System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving and storing registration information of a user in a database; means for providing an initial evaluation test for analyzing a learning style and a literacy level of the user; means for generating a personalized learning module according to the learning style of the user based on a result of the initial evaluation test; means for providing the generated learning module to a terminal of the user and presenting learning contents; and means for tracking a learning progress situation of the user and generating a next learning module based thereon.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] Conventional literacy education systems often have uniform educational curricula that make it difficult to accommodate the progress and learning styles of individual learners. As a result, they are unable to adapt to the needs of diverse learners, and are unable to provide effective education, particularly to regions and learners where literacy improvement is required. Furthermore, large-scale educational programs are costly and time-consuming, making them difficult to implement. The purpose of this invention is to solve these problems and provide effective and efficient literacy education. [Means for solving the problem]

[0005] The present invention includes a means for receiving user registration information and storing it in a database, a means for providing an initial assessment test to analyze the user's learning style and literacy level, a means for generating a personalized learning module based on the results of the initial assessment test, a means for providing the generated learning module to the user's device and presenting learning content, and a means for tracking the user's learning progress and generating the next learning module based on the results. The system also includes a means for generating multi-sensory content and providing it to the user in providing the initial assessment test and learning module. The generated learning module further includes a means for using a generation AI to convert the content into simple blocks based on the user's literacy level. This provides an optimal learning experience for each learner, realizing a system that supports literacy improvement.

[0006] "User" refers to an individual who uses the system to receive literacy education.

[0007] "Registration Information" refers to basic data such as name, email address, and password that a User provides when first accessing the System.

[0008] "Database" refers to the storage system that stores registration information and learning data and makes them accessible to various functions of the system.

[0009] "Initial Assessment Test" refers to a test provided to assess a user's current literacy level and learning style.

[0010] "Learning style" refers to a tendency that indicates how a user learns most effectively (e.g., visual, auditory, etc.).

[0011] "Literacy level" refers to a user's current level of literacy.

[0012] "Personalized Learning Modules" refers to educational content that is specifically created based on a user's learning style and literacy level.

[0013] "Terminal" refers to the device (e.g., smartphone, tablet, PC, etc.) used by a user to access the system.

[0014] "Learning Module" refers to educational content that includes learning material and exercises.

[0015] "Study progress" refers to information indicating how far a user has progressed in their studies.

[0016] "Multisensory content" refers to educational content that supports learning by utilizing multiple senses, such as sight and hearing.

[0017] "Generative AI" refers to artificial intelligence that generates learning modules based on user data and converts complex concepts into simple blocks. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention is a system that supports users in improving their literacy skills by providing personalized learning modules using generative AI. This system operates as follows.

[0040] User Registration

[0041] First, the user downloads the system's application onto a device such as a smartphone or tablet. When the user launches the application and enters registration information such as name, email address, and password, the device sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[0042] Initial assessment and learning style analysis

[0043] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are saved on the server, and the user's learning profile is updated.

[0044] Generate learning modules

[0045] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks. This learning module is then sent from the server to the device and presented to the user.

[0046] Delivering learning modules and tracking progress

[0047] A user starts a learning module displayed on the device. The device sequentially displays the content within the module (readings, quizzes, etc.) and records the user's progress in real time. When the user finishes the module, the device sends the progress data to the server. The server tracks the user's progress and adaptively adjusts the next learning module to be presented.

[0048] Providing multi-sensory learning modules

[0049] Furthermore, to enhance users' learning, the server generates multi-sensory content, for example, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and promoting comprehension and retention.

[0050] Specific examples

[0051] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it, stores it in a database, and creates a user profile. The user then takes an initial assessment test. After completing the test, the device sends the results in real time to the server, which uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at the beginner level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues learning using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[0052] This system configuration enables effective and efficient literacy education tailored to each user, supporting the improvement of literacy skills.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user downloads the application to their smartphone or tablet and launches it.

[0056] Step 2:

[0057] The user enters registration information such as name, email address, and password.

[0058] Step 3:

[0059] The device sends the user's registration information in JSON format to the server.

[0060] Step 4:

[0061] The server stores the received registration information in a database and generates a profile for the new user.

[0062] Step 5:

[0063] The server sends a profile creation success message to the terminal.

[0064] Step 6:

[0065] The terminal displays a message to the user indicating that registration is complete.

[0066] Step 7:

[0067] The user taps the "Start Initial Evaluation Test" button within the app.

[0068] Step 8:

[0069] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[0070] Step 9:

[0071] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[0072] Step 10:

[0073] The terminal transmits the response data to the server in real time.

[0074] Step 11:

[0075] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[0076] Step 12:

[0077] The server stores the analysis results in a database and updates the user's learning profile.

[0078] Step 13:

[0079] The server generates personalized learning modules based on the user's learning style and literacy level.

[0080] Step 14:

[0081] The server sends the generated learning module in JSON format to the terminal.

[0082] Step 15:

[0083] The terminal organizes the received learning modules and displays them to the user.

[0084] Step 16:

[0085] The user taps the displayed button to start the learning module.

[0086] Step 17:

[0087] The terminal sequentially presents the learning modules to the user and records the progress locally.

[0088] Step 18:

[0089] The user completes each piece of content (e.g., reading material, quiz) in sequence.

[0090] Step 19:

[0091] The terminal sends the progress data of the learning module to the server in batches.

[0092] Step 20:

[0093] The server analyzes the received progress data and tracks the user's learning progress.

[0094] Step 21:

[0095] If the server needs to generate a new learning module, it uses the generation AI again to prepare the next module and send it to the terminal.

[0096] Step 22:

[0097] A server generates multi-sensory content and transmits it to a terminal.

[0098] Step 23:

[0099] The terminal provides multi-sensory content to the user.

[0100] Step 24:

[0101] The user learns by using the presented multi-sensory content.

[0102] Step 25:

[0103] The device records the user's reactions and usage status and sends them to the server.

[0104] Step 26:

[0105] The server analyzes this data and evaluates the user's learning effectiveness.

[0106] Example 1

[0107] 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."

[0108] Conventional educational systems provide uniform learning content, making it difficult to adapt to the learning styles and literacy levels of individual users. This reduces learning effectiveness and hinders efficient literacy improvement. Another problem is the lack of a mechanism for tracking learning progress in real time and providing adaptive learning modules.

[0109] 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.

[0110] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style and literacy level using a generative AI model based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling effective and efficient literacy education that is personalized to the user.

[0111] "User" refers to an individual who uses the system to learn.

[0112] "Registration Information" refers to basic information such as name, email address, and password provided by a User to use the System.

[0113] "Database" refers to a data storage system for storing and managing data such as user registration information and learning status.

[0114] "Initial Assessment Test" refers to a test provided to analyze a user's learning style and literacy level.

[0115] "Learning style" refers to the characteristics of a user's learning method for effectively understanding information, and includes, for example, visual and auditory learning.

[0116] "Literacy level" refers to an indicator that shows the current state of a user's reading and writing ability.

[0117] A "generative AI model" refers to an artificial intelligence model that generates learning content appropriate for users, using AI technology that performs natural language processing, for example.

[0118] A "learning module" refers to a set of learning materials or content that allows a user to study.

[0119] "Terminal" refers to a device, such as a smartphone or tablet, that a user uses to access the system.

[0120] "Progress" refers to the user's achievement and performance as they progress through their studies.

[0121] "Multisensory content" refers to teaching materials and content that enhance learning by using multiple senses, such as sight and hearing.

[0122] The present invention provides a system for supporting users in improving their literacy skills by providing personalized learning modules using a generative AI model. Specific embodiments of the system are described in detail below.

[0123] User Registration

[0124] First, the user must download and install a dedicated application on their device, such as a smartphone or tablet. The user launches the app and enters registration information such as their name, email address, and password. This information is then sent from the device to the server. The server then stores the received data in a database (e.g., PostgreSQL) and creates a new user profile. During this process, the device sends data to the server's API endpoint using an HTTP POST request.

[0125] Initial assessment and learning style analysis

[0126] Once user registration is complete, the next step is to take an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the answer data is sent from the device to the server. Based on the received data, the server uses an AI model (e.g., TensorFlow) to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[0127] Generate learning modules

[0128] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate a personalized learning module suited to the user. The generated learning module is sent to the device and presented to the user. In this case, the server converts complex concepts into simple blocks.

[0129] Delivering learning modules and tracking progress

[0130] A user starts a learning module on their device and checks the content within the module (readings, quizzes, etc.) one by one. The device records the user's progress in real time and sends the data to the server each time the module is completed. The server tracks the progress data and adaptively adjusts and generates the next learning module to be provided based on this data.

[0131] Providing multi-sensory learning modules

[0132] To improve the user's learning effectiveness, the server generates multi-sensory content, such as illustrated learning materials for visual learners and audio learning materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, which is expected to improve understanding and memory.

[0133] Specific examples

[0134] For example, a user downloads a new app and enters information such as their name, email address, and password, which is then sent to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and once the user completes the test, the device sends the results to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at an elementary level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues to study using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[0135] Prompt Sentence Examples

[0136] "User registration: The user downloads the app and registers by entering the required information."

[0137] "Initial evaluation test: The user answers the initial evaluation test and sends the results to the server."

[0138] "Learning module generation: The server uses an AI model to analyze the user's learning style and literacy level, generate the optimal learning module, and send it to the device."

[0139] "Progress tracking: When a user completes a learning module, the device sends progress data to the server, which then coordinates and generates the next module."

[0140] This invention enables effective and efficient literacy education tailored to the user, and can support the improvement of literacy.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1: User Registration

[0143] 1. The user downloads and installs the application on their smartphone or tablet.

[0144] 2. The user launches the app and enters registration information such as name, email address, and password.

[0145] 3. The device temporarily saves the entered registration information.

[0146] 4. The device sends the entered information to the server as an HTTP POST request.

[0147] Input: User's name, email address, and password

[0148] Data processing: Convert information into JSON format

[0149] Output: Registration information sent to the server

[0150] 5. The server verifies the received data.

[0151] Input: Received registration information

[0152] Data calculation: Email address format verification, password strength check

[0153] Output: Verification result (pass or error)

[0154] 6. If the verification is successful, the server stores the user information in a database and creates a user profile.

[0155] 7. The server returns a registration success response to the terminal.

[0156] Step 2: Provide initial evaluation testing

[0157] 1. After registering, the user clicks on the link to take the initial evaluation test.

[0158] 2. The terminal sends a request for an initial evaluation test to the server.

[0159] Input: User ID

[0160] Data Processing: Request Creation

[0161] Output: The request sent to the server

[0162] 3. The server retrieves the initial evaluation test questions from the database and sends them to the terminal.

[0163] Input: User ID

[0164] Data arithmetic: Selecting appropriate test questions

[0165] Output: Assessment questions sent to the device

[0166] 4. The terminal displays the received assessment test questions.

[0167] 5. The user answers each question in the assessment test.

[0168] Step 3: Submitting assessment data and learning style analysis

[0169] 1. When the user finishes the test, the device temporarily stores the answer data and sends it to the server.

[0170] Input: User response data

[0171] Data processing: Compiling response data

[0172] Output: Response data sent to the server

[0173] 2. The server analyzes the received evaluation data using an AI model.

[0174] Input: Evaluation data

[0175] Data Computing: Analyzing Learning Styles and Literacy Levels Using AI Models

[0176] Output: Analysis results (learning style, literacy level)

[0177] 3. The server stores the analysis results in a database and updates the user's learning profile.

[0178] Step 4: Generate and deliver learning modules

[0179] 1. The server uses a generative AI model to generate learning modules appropriate for the user's learning style and literacy level.

[0180] Input: User's learning profile

[0181] Data Computation: Generating Learning Modules

[0182] Output: The generated learning module

[0183] 2. The server sends the generated learning module to the terminal.

[0184] 3. The terminal displays the received learning module on the user interface.

[0185] 4. The user begins the learning module.

[0186] Step 5: Track your progress and generate the next module

[0187] 1. The device records the user's progress in the learning module in real time.

[0188] Input: User action data

[0189] Data processing: generating progress data

[0190] Output: Progress data

[0191] 2. When the user finishes the learning module, the device sends progress data to the server.

[0192] 3. The server analyzes the received progress data and adaptively adjusts the learning module to be provided next.

[0193] Input: Progress data

[0194] Data calculation: Adjusting the next learning module

[0195] Output: Adjusted learning module

[0196] 4. The server generates a new learning module and sends it to the terminal again.

[0197] Step 6: Creating and delivering multisensory learning modules

[0198] 1. The server generates multi-sensory content according to the user's learning style.

[0199] Input: User's learning profile

[0200] Data Computing: Creating visual and auditory content

[0201] Output: Multisensory learning content

[0202] 2. The server transmits the generated multi-sensory content to the terminal.

[0203] 3. The device displays the multisensory content in the user interface.

[0204] 4. Users learn using multiple senses.

[0205] (Application example 1)

[0206] 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."

[0207] Traditional literacy systems struggle to effectively provide personalized learning experiences tailored to users' learning styles and literacy levels. Furthermore, materials that rely on a single sense often result in inefficient comprehension and retention. Furthermore, they lack the ability to track progress and adjust the generated learning modules accordingly.

[0208] 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.

[0209] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on the progress, means for generating a learning module based on the user's profile using a generative AI, means for generating multi-sensory content and providing learning materials according to the user's learning style, means for the generated learning module to use a generative AI model that converts content into simple blocks according to the user's literacy level, and means for updating the user's learning profile, thereby providing the user with an optimal learning experience and enabling efficient improvement of literacy.

[0210] "User registration information" refers to information used to identify a user and register them in the system, such as the user's name, email address, and password.

[0211] A "database" is a system that stores data such as user registration information and progress status, and makes it accessible as needed.

[0212] An "initial assessment test" is a test conducted to analyze a user's learning style and current literacy level.

[0213] "Learning style" refers to the way in which a user learns most effectively, and can be visual, auditory, tactile, or other.

[0214] "Literacy level" is an indicator of a user's level of reading ability and comprehension.

[0215] "Personalized Learning Modules" are learning content specifically designed to fit a user's learning style and literacy level.

[0216] "Generative AI" is an artificial intelligence technology that generates new content based on initial input data.

[0217] "Presenting learning content" means displaying learning materials and questions in a form that is accessible to the user.

[0218] "Learning progress" is data that indicates how much of a learning module a user has completed and how much they have learned.

[0219] "Multisensory content" is content that supports learning by utilizing multiple senses, such as sight, hearing, and touch.

[0220] A "generative AI model" is an AI algorithm that generates personalized learning modules based on a user's learning style and literacy level.

[0221] A "learning profile" is comprehensive information that includes a user's learning style, literacy level, progress, and so on.

[0222] A "terminal" is a device such as a smartphone or tablet that a user uses to access a learning module and progress through their learning.

[0223] The present invention is a system for supporting user literacy improvement by providing personalized learning modules using generative AI. The system includes means for receiving user registration information and storing it in a database, means for conducting an initial assessment test, means for generating and providing personalized learning modules based on learning style and literacy level using a generative AI model, means for generating multi-sensory content, and means for tracking the user's learning progress and generating the next learning module.

[0224] Hardware and Software Configuration

[0225] The system is implemented using the following main hardware and software:

[0226] 1. Server:

[0227] Database: Used to store user registration information, initial assessment results, learning progress data, etc.

[0228] Generative AI model: An AI algorithm that generates learning modules based on user profile information. Specifically, GPT-2 or similar generative AI models are used.

[0229] Flask framework: Acts as an application server, managing the reception of data from users and the provision of learning modules.

[0230] 2. Terminal:

[0231] Smartphones and tablets: Devices used by users to download learning modules and progress through their studies. These devices communicate with the server to send and receive data.

[0232] Data processing flow

[0233] 1. User Registration:

[0234] When a user enters registration information such as name, email address, and password, the device sends this information to the server, which stores the received data in a database and creates a profile for the new user.

[0235] 2. Initial assessment and learning style analysis:

[0236] To take an initial assessment test, the device retrieves the assessment questions from the server and displays them to the user. After the user enters their answers, the device sends the answers to the server. The server uses an AI model to analyze this data and determine the user's learning style (e.g., visual, auditory, etc.) and current literacy level.

[0237] 3. Generate learning modules:

[0238] Based on the initial assessment results, the server generates personalized learning modules suited to the user's learning style. Using a generative AI model, it converts complex concepts into simple blocks to generate learning materials and sends them to the device.

[0239] 4. Delivering learning modules and tracking progress:

[0240] The user starts and progresses through the learning modules displayed on the device. The device records the user's progress in real time and sends the completed data to the server. The server then adaptively adjusts the next learning module to be provided based on the progress data.

[0241] 5. Providing multi-sensory learning modules:

[0242] To improve the learning effect of users, the server generates learning content that utilizes multiple senses, such as sight and hearing. For example, it provides learning materials with illustrations for visual learners and audio reading materials for auditory learners.

[0243] Specific examples

[0244] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and based on the results, is determined to be a visual learner with an elementary literacy level. The server then generates learning materials with simple grammar rules and illustrations appropriate for the user and sends them to the device. As the user progresses with their learning, progress data is sent to the server, which then adaptively generates the next learning module.

[0245] Prompt Sentence Examples

[0246] "Create learning modules for visual learners with beginner literacy levels."

[0247] This process provides users with a personalized and optimal learning experience, which is expected to improve their literacy skills.

[0248] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0249] Step 1:

[0250] A user downloads the application and enters their registration information, such as their name, email address, and password, which the device sends to the server. The server receives the information and stores it in a database. The output is a user profile.

[0251] Step 2:

[0252] The user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user enters their answers, the entered data is sent from the device to the server. Based on the received data, the server uses an AI model to analyze the user's learning style and literacy level. The analysis results are stored in a database and the user's profile is updated as an output.

[0253] Step 3:

[0254] Based on the initial evaluation results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model to generate prompt sentences and creates learning materials based on them. This learning module is then sent from the server to the device. As an output, a learning module tailored to the user's characteristics, such as visual or auditory, is generated.

[0255] Step 4:

[0256] The user starts a learning module displayed on the device and proceeds with their learning. The device sequentially displays the content (readings, quizzes, etc.) within the learning module. As the user proceeds with their learning, their progress is recorded in real time. Based on the input data, the device sends progress data to the server, which tracks their learning progress.

[0257] Step 5:

[0258] The server adjusts and generates the next learning module based on the user's progress data. By analyzing the progress data and adaptively adjusting the next learning module to be provided, the server maximizes the user's learning effect. As an output, the next learning module according to the user's progress is generated and sent to the device.

[0259] Step 6:

[0260] The server generates multisensory content to enhance learning outcomes. Specifically, it provides illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. This involves using a generative AI model to generate appropriate content from prompts. As an output, a multisensory learning module is generated and sent to the device.

[0261] Step 7:

[0262] The results of the user's completed learning module are sent to the server, and the database is updated. The user's learning profile is always updated to the latest version, and this is reflected in the generation of subsequent learning modules. This ensures that optimal learning content is provided to the user without interruption. The learning progress data is updated as an output.

[0263] 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.

[0264] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust learning content according to the user's emotions. This system operates as follows.

[0265] User Registration

[0266] First, a user downloads the system's application onto a device such as a smartphone or tablet and launches it. When creating an account, the user enters registration information such as name, email address, and password. The device then sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[0267] Initial assessment and learning style analysis

[0268] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[0269] Creating and delivering learning modules

[0270] Based on the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level, using generative AI to convert complex concepts into simple blocks, which are then sent from the server to the device and presented to the user.

[0271] Introducing the Emotion Engine

[0272] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and voice to recognize their current emotions (e.g., joy, confusion, fatigue, etc.).

[0273] Dynamic content adjustment based on user emotions

[0274] The recognized emotion data is sent from the device to a server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be reduced or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[0275] Track your learning progress and provide next steps

[0276] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[0277] Providing multi-sensory learning modules

[0278] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[0279] Specific examples

[0280] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[0281] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[0282] The system provides users with a personalized and dynamic learning experience to support literacy development.

[0283] The processing flow will be explained below.

[0284] Step 1:

[0285] A user downloads the application onto a device such as a smartphone or tablet and launches it.

[0286] Step 2:

[0287] The user enters registration information such as name, email address, and password.

[0288] Step 3:

[0289] The device sends the user's registration information in JSON format to the server.

[0290] Step 4:

[0291] The server stores the received registration information in a database and generates a profile for the new user.

[0292] Step 5:

[0293] The server sends a profile creation success message to the terminal.

[0294] Step 6:

[0295] The terminal displays a message to the user indicating that registration is complete.

[0296] Step 7:

[0297] The user taps the "Start Initial Evaluation Test" button within the app.

[0298] Step 8:

[0299] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[0300] Step 9:

[0301] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[0302] Step 10:

[0303] The terminal transmits the response data to the server in real time.

[0304] Step 11:

[0305] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[0306] Step 12:

[0307] The server stores the analysis results in a database and updates the user's learning profile.

[0308] Step 13:

[0309] The server generates personalized learning modules based on the user's learning style and literacy level.

[0310] Step 14:

[0311] The server sends the generated learning module in JSON format to the terminal.

[0312] Step 15:

[0313] The terminal organizes the received learning modules and displays them to the user.

[0314] Step 16:

[0315] The user taps the displayed button to start the learning module.

[0316] Step 17:

[0317] The terminal sequentially presents the learning modules to the user and records the progress locally.

[0318] Step 18:

[0319] The emotion engine analyzes the user's facial expressions and voice in real time while using the learning module and generates emotion data.

[0320] Step 19:

[0321] The terminal transmits the emotion data to the server.

[0322] Step 20:

[0323] The server analyzes the received emotion data and dynamically adjusts the learning content based on the user's emotion.

[0324] Step 21:

[0325] The user completes each piece of content (e.g., reading material, quizzes) in the learning module in sequence.

[0326] Step 22:

[0327] The terminal sends the progress data of the learning module to the server in batches.

[0328] Step 23:

[0329] The server stores the received progress data and emotion data in a database to track the user's learning status.

[0330] Step 24:

[0331] If the server needs to generate a new learning module, it uses the generation AI again to generate the next module and sends it to the terminal.

[0332] Step 25:

[0333] The server generates multi-sensory content (e.g., illustrated learning materials for visual learners, audio reading materials for auditory learners) and transmits it to the terminal.

[0334] Step 26:

[0335] The terminal provides multi-sensory content to the user.

[0336] Step 27:

[0337] Users engage in interactive learning through multi-sensory content.

[0338] Step 28:

[0339] The device records the user's reactions and usage status and sends them to the server.

[0340] Step 29:

[0341] The server analyzes this data and evaluates the user's learning effectiveness.

[0342] Example 2

[0343] 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."

[0344] Conventional literacy education systems often provide uniform learning content because they are unable to fully reflect the learning styles and emotional states of individual learners. This can lead to differences in learner comprehension and proficiency, making efficient learning difficult. Furthermore, conventional systems struggle to dynamically adjust learning content based on real-time emotional analysis, making it difficult to maintain learner motivation.

[0345] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0346] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module based on the results of the initial assessment test in accordance with the user's learning style, means for providing the generated learning module to the user's terminal and presenting learning content, means for recognizing the user's emotions in real time and transmitting the emotion data to the server, means for dynamically adjusting the learning content based on the emotion data, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling a personalized learning experience and dynamic adjustment of the learning content based on real-time emotion analysis.

[0347] "User" refers to an individual who uses the system to perform learning activities.

[0348] "Registration Information" refers to basic personal information such as name, email address, and password that a User provides when first accessing the System.

[0349] "Database" refers to data storage within the System for storing user registration information, learning profiles, progress data, emotional data, etc.

[0350] "Initial Assessment Test" refers to a series of questions or tasks provided by the system to assess a user's learning style and literacy level.

[0351] "Learning style" refers to the method or technique (e.g., visual, auditory, etc.) that a user uses to learn most effectively.

[0352] "Literacy level" refers to the result of assessing the user's current literacy skills, such as reading and writing ability and vocabulary.

[0353] "Learning Module" refers to system-generated learning materials and activities that are customized to a user's learning style and literacy level.

[0354] "Generative AI" refers to a system component that automatically generates content for learning modules using machine learning models and artificial intelligence techniques.

[0355] An "emotion engine" refers to software or algorithms that analyze a user's real-time facial expressions and voice to recognize their emotional state.

[0356] "Emotion data" refers to information indicating the user's emotional state (e.g., joy, confusion, fatigue, etc.) recognized by the emotion engine.

[0357] "Progress" refers to data indicating how far a user has progressed through a learning module.

[0358] This invention is a literacy education system that combines a generative AI model and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system consists of three main components: a server, a terminal, and a user.

[0359] User Registration

[0360] A user downloads and launches the system application onto a device such as a smartphone or tablet. The user enters registration information such as name, email address, and password. The device sends this information to the server, which stores the received data in a database. A new user profile is created and registration is complete.

[0361] Initial assessment and learning style analysis

[0362] After completing user registration, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. The server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level, and stores the results in a database.

[0363] Creating and delivering learning modules

[0364] Based on the results of the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks, and the learning module is then sent from the server to the device. The user progresses through the learning module.

[0365] Introducing the Emotion Engine

[0366] While using the learning module, an emotion engine runs on the device to recognize the user's emotions in real time. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions (e.g., joy, confusion, fatigue, etc.). Emotion data is sent from the device to the server.

[0367] Dynamic content adjustment based on user emotions

[0368] The server dynamically adjusts learning content based on the recognized emotion data. For example, if the user is confused, it may reduce the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it may provide more challenging content, optimizing the user's learning experience.

[0369] Track your learning progress and provide next steps

[0370] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next module to be provided. This data is stored in a database and is also used to analyze long-term learning patterns.

[0371] Providing multi-sensory learning modules

[0372] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[0373] Specific examples

[0374] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level, and determines that they are a visual learner and their literacy level is beginner. Based on this, the server generates learning materials with simple illustrations of grammar rules and sends them to the device.

[0375] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[0376] Prompt Sentence Examples

[0377] Please list the information required for new user registration.

[0378] "Please provide an example of an initial assessment test to analyze users' learning styles."

[0379] "Please explain the types of emotions the emotion engine can recognize."

[0380] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0381] Step 1: User Registration

[0382] A user downloads and launches the system application on a device such as a smartphone or tablet. After the user enters registration information such as name, email address, and password, the device sends this information to the server as a JSON-formatted object. The server verifies the received data and stores it in a database. It then generates a new user profile and sends a registration completion notification to the device. The input of this step is the user's basic information, and the output is the user's profile data stored in the database.

[0383] Step 2: Initial assessment and learning style analysis

[0384] Once user registration is complete, the device retrieves assessment test questions from the server to present the user with an initial assessment test. When the user answers the test questions, the device sends the answer data in JSON format to the server. The server uses an AI model (e.g., TensorFlow or PyTorch) to analyze the user's learning style and literacy level based on the answer data. The analysis results are stored in a database, and the user's learning profile is updated. The input of this step is the user's answer data, and the output is the analysis results of the learning style and literacy level.

[0385] Step 3: Generate and deliver learning modules

[0386] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to convert concepts into simple blocks. The generated learning module is sent from the server to the device in HTML or Markdown format and presented to the user. The input of this step is the analysis results of the learning style and literacy level, and the output is a personalized learning module.

[0387] Step 4: Implementing the Emotion Engine

[0388] While the learning module is in use, an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) runs on the device to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize their current emotion (e.g., joy, confusion, fatigue, etc.). The recognized emotion data is sent to the server in JSON format. The input of this step is the user's facial expression and voice data, and the output is the recognized emotion data.

[0389] Step 5: Dynamically adjust content based on user sentiment

[0390] Based on the recognized emotion data, the server dynamically adjusts the learning content. For example, if the user is confused, the server may lower the difficulty of the learning material or generate additional explanations and send them to the device. Conversely, if the user is satisfied, the server may adjust the content to provide more challenging content. The input of this step is emotion data, and the output is an adjusted learning module.

[0391] Step 6: Track learning progress and provide next steps

[0392] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts and generates the next learning module to provide. The progress data includes the completion status and correct answer rate for each learning module. This data is sent to the server in JSON format and stored in a database. The input of this step is the learning progress data and emotion data, and the output is the next learning module.

[0393] Step 7: Provide multisensory learning modules

[0394] The server generates multisensory content (visual, auditory, etc.) and sends it to the device. Specifically, it uses image processing libraries (e.g., Pillow or OpenCV) and speech synthesis software (e.g., Google Text-to-Speech API) to provide illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. The generated content is sent from the server to the device in file format (e.g., JPEG, MP3). The input of this step is the user's learning style data, and the output is a multisensory learning module.

[0395] (Application example 2)

[0396] 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."

[0397] While conventional literacy education systems can provide personalized learning modules tailored to a user's learning style and literacy level, they lack the ability to dynamically adjust learning content based on the user's emotions. This makes it difficult to maintain the user's interest and concentration, limiting the effectiveness of learning. In particular, systems that can respond to changing user emotions in real time are needed for the education and training of store clerks in brick-and-mortar stores.

[0398] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module tailored to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on this, and means for recognizing the user's emotions in real time and dynamically adjusting the learning content based on the emotion data. This enables the learning content to be adapted based on the user's emotions, providing an effective learning experience, particularly in the education and training of store clerks in physical stores.

[0399] "User registration information" refers to a user's personal information and basic profile information in the system, including name, email address, password, etc.

[0400] A "database" is a digital storage system that stores registered user information, learning progress, emotional data, etc., and retrieves and references them as needed.

[0401] An "initial assessment test" is an assessment test conducted to measure a user's learning style and current literacy level or learning ability.

[0402] "Learning style" refers to the way in which a user most effectively absorbs information during learning, and includes visual, auditory, tactile, and other styles.

[0403] "Literacy level" is an indicator of a user's level of ability to understand, read, and write a language.

[0404] A "personalized learning module" is a collection of learning materials and content optimized for each user's learning style and literacy level based on the results of an initial assessment test.

[0405] "Means for presenting learning content" refers to a method or device for providing the created learning module to the user's terminal and displaying and playing it.

[0406] "Study progress" is data that indicates the results and level of achievement achieved by the user through their learning activities.

[0407] "Dynamic adjustment" refers to optimizing and changing learning content on an ongoing basis based on data obtained in real time.

[0408] The "emotion engine" is a system that recognizes emotions in real time by analyzing the user's facial expressions and voice.

[0409] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system is particularly effective in educating and training store staff in brick-and-mortar stores.

[0410] System Configuration

[0411] The system consists of the following main components:

[0412] 1. Server

[0413] 2. Devices (smartphones, tablets)

[0414] 3. Emotion Engine

[0415] 4. Generative AI Models

[0416] User Registration

[0417] First, a user downloads the system's application onto their smartphone or tablet. Then, they launch the application and enter their registration information, such as their name, email address, and password. This information is sent from the device to the server and stored in a database. The server then creates a profile for the new user.

[0418] Initial assessment and learning style analysis

[0419] Once user registration is complete, the user takes an initial assessment test. This test is conducted to analyze the user's learning style and literacy level. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the data is sent from the device to the server. The server uses an AI model based on this data to analyze the user's learning style and literacy level, and stores the results in a database.

[0420] Creating and delivering learning modules

[0421] Based on the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Using a generative AI model, complex concepts are transformed into simple blocks, and this learning module is sent from the server to the device and presented to the user.

[0422] Introducing the Emotion Engine

[0423] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time. Specifically, it uses a camera to analyze the user's facial expressions and voice to recognize emotions (e.g., joy, confusion, fatigue, etc.). This is done using software such as Keras and OpenCV.

[0424] Dynamic content adjustment based on user emotions

[0425] The emotion data recognized by the emotion engine is sent from the device to the server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be lowered or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[0426] Track your learning progress and provide next steps

[0427] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[0428] Providing multi-sensory learning modules

[0429] In addition, the server generates and transmits multi-sensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, to the device, allowing users to learn using multiple senses and promoting comprehension and memorization.

[0430] Specific examples

[0431] For example, a user downloads a new application, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[0432] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device.

[0433] Prompt Sentence Examples

[0434] “Deviate a system where an emotion engine can sense when a store clerk is confused, and the learning difficulty or additional explanations are adjusted based on that emotion data.

[0435] Input data: face image, recognized emotion data, user ID

[0436] Output data: Type of learning module (difficulty adjustment, additional learning materials)

[0437] Libraries used: Keras, OpenCV, requests

[0438] This system provides a personalized and dynamic learning experience tailored to the user, effectively supporting sales associate training in brick-and-mortar stores.

[0439] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0440] Step 1: Enter and save your user registration information

[0441] The user downloads the application onto their smartphone or tablet and launches it. The user enters registration information such as their name, email address, and password. The device sends this information to the server, which then stores the received data in a database. Input data: User's personal information. Output data: User profile stored in the database.

[0442] Step 2: Providing and conducting initial evaluation tests

[0443] The server provides an initial assessment test to analyze the user's learning style and literacy level. The terminal retrieves the assessment test questions from the server and displays them to the user. After the user answers the questions, the terminal sends the answer data to the server. Input data: User's answer data. Output data: Analysis results of the user's learning style and literacy level.

[0444] Step 3: Generate and deliver personalized learning modules

[0445] Based on the results of the initial assessment test, the server generates a personalized learning module suited to the user's learning style and literacy level. A generative AI model is used to convert complex concepts into simple blocks. This learning module is sent from the server to the device and presented to the user. Input data: User's learning style and literacy level. Output data: Personalized learning module.

[0446] Step 4: Real-time recognition of user emotions by the emotion engine

[0447] The device's camera is used to capture the user's facial expressions and voice in real time. Keras and OpenCV are used to recognize emotions and analyze the data. The emotion data is sent from the device to the server. Input data: User's facial expressions and voice. Output data: Recognized emotion data.

[0448] Step 5: Dynamically adjust learning content based on emotional data

[0449] The server dynamically adjusts the learning content based on the received emotional data. For example, if the user is confused, it will lower the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it will provide more challenging content. Input data: Recognized emotional data. Output data: Adjusted learning content.

[0450] Step 6: Submit your learning progress data and receive next steps

[0451] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next learning module to be provided. Input data: learning progress data and emotion data. Output data: next learning module.

[0452] Step 7: Provide multisensory learning modules

[0453] The server generates multisensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, promoting comprehension and memorization. Input data: User's learning style. Output data: Multisensory learning module.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] [Second embodiment]

[0458] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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."

[0470] The present invention is a system that supports users in improving their literacy skills by providing personalized learning modules using generative AI. This system operates as follows.

[0471] User Registration

[0472] First, the user downloads the system's application onto a device such as a smartphone or tablet. When the user launches the application and enters registration information such as name, email address, and password, the device sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[0473] Initial assessment and learning style analysis

[0474] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are saved on the server, and the user's learning profile is updated.

[0475] Generate learning modules

[0476] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks. This learning module is then sent from the server to the device and presented to the user.

[0477] Delivering learning modules and tracking progress

[0478] A user starts a learning module displayed on the device. The device sequentially displays the content within the module (readings, quizzes, etc.) and records the user's progress in real time. When the user finishes the module, the device sends the progress data to the server. The server tracks the user's progress and adaptively adjusts the next learning module to be presented.

[0479] Providing multi-sensory learning modules

[0480] Furthermore, to enhance users' learning, the server generates multi-sensory content, for example, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and promoting comprehension and retention.

[0481] Specific examples

[0482] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it, stores it in a database, and creates a user profile. The user then takes an initial assessment test. After completing the test, the device sends the results in real time to the server, which uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at the beginner level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues learning using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[0483] This system configuration enables effective and efficient literacy education tailored to each user, supporting the improvement of literacy skills.

[0484] The processing flow will be explained below.

[0485] Step 1:

[0486] The user downloads the application to their smartphone or tablet and launches it.

[0487] Step 2:

[0488] The user enters registration information such as name, email address, and password.

[0489] Step 3:

[0490] The device sends the user's registration information in JSON format to the server.

[0491] Step 4:

[0492] The server stores the received registration information in a database and generates a profile for the new user.

[0493] Step 5:

[0494] The server sends a profile creation success message to the terminal.

[0495] Step 6:

[0496] The terminal displays a message to the user indicating that registration is complete.

[0497] Step 7:

[0498] The user taps the "Start Initial Evaluation Test" button within the app.

[0499] Step 8:

[0500] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[0501] Step 9:

[0502] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[0503] Step 10:

[0504] The terminal transmits the response data to the server in real time.

[0505] Step 11:

[0506] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[0507] Step 12:

[0508] The server stores the analysis results in a database and updates the user's learning profile.

[0509] Step 13:

[0510] The server generates personalized learning modules based on the user's learning style and literacy level.

[0511] Step 14:

[0512] The server sends the generated learning module in JSON format to the terminal.

[0513] Step 15:

[0514] The terminal organizes the received learning modules and displays them to the user.

[0515] Step 16:

[0516] The user taps the displayed button to start the learning module.

[0517] Step 17:

[0518] The terminal sequentially presents the learning modules to the user and records the progress locally.

[0519] Step 18:

[0520] The user completes each piece of content (e.g., reading material, quiz) in sequence.

[0521] Step 19:

[0522] The terminal sends the progress data of the learning module to the server in batches.

[0523] Step 20:

[0524] The server analyzes the received progress data and tracks the user's learning progress.

[0525] Step 21:

[0526] If the server needs to generate a new learning module, it uses the generation AI again to prepare the next module and send it to the terminal.

[0527] Step 22:

[0528] A server generates multi-sensory content and transmits it to a terminal.

[0529] Step 23:

[0530] The terminal provides multi-sensory content to the user.

[0531] Step 24:

[0532] The user learns by using the presented multi-sensory content.

[0533] Step 25:

[0534] The device records the user's reactions and usage status and sends them to the server.

[0535] Step 26:

[0536] The server analyzes this data and evaluates the user's learning effectiveness.

[0537] Example 1

[0538] 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."

[0539] Conventional educational systems provide uniform learning content, making it difficult to adapt to the learning styles and literacy levels of individual users. This reduces learning effectiveness and hinders efficient literacy improvement. Another problem is the lack of a mechanism for tracking learning progress in real time and providing adaptive learning modules.

[0540] 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.

[0541] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style and literacy level using a generative AI model based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling effective and efficient literacy education that is personalized to the user.

[0542] "User" refers to an individual who uses the system to learn.

[0543] "Registration Information" refers to basic information such as name, email address, and password provided by a User to use the System.

[0544] "Database" refers to a data storage system for storing and managing data such as user registration information and learning status.

[0545] "Initial Assessment Test" refers to a test provided to analyze a user's learning style and literacy level.

[0546] "Learning style" refers to the characteristics of a user's learning method for effectively understanding information, and includes, for example, visual and auditory learning.

[0547] "Literacy level" refers to an indicator that shows the current state of a user's reading and writing ability.

[0548] A "generative AI model" refers to an artificial intelligence model that generates learning content appropriate for users, using AI technology that performs natural language processing, for example.

[0549] A "learning module" refers to a set of learning materials or content that allows a user to study.

[0550] "Terminal" refers to a device, such as a smartphone or tablet, that a user uses to access the system.

[0551] "Progress" refers to the user's achievement and performance as they progress through their studies.

[0552] "Multisensory content" refers to teaching materials and content that enhance learning by using multiple senses, such as sight and hearing.

[0553] The present invention provides a system for supporting users in improving their literacy skills by providing personalized learning modules using a generative AI model. Specific embodiments of the system are described in detail below.

[0554] User Registration

[0555] First, the user must download and install a dedicated application on their device, such as a smartphone or tablet. The user launches the app and enters registration information such as their name, email address, and password. This information is then sent from the device to the server. The server then stores the received data in a database (e.g., PostgreSQL) and creates a new user profile. During this process, the device sends data to the server's API endpoint using an HTTP POST request.

[0556] Initial assessment and learning style analysis

[0557] Once user registration is complete, the next step is to take an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the answer data is sent from the device to the server. Based on the received data, the server uses an AI model (e.g., TensorFlow) to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[0558] Generate learning modules

[0559] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate a personalized learning module suited to the user. The generated learning module is sent to the device and presented to the user. In this case, the server converts complex concepts into simple blocks.

[0560] Delivering learning modules and tracking progress

[0561] A user starts a learning module on their device and checks the content within the module (readings, quizzes, etc.) one by one. The device records the user's progress in real time and sends the data to the server each time the module is completed. The server tracks the progress data and adaptively adjusts and generates the next learning module to be provided based on this data.

[0562] Providing multi-sensory learning modules

[0563] To improve the user's learning effectiveness, the server generates multi-sensory content, such as illustrated learning materials for visual learners and audio learning materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, which is expected to improve understanding and memory.

[0564] Specific examples

[0565] For example, a user downloads a new app and enters information such as their name, email address, and password, which is then sent to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and once the user completes the test, the device sends the results to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at an elementary level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues to study using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[0566] Prompt Sentence Examples

[0567] "User registration: The user downloads the app and registers by entering the required information."

[0568] "Initial evaluation test: The user answers the initial evaluation test and sends the results to the server."

[0569] "Learning module generation: The server uses an AI model to analyze the user's learning style and literacy level, generate the optimal learning module, and send it to the device."

[0570] "Progress tracking: When a user completes a learning module, the device sends progress data to the server, which then coordinates and generates the next module."

[0571] This invention enables effective and efficient literacy education tailored to the user, and can support the improvement of literacy.

[0572] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0573] Step 1: User Registration

[0574] 1. The user downloads and installs the application on their smartphone or tablet.

[0575] 2. The user launches the app and enters registration information such as name, email address, and password.

[0576] 3. The device temporarily saves the entered registration information.

[0577] 4. The device sends the entered information to the server as an HTTP POST request.

[0578] Input: User's name, email address, and password

[0579] Data processing: Convert information into JSON format

[0580] Output: Registration information sent to the server

[0581] 5. The server verifies the received data.

[0582] Input: Received registration information

[0583] Data calculation: Email address format verification, password strength check

[0584] Output: Verification result (pass or error)

[0585] 6. If the verification is successful, the server stores the user information in a database and creates a user profile.

[0586] 7. The server returns a registration success response to the terminal.

[0587] Step 2: Provide initial evaluation testing

[0588] 1. After registering, the user clicks on the link to take the initial evaluation test.

[0589] 2. The terminal sends a request for an initial evaluation test to the server.

[0590] Input: User ID

[0591] Data Processing: Request Creation

[0592] Output: The request sent to the server

[0593] 3. The server retrieves the initial evaluation test questions from the database and sends them to the terminal.

[0594] Input: User ID

[0595] Data arithmetic: Selecting appropriate test questions

[0596] Output: Assessment questions sent to the device

[0597] 4. The terminal displays the received assessment test questions.

[0598] 5. The user answers each question in the assessment test.

[0599] Step 3: Submitting assessment data and learning style analysis

[0600] 1. When the user finishes the test, the device temporarily stores the answer data and sends it to the server.

[0601] Input: User response data

[0602] Data processing: Compiling response data

[0603] Output: Response data sent to the server

[0604] 2. The server analyzes the received evaluation data using an AI model.

[0605] Input: Evaluation data

[0606] Data Computing: Analyzing Learning Styles and Literacy Levels Using AI Models

[0607] Output: Analysis results (learning style, literacy level)

[0608] 3. The server stores the analysis results in a database and updates the user's learning profile.

[0609] Step 4: Generate and deliver learning modules

[0610] 1. The server uses a generative AI model to generate learning modules appropriate for the user's learning style and literacy level.

[0611] Input: User's learning profile

[0612] Data Computation: Generating Learning Modules

[0613] Output: The generated learning module

[0614] 2. The server sends the generated learning module to the terminal.

[0615] 3. The terminal displays the received learning module on the user interface.

[0616] 4. The user begins the learning module.

[0617] Step 5: Track your progress and generate the next module

[0618] 1. The device records the user's progress in the learning module in real time.

[0619] Input: User action data

[0620] Data processing: generating progress data

[0621] Output: Progress data

[0622] 2. When the user finishes the learning module, the device sends progress data to the server.

[0623] 3. The server analyzes the received progress data and adaptively adjusts the learning module to be provided next.

[0624] Input: Progress data

[0625] Data calculation: Adjusting the next learning module

[0626] Output: Adjusted learning module

[0627] 4. The server generates a new learning module and sends it to the terminal again.

[0628] Step 6: Creating and delivering multisensory learning modules

[0629] 1. The server generates multi-sensory content according to the user's learning style.

[0630] Input: User's learning profile

[0631] Data Computing: Creating visual and auditory content

[0632] Output: Multisensory learning content

[0633] 2. The server transmits the generated multi-sensory content to the terminal.

[0634] 3. The device displays the multisensory content in the user interface.

[0635] 4. Users learn using multiple senses.

[0636] (Application example 1)

[0637] 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."

[0638] Traditional literacy systems struggle to effectively provide personalized learning experiences tailored to users' learning styles and literacy levels. Furthermore, materials that rely on a single sense often result in inefficient comprehension and retention. Furthermore, they lack the ability to track progress and adjust the generated learning modules accordingly.

[0639] 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.

[0640] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on the progress, means for generating a learning module based on the user's profile using a generative AI, means for generating multi-sensory content and providing learning materials according to the user's learning style, means for the generated learning module to use a generative AI model that converts content into simple blocks according to the user's literacy level, and means for updating the user's learning profile, thereby providing the user with an optimal learning experience and enabling efficient improvement of literacy.

[0641] "User registration information" refers to information used to identify a user and register them in the system, such as the user's name, email address, and password.

[0642] A "database" is a system that stores data such as user registration information and progress status, and makes it accessible as needed.

[0643] An "initial assessment test" is a test conducted to analyze a user's learning style and current literacy level.

[0644] "Learning style" refers to the way in which a user learns most effectively, and can be visual, auditory, tactile, or other.

[0645] "Literacy level" is an indicator of a user's level of reading ability and comprehension.

[0646] "Personalized Learning Modules" are learning content specifically designed to fit a user's learning style and literacy level.

[0647] "Generative AI" is an artificial intelligence technology that generates new content based on initial input data.

[0648] "Presenting learning content" means displaying learning materials and questions in a form that is accessible to the user.

[0649] "Learning progress" is data that indicates how much of a learning module a user has completed and how much they have learned.

[0650] "Multisensory content" is content that supports learning by utilizing multiple senses, such as sight, hearing, and touch.

[0651] A "generative AI model" is an AI algorithm that generates personalized learning modules based on a user's learning style and literacy level.

[0652] A "learning profile" is comprehensive information that includes a user's learning style, literacy level, progress, and so on.

[0653] A "terminal" is a device such as a smartphone or tablet that a user uses to access a learning module and progress through their learning.

[0654] The present invention is a system for supporting user literacy improvement by providing personalized learning modules using generative AI. The system includes means for receiving user registration information and storing it in a database, means for conducting an initial assessment test, means for generating and providing personalized learning modules based on learning style and literacy level using a generative AI model, means for generating multi-sensory content, and means for tracking the user's learning progress and generating the next learning module.

[0655] Hardware and Software Configuration

[0656] The system is implemented using the following main hardware and software:

[0657] 1. Server:

[0658] Database: Used to store user registration information, initial assessment results, learning progress data, etc.

[0659] Generative AI model: An AI algorithm that generates learning modules based on user profile information. Specifically, GPT-2 or similar generative AI models are used.

[0660] Flask framework: Acts as an application server, managing the reception of data from users and the provision of learning modules.

[0661] 2. Terminal:

[0662] Smartphones and tablets: Devices used by users to download learning modules and progress through their studies. These devices communicate with the server to send and receive data.

[0663] Data processing flow

[0664] 1. User Registration:

[0665] When a user enters registration information such as name, email address, and password, the device sends this information to the server, which stores the received data in a database and creates a profile for the new user.

[0666] 2. Initial assessment and learning style analysis:

[0667] To take an initial assessment test, the device retrieves the assessment questions from the server and displays them to the user. After the user enters their answers, the device sends the answers to the server. The server uses an AI model to analyze this data and determine the user's learning style (e.g., visual, auditory, etc.) and current literacy level.

[0668] 3. Generate learning modules:

[0669] Based on the initial assessment results, the server generates personalized learning modules suited to the user's learning style. Using a generative AI model, it converts complex concepts into simple blocks to generate learning materials and sends them to the device.

[0670] 4. Delivering learning modules and tracking progress:

[0671] The user starts and progresses through the learning modules displayed on the device. The device records the user's progress in real time and sends the completed data to the server. The server then adaptively adjusts the next learning module to be provided based on the progress data.

[0672] 5. Providing multi-sensory learning modules:

[0673] To improve the learning effect of users, the server generates learning content that utilizes multiple senses, such as sight and hearing. For example, it provides learning materials with illustrations for visual learners and audio reading materials for auditory learners.

[0674] Specific examples

[0675] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and based on the results, is determined to be a visual learner with an elementary literacy level. The server then generates learning materials with simple grammar rules and illustrations appropriate for the user and sends them to the device. As the user progresses with their learning, progress data is sent to the server, which then adaptively generates the next learning module.

[0676] Prompt Sentence Examples

[0677] "Create learning modules for visual learners with beginner literacy levels."

[0678] This process provides users with a personalized and optimal learning experience, which is expected to improve their literacy skills.

[0679] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0680] Step 1:

[0681] A user downloads the application and enters their registration information, such as their name, email address, and password, which the device sends to the server. The server receives the information and stores it in a database. The output is a user profile.

[0682] Step 2:

[0683] The user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user enters their answers, the entered data is sent from the device to the server. Based on the received data, the server uses an AI model to analyze the user's learning style and literacy level. The analysis results are stored in a database and the user's profile is updated as an output.

[0684] Step 3:

[0685] Based on the initial evaluation results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model to generate prompt sentences and creates learning materials based on them. This learning module is then sent from the server to the device. As an output, a learning module tailored to the user's characteristics, such as visual or auditory, is generated.

[0686] Step 4:

[0687] The user starts a learning module displayed on the device and proceeds with their learning. The device sequentially displays the content (readings, quizzes, etc.) within the learning module. As the user proceeds with their learning, their progress is recorded in real time. Based on the input data, the device sends progress data to the server, which tracks their learning progress.

[0688] Step 5:

[0689] The server adjusts and generates the next learning module based on the user's progress data. By analyzing the progress data and adaptively adjusting the next learning module to be provided, the server maximizes the user's learning effect. As an output, the next learning module according to the user's progress is generated and sent to the device.

[0690] Step 6:

[0691] The server generates multisensory content to enhance learning outcomes. Specifically, it provides illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. This involves using a generative AI model to generate appropriate content from prompts. As an output, a multisensory learning module is generated and sent to the device.

[0692] Step 7:

[0693] The results of the user's completed learning module are sent to the server, and the database is updated. The user's learning profile is always updated to the latest version, and this is reflected in the generation of subsequent learning modules. This ensures that optimal learning content is provided to the user without interruption. The learning progress data is updated as an output.

[0694] 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.

[0695] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust learning content according to the user's emotions. This system operates as follows.

[0696] User Registration

[0697] First, a user downloads the system's application onto a device such as a smartphone or tablet and launches it. When creating an account, the user enters registration information such as name, email address, and password. The device then sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[0698] Initial assessment and learning style analysis

[0699] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[0700] Creating and delivering learning modules

[0701] Based on the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level, using generative AI to convert complex concepts into simple blocks, which are then sent from the server to the device and presented to the user.

[0702] Introducing the Emotion Engine

[0703] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and voice to recognize their current emotions (e.g., joy, confusion, fatigue, etc.).

[0704] Dynamic content adjustment based on user emotions

[0705] The recognized emotion data is sent from the device to a server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be reduced or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[0706] Track your learning progress and provide next steps

[0707] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[0708] Providing multi-sensory learning modules

[0709] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[0710] Specific examples

[0711] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[0712] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[0713] The system provides users with a personalized and dynamic learning experience to support literacy development.

[0714] The processing flow will be explained below.

[0715] Step 1:

[0716] A user downloads the application onto a device such as a smartphone or tablet and launches it.

[0717] Step 2:

[0718] The user enters registration information such as name, email address, and password.

[0719] Step 3:

[0720] The device sends the user's registration information in JSON format to the server.

[0721] Step 4:

[0722] The server stores the received registration information in a database and generates a profile for the new user.

[0723] Step 5:

[0724] The server sends a profile creation success message to the terminal.

[0725] Step 6:

[0726] The terminal displays a message to the user indicating that registration is complete.

[0727] Step 7:

[0728] The user taps the "Start Initial Evaluation Test" button within the app.

[0729] Step 8:

[0730] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[0731] Step 9:

[0732] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[0733] Step 10:

[0734] The terminal transmits the response data to the server in real time.

[0735] Step 11:

[0736] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[0737] Step 12:

[0738] The server stores the analysis results in a database and updates the user's learning profile.

[0739] Step 13:

[0740] The server generates personalized learning modules based on the user's learning style and literacy level.

[0741] Step 14:

[0742] The server sends the generated learning module in JSON format to the terminal.

[0743] Step 15:

[0744] The terminal organizes the received learning modules and displays them to the user.

[0745] Step 16:

[0746] The user taps the displayed button to start the learning module.

[0747] Step 17:

[0748] The terminal sequentially presents the learning modules to the user and records the progress locally.

[0749] Step 18:

[0750] The emotion engine analyzes the user's facial expressions and voice in real time while using the learning module and generates emotion data.

[0751] Step 19:

[0752] The terminal transmits the emotion data to the server.

[0753] Step 20:

[0754] The server analyzes the received emotion data and dynamically adjusts the learning content based on the user's emotion.

[0755] Step 21:

[0756] The user completes each piece of content (e.g., reading material, quizzes) in the learning module in sequence.

[0757] Step 22:

[0758] The terminal sends the progress data of the learning module to the server in batches.

[0759] Step 23:

[0760] The server stores the received progress data and emotion data in a database to track the user's learning status.

[0761] Step 24:

[0762] If the server needs to generate a new learning module, it uses the generation AI again to generate the next module and sends it to the terminal.

[0763] Step 25:

[0764] The server generates multi-sensory content (e.g., illustrated learning materials for visual learners, audio reading materials for auditory learners) and transmits it to the terminal.

[0765] Step 26:

[0766] The terminal provides multi-sensory content to the user.

[0767] Step 27:

[0768] Users engage in interactive learning through multi-sensory content.

[0769] Step 28:

[0770] The device records the user's reactions and usage status and sends them to the server.

[0771] Step 29:

[0772] The server analyzes this data and evaluates the user's learning effectiveness.

[0773] Example 2

[0774] 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."

[0775] Conventional literacy education systems often provide uniform learning content because they are unable to fully reflect the learning styles and emotional states of individual learners. This can lead to differences in learner comprehension and proficiency, making efficient learning difficult. Furthermore, conventional systems struggle to dynamically adjust learning content based on real-time emotional analysis, making it difficult to maintain learner motivation.

[0776] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0777] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module based on the results of the initial assessment test in accordance with the user's learning style, means for providing the generated learning module to the user's terminal and presenting learning content, means for recognizing the user's emotions in real time and transmitting the emotion data to the server, means for dynamically adjusting the learning content based on the emotion data, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling a personalized learning experience and dynamic adjustment of the learning content based on real-time emotion analysis.

[0778] "User" refers to an individual who uses the system to perform learning activities.

[0779] "Registration Information" refers to basic personal information such as name, email address, and password that a User provides when first accessing the System.

[0780] "Database" refers to data storage within the System for storing user registration information, learning profiles, progress data, emotional data, etc.

[0781] "Initial Assessment Test" refers to a series of questions or tasks provided by the system to assess a user's learning style and literacy level.

[0782] "Learning style" refers to the method or technique (e.g., visual, auditory, etc.) that a user uses to learn most effectively.

[0783] "Literacy level" refers to the result of assessing the user's current literacy skills, such as reading and writing ability and vocabulary.

[0784] "Learning Module" refers to system-generated learning materials and activities that are customized to a user's learning style and literacy level.

[0785] "Generative AI" refers to a system component that automatically generates content for learning modules using machine learning models and artificial intelligence techniques.

[0786] An "emotion engine" refers to software or algorithms that analyze a user's real-time facial expressions and voice to recognize their emotional state.

[0787] "Emotion data" refers to information indicating the user's emotional state (e.g., joy, confusion, fatigue, etc.) recognized by the emotion engine.

[0788] "Progress" refers to data indicating how far a user has progressed through a learning module.

[0789] This invention is a literacy education system that combines a generative AI model and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system consists of three main components: a server, a terminal, and a user.

[0790] User Registration

[0791] A user downloads and launches the system application onto a device such as a smartphone or tablet. The user enters registration information such as name, email address, and password. The device sends this information to the server, which stores the received data in a database. A new user profile is created and registration is complete.

[0792] Initial assessment and learning style analysis

[0793] After completing user registration, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. The server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level, and stores the results in a database.

[0794] Creating and delivering learning modules

[0795] Based on the results of the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks, and the learning module is then sent from the server to the device. The user progresses through the learning module.

[0796] Introducing the Emotion Engine

[0797] While using the learning module, an emotion engine runs on the device to recognize the user's emotions in real time. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions (e.g., joy, confusion, fatigue, etc.). Emotion data is sent from the device to the server.

[0798] Dynamic content adjustment based on user emotions

[0799] The server dynamically adjusts learning content based on the recognized emotion data. For example, if the user is confused, it may reduce the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it may provide more challenging content, optimizing the user's learning experience.

[0800] Track your learning progress and provide next steps

[0801] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next module to be provided. This data is stored in a database and is also used to analyze long-term learning patterns.

[0802] Providing multi-sensory learning modules

[0803] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[0804] Specific examples

[0805] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level, and determines that they are a visual learner and their literacy level is beginner. Based on this, the server generates learning materials with simple illustrations of grammar rules and sends them to the device.

[0806] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[0807] Prompt Sentence Examples

[0808] Please list the information required for new user registration.

[0809] "Please provide an example of an initial assessment test to analyze users' learning styles."

[0810] "Please explain the types of emotions the emotion engine can recognize."

[0811] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0812] Step 1: User Registration

[0813] A user downloads and launches the system application on a device such as a smartphone or tablet. After the user enters registration information such as name, email address, and password, the device sends this information to the server as a JSON-formatted object. The server verifies the received data and stores it in a database. It then generates a new user profile and sends a registration completion notification to the device. The input of this step is the user's basic information, and the output is the user's profile data stored in the database.

[0814] Step 2: Initial assessment and learning style analysis

[0815] Once user registration is complete, the device retrieves assessment test questions from the server to present the user with an initial assessment test. When the user answers the test questions, the device sends the answer data in JSON format to the server. The server uses an AI model (e.g., TensorFlow or PyTorch) to analyze the user's learning style and literacy level based on the answer data. The analysis results are stored in a database, and the user's learning profile is updated. The input of this step is the user's answer data, and the output is the analysis results of the learning style and literacy level.

[0816] Step 3: Generate and deliver learning modules

[0817] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to convert concepts into simple blocks. The generated learning module is sent from the server to the device in HTML or Markdown format and presented to the user. The input of this step is the analysis results of the learning style and literacy level, and the output is a personalized learning module.

[0818] Step 4: Implementing the Emotion Engine

[0819] While the learning module is in use, an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) runs on the device to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize their current emotion (e.g., joy, confusion, fatigue, etc.). The recognized emotion data is sent to the server in JSON format. The input of this step is the user's facial expression and voice data, and the output is the recognized emotion data.

[0820] Step 5: Dynamically adjust content based on user sentiment

[0821] Based on the recognized emotion data, the server dynamically adjusts the learning content. For example, if the user is confused, the server may lower the difficulty of the learning material or generate additional explanations and send them to the device. Conversely, if the user is satisfied, the server may adjust the content to provide more challenging content. The input of this step is emotion data, and the output is an adjusted learning module.

[0822] Step 6: Track learning progress and provide next steps

[0823] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts and generates the next learning module to provide. The progress data includes the completion status and correct answer rate for each learning module. This data is sent to the server in JSON format and stored in a database. The input of this step is the learning progress data and emotion data, and the output is the next learning module.

[0824] Step 7: Provide multisensory learning modules

[0825] The server generates multisensory content (visual, auditory, etc.) and sends it to the device. Specifically, it uses image processing libraries (e.g., Pillow or OpenCV) and speech synthesis software (e.g., Google Text-to-Speech API) to provide illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. The generated content is sent from the server to the device in file format (e.g., JPEG, MP3). The input of this step is the user's learning style data, and the output is a multisensory learning module.

[0826] (Application example 2)

[0827] 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."

[0828] While conventional literacy education systems can provide personalized learning modules tailored to a user's learning style and literacy level, they lack the ability to dynamically adjust learning content based on the user's emotions. This makes it difficult to maintain the user's interest and concentration, limiting the effectiveness of learning. In particular, systems that can respond to changing user emotions in real time are needed for the education and training of store clerks in brick-and-mortar stores.

[0829] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module tailored to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on this, and means for recognizing the user's emotions in real time and dynamically adjusting the learning content based on the emotion data. This enables the learning content to be adapted based on the user's emotions, providing an effective learning experience, particularly in the education and training of store clerks in physical stores.

[0830] "User registration information" refers to a user's personal information and basic profile information in the system, including name, email address, password, etc.

[0831] A "database" is a digital storage system that stores registered user information, learning progress, emotional data, etc., and retrieves and references them as needed.

[0832] An "initial assessment test" is an assessment test conducted to measure a user's learning style and current literacy level or learning ability.

[0833] "Learning style" refers to the way in which a user most effectively absorbs information during learning, and includes visual, auditory, tactile, and other styles.

[0834] "Literacy level" is an indicator of a user's level of ability to understand, read, and write a language.

[0835] A "personalized learning module" is a collection of learning materials and content optimized for each user's learning style and literacy level based on the results of an initial assessment test.

[0836] "Means for presenting learning content" refers to a method or device for providing the created learning module to the user's terminal and displaying and playing it.

[0837] "Study progress" is data that indicates the results and level of achievement achieved by the user through their learning activities.

[0838] "Dynamic adjustment" refers to optimizing and changing learning content on an ongoing basis based on data obtained in real time.

[0839] The "emotion engine" is a system that recognizes emotions in real time by analyzing the user's facial expressions and voice.

[0840] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system is particularly effective in educating and training store staff in brick-and-mortar stores.

[0841] System Configuration

[0842] The system consists of the following main components:

[0843] 1. Server

[0844] 2. Devices (smartphones, tablets)

[0845] 3. Emotion Engine

[0846] 4. Generative AI Models

[0847] User Registration

[0848] First, a user downloads the system's application onto their smartphone or tablet. Then, they launch the application and enter their registration information, such as their name, email address, and password. This information is sent from the device to the server and stored in a database. The server then creates a profile for the new user.

[0849] Initial assessment and learning style analysis

[0850] Once user registration is complete, the user takes an initial assessment test. This test is conducted to analyze the user's learning style and literacy level. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the data is sent from the device to the server. The server uses an AI model based on this data to analyze the user's learning style and literacy level, and stores the results in a database.

[0851] Creating and delivering learning modules

[0852] Based on the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Using a generative AI model, complex concepts are transformed into simple blocks, and this learning module is sent from the server to the device and presented to the user.

[0853] Introducing the Emotion Engine

[0854] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time. Specifically, it uses a camera to analyze the user's facial expressions and voice to recognize emotions (e.g., joy, confusion, fatigue, etc.). This is done using software such as Keras and OpenCV.

[0855] Dynamic content adjustment based on user emotions

[0856] The emotion data recognized by the emotion engine is sent from the device to the server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be lowered or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[0857] Track your learning progress and provide next steps

[0858] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[0859] Providing multi-sensory learning modules

[0860] In addition, the server generates and transmits multi-sensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, to the device, allowing users to learn using multiple senses and promoting comprehension and memorization.

[0861] Specific examples

[0862] For example, a user downloads a new application, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[0863] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device.

[0864] Prompt Sentence Examples

[0865] “Deviate a system where an emotion engine can sense when a store clerk is confused, and the learning difficulty or additional explanations are adjusted based on that emotion data.

[0866] Input data: face image, recognized emotion data, user ID

[0867] Output data: Type of learning module (difficulty adjustment, additional learning materials)

[0868] Libraries used: Keras, OpenCV, requests

[0869] This system provides a personalized and dynamic learning experience tailored to the user, effectively supporting sales associate training in brick-and-mortar stores.

[0870] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0871] Step 1: Enter and save your user registration information

[0872] The user downloads the application onto their smartphone or tablet and launches it. The user enters registration information such as their name, email address, and password. The device sends this information to the server, which then stores the received data in a database. Input data: User's personal information. Output data: User profile stored in the database.

[0873] Step 2: Providing and conducting initial evaluation tests

[0874] The server provides an initial assessment test to analyze the user's learning style and literacy level. The terminal retrieves the assessment test questions from the server and displays them to the user. After the user answers the questions, the terminal sends the answer data to the server. Input data: User's answer data. Output data: Analysis results of the user's learning style and literacy level.

[0875] Step 3: Generate and deliver personalized learning modules

[0876] Based on the results of the initial assessment test, the server generates a personalized learning module suited to the user's learning style and literacy level. A generative AI model is used to convert complex concepts into simple blocks. This learning module is sent from the server to the device and presented to the user. Input data: User's learning style and literacy level. Output data: Personalized learning module.

[0877] Step 4: Real-time recognition of user emotions by the emotion engine

[0878] The device's camera is used to capture the user's facial expressions and voice in real time. Keras and OpenCV are used to recognize emotions and analyze the data. The emotion data is sent from the device to the server. Input data: User's facial expressions and voice. Output data: Recognized emotion data.

[0879] Step 5: Dynamically adjust learning content based on emotional data

[0880] The server dynamically adjusts the learning content based on the received emotional data. For example, if the user is confused, it will lower the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it will provide more challenging content. Input data: Recognized emotional data. Output data: Adjusted learning content.

[0881] Step 6: Submit your learning progress data and receive next steps

[0882] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next learning module to be provided. Input data: learning progress data and emotion data. Output data: next learning module.

[0883] Step 7: Provide multisensory learning modules

[0884] The server generates multisensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, promoting comprehension and memorization. Input data: User's learning style. Output data: Multisensory learning module.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] [Third embodiment]

[0889] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0890] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0891] 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).

[0892] 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.

[0893] 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.

[0894] 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).

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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."

[0901] The present invention is a system that supports users in improving their literacy skills by providing personalized learning modules using generative AI. This system operates as follows.

[0902] User Registration

[0903] First, the user downloads the system's application onto a device such as a smartphone or tablet. When the user launches the application and enters registration information such as name, email address, and password, the device sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[0904] Initial assessment and learning style analysis

[0905] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are saved on the server, and the user's learning profile is updated.

[0906] Generate learning modules

[0907] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks. This learning module is then sent from the server to the device and presented to the user.

[0908] Delivering learning modules and tracking progress

[0909] A user starts a learning module displayed on the device. The device sequentially displays the content within the module (readings, quizzes, etc.) and records the user's progress in real time. When the user finishes the module, the device sends the progress data to the server. The server tracks the user's progress and adaptively adjusts the next learning module to be presented.

[0910] Providing multi-sensory learning modules

[0911] Furthermore, to enhance users' learning, the server generates multi-sensory content, for example, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and promoting comprehension and retention.

[0912] Specific examples

[0913] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it, stores it in a database, and creates a user profile. The user then takes an initial assessment test. After completing the test, the device sends the results in real time to the server, which uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at the beginner level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues learning using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[0914] This system configuration enables effective and efficient literacy education tailored to each user, supporting the improvement of literacy skills.

[0915] The processing flow will be explained below.

[0916] Step 1:

[0917] The user downloads the application to their smartphone or tablet and launches it.

[0918] Step 2:

[0919] The user enters registration information such as name, email address, and password.

[0920] Step 3:

[0921] The device sends the user's registration information in JSON format to the server.

[0922] Step 4:

[0923] The server stores the received registration information in a database and generates a profile for the new user.

[0924] Step 5:

[0925] The server sends a profile creation success message to the terminal.

[0926] Step 6:

[0927] The terminal displays a message to the user indicating that registration is complete.

[0928] Step 7:

[0929] The user taps the "Start Initial Evaluation Test" button within the app.

[0930] Step 8:

[0931] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[0932] Step 9:

[0933] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[0934] Step 10:

[0935] The terminal transmits the response data to the server in real time.

[0936] Step 11:

[0937] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[0938] Step 12:

[0939] The server stores the analysis results in a database and updates the user's learning profile.

[0940] Step 13:

[0941] The server generates personalized learning modules based on the user's learning style and literacy level.

[0942] Step 14:

[0943] The server sends the generated learning module in JSON format to the terminal.

[0944] Step 15:

[0945] The terminal organizes the received learning modules and displays them to the user.

[0946] Step 16:

[0947] The user taps the displayed button to start the learning module.

[0948] Step 17:

[0949] The terminal sequentially presents the learning modules to the user and records the progress locally.

[0950] Step 18:

[0951] The user completes each piece of content (e.g., reading material, quiz) in sequence.

[0952] Step 19:

[0953] The terminal transmits the progress data of the learning module to the server in batches.

[0954] Step 20:

[0955] The server analyzes the received progress data and tracks the user's learning progress.

[0956] Step 21:

[0957] If the server needs to generate a new learning module, it uses the generation AI again to prepare the next module and send it to the terminal.

[0958] Step 22:

[0959] A server generates multi-sensory content and transmits it to a terminal.

[0960] Step 23:

[0961] The terminal provides multi-sensory content to the user.

[0962] Step 24:

[0963] The user learns by utilizing the presented multi-sensory content.

[0964] Step 25:

[0965] The device records the user's reactions and usage status and sends them to the server.

[0966] Step 26:

[0967] The server analyzes this data and evaluates the user's learning effectiveness.

[0968] Example 1

[0969] 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."

[0970] Conventional educational systems provide uniform learning content, making it difficult to adapt to the learning styles and literacy levels of individual users. This reduces learning effectiveness and hinders efficient literacy improvement. Another problem is the lack of a mechanism for tracking learning progress in real time and providing adaptive learning modules.

[0971] 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.

[0972] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style and literacy level using a generative AI model based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling effective and efficient literacy education that is personalized to the user.

[0973] "User" refers to an individual who uses the system to learn.

[0974] "Registration Information" refers to basic information such as name, email address, and password provided by a User to use the System.

[0975] "Database" refers to a data storage system for storing and managing data such as user registration information and learning status.

[0976] "Initial Assessment Test" refers to a test provided to analyze a user's learning style and literacy level.

[0977] "Learning style" refers to the characteristics of a user's learning method for effectively understanding information, and includes, for example, visual and auditory learning.

[0978] "Literacy level" refers to an indicator that shows the current state of a user's reading and writing ability.

[0979] A "generative AI model" refers to an artificial intelligence model that generates learning content appropriate for users, using AI technology that performs natural language processing, for example.

[0980] A "learning module" refers to a set of learning materials or content that allows a user to study.

[0981] "Terminal" refers to a device, such as a smartphone or tablet, that a user uses to access the system.

[0982] "Progress" refers to the user's achievement and performance as they progress through their studies.

[0983] "Multisensory content" refers to teaching materials and content that enhance learning by using multiple senses, such as sight and hearing.

[0984] The present invention provides a system for supporting users in improving their literacy skills by providing personalized learning modules using a generative AI model. Specific embodiments of the system are described in detail below.

[0985] User Registration

[0986] First, the user must download and install a dedicated application on their device, such as a smartphone or tablet. The user launches the app and enters registration information such as their name, email address, and password. This information is then sent from the device to the server. The server then stores the received data in a database (e.g., PostgreSQL) and creates a new user profile. During this process, the device sends data to the server's API endpoint using an HTTP POST request.

[0987] Initial assessment and learning style analysis

[0988] Once user registration is complete, the next step is to take an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the answer data is sent from the device to the server. Based on the received data, the server uses an AI model (e.g., TensorFlow) to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[0989] Generate learning modules

[0990] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate a personalized learning module suited to the user. The generated learning module is sent to the device and presented to the user. In this case, the server converts complex concepts into simple blocks.

[0991] Delivering learning modules and tracking progress

[0992] A user starts a learning module on their device and checks the content within the module (readings, quizzes, etc.) one by one. The device records the user's progress in real time and sends the data to the server each time the module is completed. The server tracks the progress data and adaptively adjusts and generates the next learning module to be provided based on this data.

[0993] Providing multi-sensory learning modules

[0994] To improve the user's learning effectiveness, the server generates multi-sensory content, such as illustrated learning materials for visual learners and audio learning materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, which is expected to improve understanding and memory.

[0995] Specific examples

[0996] For example, a user downloads a new app and enters information such as their name, email address, and password, which is then sent to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and once the user completes the test, the device sends the results to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at an elementary level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues to study using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[0997] Prompt Sentence Examples

[0998] "User registration: The user downloads the app and registers by entering the required information."

[0999] "Initial evaluation test: The user answers the initial evaluation test and sends the results to the server."

[1000] "Learning module generation: The server uses an AI model to analyze the user's learning style and literacy level, generate the optimal learning module, and send it to the device."

[1001] "Progress tracking: When a user completes a learning module, the device sends progress data to the server, which then coordinates and generates the next module."

[1002] This invention enables effective and efficient literacy education tailored to the user, and can support the improvement of literacy.

[1003] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1004] Step 1: User Registration

[1005] 1. The user downloads and installs the application on their smartphone or tablet.

[1006] 2. The user launches the app and enters registration information such as name, email address, and password.

[1007] 3. The device temporarily saves the entered registration information.

[1008] 4. The device sends the entered information to the server as an HTTP POST request.

[1009] Input: User's name, email address, and password

[1010] Data processing: Convert information into JSON format

[1011] Output: Registration information sent to the server

[1012] 5. The server verifies the received data.

[1013] Input: Received registration information

[1014] Data calculation: Email address format verification, password strength check

[1015] Output: Verification result (pass or error)

[1016] 6. If the verification is successful, the server stores the user information in a database and creates a user profile.

[1017] 7. The server returns a registration success response to the terminal.

[1018] Step 2: Provide initial evaluation testing

[1019] 1. After registering, the user clicks on the link to take the initial evaluation test.

[1020] 2. The terminal sends a request for an initial evaluation test to the server.

[1021] Input: User ID

[1022] Data Processing: Request Creation

[1023] Output: The request sent to the server

[1024] 3. The server retrieves the initial evaluation test questions from the database and sends them to the terminal.

[1025] Input: User ID

[1026] Data arithmetic: Selecting appropriate test questions

[1027] Output: Assessment questions sent to the device

[1028] 4. The terminal displays the received assessment test questions.

[1029] 5. The user answers each question in the assessment test.

[1030] Step 3: Submitting assessment data and learning style analysis

[1031] 1. When the user finishes the test, the device temporarily stores the answer data and sends it to the server.

[1032] Input: User response data

[1033] Data processing: Compiling response data

[1034] Output: Response data sent to the server

[1035] 2. The server analyzes the received evaluation data using an AI model.

[1036] Input: Evaluation data

[1037] Data Computing: Analyzing Learning Styles and Literacy Levels Using AI Models

[1038] Output: Analysis results (learning style, literacy level)

[1039] 3. The server stores the analysis results in a database and updates the user's learning profile.

[1040] Step 4: Generate and deliver learning modules

[1041] 1. The server uses a generative AI model to generate learning modules appropriate for the user's learning style and literacy level.

[1042] Input: User's learning profile

[1043] Data Computation: Generating Learning Modules

[1044] Output: The generated learning module

[1045] 2. The server sends the generated learning module to the terminal.

[1046] 3. The terminal displays the received learning module on the user interface.

[1047] 4. The user begins the learning module.

[1048] Step 5: Track your progress and generate the next module

[1049] 1. The device records the user's progress in the learning module in real time.

[1050] Input: User action data

[1051] Data processing: generating progress data

[1052] Output: Progress data

[1053] 2. When the user finishes the learning module, the device sends progress data to the server.

[1054] 3. The server analyzes the received progress data and adaptively adjusts the learning module to be provided next.

[1055] Input: Progress data

[1056] Data calculation: Adjusting the next learning module

[1057] Output: Adjusted learning module

[1058] 4. The server generates a new learning module and sends it to the terminal again.

[1059] Step 6: Creating and delivering multisensory learning modules

[1060] 1. The server generates multi-sensory content according to the user's learning style.

[1061] Input: User's learning profile

[1062] Data Computing: Creating visual and auditory content

[1063] Output: Multisensory learning content

[1064] 2. The server transmits the generated multi-sensory content to the terminal.

[1065] 3. The device displays the multisensory content in the user interface.

[1066] 4. Users learn using multiple senses.

[1067] (Application example 1)

[1068] 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."

[1069] Traditional literacy systems struggle to effectively provide personalized learning experiences tailored to users' learning styles and literacy levels. Furthermore, materials that rely on a single sense often result in inefficient comprehension and retention. Furthermore, they lack the ability to adequately track progress and adjust the generated learning modules accordingly.

[1070] 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.

[1071] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on the progress, means for generating a learning module based on the user's profile using a generative AI, means for generating multi-sensory content and providing learning materials according to the user's learning style, means for the generated learning module to use a generative AI model that converts content into simple blocks according to the user's literacy level, and means for updating the user's learning profile, thereby providing the user with an optimal learning experience and enabling efficient improvement of literacy.

[1072] "User registration information" refers to information used to identify a user and register them in the system, such as the user's name, email address, and password.

[1073] A "database" is a system that stores data such as user registration information and progress status, and makes it accessible as needed.

[1074] An "initial assessment test" is a test conducted to analyze a user's learning style and current literacy level.

[1075] "Learning style" refers to the way in which a user learns most effectively, and can be visual, auditory, tactile, or other.

[1076] "Literacy level" is an indicator of a user's level of reading ability and comprehension.

[1077] "Personalized Learning Modules" are learning content specifically designed to fit a user's learning style and literacy level.

[1078] "Generative AI" is an artificial intelligence technology that generates new content based on initial input data.

[1079] "Presenting learning content" means displaying learning materials and questions in a form that is accessible to the user.

[1080] "Learning progress" is data that indicates how much of a learning module a user has completed and how much they have learned.

[1081] "Multisensory content" is content that supports learning by utilizing multiple senses, such as sight, hearing, and touch.

[1082] A "generative AI model" is an AI algorithm that generates personalized learning modules based on a user's learning style and literacy level.

[1083] A "learning profile" is comprehensive information that includes a user's learning style, literacy level, progress, and so on.

[1084] A "terminal" is a device such as a smartphone or tablet that a user uses to access a learning module and progress through their learning.

[1085] The present invention is a system for supporting user literacy improvement by providing personalized learning modules using generative AI. The system includes means for receiving user registration information and storing it in a database, means for conducting an initial assessment test, means for generating and providing personalized learning modules based on learning style and literacy level using a generative AI model, means for generating multi-sensory content, and means for tracking the user's learning progress and generating the next learning module.

[1086] Hardware and Software Configuration

[1087] The system is implemented using the following main hardware and software:

[1088] 1. Server:

[1089] Database: Used to store user registration information, initial assessment results, learning progress data, etc.

[1090] Generative AI model: An AI algorithm that generates learning modules based on user profile information. Specifically, a generative AI model such as GPT-2 or similar is used.

[1091] Flask framework: Acts as an application server, managing the reception of data from users and the provision of learning modules.

[1092] 2. Terminal:

[1093] Smartphones and tablets: Devices used by users to download learning modules and progress through their studies. These devices communicate with the server to send and receive data.

[1094] Data processing flow

[1095] 1. User Registration:

[1096] When a user enters registration information such as name, email address, and password, the device sends this information to the server, which stores the received data in a database and creates a profile for the new user.

[1097] 2. Initial assessment and learning style analysis:

[1098] To take an initial assessment test, the device retrieves the assessment questions from the server and displays them to the user. After the user enters their answers, the device sends the answers to the server. The server uses an AI model to analyze this data and determine the user's learning style (e.g., visual, auditory, etc.) and current literacy level.

[1099] 3. Generate learning modules:

[1100] Based on the initial assessment results, the server generates personalized learning modules suited to the user's learning style. Using a generative AI model, it converts complex concepts into simple blocks to generate learning materials, which are then sent to the device.

[1101] 4. Delivering learning modules and tracking progress:

[1102] The user starts and progresses through the learning modules displayed on the device. The device records the user's progress in real time and sends the completed data to the server. The server then adaptively adjusts the next learning module to be provided based on the progress data.

[1103] 5. Providing multi-sensory learning modules:

[1104] To improve the learning effect of users, the server generates learning content that utilizes multiple senses, such as sight and hearing. For example, it provides learning materials with illustrations for visual learners and audio reading materials for auditory learners.

[1105] Specific examples

[1106] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and based on the results, is determined to be a visual learner with an elementary literacy level. The server then generates learning materials with simple grammar rules and illustrations appropriate for the user and sends them to the device. As the user progresses with their learning, progress data is sent to the server, which then adaptively generates the next learning module.

[1107] Prompt Sentence Examples

[1108] "Create learning modules for visual learners with beginner literacy levels."

[1109] This process provides users with a personalized and optimal learning experience, which is expected to improve their literacy skills.

[1110] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1111] Step 1:

[1112] A user downloads the application and enters their registration information, such as their name, email address, and password, which the device sends to the server. The server receives the information and stores it in a database. The output is a user profile.

[1113] Step 2:

[1114] The user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user enters their answers, the entered data is sent from the device to the server. Based on the received data, the server uses an AI model to analyze the user's learning style and literacy level. The analysis results are stored in a database and the user's profile is updated as an output.

[1115] Step 3:

[1116] Based on the initial evaluation results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model to generate prompt sentences and creates learning materials based on them. This learning module is then sent from the server to the device. As an output, a learning module tailored to the user's characteristics, such as visual or auditory, is generated.

[1117] Step 4:

[1118] The user starts a learning module displayed on the device and proceeds with their learning. The device sequentially displays the content (readings, quizzes, etc.) within the learning module. As the user proceeds with their learning, their progress is recorded in real time. Based on the input data, the device sends progress data to the server, which tracks their learning progress.

[1119] Step 5:

[1120] The server adjusts and generates the next learning module based on the user's progress data. By analyzing the progress data and adaptively adjusting the next learning module to be provided, the server maximizes the user's learning effect. As an output, the next learning module according to the user's progress is generated and sent to the device.

[1121] Step 6:

[1122] The server generates multisensory content to enhance learning outcomes. Specifically, it provides illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. This involves using a generative AI model to generate appropriate content from prompts. As an output, a multisensory learning module is generated and sent to the device.

[1123] Step 7:

[1124] The results of the user's completed learning module are sent to the server, and the database is updated. The user's learning profile is always updated to the latest version, and this is reflected in the generation of subsequent learning modules. This ensures that optimal learning content is provided to the user without interruption. The learning progress data is updated as an output.

[1125] 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.

[1126] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust learning content according to the user's emotions. This system operates as follows.

[1127] User Registration

[1128] First, a user downloads the system's application onto a device such as a smartphone or tablet and launches it. When creating an account, the user enters registration information such as name, email address, and password. The device then sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[1129] Initial assessment and learning style analysis

[1130] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[1131] Creating and delivering learning modules

[1132] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level, using generative AI to convert complex concepts into simple blocks, which are then sent from the server to the device and presented to the user.

[1133] Introducing the Emotion Engine

[1134] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and voice to recognize their current emotions (e.g., joy, confusion, fatigue, etc.).

[1135] Dynamic content adjustment based on user emotions

[1136] The recognized emotion data is sent from the device to a server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be reduced or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[1137] Track your learning progress and provide next steps

[1138] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[1139] Providing multi-sensory learning modules

[1140] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[1141] Specific examples

[1142] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[1143] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[1144] The system provides users with a personalized and dynamic learning experience to support literacy development.

[1145] The processing flow will be explained below.

[1146] Step 1:

[1147] A user downloads the application onto a device such as a smartphone or tablet and launches it.

[1148] Step 2:

[1149] The user enters registration information such as name, email address, and password.

[1150] Step 3:

[1151] The device sends the user's registration information in JSON format to the server.

[1152] Step 4:

[1153] The server stores the received registration information in a database and generates a profile for the new user.

[1154] Step 5:

[1155] The server sends a profile creation success message to the terminal.

[1156] Step 6:

[1157] The terminal displays a message to the user indicating that registration is complete.

[1158] Step 7:

[1159] The user taps the "Start Initial Evaluation Test" button within the app.

[1160] Step 8:

[1161] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[1162] Step 9:

[1163] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[1164] Step 10:

[1165] The terminal transmits the response data to the server in real time.

[1166] Step 11:

[1167] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[1168] Step 12:

[1169] The server stores the analysis results in a database and updates the user's learning profile.

[1170] Step 13:

[1171] The server generates personalized learning modules based on the user's learning style and literacy level.

[1172] Step 14:

[1173] The server sends the generated learning module in JSON format to the terminal.

[1174] Step 15:

[1175] The terminal organizes the received learning modules and displays them to the user.

[1176] Step 16:

[1177] The user taps the displayed button to start the learning module.

[1178] Step 17:

[1179] The terminal sequentially presents the learning modules to the user and records the progress locally.

[1180] Step 18:

[1181] The emotion engine analyzes the user's facial expressions and voice in real time while using the learning module and generates emotion data.

[1182] Step 19:

[1183] The terminal transmits the emotion data to the server.

[1184] Step 20:

[1185] The server analyzes the received emotion data and dynamically adjusts the learning content based on the user's emotion.

[1186] Step 21:

[1187] The user completes each piece of content (e.g., reading material, quizzes) in the learning module in sequence.

[1188] Step 22:

[1189] The terminal transmits the progress data of the learning module to the server in batches.

[1190] Step 23:

[1191] The server stores the received progress data and emotion data in a database to track the user's learning status.

[1192] Step 24:

[1193] If the server needs to generate a new learning module, it uses the generation AI again to generate the next module and sends it to the terminal.

[1194] Step 25:

[1195] The server generates multi-sensory content (e.g., illustrated learning materials for visual learners, audio reading materials for auditory learners) and transmits it to the terminal.

[1196] Step 26:

[1197] The terminal provides multi-sensory content to the user.

[1198] Step 27:

[1199] Users engage in interactive learning through multi-sensory content.

[1200] Step 28:

[1201] The device records the user's reactions and usage status and sends them to the server.

[1202] Step 29:

[1203] The server analyzes this data and evaluates the user's learning effectiveness.

[1204] Example 2

[1205] 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."

[1206] Conventional literacy education systems often provide uniform learning content because they are unable to fully reflect the learning styles and emotional states of individual learners. This can lead to differences in learner comprehension and proficiency, making efficient learning difficult. Furthermore, conventional systems struggle to dynamically adjust learning content based on real-time emotional analysis, making it difficult to maintain learner motivation.

[1207] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1208] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module based on the results of the initial assessment test in accordance with the user's learning style, means for providing the generated learning module to the user's terminal and presenting learning content, means for recognizing the user's emotions in real time and transmitting the emotion data to the server, means for dynamically adjusting the learning content based on the emotion data, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling a personalized learning experience and dynamic adjustment of the learning content based on real-time emotion analysis.

[1209] "User" refers to an individual who uses the system to perform learning activities.

[1210] "Registration Information" refers to basic personal information such as name, email address, and password that a User provides when first accessing the System.

[1211] "Database" refers to data storage within the System for storing user registration information, learning profiles, progress data, emotional data, etc.

[1212] "Initial Assessment Test" refers to a series of questions or tasks provided by the system to assess a user's learning style and literacy level.

[1213] "Learning style" refers to the method or technique (e.g., visual, auditory, etc.) that a user uses to learn most effectively.

[1214] "Literacy level" refers to the result of assessing the user's current literacy skills, such as reading and writing ability and vocabulary.

[1215] "Learning Module" refers to system-generated learning materials and activities that are customized to a user's learning style and literacy level.

[1216] "Generative AI" refers to a system component that automatically generates content for learning modules using machine learning models and artificial intelligence techniques.

[1217] An "emotion engine" refers to software or algorithms that analyze a user's real-time facial expressions and voice to recognize their emotional state.

[1218] "Emotion data" refers to information indicating the user's emotional state (e.g., joy, confusion, fatigue, etc.) recognized by the emotion engine.

[1219] "Progress" refers to data indicating how far a user has progressed through a learning module.

[1220] This invention is a literacy education system that combines a generative AI model and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system consists of three main components: a server, a terminal, and a user.

[1221] User Registration

[1222] A user downloads and launches the system application onto a device such as a smartphone or tablet. The user enters registration information such as name, email address, and password. The device sends this information to the server, which stores the received data in a database. A new user profile is created and registration is complete.

[1223] Initial assessment and learning style analysis

[1224] After completing user registration, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. The server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level, and stores the results in a database.

[1225] Creating and delivering learning modules

[1226] Based on the results of the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks, and the learning module is then sent from the server to the device. The user progresses through the learning module.

[1227] Introducing the Emotion Engine

[1228] While using the learning module, an emotion engine runs on the device to recognize the user's emotions in real time. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions (e.g., joy, confusion, fatigue, etc.). Emotion data is sent from the device to the server.

[1229] Dynamic content adjustment based on user emotions

[1230] The server dynamically adjusts learning content based on the recognized emotion data. For example, if the user is confused, it may reduce the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it may provide more challenging content, optimizing the user's learning experience.

[1231] Track your learning progress and provide next steps

[1232] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next module to be provided. This data is stored in a database and is also used to analyze long-term learning patterns.

[1233] Providing multi-sensory learning modules

[1234] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[1235] Specific examples

[1236] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level, and determines that they are a visual learner and their literacy level is beginner. Based on this, the server generates learning materials with simple illustrations of grammar rules and sends them to the device.

[1237] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[1238] Prompt Sentence Examples

[1239] Please list the information required for new user registration.

[1240] "Please provide an example of an initial assessment test to analyze users' learning styles."

[1241] "Please explain the types of emotions the emotion engine can recognize."

[1242] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1243] Step 1: User Registration

[1244] A user downloads and launches the system application on a device such as a smartphone or tablet. After the user enters registration information such as name, email address, and password, the device sends this information to the server as a JSON-formatted object. The server verifies the received data and stores it in a database. It then generates a new user profile and sends a registration completion notification to the device. The input of this step is the user's basic information, and the output is the user's profile data stored in the database.

[1245] Step 2: Initial assessment and learning style analysis

[1246] Once user registration is complete, the device retrieves assessment test questions from the server to present the user with an initial assessment test. When the user answers the test questions, the device sends the answer data in JSON format to the server. The server uses an AI model (e.g., TensorFlow or PyTorch) to analyze the user's learning style and literacy level based on the answer data. The analysis results are stored in a database, and the user's learning profile is updated. The input of this step is the user's answer data, and the output is the analysis results of the learning style and literacy level.

[1247] Step 3: Generate and deliver learning modules

[1248] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to convert concepts into simple blocks. The generated learning module is sent from the server to the device in HTML or Markdown format and presented to the user. The input of this step is the analysis results of the learning style and literacy level, and the output is a personalized learning module.

[1249] Step 4: Implementing the Emotion Engine

[1250] While the learning module is in use, an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) runs on the device to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize their current emotion (e.g., joy, confusion, fatigue, etc.). The recognized emotion data is sent to the server in JSON format. The input of this step is the user's facial expression and voice data, and the output is the recognized emotion data.

[1251] Step 5: Dynamically adjust content based on user sentiment

[1252] Based on the recognized emotion data, the server dynamically adjusts the learning content. For example, if the user is confused, the server may lower the difficulty of the learning material or generate additional explanations and send them to the device. Conversely, if the user is satisfied, the server may adjust the content to provide more challenging content. The input of this step is emotion data, and the output is an adjusted learning module.

[1253] Step 6: Track learning progress and provide next steps

[1254] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts and generates the next learning module to provide. The progress data includes the completion status and correct answer rate for each learning module. This data is sent to the server in JSON format and stored in a database. The input of this step is the learning progress data and emotion data, and the output is the next learning module.

[1255] Step 7: Provide multisensory learning modules

[1256] The server generates multisensory content (visual, auditory, etc.) and sends it to the device. Specifically, it uses image processing libraries (e.g., Pillow or OpenCV) and speech synthesis software (e.g., Google Text-to-Speech API) to provide illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. The generated content is sent from the server to the device in file format (e.g., JPEG, MP3). The input of this step is the user's learning style data, and the output is a multisensory learning module.

[1257] (Application example 2)

[1258] 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."

[1259] While conventional literacy education systems can provide personalized learning modules tailored to a user's learning style and literacy level, they lack the ability to dynamically adjust learning content based on the user's emotions. This makes it difficult to maintain the user's interest and concentration, limiting the effectiveness of learning. In particular, systems that can respond to changing user emotions in real time are needed for the education and training of store clerks in brick-and-mortar stores.

[1260] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module tailored to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on this, and means for recognizing the user's emotions in real time and dynamically adjusting the learning content based on the emotion data. This enables the learning content to be adapted based on the user's emotions, providing an effective learning experience, particularly in the education and training of store clerks in physical stores.

[1261] "User registration information" refers to a user's personal information and basic profile information in the system, including name, email address, password, etc.

[1262] A "database" is a digital storage system that stores registered user information, learning progress, emotional data, etc., and retrieves and references them as needed.

[1263] An "initial assessment test" is an assessment test conducted to measure a user's learning style and current literacy level or learning ability.

[1264] "Learning style" refers to the way in which a user most effectively absorbs information during learning, and includes visual, auditory, tactile, and other styles.

[1265] "Literacy level" is an indicator of a user's level of ability to understand, read, and write a language.

[1266] A "personalized learning module" is a collection of learning materials and content optimized for each user's learning style and literacy level based on the results of an initial assessment test.

[1267] "Means for presenting learning content" refers to a method or device for providing the created learning module to the user's terminal and displaying and playing it.

[1268] "Study progress" is data that indicates the results and level of achievement achieved by the user through their learning activities.

[1269] "Dynamic adjustment" refers to optimizing and changing learning content on an ongoing basis based on data obtained in real time.

[1270] The "emotion engine" is a system that recognizes emotions in real time by analyzing the user's facial expressions and voice.

[1271] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system is particularly effective in educating and training store staff in brick-and-mortar stores.

[1272] System Configuration

[1273] The system consists of the following main components:

[1274] 1. Server

[1275] 2. Devices (smartphones, tablets)

[1276] 3. Emotion Engine

[1277] 4. Generative AI Models

[1278] User Registration

[1279] First, a user downloads the system's application onto their smartphone or tablet. Then, they launch the application and enter their registration information, such as their name, email address, and password. This information is sent from the device to the server and stored in a database. The server then creates a profile for the new user.

[1280] Initial assessment and learning style analysis

[1281] Once user registration is complete, the user takes an initial assessment test. This test is conducted to analyze the user's learning style and literacy level. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the data is sent from the device to the server. The server uses an AI model based on this data to analyze the user's learning style and literacy level, and stores the results in a database.

[1282] Creating and delivering learning modules

[1283] Based on the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Using a generative AI model, complex concepts are transformed into simple blocks, and this learning module is sent from the server to the device and presented to the user.

[1284] Introducing the Emotion Engine

[1285] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time. Specifically, it uses a camera to analyze the user's facial expressions and voice to recognize emotions (e.g., joy, confusion, fatigue, etc.). This is done using software such as Keras and OpenCV.

[1286] Dynamic content adjustment based on user emotions

[1287] The emotion data recognized by the emotion engine is sent from the device to the server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be lowered or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[1288] Track your learning progress and provide next steps

[1289] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[1290] Providing multi-sensory learning modules

[1291] In addition, the server generates and transmits multi-sensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, to the device, allowing users to learn using multiple senses and promoting comprehension and memorization.

[1292] Specific examples

[1293] For example, a user downloads a new application, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[1294] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device.

[1295] Prompt Sentence Examples

[1296] “Deviate a system where an emotion engine can sense when a store clerk is confused, and the learning difficulty or additional explanations are adjusted based on that emotion data.

[1297] Input data: face image, recognized emotion data, user ID

[1298] Output data: Type of learning module (difficulty adjustment, additional learning materials)

[1299] Libraries used: Keras, OpenCV, requests

[1300] This system provides a personalized and dynamic learning experience tailored to the user, effectively supporting sales associate training in brick-and-mortar stores.

[1301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1302] Step 1: Enter and save your user registration information

[1303] The user downloads the application onto their smartphone or tablet and launches it. The user enters registration information such as their name, email address, and password. The device sends this information to the server, which then stores the received data in a database. Input data: User's personal information. Output data: User profile stored in the database.

[1304] Step 2: Providing and conducting initial evaluation tests

[1305] The server provides an initial assessment test to analyze the user's learning style and literacy level. The terminal retrieves the assessment test questions from the server and displays them to the user. After the user answers the questions, the terminal sends the answer data to the server. Input data: User's answer data. Output data: Analysis results of the user's learning style and literacy level.

[1306] Step 3: Generate and deliver personalized learning modules

[1307] Based on the results of the initial assessment test, the server generates a personalized learning module suited to the user's learning style and literacy level. A generative AI model is used to convert complex concepts into simple blocks. This learning module is sent from the server to the device and presented to the user. Input data: User's learning style and literacy level. Output data: Personalized learning module.

[1308] Step 4: Real-time recognition of user emotions by the emotion engine

[1309] The device's camera is used to capture the user's facial expressions and voice in real time. Keras and OpenCV are used to recognize emotions and analyze the data. The emotion data is sent from the device to the server. Input data: User's facial expressions and voice. Output data: Recognized emotion data.

[1310] Step 5: Dynamically adjust learning content based on emotional data

[1311] The server dynamically adjusts the learning content based on the received emotional data. For example, if the user is confused, it will lower the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it will provide more challenging content. Input data: Recognized emotional data. Output data: Adjusted learning content.

[1312] Step 6: Submit your learning progress data and receive next steps

[1313] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next learning module to be provided. Input data: learning progress data and emotion data. Output data: next learning module.

[1314] Step 7: Provide multisensory learning modules

[1315] The server generates multisensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, promoting comprehension and memorization. Input data: User's learning style. Output data: Multisensory learning module.

[1316] 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.

[1317] 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.

[1318] 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.

[1319] [Fourth embodiment]

[1320] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1321] 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.

[1322] 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).

[1323] 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.

[1324] 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.

[1325] 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).

[1326] 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.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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.

[1332] 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."

[1333] The present invention is a system that supports users in improving their literacy skills by providing personalized learning modules using generative AI. This system operates as follows.

[1334] User Registration

[1335] First, the user downloads the system's application onto a device such as a smartphone or tablet. When the user launches the application and enters registration information such as name, email address, and password, the device sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[1336] Initial assessment and learning style analysis

[1337] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are saved on the server, and the user's learning profile is updated.

[1338] Generate learning modules

[1339] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks. This learning module is then sent from the server to the device and presented to the user.

[1340] Delivering learning modules and tracking progress

[1341] A user starts a learning module displayed on the device. The device sequentially displays the content within the module (readings, quizzes, etc.) and records the user's progress in real time. When the user finishes the module, the device sends the progress data to the server. The server tracks the user's progress and adaptively adjusts the next learning module to be presented.

[1342] Providing multi-sensory learning modules

[1343] Furthermore, to enhance users' learning, the server generates multi-sensory content, for example, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and promoting comprehension and retention.

[1344] Specific examples

[1345] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it, stores it in a database, and creates a user profile. The user then takes an initial assessment test. After completing the test, the device sends the results in real time to the server, which uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at the beginner level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues learning using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[1346] This system configuration enables effective and efficient literacy education tailored to each user, supporting the improvement of literacy skills.

[1347] The processing flow will be explained below.

[1348] Step 1:

[1349] The user downloads the application to their smartphone or tablet and launches it.

[1350] Step 2:

[1351] The user enters registration information such as name, email address, and password.

[1352] Step 3:

[1353] The device sends the user's registration information in JSON format to the server.

[1354] Step 4:

[1355] The server stores the received registration information in a database and generates a profile for the new user.

[1356] Step 5:

[1357] The server sends a profile creation success message to the terminal.

[1358] Step 6:

[1359] The terminal displays a message to the user indicating that registration is complete.

[1360] Step 7:

[1361] The user taps the "Start Initial Evaluation Test" button within the app.

[1362] Step 8:

[1363] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[1364] Step 9:

[1365] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[1366] Step 10:

[1367] The terminal transmits the response data to the server in real time.

[1368] Step 11:

[1369] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[1370] Step 12:

[1371] The server stores the analysis results in a database and updates the user's learning profile.

[1372] Step 13:

[1373] The server generates personalized learning modules based on the user's learning style and literacy level.

[1374] Step 14:

[1375] The server sends the generated learning module in JSON format to the terminal.

[1376] Step 15:

[1377] The terminal organizes the received learning modules and displays them to the user.

[1378] Step 16:

[1379] The user taps the displayed button to start the learning module.

[1380] Step 17:

[1381] The terminal sequentially presents the learning modules to the user and records the progress locally.

[1382] Step 18:

[1383] The user completes each piece of content (e.g., reading material, quiz) in sequence.

[1384] Step 19:

[1385] The terminal transmits the progress data of the learning module to the server in batches.

[1386] Step 20:

[1387] The server analyzes the received progress data and tracks the user's learning progress.

[1388] Step 21:

[1389] If the server needs to generate a new learning module, it uses the generation AI again to prepare the next module and send it to the terminal.

[1390] Step 22:

[1391] A server generates multi-sensory content and transmits it to a terminal.

[1392] Step 23:

[1393] The terminal provides multi-sensory content to the user.

[1394] Step 24:

[1395] The user learns by utilizing the presented multi-sensory content.

[1396] Step 25:

[1397] The device records the user's reactions and usage status and sends them to the server.

[1398] Step 26:

[1399] The server analyzes this data and evaluates the user's learning effectiveness.

[1400] Example 1

[1401] 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."

[1402] Conventional educational systems provide uniform learning content, making it difficult to adapt to the learning styles and literacy levels of individual users. This reduces learning effectiveness and hinders efficient literacy improvement. Another problem is the lack of a mechanism for tracking learning progress in real time and providing adaptive learning modules.

[1403] 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.

[1404] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style and literacy level using a generative AI model based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling effective and efficient literacy education that is personalized to the user.

[1405] "User" refers to an individual who uses the system to learn.

[1406] "Registration Information" refers to basic information such as name, email address, and password provided by a User to use the System.

[1407] "Database" refers to a data storage system for storing and managing data such as user registration information and learning status.

[1408] "Initial Assessment Test" refers to a test provided to analyze a user's learning style and literacy level.

[1409] "Learning style" refers to the characteristics of a user's learning method for effectively understanding information, and includes, for example, visual and auditory learning.

[1410] "Literacy level" refers to an indicator that shows the current state of a user's reading and writing ability.

[1411] A "generative AI model" refers to an artificial intelligence model that generates learning content appropriate for users, using AI technology that performs natural language processing, for example.

[1412] A "learning module" refers to a set of learning materials or content that allows a user to study.

[1413] "Terminal" refers to a device, such as a smartphone or tablet, that a user uses to access the system.

[1414] "Progress" refers to the user's achievement and performance as they progress through their studies.

[1415] "Multisensory content" refers to teaching materials and content that enhance learning by using multiple senses, such as sight and hearing.

[1416] The present invention provides a system for supporting users in improving their literacy skills by providing personalized learning modules using a generative AI model. Specific embodiments of the system are described in detail below.

[1417] User Registration

[1418] First, the user must download and install a dedicated application on their device, such as a smartphone or tablet. The user launches the app and enters registration information such as their name, email address, and password. This information is then sent from the device to the server. The server then stores the received data in a database (e.g., PostgreSQL) and creates a new user profile. During this process, the device sends data to the server's API endpoint using an HTTP POST request.

[1419] Initial assessment and learning style analysis

[1420] Once user registration is complete, the next step is to take an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the answer data is sent from the device to the server. Based on the received data, the server uses an AI model (e.g., TensorFlow) to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[1421] Generate learning modules

[1422] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate a personalized learning module suited to the user. The generated learning module is sent to the device and presented to the user. In this case, the server converts complex concepts into simple blocks.

[1423] Delivering learning modules and tracking progress

[1424] A user starts a learning module on their device and checks the content within the module (readings, quizzes, etc.) one by one. The device records the user's progress in real time and sends the data to the server each time the module is completed. The server tracks the progress data and adaptively adjusts and generates the next learning module to be provided based on this data.

[1425] Providing multi-sensory learning modules

[1426] To improve the user's learning effectiveness, the server generates multi-sensory content, such as illustrated learning materials for visual learners and audio learning materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, which is expected to improve understanding and memory.

[1427] Specific examples

[1428] For example, a user downloads a new app and enters information such as their name, email address, and password, which is then sent to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and once the user completes the test, the device sends the results to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. The results indicate that the user is a visual learner and their literacy level is at an elementary level. Based on this, the server generates learning materials with easy-to-understand visual illustrations of simple grammar rules and sends them to the device. The user continues to study using the materials, and their progress is sent from the device to the server. As a next step, the server generates more challenging learning materials and sends them back to the device. This process allows the user to receive a personalized, optimal learning experience.

[1429] Prompt Sentence Examples

[1430] "User registration: The user downloads the app and registers by entering the required information."

[1431] "Initial evaluation test: The user answers the initial evaluation test and sends the results to the server."

[1432] "Learning module generation: The server uses an AI model to analyze the user's learning style and literacy level, generate the optimal learning module, and send it to the device."

[1433] "Progress tracking: When a user completes a learning module, the device sends progress data to the server, which then coordinates and generates the next module."

[1434] This invention enables effective and efficient literacy education tailored to the user, and can support the improvement of literacy.

[1435] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1436] Step 1: User Registration

[1437] 1. The user downloads and installs the application on their smartphone or tablet.

[1438] 2. The user launches the app and enters registration information such as name, email address, and password.

[1439] 3. The device temporarily saves the entered registration information.

[1440] 4. The device sends the entered information to the server as an HTTP POST request.

[1441] Input: User's name, email address, and password

[1442] Data processing: Convert information into JSON format

[1443] Output: Registration information sent to the server

[1444] 5. The server verifies the received data.

[1445] Input: Received registration information

[1446] Data calculation: Email address format verification, password strength check

[1447] Output: Verification result (pass or error)

[1448] 6. If the verification is successful, the server stores the user information in a database and creates a user profile.

[1449] 7. The server returns a registration success response to the terminal.

[1450] Step 2: Provide initial evaluation testing

[1451] 1. After registering, the user clicks on the link to take the initial evaluation test.

[1452] 2. The terminal sends a request for an initial evaluation test to the server.

[1453] Input: User ID

[1454] Data Processing: Request Creation

[1455] Output: The request sent to the server

[1456] 3. The server retrieves the initial evaluation test questions from the database and sends them to the terminal.

[1457] Input: User ID

[1458] Data arithmetic: Selecting appropriate test questions

[1459] Output: Assessment questions sent to the device

[1460] 4. The terminal displays the received assessment test questions.

[1461] 5. The user answers each question in the assessment test.

[1462] Step 3: Submitting assessment data and learning style analysis

[1463] 1. When the user finishes the test, the device temporarily stores the answer data and sends it to the server.

[1464] Input: User response data

[1465] Data processing: Compiling response data

[1466] Output: Response data sent to the server

[1467] 2. The server analyzes the received evaluation data using an AI model.

[1468] Input: Evaluation data

[1469] Data Computing: Analyzing Learning Styles and Literacy Levels Using AI Models

[1470] Output: Analysis results (learning style, literacy level)

[1471] 3. The server stores the analysis results in a database and updates the user's learning profile.

[1472] Step 4: Generate and deliver learning modules

[1473] 1. The server uses a generative AI model to generate learning modules appropriate for the user's learning style and literacy level.

[1474] Input: User's learning profile

[1475] Data Computation: Generating Learning Modules

[1476] Output: The generated learning module

[1477] 2. The server sends the generated learning module to the terminal.

[1478] 3. The terminal displays the received learning module on the user interface.

[1479] 4. The user begins the learning module.

[1480] Step 5: Track your progress and generate the next module

[1481] 1. The device records the user's progress in the learning module in real time.

[1482] Input: User action data

[1483] Data processing: generating progress data

[1484] Output: Progress data

[1485] 2. When the user finishes the learning module, the device sends progress data to the server.

[1486] 3. The server analyzes the received progress data and adaptively adjusts the learning module to be provided next.

[1487] Input: Progress data

[1488] Data calculation: Adjusting the next learning module

[1489] Output: Adjusted learning module

[1490] 4. The server generates a new learning module and sends it to the terminal again.

[1491] Step 6: Creating and delivering multisensory learning modules

[1492] 1. The server generates multi-sensory content according to the user's learning style.

[1493] Input: User's learning profile

[1494] Data Computing: Creating visual and auditory content

[1495] Output: Multisensory learning content

[1496] 2. The server transmits the generated multi-sensory content to the terminal.

[1497] 3. The device displays the multisensory content in the user interface.

[1498] 4. Users learn using multiple senses.

[1499] (Application example 1)

[1500] 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."

[1501] Traditional literacy systems struggle to effectively provide personalized learning experiences tailored to users' learning styles and literacy levels. Furthermore, materials that rely on a single sense often result in inefficient comprehension and retention. Furthermore, they lack the ability to adequately track progress and adjust the generated learning modules accordingly.

[1502] 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.

[1503] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module according to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on the progress, means for generating a learning module based on the user's profile using a generative AI, means for generating multi-sensory content and providing learning materials according to the user's learning style, means for the generated learning module to use a generative AI model that converts content into simple blocks according to the user's literacy level, and means for updating the user's learning profile, thereby providing the user with an optimal learning experience and enabling efficient improvement of literacy.

[1504] "User registration information" refers to information used to identify a user and register them in the system, such as the user's name, email address, and password.

[1505] A "database" is a system that stores data such as user registration information and progress status, and makes it accessible as needed.

[1506] An "initial assessment test" is a test conducted to analyze a user's learning style and current literacy level.

[1507] "Learning style" refers to the way in which a user learns most effectively, and can be visual, auditory, tactile, or other.

[1508] "Literacy level" is an indicator of a user's level of reading ability and comprehension.

[1509] "Personalized Learning Modules" are learning content specifically designed to fit a user's learning style and literacy level.

[1510] "Generative AI" is an artificial intelligence technology that generates new content based on initial input data.

[1511] "Presenting learning content" means displaying learning materials and questions in a form that is accessible to the user.

[1512] "Learning progress" is data that indicates how much of a learning module a user has completed and how much they have learned.

[1513] "Multisensory content" is content that supports learning by utilizing multiple senses, such as sight, hearing, and touch.

[1514] A "generative AI model" is an AI algorithm that generates personalized learning modules based on a user's learning style and literacy level.

[1515] A "learning profile" is comprehensive information that includes a user's learning style, literacy level, progress, and so on.

[1516] A "terminal" is a device such as a smartphone or tablet that a user uses to access a learning module and progress through their learning.

[1517] The present invention is a system for supporting user literacy improvement by providing personalized learning modules using generative AI. The system includes means for receiving user registration information and storing it in a database, means for conducting an initial assessment test, means for generating and providing personalized learning modules based on learning style and literacy level using a generative AI model, means for generating multi-sensory content, and means for tracking the user's learning progress and generating the next learning module.

[1518] Hardware and Software Configuration

[1519] The system is implemented using the following main hardware and software:

[1520] 1. Server:

[1521] Database: Used to store user registration information, initial assessment results, learning progress data, etc.

[1522] Generative AI model: An AI algorithm that generates learning modules based on user profile information. Specifically, a generative AI model such as GPT-2 or similar is used.

[1523] Flask framework: Acts as an application server, managing the reception of data from users and the provision of learning modules.

[1524] 2. Terminal:

[1525] Smartphones and tablets: Devices used by users to download learning modules and progress through their studies. These devices communicate with the server to send and receive data.

[1526] Data processing flow

[1527] 1. User Registration:

[1528] When a user enters registration information such as name, email address, and password, the device sends this information to the server, which stores the received data in a database and creates a profile for the new user.

[1529] 2. Initial assessment and learning style analysis:

[1530] To take an initial assessment test, the device retrieves the assessment questions from the server and displays them to the user. After the user enters their answers, the device sends the answers to the server. The server uses an AI model to analyze this data and determine the user's learning style (e.g., visual, auditory, etc.) and current literacy level.

[1531] 3. Generate learning modules:

[1532] Based on the initial assessment results, the server generates personalized learning modules suited to the user's learning style. Using a generative AI model, it converts complex concepts into simple blocks to generate learning materials, which are then sent to the device.

[1533] 4. Delivering learning modules and tracking progress:

[1534] The user starts and progresses through the learning modules displayed on the device. The device records the user's progress in real time and sends the completed data to the server. The server then adaptively adjusts the next learning module to be provided based on the progress data.

[1535] 5. Providing multi-sensory learning modules:

[1536] To improve the learning effect of users, the server generates learning content that utilizes multiple senses, such as sight and hearing. For example, it provides learning materials with illustrations for visual learners and audio reading materials for auditory learners.

[1537] Specific examples

[1538] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives this information, stores it in a database, and creates a user profile. The user then takes an initial assessment test, and based on the results, is determined to be a visual learner with an elementary literacy level. The server then generates learning materials with simple grammar rules and illustrations appropriate for the user and sends them to the device. As the user progresses with their learning, progress data is sent to the server, which then adaptively generates the next learning module.

[1539] Prompt Sentence Examples

[1540] "Create learning modules for visual learners with beginner literacy levels."

[1541] This process provides users with a personalized and optimal learning experience, which is expected to improve their literacy skills.

[1542] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1543] Step 1:

[1544] A user downloads the application and enters their registration information, such as their name, email address, and password, which the device sends to the server. The server receives the information and stores it in a database. The output is a user profile.

[1545] Step 2:

[1546] The user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user enters their answers, the entered data is sent from the device to the server. Based on the received data, the server uses an AI model to analyze the user's learning style and literacy level. The analysis results are stored in a database and the user's profile is updated as an output.

[1547] Step 3:

[1548] Based on the initial evaluation results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model to generate prompt sentences and creates learning materials based on them. This learning module is then sent from the server to the device. As an output, a learning module tailored to the user's characteristics, such as visual or auditory, is generated.

[1549] Step 4:

[1550] The user starts a learning module displayed on the device and proceeds with their learning. The device sequentially displays the content (readings, quizzes, etc.) within the learning module. As the user proceeds with their learning, their progress is recorded in real time. Based on the input data, the device sends progress data to the server, which tracks their learning progress.

[1551] Step 5:

[1552] The server adjusts and generates the next learning module based on the user's progress data. By analyzing the progress data and adaptively adjusting the next learning module to be provided, the server maximizes the user's learning effect. As an output, the next learning module according to the user's progress is generated and sent to the device.

[1553] Step 6:

[1554] The server generates multisensory content to enhance learning outcomes. Specifically, it provides illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. This involves using a generative AI model to generate appropriate content from prompts. As an output, a multisensory learning module is generated and sent to the device.

[1555] Step 7:

[1556] The results of the user's completed learning module are sent to the server, and the database is updated. The user's learning profile is always updated to the latest version, and this is reflected in the generation of subsequent learning modules. This ensures that optimal learning content is provided to the user without interruption. The learning progress data is updated as an output.

[1557] 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.

[1558] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust learning content according to the user's emotions. This system operates as follows.

[1559] User Registration

[1560] First, a user downloads the system's application onto a device such as a smartphone or tablet and launches it. When creating an account, the user enters registration information such as name, email address, and password. The device then sends this information to the server. The server stores the received data in a database and creates a profile for the new user.

[1561] Initial assessment and learning style analysis

[1562] After user registration is complete, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. Based on this data, the server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level. The analysis results are stored in a database, and the user's learning profile is updated.

[1563] Creating and delivering learning modules

[1564] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level, using generative AI to convert complex concepts into simple blocks, which are then sent from the server to the device and presented to the user.

[1565] Introducing the Emotion Engine

[1566] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and voice to recognize their current emotions (e.g., joy, confusion, fatigue, etc.).

[1567] Dynamic content adjustment based on user emotions

[1568] The recognized emotion data is sent from the device to a server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be reduced or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[1569] Track your learning progress and provide next steps

[1570] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[1571] Providing multi-sensory learning modules

[1572] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[1573] Specific examples

[1574] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[1575] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[1576] The system provides users with a personalized and dynamic learning experience to support literacy development.

[1577] The processing flow will be explained below.

[1578] Step 1:

[1579] A user downloads the application onto a device such as a smartphone or tablet and launches it.

[1580] Step 2:

[1581] The user enters registration information such as name, email address, and password.

[1582] Step 3:

[1583] The device sends the user's registration information in JSON format to the server.

[1584] Step 4:

[1585] The server stores the received registration information in a database and generates a profile for the new user.

[1586] Step 5:

[1587] The server sends a profile creation success message to the terminal.

[1588] Step 6:

[1589] The terminal displays a message to the user indicating that registration is complete.

[1590] Step 7:

[1591] The user taps the "Start Initial Evaluation Test" button within the app.

[1592] Step 8:

[1593] The terminal acquires questions for the initial evaluation test from the server and displays them to the user.

[1594] Step 9:

[1595] The user answers the questions in the evaluation test and presses the send button to send the answers to the terminal.

[1596] Step 10:

[1597] The terminal transmits the response data to the server in real time.

[1598] Step 11:

[1599] The server inputs the received response data into an AI model to analyze the user's learning style and current literacy level.

[1600] Step 12:

[1601] The server stores the analysis results in a database and updates the user's learning profile.

[1602] Step 13:

[1603] The server generates personalized learning modules based on the user's learning style and literacy level.

[1604] Step 14:

[1605] The server sends the generated learning module in JSON format to the terminal.

[1606] Step 15:

[1607] The terminal organizes the received learning modules and displays them to the user.

[1608] Step 16:

[1609] The user taps the displayed button to start the learning module.

[1610] Step 17:

[1611] The terminal sequentially presents the learning modules to the user and records the progress locally.

[1612] Step 18:

[1613] The emotion engine analyzes the user's facial expressions and voice in real time while using the learning module and generates emotion data.

[1614] Step 19:

[1615] The terminal transmits the emotion data to the server.

[1616] Step 20:

[1617] The server analyzes the received emotion data and dynamically adjusts the learning content based on the user's emotion.

[1618] Step 21:

[1619] The user completes each piece of content (e.g., reading material, quizzes) in the learning module in sequence.

[1620] Step 22:

[1621] The terminal transmits the progress data of the learning module to the server in batches.

[1622] Step 23:

[1623] The server stores the received progress data and emotion data in a database to track the user's learning status.

[1624] Step 24:

[1625] If the server needs to generate a new learning module, it uses the generation AI again to generate the next module and sends it to the terminal.

[1626] Step 25:

[1627] The server generates multi-sensory content (e.g., illustrated learning materials for visual learners, audio reading materials for auditory learners) and transmits it to the terminal.

[1628] Step 26:

[1629] The terminal provides multi-sensory content to the user.

[1630] Step 27:

[1631] Users engage in interactive learning through multi-sensory content.

[1632] Step 28:

[1633] The device records the user's reactions and usage status and sends them to the server.

[1634] Step 29:

[1635] The server analyzes this data and evaluates the user's learning effectiveness.

[1636] Example 2

[1637] 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."

[1638] Conventional literacy education systems often provide uniform learning content because they are unable to fully reflect the learning styles and emotional states of individual learners. This can lead to differences in learner comprehension and proficiency, making efficient learning difficult. Furthermore, conventional systems struggle to dynamically adjust learning content based on real-time emotional analysis, making it difficult to maintain learner motivation.

[1639] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1640] In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module based on the results of the initial assessment test in accordance with the user's learning style, means for providing the generated learning module to the user's terminal and presenting learning content, means for recognizing the user's emotions in real time and transmitting the emotion data to the server, means for dynamically adjusting the learning content based on the emotion data, and means for tracking the user's learning progress and generating the next learning module based on the tracking, thereby enabling a personalized learning experience and dynamic adjustment of the learning content based on real-time emotion analysis.

[1641] "User" refers to an individual who uses the system to perform learning activities.

[1642] "Registration Information" refers to basic personal information such as name, email address, and password that a User provides when first accessing the System.

[1643] "Database" refers to data storage within the System for storing user registration information, learning profiles, progress data, emotional data, etc.

[1644] "Initial Assessment Test" refers to a series of questions or tasks provided by the system to assess a user's learning style and literacy level.

[1645] "Learning style" refers to the method or technique (e.g., visual, auditory, etc.) that a user uses to learn most effectively.

[1646] "Literacy level" refers to the result of assessing the user's current literacy skills, such as reading and writing ability and vocabulary.

[1647] "Learning Module" refers to system-generated learning materials and activities that are customized to a user's learning style and literacy level.

[1648] "Generative AI" refers to a system component that automatically generates content for learning modules using machine learning models and artificial intelligence techniques.

[1649] An "emotion engine" refers to software or algorithms that analyze a user's real-time facial expressions and voice to recognize their emotional state.

[1650] "Emotion data" refers to information indicating the user's emotional state (e.g., joy, confusion, fatigue, etc.) recognized by the emotion engine.

[1651] "Progress" refers to data indicating how far a user has progressed through a learning module.

[1652] This invention is a literacy education system that combines a generative AI model and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system consists of three main components: a server, a terminal, and a user.

[1653] User Registration

[1654] A user downloads and launches the system application onto a device such as a smartphone or tablet. The user enters registration information such as name, email address, and password. The device sends this information to the server, which stores the received data in a database. A new user profile is created and registration is complete.

[1655] Initial assessment and learning style analysis

[1656] After completing user registration, the user takes an initial assessment test. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the device sends the answer data to the server. The server uses an AI model to analyze the user's learning style (visual, auditory, etc.) and current literacy level, and stores the results in a database.

[1657] Creating and delivering learning modules

[1658] Based on the results of the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Generative AI is used to convert complex concepts into simple blocks, and the learning module is then sent from the server to the device. The user progresses through the learning module.

[1659] Introducing the Emotion Engine

[1660] While using the learning module, an emotion engine runs on the device to recognize the user's emotions in real time. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions (e.g., joy, confusion, fatigue, etc.). Emotion data is sent from the device to the server.

[1661] Dynamic content adjustment based on user emotions

[1662] The server dynamically adjusts learning content based on the recognized emotion data. For example, if the user is confused, it may reduce the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it may provide more challenging content, optimizing the user's learning experience.

[1663] Track your learning progress and provide next steps

[1664] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next module to be provided. This data is stored in a database and is also used to analyze long-term learning patterns.

[1665] Providing multi-sensory learning modules

[1666] In addition, the server generates and transmits multi-sensory content to the device, providing illustrated learning materials for visual learners and audio-reading materials for auditory learners, allowing users to learn using multiple senses and facilitating comprehension and retention.

[1667] Specific examples

[1668] For example, a user downloads a new app, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level, and determines that they are a visual learner and their literacy level is beginner. Based on this, the server generates learning materials with simple illustrations of grammar rules and sends them to the device.

[1669] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device. This provides the user with an optimal learning experience and effectively supports the improvement of literacy skills.

[1670] Prompt Sentence Examples

[1671] Please list the information required for new user registration.

[1672] "Please provide an example of an initial assessment test to analyze users' learning styles."

[1673] "Please explain the types of emotions the emotion engine can recognize."

[1674] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1675] Step 1: User Registration

[1676] A user downloads and launches the system application on a device such as a smartphone or tablet. After the user enters registration information such as name, email address, and password, the device sends this information to the server as a JSON-formatted object. The server verifies the received data and stores it in a database. It then generates a new user profile and sends a registration completion notification to the device. The input of this step is the user's basic information, and the output is the user's profile data stored in the database.

[1677] Step 2: Initial assessment and learning style analysis

[1678] Once user registration is complete, the device retrieves assessment test questions from the server to present the user with an initial assessment test. When the user answers the test questions, the device sends the answer data in JSON format to the server. The server uses an AI model (e.g., TensorFlow or PyTorch) to analyze the user's learning style and literacy level based on the answer data. The analysis results are stored in a database, and the user's learning profile is updated. The input of this step is the user's answer data, and the output is the analysis results of the learning style and literacy level.

[1679] Step 3: Generate and deliver learning modules

[1680] Based on the initial assessment results, the server generates a personalized learning module suited to the user's learning style and literacy level. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to convert concepts into simple blocks. The generated learning module is sent from the server to the device in HTML or Markdown format and presented to the user. The input of this step is the analysis results of the learning style and literacy level, and the output is a personalized learning module.

[1681] Step 4: Implementing the Emotion Engine

[1682] While the learning module is in use, an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) runs on the device to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize their current emotion (e.g., joy, confusion, fatigue, etc.). The recognized emotion data is sent to the server in JSON format. The input of this step is the user's facial expression and voice data, and the output is the recognized emotion data.

[1683] Step 5: Dynamically adjust content based on user sentiment

[1684] Based on the recognized emotion data, the server dynamically adjusts the learning content. For example, if the user is confused, the server may lower the difficulty of the learning material or generate additional explanations and send them to the device. Conversely, if the user is satisfied, the server may adjust the content to provide more challenging content. The input of this step is emotion data, and the output is an adjusted learning module.

[1685] Step 6: Track learning progress and provide next steps

[1686] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts and generates the next learning module to provide. The progress data includes the completion status and correct answer rate for each learning module. This data is sent to the server in JSON format and stored in a database. The input of this step is the learning progress data and emotion data, and the output is the next learning module.

[1687] Step 7: Provide multisensory learning modules

[1688] The server generates multisensory content (visual, auditory, etc.) and sends it to the device. Specifically, it uses image processing libraries (e.g., Pillow or OpenCV) and speech synthesis software (e.g., Google Text-to-Speech API) to provide illustrated learning materials for visual learners and audio-readable learning materials for auditory learners. The generated content is sent from the server to the device in file format (e.g., JPEG, MP3). The input of this step is the user's learning style data, and the output is a multisensory learning module.

[1689] (Application example 2)

[1690] 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."

[1691] While conventional literacy education systems can provide personalized learning modules tailored to a user's learning style and literacy level, they lack the ability to dynamically adjust learning content based on the user's emotions. This makes it difficult to maintain the user's interest and concentration, limiting the effectiveness of learning. In particular, systems that can respond to changing user emotions in real time are needed for the education and training of store clerks in brick-and-mortar stores.

[1692] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user registration information and storing it in a database, means for providing an initial assessment test to analyze the user's learning style and literacy level, means for generating a personalized learning module tailored to the user's learning style based on the results of the initial assessment test, means for providing the generated learning module to the user's terminal and presenting learning content, means for tracking the user's learning progress and generating the next learning module based on this, and means for recognizing the user's emotions in real time and dynamically adjusting the learning content based on the emotion data. This enables the learning content to be adapted based on the user's emotions, providing an effective learning experience, particularly in the education and training of store clerks in physical stores.

[1693] "User registration information" refers to a user's personal information and basic profile information in the system, including name, email address, password, etc.

[1694] A "database" is a digital storage system that stores registered user information, learning progress, emotional data, etc., and retrieves and references them as needed.

[1695] An "initial assessment test" is an assessment test conducted to measure a user's learning style and current literacy level or learning ability.

[1696] "Learning style" refers to the way in which a user most effectively absorbs information during learning, and includes visual, auditory, tactile, and other styles.

[1697] "Literacy level" is an indicator of a user's level of ability to understand, read, and write a language.

[1698] A "personalized learning module" is a collection of learning materials and content optimized for each user's learning style and literacy level based on the results of an initial assessment test.

[1699] "Means for presenting learning content" refers to a method or device for providing the created learning module to the user's terminal and displaying and playing it.

[1700] "Study progress" is data that indicates the results and level of achievement achieved by the user through their learning activities.

[1701] "Dynamic adjustment" refers to optimizing and changing learning content on an ongoing basis based on data obtained in real time.

[1702] The "emotion engine" is a system that recognizes emotions in real time by analyzing the user's facial expressions and voice.

[1703] This invention is a literacy education system that combines generative AI and an emotion engine to provide a personalized learning experience and dynamically adjust the learning content according to the user's emotions. This system is particularly effective in educating and training store staff in brick-and-mortar stores.

[1704] System Configuration

[1705] The system consists of the following main components:

[1706] 1. Server

[1707] 2. Devices (smartphones, tablets)

[1708] 3. Emotion Engine

[1709] 4. Generative AI Models

[1710] User Registration

[1711] First, a user downloads the system's application onto their smartphone or tablet. Then, they launch the application and enter their registration information, such as their name, email address, and password. This information is sent from the device to the server and stored in a database. The server then creates a profile for the new user.

[1712] Initial assessment and learning style analysis

[1713] Once user registration is complete, the user takes an initial assessment test. This test is conducted to analyze the user's learning style and literacy level. The device retrieves the assessment test questions from the server and displays them to the user. When the user answers the questions, the data is sent from the device to the server. The server uses an AI model based on this data to analyze the user's learning style and literacy level, and stores the results in a database.

[1714] Creating and delivering learning modules

[1715] Based on the initial assessment, the server generates a personalized learning module suited to the user's learning style and literacy level. Using a generative AI model, complex concepts are transformed into simple blocks, and this learning module is sent from the server to the device and presented to the user.

[1716] Introducing the Emotion Engine

[1717] While using the learning module, the device is equipped with an emotion engine that recognizes the user's emotions in real time. Specifically, it uses a camera to analyze the user's facial expressions and voice to recognize emotions (e.g., joy, confusion, fatigue, etc.). This is done using software such as Keras and OpenCV.

[1718] Dynamic content adjustment based on user emotions

[1719] The emotion data recognized by the emotion engine is sent from the device to the server, which then dynamically adjusts the learning content based on that data. For example, if the user is confused, the difficulty level of the learning material can be lowered or additional explanations can be provided. Conversely, if the user is satisfied, more challenging content can be provided.

[1720] Track your learning progress and provide next steps

[1721] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotional data and adjusts the next module to be provided. The emotional data is also stored in a database and used to analyze long-term learning patterns.

[1722] Providing multi-sensory learning modules

[1723] In addition, the server generates and transmits multi-sensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, to the device, allowing users to learn using multiple senses and promoting comprehension and memorization.

[1724] Specific examples

[1725] For example, a user downloads a new application, enters their registration information, and sends it to the server. The server receives it and stores it in a database. The user then takes an initial assessment test, and the results are sent to the server in real time. The server uses an AI model to analyze the user's learning style and literacy level. If the results show that the user is a visual learner and their literacy level is beginner, the server will generate a simple illustrated grammar rule learning material and send it to the device.

[1726] As the user progresses with their learning, the emotion engine recognizes their emotions and sends them from the device to the server. For example, if the user is confused, the server can lower the difficulty of the learning material or generate additional explanations and send them to the device.

[1727] Prompt Sentence Examples

[1728] “Deviate a system where an emotion engine can sense when a store clerk is confused, and the learning difficulty or additional explanations are adjusted based on that emotion data.

[1729] Input data: face image, recognized emotion data, user ID

[1730] Output data: Type of learning module (difficulty adjustment, additional learning materials)

[1731] Libraries used: Keras, OpenCV, requests

[1732] This system provides a personalized and dynamic learning experience tailored to the user, effectively supporting sales associate training in brick-and-mortar stores.

[1733] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1734] Step 1: Enter and save your user registration information

[1735] The user downloads the application onto their smartphone or tablet and launches it. The user enters registration information such as their name, email address, and password. The device sends this information to the server, which then stores the received data in a database. Input data: User's personal information. Output data: User profile stored in the database.

[1736] Step 2: Providing and conducting initial evaluation tests

[1737] The server provides an initial assessment test to analyze the user's learning style and literacy level. The terminal retrieves the assessment test questions from the server and displays them to the user. After the user answers the questions, the terminal sends the answer data to the server. Input data: User's answer data. Output data: Analysis results of the user's learning style and literacy level.

[1738] Step 3: Generate and deliver personalized learning modules

[1739] Based on the results of the initial assessment test, the server generates a personalized learning module suited to the user's learning style and literacy level. A generative AI model is used to convert complex concepts into simple blocks. This learning module is sent from the server to the device and presented to the user. Input data: User's learning style and literacy level. Output data: Personalized learning module.

[1740] Step 4: Real-time recognition of user emotions by the emotion engine

[1741] The device's camera is used to capture the user's facial expressions and voice in real time. Keras and OpenCV are used to recognize emotions and analyze the data. The emotion data is sent from the device to the server. Input data: User's facial expressions and voice. Output data: Recognized emotion data.

[1742] Step 5: Dynamically adjust learning content based on emotional data

[1743] The server dynamically adjusts the learning content based on the received emotional data. For example, if the user is confused, it will lower the difficulty of the learning material or provide additional explanations. Conversely, if the user is satisfied, it will provide more challenging content. Input data: Recognized emotional data. Output data: Adjusted learning content.

[1744] Step 6: Submit your learning progress data and receive next steps

[1745] When a user completes a learning module, the device sends the progress data to the server. The server tracks the user's learning status based on the progress data and emotion data, and adjusts the next learning module to be provided. Input data: learning progress data and emotion data. Output data: next learning module.

[1746] Step 7: Provide multisensory learning modules

[1747] The server generates multisensory content, such as illustrated learning materials for visual learners and audio-reading materials for auditory learners, and sends it to the device. This allows users to learn using multiple senses, promoting comprehension and memorization. Input data: User's learning style. Output data: Multisensory learning module.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] 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.

[1753] 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.

[1754] 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).

[1755] 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.

[1756] 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."

[1757] 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.

[1758] 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).

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] The following is further disclosed regarding the above embodiment.

[1770] (Claim 1)

[1771] means for receiving and storing user registration information in a database;

[1772] means for providing an initial assessment test to analyze the user's learning style and literacy level;

[1773] A means for generating a personalized learning module according to the user's learning style based on the results of the initial evaluation test;

[1774] A means for providing the generated learning module to a user's terminal and presenting the learning content;

[1775] means for tracking the user's learning progress and generating the next learning module based thereon;

[1776] A system including:

[1777] (Claim 2)

[1778] means for generating and providing multi-sensory content to users in providing initial assessment tests and learning modules;

[1779] The system of claim 1 further comprising:

[1780] (Claim 3)

[1781] The generated learning module uses a generative AI to convert the content into simple blocks according to the user's literacy level;

[1782] 10. The system of claim 1, comprising:

[1783] "Example 1"

[1784] (Claim 1)

[1785] means for receiving and storing user registration information in a database;

[1786] means for providing an initial assessment test to analyze the user's learning style and literacy level;

[1787] a means for generating personalized learning modules based on the results of the initial assessment test using a generative AI model, the personalized learning modules being tailored to the user's learning style and literacy level;

[1788] A means for providing the generated learning module to a user's terminal and presenting the learning content;

[1789] means for tracking the user's learning progress and generating the next learning module based thereon;

[1790] A system including:

[1791] (Claim 2)

[1792] means for generating and providing multi-sensory content to users in providing initial assessment tests and learning modules;

[1793] The system of claim 1 further comprising:

[1794] (Claim 3)

[1795] The generated learning module uses a generative AI to convert the content into simple blocks according to the user's literacy level;

[1796] 10. The system of claim 1, comprising:

[1797] "Application Example 1"

[1798] (Claim 1)

[1799] means for receiving and storing user registration information in a database;

[1800] means for providing an initial assessment test to analyze the user's learning style and literacy level;

[1801] A means for generating a personalized learning module according to the user's learning style based on the results of the initial evaluation test;

[1802] A means for providing the generated learning module to a user's terminal and presenting the learning content;

[1803] means for tracking the user's learning progress and generating the next learning module based thereon;

[1804] a means for generating a learning module based on a user's profile using a generative AI;

[1805] A system including:

[1806] (Claim 2)

[1807] means for generating multi-sensory content and providing educational materials according to a user's learning style;

[1808] The system of claim 1 further comprising:

[1809] (Claim 3)

[1810] The generated learning module uses a generative AI model that converts content into simple blocks according to the user's literacy level;

[1811] means for updating a user's learning profile;

[1812] 10. The system of claim 1, comprising:

[1813] "Example 2: Combining Emotion Engines"

[1814] (Claim 1)

[1815] means for receiving and storing user registration information in a database;

[1816] means for providing an initial assessment test to analyze the user's learning style and literacy level;

[1817] A means for generating a personalized learning module according to the user's learning style based on the results of the initial evaluation test;

[1818] A means for providing the generated learning module to a user's terminal and presenting the learning content;

[1819] means for recognizing a user's emotion in real time and transmitting the emotion data to a server;

[1820] a means for dynamically adjusting learning content based on emotion data;

[1821] means for tracking the user's learning progress and generating the next learning module based thereon;

[1822] A system including:

[1823] (Claim 2)

[1824] means for generating and providing multi-sensory content to users in providing initial assessment tests and learning modules;

[1825] The generated learning module uses a generative AI to convert the content into simple blocks according to the user's literacy level;

[1826] The system of claim 1 further comprising:

[1827] (Claim 3)

[1828] A means for analyzing a user's emotions using an emotion engine and dynamically adjusting learning content based on the emotion data;

[1829] The system of claim 1 further comprising:

[1830] "Application example 2 when comb...

Claims

1. means for receiving and storing user registration information in a database; means for providing an initial assessment test to analyze the user's learning style and literacy level; A means for generating a personalized learning module according to the user's learning style based on the results of the initial evaluation test; A means for providing the generated learning module to a user's terminal and presenting the learning content; means for tracking the user's learning progress and generating the next learning module based thereon; A system including:

2. means for generating and providing multi-sensory content to users in providing initial assessment tests and learning modules; The system of claim 1 further comprising:

3. The generated learning module uses a generative AI to convert the content into simple blocks according to the user's literacy level; The system of claim 1 , comprising:

Images