content and its generative models based on feedback and test results.

[0939] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. This system is mainly composed of three elements: a server, a terminal, and a user. Specific embodiments of the present invention are described below.

[0940] The server is responsible for managing learning content, building models using generative AI, and managing the database. The server receives data provided by learning content providers and stores it in a database. The stored data includes, for example, text, videos, and images, along with metadata such as subject, difficulty level, and format. As a specific example of use, a learning content model is built using OpenAI's GPT-4 model. This model is trained to accommodate a variety of learning styles and difficulty levels.

[0941] The server then uses a generative AI model to generate customized learning content based on the user's input. The information input by the user includes the desired subject, proficiency level, learning style, and so on. For example, if a user inputs prompts such as "Mathematics," "Beginner," and "Visual Learning," the server generates customized learning content based on that information. The generative AI model then uses that information to generate optimal learning content, such as a video that explains how to solve linear equations using diagrams and animations, and sends it to the device.

[0942] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The device also displays customized learning content sent from the server. The displayed content is provided in the form of, for example, videos or interactive questions. Users can use this content to advance their studies.

[0943] Furthermore, the device is equipped with an interface that allows the device to collect feedback and proficiency test results after the user has used the learning content and send them to the server. For example, the user can enter specific feedback and test results, such as "Understanding: 80%" and "Test result: 85 points," and send them to the server. Based on this information, the server retrains the generative AI and optimizes the learning content model. This allows the next learning content to be further improved and better suited to the needs of each learner.

[0944] As a concrete example, when a first-year high school student named "A" uses this system to improve his or her math grades, the following series of operations takes place: A enters "Math," "Beginner," and "Visual" style into his or her device in the school's computer lab and sends that information to the server. Based on A's input, the server uses the generative AI to generate beginner-level visual learning content and sends it to the device. A watches and studies the provided visual videos, enters comprehension ratings and feedback, takes a proficiency test, and sends the results to the server. Based on this feedback and test results, the server retrains the generative AI to further optimize the learning content it provides next time.

[0945] In this way, the system can provide learning content optimized for each user and support efficient learning.

[0946] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0947] Step 1:

[0948] Registering content in the database

[0949] Server Processing

[0950] Input: Data provided by learning content providers (text, videos, images, etc.).

[0951] Specific operation: The server receives the provided learning content data.

[0952] Data processing: Formatting the received data along with metadata (subject, level, format, etc.).

[0953] Output: Save the formatted data to the database.

[0954] Specific operation: The server writes the formatted data to the database.

[0955] Step 2:

[0956] Building a learning content model

[0957] Server Processing

[0958] Input: Learning content data stored in the database.

[0959] Specific operation: The server retrieves the stored learning content data from the database.

[0960] Data computation: Training a generative AI model (e.g., OpenAI's GPT-4) based on the acquired data.

[0961] Output: A trained learning content model.

[0962] Specific operation: The server stores the trained generative AI model.

[0963] Step 3:

[0964] Entering user information

[0965] User Action

[0966] Input: Information such as subjects you wish to study, your proficiency level, and your learning style.

[0967] Specific operation: The user inputs desired information into the terminal interface.

[0968] Output: Sends user input information to the server.

[0969] Terminal handling

[0970] Specific operation: The terminal transfers the entered information to the server.

[0971] Step 4:

[0972] Generate customized learning content

[0973] Server Processing

[0974] Input: User submitted information about desired subjects, proficiency level, and learning style.

[0975] Specific operation: The server analyzes the received user information.

[0976] Data calculation: Generate customized learning content using a generative AI model based on analyzed user information.

[0977] Output: Customized learning content (e.g., a video explaining how to solve linear equations with diagrams and animations).

[0978] Specific operation: Send the generated learning content to the device.

[0979] Step 5:

[0980] View learning content

[0981] Terminal handling

[0982] Input: Customized learning content sent from the server.

[0983] Specific operation: The device displays the received learning content.

[0984] Output: The customized learning content that is displayed to the user.

[0985] What it does: Videos and interactive content appear on the screen.

[0986] Step 6:

[0987] Submitting feedback and test results

[0988] User Action

[0989] Input: Feedback and proficiency test results.

[0990] Specific actions: The user enters feedback and test results into the device interface.

[0991] Output: Sends feedback and proficiency test results to the server.

[0992] Terminal handling

[0993] Specific operation: The device transfers the collected information to the server.

[0994] Server Processing

[0995] Input: User-submitted feedback and test results.

[0996] What happens: The server stores the feedback and test results in a database.

[0997] Step 7:

[0998] Content Optimization

[0999] Server Processing

[1000] Input: Feedback and test results stored in the database.

[1001] Specific Actions: The server retrieves the stored feedback and test results.

[1002] Data computation: Retraining generative AI models based on feedback and testing results, and optimizing learning content models.

[1003] Output: Optimized learning content model.

[1004] Specific action: The next learning content provided will be more accurate.

[1005] (Application example 1)

[1006] 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."

[1007] In conventional learning systems, because each user has different learning needs, it is difficult to achieve efficient learning with uniform learning content. Customizing learning content also requires a huge amount of time and effort, making it unrealistic. Furthermore, because content is not optimized in real time based on the user's learning progress, there is a problem in that learning effectiveness is not fully realized.

[1008] 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.

[1009] In this invention, the server includes means for storing data in a database that provides learning content, means for constructing a generated learning content model based on the stored data, means for generating customized learning content based on user input information, means for collecting user feedback and test results and optimizing the learning content model, means for generating learning content using the generative AI model, and means for displaying the generated customized learning content on a smartphone or head-mounted display. This allows for efficient generation of learning content customized for each user and real-time content optimization.

[1010] A "database" is an information management system for systematically storing and managing learning content.

[1011] A "generated learning content model" is a model for representing learning content that is constructed using generative AI based on stored data.

[1012] "Customized learning content" means learning materials generated based on user input in a format appropriate for specific learning needs and proficiency levels.

[1013] "Feedback" refers to information provided by users after learning about their level of understanding and satisfaction.

[1014] "Test results" are the results of a test used to assess the level of comprehension of learning content.

[1015] A "generative AI model" is a computational model that uses artificial intelligence to generate new learning content.

[1016] A "smartphone" is a portable device that combines advanced computing and connectivity capabilities with the functionality of a mobile phone.

[1017] A "head-mounted display" is a device that is worn on the user's head to display a screen.

[1018] "Device" means an electronic device that allows a user to access and interact with learning content.

[1019] To specifically illustrate the embodiment of the present invention, the roles and processes of the server, terminal, and user are described in detail below, along with specific examples and prompts.

[1020] Server Processing

[1021] The server manages learning content, builds generative AI models, generates customized learning content, and optimizes feedback and test results. Here, we explain the specific process flow.

[1022] 1. Providing learning content and managing the database

[1023] The server processes the data and stores it in a database that provides learning content. When content is registered in the database, metadata about the content (subject, difficulty level, format, etc.) is also stored.

[1024] 2. Building a generative AI model

[1025] The server uses the stored data to build learning content models using generative AI, which uses natural language generation models such as OpenAI's GPT-3, and is trained to accommodate a variety of learning styles and levels of difficulty.

[1026] 3. Creating customized learning content

[1027] The AI ​​generates customized learning content based on information such as the user's desired subject, proficiency level, and learning style. For example, the user can enter a prompt such as "Create an interactive learning content for intermediate level math."

[1028] 4. Gather feedback and test results and optimize

[1029] As users learn, they provide feedback and test results, which are then sent to the server, which then collects and stores the data in a database.The generative AI uses this feedback data to retrain and optimize the learning content model.

[1030] Terminal handling

[1031] The terminal receives input from the user, displays customized learning content, and collects feedback.

[1032] 1. Accepting user input

[1033] The terminal provides an interface for users to input their desired subjects, proficiency level, and learning style, which is then sent to the server.

[1034] 2. Displaying customized learning content

[1035] The system displays customized learning content received from the server, which may be presented in video, text, interactive formats, etc.

[1036] 3. Submitting feedback and test results

[1037] The terminal provides an interface for collecting and transmitting user-provided feedback and proficiency test results to a server.

[1038] User Action

[1039] Users input information, access customized learning content, and provide feedback through an interface provided by the terminal.

[1040] 1. Enter your information

[1041] Users input information such as the subject they wish to study, their level of proficiency, and their learning style into the terminal. For example, they input details such as "mathematics," "intermediate," and "interactive learning."

[1042] 2. Use of learning content

[1043] The device will display customized learning content, such as interactive math problems at an intermediate level, to help students progress through their studies.

[1044] 3. Providing Feedback

[1045] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[1046] Examples and prompts

[1047] For example, if a high school student uses this system to improve their math grades, the following process will occur:

[1048] 1. User Input

[1049] "Mathematics," "Intermediate," and "Interactive" styles are entered into the terminal, and the information is sent to the server.

[1050] 2. Providing learning content

[1051] The server uses a generative AI based on the user's input information to generate "interactive intermediate level math problems" and deliver them to the device.

[1052] 3. Learning progression and feedback

[1053] The user proceeds with the study using the provided interactive learning content, and then inputs feedback and test results, which are then transmitted to the server.

[1054] The above process provides a customized and efficient learning environment for each user. The system can improve the user's learning experience by using a generative AI model to generate new learning content based on prompts.

[1055] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1056] Step 1:

[1057] User input acceptance

[1058] The device provides an interface for users to input their desired subject, proficiency level, and learning style. The user inputs this information (e.g., "Mathematics," "Intermediate," "Interactive"), and the device sends it to the server. Specifically, the input data is packaged in JSON format and sent to the server's API endpoint.

[1059] Input: Subjects you wish to study, level of proficiency, learning style

[1060] Output: Request data to the server

[1061] Processing: Packaging input data on the device and sending it to the server

[1062] Step 2:

[1063] Generate customized learning content

[1064] The server generates learning content using a generative AI model (e.g., GPT-3) based on the information received from the user. At this time, a prompt sentence is passed to the generative AI model (e.g., "Create an interactive learning content for intermediate level math."). The generative AI model generates customized learning content based on the prompt and returns the data to the server.

[1065] Input: User input information, prompt text

[1066] Output: Customized learning content

[1067] Processing: Content generation using generative AI models

[1068] Step 3:

[1069] Providing learning content

[1070] The server then transmits the generated customized learning content to the user's device, which interprets the received data and displays it in a user interface, such as displaying generated interactive questions or videos for the user to view.

[1071] Input: Customized learning content

[1072] Output: Display content on the user's device

[1073] Processing: Sending data from the server to the device and displaying it on the device

[1074] Step 4:

[1075] Progressing learning and collecting feedback

[1076] The user uses the provided learning content to progress through the learning process. After completing the learning, the device collects feedback from the user regarding their level of understanding and satisfaction. The user enters evaluation data, which the device then sends to the server.

[1077] Input: User learning feedback

[1078] Output: Feedback data to the server

[1079] Processing: Collecting feedback on the device and sending it to the server

[1080] Step 5:

[1081] Feedback analysis and model optimization

[1082] The server analyzes the received feedback and test results, and uses this data to retrain the generative AI model and optimize the learning content model, for example, updating new learning content to be more effective based on the feedback data.

[1083] Input: User feedback and test results

[1084] Output: Optimized learning content model

[1085] Processing: Analyzing feedback data and retraining the generated AI model

[1086] Through each of the above steps, customized learning content is provided to users, and a continuously optimized system is realized.

[1087] 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.

[1088] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[1089] Overview of program processing

[1090] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[1091] Natural language explanation of program processing

[1092] Server Processing

[1093] 1. Registering content in the database

[1094] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[1095] 2. Building a learning content model

[1096] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[1097] 3. Creating customized learning content

[1098] The server uses generative AI to generate customized learning content based on the user's desired study subjects, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[1099] 4. Feedback and optimization

[1100] As the user progresses with their learning, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[1101] Terminal handling

[1102] 1. Accepting user input

[1103] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[1104] 2. Viewing learning content

[1105] The terminal receives the customized learning content and content corresponding to the user's emotions sent from the server and displays them to the user, who can then use them to advance their learning.

[1106] 3. Submitting feedback and test results

[1107] The device provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server, where emotion information collected by the emotion engine is also sent.

[1108] User Action

[1109] 1. Enter your information

[1110] The user inputs information into the device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[1111] 2. Use of learning content

[1112] The device displays customized learning content and emotionally relevant content to guide students through their learning, such as visual videos and interactive puzzles to teach the basics of factoring.

[1113] 3. Providing Feedback

[1114] After using the learning content, users enter feedback on their level of understanding and satisfaction through their device and send it to the server. They also take the provided proficiency test and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[1115] Specific examples

[1116] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[1117] 1. User Input

[1118] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes Person A's facial expressions and voice to obtain emotional information.

[1119] 2. Providing learning content

[1120] Based on A's input and emotional information, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, it could provide a video that uses diagrams and animations to explain how to solve linear equations. If the emotion engine detects stress or confusion while A is learning, the server will immediately provide support materials and hints.

[1121] 3. Learning progression and feedback

[1122] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of his or her level of understanding and feedback into the device and takes a proficiency test. Result information such as "Understanding: 80%" and "Test result: 85 points" is sent to the server via the device. Emotion data collected by the emotion engine is also sent to the server.

[1123] 4. Content optimization

[1124] Based on the feedback, test results, and emotional information received, the server retrains the generative AI to further optimize the learning content it provides next time.

[1125] By repeating this process, learning content optimized for each user is provided, enabling efficient learning, and by utilizing emotional information, the user's learning experience is further improved.

[1126] The processing flow will be explained below.

[1127] Step 1: Registering content in the database

[1128] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are also stored.

[1129] Step 2: Building a learning content model

[1130] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[1131] Step 3: Accepting User Input

[1132] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[1133] Step 4: Emotion Engine Activation and Analysis

[1134] The device activates an emotion engine to monitor the user's facial expressions and voice in real time. The emotion engine analyzes the data and recognizes the user's emotional state (e.g., joy, confusion, concentration). The recognized emotion data is sent to the server.

[1135] Step 5: Generate customized learning content

[1136] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[1137] Step 6: View learning content

[1138] The terminal receives the customized learning content sent from the server and displays it to the user, for example, visual learning content for beginners' level mathematics.

[1139] Step 7: Gather feedback and test results

[1140] After the user uses the learning content, the device collects feedback and proficiency test results from the user and sends them to the server. The emotion engine also continuously monitors the user's emotional state during learning and sends this data to the server.

[1141] Step 8: Optimize based on feedback

[1142] The server analyzes the collected feedback and test result data, as well as the emotional data from the emotion engine, and feeds it back to the generative AI, which uses this data to retrain its model and optimize the learning content model. Through this process, the learning content is continuously optimized.

[1143] In this way, each step works together as a series of steps to efficiently provide learning content optimized for each user and create a personalized learning experience that takes into account the user's emotional state.

[1144] Example 2

[1145] 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."

[1146] Conventional learning systems have difficulty providing content customized to users' learning needs and emotional state, preventing them from providing an efficient learning experience. Furthermore, there are limited means to optimize learning content using user feedback and test results. Therefore, there is a need to provide optimal learning content for each individual user and maximize learning effectiveness.

[1147] 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.

[1148] In this invention, the server includes means for storing data in a database that provides digital data, means for creating a digital model constructed based on the stored data, means for generating customized digital content based on user input information and emotion data, and means for collecting feedback and test results from users and optimizing the digital model, thereby enabling the provision of learning content optimized for each user and continuous content optimization.

[1149] "Digital data" refers to information or content stored in electronic form.

[1150] A "database" refers to a system for efficiently storing, managing, and accessing large amounts of digital data.

[1151] "Digital model" refers to a product or representative form constructed from specific digital data according to certain conditions or methods.

[1152] "User" means an individual end user who uses the System to receive and use Learning Content.

[1153] "Input information" refers to data provided by a user to the system, including desired subjects, proficiency level, and learning style.

[1154] "Emotional data" refers to information that expresses a user's emotional state in numerical or categorical terms.

[1155] "Customized digital content" refers to digital data that is individually tailored and generated based on user input and emotional data.

[1156] "Feedback" refers to the evaluations, opinions, and information about understanding that users provide to the system.

[1157] "Test results" refers to the results of an assessment conducted to measure the level of proficiency and understanding of the learning content.

[1158] "Device" means the device used by a User to access the System and receive Digital Content.

[1159] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[1160] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[1161] Server Processing

[1162] The server receives digital data provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved. The server then uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and difficulty levels. The server then uses generative AI to generate customized digital content based on the user's desired study subject, proficiency level, and learning style, as well as emotional information provided by the emotion engine. The generated content is optimized with a format and content that meets the user's needs. As the user progresses with their studies, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is then retrained based on the feedback data, optimizing the digital model.

[1163] Terminal handling

[1164] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information and sends this data to the server. The device receives customized digital content and content based on the user's emotions sent from the server and displays it to the user. The user can use this content to advance their studies. The device also provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server. The emotional information collected by the emotion engine is also sent to the server.

[1165] User Action

[1166] Users input information into their device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice. The user progresses through the study using customized digital content displayed on the device and content tailored to the user's emotions. For example, visual videos and interactive problems are provided to teach the basics of factorization. After using the learning content, the user inputs feedback regarding their level of understanding and satisfaction through the device and sends it to the server. The user also takes the provided proficiency test and sends the results to the server. Emotional data during the study is also sent to the server via the emotion engine.

[1167] As a concrete example, when a first-year high school student uses this system to improve their math grades, the following process takes place: The user enters "math," "beginner," and "visual" styles into their device in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to obtain emotional information. Based on the user's input and emotional information, the server uses generative AI to generate practical, beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations using diagrams and animations might be provided. If the emotion engine detects stress or confusion during the user's learning, the server immediately provides support materials and hints. After the user watches the provided visual video and studies, they enter a comprehension assessment and feedback and take a proficiency test. The results and emotional data are sent to the server, which then retrains the generative AI based on the received information to further optimize the learning content provided next time.

[1168] An example prompt is, "Generate visual content for beginner level mathematics aimed at first-year high school students. The user's emotional information suggests stress, so please include easy-to-understand illustrations and animations."

[1169] In this way, the present invention not only provides learning content customized for each user, enabling efficient learning, but also improves the quality of the learning experience by utilizing the user's emotional information.

[1170] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1171] Step 1:

[1172] Enter user information

[1173] The user uses the device to input the subject they wish to study, their level of proficiency, and their learning style. The device receives this input information and sends it to the server. Specifically, if the user inputs "math," "beginner," and "visual learning," the information is sent to the server.

[1174] Input: Subject you wish to study, proficiency level, learning style

[1175] Output: Data sent to the server

[1176] Step 2:

[1177] Emotion data acquisition using emotion engine

[1178] The device activates an emotion engine that analyzes the user's facial expressions and voice in real time. The emotion engine acquires the user's emotional state (e.g., stress, joy, confusion) and transmits the emotional data to the server.

[1179] Input: User's facial expression, voice

[1180] Output: Emotion data

[1181] Step 3:

[1182] Collection of learning content data and database registration

[1183] The server receives digital data such as text, videos, and images provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are included. The server then manages the digital data.

[1184] Input: Digital data, metadata

[1185] Output: Registration to database completed

[1186] Step 4:

[1187] Building a learning content model

[1188] The server uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and levels of difficulty. Generative AI uses large amounts of data for machine learning.

[1189] Input: Digital data in a database

[1190] Output: Learning content model

[1191] Step 5:

[1192] Generate customized learning content

[1193] The server uses the user's desired study subject, proficiency level, learning style, and emotional information provided by the emotion engine to generate customized digital content using generative AI. For example, it generates a video that explains how to solve linear equations using diagrams and animations. The generated content is then sent to the user's device.

[1194] Input: Learning preference information, emotion data, learning content model

[1195] Output: Customized digital content

[1196] Step 6:

[1197] View learning content

[1198] The device receives the customized digital content sent from the server and displays it to the user, who can then use it to further their learning. For example, the device may play an interactive visual video.

[1199] Input: Customized digital content from the server

[1200] Output: View learning content

[1201] Step 7:

[1202] Getting feedback and test results

[1203] After learning, the device collects feedback from the user and the results of the proficiency test, and sends this feedback and test results to the server.

[1204] Input: User feedback, test results

[1205] Output: Data sent to the server

[1206] Step 8:

[1207] Content Optimization

[1208] The server retrains the generative AI based on the received feedback, test results, and emotional data, optimizing the digital model to improve the accuracy and adaptability of the learning content provided next time, for example, by improving the learning materials to reduce stress for the user.

[1209] Input: Feedback, test results, sentiment data

[1210] Output: Optimized digital content model

[1211] (Application example 2)

[1212] 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."

[1213] In modern virtual stores, users often lack sufficient information to understand the characteristics and usage of products they are considering purchasing, and the information provided is often uniform, making it difficult to address the diverse needs and emotional states of users. Therefore, to increase users' purchasing motivation and product understanding, it is necessary to provide product information and tutorials customized for each individual user. However, providing such personalized information efficiently has been difficult using conventional methods.

[1214] 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 storing data in a database that provides learning content, means for constructing a learning content model based on the stored data, means for generating customized learning content based on user input information and emotional information, means for collecting user feedback, emotional data, and purchase history and optimizing the learning content model, and means for displaying the generated customized product information and tutorials on the terminal. This makes it possible to provide product information and tutorials tailored to the individual needs and emotional state of each user in a virtual store, thereby improving the user's purchasing motivation and product understanding.

[1215] "Learning Content" refers to teaching materials and resources used by users to acquire specific knowledge or skills.

[1216] A "database" is a system for storing and managing learning content and related data.

[1217] A "generated learning content model" is a model built using generative AI based on stored data to accommodate various learning styles and levels of difficulty.

[1218] "User input information" refers to information such as the subject desired to study, proficiency level, learning style, product category, characteristics, and usage method.

[1219] "Emotional information" is data related to the emotional state of the user analyzed from facial expressions, voice, etc.

[1220] "Customized learning content" refers to personalized learning materials and information generated based on user input and emotional information.

[1221] "Feedback" refers to evaluations and opinions regarding learning content and product information provided by users.

[1222] "Purchase history" is a record of products that a user has purchased in the past.

[1223] "Optimizing" means retraining the generative AI based on the collected data to improve its learning content model and the information it provides.

[1224] "Product information" refers to information about the characteristics, usage, reviews, etc. of products offered in the virtual store.

[1225] "Tutorials" are interactive guides or videos that explain the use or features of a product.

[1226] A "terminal" is a device that allows a user to input information and display customized content.

[1227] The present invention is a system for providing users with personalized product information and tutorials in a virtual store. This system utilizes a database that provides learning content, a generative AI model, and an emotion engine to generate and display optimal information based on the user's input information and emotion information. Specific embodiments of the system are described below.

[1228] Server Processing

[1229] 1. Registering content in the database

[1230] The server receives data such as product information, reviews, and tutorial videos provided by the virtual store and registers them in a database, including metadata such as product category, characteristics, and usage instructions.

[1231] 2. Building a learning content model

[1232] Using the stored data, generative AI is used to build learning content models that are trained to accommodate different shopping styles and product categories.

[1233] 3. Generating customized learning content

[1234] The server uses generative AI to generate customized learning content based on the user's input information (e.g., product category, characteristics, and usage) and the emotional information provided by the emotion engine, taking into account the user's past purchase history and emotional data.

[1235] 4. Feedback and optimization

[1236] Users browse product information and send their post-purchase feedback and sentiment data to the server. The server receives this data and stores it in a database. The AI ​​is retrained based on the feedback data and optimizes the learning content model.

[1237] Terminal handling

[1238] 1. Accepting user input

[1239] The terminal provides an interface for users to input the products and categories they are interested in. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[1240] 2. Viewing learning content

[1241] The terminal receives customized product information and tutorials sent from the server and displays them to the user, who can use this information to deepen their understanding of the product and consider purchasing it.

[1242] 3. Submitting feedback and ratings

[1243] The device provides an interface to collect feedback and ratings provided by users and send them to the server, where emotion information collected by the emotion engine is also sent.

[1244] User Action

[1245] 1. Enter your information

[1246] Users input the category and characteristics of the product they wish to purchase into the device. For example, they input information such as "electronic device," "smartphone," or "for beginners." During the learning process, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[1247] 2. Use of learning content

[1248] By viewing customized product information and tutorials displayed on the device, users can learn about the product's features and how to use it. For example, a video explaining how to set up a smartphone is provided.

[1249] 3. Providing Feedback

[1250] After using the learning content, users enter feedback on their level of understanding and satisfaction through their devices and send it to the server. They also rate the products provided and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[1251] Specific examples

[1252] For example, suppose a user is considering purchasing the latest smartphone and wants to learn how to use it. In this case, the user enters "electronic device," "smartphone," and "for beginners" into the device, and the emotion engine acquires emotional information from facial expressions and voice. Based on this information, the server uses generative AI to generate a customized visual tutorial explaining how to set up the smartphone and sends it to the device. After the user watches this tutorial and deepens their understanding of the product, they send feedback via the device saying, "This tutorial video was very helpful." Emotional data generated by the emotion engine is also sent to the server.

[1253] Prompt Sentence Examples

[1254] "Welcome to SmartShop Tutor. If you want to learn how to use the latest smartphone, what information do you want? For example, 'How to set it up for beginners' or 'How to best use apps'?"

[1255] "We'll provide you with a customized smartphone tutorial based on your interests to help you make your purchase decision."

[1256] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1257] Step 1: Registering content in the database

[1258] The server receives product information (category, characteristics, usage, reviews, tutorial videos, etc.) provided by the virtual store and stores it in a database. At this time, product metadata is also registered. Specifically, the server obtains data from the product provider and stores it in the appropriate fields of the database. The input is product information data, and the output is the product information data stored in the database.

[1259] Step 2: Building a generative AI model

[1260] The server uses a generative AI to build a learning content model based on the product information data stored in the database. This model is trained to flexibly respond to the differences associated with each product. Specifically, the server retrieves data from the database, inputs it into the generative AI, and performs training. The input is the product information data retrieved from the database, and the output is the constructed learning content model.

[1261] Step 3: Accepting User Input

[1262] The terminal provides an interface for users to input information such as the category, characteristics, and usage of the product they are considering purchasing. It also uses an emotion engine to analyze the user's facial expressions and voice to obtain emotional information. Specifically, the terminal receives input information through the user interface and runs the emotion engine to analyze the voice and facial expression data. The input is the user's input information and emotional data, and the output is the user's input information and emotional data sent to the server.

[1263] Step 4: Generate customized learning content

[1264] The server uses generative AI to generate customized learning content based on the input information and emotional information sent by the user. This generation also takes into account the user's past purchase history and emotional data. Specifically, the server inputs the user's acquired data into a model to generate optimized learning content. The input is the user's input information and emotional data, and the output is customized learning content.

[1265] Step 5: View learning content

[1266] The terminal receives customized product information and tutorials sent from the server and displays them to the user. Specifically, the terminal receives data from the server and displays it on the display. The input is the learning content sent from the server, and the output is the customized learning content displayed on the terminal display.

[1267] Step 6: Submit your feedback and rating

[1268] The device collects feedback and evaluations provided by users and sends them to the server. It also sends emotional information acquired by the emotion engine to the server. Specifically, the device collects feedback data through the user interface and sends it together with emotional data. The input is the user's feedback data and emotional data, and the output is the feedback data and emotional data sent to the server.

[1269] Step 7: Feedback and optimization

[1270] The server stores the received feedback, emotional data, and purchase history in a database, and uses this information to retrain and optimize the generative AI model. Specifically, the server stores the collected data in a database and inputs it into the generative AI for retraining. The input is user feedback data, emotional data, and purchase history, and the output is an optimized learning content model.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] [Fourth embodiment]

[1275] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1276] 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.

[1277] 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).

[1278] 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.

[1279] 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.

[1280] 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).

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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."

[1288] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. Specific embodiments of the system are described below.

[1289] Overview of program processing

[1290] This system consists of three main components: a server, a device, and a user. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users input information based on their own learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content through feedback and test results.

[1291] Natural language explanation of program processing

[1292] Server Processing

[1293] 1. Registering content in the database

[1294] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[1295] 2. Building a learning content model

[1296] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[1297] 3. Creating customized learning content

[1298] The server receives information sent by the user, such as the subjects they wish to study, their level of proficiency, and their learning style, and the AI ​​then generates customized learning content based on that information. This content is then sent to the device.

[1299] 4. Feedback and optimization

[1300] As users progress through their learning, they send feedback and proficiency test results to the server, which receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[1301] Terminal handling

[1302] 1. Accepting user input

[1303] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style, and sends this information to the server.

[1304] 2. Viewing learning content

[1305] The customized learning content received from the server is displayed on the device, and the displayed content is provided in the form of videos and interactive questions.

[1306] 3. Submitting feedback and test results

[1307] The terminal provides an interface for collecting user-provided feedback and proficiency test results and transmitting them to a server.

[1308] User Action

[1309] 1. Enter your information

[1310] Users input information into the device such as the subject they wish to study, their level of proficiency, and their learning style, for example, "math," "beginner," and "visual learning."

[1311] 2. Use of learning content

[1312] Students learn with customized learning content displayed on their device, including visual videos and interactive exercises to teach the basics of factoring.

[1313] 3. Providing Feedback

[1314] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[1315] Specific examples

[1316] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[1317] 1. User Input

[1318] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server.

[1319] 2. Providing learning content

[1320] Based on the information entered by Mr. A, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations with diagrams and animations is provided.

[1321] 3. Learning progression and feedback

[1322] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of comprehension and feedback into the device and takes a proficiency test. Result information such as "Comprehension: 80%" and "Test result: 85 points" is sent to the server via the device.

[1323] 4. Content optimization

[1324] Based on the feedback and test results received, the server retrains the generative AI to further optimize the learning content it provides next time.

[1325] By repeating this process, learning content optimized for each user can be provided, enabling efficient learning.

[1326] The processing flow will be explained below.

[1327] Step 1: Registering content in the database

[1328] The server receives data provided by learning content providers and stores it in a database, along with metadata such as subject, difficulty level, and format.

[1329] Step 2: Building a learning content model

[1330] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[1331] Step 3: Accepting User Input

[1332] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[1333] Step 4: Generate customized learning content

[1334] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, and learning style information. The generated content is optimized in terms of format and content to meet the user's needs.

[1335] Step 5: View learning content

[1336] The terminal receives the customized learning content sent from the server and displays it to the user, who can then use the provided content to continue their learning.

[1337] Step 6: Gather feedback and test results

[1338] After the user has used the learning content, the device collects feedback from the user and the results of the proficiency test, and sends this to the server. The feedback includes information about the user's level of understanding and satisfaction.

[1339] Step 7: Optimize based on feedback

[1340] The server analyzes the collected feedback and test result data and feeds it back to the generation AI, which uses this data to retrain its model and reflect it in the next generation of learning content. This process ensures that the learning content is continuously optimized.

[1341] In this way, each step works together as a series of steps, creating a system that efficiently provides learning content optimized for each user.

[1342] Example 1

[1343] 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."

[1344] Providing customized learning content that meets the needs of individual learners has been difficult. In particular, there is a need for an effective method for efficiently generating and continuously optimizing learning content that accommodates different learning styles and proficiency levels. Furthermore, there is a lack of mechanisms for optimizing content using feedback and test results, making it difficult to ensure an efficient learning process for learners.

[1345] 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.

[1346] In this invention, the server includes a storage means for storing data, a means for constructing a generative learning content model based on the stored data, a means for using a generative AI model to generate customized learning content based on user input information, and a means for collecting user feedback and test results and optimizing the learning content model, thereby enabling efficient provision of customized learning content tailored to the needs of individual learners and utilizing feedback to continuously optimize the content.

[1347] A "storage means" is a device or system for storing data.

[1348] "Learning content" refers to information and teaching materials for use by learners, including text, videos, images, etc.

[1349] A "learning content model" is an algorithm or data structure built to generate and manage learning content.

[1350] A "generative AI model" is a function or program that uses artificial intelligence technology to generate content that meets user needs.

[1351] "User" refers to the learner or educator who uses this system.

[1352] "Input information" refers to data such as the subjects the user wishes to study, skill level, learning style, etc., that the user provides to the system.

[1353] "Feedback" refers to opinions and evaluations of learning content provided by learners.

[1354] "Test results" refers to the scores and evaluations of tests taken by learners to measure their proficiency.

[1355] "Device" refers to a device or terminal that displays learning content and accepts user input.

[1356] "Optimization" is the process of improving learning content and its generative models based on feedback and test results.

[1357] The present invention is a system that utilizes generative AI to provide learning content customized to the user's learning needs. This system is mainly composed of three elements: a server, a terminal, and a user. Specific embodiments of the present invention are described below.

[1358] The server is responsible for managing learning content, building models using generative AI, and managing the database. The server receives data provided by learning content providers and stores it in a database. The stored data includes, for example, text, videos, and images, along with metadata such as subject, difficulty level, and format. As a specific example of use, a learning content model is built using OpenAI's GPT-4 model. This model is trained to accommodate a variety of learning styles and difficulty levels.

[1359] The server then uses a generative AI model to generate customized learning content based on the user's input. The information input by the user includes the desired subject, proficiency level, learning style, and so on. For example, if a user inputs prompts such as "Mathematics," "Beginner," and "Visual Learning," the server generates customized learning content based on that information. The generative AI model then uses that information to generate optimal learning content, such as a video that explains how to solve linear equations using diagrams and animations, and sends it to the device.

[1360] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The device also displays customized learning content sent from the server. The displayed content is provided in the form of, for example, videos or interactive questions. Users can use this content to advance their studies.

[1361] Furthermore, the device is equipped with an interface that allows the device to collect feedback and proficiency test results after the user has used the learning content and send them to the server. For example, the user can enter specific feedback and test results, such as "Understanding: 80%" and "Test result: 85 points," and send them to the server. Based on this information, the server retrains the generative AI and optimizes the learning content model. This allows the next learning content to be further improved and better suited to the needs of each learner.

[1362] As a concrete example, when a first-year high school student named "A" uses this system to improve his or her math grades, the following series of operations takes place: A enters "Math," "Beginner," and "Visual" style into his or her device in the school's computer lab and sends that information to the server. Based on A's input, the server uses the generative AI to generate beginner-level visual learning content and sends it to the device. A watches and studies the provided visual videos, enters comprehension ratings and feedback, takes a proficiency test, and sends the results to the server. Based on this feedback and test results, the server retrains the generative AI to further optimize the learning content it provides next time.

[1363] In this way, the system can provide learning content optimized for each user and support efficient learning.

[1364] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1365] Step 1:

[1366] Registering content in the database

[1367] Server Processing

[1368] Input: Data provided by learning content providers (text, videos, images, etc.).

[1369] Specific operation: The server receives the provided learning content data.

[1370] Data processing: Formatting the received data along with metadata (subject, level, format, etc.).

[1371] Output: Save the formatted data to the database.

[1372] Specific operation: The server writes the formatted data to the database.

[1373] Step 2:

[1374] Building a learning content model

[1375] Server Processing

[1376] Input: Learning content data stored in the database.

[1377] Specific operation: The server retrieves the stored learning content data from the database.

[1378] Data computation: Training a generative AI model (e.g., OpenAI's GPT-4) based on the acquired data.

[1379] Output: A trained learning content model.

[1380] Specific operation: The server stores the trained generative AI model.

[1381] Step 3:

[1382] Entering user information

[1383] User Action

[1384] Input: Information such as subjects you wish to study, your proficiency level, and your learning style.

[1385] Specific operation: The user inputs desired information into the terminal interface.

[1386] Output: Sends user input information to the server.

[1387] Terminal handling

[1388] Specific operation: The terminal transfers the entered information to the server.

[1389] Step 4:

[1390] Generate customized learning content

[1391] Server Processing

[1392] Input: User submitted information about desired subjects, proficiency level, and learning style.

[1393] Specific operation: The server analyzes the received user information.

[1394] Data calculation: Generate customized learning content using a generative AI model based on analyzed user information.

[1395] Output: Customized learning content (e.g., a video explaining how to solve linear equations with diagrams and animations).

[1396] Specific operation: Send the generated learning content to the device.

[1397] Step 5:

[1398] View learning content

[1399] Terminal handling

[1400] Input: Customized learning content sent from the server.

[1401] Specific operation: The device displays the received learning content.

[1402] Output: The customized learning content that is displayed to the user.

[1403] What it does: Videos and interactive content appear on the screen.

[1404] Step 6:

[1405] Submitting feedback and test results

[1406] User Action

[1407] Input: Feedback and proficiency test results.

[1408] Specific actions: The user enters feedback and test results into the device interface.

[1409] Output: Sends feedback and proficiency test results to the server.

[1410] Terminal handling

[1411] Specific operation: The device transfers the collected information to the server.

[1412] Server Processing

[1413] Input: User-submitted feedback and test results.

[1414] What happens: The server stores the feedback and test results in a database.

[1415] Step 7:

[1416] Content Optimization

[1417] Server Processing

[1418] Input: Feedback and test results stored in the database.

[1419] Specific Actions: The server retrieves the stored feedback and test results.

[1420] Data computation: Retraining generative AI models based on feedback and testing results, and optimizing learning content models.

[1421] Output: Optimized learning content model.

[1422] Specific action: The next learning content provided will be more accurate.

[1423] (Application example 1)

[1424] 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."

[1425] In conventional learning systems, because each user has different learning needs, it is difficult to achieve efficient learning with uniform learning content. Customizing learning content also requires a huge amount of time and effort, making it unrealistic. Furthermore, because content is not optimized in real time based on the user's learning progress, there is a problem in that learning effectiveness is not fully realized.

[1426] 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.

[1427] In this invention, the server includes means for storing data in a database that provides learning content, means for constructing a generated learning content model based on the stored data, means for generating customized learning content based on user input information, means for collecting user feedback and test results and optimizing the learning content model, means for generating learning content using the generative AI model, and means for displaying the generated customized learning content on a smartphone or head-mounted display. This allows for efficient generation of learning content customized for each user and real-time content optimization.

[1428] A "database" is an information management system for systematically storing and managing learning content.

[1429] A "generated learning content model" is a model for representing learning content that is constructed using generative AI based on stored data.

[1430] "Customized learning content" means learning materials generated based on user input in a format appropriate for specific learning needs and proficiency levels.

[1431] "Feedback" refers to information provided by users after learning about their level of understanding and satisfaction.

[1432] "Test results" are the results of a test used to assess the level of comprehension of learning content.

[1433] A "generative AI model" is a computational model that uses artificial intelligence to generate new learning content.

[1434] A "smartphone" is a portable device that combines advanced computing and connectivity capabilities with the functionality of a mobile phone.

[1435] A "head-mounted display" is a device that is worn on the user's head to display a screen.

[1436] "Device" means an electronic device that allows a user to access and interact with learning content.

[1437] To specifically illustrate the embodiment of the present invention, the roles and processes of the server, terminal, and user are described in detail below, along with specific examples and prompts.

[1438] Server Processing

[1439] The server manages learning content, builds generative AI models, generates customized learning content, and optimizes feedback and test results. Here, we explain the specific process flow.

[1440] 1. Providing learning content and managing the database

[1441] The server processes the data and stores it in a database that provides learning content. When content is registered in the database, metadata about the content (subject, difficulty level, format, etc.) is also stored.

[1442] 2. Building a generative AI model

[1443] The server uses the stored data to build learning content models using generative AI, which uses natural language generation models such as OpenAI's GPT-3, and is trained to accommodate a variety of learning styles and levels of difficulty.

[1444] 3. Creating customized learning content

[1445] The AI ​​generates customized learning content based on information such as the user's desired subject, proficiency level, and learning style. For example, the user can enter a prompt such as "Create an interactive learning content for intermediate level math."

[1446] 4. Gather feedback and test results and optimize

[1447] As users learn, they provide feedback and test results, which are then sent to the server, which then collects and stores the data in a database.The generative AI uses this feedback data to retrain and optimize the learning content model.

[1448] Terminal handling

[1449] The terminal receives input from the user, displays customized learning content, and collects feedback.

[1450] 1. Accepting user input

[1451] The terminal provides an interface for users to input their desired subjects, proficiency level, and learning style, which is then sent to the server.

[1452] 2. Displaying customized learning content

[1453] The system displays customized learning content received from the server, which may be presented in video, text, interactive formats, etc.

[1454] 3. Submitting feedback and test results

[1455] The terminal provides an interface for collecting and transmitting user-provided feedback and proficiency test results to a server.

[1456] User Action

[1457] Users input information, access customized learning content, and provide feedback through an interface provided by the terminal.

[1458] 1. Enter your information

[1459] Users input information such as the subject they wish to study, their level of proficiency, and their learning style into the terminal. For example, they input details such as "mathematics," "intermediate," and "interactive learning."

[1460] 2. Use of learning content

[1461] The device will display customized learning content, such as interactive math problems at an intermediate level, to help students progress through their studies.

[1462] 3. Providing Feedback

[1463] After using the learning content, users input feedback on their level of understanding and satisfaction through their devices and send it to the server. They also take the provided proficiency test and send the results to the server.

[1464] Examples and prompts

[1465] For example, if a high school student uses this system to improve their math grades, the following process will occur:

[1466] 1. User Input

[1467] "Mathematics," "Intermediate," and "Interactive" styles are entered into the terminal, and the information is sent to the server.

[1468] 2. Providing learning content

[1469] The server uses a generative AI based on the user's input information to generate "interactive intermediate level math problems" and deliver them to the device.

[1470] 3. Learning progression and feedback

[1471] The user proceeds with the study using the provided interactive learning content, and then inputs feedback and test results, which are then transmitted to the server.

[1472] The above process provides a customized and efficient learning environment for each user. The system can improve the user's learning experience by using a generative AI model to generate new learning content based on prompts.

[1473] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1474] Step 1:

[1475] User input acceptance

[1476] The device provides an interface for users to input their desired subject, proficiency level, and learning style. The user inputs this information (e.g., "Mathematics," "Intermediate," "Interactive"), and the device sends it to the server. Specifically, the input data is packaged in JSON format and sent to the server's API endpoint.

[1477] Input: Subjects you wish to study, level of proficiency, learning style

[1478] Output: Request data to the server

[1479] Processing: Packaging input data on the device and sending it to the server

[1480] Step 2:

[1481] Generate customized learning content

[1482] The server generates learning content using a generative AI model (e.g., GPT-3) based on the information received from the user. At this time, a prompt sentence is passed to the generative AI model (e.g., "Create an interactive learning content for intermediate level math."). The generative AI model generates customized learning content based on the prompt and returns the data to the server.

[1483] Input: User input information, prompt text

[1484] Output: Customized learning content

[1485] Processing: Content generation using generative AI models

[1486] Step 3:

[1487] Providing learning content

[1488] The server then transmits the generated customized learning content to the user's device, which interprets the received data and displays it in a user interface, such as displaying generated interactive questions or videos for the user to view.

[1489] Input: Customized learning content

[1490] Output: Display content on the user's device

[1491] Processing: Sending data from the server to the device and displaying it on the device

[1492] Step 4:

[1493] Progressing learning and collecting feedback

[1494] The user uses the provided learning content to progress through the learning process. After completing the learning, the device collects feedback from the user regarding their level of understanding and satisfaction. The user enters evaluation data, which the device then sends to the server.

[1495] Input: User learning feedback

[1496] Output: Feedback data to the server

[1497] Processing: Collecting feedback on the device and sending it to the server

[1498] Step 5:

[1499] Feedback analysis and model optimization

[1500] The server analyzes the received feedback and test results, and uses this data to retrain the generative AI model and optimize the learning content model, for example, updating new learning content to be more effective based on the feedback data.

[1501] Input: User feedback and test results

[1502] Output: Optimized learning content model

[1503] Processing: Analyzing feedback data and retraining the generated AI model

[1504] Through each of the above steps, customized learning content is provided to users, and a continuously optimized system is realized.

[1505] 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.

[1506] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[1507] Overview of program processing

[1508] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[1509] Natural language explanation of program processing

[1510] Server Processing

[1511] 1. Registering content in the database

[1512] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved.

[1513] 2. Building a learning content model

[1514] The server uses generative AI to build learning content models based on the collected content data, which are trained to accommodate different learning styles and levels of difficulty.

[1515] 3. Creating customized learning content

[1516] The server uses generative AI to generate customized learning content based on the user's desired study subjects, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[1517] 4. Feedback and optimization

[1518] As the user progresses with their learning, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is retrained based on the feedback data and optimizes the learning content model.

[1519] Terminal handling

[1520] 1. Accepting user input

[1521] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[1522] 2. Viewing learning content

[1523] The terminal receives the customized learning content and content corresponding to the user's emotions sent from the server and displays them to the user, who can then use them to advance their learning.

[1524] 3. Submitting feedback and test results

[1525] The device provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server, where emotion information collected by the emotion engine is also sent.

[1526] User Action

[1527] 1. Enter your information

[1528] The user inputs information into the device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[1529] 2. Use of learning content

[1530] The device displays customized learning content and emotionally relevant content to guide students through their learning, such as visual videos and interactive puzzles to teach the basics of factoring.

[1531] 3. Providing Feedback

[1532] After using the learning content, users enter feedback on their level of understanding and satisfaction through their device and send it to the server. They also take the provided proficiency test and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[1533] Specific examples

[1534] For example, if a first-year high school student named "Mr. A" uses this system to improve his or her math grades, the following process will take place.

[1535] 1. User Input

[1536] Person A enters the "Mathematics," "Beginner," and "Visual" styles into a terminal in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes Person A's facial expressions and voice to obtain emotional information.

[1537] 2. Providing learning content

[1538] Based on A's input and emotional information, the server uses generative AI to generate practical beginner-level visual learning content and sends it to the device. For example, it could provide a video that uses diagrams and animations to explain how to solve linear equations. If the emotion engine detects stress or confusion while A is learning, the server will immediately provide support materials and hints.

[1539] 3. Learning progression and feedback

[1540] Person A watches the provided visual video and studies. Afterwards, he or she enters an assessment of his or her level of understanding and feedback into the device and takes a proficiency test. Result information such as "Understanding: 80%" and "Test result: 85 points" is sent to the server via the device. Emotion data collected by the emotion engine is also sent to the server.

[1541] 4. Content optimization

[1542] Based on the feedback, test results, and emotional information received, the server retrains the generative AI to further optimize the learning content it provides next time.

[1543] By repeating this process, learning content optimized for each user is provided, enabling efficient learning, and by utilizing emotional information, the user's learning experience is further improved.

[1544] The processing flow will be explained below.

[1545] Step 1: Registering content in the database

[1546] The server receives data (e.g., text, video, and images) provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are also stored.

[1547] Step 2: Building a learning content model

[1548] The server uses the stored content data to build a learning content model using generative AI. The generative AI uses the collected data as training data to build a model that can accommodate various learning styles and difficulty levels.

[1549] Step 3: Accepting User Input

[1550] The terminal provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The information entered by the user is sent to the server.

[1551] Step 4: Emotion Engine Activation and Analysis

[1552] The device activates an emotion engine to monitor the user's facial expressions and voice in real time. The emotion engine analyzes the data and recognizes the user's emotional state (e.g., joy, confusion, concentration). The recognized emotion data is sent to the server.

[1553] Step 5: Generate customized learning content

[1554] The server uses generative AI to generate customized learning content based on the user's desired subject, proficiency level, learning style, and emotional information provided by the emotion engine. The generated content is optimized in terms of format and content to meet the user's needs.

[1555] Step 6: View learning content

[1556] The terminal receives the customized learning content sent from the server and displays it to the user, for example, visual learning content for beginners' level mathematics.

[1557] Step 7: Gather feedback and test results

[1558] After the user uses the learning content, the device collects feedback and proficiency test results from the user and sends them to the server. The emotion engine also continuously monitors the user's emotional state during learning and sends this data to the server.

[1559] Step 8: Optimize based on feedback

[1560] The server analyzes the collected feedback and test result data, as well as the emotional data from the emotion engine, and feeds it back to the generative AI, which uses this data to retrain its model and optimize the learning content model. Through this process, the learning content is continuously optimized.

[1561] In this way, each step works together as a series of steps to efficiently provide learning content optimized for each user and create a personalized learning experience that takes into account the user's emotional state.

[1562] Example 2

[1563] 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."

[1564] Conventional learning systems have difficulty providing content customized to users' learning needs and emotional state, preventing them from providing an efficient learning experience. Furthermore, there are limited means to optimize learning content using user feedback and test results. Therefore, there is a need to provide optimal learning content for each individual user and maximize learning effectiveness.

[1565] 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.

[1566] In this invention, the server includes means for storing data in a database that provides digital data, means for creating a digital model constructed based on the stored data, means for generating customized digital content based on user input information and emotion data, and means for collecting feedback and test results from users and optimizing the digital model, thereby enabling the provision of learning content optimized for each user and continuous content optimization.

[1567] "Digital data" refers to information or content stored in electronic form.

[1568] A "database" refers to a system for efficiently storing, managing, and accessing large amounts of digital data.

[1569] "Digital model" refers to a product or representative form constructed from specific digital data according to certain conditions or methods.

[1570] "User" means an individual end user who uses the System to receive and use Learning Content.

[1571] "Input information" refers to data provided by a user to the system, including desired subjects, proficiency level, and learning style.

[1572] "Emotional data" refers to information that expresses a user's emotional state in numerical or categorical terms.

[1573] "Customized digital content" refers to digital data that is individually tailored and generated based on user input and emotional data.

[1574] "Feedback" refers to the evaluations, opinions, and information about understanding that users provide to the system.

[1575] "Test results" refers to the results of an assessment conducted to measure the level of proficiency and understanding of the learning content.

[1576] "Device" means the device used by a User to access the System and receive Digital Content.

[1577] The present invention is a system that utilizes generative AI to provide learning content customized according to the learning needs and emotional state of a user. Specific embodiments of the system are described below.

[1578] This system consists of three main elements: a server, a device, and a user, as well as an emotion engine. The server is responsible for managing learning content, building models using generative AI, and managing the database, while the device accepts user input and displays customized learning content. Users enter information based on their learning needs, and the server and device work together to provide optimized learning content. The server also continuously optimizes the content by utilizing feedback, test results, and emotion data obtained through the emotion engine.

[1579] Server Processing

[1580] The server receives digital data provided by learning content providers and registers it in a database. When registered, metadata such as subject, difficulty level, and format are also saved. The server then uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and difficulty levels. The server then uses generative AI to generate customized digital content based on the user's desired study subject, proficiency level, and learning style, as well as emotional information provided by the emotion engine. The generated content is optimized with a format and content that meets the user's needs. As the user progresses with their studies, they send feedback, proficiency test results, and emotional data from the emotion engine to the server. The server receives this data and stores it in a database. The generative AI is then retrained based on the feedback data, optimizing the digital model.

[1581] Terminal handling

[1582] The device provides an interface for users to input the subjects they wish to study, their level of proficiency, and their learning style. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information and sends this data to the server. The device receives customized digital content and content based on the user's emotions sent from the server and displays it to the user. The user can use this content to advance their studies. The device also provides an interface for collecting feedback and proficiency test results provided by the user and sending them to the server. The emotional information collected by the emotion engine is also sent to the server.

[1583] User Action

[1584] Users input information into their device, such as the subject they wish to study, their level of proficiency, and their learning style. For example, they might input "math," "beginner," and "visual learning." During the study, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice. The user progresses through the study using customized digital content displayed on the device and content tailored to the user's emotions. For example, visual videos and interactive problems are provided to teach the basics of factorization. After using the learning content, the user inputs feedback regarding their level of understanding and satisfaction through the device and sends it to the server. The user also takes the provided proficiency test and sends the results to the server. Emotional data during the study is also sent to the server via the emotion engine.

[1585] As a concrete example, when a first-year high school student uses this system to improve their math grades, the following process takes place: The user enters "math," "beginner," and "visual" styles into their device in the school's computer lab and sends the information to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to obtain emotional information. Based on the user's input and emotional information, the server uses generative AI to generate practical, beginner-level visual learning content and sends it to the device. For example, a video explaining how to solve linear equations using diagrams and animations might be provided. If the emotion engine detects stress or confusion during the user's learning, the server immediately provides support materials and hints. After the user watches the provided visual video and studies, they enter a comprehension assessment and feedback and take a proficiency test. The results and emotional data are sent to the server, which then retrains the generative AI based on the received information to further optimize the learning content provided next time.

[1586] An example prompt is, "Generate visual content for beginner level mathematics aimed at first-year high school students. The user's emotional information suggests stress, so please include easy-to-understand illustrations and animations."

[1587] In this way, the present invention not only provides learning content customized for each user, enabling efficient learning, but also improves the quality of the learning experience by utilizing the user's emotional information.

[1588] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1589] Step 1:

[1590] Enter user information

[1591] The user uses the device to input the subject they wish to study, their level of proficiency, and their learning style. The device receives this input information and sends it to the server. Specifically, if the user inputs "math," "beginner," and "visual learning," the information is sent to the server.

[1592] Input: Subject you wish to study, proficiency level, learning style

[1593] Output: Data sent to the server

[1594] Step 2:

[1595] Emotion data acquisition using emotion engine

[1596] The device activates an emotion engine that analyzes the user's facial expressions and voice in real time. The emotion engine acquires the user's emotional state (e.g., stress, joy, confusion) and transmits the emotional data to the server.

[1597] Input: User's facial expression, voice

[1598] Output: Emotion data

[1599] Step 3:

[1600] Collection of learning content data and database registration

[1601] The server receives digital data such as text, videos, and images provided by learning content providers and registers it in a database. When registering, metadata such as subject, difficulty level, and format are included. The server then manages the digital data.

[1602] Input: Digital data, metadata

[1603] Output: Registration to database completed

[1604] Step 4:

[1605] Building a learning content model

[1606] The server uses generative AI to build a digital model based on the collected content data. This model is trained to accommodate various learning styles and levels of difficulty. Generative AI uses large amounts of data for machine learning.

[1607] Input: Digital data in a database

[1608] Output: Learning content model

[1609] Step 5:

[1610] Generate customized learning content

[1611] The server uses the user's desired study subject, proficiency level, learning style, and emotional information provided by the emotion engine to generate customized digital content using generative AI. For example, it generates a video that explains how to solve linear equations using diagrams and animations. The generated content is then sent to the user's device.

[1612] Input: Learning preference information, emotion data, learning content model

[1613] Output: Customized digital content

[1614] Step 6:

[1615] View learning content

[1616] The device receives the customized digital content sent from the server and displays it to the user, who can then use it to further their learning. For example, the device may play an interactive visual video.

[1617] Input: Customized digital content from the server

[1618] Output: View learning content

[1619] Step 7:

[1620] Getting feedback and test results

[1621] After learning, the device collects feedback from the user and the results of the proficiency test, and sends this feedback and test results to the server.

[1622] Input: User feedback, test results

[1623] Output: Data sent to the server

[1624] Step 8:

[1625] Content Optimization

[1626] The server retrains the generative AI based on the received feedback, test results, and emotional data, optimizing the digital model to improve the accuracy and adaptability of the learning content provided next time, for example, by improving the learning materials to reduce stress for the user.

[1627] Input: Feedback, test results, sentiment data

[1628] Output: Optimized digital content model

[1629] (Application example 2)

[1630] 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."

[1631] In modern virtual stores, users often lack sufficient information to understand the characteristics and usage of products they are considering purchasing, and the information provided is often uniform, making it difficult to address the diverse needs and emotional states of users. Therefore, to increase users' purchasing motivation and product understanding, it is necessary to provide product information and tutorials customized for each individual user. However, providing such personalized information efficiently has been difficult using conventional methods.

[1632] 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 storing data in a database that provides learning content, means for constructing a learning content model based on the stored data, means for generating customized learning content based on user input information and emotional information, means for collecting user feedback, emotional data, and purchase history and optimizing the learning content model, and means for displaying the generated customized product information and tutorials on the terminal. This makes it possible to provide product information and tutorials tailored to the individual needs and emotional state of each user in a virtual store, thereby improving the user's purchasing motivation and product understanding.

[1633] "Learning Content" refers to teaching materials and resources used by users to acquire specific knowledge or skills.

[1634] A "database" is a system for storing and managing learning content and related data.

[1635] A "generated learning content model" is a model built using generative AI based on stored data to accommodate various learning styles and levels of difficulty.

[1636] "User input information" refers to information such as the subject desired to study, proficiency level, learning style, product category, characteristics, and usage method.

[1637] "Emotional information" is data related to the emotional state of the user analyzed from facial expressions, voice, etc.

[1638] "Customized learning content" refers to personalized learning materials and information generated based on user input and emotional information.

[1639] "Feedback" refers to evaluations and opinions regarding learning content and product information provided by users.

[1640] "Purchase history" is a record of products that a user has purchased in the past.

[1641] "Optimizing" means retraining the generative AI based on the collected data to improve its learning content model and the information it provides.

[1642] "Product information" refers to information about the characteristics, usage, reviews, etc. of products offered in the virtual store.

[1643] "Tutorials" are interactive guides or videos that explain the use or features of a product.

[1644] A "terminal" is a device that allows a user to input information and display customized content.

[1645] The present invention is a system for providing users with personalized product information and tutorials in a virtual store. This system utilizes a database that provides learning content, a generative AI model, and an emotion engine to generate and display optimal information based on the user's input information and emotion information. Specific embodiments of the system are described below.

[1646] Server Processing

[1647] 1. Registering content in the database

[1648] The server receives data such as product information, reviews, and tutorial videos provided by the virtual store and registers them in a database, including metadata such as product category, characteristics, and usage instructions.

[1649] 2. Building a learning content model

[1650] Using the stored data, generative AI is used to build learning content models that are trained to accommodate different shopping styles and product categories.

[1651] 3. Generating customized learning content

[1652] The server uses generative AI to generate customized learning content based on the user's input information (e.g., product category, characteristics, and usage) and the emotional information provided by the emotion engine, taking into account the user's past purchase history and emotional data.

[1653] 4. Feedback and optimization

[1654] Users browse product information and send their post-purchase feedback and sentiment data to the server. The server receives this data and stores it in a database. The AI ​​is retrained based on the feedback data and optimizes the learning content model.

[1655] Terminal handling

[1656] 1. Accepting user input

[1657] The terminal provides an interface for users to input the products and categories they are interested in. The emotion engine also analyzes the user's facial expressions and voice to obtain emotional information, and sends this data to the server.

[1658] 2. Viewing learning content

[1659] The terminal receives customized product information and tutorials sent from the server and displays them to the user, who can use this information to deepen their understanding of the product and consider purchasing it.

[1660] 3. Submitting feedback and ratings

[1661] The device provides an interface to collect feedback and ratings provided by users and send them to the server, where emotion information collected by the emotion engine is also sent.

[1662] User Action

[1663] 1. Enter your information

[1664] Users input the category and characteristics of the product they wish to purchase into the device. For example, they input information such as "electronic device," "smartphone," or "for beginners." During the learning process, the emotion engine automatically acquires emotional information by analyzing the user's facial expressions and voice.

[1665] 2. Use of learning content

[1666] By viewing customized product information and tutorials displayed on the device, users can learn about the product's features and how to use it. For example, a video explaining how to set up a smartphone is provided.

[1667] 3. Providing Feedback

[1668] After using the learning content, users enter feedback on their level of understanding and satisfaction through their devices and send it to the server. They also rate the products provided and send the results to the server. Emotional data from the learning process is also sent to the server via the emotion engine.

[1669] Specific examples

[1670] For example, suppose a user is considering purchasing the latest smartphone and wants to learn how to use it. In this case, the user enters "electronic device," "smartphone," and "for beginners" into the device, and the emotion engine acquires emotional information from facial expressions and voice. Based on this information, the server uses generative AI to generate a customized visual tutorial explaining how to set up the smartphone and sends it to the device. After the user watches this tutorial and deepens their understanding of the product, they send feedback via the device saying, "This tutorial video was very helpful." Emotional data generated by the emotion engine is also sent to the server.

[1671] Prompt Sentence Examples

[1672] "Welcome to SmartShop Tutor. If you want to learn how to use the latest smartphone, what information do you want? For example, 'How to set it up for beginners' or 'How to best use apps'?"

[1673] "We'll provide you with a customized smartphone tutorial based on your interests to help you make your purchase decision."

[1674] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1675] Step 1: Registering content in the database

[1676] The server receives product information (category, characteristics, usage, reviews, tutorial videos, etc.) provided by the virtual store and stores it in a database. At this time, product metadata is also registered. Specifically, the server obtains data from the product provider and stores it in the appropriate fields of the database. The input is product information data, and the output is the product information data stored in the database.

[1677] Step 2: Building a generative AI model

[1678] The server uses a generative AI to build a learning content model based on the product information data stored in the database. This model is trained to flexibly respond to the differences associated with each product. Specifically, the server retrieves data from the database, inputs it into the generative AI, and performs training. The input is the product information data retrieved from the database, and the output is the constructed learning content model.

[1679] Step 3: Accepting User Input

[1680] The terminal provides an interface for users to input information such as the category, characteristics, and usage of the product they are considering purchasing. It also uses an emotion engine to analyze the user's facial expressions and voice to obtain emotional information. Specifically, the terminal receives input information through the user interface and runs the emotion engine to analyze the voice and facial expression data. The input is the user's input information and emotional data, and the output is the user's input information and emotional data sent to the server.

[1681] Step 4: Generate customized learning content

[1682] The server uses generative AI to generate customized learning content based on the input information and emotional information sent by the user. This generation also takes into account the user's past purchase history and emotional data. Specifically, the server inputs the user's acquired data into a model to generate optimized learning content. The input is the user's input information and emotional data, and the output is customized learning content.

[1683] Step 5: View learning content

[1684] The terminal receives customized product information and tutorials sent from the server and displays them to the user. Specifically, the terminal receives data from the server and displays it on the display. The input is the learning content sent from the server, and the output is the customized learning content displayed on the terminal display.

[1685] Step 6: Submit your feedback and rating

[1686] The device collects feedback and evaluations provided by users and sends them to the server. It also sends emotional information acquired by the emotion engine to the server. Specifically, the device collects feedback data through the user interface and sends it together with emotional data. The input is the user's feedback data and emotional data, and the output is the feedback data and emotional data sent to the server.

[1687] Step 7: Feedback and optimization

[1688] The server stores the received feedback, emotional data, and purchase history in a database, and uses this information to retrain and optimize the generative AI model. Specifically, the server stores the collected data in a database and inputs it into the generative AI for retraining. The input is user feedback data, emotional data, and purchase history, and the output is an optimized learning content model.

[1689] 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.

[1690] 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.

[1691] 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.

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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).

[1696] 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.

[1697] 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."

[1698] 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.

[1699] 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).

[1700] 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.

[1701] 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.

[1702] 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.

[1703] 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.

[1704] 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.

[1705] 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.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] The following is further disclosed regarding the above embodiment.

[1711] (Claim 1)

[1712] a means for storing data in a database that provides learning content;

[1713] a means for constructing a generated learning content model based on the stored data;

[1714] means for generating customized learning content based on user input information;

[1715] a means for collecting user feedback and test results to optimize the learning content model;

[1716] A system including:

[1717] (Claim 2)

[1718] 2. The system of claim 1, wherein the user's input information includes a subject desired to be studied, a level of proficiency, and a learning style.

[1719] (Claim 3)

[1720] 10. The system of claim 1, further comprising means for displaying the generated customized learning content on the user's terminal.

[1721] "Example 1"

[1722] (Claim 1)

[1723] storage means for storing data;

[1724] a means for constructing a generated learning content model based on the stored data;

[1725] a means using a generative AI model to generate customized learning content based on user input;

[1726] a means for collecting user feedback and test results to optimize the learning content model;

[1727] A system including:

[1728] (Claim 2)

[1729] 2. The system of claim 1, wherein the user's input information includes a desired topic to learn, a skill level, and a learning style.

[1730] (Claim 3)

[1731] 10. The system of claim 1, further comprising means for displaying the generated customized learning content on the user's device.

[1732] "Application Example 1"

[1733] (Claim 1)

[1734] a means for storing data in a database that provides learning content;

[1735] a means for constructing a generated learning content model based on the stored data;

[1736] means for generating customized learning content based on user input information;

[1737] a means for collecting user feedback and test results to optimize the learning content model;

[1738] a means for generating learning content using a generative AI model;

[1739] a means for displaying the generated customized learning content on a smartphone or a head-mounted display;

[1740] A system including:

[1741] (Claim 2)

[1742] 2. The system of claim 1, wherein the user's input information includes a subject desired to be studied, a level of proficiency, and a learning style.

[1743] (Claim 3)

[1744] 10. The system of claim 1, further comprising means for displaying the generated customized learning content on the user's terminal.

[1745] "Example 2: Combining Emotion Engines"

[1746] (Claim 1)

[1747] a means for storing data in a database that provides digital data;

[1748] a means for creating a digital model built on the stored data;

[1749] means for generating customized digital content based on user input information and emotion data;

[1750] A means of collecting user feedback and test results to optimize the digital model; and

[1751] A system including:

[1752] (Claim 2)

[1753] 2. The system of claim 1, wherein the user's input information includes a subject desired to be studied, a level of proficiency, and a learning style.

[1754] (Claim 3)

[1755] 10. The system of claim 1, further comprising means for displaying the generated customized digital content and real-time adjustments based on the emotion data on the user's device.

[1756] "Application example 2 when combining emotion engines"

[1757] (Claim 1)

[1758] a means for storing data in a database that provides learning content;

[1759] a means for constructing a generated learning content model based on the stored data;

[1760] means for generating customized learning content based on user input information and emotional information;

[1761] a means for collecting user feedback, sentiment data, and purchase history to optimize the learning content model;

[1762] a means for displaying the generated customized product information and tutorials on a terminal;

[1763] A system including:

[1764] (Claim 2)

[1765] 10. The system of claim 1, wherein the user's input information includes the product's category, characteristics, and usage.

[1766] (Claim 3)

[1767] 10. The system according to claim 1, further comprising means for displaying the generated customized product information and tutorials on a user terminal. [Explanation of symbols]

[1768] 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 for storing data in a database that provides learning content; a means for constructing a generated learning content model based on the stored data; means for generating customized learning content based on user input information; a means for collecting user feedback and test results to optimize the learning content model; A system including:

2. 2. The system of claim 1, wherein the user's input information includes a subject desired to be studied, a level of proficiency, and a learning style.

3. 10. The system of claim 1, further comprising means for displaying the generated customized learning content on the user's terminal.

Images