System

Abstract

A system is provided.SOLUTION: A system comprising: means for aggregating lesson content provided by educators and storing the aggregated lesson content in a database; means for generating educational content optimized for individual users based on AI input to a generative data model; means for providing the generated educational content in response to access from terminals of the users; and means for analyzing content usage information of the users and providing reward points.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The modern educational environment faces several challenges. First, there is confusion due to the abundance of information and the lack of accuracy of that information. It is becoming increasingly difficult for users to find reliable information when using the internet or generative AI. Furthermore, there is also the problem of a decline in the quality of education due to a decrease in the number of people wanting to become teachers. As a result, students have fewer opportunities to receive a high-quality education, and the academic achievement gap is widening. To solve these problems, a system is needed to efficiently provide reliable educational content. [Means for solving the problem]

[0005] The present invention provides a means for aggregating lesson content provided by educators and storing it in a database. It then includes a means for generating educational content optimized for individual users based on the data input into a generative AI model. It also provides a system for providing the generated educational content in response to access from the user's device. The system also includes a means for analyzing the user's content usage data and awarding reward points, thereby increasing motivation to learn. This system efficiently provides high-quality, reliable educational content, thereby reducing academic ability gaps and improving the quality of education.

[0006] "Educators" are professionals who provide educational content, such as school teachers and university professors.

[0007] "Class content" refers to data such as educational videos, text, images, and web articles provided by educators.

[0008] A "database" is a system for organizing and storing collected lesson content and metadata.

[0009] A "generative AI model" is an artificial intelligence model that analyzes and optimizes input data to generate educational content.

[0010] "Users" refer to students and learners who study educational content through this system.

[0011] A "terminal" is an electronic device (such as a personal computer, smartphone, or tablet) that a user uses to access the system.

[0012] "Reward points" are incentives given to users each time they use content.

[0013] "Data analysis" is the process of collecting and analyzing user content usage data.

[0014] "Optimized educational content" refers to customized educational materials that are adjusted and created by a generative AI model based on the user's learning situation and needs. [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 aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Specific embodiments of the system are described below.

[0037] Overall system description

[0038] The system consists of three main components: a server, a device, and a user. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices and study the optimized educational content. Furthermore, the system analyzes users' educational content usage data and awards reward points.

[0039] Consolidation of educational content

[0040] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database. At the same time, the metadata of the lesson content (title, description, target age, subject, etc.) is also extracted and stored in the database.

[0041] Optimization with generative AI models

[0042] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This process takes into account data such as the user's age, learning history, and interests.

[0043] User Access and Learning

[0044] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0045] Usage data analysis and reward system

[0046] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device sequentially transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0047] Specific examples of effects

[0048] For example, if an elementary school student selects "Basics of Chemistry" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[0049] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by introducing a reward system based on frequency of use, it has the effect of increasing users' motivation to learn.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video on "Basics of Mathematics" to the server, the server receives the video.

[0053] Step 2:

[0054] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title of a lesson video, description, target grade, and subject information are stored in the database.

[0055] Step 3:

[0056] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[0057] Step 4:

[0058] The server inputs the lesson content from the database into the generative AI model. For example, a "Basics of Mathematics" video and its explanatory text are input into the generative AI model, and analysis begins.

[0059] Step 5:

[0060] The generative AI model analyzes the input content and generates educational content optimized for the user, such as problem-solving content to deepen an 8-year-old student's understanding of basic addition and subtraction.

[0061] Step 6:

[0062] Users access the system using a device (such as a PC, smartphone, or tablet) and select the subject or topic they wish to study. For example, a user may select that they want to learn "basic arithmetic."

[0063] Step 7:

[0064] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Basic Math for 8-Year-Olds" content from the database.

[0065] Step 8:

[0066] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[0067] Step 9:

[0068] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[0069] Step 10:

[0070] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[0071] Step 11:

[0072] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[0073] Through the above steps, this system provides educational content efficiently and with high quality, and increases users' motivation to learn.

[0074] Example 1

[0075] 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."

[0076] In traditional education systems, the same educational content is provided to all students, making it difficult to address individual needs. It is also difficult to accurately measure class progress and learning outcomes, and there is no reward system to maintain student motivation. Furthermore, educational content is not adequately optimized, limiting learning effectiveness.

[0077] 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.

[0078] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, a means for instructing the generative AI model to generate educational content based on prompt statements, and a means for continuously transmitting the user's learning progress. This makes it possible to provide educational content that meets individual needs, measure learning effectiveness, and increase motivation to learn through a reward system.

[0079] "Educators" refers to instructors and other teachers who provide lesson content.

[0080] "Class content" refers to educational materials such as videos, texts, images, and web articles provided by educators for use in classes.

[0081] "Database" refers to a storage device for storing and managing lesson content and its metadata.

[0082] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates educational content optimized for individual users.

[0083] "Users" refer to students and learners who use this system to study educational content.

[0084] "Terminal" refers to an electronic device such as a PC, smartphone, or tablet that a user uses to access the system.

[0085] "Reward points" refer to points awarded based on a user's learning progress and frequency of use.

[0086] "Prompt" refers to a text document used to specify instructions to a generative AI model.

[0087] "Learning progress" refers to data indicating how much a user has learned educational content.

[0088] This system aggregates various lesson contents provided by educators and provides educational contents optimized for individual users. This system consists of three main components: a server, a terminal, and a user.

[0089] Server Operation

[0090] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. At the same time, it also extracts and stores the lesson content's metadata (title, description, target age group, subject, etc.). For example, if a teacher uploads a lesson video titled "Basic Math," the video is stored in AWS S3 storage, and the metadata is recorded in a PostgreSQL database.

[0091] The server then inputs the educational content from the database into a generative AI model (OpenAI's GPT model). The generative AI model generates educational content optimized for each individual user based on the input data. This process takes into account data such as the user's age, learning history, and interests. For example, an 8-year-old student would receive interactive problem-solving content to deepen their understanding of basic addition and subtraction.

[0092] Device behavior

[0093] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0094] User Behavior and Learning

[0095] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0096] Specific examples

[0097] For example, if an elementary school student selects to learn "Basic Mathematics" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[0098] Prompt Sentence Examples

[0099] For example, a prompt for a generative AI model might look like this:

[0100] "My 8-year-old elementary school student wants to learn addition and subtraction in math. I'd like you to create educational content that explains the basic concepts."

[0101] This system allows educators to efficiently provide high-quality lesson content, and users to progress with their studies through individually optimized educational content. In addition, a reward system based on frequency of use can increase users' motivation to learn.

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

[0103] Step 1:

[0104] The server receives lesson content (videos, text, images, web articles) from educators. Specifically, the files provided by educators are uploaded to the server. The input is the educator's content, and the output is a content file stored in AWS S3 storage.

[0105] Step 2:

[0106] The server extracts the metadata (title, description, target age, subject, etc.) of the uploaded lesson content and stores it in a database. Specifically, it saves the extracted metadata in a PostgreSQL database. The input at this time is the lesson content file itself, and the output is the metadata stored in the database.

[0107] Step 3:

[0108] The server inputs the educational content stored in the database into the generative AI model. Specifically, it inputs the content along with the user's age, learning history, and interest data into the generative AI model (OpenAI's GPT model). In this process, the input is the educational content in the database and the user profile, and the output is optimized educational content.

[0109] Step 4:

[0110] Users access the system using their own devices and select the topic or subject they want to learn. Specifically, when a user selects "Basic Math," the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. In this process, the input is the user's selection, and the output is the optimized content displayed on the user's device.

[0111] Step 5:

[0112] The device transmits the user's learning progress and usage data (such as browsing time and answer results) to the server in real time. Specifically, all user actions during learning are recorded and transmitted sequentially to the server. In this process, the input is the user's learning activity, and the output is the usage data transmitted to the server.

[0113] Step 6:

[0114] The server analyzes the acquired usage data and awards reward points to the user. Specifically, based on the analysis results, points are calculated and added to the user's account. In this process, the input is usage data, and the output is the awarded reward points and a notification.

[0115] (Application example 1)

[0116] 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."

[0117] While individualized instruction is important in the education field, its realization requires time and resources. There is also a need for a method to efficiently provide educational content in brick-and-mortar stores and increase learning motivation. Furthermore, there is no method to provide optimal content in real time using user location information, making it difficult to provide an educational experience tailored to each individual user.

[0118] 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.

[0119] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for detecting the user's location in a physical store in real time and providing the optimal educational content based on the detected location. This makes it possible to provide educational content tailored to each user in real time even in a physical store, thereby improving learning effectiveness and motivation.

[0120] "Educational content" refers to information and materials such as videos, text, images, and web articles intended for user learning purposes.

[0121] A "generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for each individual user.

[0122] "Server" refers to a central control device that aggregates lesson content provided by educators, stores it in a database, optimizes the educational content using a generative AI model, and provides it to users.

[0123] "Terminal" means a device that a user uses to access the server and view and use the provided educational content, including smartphones, tablets, and PCs.

[0124] "Metadata" refers to additional information about lesson content, such as title, description, target age, and subject.

[0125] "Reward points" are points that are awarded based on the user's content usage data, and function as an incentive to increase the user's motivation to learn.

[0126] "Real-time location detection" refers to technology that detects the user's location within a physical store in real time.

[0127] "Database" refers to a data structure for efficiently storing and managing lesson content, user information, usage data, etc.

[0128] "Usage data" refers to behavioral data when a user uses educational content, and includes viewing time, answer results, progress, and the like.

[0129] This invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual users based on that content. Specifically, it consists of three main components: a server, a terminal, and a user.

[0130] Server-based aggregation of educational content

[0131] The server receives lesson content sent by educators and stores it in a database. Lesson content includes videos, text, images, web articles, etc. For example, if an educator uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database and also extracts and saves related metadata (title, description, target age group, subject, etc.).

[0132] Content optimization with generative AI models

[0133] The server inputs educational content from the database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This analysis takes into account data such as the user's age, learning history, and interests.

[0134] User Access and Learning

[0135] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0136] Usage data analysis and reward system

[0137] The user's device transmits learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0138] Real-time location detection and content provision in physical stores

[0139] This system also allows users to access educational content within a physical store. The system detects the user's location within the store in real time and provides the most appropriate educational content based on that location. For example, if a user is in the "science" section of a bookstore, science-related educational content will be provided.

[0140] Examples and prompts

[0141] For example, if a 10-year-old user walks into a bookstore and stops in the "Science" section, the app might:

[0142] 1. Determine from location information that the user is in the "science" section of a bookstore.

[0143] 2. The server sends the following prompt to OpenAI GPT-3:

[0144] My 10-year-old child is interested in science. Please provide educational content that is most suitable for this child.

[0145] 3. Providing generated content to smartphones and smart glasses in real time.

[0146] 4. After the user has finished studying the content, reward points will be added to their account.

[0147] The present invention makes it possible to provide educational content suited to individual users in real time, even in a physical store, thereby improving learning effectiveness and motivation.

[0148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0149] Step 1:

[0150] Consolidation of educational content

[0151] The server receives lesson content (videos, text, images, web articles, etc.) from educators and stores it in a database.

[0152] Input: Lesson content provided by educators.

[0153] Data processing: Content data and metadata (title, description, target age, subject, etc.) are extracted and stored.

[0154] Output: Lesson content stored in a database.

[0155] Step 2:

[0156] Content optimization with generative AI models

[0157] The server inputs educational content from the database into the generative AI model.

[0158] Input: Educational content stored in a database.

[0159] Data calculation: A generative AI model analyzes input content and generates educational content optimized for each individual user.

[0160] Output: Generated optimized educational content.

[0161] Step 3:

[0162] Access and content provision via user terminals

[0163] Users access the system from their own devices and select the topic or subject they want to learn. The server retrieves the generated educational content as a query and sends it to the user's device.

[0164] Input: A request from the user's device to select a topic or subject.

[0165] Data processing: Retrieving optimized educational content from the database.

[0166] Output: The educational content sent to the user's device.

[0167] Step 4:

[0168] Real-time location detection and in-store content delivery

[0169] The device detects the user's location in the physical store in real time, and based on the detected location, sends a request to the server to provide the most appropriate educational content.

[0170] Input: Real-time location information from the user's device.

[0171] Data calculation: Determines relevant educational content based on location information and sends a request to the server.

[0172] Output: The optimal educational content is displayed on the user's device.

[0173] Step 5:

[0174] Analysis of usage data and awarding of reward points

[0175] The device transmits the user's learning progress and usage data to the server in real time, which analyzes the data and awards reward points to the user.

[0176] Input: User's learning progress and usage data (viewing time, answer results, etc.).

[0177] Data calculation: Analyze usage data and calculate reward points.

[0178] Output: The calculated reward points are recorded in the user account and notified.

[0179] 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.

[0180] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content, and also combines it with an emotion engine to dynamically generate and provide more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[0181] Overall system description

[0182] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices to study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[0183] Consolidation of educational content

[0184] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[0185] Optimization with generative AI models

[0186] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[0187] Emotion Engine Functions

[0188] The emotion engine analyzes emotion data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, the camera analyzes the user's facial expressions and voice tone using voice recognition. The analyzed emotion data is sent to the server.

[0189] User Access and Learning

[0190] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[0191] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[0192] Real-time adjustments based on emotion data

[0193] The server adjusts the difficulty and format of educational content in real time based on the emotional data sent by the emotion engine. For example, if the server detects emotions like "boredom" or "confusion" while a user is watching a video, it will immediately issue instructions to simplify the video content or add interactive elements.

[0194] Usage data analysis and reward system

[0195] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device transmits the user's progress status sequentially to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award result and the points are recorded in the user's account.

[0196] Specific examples of effects

[0197] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[0198] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by combining a reward system based on frequency of use with an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[0199] The processing flow will be explained below.

[0200] Step 1:

[0201] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video about "Science Fundamentals" to the server, the server receives the video.

[0202] Step 2:

[0203] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title, description, target grade, and subject information of a lesson video can be saved in the database to make it easier to search.

[0204] Step 3:

[0205] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[0206] Step 4:

[0207] The server inputs the lesson content from the database into the generative AI model. For example, a "Science Fundamentals" video and its explanatory text are input into the generative AI model and analysis begins.

[0208] Step 5:

[0209] The generative AI model analyzes the input content and generates educational content optimized for the user, such as interactive problem-solving content to help an 8-year-old student understand basic science concepts, taking into account data such as the user's age, learning history, and interests.

[0210] Step 6:

[0211] The emotion engine uses the camera and microphone on the user's device to collect the user's facial expressions and voice in real time. For example, while the user is watching a video, the camera captures the user's facial expressions and the microphone analyzes the tone of the user's voice.

[0212] Step 7:

[0213] The emotion engine analyzes the collected data and determines the user's emotional state (happiness, confusion, interest, boredom, etc.) in real time. For example, if a user shows a confused expression while watching a video, that emotion will be recognized.

[0214] Step 8:

[0215] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[0216] Step 9:

[0217] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[0218] Step 10:

[0219] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[0220] Step 11:

[0221] The server adjusts the difficulty and format of educational content in real time based on the emotion data sent by the emotion engine. For example, if the server detects the emotion of "confusion" while a user is watching a video, it will simplify the video content or provide additional explanations.

[0222] Step 12:

[0223] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[0224] Step 13:

[0225] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[0226] Step 14:

[0227] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[0228] This system can efficiently provide high-quality and reliable educational content, increasing users' motivation to learn. In addition, by using an emotion engine, it is possible to provide educational content that is more suited to user needs.

[0229] Example 2

[0230] 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."

[0231] In conventional educational systems, educational content is provided uniformly, making it difficult to provide an optimal learning experience for each individual user. Furthermore, there is a lack of mechanisms to maintain and improve motivation for learning, and the lack of dynamic content adjustment based on the user's progress and emotions is also an issue.

[0232] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, and a means for providing the generated educational content in response to access from the user's terminal. This makes it possible to provide educational content optimized for each user and maintain and improve their motivation to learn.

[0233] "Educators" refers to those responsible for providing educational content and experts.

[0234] "Class content" refers to educational materials provided by educators, including information assets such as videos, text, images, and web articles.

[0235] "Database" refers to a digital storage system for efficiently storing and managing aggregated course content and metadata.

[0236] "Generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for individual users.

[0237] "User" refers to an individual who uses this system to study educational content.

[0238] "Terminal" means a device used by a user to access the system, including a PC, smartphone, tablet, etc.

[0239] "Emotional data" refers to information about a user's emotional state that is analyzed from the user's facial expressions, voice, character input, and the like.

[0240] "Reward points" refer to incentives awarded based on a user's learning progress and usage data.

[0241] "Analysis" refers to the process of processing data and extracting meaningful information and patterns.

[0242] "Real time" refers to a timing range in which events that occur are processed nearly simultaneously.

[0243] MODE FOR CARRYING OUT THE INVENTION

[0244] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Furthermore, by combining an emotion engine, the system dynamically generates and provides more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[0245] Overall system overview

[0246] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users access the system using their devices and study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[0247] Consolidation of educational content

[0248] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[0249] Optimization with generative AI models

[0250] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it generates interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[0251] Emotion Engine Functions

[0252] The emotion engine analyzes emotional data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, a camera can analyze their facial expressions, and speech recognition can analyze their tone of voice. The analyzed emotional data is sent to a server, which then uses this data to adjust the difficulty and format of the educational content in real time. For example, if the server detects emotions like "boredom" or "confusion" while the user is watching a video, it can immediately issue instructions to simplify the video content or add interactive elements.

[0253] User Access and Learning

[0254] Users access the system using their own devices (PCs, smartphones, tablets, etc.) and select the subjects or topics they want to learn. For example, if a user selects to learn "Science Fundamentals" on a tablet, the device sends the request to the server, and the server generates and distributes the most appropriate educational content to the device.

[0255] Usage data analysis and reward system

[0256] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is viewing a basic science video and solving problems, the device transmits the user's progress in real time to the server. The server analyzes the acquired data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0257] Specific examples of effects

[0258] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[0259] Prompt Sentence Examples

[0260] "An 8-year-old wants to learn the basics of science, so generate interactive educational content accordingly. Also, adjust the content in real time based on the user's emotional data as they learn."

[0261] As described above, this invention is a system that efficiently provides high-quality, reliable educational content and enables users to learn optimally. Furthermore, by combining a reward system and an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[0262] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0263] Step 1: Collect and store educational content

[0264] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. For example, when an educator uploads a lesson video on "Basics of Chemistry," the server receives the video. At the same time, the server also extracts and stores metadata such as the title, description, target age group, and subject. The input data is the lesson content and metadata, and the output data is the content and metadata stored in the database.

[0265] Step 2: Collect user data

[0266] While the user is using the system, the device collects data such as learning history, grades, and interests, and sends it to the server. For example, a user watches a lecture on "Science Fundamentals" and answers related questions. This causes the device to record the learning history and answers. The input data is the user's learning behavior, and the output data is the user data sent to the server.

[0267] Step 3: Generate and deliver educational content

[0268] The server inputs the educational content and user data from the database into a generative AI model to generate prompts. The generative AI model generates appropriate educational content based on the user's age, learning history, and interests. For example, an 8-year-old user would be provided with interactive problem-solving content on basic science. The server outputs the generated prompts and delivers them to the user's device upon request. The input data are educational content and user data, and the output data is optimized educational content.

[0269] Step 4: User interaction and data submission

[0270] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they want to learn. For example, a user may select "Science Fundamentals" using a tablet. The device sends the selection to the server, which then generates corresponding educational content and provides it to the device. The input data is the user's selection, and the output data is the corresponding educational content.

[0271] Step 5: Analyze emotional data and adjust educational content

[0272] The emotion engine analyzes the user's facial expressions, voice, and text input in real time to extract the user's emotional data. For example, while the user is watching a video, the camera analyzes the user's facial expressions and the voice recognition system extracts the tone of the user's voice. This emotional data is sent to the server, which then adjusts the difficulty and format of the educational content based on this data. The input data is the user's emotional data, and the output data is the adjusted educational content.

[0273] Step 6: Analyze usage data and award reward points

[0274] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is watching a basic science video and answering questions, their progress is transmitted to the server in real time. The server aggregates and analyzes this data, and calculates and awards reward points to the user. The input data is the user's usage data, and the output data is the awarded reward points and a notification of the points.

[0275] (Application example 2)

[0276] 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."

[0277] Conventional educational content delivery systems provide fixed content without considering the user's individual emotional state, making it difficult to provide appropriate learning support based on the user's interests and level of understanding. Furthermore, optimization based solely on content usage data is unable to respond in real time, limiting the user experience. Furthermore, when applying education to customer support in brick-and-mortar stores, it is difficult to make optimal product recommendations based on customer emotion analysis.

[0278] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0279] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for individual users based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for analyzing emotional data from the user's facial expressions and voice and adjusting the content in real time based on the analysis results. This enables real-time optimization of educational content according to the user's emotional state and improved customer support in physical stores.

[0280] "Educational content" refers to information about lesson content provided by educators, and includes formats such as videos, text, images, and web articles.

[0281] A "generative AI model" is an artificial intelligence model that uses aggregated educational content and user attribute information as input to generate educational content optimized for individual users.

[0282] "Emotion data" refers to data relating to the emotional state of the user that is acquired in real time from facial expressions, voice, and the like.

[0283] "User's device" refers to an electronic device used by a user to access the system and use educational content, including a PC, smartphone, tablet, etc.

[0284] "Usage data" refers to various data collected when a user uses educational content, including viewing time, answer results, learning progress, and the like.

[0285] "Reward points" are incentive points that are awarded based on the user's use of educational content and results.

[0286] "Real-time adjustment" refers to the process of instantly changing and adapting the content and difficulty of educational content provided based on the user's emotional data.

[0287] "Database" means an information system for efficiently storing and managing aggregated educational content and associated metadata.

[0288] "Facial expressions" are non-verbal cues that indicate a user's emotional state based on their facial movements and expressions.

[0289] "Voice" refers to data for analyzing the emotional state of a user from vocal characteristics such as tone and intonation.

[0290] MODE FOR CARRYING OUT THE INVENTION

[0291] The present invention provides a system for providing educational content and enhancing the learning effect of users. The configuration and operation of this system will be described below.

[0292] System configuration

[0293] 1. Server

[0294] Database: Stores lesson content (videos, text, images, web articles, etc.) provided by educators. Metadata is also stored.

[0295] Generative AI models: Generate optimized educational content based on input educational content and user attribute information. This includes natural language processing models such as BERT and recommendation systems.

[0296] Emotion engine: Analyzes emotion data from the user's facial expressions and voice in real time. Technologies used include OpenCV and Dlib.

[0297] 2. Terminal

[0298] A device (smartphone, smart glasses, tablet, PC, etc.) that allows a user to access the system. It is desirable that it is equipped with a camera and microphone.

[0299] Optimized educational content is provided by accessing the server from the terminal.

[0300] 3. Users

[0301] Students access the system and use the educational content provided, and their learning progress and emotional data are collected in real time.

[0302] How it works

[0303] Consolidation of educational content

[0304] The server aggregates lesson content provided by educators and stores it in a database. It also extracts and stores metadata about the content (title, description, target age group, subject, etc.).

[0305] Content Optimization

[0306] The server inputs the educational content stored in the database into a generative AI model to generate educational content optimized for each individual user, taking into account the user's age, learning history, interests, and emotional data.

[0307] Emotion data analysis and real-time adjustment

[0308] The server uses an emotion engine to analyze emotion data from the user's facial expressions and voice. For example, it uses OpenCV and Dlib to analyze the user's facial expressions and voice tone using speech recognition technology. Based on this, the difficulty level and format of the educational content can be adjusted in real time.

[0309] Usage data collection and reward system

[0310] The device sends the user's learning progress and usage data to the server. The server analyzes the collected data and awards reward points to the user. The results of the awarding of reward points are notified to the user and recorded in the user's account.

[0311] Specific examples

[0312] For example, if an elementary school student is learning "Science Fundamentals" on a tablet, the optimal content generated by the generative AI model will be displayed on the device. While the user is using the content, the camera analyzes their facial expressions and the microphone analyzes their voice to collect emotional data. If the emotion engine detects "confusion," the system immediately issues instructions to provide more detailed explanations of the educational content, resulting in content that is easier for the user to understand.

[0313] An example of a prompt might be:

[0314] While the user is wearing the smart glasses, explain the features of the product in front of them, analyze the customer's facial expressions and voice to see if they are interested, and determine if further explanation is needed, providing additional information in real time if necessary.

[0315] This invention is expected to highly optimize the user's learning experience and improve customer support in physical stores.

[0316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0317] Step 1:

[0318] The server receives lesson content provided by educators and stores the content and metadata in a database. The input is the lesson content (videos, text, images, web articles) provided by educators, and the output is the content and metadata stored in the database. Data processing involves unifying the content format and extracting metadata (title, description, target age group, subject, etc.).

[0319] Step 2:

[0320] The server inputs educational content stored in the database into a generative AI model to generate educational content optimized for each individual user. The input is the educational content in the database and the user's attribute data (age, learning history, interests), and the output is optimized educational content. As a data calculation, the AI ​​model analyzes multiple attribute data and generates and optimizes educational content based on that data.

[0321] Step 3:

[0322] Users access the system using a terminal and select the subjects or topics they wish to study. The input is the user's selection information (subjects or topics), and the output is a request for optimized content based on the selected information. Specifically, users select subjects using a tablet or smartphone.

[0323] Step 4:

[0324] The emotion engine analyzes camera footage and audio data provided by the user's device to obtain emotional data in real time. The input is the user's facial expression and audio data, and the output is emotional data obtained in real time. Data processing involves facial recognition using OpenCV, facial expression analysis using Dlib, and voice recognition technology to analyze voice tone.

[0325] Step 5:

[0326] The server adjusts the difficulty and format of the optimized educational content in real time based on the emotional data. The input is the emotional data from the emotion engine, and the output is the adjusted educational content. As a data calculation, the emotional data is evaluated and, if necessary, re-input into the generative AI model to regenerate the content.

[0327] Step 6:

[0328] The device collects the user's learning progress and usage data and sends it to the server. The input is the user's learning usage data (viewing time, answer results, progress), and the output is the usage data sent to the server. Specifically, the device has a mechanism to periodically upload data to the server.

[0329] Step 7:

[0330] The server analyzes the user's usage data and awards reward points. The input is the collected usage data, and the output is the reward point award result. As a data calculation, the usage data is evaluated and reward points are calculated based on the pre-set conditions. The calculated points are recorded in the user's account and notified.

[0331] The above are the specific processing steps of this invention. By configuring the system in this way, it becomes possible to optimize educational content in real time according to the user's emotional state and improve customer support in physical stores.

[0332] 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.

[0333] 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.

[0334] 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.

[0335] [Second embodiment]

[0336] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0337] 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.

[0338] 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).

[0339] 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.

[0340] 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.

[0341] 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).

[0342] 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.

[0343] 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.

[0344] 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.

[0345] 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.

[0346] 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.

[0347] 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."

[0348] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Specific embodiments of the system are described below.

[0349] Overall system description

[0350] The system consists of three main components: a server, a device, and a user. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices and study the optimized educational content. Furthermore, the system analyzes users' educational content usage data and awards reward points.

[0351] Consolidation of educational content

[0352] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database. At the same time, the metadata of the lesson content (title, description, target age, subject, etc.) is also extracted and stored in the database.

[0353] Optimization with generative AI models

[0354] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This process takes into account data such as the user's age, learning history, and interests.

[0355] User Access and Learning

[0356] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0357] Usage data analysis and reward system

[0358] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device sequentially transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0359] Specific examples of effects

[0360] For example, if an elementary school student selects "Basics of Chemistry" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[0361] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by introducing a reward system based on frequency of use, it has the effect of increasing users' motivation to learn.

[0362] The processing flow will be explained below.

[0363] Step 1:

[0364] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video on "Basics of Mathematics" to the server, the server receives the video.

[0365] Step 2:

[0366] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title of a lesson video, description, target grade, and subject information are stored in the database.

[0367] Step 3:

[0368] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[0369] Step 4:

[0370] The server inputs the lesson content from the database into the generative AI model. For example, a "Basics of Mathematics" video and its explanatory text are input into the generative AI model, and analysis begins.

[0371] Step 5:

[0372] The generative AI model analyzes the input content and generates educational content optimized for the user, such as problem-solving content to deepen an 8-year-old student's understanding of basic addition and subtraction.

[0373] Step 6:

[0374] Users access the system using a device (such as a PC, smartphone, or tablet) and select the subject or topic they wish to study. For example, a user may select that they want to learn "basic arithmetic."

[0375] Step 7:

[0376] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Basic Math for 8-Year-Olds" content from the database.

[0377] Step 8:

[0378] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[0379] Step 9:

[0380] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[0381] Step 10:

[0382] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[0383] Step 11:

[0384] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[0385] Through the above steps, this system provides educational content efficiently and with high quality, and increases users' motivation to learn.

[0386] Example 1

[0387] 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."

[0388] In traditional education systems, the same educational content is provided to all students, making it difficult to address individual needs. It is also difficult to accurately measure class progress and learning outcomes, and there is no reward system to maintain student motivation. Furthermore, educational content is not adequately optimized, limiting learning effectiveness.

[0389] 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.

[0390] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, a means for instructing the generative AI model to generate educational content based on prompt statements, and a means for continuously transmitting the user's learning progress. This makes it possible to provide educational content that meets individual needs, measure learning effectiveness, and increase motivation to learn through a reward system.

[0391] "Educators" refers to instructors and other teachers who provide lesson content.

[0392] "Class content" refers to educational materials such as videos, texts, images, and web articles provided by educators for use in classes.

[0393] "Database" refers to a storage device for storing and managing lesson content and its metadata.

[0394] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates educational content optimized for individual users.

[0395] "Users" refer to students and learners who use this system to study educational content.

[0396] "Terminal" refers to an electronic device such as a PC, smartphone, or tablet that a user uses to access the system.

[0397] "Reward points" refer to points awarded based on a user's learning progress and frequency of use.

[0398] "Prompt" refers to a text document used to specify instructions to a generative AI model.

[0399] "Learning progress" refers to data indicating how much a user has learned educational content.

[0400] This system aggregates various lesson contents provided by educators and provides educational contents optimized for individual users. This system consists of three main components: a server, a terminal, and a user.

[0401] Server Operation

[0402] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. At the same time, it also extracts and stores the lesson content's metadata (title, description, target age group, subject, etc.). For example, if a teacher uploads a lesson video titled "Basic Math," the video is stored in AWS S3 storage, and the metadata is recorded in a PostgreSQL database.

[0403] The server then inputs the educational content from the database into a generative AI model (OpenAI's GPT model). The generative AI model generates educational content optimized for each individual user based on the input data. This process takes into account data such as the user's age, learning history, and interests. For example, an 8-year-old student would receive interactive problem-solving content to deepen their understanding of basic addition and subtraction.

[0404] Device behavior

[0405] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0406] User Behavior and Learning

[0407] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0408] Specific examples

[0409] For example, if an elementary school student selects to learn "Basic Mathematics" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[0410] Prompt Sentence Examples

[0411] For example, a prompt for a generative AI model might look like this:

[0412] "My 8-year-old elementary school student wants to learn addition and subtraction in math. I'd like you to create educational content that explains the basic concepts."

[0413] This system allows educators to efficiently provide high-quality lesson content, and users to progress with their studies through individually optimized educational content. In addition, a reward system based on frequency of use can increase users' motivation to learn.

[0414] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0415] Step 1:

[0416] The server receives lesson content (videos, text, images, web articles) from educators. Specifically, the files provided by educators are uploaded to the server. The input is the educator's content, and the output is a content file stored in AWS S3 storage.

[0417] Step 2:

[0418] The server extracts the metadata (title, description, target age, subject, etc.) of the uploaded lesson content and stores it in a database. Specifically, it saves the extracted metadata in a PostgreSQL database. The input at this time is the lesson content file itself, and the output is the metadata stored in the database.

[0419] Step 3:

[0420] The server inputs the educational content stored in the database into the generative AI model. Specifically, it inputs the content along with the user's age, learning history, and interest data into the generative AI model (OpenAI's GPT model). In this process, the input is the educational content in the database and the user profile, and the output is optimized educational content.

[0421] Step 4:

[0422] Users access the system using their own devices and select the topic or subject they want to learn. Specifically, when a user selects "Basic Math," the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. In this process, the input is the user's selection, and the output is the optimized content displayed on the user's device.

[0423] Step 5:

[0424] The device transmits the user's learning progress and usage data (such as browsing time and answer results) to the server in real time. Specifically, all user actions during learning are recorded and transmitted sequentially to the server. In this process, the input is the user's learning activity, and the output is the usage data transmitted to the server.

[0425] Step 6:

[0426] The server analyzes the acquired usage data and awards reward points to the user. Specifically, based on the analysis results, points are calculated and added to the user's account. In this process, the input is usage data, and the output is the awarded reward points and a notification.

[0427] (Application example 1)

[0428] 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."

[0429] While individualized instruction is important in the education field, its realization requires time and resources. There is also a need for a method to efficiently provide educational content in brick-and-mortar stores and increase learning motivation. Furthermore, there is no method to provide optimal content in real time using user location information, making it difficult to provide an educational experience tailored to each individual user.

[0430] 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.

[0431] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for detecting the user's location in a physical store in real time and providing the optimal educational content based on the detected location. This makes it possible to provide educational content tailored to each user in real time even in a physical store, thereby improving learning effectiveness and motivation.

[0432] "Educational content" refers to information and materials such as videos, text, images, and web articles intended for user learning purposes.

[0433] A "generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for each individual user.

[0434] "Server" refers to a central control device that aggregates lesson content provided by educators, stores it in a database, optimizes the educational content using a generative AI model, and provides it to users.

[0435] "Terminal" means a device that a user uses to access the server and view and use the provided educational content, including smartphones, tablets, and PCs.

[0436] "Metadata" refers to additional information about lesson content, such as title, description, target age, and subject.

[0437] "Reward points" are points that are awarded based on the user's content usage data, and function as an incentive to increase the user's motivation to learn.

[0438] "Real-time location detection" refers to technology that detects the user's location within a physical store in real time.

[0439] "Database" refers to a data structure for efficiently storing and managing lesson content, user information, usage data, etc.

[0440] "Usage data" refers to behavioral data when a user uses educational content, and includes viewing time, answer results, progress, and the like.

[0441] This invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual users based on that content. Specifically, it consists of three main components: a server, a terminal, and a user.

[0442] Server-based aggregation of educational content

[0443] The server receives lesson content sent by educators and stores it in a database. Lesson content includes videos, text, images, web articles, etc. For example, if an educator uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database and also extracts and saves related metadata (title, description, target age group, subject, etc.).

[0444] Content optimization with generative AI models

[0445] The server inputs educational content from the database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This analysis takes into account data such as the user's age, learning history, and interests.

[0446] User Access and Learning

[0447] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0448] Usage data analysis and reward system

[0449] The user's device transmits learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0450] Real-time location detection and content provision in physical stores

[0451] This system also allows users to access educational content within a physical store. The system detects the user's location within the store in real time and provides the most appropriate educational content based on that location. For example, if a user is in the "science" section of a bookstore, science-related educational content will be provided.

[0452] Examples and prompts

[0453] For example, if a 10-year-old user walks into a bookstore and stops in the "Science" section, the app might:

[0454] 1. Determine from location information that the user is in the "science" section of a bookstore.

[0455] 2. The server sends the following prompt to OpenAI GPT-3:

[0456] My 10-year-old child is interested in science. Please provide educational content that is most suitable for this child.

[0457] 3. Providing generated content to smartphones and smart glasses in real time.

[0458] 4. After the user has finished studying the content, reward points will be added to their account.

[0459] The present invention makes it possible to provide educational content suited to individual users in real time, even in a physical store, thereby improving learning effectiveness and motivation.

[0460] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0461] Step 1:

[0462] Consolidation of educational content

[0463] The server receives lesson content (videos, text, images, web articles, etc.) from educators and stores it in a database.

[0464] Input: Lesson content provided by educators.

[0465] Data processing: Content data and metadata (title, description, target age, subject, etc.) are extracted and stored.

[0466] Output: Lesson content stored in a database.

[0467] Step 2:

[0468] Content optimization with generative AI models

[0469] The server inputs educational content from the database into the generative AI model.

[0470] Input: Educational content stored in a database.

[0471] Data calculation: A generative AI model analyzes input content and generates educational content optimized for each individual user.

[0472] Output: Generated optimized educational content.

[0473] Step 3:

[0474] Access and content provision via user terminals

[0475] Users access the system from their own devices and select the topic or subject they want to learn. The server retrieves the generated educational content as a query and sends it to the user's device.

[0476] Input: A request from the user's device to select a topic or subject.

[0477] Data processing: Retrieving optimized educational content from the database.

[0478] Output: The educational content sent to the user's device.

[0479] Step 4:

[0480] Real-time location detection and in-store content delivery

[0481] The device detects the user's location in the physical store in real time, and based on the detected location, sends a request to the server to provide the most appropriate educational content.

[0482] Input: Real-time location information from the user's device.

[0483] Data calculation: Determines relevant educational content based on location information and sends a request to the server.

[0484] Output: The optimal educational content is displayed on the user's device.

[0485] Step 5:

[0486] Analysis of usage data and awarding of reward points

[0487] The device transmits the user's learning progress and usage data to the server in real time, which analyzes the data and awards reward points to the user.

[0488] Input: User's learning progress and usage data (viewing time, answer results, etc.).

[0489] Data calculation: Analyze usage data and calculate reward points.

[0490] Output: The calculated reward points are recorded in the user account and notified.

[0491] 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.

[0492] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content, and also combines it with an emotion engine to dynamically generate and provide more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[0493] Overall system description

[0494] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices to study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[0495] Consolidation of educational content

[0496] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[0497] Optimization with generative AI models

[0498] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[0499] Emotion Engine Functions

[0500] The emotion engine analyzes emotion data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, the camera analyzes the user's facial expressions and voice tone using voice recognition. The analyzed emotion data is sent to the server.

[0501] User Access and Learning

[0502] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[0503] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[0504] Real-time adjustments based on emotion data

[0505] The server adjusts the difficulty and format of educational content in real time based on the emotional data sent by the emotion engine. For example, if the server detects emotions like "boredom" or "confusion" while a user is watching a video, it will immediately issue instructions to simplify the video content or add interactive elements.

[0506] Usage data analysis and reward system

[0507] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device transmits the user's progress status sequentially to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award result and the points are recorded in the user's account.

[0508] Specific examples of effects

[0509] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[0510] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by combining a reward system based on frequency of use with an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[0511] The processing flow will be explained below.

[0512] Step 1:

[0513] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video about "Science Fundamentals" to the server, the server receives the video.

[0514] Step 2:

[0515] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title, description, target grade, and subject information of a lesson video can be saved in the database to make it easier to search.

[0516] Step 3:

[0517] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[0518] Step 4:

[0519] The server inputs the lesson content from the database into the generative AI model. For example, a "Science Fundamentals" video and its explanatory text are input into the generative AI model and analysis begins.

[0520] Step 5:

[0521] The generative AI model analyzes the input content and generates educational content optimized for the user, such as interactive problem-solving content to help an 8-year-old student understand basic science concepts, taking into account data such as the user's age, learning history, and interests.

[0522] Step 6:

[0523] The emotion engine uses the camera and microphone on the user's device to collect the user's facial expressions and voice in real time. For example, while the user is watching a video, the camera captures the user's facial expressions and the microphone analyzes the tone of the user's voice.

[0524] Step 7:

[0525] The emotion engine analyzes the collected data and determines the user's emotional state (happiness, confusion, interest, boredom, etc.) in real time. For example, if a user shows a confused expression while watching a video, that emotion will be recognized.

[0526] Step 8:

[0527] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[0528] Step 9:

[0529] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[0530] Step 10:

[0531] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[0532] Step 11:

[0533] The server adjusts the difficulty and format of educational content in real time based on the emotion data sent by the emotion engine. For example, if the server detects the emotion of "confusion" while a user is watching a video, it will simplify the video content or provide additional explanations.

[0534] Step 12:

[0535] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[0536] Step 13:

[0537] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[0538] Step 14:

[0539] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[0540] This system can efficiently provide high-quality and reliable educational content, increasing users' motivation to learn. In addition, by using an emotion engine, it is possible to provide educational content that is more suited to user needs.

[0541] Example 2

[0542] 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."

[0543] In conventional educational systems, educational content is provided uniformly, making it difficult to provide an optimal learning experience for each individual user. Furthermore, there is a lack of mechanisms to maintain and improve motivation for learning, and the lack of dynamic content adjustment based on the user's progress and emotions is also an issue.

[0544] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, and a means for providing the generated educational content in response to access from the user's terminal. This makes it possible to provide educational content optimized for each user and maintain and improve their motivation to learn.

[0545] "Educators" refers to those responsible for providing educational content and experts.

[0546] "Class content" refers to educational materials provided by educators, including information assets such as videos, text, images, and web articles.

[0547] "Database" refers to a digital storage system for efficiently storing and managing aggregated course content and metadata.

[0548] "Generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for individual users.

[0549] "User" refers to an individual who uses this system to study educational content.

[0550] "Terminal" means a device used by a user to access the system, including a PC, smartphone, tablet, etc.

[0551] "Emotional data" refers to information about a user's emotional state that is analyzed from the user's facial expressions, voice, character input, and the like.

[0552] "Reward points" refer to incentives awarded based on a user's learning progress and usage data.

[0553] "Analysis" refers to the process of processing data and extracting meaningful information and patterns.

[0554] "Real time" refers to a timing range in which events that occur are processed nearly simultaneously.

[0555] MODE FOR CARRYING OUT THE INVENTION

[0556] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Furthermore, by combining an emotion engine, the system dynamically generates and provides more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[0557] Overall system overview

[0558] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users access the system using their devices and study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[0559] Consolidation of educational content

[0560] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[0561] Optimization with generative AI models

[0562] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it generates interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[0563] Emotion Engine Functions

[0564] The emotion engine analyzes emotional data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, a camera can analyze their facial expressions, and speech recognition can analyze their tone of voice. The analyzed emotional data is sent to a server, which then uses this data to adjust the difficulty and format of the educational content in real time. For example, if the server detects emotions like "boredom" or "confusion" while the user is watching a video, it can immediately issue instructions to simplify the video content or add interactive elements.

[0565] User Access and Learning

[0566] Users access the system using their own devices (PCs, smartphones, tablets, etc.) and select the subjects or topics they want to learn. For example, if a user selects to learn "Science Fundamentals" on a tablet, the device sends the request to the server, and the server generates and distributes the most appropriate educational content to the device.

[0567] Usage data analysis and reward system

[0568] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is viewing a basic science video and solving problems, the device transmits the user's progress in real time to the server. The server analyzes the acquired data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0569] Specific examples of effects

[0570] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[0571] Prompt Sentence Examples

[0572] "An 8-year-old wants to learn the basics of science, so generate interactive educational content accordingly. Also, adjust the content in real time based on the user's emotional data as they learn."

[0573] As described above, this invention is a system that efficiently provides high-quality, reliable educational content and enables users to learn optimally. Furthermore, by combining a reward system and an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[0574] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0575] Step 1: Collect and store educational content

[0576] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. For example, when an educator uploads a lesson video on "Basics of Chemistry," the server receives the video. At the same time, the server also extracts and stores metadata such as the title, description, target age group, and subject. The input data is the lesson content and metadata, and the output data is the content and metadata stored in the database.

[0577] Step 2: Collect user data

[0578] While the user is using the system, the device collects data such as learning history, grades, and interests, and sends it to the server. For example, a user watches a lecture on "Science Fundamentals" and answers related questions. This causes the device to record the learning history and answers. The input data is the user's learning behavior, and the output data is the user data sent to the server.

[0579] Step 3: Generate and deliver educational content

[0580] The server inputs the educational content and user data from the database into a generative AI model to generate prompts. The generative AI model generates appropriate educational content based on the user's age, learning history, and interests. For example, an 8-year-old user would be provided with interactive problem-solving content on basic science. The server outputs the generated prompts and delivers them to the user's device upon request. The input data are educational content and user data, and the output data is optimized educational content.

[0581] Step 4: User interaction and data submission

[0582] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they want to learn. For example, a user may select "Science Fundamentals" using a tablet. The device sends the selection to the server, which then generates corresponding educational content and provides it to the device. The input data is the user's selection, and the output data is the corresponding educational content.

[0583] Step 5: Analyze emotional data and adjust educational content

[0584] The emotion engine analyzes the user's facial expressions, voice, and text input in real time to extract the user's emotional data. For example, while the user is watching a video, the camera analyzes the user's facial expressions and the voice recognition system extracts the tone of the user's voice. This emotional data is sent to the server, which then adjusts the difficulty and format of the educational content based on this data. The input data is the user's emotional data, and the output data is the adjusted educational content.

[0585] Step 6: Analyze usage data and award reward points

[0586] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is watching a basic science video and answering questions, their progress is transmitted to the server in real time. The server aggregates and analyzes this data, and calculates and awards reward points to the user. The input data is the user's usage data, and the output data is the awarded reward points and a notification of the points.

[0587] (Application example 2)

[0588] 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."

[0589] Conventional educational content delivery systems provide fixed content without considering the user's individual emotional state, making it difficult to provide appropriate learning support based on the user's interests and level of understanding. Furthermore, optimization based solely on content usage data is unable to respond in real time, limiting the user experience. Furthermore, when applying education to customer support in brick-and-mortar stores, it is difficult to make optimal product recommendations based on customer emotion analysis.

[0590] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0591] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for individual users based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for analyzing emotional data from the user's facial expressions and voice and adjusting the content in real time based on the analysis results. This enables real-time optimization of educational content according to the user's emotional state and improved customer support in physical stores.

[0592] "Educational content" refers to information about lesson content provided by educators, and includes formats such as videos, text, images, and web articles.

[0593] A "generative AI model" is an artificial intelligence model that uses aggregated educational content and user attribute information as input to generate educational content optimized for individual users.

[0594] "Emotion data" refers to data relating to the emotional state of the user that is acquired in real time from facial expressions, voice, and the like.

[0595] "User's device" refers to an electronic device used by a user to access the system and use educational content, including a PC, smartphone, tablet, etc.

[0596] "Usage data" refers to various data collected when a user uses educational content, including viewing time, answer results, learning progress, and the like.

[0597] "Reward points" are incentive points that are awarded based on the user's use of educational content and results.

[0598] "Real-time adjustment" refers to the process of instantly changing and adapting the content and difficulty of educational content provided based on the user's emotional data.

[0599] "Database" means an information system for efficiently storing and managing aggregated educational content and associated metadata.

[0600] "Facial expressions" are non-verbal cues that indicate a user's emotional state based on their facial movements and expressions.

[0601] "Voice" refers to data for analyzing the emotional state of a user from vocal characteristics such as tone and intonation.

[0602] MODE FOR CARRYING OUT THE INVENTION

[0603] The present invention provides a system for providing educational content and enhancing the learning effect of users. The configuration and operation of this system will be described below.

[0604] System configuration

[0605] 1. Server

[0606] Database: Stores lesson content (videos, text, images, web articles, etc.) provided by educators. Metadata is also stored.

[0607] Generative AI models: Generate optimized educational content based on input educational content and user attribute information. This includes natural language processing models such as BERT and recommendation systems.

[0608] Emotion engine: Analyzes emotion data from the user's facial expressions and voice in real time. Technologies used include OpenCV and Dlib.

[0609] 2. Terminal

[0610] A device (smartphone, smart glasses, tablet, PC, etc.) that allows a user to access the system. It is desirable that it is equipped with a camera and microphone.

[0611] Optimized educational content is provided by accessing the server from the terminal.

[0612] 3. Users

[0613] Students access the system and use the educational content provided, and their learning progress and emotional data are collected in real time.

[0614] How it works

[0615] Consolidation of educational content

[0616] The server aggregates lesson content provided by educators and stores it in a database. It also extracts and stores metadata about the content (title, description, target age group, subject, etc.).

[0617] Content Optimization

[0618] The server inputs the educational content stored in the database into a generative AI model to generate educational content optimized for each individual user, taking into account the user's age, learning history, interests, and emotional data.

[0619] Emotion data analysis and real-time adjustment

[0620] The server uses an emotion engine to analyze emotion data from the user's facial expressions and voice. For example, it uses OpenCV and Dlib to analyze the user's facial expressions and voice tone using speech recognition technology. Based on this, the difficulty level and format of the educational content can be adjusted in real time.

[0621] Usage data collection and reward system

[0622] The device sends the user's learning progress and usage data to the server. The server analyzes the collected data and awards reward points to the user. The results of the awarding of reward points are notified to the user and recorded in the user's account.

[0623] Specific examples

[0624] For example, if an elementary school student is learning "Science Fundamentals" on a tablet, the optimal content generated by the generative AI model will be displayed on the device. While the user is using the content, the camera analyzes their facial expressions and the microphone analyzes their voice to collect emotional data. If the emotion engine detects "confusion," the system immediately issues instructions to provide more detailed explanations of the educational content, resulting in content that is easier for the user to understand.

[0625] An example of a prompt might be:

[0626] While the user is wearing the smart glasses, explain the features of the product in front of them, analyze the customer's facial expressions and voice to see if they are interested, and determine if further explanation is needed, providing additional information in real time if necessary.

[0627] This invention is expected to highly optimize the user's learning experience and improve customer support in physical stores.

[0628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0629] Step 1:

[0630] The server receives lesson content provided by educators and stores the content and metadata in a database. The input is the lesson content (videos, text, images, web articles) provided by educators, and the output is the content and metadata stored in the database. Data processing involves unifying the content format and extracting metadata (title, description, target age group, subject, etc.).

[0631] Step 2:

[0632] The server inputs educational content stored in the database into a generative AI model to generate educational content optimized for each individual user. The input is the educational content in the database and the user's attribute data (age, learning history, interests), and the output is optimized educational content. As a data calculation, the AI ​​model analyzes multiple attribute data and generates and optimizes educational content based on that data.

[0633] Step 3:

[0634] Users access the system using a terminal and select the subjects or topics they wish to study. The input is the user's selection information (subjects or topics), and the output is a request for optimized content based on the selected information. Specifically, users select subjects using a tablet or smartphone.

[0635] Step 4:

[0636] The emotion engine analyzes camera footage and audio data provided by the user's device to obtain emotional data in real time. The input is the user's facial expression and audio data, and the output is emotional data obtained in real time. Data processing involves facial recognition using OpenCV, facial expression analysis using Dlib, and voice recognition technology to analyze voice tone.

[0637] Step 5:

[0638] The server adjusts the difficulty and format of the optimized educational content in real time based on the emotional data. The input is the emotional data from the emotion engine, and the output is the adjusted educational content. As a data calculation, the emotional data is evaluated and, if necessary, re-input into the generative AI model to regenerate the content.

[0639] Step 6:

[0640] The device collects the user's learning progress and usage data and sends it to the server. The input is the user's learning usage data (viewing time, answer results, progress), and the output is the usage data sent to the server. Specifically, the device has a mechanism to periodically upload data to the server.

[0641] Step 7:

[0642] The server analyzes the user's usage data and awards reward points. The input is the collected usage data, and the output is the reward point award result. As a data calculation, the usage data is evaluated and reward points are calculated based on the pre-set conditions. The calculated points are recorded in the user's account and notified.

[0643] The above are the specific processing steps of this invention. By configuring the system in this way, it becomes possible to optimize educational content in real time according to the user's emotional state and improve customer support in physical stores.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] [Third embodiment]

[0648] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0649] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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).

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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."

[0660] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Specific embodiments of the system are described below.

[0661] Overall system description

[0662] The system consists of three main components: a server, a device, and a user. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices and study the optimized educational content. Furthermore, the system analyzes users' educational content usage data and awards reward points.

[0663] Consolidation of educational content

[0664] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database. At the same time, the metadata of the lesson content (title, description, target age, subject, etc.) is also extracted and stored in the database.

[0665] Optimization with generative AI models

[0666] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This process takes into account data such as the user's age, learning history, and interests.

[0667] User Access and Learning

[0668] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0669] Usage data analysis and reward system

[0670] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device sequentially transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0671] Specific examples of effects

[0672] For example, if an elementary school student selects "Basics of Chemistry" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[0673] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by introducing a reward system based on frequency of use, it has the effect of increasing users' motivation to learn.

[0674] The processing flow will be explained below.

[0675] Step 1:

[0676] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video on "Basics of Mathematics" to the server, the server receives the video.

[0677] Step 2:

[0678] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title of a lesson video, description, target grade, and subject information are stored in the database.

[0679] Step 3:

[0680] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[0681] Step 4:

[0682] The server inputs the lesson content from the database into the generative AI model. For example, a "Basics of Mathematics" video and its explanatory text are input into the generative AI model, and analysis begins.

[0683] Step 5:

[0684] The generative AI model analyzes the input content and generates educational content optimized for the user, such as problem-solving content to deepen an 8-year-old student's understanding of basic addition and subtraction.

[0685] Step 6:

[0686] Users access the system using a device (such as a PC, smartphone, or tablet) and select the subject or topic they wish to study. For example, a user may select that they want to learn "basic arithmetic."

[0687] Step 7:

[0688] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Basic Math for 8-Year-Olds" content from the database.

[0689] Step 8:

[0690] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[0691] Step 9:

[0692] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[0693] Step 10:

[0694] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[0695] Step 11:

[0696] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[0697] Through the above steps, this system provides educational content efficiently and with high quality, and increases users' motivation to learn.

[0698] Example 1

[0699] 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."

[0700] In traditional education systems, the same educational content is provided to all students, making it difficult to address individual needs. It is also difficult to accurately measure class progress and learning outcomes, and there is no reward system to maintain student motivation. Furthermore, educational content is not adequately optimized, limiting learning effectiveness.

[0701] 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.

[0702] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, a means for instructing the generative AI model to generate educational content based on prompt statements, and a means for continuously transmitting the user's learning progress. This makes it possible to provide educational content that meets individual needs, measure learning effectiveness, and increase motivation to learn through a reward system.

[0703] "Educators" refers to instructors and other teachers who provide lesson content.

[0704] "Class content" refers to educational materials such as videos, texts, images, and web articles provided by educators for use in classes.

[0705] "Database" refers to a storage device for storing and managing lesson content and its metadata.

[0706] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates educational content optimized for individual users.

[0707] "Users" refer to students and learners who use this system to study educational content.

[0708] "Terminal" refers to an electronic device such as a PC, smartphone, or tablet that a user uses to access the system.

[0709] "Reward points" refer to points awarded based on a user's learning progress and frequency of use.

[0710] "Prompt" refers to a text document used to specify instructions to a generative AI model.

[0711] "Learning progress" refers to data indicating how much a user has learned educational content.

[0712] This system aggregates various lesson contents provided by educators and provides educational contents optimized for individual users. This system consists of three main components: a server, a terminal, and a user.

[0713] Server Operation

[0714] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. At the same time, it also extracts and stores the lesson content's metadata (title, description, target age group, subject, etc.). For example, if a teacher uploads a lesson video titled "Basic Math," the video is stored in AWS S3 storage, and the metadata is recorded in a PostgreSQL database.

[0715] The server then inputs the educational content from the database into a generative AI model (OpenAI's GPT model). The generative AI model generates educational content optimized for each individual user based on the input data. This process takes into account data such as the user's age, learning history, and interests. For example, an 8-year-old student would receive interactive problem-solving content to deepen their understanding of basic addition and subtraction.

[0716] Device behavior

[0717] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0718] User Behavior and Learning

[0719] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0720] Specific examples

[0721] For example, if an elementary school student selects to learn "Basic Mathematics" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[0722] Prompt Sentence Examples

[0723] For example, a prompt for a generative AI model might look like this:

[0724] "My 8-year-old elementary school student wants to learn addition and subtraction in math. I'd like you to create educational content that explains the basic concepts."

[0725] This system allows educators to efficiently provide high-quality lesson content, and users to progress with their studies through individually optimized educational content. In addition, a reward system based on frequency of use can increase users' motivation to learn.

[0726] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0727] Step 1:

[0728] The server receives lesson content (videos, text, images, web articles) from educators. Specifically, the files provided by educators are uploaded to the server. The input is the educator's content, and the output is a content file stored in AWS S3 storage.

[0729] Step 2:

[0730] The server extracts the metadata (title, description, target age, subject, etc.) of the uploaded lesson content and stores it in a database. Specifically, it saves the extracted metadata in a PostgreSQL database. The input at this time is the lesson content file itself, and the output is the metadata stored in the database.

[0731] Step 3:

[0732] The server inputs the educational content stored in the database into the generative AI model. Specifically, it inputs the content along with the user's age, learning history, and interest data into the generative AI model (OpenAI's GPT model). In this process, the input is the educational content in the database and the user profile, and the output is optimized educational content.

[0733] Step 4:

[0734] Users access the system using their own devices and select the topic or subject they want to learn. Specifically, when a user selects "Basic Math," the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. In this process, the input is the user's selection, and the output is the optimized content displayed on the user's device.

[0735] Step 5:

[0736] The device transmits the user's learning progress and usage data (such as browsing time and answer results) to the server in real time. Specifically, all user actions during learning are recorded and transmitted sequentially to the server. In this process, the input is the user's learning activity, and the output is the usage data transmitted to the server.

[0737] Step 6:

[0738] The server analyzes the acquired usage data and awards reward points to the user. Specifically, based on the analysis results, points are calculated and added to the user's account. In this process, the input is usage data, and the output is the awarded reward points and a notification.

[0739] (Application example 1)

[0740] 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."

[0741] While individualized instruction is important in the education field, its realization requires time and resources. There is also a need for a method to efficiently provide educational content in brick-and-mortar stores and increase learning motivation. Furthermore, there is no method to provide optimal content in real time using user location information, making it difficult to provide an educational experience tailored to each individual user.

[0742] 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.

[0743] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for detecting the user's location in a physical store in real time and providing the optimal educational content based on the detected location. This makes it possible to provide educational content tailored to each user in real time even in a physical store, thereby improving learning effectiveness and motivation.

[0744] "Educational content" refers to information and materials such as videos, text, images, and web articles intended for user learning purposes.

[0745] A "generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for each individual user.

[0746] "Server" refers to a central control device that aggregates lesson content provided by educators, stores it in a database, optimizes the educational content using a generative AI model, and provides it to users.

[0747] "Terminal" means a device that a user uses to access the server and view and use the provided educational content, including smartphones, tablets, and PCs.

[0748] "Metadata" refers to additional information about lesson content, such as title, description, target age, and subject.

[0749] "Reward points" are points that are awarded based on the user's content usage data, and function as an incentive to increase the user's motivation to learn.

[0750] "Real-time location detection" refers to technology that detects the user's location within a physical store in real time.

[0751] "Database" refers to a data structure for efficiently storing and managing lesson content, user information, usage data, etc.

[0752] "Usage data" refers to behavioral data when a user uses educational content, and includes viewing time, answer results, progress, and the like.

[0753] This invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual users based on that content. Specifically, it consists of three main components: a server, a terminal, and a user.

[0754] Server-based aggregation of educational content

[0755] The server receives lesson content sent by educators and stores it in a database. Lesson content includes videos, text, images, web articles, etc. For example, if an educator uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database and also extracts and saves related metadata (title, description, target age group, subject, etc.).

[0756] Content optimization with generative AI models

[0757] The server inputs educational content from the database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This analysis takes into account data such as the user's age, learning history, and interests.

[0758] User Access and Learning

[0759] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0760] Usage data analysis and reward system

[0761] The user's device transmits learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0762] Real-time location detection and content provision in physical stores

[0763] This system also allows users to access educational content within a physical store. The system detects the user's location within the store in real time and provides the most appropriate educational content based on that location. For example, if a user is in the "science" section of a bookstore, science-related educational content will be provided.

[0764] Examples and prompts

[0765] For example, if a 10-year-old user walks into a bookstore and stops in the "Science" section, the app might:

[0766] 1. Determine from location information that the user is in the "science" section of a bookstore.

[0767] 2. The server sends the following prompt to OpenAI GPT-3:

[0768] My 10-year-old child is interested in science. Please provide educational content that is most suitable for this child.

[0769] 3. Providing generated content to smartphones and smart glasses in real time.

[0770] 4. After the user has finished studying the content, reward points will be added to their account.

[0771] The present invention makes it possible to provide educational content suited to individual users in real time, even in a physical store, thereby improving learning effectiveness and motivation.

[0772] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0773] Step 1:

[0774] Consolidation of educational content

[0775] The server receives lesson content (videos, text, images, web articles, etc.) from educators and stores it in a database.

[0776] Input: Lesson content provided by educators.

[0777] Data processing: Content data and metadata (title, description, target age, subject, etc.) are extracted and stored.

[0778] Output: Lesson content stored in a database.

[0779] Step 2:

[0780] Content optimization with generative AI models

[0781] The server inputs educational content from the database into the generative AI model.

[0782] Input: Educational content stored in a database.

[0783] Data calculation: A generative AI model analyzes input content and generates educational content optimized for each individual user.

[0784] Output: Generated optimized educational content.

[0785] Step 3:

[0786] Access and content provision via user terminals

[0787] Users access the system from their own devices and select the topic or subject they want to learn. The server retrieves the generated educational content as a query and sends it to the user's device.

[0788] Input: A request from the user's device to select a topic or subject.

[0789] Data processing: Retrieving optimized educational content from the database.

[0790] Output: The educational content sent to the user's device.

[0791] Step 4:

[0792] Real-time location detection and in-store content delivery

[0793] The device detects the user's location in the physical store in real time, and based on the detected location, sends a request to the server to provide the most appropriate educational content.

[0794] Input: Real-time location information from the user's device.

[0795] Data calculation: Determines relevant educational content based on location information and sends a request to the server.

[0796] Output: The optimal educational content is displayed on the user's device.

[0797] Step 5:

[0798] Analysis of usage data and awarding of reward points

[0799] The device transmits the user's learning progress and usage data to the server in real time, which analyzes the data and awards reward points to the user.

[0800] Input: User's learning progress and usage data (viewing time, answer results, etc.).

[0801] Data calculation: Analyze usage data and calculate reward points.

[0802] Output: The calculated reward points are recorded in the user account and notified.

[0803] 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.

[0804] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content, and also combines it with an emotion engine to dynamically generate and provide more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[0805] Overall system description

[0806] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices to study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[0807] Consolidation of educational content

[0808] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[0809] Optimization with generative AI models

[0810] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[0811] Emotion Engine Functions

[0812] The emotion engine analyzes emotion data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, the camera analyzes the user's facial expressions and voice tone using voice recognition. The analyzed emotion data is sent to the server.

[0813] User Access and Learning

[0814] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[0815] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[0816] Real-time adjustments based on emotion data

[0817] The server adjusts the difficulty and format of educational content in real time based on the emotional data sent by the emotion engine. For example, if the server detects emotions like "boredom" or "confusion" while a user is watching a video, it will immediately issue instructions to simplify the video content or add interactive elements.

[0818] Usage data analysis and reward system

[0819] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device transmits the user's progress status sequentially to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award result and the points are recorded in the user's account.

[0820] Specific examples of effects

[0821] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[0822] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by combining a reward system based on frequency of use with an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[0823] The processing flow will be explained below.

[0824] Step 1:

[0825] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video about "Science Fundamentals" to the server, the server receives the video.

[0826] Step 2:

[0827] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title, description, target grade, and subject information of a lesson video can be saved in the database to make it easier to search.

[0828] Step 3:

[0829] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[0830] Step 4:

[0831] The server inputs the lesson content from the database into the generative AI model. For example, a "Science Fundamentals" video and its explanatory text are input into the generative AI model and analysis begins.

[0832] Step 5:

[0833] The generative AI model analyzes the input content and generates educational content optimized for the user, such as interactive problem-solving content to help an 8-year-old student understand basic science concepts, taking into account data such as the user's age, learning history, and interests.

[0834] Step 6:

[0835] The emotion engine uses the camera and microphone on the user's device to collect the user's facial expressions and voice in real time. For example, while the user is watching a video, the camera captures the user's facial expressions and the microphone analyzes the tone of the user's voice.

[0836] Step 7:

[0837] The emotion engine analyzes the collected data and determines the user's emotional state (happiness, confusion, interest, boredom, etc.) in real time. For example, if a user shows a confused expression while watching a video, that emotion will be recognized.

[0838] Step 8:

[0839] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[0840] Step 9:

[0841] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[0842] Step 10:

[0843] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[0844] Step 11:

[0845] The server adjusts the difficulty and format of educational content in real time based on the emotion data sent by the emotion engine. For example, if the server detects the emotion of "confusion" while a user is watching a video, it will simplify the video content or provide additional explanations.

[0846] Step 12:

[0847] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[0848] Step 13:

[0849] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[0850] Step 14:

[0851] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[0852] This system can efficiently provide high-quality and reliable educational content, increasing users' motivation to learn. In addition, by using an emotion engine, it is possible to provide educational content that is more suited to user needs.

[0853] Example 2

[0854] 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."

[0855] In conventional educational systems, educational content is provided uniformly, making it difficult to provide an optimal learning experience for each individual user. Furthermore, there is a lack of mechanisms to maintain and improve motivation for learning, and the lack of dynamic content adjustment based on the user's progress and emotions is also an issue.

[0856] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, and a means for providing the generated educational content in response to access from the user's terminal. This makes it possible to provide educational content optimized for each user and maintain and improve their motivation to learn.

[0857] "Educators" refers to those responsible for providing educational content and experts.

[0858] "Class content" refers to educational materials provided by educators, including information assets such as videos, text, images, and web articles.

[0859] "Database" refers to a digital storage system for efficiently storing and managing aggregated course content and metadata.

[0860] "Generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for individual users.

[0861] "User" refers to an individual who uses this system to study educational content.

[0862] "Terminal" means a device used by a user to access the system, including a PC, smartphone, tablet, etc.

[0863] "Emotional data" refers to information about a user's emotional state that is analyzed from the user's facial expressions, voice, character input, and the like.

[0864] "Reward points" refer to incentives awarded based on a user's learning progress and usage data.

[0865] "Analysis" refers to the process of processing data and extracting meaningful information and patterns.

[0866] "Real time" refers to a timing range in which events that occur are processed nearly simultaneously.

[0867] MODE FOR CARRYING OUT THE INVENTION

[0868] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Furthermore, by combining an emotion engine, the system dynamically generates and provides more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[0869] Overall system overview

[0870] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users access the system using their devices and study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[0871] Consolidation of educational content

[0872] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[0873] Optimization with generative AI models

[0874] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it generates interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[0875] Emotion Engine Functions

[0876] The emotion engine analyzes emotional data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, a camera can analyze their facial expressions, and speech recognition can analyze their tone of voice. The analyzed emotional data is sent to a server, which then uses this data to adjust the difficulty and format of the educational content in real time. For example, if the server detects emotions like "boredom" or "confusion" while the user is watching a video, it can immediately issue instructions to simplify the video content or add interactive elements.

[0877] User Access and Learning

[0878] Users access the system using their own devices (PCs, smartphones, tablets, etc.) and select the subjects or topics they want to learn. For example, if a user selects to learn "Science Fundamentals" on a tablet, the device sends the request to the server, and the server generates and distributes the most appropriate educational content to the device.

[0879] Usage data analysis and reward system

[0880] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is viewing a basic science video and solving problems, the device transmits the user's progress in real time to the server. The server analyzes the acquired data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0881] Specific examples of effects

[0882] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[0883] Prompt Sentence Examples

[0884] "An 8-year-old wants to learn the basics of science, so generate interactive educational content accordingly. Also, adjust the content in real time based on the user's emotional data as they learn."

[0885] As described above, this invention is a system that efficiently provides high-quality, reliable educational content and enables users to learn optimally. Furthermore, by combining a reward system and an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[0886] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0887] Step 1: Collect and store educational content

[0888] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. For example, when an educator uploads a lesson video on "Basics of Chemistry," the server receives the video. At the same time, the server also extracts and stores metadata such as the title, description, target age group, and subject. The input data is the lesson content and metadata, and the output data is the content and metadata stored in the database.

[0889] Step 2: Collect user data

[0890] While the user is using the system, the device collects data such as learning history, grades, and interests, and sends it to the server. For example, a user watches a lecture on "Science Fundamentals" and answers related questions. This causes the device to record the learning history and answers. The input data is the user's learning behavior, and the output data is the user data sent to the server.

[0891] Step 3: Generate and deliver educational content

[0892] The server inputs the educational content and user data from the database into a generative AI model to generate prompts. The generative AI model generates appropriate educational content based on the user's age, learning history, and interests. For example, an 8-year-old user would be provided with interactive problem-solving content on basic science. The server outputs the generated prompts and delivers them to the user's device upon request. The input data are educational content and user data, and the output data is optimized educational content.

[0893] Step 4: User interaction and data submission

[0894] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they want to learn. For example, a user may select "Science Fundamentals" using a tablet. The device sends the selection to the server, which then generates corresponding educational content and provides it to the device. The input data is the user's selection, and the output data is the corresponding educational content.

[0895] Step 5: Analyze emotional data and adjust educational content

[0896] The emotion engine analyzes the user's facial expressions, voice, and text input in real time to extract the user's emotional data. For example, while the user is watching a video, the camera analyzes the user's facial expressions and the voice recognition system extracts the tone of the user's voice. This emotional data is sent to the server, which then adjusts the difficulty and format of the educational content based on this data. The input data is the user's emotional data, and the output data is the adjusted educational content.

[0897] Step 6: Analyze usage data and award reward points

[0898] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is watching a basic science video and answering questions, their progress is transmitted to the server in real time. The server aggregates and analyzes this data, and calculates and awards reward points to the user. The input data is the user's usage data, and the output data is the awarded reward points and a notification of the points.

[0899] (Application example 2)

[0900] 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."

[0901] Conventional educational content delivery systems provide fixed content without considering the user's individual emotional state, making it difficult to provide appropriate learning support based on the user's interests and level of understanding. Furthermore, optimization based solely on content usage data is unable to respond in real time, limiting the user experience. Furthermore, when applying education to customer support in brick-and-mortar stores, it is difficult to make optimal product recommendations based on customer emotion analysis.

[0902] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0903] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for individual users based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for analyzing emotional data from the user's facial expressions and voice and adjusting the content in real time based on the analysis results. This enables real-time optimization of educational content according to the user's emotional state and improved customer support in physical stores.

[0904] "Educational content" refers to information about lesson content provided by educators, and includes formats such as videos, text, images, and web articles.

[0905] A "generative AI model" is an artificial intelligence model that uses aggregated educational content and user attribute information as input to generate educational content optimized for individual users.

[0906] "Emotion data" refers to data relating to the emotional state of the user that is acquired in real time from facial expressions, voice, and the like.

[0907] "User's device" refers to an electronic device used by a user to access the system and use educational content, including a PC, smartphone, tablet, etc.

[0908] "Usage data" refers to various data collected when a user uses educational content, including viewing time, answer results, learning progress, and the like.

[0909] "Reward points" are incentive points that are awarded based on the user's use of educational content and results.

[0910] "Real-time adjustment" refers to the process of instantly changing and adapting the content and difficulty of educational content provided based on the user's emotional data.

[0911] "Database" means an information system for efficiently storing and managing aggregated educational content and associated metadata.

[0912] "Facial expressions" are non-verbal cues that indicate a user's emotional state based on their facial movements and expressions.

[0913] "Voice" refers to data for analyzing the emotional state of a user from vocal characteristics such as tone and intonation.

[0914] MODE FOR CARRYING OUT THE INVENTION

[0915] The present invention provides a system for providing educational content and enhancing the learning effect of users. The configuration and operation of this system will be described below.

[0916] System configuration

[0917] 1. Server

[0918] Database: Stores lesson content (videos, text, images, web articles, etc.) provided by educators. Metadata is also stored.

[0919] Generative AI models: Generate optimized educational content based on input educational content and user attribute information. This includes natural language processing models such as BERT and recommendation systems.

[0920] Emotion engine: Analyzes emotion data from the user's facial expressions and voice in real time. Technologies used include OpenCV and Dlib.

[0921] 2. Terminal

[0922] A device (smartphone, smart glasses, tablet, PC, etc.) that allows a user to access the system. It is desirable that it is equipped with a camera and microphone.

[0923] Optimized educational content is provided by accessing the server from the terminal.

[0924] 3. Users

[0925] Students access the system and use the educational content provided, and their learning progress and emotional data are collected in real time.

[0926] How it works

[0927] Consolidation of educational content

[0928] The server aggregates lesson content provided by educators and stores it in a database. It also extracts and stores metadata about the content (title, description, target age group, subject, etc.).

[0929] Content Optimization

[0930] The server inputs the educational content stored in the database into a generative AI model to generate educational content optimized for each individual user, taking into account the user's age, learning history, interests, and emotional data.

[0931] Emotion data analysis and real-time adjustment

[0932] The server uses an emotion engine to analyze emotion data from the user's facial expressions and voice. For example, it uses OpenCV and Dlib to analyze the user's facial expressions and voice tone using speech recognition technology. Based on this, the difficulty level and format of the educational content can be adjusted in real time.

[0933] Usage data collection and reward system

[0934] The device sends the user's learning progress and usage data to the server. The server analyzes the collected data and awards reward points to the user. The results of the awarding of reward points are notified to the user and recorded in the user's account.

[0935] Specific examples

[0936] For example, if an elementary school student is learning "Science Fundamentals" on a tablet, the optimal content generated by the generative AI model will be displayed on the device. While the user is using the content, the camera analyzes their facial expressions and the microphone analyzes their voice to collect emotional data. If the emotion engine detects "confusion," the system immediately issues instructions to provide more detailed explanations of the educational content, resulting in content that is easier for the user to understand.

[0937] An example of a prompt might be:

[0938] While the user is wearing the smart glasses, explain the features of the product in front of them, analyze the customer's facial expressions and voice to see if they are interested, and determine if further explanation is needed, providing additional information in real time if necessary.

[0939] This invention is expected to highly optimize the user's learning experience and improve customer support in physical stores.

[0940] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0941] Step 1:

[0942] The server receives lesson content provided by educators and stores the content and metadata in a database. The input is the lesson content (videos, text, images, web articles) provided by educators, and the output is the content and metadata stored in the database. Data processing involves unifying the content format and extracting metadata (title, description, target age group, subject, etc.).

[0943] Step 2:

[0944] The server inputs educational content stored in the database into a generative AI model to generate educational content optimized for each individual user. The input is the educational content in the database and the user's attribute data (age, learning history, interests), and the output is optimized educational content. As a data calculation, the AI ​​model analyzes multiple attribute data and generates and optimizes educational content based on that data.

[0945] Step 3:

[0946] Users access the system using a terminal and select the subjects or topics they wish to study. The input is the user's selection information (subjects or topics), and the output is a request for optimized content based on the selected information. Specifically, users select subjects using a tablet or smartphone.

[0947] Step 4:

[0948] The emotion engine analyzes camera footage and audio data provided by the user's device to obtain emotional data in real time. The input is the user's facial expression and audio data, and the output is emotional data obtained in real time. Data processing involves facial recognition using OpenCV, facial expression analysis using Dlib, and voice recognition technology to analyze voice tone.

[0949] Step 5:

[0950] The server adjusts the difficulty and format of the optimized educational content in real time based on the emotional data. The input is the emotional data from the emotion engine, and the output is the adjusted educational content. As a data calculation, the emotional data is evaluated and, if necessary, re-input into the generative AI model to regenerate the content.

[0951] Step 6:

[0952] The device collects the user's learning progress and usage data and sends it to the server. The input is the user's learning usage data (viewing time, answer results, progress), and the output is the usage data sent to the server. Specifically, the device has a mechanism to periodically upload data to the server.

[0953] Step 7:

[0954] The server analyzes the user's usage data and awards reward points. The input is the collected usage data, and the output is the reward point award result. As a data calculation, the usage data is evaluated and reward points are calculated based on the pre-set conditions. The calculated points are recorded in the user's account and notified.

[0955] The above are the specific processing steps of this invention. By configuring the system in this way, it becomes possible to optimize educational content in real time according to the user's emotional state and improve customer support in physical stores.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] [Fourth embodiment]

[0960] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0961] 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.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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).

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] 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."

[0973] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Specific embodiments of the system are described below.

[0974] Overall system description

[0975] The system consists of three main components: a server, a device, and a user. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices and study the optimized educational content. Furthermore, the system analyzes users' educational content usage data and awards reward points.

[0976] Consolidation of educational content

[0977] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database. At the same time, the metadata of the lesson content (title, description, target age, subject, etc.) is also extracted and stored in the database.

[0978] Optimization with generative AI models

[0979] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This process takes into account data such as the user's age, learning history, and interests.

[0980] User Access and Learning

[0981] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[0982] Usage data analysis and reward system

[0983] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device sequentially transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[0984] Specific examples of effects

[0985] For example, if an elementary school student selects "Basics of Chemistry" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[0986] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by introducing a reward system based on frequency of use, it has the effect of increasing users' motivation to learn.

[0987] The processing flow will be explained below.

[0988] Step 1:

[0989] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video on "Basics of Mathematics" to the server, the server receives the video.

[0990] Step 2:

[0991] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title of a lesson video, description, target grade, and subject information are stored in the database.

[0992] Step 3:

[0993] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[0994] Step 4:

[0995] The server inputs the lesson content from the database into the generative AI model. For example, a "Basics of Mathematics" video and its explanatory text are input into the generative AI model, and analysis begins.

[0996] Step 5:

[0997] The generative AI model analyzes the input content and generates educational content optimized for the user, such as problem-solving content to deepen an 8-year-old student's understanding of basic addition and subtraction.

[0998] Step 6:

[0999] Users access the system using a device (such as a PC, smartphone, or tablet) and select the subject or topic they wish to study. For example, a user may select that they want to learn "basic arithmetic."

[1000] Step 7:

[1001] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Basic Math for 8-Year-Olds" content from the database.

[1002] Step 8:

[1003] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[1004] Step 9:

[1005] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[1006] Step 10:

[1007] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[1008] Step 11:

[1009] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[1010] Through the above steps, this system provides educational content efficiently and with high quality, and increases users' motivation to learn.

[1011] Example 1

[1012] 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."

[1013] In traditional education systems, the same educational content is provided to all students, making it difficult to address individual needs. It is also difficult to accurately measure class progress and learning outcomes, and there is no reward system to maintain student motivation. Furthermore, educational content is not adequately optimized, limiting learning effectiveness.

[1014] 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.

[1015] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, a means for instructing the generative AI model to generate educational content based on prompt statements, and a means for continuously transmitting the user's learning progress. This makes it possible to provide educational content that meets individual needs, measure learning effectiveness, and increase motivation to learn through a reward system.

[1016] "Educators" refers to instructors and other teachers who provide lesson content.

[1017] "Class content" refers to educational materials such as videos, texts, images, and web articles provided by educators for use in classes.

[1018] "Database" refers to a storage device for storing and managing lesson content and its metadata.

[1019] A "generative AI model" refers to an artificial intelligence model that analyzes input data and generates educational content optimized for individual users.

[1020] "Users" refer to students and learners who use this system to study educational content.

[1021] "Terminal" refers to an electronic device such as a PC, smartphone, or tablet that a user uses to access the system.

[1022] "Reward points" refer to points awarded based on a user's learning progress and frequency of use.

[1023] "Prompt" refers to a text document used to specify instructions to a generative AI model.

[1024] "Learning progress" refers to data indicating how much a user has learned educational content.

[1025] This system aggregates various lesson contents provided by educators and provides educational contents optimized for individual users. This system consists of three main components: a server, a terminal, and a user.

[1026] Server Operation

[1027] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. At the same time, it also extracts and stores the lesson content's metadata (title, description, target age group, subject, etc.). For example, if a teacher uploads a lesson video titled "Basic Math," the video is stored in AWS S3 storage, and the metadata is recorded in a PostgreSQL database.

[1028] The server then inputs the educational content from the database into a generative AI model (OpenAI's GPT model). The generative AI model generates educational content optimized for each individual user based on the input data. This process takes into account data such as the user's age, learning history, and interests. For example, an 8-year-old student would receive interactive problem-solving content to deepen their understanding of basic addition and subtraction.

[1029] Device behavior

[1030] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[1031] User Behavior and Learning

[1032] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[1033] Specific examples

[1034] For example, if an elementary school student selects to learn "Basic Mathematics" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage data will be analyzed and appropriate reward points will be automatically awarded.

[1035] Prompt Sentence Examples

[1036] For example, a prompt for a generative AI model might look like this:

[1037] "My 8-year-old elementary school student wants to learn addition and subtraction in math. I'd like you to create educational content that explains the basic concepts."

[1038] This system allows educators to efficiently provide high-quality lesson content, and users to progress with their studies through individually optimized educational content. In addition, a reward system based on frequency of use can increase users' motivation to learn.

[1039] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1040] Step 1:

[1041] The server receives lesson content (videos, text, images, web articles) from educators. Specifically, the files provided by educators are uploaded to the server. The input is the educator's content, and the output is a content file stored in AWS S3 storage.

[1042] Step 2:

[1043] The server extracts the metadata (title, description, target age, subject, etc.) of the uploaded lesson content and stores it in a database. Specifically, it saves the extracted metadata in a PostgreSQL database. The input at this time is the lesson content file itself, and the output is the metadata stored in the database.

[1044] Step 3:

[1045] The server inputs the educational content stored in the database into the generative AI model. Specifically, it inputs the content along with the user's age, learning history, and interest data into the generative AI model (OpenAI's GPT model). In this process, the input is the educational content in the database and the user profile, and the output is optimized educational content.

[1046] Step 4:

[1047] Users access the system using their own devices and select the topic or subject they want to learn. Specifically, when a user selects "Basic Math," the server retrieves educational content optimized by the generative AI model from the database and sends it to the user's device. In this process, the input is the user's selection, and the output is the optimized content displayed on the user's device.

[1048] Step 5:

[1049] The device transmits the user's learning progress and usage data (such as browsing time and answer results) to the server in real time. Specifically, all user actions during learning are recorded and transmitted sequentially to the server. In this process, the input is the user's learning activity, and the output is the usage data transmitted to the server.

[1050] Step 6:

[1051] The server analyzes the acquired usage data and awards reward points to the user. Specifically, based on the analysis results, points are calculated and added to the user's account. In this process, the input is usage data, and the output is the awarded reward points and a notification.

[1052] (Application example 1)

[1053] 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."

[1054] While individualized instruction is important in the education field, its realization requires time and resources. There is also a need for a method to efficiently provide educational content in brick-and-mortar stores and increase learning motivation. Furthermore, there is no method to provide optimal content in real time using user location information, making it difficult to provide an educational experience tailored to each individual user.

[1055] 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.

[1056] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for detecting the user's location in a physical store in real time and providing the optimal educational content based on the detected location. This makes it possible to provide educational content tailored to each user in real time even in a physical store, thereby improving learning effectiveness and motivation.

[1057] "Educational content" refers to information and materials such as videos, text, images, and web articles intended for user learning purposes.

[1058] A "generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for each individual user.

[1059] "Server" refers to a central control device that aggregates lesson content provided by educators, stores it in a database, optimizes the educational content using a generative AI model, and provides it to users.

[1060] "Terminal" means a device that a user uses to access the server and view and use the provided educational content, including smartphones, tablets, and PCs.

[1061] "Metadata" refers to additional information about lesson content, such as title, description, target age, and subject.

[1062] "Reward points" are points that are awarded based on the user's content usage data, and function as an incentive to increase the user's motivation to learn.

[1063] "Real-time location detection" refers to technology that detects the user's location within a physical store in real time.

[1064] "Database" refers to a data structure for efficiently storing and managing lesson content, user information, usage data, etc.

[1065] "Usage data" refers to behavioral data when a user uses educational content, and includes viewing time, answer results, progress, and the like.

[1066] This invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual users based on that content. Specifically, it consists of three main components: a server, a terminal, and a user.

[1067] Server-based aggregation of educational content

[1068] The server receives lesson content sent by educators and stores it in a database. Lesson content includes videos, text, images, web articles, etc. For example, if an educator uploads a lesson video on "Basic Mathematics" to the server, the server stores the video in a database and also extracts and saves related metadata (title, description, target age group, subject, etc.).

[1069] Content optimization with generative AI models

[1070] The server inputs educational content from the database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to deepen their understanding of basic addition and subtraction. This analysis takes into account data such as the user's age, learning history, and interests.

[1071] User Access and Learning

[1072] Users access the system using their own devices (PCs, smartphones, tablets, etc.). When the user selects the theme or subject they want to learn, the server retrieves the educational content optimized by the generative AI model from the database as a query and sends it to the user's device. For example, if the user selects "Basic Math," the server sends the optimized educational content to the user's device and displays it.

[1073] Usage data analysis and reward system

[1074] The user's device transmits learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device continuously transmits the progress to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[1075] Real-time location detection and content provision in physical stores

[1076] This system also allows users to access educational content within a physical store. The system detects the user's location within the store in real time and provides the most appropriate educational content based on that location. For example, if a user is in the "science" section of a bookstore, science-related educational content will be provided.

[1077] Examples and prompts

[1078] For example, if a 10-year-old user walks into a bookstore and stops in the "Science" section, the app might:

[1079] 1. Determine from location information that the user is in the "science" section of a bookstore.

[1080] 2. The server sends the following prompt to OpenAI GPT-3:

[1081] My 10-year-old child is interested in science. Please provide educational content that is most suitable for this child.

[1082] 3. Providing generated content to smartphones and smart glasses in real time.

[1083] 4. After the user has finished studying the content, reward points will be added to their account.

[1084] The present invention makes it possible to provide educational content suited to individual users in real time, even in a physical store, thereby improving learning effectiveness and motivation.

[1085] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1086] Step 1:

[1087] Consolidation of educational content

[1088] The server receives lesson content (videos, text, images, web articles, etc.) from educators and stores it in a database.

[1089] Input: Lesson content provided by educators.

[1090] Data processing: Content data and metadata (title, description, target age, subject, etc.) are extracted and stored.

[1091] Output: Lesson content stored in a database.

[1092] Step 2:

[1093] Content optimization with generative AI models

[1094] The server inputs educational content from the database into the generative AI model.

[1095] Input: Educational content stored in a database.

[1096] Data calculation: A generative AI model analyzes input content and generates educational content optimized for each individual user.

[1097] Output: Generated optimized educational content.

[1098] Step 3:

[1099] Access and content provision via user terminals

[1100] Users access the system from their own devices and select the topic or subject they want to learn. The server retrieves the generated educational content as a query and sends it to the user's device.

[1101] Input: A request from the user's device to select a topic or subject.

[1102] Data processing: Retrieving optimized educational content from the database.

[1103] Output: The educational content sent to the user's device.

[1104] Step 4:

[1105] Real-time location detection and in-store content delivery

[1106] The device detects the user's location in the physical store in real time, and based on the detected location, sends a request to the server to provide the most appropriate educational content.

[1107] Input: Real-time location information from the user's device.

[1108] Data calculation: Determines relevant educational content based on location information and sends a request to the server.

[1109] Output: The optimal educational content is displayed on the user's device.

[1110] Step 5:

[1111] Analysis of usage data and awarding of reward points

[1112] The device transmits the user's learning progress and usage data to the server in real time, which analyzes the data and awards reward points to the user.

[1113] Input: User's learning progress and usage data (viewing time, answer results, etc.).

[1114] Data calculation: Analyze usage data and calculate reward points.

[1115] Output: The calculated reward points are recorded in the user account and notified.

[1116] 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.

[1117] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content, and also combines it with an emotion engine to dynamically generate and provide more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[1118] Overall system description

[1119] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users can access the system using their devices to study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[1120] Consolidation of educational content

[1121] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[1122] Optimization with generative AI models

[1123] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it would generate interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[1124] Emotion Engine Functions

[1125] The emotion engine analyzes emotion data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, the camera analyzes the user's facial expressions and voice tone using voice recognition. The analyzed emotion data is sent to the server.

[1126] User Access and Learning

[1127] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[1128] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[1129] Real-time adjustments based on emotion data

[1130] The server adjusts the difficulty and format of educational content in real time based on the emotional data sent by the emotion engine. For example, if the server detects emotions like "boredom" or "confusion" while a user is watching a video, it will immediately issue instructions to simplify the video content or add interactive elements.

[1131] Usage data analysis and reward system

[1132] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is watching a video and solving problems, the device transmits the user's progress status sequentially to the server. The server analyzes the acquired usage data and awards reward points to the user. The user is notified of the award result and the points are recorded in the user's account.

[1133] Specific examples of effects

[1134] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[1135] As described above, the present invention is a system that efficiently provides high-quality and reliable educational content, enabling users to learn optimally. Furthermore, by combining a reward system based on frequency of use with an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators. For example, when a teacher uploads a lesson video about "Science Fundamentals" to the server, the server receives the video.

[1139] Step 2:

[1140] The server extracts metadata (title, description, target age, subject, etc.) from the received content and stores it in a database. For example, the title, description, target grade, and subject information of a lesson video can be saved in the database to make it easier to search.

[1141] Step 3:

[1142] The server stores the aggregated content files in physical storage or cloud storage and associates them with a database. For example, the server stores the video files themselves in cloud storage and registers their URLs in the database.

[1143] Step 4:

[1144] The server inputs the lesson content from the database into the generative AI model. For example, a "Science Fundamentals" video and its explanatory text are input into the generative AI model and analysis begins.

[1145] Step 5:

[1146] The generative AI model analyzes the input content and generates educational content optimized for the user, such as interactive problem-solving content to help an 8-year-old student understand basic science concepts, taking into account data such as the user's age, learning history, and interests.

[1147] Step 6:

[1148] The emotion engine uses the camera and microphone on the user's device to collect the user's facial expressions and voice in real time. For example, while the user is watching a video, the camera captures the user's facial expressions and the microphone analyzes the tone of the user's voice.

[1149] Step 7:

[1150] The emotion engine analyzes the collected data and determines the user's emotional state (happiness, confusion, interest, boredom, etc.) in real time. For example, if a user shows a confused expression while watching a video, that emotion will be recognized.

[1151] Step 8:

[1152] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they wish to study. For example, a user may select "Science Fundamentals" on a tablet.

[1153] Step 9:

[1154] The server retrieves educational content optimized by the generative AI model from the database in response to a user request, for example, searching for and retrieving "Science Basics for 8-Year-Olds" content from the database.

[1155] Step 10:

[1156] The server then transmits the acquired learning content to the user's device for display. For example, the server may transmit a video link or an interactive problem set to the user's device and display it on the device screen.

[1157] Step 11:

[1158] The server adjusts the difficulty and format of educational content in real time based on the emotion data sent by the emotion engine. For example, if the server detects the emotion of "confusion" while a user is watching a video, it will simplify the video content or provide additional explanations.

[1159] Step 12:

[1160] The device transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server in real time. For example, while the user is viewing a video and solving problems, the device transmits the user's progress to the server sequentially.

[1161] Step 13:

[1162] The server analyzes the acquired usage data and awards reward points to the user. For example, it analyzes the number of times the user views the page and the results of their responses, and calculates and awards reward points based on the results.

[1163] Step 14:

[1164] The server notifies the user of the reward point allocation result and records it in the user's account. For example, the server notifies the user that "50 points have been allocated" and records the information in the user's account.

[1165] This system can efficiently provide high-quality and reliable educational content, increasing users' motivation to learn. In addition, by using an emotion engine, it is possible to provide educational content that is more suited to user needs.

[1166] Example 2

[1167] 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."

[1168] In conventional educational systems, educational content is provided uniformly, making it difficult to provide an optimal learning experience for each individual user. Furthermore, there is a lack of mechanisms to maintain and improve motivation for learning, and the lack of dynamic content adjustment based on the user's progress and emotions is also an issue.

[1169] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for each user based on data input to the generative AI model, and a means for providing the generated educational content in response to access from the user's terminal. This makes it possible to provide educational content optimized for each user and maintain and improve their motivation to learn.

[1170] "Educators" refers to those responsible for providing educational content and experts.

[1171] "Class content" refers to educational materials provided by educators, including information assets such as videos, text, images, and web articles.

[1172] "Database" refers to a digital storage system for efficiently storing and managing aggregated course content and metadata.

[1173] "Generative AI model" refers to an artificial intelligence algorithm that analyzes input data and generates educational content optimized for individual users.

[1174] "User" refers to an individual who uses this system to study educational content.

[1175] "Terminal" means a device used by a user to access the system, including a PC, smartphone, tablet, etc.

[1176] "Emotional data" refers to information about a user's emotional state that is analyzed from the user's facial expressions, voice, character input, and the like.

[1177] "Reward points" refer to incentives awarded based on a user's learning progress and usage data.

[1178] "Analysis" refers to the process of processing data and extracting meaningful information and patterns.

[1179] "Real time" refers to a timing range in which events that occur are processed nearly simultaneously.

[1180] MODE FOR CARRYING OUT THE INVENTION

[1181] The present invention is a system that aggregates lesson content provided by educators and provides educational content optimized for individual students based on that content. Furthermore, by combining an emotion engine, the system dynamically generates and provides more appropriate content based on the user's emotion data. Specific embodiments of the system are described below.

[1182] Overall system overview

[1183] The system consists of four main components: a server, devices, users, and an emotion engine. Educators provide lesson content, which is aggregated on the server. The aggregated content is input into a generative AI model, which generates educational content optimized for the user. Users access the system using their devices and study the optimized educational content. Furthermore, the system not only analyzes users' educational content usage data and awards reward points, but also uses the emotion engine to analyze users' emotional data and adjust educational content in real time based on that data.

[1184] Consolidation of educational content

[1185] The server receives lesson content (videos, text, images, web articles, etc.) sent by educators and stores it in a database. For example, when a teacher uploads a lesson video on "Basics of Chemistry" to the server, the server stores the video in the database. At the same time, the server also extracts the lesson content's metadata (title, description, target age group, subject, etc.) and stores it in the database.

[1186] Optimization with generative AI models

[1187] The server inputs educational content from its database into a generative AI model. The generative AI model analyzes the input data and generates educational content tailored to each individual user. For example, for an 8-year-old student, it generates interactive problem-solving content to help them understand basic scientific concepts. This process takes into account data such as the user's age, learning history, and interests.

[1188] Emotion Engine Functions

[1189] The emotion engine analyzes emotional data in real time from the user's facial expressions, voice, and text input. For example, while the user is watching a video, a camera can analyze their facial expressions, and speech recognition can analyze their tone of voice. The analyzed emotional data is sent to a server, which then uses this data to adjust the difficulty and format of the educational content in real time. For example, if the server detects emotions like "boredom" or "confusion" while the user is watching a video, it can immediately issue instructions to simplify the video content or add interactive elements.

[1190] User Access and Learning

[1191] Users access the system using their own devices (PCs, smartphones, tablets, etc.) and select the subjects or topics they want to learn. For example, if a user selects to learn "Science Fundamentals" on a tablet, the device sends the request to the server, and the server generates and distributes the most appropriate educational content to the device.

[1192] Usage data analysis and reward system

[1193] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is viewing a basic science video and solving problems, the device transmits the user's progress in real time to the server. The server analyzes the acquired data and awards reward points to the user. The user is notified of the award results and the points are recorded in the user's account.

[1194] Specific examples of effects

[1195] For example, if an elementary school student selects "Science Fundamentals" on their tablet, the optimal content generated by the generative AI model will be displayed on the device. If the user uses the content 15 times in a week, their usage and emotional data will be analyzed and appropriate reward points will be automatically awarded. Furthermore, if the emotional engine detects "confusion" during learning, the system will immediately adjust the educational content by providing more detailed or concise explanations.

[1196] Prompt Sentence Examples

[1197] "An 8-year-old wants to learn the basics of science, so generate interactive educational content accordingly. Also, adjust the content in real time based on the user's emotional data as they learn."

[1198] As described above, this invention is a system that efficiently provides high-quality, reliable educational content and enables users to learn optimally. Furthermore, by combining a reward system and an emotion engine, it is possible to increase users' motivation to learn and further improve the quality of their learning.

[1199] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1200] Step 1: Collect and store educational content

[1201] The server receives lesson content (videos, text, images, web articles, etc.) provided by educators and stores it in a database. For example, when an educator uploads a lesson video on "Basics of Chemistry," the server receives the video. At the same time, the server also extracts and stores metadata such as the title, description, target age group, and subject. The input data is the lesson content and metadata, and the output data is the content and metadata stored in the database.

[1202] Step 2: Collect user data

[1203] While the user is using the system, the device collects data such as learning history, grades, and interests, and sends it to the server. For example, a user watches a lecture on "Science Fundamentals" and answers related questions. This causes the device to record the learning history and answers. The input data is the user's learning behavior, and the output data is the user data sent to the server.

[1204] Step 3: Generate and deliver educational content

[1205] The server inputs the educational content and user data from the database into a generative AI model to generate prompts. The generative AI model generates appropriate educational content based on the user's age, learning history, and interests. For example, an 8-year-old user would be provided with interactive problem-solving content on basic science. The server outputs the generated prompts and delivers them to the user's device upon request. The input data are educational content and user data, and the output data is optimized educational content.

[1206] Step 4: User interaction and data submission

[1207] Users access the system using their own devices (PC, smartphone, tablet, etc.) and select the subject or topic they want to learn. For example, a user may select "Science Fundamentals" using a tablet. The device sends the selection to the server, which then generates corresponding educational content and provides it to the device. The input data is the user's selection, and the output data is the corresponding educational content.

[1208] Step 5: Analyze emotional data and adjust educational content

[1209] The emotion engine analyzes the user's facial expressions, voice, and text input in real time to extract the user's emotional data. For example, while the user is watching a video, the camera analyzes the user's facial expressions and the voice recognition system extracts the tone of the user's voice. This emotional data is sent to the server, which then adjusts the difficulty and format of the educational content based on this data. The input data is the user's emotional data, and the output data is the adjusted educational content.

[1210] Step 6: Analyze usage data and award reward points

[1211] The device sequentially transmits the user's learning progress and usage data (viewing time, answer results, etc.) to the server. For example, while a user is watching a basic science video and answering questions, their progress is transmitted to the server in real time. The server aggregates and analyzes this data, and calculates and awards reward points to the user. The input data is the user's usage data, and the output data is the awarded reward points and a notification of the points.

[1212] (Application example 2)

[1213] 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."

[1214] Conventional educational content delivery systems provide fixed content without considering the user's individual emotional state, making it difficult to provide appropriate learning support based on the user's interests and level of understanding. Furthermore, optimization based solely on content usage data is unable to respond in real time, limiting the user experience. Furthermore, when applying education to customer support in brick-and-mortar stores, it is difficult to make optimal product recommendations based on customer emotion analysis.

[1215] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1216] In this invention, the server includes a means for aggregating lesson content provided by educators and storing it in a database, a means for generating educational content optimized for individual users based on data input into a generative AI model, a means for providing the generated educational content in response to access from the user's terminal, a means for analyzing the user's content usage data and awarding reward points, and a means for analyzing emotional data from the user's facial expressions and voice and adjusting the content in real time based on the analysis results. This enables real-time optimization of educational content according to the user's emotional state and improved customer support in physical stores.

[1217] "Educational content" refers to information about lesson content provided by educators, and includes formats such as videos, text, images, and web articles.

[1218] A "generative AI model" is an artificial intelligence model that uses aggregated educational content and user attribute information as input to generate educational content optimized for individual users.

[1219] "Emotion data" refers to data relating to the emotional state of the user that is acquired in real time from facial expressions, voice, and the like.

[1220] "User's device" refers to an electronic device used by a user to access the system and use educational content, including a PC, smartphone, tablet, etc.

[1221] "Usage data" refers to various data collected when a user uses educational content, including viewing time, answer results, learning progress, and the like.

[1222] "Reward points" are incentive points that are awarded based on the user's use of educational content and results.

[1223] "Real-time adjustment" refers to the process of instantly changing and adapting the content and difficulty of educational content provided based on the user's emotional data.

[1224] "Database" means an information system for efficiently storing and managing aggregated educational content and associated metadata.

[1225] "Facial expressions" are non-verbal cues that indicate a user's emotional state based on their facial movements and expressions.

[1226] "Voice" refers to data for analyzing the emotional state of a user from vocal characteristics such as tone and intonation.

[1227] MODE FOR CARRYING OUT THE INVENTION

[1228] The present invention provides a system for providing educational content and enhancing the learning effect of users. The configuration and operation of this system will be described below.

[1229] System configuration

[1230] 1. Server

[1231] Database: Stores lesson content (videos, text, images, web articles, etc.) provided by educators. Metadata is also stored.

[1232] Generative AI models: Generate optimized educational content based on input educational content and user attribute information. This includes natural language processing models such as BERT and recommendation systems.

[1233] Emotion engine: Analyzes emotion data from the user's facial expressions and voice in real time. Technologies used include OpenCV and Dlib.

[1234] 2. Terminal

[1235] A device (smartphone, smart glasses, tablet, PC, etc.) that allows a user to access the system. It is desirable that it is equipped with a camera and microphone.

[1236] Optimized educational content is provided by accessing the server from the terminal.

[1237] 3. Users

[1238] Students access the system and use the educational content provided, and their learning progress and emotional data are collected in real time.

[1239] How it works

[1240] Consolidation of educational content

[1241] The server aggregates lesson content provided by educators and stores it in a database. It also extracts and stores metadata about the content (title, description, target age group, subject, etc.).

[1242] Content Optimization

[1243] The server inputs the educational content stored in the database into a generative AI model to generate educational content optimized for each individual user, taking into account the user's age, learning history, interests, and emotional data.

[1244] Emotion data analysis and real-time adjustment

[1245] The server uses an emotion engine to analyze emotion data from the user's facial expressions and voice. For example, it uses OpenCV and Dlib to analyze the user's facial expressions and voice tone using speech recognition technology. Based on this, the difficulty level and format of the educational content can be adjusted in real time.

[1246] Usage data collection and reward system

[1247] The device sends the user's learning progress and usage data to the server. The server analyzes the collected data and awards reward points to the user. The results of the awarding of reward points are notified to the user and recorded in the user's account.

[1248] Specific examples

[1249] For example, if an elementary school student is learning "Science Fundamentals" on a tablet, the optimal content generated by the generative AI model will be displayed on the device. While the user is using the content, the camera analyzes their facial expressions and the microphone analyzes their voice to collect emotional data. If the emotion engine detects "confusion," the system immediately issues instructions to provide more detailed explanations of the educational content, resulting in content that is easier for the user to understand.

[1250] An example of a prompt might be:

[1251] While the user is wearing the smart glasses, explain the features of the product in front of them, analyze the customer's facial expressions and voice to see if they are interested, and determine if further explanation is needed, providing additional information in real time if necessary.

[1252] This invention is expected to highly optimize the user's learning experience and improve customer support in physical stores.

[1253] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1254] Step 1:

[1255] The server receives lesson content provided by educators and stores the content and metadata in a database. The input is the lesson content (videos, text, images, web articles) provided by educators, and the output is the content and metadata stored in the database. Data processing involves unifying the content format and extracting metadata (title, description, target age group, subject, etc.).

[1256] Step 2:

[1257] The server inputs educational content stored in the database into a generative AI model to generate educational content optimized for each individual user. The input is the educational content in the database and the user's attribute data (age, learning history, interests), and the output is optimized educational content. As a data calculation, the AI ​​model analyzes multiple attribute data and generates and optimizes educational content based on that data.

[1258] Step 3:

[1259] Users access the system using a terminal and select the subjects or topics they wish to study. The input is the user's selection information (subjects or topics), and the output is a request for optimized content based on the selected information. Specifically, users select subjects using a tablet or smartphone.

[1260] Step 4:

[1261] The emotion engine analyzes camera footage and audio data provided by the user's device to obtain emotional data in real time. The input is the user's facial expression and audio data, and the output is emotional data obtained in real time. Data processing involves facial recognition using OpenCV, facial expression analysis using Dlib, and voice recognition technology to analyze voice tone.

[1262] Step 5:

[1263] The server adjusts the difficulty and format of the optimized educational content in real time based on the emotional data. The input is the emotional data from the emotion engine, and the output is the adjusted educational content. As a data calculation, the emotional data is evaluated and, if necessary, re-input into the generative AI model to regenerate the content.

[1264] Step 6:

[1265] The device collects the user's learning progress and usage data and sends it to the server. The input is the user's learning usage data (viewing time, answer results, progress), and the output is the usage data sent to the server. Specifically, the device has a mechanism to periodically upload data to the server.

[1266] Step 7:

[1267] The server analyzes the user's usage data and awards reward points. The input is the collected usage data, and the output is the reward point award result. As a data calculation, the usage data is evaluated and reward points are calculated based on the pre-set conditions. The calculated points are recorded in the user's account and notified.

[1268] The above are the specific processing steps of this invention. By configuring the system in this way, it becomes possible to optimize educational content in real time according to the user's emotional state and improve customer support in physical stores.

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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.

[1275] 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).

[1276] 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.

[1277] 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."

[1278] 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.

[1279] 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).

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] 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.

[1290] The following is further disclosed regarding the above embodiment.

[1291] (Claim 1)

[1292] A means for aggregating lesson content provided by educators and storing it in a database;

[1293] A means for generating educational content optimized for individual users based on the data input into the generative AI model;

[1294] a means for providing the generated educational content in response to access from a user's terminal;

[1295] A means for analyzing content usage data of users and awarding reward points;

[1296] A system including:

[1297] (Claim 2)

[1298] 10. The system of claim 1, wherein the lesson content provided by the educator includes video, text, images, and web articles.

[1299] (Claim 3)

[1300] The system of claim 1, wherein the generative AI model optimizes educational content by taking into account data such as the user's age, learning history, and interests.

[1301] "Example 1"

[1302] (Claim 1)

[1303] A means for aggregating lesson content provided by educators and storing it in a database;

[1304] A means for generating educational content optimized for individual users based on the data input into the generative AI model;

[1305] a means for providing the generated educational content in response to access from a user's terminal;

[1306] A means for analyzing content usage data of users and awarding reward points;

[1307] A means for instructing the generative AI model to generate educational content based on a prompt sentence;

[1308] means for sequentially transmitting the user's learning progress;

[1309] A system including:

[1310] (Claim 2)

[1311] 10. The system of claim 1, wherein the lesson content provided by the educator includes video, text, images, and web articles.

[1312] (Claim 3)

[1313] The system of claim 1, wherein the generative AI model optimizes educational content by taking into account data such as the user's age, learning history, and interests.

[1314] "Application Example 1"

[1315] (Claim 1)

[1316] A means for aggregating lesson content provided by educators and storing it in a database;

[1317] A means for generating educational content optimized for individual users based on the data input into the generative AI model;

[1318] a means for providing the generated educational content in response to access from a user's terminal;

[1319] A means for analyzing content usage data of users and awarding reward points;

[1320] A means for detecting a user's location in a physical store in real time and providing optimal educational content based on the detected location;

[1321] A system including:

[1322] (Claim 2)

[1323] 10. The system of claim 1, wherein the lesson content provided by the educator includes video, text, images, and web articles.

[1324] (Claim 3)

[1325] The system of claim 1, wherein the generative AI model optimizes educational content by taking into account data such as the user's age, learning history, and interests.

[1326] "Example 2: Combining Emotion Engines"

[1327] (Claim 1)

[1328] A means for aggregating lesson content provided by educators and storing it in a database;

[1329] A means for generating educational content optimized for individual users based on the data input into the generative AI model;

[1330] a means for providing the generated educational content in response to access from a user's terminal;

[1331] A means for analyzing user emotional data and adjusting educational content in real time;

[1332] A means for analyzing content usage data of users and awarding reward points;

[1333] A system including:

[1334] (Claim 2)

[1335] 10. The system of claim 1, wherein the lesson content provided by the educator includes video, text, images, and web articles.

[1336] (Claim 3)

[1337] The system of claim 1, wherein the generative AI model optimizes educational content by taking into account data such as the user's age, learning history, and interests.

[1338] "Application example 2 when combining emotion engines"

[1339] (Claim 1)

[1340] A means for aggregating lesson content provided by educators and storing it in a database;

[1341] A means for generating educational content optimized for individual users based on the data input into the generative AI model;

[1342] a means for providing the generated educational content in response to access from a user's terminal;

[1343] A means for analyzing content usage data of users and awarding reward points;

[1344] A means for analyzing emotional data from a user's facial expressions and voice and adjusting content in real time based on the analysis results;

[1345] A system including:

[1346] (Claim 2)

[1347] 10. The system of claim 1, wherein the lesson content provided by the educator includes video, text, images, and web articles.

[1348] (Claim 3)

[1349] 10. The system of claim 1, wherein the generative AI model optimizes educational content by taking into account the user's age, learning history, interests, and emotional data. [Explanation of symbols]

[1350] 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 aggregating lesson content provided by educators and storing it in a database; A means for generating educational content optimized for individual users based on the data input into the generative AI model; a means for providing the generated educational content in response to access from a user's terminal; A means for analyzing content usage data of users and awarding reward points; A system including:

2. The system of claim 1 , wherein the lesson content provided by the educator includes video, text, images, and web articles.

3. The system of claim 1, wherein the generative AI model optimizes educational content by taking into account data such as the user's age, learning history, and interests.

Images