system

Abstract

A system is provided.SOLUTION: A system, comprising: means for a user to post learning data; server means for collecting and accumulating the posted learning data; means for a generative AI model to design a learning plan using the collected learning data; means for providing the designed learning plan to the user; and PDCA cycle means for improving the generative AI model based on the collected learning data.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] This invention relates to a method and system for eliminating educational disparities caused by income disparities, and aims to enable students from low-income families to receive effective learning guidance by providing a low-cost learning content design service.By providing learning opportunities that are not dependent on parental income, we aim to achieve equal educational opportunities and improve academic ability throughout society. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. Specifically, a system is provided that includes: a means for users to post study data; a server means for collecting and storing the posted study data; a means for a generative AI model to design a study plan using the collected data; a means for providing the designed study plan to the user; and a PDCA cycle means for improving the generative AI model based on the collected data. This makes it possible to provide optimal study plans to each user at low cost and reduce educational disparities. Furthermore, by basing the system on the user's study progress and test results, efficient study guidance tailored to individual learning is realized.

[0006] "User" refers to a user who posts study data and proceeds with study according to the provided study plan.

[0007] "Study data" refers to information such as study progress and test results posted by users to the system.

[0008] "Server" refers to the computer system that collects and stores submitted learning data and runs the generative AI model to design learning plans.

[0009] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates the optimal learning plan for each user based on collected learning data.

[0010] "Study plan" refers to the optimal learning content and recommended learning material list provided to the user, designed by the generative AI model.

[0011] "PDCA cycle" stands for Plan-Do-Check-Act and refers to the process of repeatedly collecting learning data, designing a generative AI model, and evaluating and improving it in a system. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. This system allows users to submit study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle.

[0034] System Overview

[0035] The system includes the following elements:

[0036] 1. User terminal: A device for users to input and post learning data.

[0037] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[0038] 3. Generative AI model: An algorithm that generates an optimal learning plan based on each user's data.

[0039] 4. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[0040] Program processing overview

[0041] 1. User submits training data:

[0042] A user submits their learning progress and test results to the system through an input form. For example, a junior high school student enters their math test score as "75 points" and submits the test date as "2023-10-15." The server receives the data.

[0043] 2. The server collects and stores the data:

[0044] The server stores the learning data posted by users in a database, allowing all users' learning data to be managed centrally.

[0045] 3. Designing lesson plans using generative AI models:

[0046] Based on the data stored on the server, the generative AI model designs a study plan for each user. For example, if a user's math test reveals that they have weak areas, the model will recommend additional practice problems and explanatory videos.

[0047] 4. Provide users with a learning plan:

[0048] The server provides the generated study plan to the user, who can then log in to view their own study plan and proceed with their studies according to the recommended study content.

[0049] 5. Implementing the PDCA cycle:

[0050] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan.

[0051] Specific examples

[0052] For example, imagine a high school student is using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need improvement (e.g., basic electromagnetism) and generates a study plan that includes practice problems and reference videos specific to that area. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[0053] This system of the present invention makes it possible to provide high-quality educational instruction at low cost, especially to students from low-income families. Furthermore, by implementing the PDCA cycle, the accuracy of the generative AI model is continuously improved, enabling the provision of learning plans that are more tailored to individual needs.

[0054] The processing flow will be explained below.

[0055] Step 1: User submits training data

[0056] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[0057] Step 2: The server receives and stores the data

[0058] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0059] Step 3: The server uses the generative AI model to design a learning plan

[0060] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0061] Step 4: The server provides the lesson plan to the user

[0062] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0063] Step 5: The server executes the PDCA cycle to improve the model

[0064] Every time a user periodically submits new learning data, that data is collected and stored in a database. The server retrains the generative AI model using the latest learning data, improving the model's accuracy. This ensures that future learning plans are more suited to the user's needs. The effectiveness of the plan is evaluated, and insights gained from the data are reflected to continuously improve the model.

[0065] Example 1

[0066] 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."

[0067] In modern society, income disparities cause educational disparities, making it difficult for students from low-income families to access high-quality education. The present invention aims to provide a system that reduces this educational disparity and enables all students to learn effectively.

[0068] 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.

[0069] In this invention, the server includes a means for users to post learning data, a database means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, a means for providing the designed learning plan to the user, and a PDCA cycle means for improving the generative AI model based on the collected data, which makes it possible to provide an optimal learning plan based on individual learning progress and needs.

[0070] "User" means an individual or organization that uses the System to input and post learning data.

[0071] "Study data" refers to data such as study progress and test results that users enter and post into the system.

[0072] "Means for posting" refers to an interface or device that allows a user to input and transmit learning data into the system.

[0073] The "database means for collecting and storing" is a database system for receiving and centrally managing submitted learning data.

[0074] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[0075] The "means of designing a learning plan" is the process of using a generative AI model to create an optimal learning plan for each user.

[0076] The "means of providing" refers to an interface or system that allows users to view the designed learning plan.

[0077] The "PDCA cycle method" is a process for continuously improving the generative AI model based on collected data.

[0078] The "system" refers to the overall mechanism for eliminating educational disparities, including the measures mentioned above.

[0079] This invention is a system designed to eliminate educational disparities, particularly those caused by income disparities. This system allows users to input and post learning data, and a generative AI model then proposes an optimal learning plan based on that data. Furthermore, it includes a mechanism for improving the accuracy of the generative AI model through the PDCA cycle.

[0080] Hardware and software used

[0081] Hardware

[0082] 1. User terminal: A device used by users to input and post learning data. Specifically, this includes PCs, smartphones, tablets, etc.

[0083] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. It uses a high-performance server machine.

[0084] software

[0085] 1. Database system: A database for centrally managing the submitted learning data. A relational database management system such as MySQL or PostgreSQL is used.

[0086] 2. Generative AI model: An algorithm that generates the optimal learning plan based on user data. In this case, we use GPT-4, a generative natural language model.

[0087] 3. Web application: An interface for users to input learning data and a platform for displaying the generated learning plan. It uses a front-end framework such as React or Vue.js and a back-end framework such as Django or Flask.

[0088] Data processing and calculation

[0089] 1. Users submit their training data

[0090] The user enters their learning progress and test results into the form and presses the send button. This data is sent from the user's device to the server.

[0091] Example: A junior high school student user enters the math test result "75 points" and the test date "2023-10-15" and submits it.

[0092] 2. The server collects and stores data

[0093] The server stores the received data in a database, where all user learning data is managed in a unified manner.

[0094] Software used: MySQL

[0095] Example: Insert data into the database using the SQL query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[0096] 3. The server designs a learning plan using the generative AI model

[0097] Based on the data stored on the server, the generative AI model designs the optimal learning plan for each user. The generative AI model calls the GPT-4 model using a Python script.

[0098] Software used: GPT-4

[0099] Example: Send the prompt "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user."

[0100] 4. The server provides the study plan to the user

[0101] The generated learning plan is displayed on the user's dashboard, where the user can log in and view their own learning plan.

[0102] Software used: React, Django

[0103] Example: Displaying the following on the dashboard: "Your study plan for the next week: We provide practice questions and helpful video links to help you focus on 'Fundamentals of Electromagnetism.'"

[0104] 5. The server executes the PDCA cycle

[0105] The server continuously collects new training data and retrains the generative AI model to improve the accuracy of its learning plans, using machine learning libraries such as TensorFlow and PyTorch.

[0106] Software used: TensorFlow, PyTorch

[0107] Example: Once a month, run a script called "train.py" that retrains your AI model based on newly collected data.

[0108] In this way, the system provides a customized learning plan for each user, making it a powerful tool for narrowing educational gaps.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] Users post training data.

[0112] Input: Users enter their learning progress and test results into an input form.

[0113] Data processing: The contents of the input form are sent from the user's terminal to the server.

[0114] Output: The training data is sent to the server.

[0115] Specific operation: A user accesses a web application and navigates to a form page for learning management. For example, a junior high school student enters their math test score (75 points) and the test date (2023-10-15), and clicks the submit button.

[0116] Step 2:

[0117] The server collects and stores the data.

[0118] Input: Training data submitted by the user.

[0119] Data processing: Sanitize the received data and insert it into the database using SQL queries.

[0120] Output: Training data stored in a database.

[0121] What it does: The server formats the data it receives and inserts it into the MySQL database using the query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[0122] Step 3:

[0123] The server designs a learning plan using a generative AI model.

[0124] Input: User learning data stored in a database.

[0125] Data processing: Send prompts to the generative AI model based on data retrieved from the database.

[0126] Output: The generated learning plan.

[0127] Specific operation: The server runs a Python script and sends the prompt message "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user" to the generative AI model (GPT-4), and the AI ​​model then generates a study plan.

[0128] Step 4:

[0129] The server provides the lesson plan to the user.

[0130] Input: The generated learning plan.

[0131] Data processing: Embed the learning plan into an HTML template and render it as a web page.

[0132] Output: The lesson plan provided to the user.

[0133] Specific operation: The server embeds the generated study plan on the user's dashboard page, and the user can log in and check their own study plan. For example, the dashboard will display "Your study plan for the next week: We will provide practice questions and reference video links to focus on studying 'Fundamentals of Electromagnetism'."

[0134] Step 5:

[0135] The server executes the PDCA cycle.

[0136] Input: New training data.

[0137] Data processing: Add new data to the dataset and retrain the AI ​​model using machine learning libraries.

[0138] Output: A generative AI model with improved accuracy.

[0139] What it does: The server periodically runs a Python script to add newly collected data to the dataset and retrain the model with a script called “train.py.”

[0140] (Application example 1)

[0141] 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."

[0142] The challenge is to eliminate the educational disparity caused by income disparity and provide high-quality educational instruction, especially to students from low-income families. Furthermore, it is necessary to create an environment in which students can study efficiently by providing easy-to-use study plans on smartphones.

[0143] 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.

[0144] In this invention, the server includes a means for users to post study data, a server means for collecting and storing the posted study data, a means for a generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a PDCA cycle means for improving the generative AI model based on the collected data, a means for users to post study data from a smartphone, and a means for presenting the generated study plan on the smartphone. This makes it possible to eliminate educational disparities and provide an efficient learning environment where students can concentrate on their studies.

[0145] We have created definitions for the following important words:

[0146] The "means for users to post learning data" refers to an interface that allows users to input learning data such as their own learning progress and test results and send it to the system.

[0147] The "server means for collecting and storing submitted learning data" refers to a server device and database mechanism for receiving and centrally managing learning data sent by users.

[0148] The "means by which the generative AI model designs a learning plan using collected data" refers to the AI ​​algorithms and calculation mechanisms that analyze the accumulated learning data and generate an optimal learning plan for each user.

[0149] The "means for providing the designed lesson plan to the user" is an interface and notification system that informs the user of the created lesson plan and allows them to execute it.

[0150] The "PDCA cycle method for improving generative AI models based on collected data" is a process of continuously collecting new training data and repeating the cycle of planning (Plan), doing (Do), evaluating (Check), and improving (Act) to improve the accuracy of generative AI models.

[0151] "Means for users to post learning data from their smartphones" refers to applications and interfaces for inputting and sending learning data using a smartphone.

[0152] The "means for presenting the generated study plan on a smartphone" refers to an application and an interface for visually displaying the study plan generated on the smartphone to the user.

[0153] This invention is a system for eliminating educational disparities, particularly reducing inequalities in educational opportunities due to income disparities. This system allows users to upload their own learning data using their smartphones, and a generative AI model then designs an optimal learning plan based on that data and provides it to the user. It also has a function for improving the accuracy of the generative AI model using the PDCA cycle.

[0154] System Overview

[0155] The system is broadly composed of the following elements:

[0156] 1. User device: A smartphone used by the user to input and post learning data.

[0157] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a cloud server is used to host the database and AI models.

[0158] 3. Generative AI models: Algorithms that generate optimal learning plans based on each user's data. These typically use Python and scikit-learn.

[0159] 4. PDCA cycle: The process of continuously collecting learning data and retraining the AI ​​model.

[0160] Program processing

[0161] 1. User Data Submission:

[0162] Users can submit their study progress and test results to the system via an input form on their smartphones. This data includes test scores, study time, weak areas, etc.

[0163] 2. Data collection and storage:

[0164] The server receives the data posted by users and stores it in a database, allowing all users' learning data to be managed centrally.

[0165] 3. Designing a learning plan:

[0166] Using data stored on the server, the generative AI model designs an optimal learning plan for each individual user, for example, recommending additional practice problems or explanatory videos to users who struggle with math.

[0167] 4. Providing a study plan:

[0168] The server then sends the generated study plan to the user's smartphone, where the user can review it and proceed with their studies according to the suggested study content.

[0169] 5. Implementing the PDCA cycle:

[0170] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan and providing more personalized learning.

[0171] Specific examples

[0172] For example, if a student scores 45 points on a physics test, they can submit that data from their smartphone. The server receives the information and stores it in a database. The generative AI model uses this data to generate recommendations, such as "Watch a video on the basics of electromagnetism." This recommendation is then sent to the user's smartphone, allowing them to proceed with their studies according to the submitted study plan.

[0173] An example of a prompt is:

[0174] "Please generate a study plan based on the following user data: User ID: 1, Subject: Physics, Score: 45 points, Date: 2023-10-20."

[0175] The text format is used.

[0176] In this way, this system aims to correct educational disparities and can provide a comfortable and efficient learning environment by using users' smartphones.

[0177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0178] Step 1:

[0179] The user posts their study data from their smartphone. Specifically, the user launches the application, enters their study progress and test results into the input form, and presses the submit button. At this time, input includes test scores, subjects, date and time, etc. The submitted data is sent from the smartphone to the server.

[0180] Step 2:

[0181] The server collects the learning data sent by the user and stores it in a database. The server analyzes the received data and converts it into an appropriate format for saving in the database. For example, data such as "User ID: 1, Subject: Physics, Score: 45 points, Date and Time: 2023-10-20" is saved in the corresponding field in the database. In this process, the input is the submitted raw data, and the output is the data stored in the database.

[0182] Step 3:

[0183] The server uses a generative AI model to design a learning plan based on the accumulated data. Specifically, it analyzes the collected learning data and recommends additional learning resources based on each user's grades and progress. For example, for a user who received a 45 in physics, a recommendation to "watch basic physics videos" is generated. The input here is the learning data stored in the database, and the output is a learning plan for the user.

[0184] Step 4:

[0185] To provide the generated study plan to the user, the server sends a notification to the user's smartphone. The user can then check the generated study plan through their smartphone. Specifically, the recommended study content is displayed on the application's dashboard. The input here is the generated study plan, and the output is the recommended content displayed on the user's smartphone.

[0186] Step 5:

[0187] The server continues to collect new training data and executes a PDCA cycle to improve the generative AI model. In this cycle, the AI ​​model is retrained based on the new data collected, improving its accuracy. For example, data from users with new test results is added, and the model's performance is evaluated and improved against previous recommendations. The input is new training data, and the output is an improved generative AI model.

[0188] Through the above steps, the system of the present invention provides users with efficient and personalized learning plans, contributing to the elimination of educational disparities. Furthermore, the system's simple operation on a smartphone improves user convenience.

[0189] 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.

[0190] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users post their study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention realizes adjustments to the study plan according to the user's emotional state.

[0191] System Overview

[0192] The system includes the following elements:

[0193] 1. User terminal: A device for users to input and post learning data.

[0194] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[0195] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data.

[0196] 4. Emotion Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan.

[0197] 5. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[0198] Program processing overview

[0199] 1. User submits training data:

[0200] Users submit their learning progress and test results to the system through an input form. For example, if a middle school student user gets 75 points on a math test, they enter the score and the test date (2023-10-15) and submit. When the user presses the submit button, the data is sent to the server.

[0201] 2. The server receives and stores the data:

[0202] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0203] 3. The server designs a learning plan using the generative AI model:

[0204] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0205] 4. Emotion engine analyzes user emotions:

[0206] Emotional data is collected while the user is studying, and the emotion engine analyzes the data. For example, if the user feels tired after studying for a long time, the system will recognize that emotional state.

[0207] 5. Generative AI models adjust learning plans:

[0208] The server takes into account the analysis results of the emotion engine and provides feedback to the generative AI model to adjust the study plan according to the user's emotional state. For example, if the user feels tired, the study plan will include breaks for relaxation and lighter learning content.

[0209] 6. The server provides the study plan to the user:

[0210] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0211] 7. Implementing the PDCA cycle:

[0212] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[0213] Specific examples

[0214] For example, consider a high school student using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. The emotion engine also analyzes the user's emotional data. If the user indicates high stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently. This system can provide high-quality educational instruction at low cost, especially for students from low-income families, and also enables personalized learning based on the user's emotional state.

[0215] The processing flow will be explained below.

[0216] Step 1: User submits training data

[0217] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[0218] Step 2: The server receives and stores the data

[0219] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0220] Step 3: The server uses the generative AI model to design a learning plan

[0221] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0222] Step 4: The device collects emotion data

[0223] The user's device is equipped with an emotion engine that uses sensors to collect the user's facial expressions, input speed, voice, etc. The emotion engine uses the collected data to estimate the user's emotional state. For example, if the user's face remains expressionless for a long period of time, it is determined that the user is tired.

[0224] Step 5: The server receives the analysis results of the emotion engine.

[0225] The analysis results of the emotion engine are sent to the server. The server receives this data and records it in a database as the user's emotional state. For example, it might record a state such as "highly tired" or "highly focused."

[0226] Step 6: The server adjusts the learning plan

[0227] Based on the analysis results of the emotion engine, the server provides feedback to the generative AI model and adjusts the study plan according to the user's emotional state. For example, if the user is tired, it will add lighter study content that does not require much concentration and intervals for relaxation to the study plan.

[0228] Step 7: The server provides the lesson plan to the user

[0229] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0230] Step 8: The server executes the PDCA cycle to improve the model

[0231] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[0232] Example 2

[0233] 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."

[0234] Conventional educational systems provided study plans based on a user's learning progress and test results, but were unable to provide individualized study plans that took the user's emotional state into account. Furthermore, there were limited means of improving the accuracy of generative AI models using the PDCA cycle. This made it difficult to provide appropriate study plans, especially for users who were feeling stressed or fatigued, resulting in issues with learning continuity and efficiency. Furthermore, there was a need to automate the process of accumulating and analyzing learning data and flexibly provide optimal study plans for individual users.

[0235] 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.

[0236] In this invention, the server includes a means for users to post study data, a means for collecting and storing the posted study data, a means for the generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a sentiment analysis means for analyzing the user's emotional data, a means for adjusting the study plan based on the results of the sentiment analysis means, and a PDCA cycle means for improving the generative AI model based on the collected data. This makes it possible to provide an individual study plan that takes into account not only the user's study progress and test results but also their emotional state, significantly improving the continuity and efficiency of learning. Furthermore, the accuracy of the generative AI model can be continuously improved using the PDCA cycle, making it possible to always provide the latest and most optimal study plans.

[0237] "User" means a person who uses the system to input and post learning data.

[0238] "Learning data" refers to information related to learning, such as a user's learning progress and test results.

[0239] The "server" is a central device for collecting, storing, and analyzing submitted learning data.

[0240] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[0241] A "study plan" is a specific plan created by a generative AI model that includes learning procedures, study materials, and problem sets provided to the user.

[0242] "Emotion analysis means" refers to techniques and devices for analyzing a user's emotional state.

[0243] The PDCA cycle is a process of improving the accuracy of generative AI models through a cycle of planning (Plan), execution (Do), evaluation (Check), and improvement (Act).

[0244] A "database" is a system that centrally stores and manages collected learning data.

[0245] "Emotion data" is information about the user's emotional state, including, for example, stress and fatigue.

[0246] "Feedback" is the action of improving systems and processes based on information derived from analysis and evaluation results.

[0247] This invention is a system for resolving educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users input and post study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the study plan according to the user's emotional state.

[0248] System configuration

[0249] The system includes the following elements:

[0250] 1. User device: The device on which the user inputs and posts learning data. Typically, a PC, tablet, or smartphone is used.

[0251] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a high-performance database server or cloud computing platform is often used.

[0252] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data, using, for example, machine learning or deep learning techniques.

[0253] 4. Emotion Analysis Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan. It uses facial recognition and voice analysis technologies.

[0254] 5. PDCA cycle: The process of continuously collecting training data and improving generative AI models.

[0255] Overview of program processing

[0256] 1. The user posts their learning data. The user posts their learning progress and test results to the system through a dedicated input form. For example, they enter data such as "I got 75 points on the math test, and the test date was 2023-10-15."

[0257] 2. The server receives and stores the data. The server receives the learning data sent by the user and stores it in a database. The data includes the user ID, subject, score, test date, etc.

[0258] 3. The server designs a study plan using a generative AI model. The server retrieves the user's latest study data from the database and inputs this data into the generative AI model. For example, if the user's math test score is below average, the server will suggest special practice sets and video lectures to strengthen the foundations of that subject.

[0259] 4. The emotion analysis engine analyzes the user's emotions. The emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[0260] 5. The generative AI model adjusts the study plan. The server feeds back the results of the emotion analysis engine's analysis to the generative AI model, which then adjusts the study plan according to the user's emotional state. For example, "If the user feels tired, add breaks and lighter learning content to the study plan to help them relax."

[0261] 6. The server provides the user with the study plan. The server updates the platform with the generated study plan. The user can then log in to the platform via their device and check the latest study plan on their dashboard. Specifically, the plan displays exercises, recommended learning materials, study schedules, and more.

[0262] 7. Implement the PDCA cycle. The server continuously collects new learning data and emotion data, and retrains the generative AI model to improve its accuracy. This allows future learning plans to be more tailored to the user's needs.

[0263] Specific examples

[0264] For example, a high school student user could enter their physics test score of 60 into the system. The server receives this information and stores it in a database. The generative AI model uses this data to identify areas that need reinforcement (for example, the basics of electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. An emotion analysis engine also analyzes the user's emotional data, and if the user is experiencing high levels of stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce stress. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently.

[0265] Prompt Sentence Examples

[0266] Here is an example of a prompt to input to a generative AI model:

[0267] User ID: A12345

[0268] Subject: Mathematics

[0269] Points scored: 75

[0270] Test date: 2023-10-15

[0271] Emotional state: Tired

[0272] When this prompt is fed into a generative AI model, it generates an optimal learning plan for the user, taking into account the user's emotional state, providing a flexible learning plan tailored to the user's situation.

[0273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0274] Step 1:

[0275] Users post training data

[0276] The user enters their learning progress and test results into the input form and sends the data to the server by pressing the send button. For example, they enter data such as "I got 75 points on the math test, and the test was held on 2023-10-15." The data entered includes the user ID, subject, score, and test date.

[0277] Specific behavior:

[0278] The user operates a device (PC or smartphone) to enter data into an input form. When the send button is pressed, the data is sent to the server via an HTTP request.

[0279] Input: Study progress and test results (e.g., subjects, scores, test dates)

[0280] Output: Training data sent to the server

[0281] Step 2:

[0282] The server receives and stores the data

[0283] The server receives learning data sent by users in real time and stores it in a database. The received data includes user ID, subjects, scores, test dates, etc. This data is organized for each user and managed centrally.

[0284] Specific behavior:

[0285] The server receives the HTTP request, extracts the data, connects to the database and inserts the data into the appropriate tables, and performs validation checks to ensure data consistency.

[0286] Input: Training data submitted by the user

[0287] Output: Training data stored in a database

[0288] Step 3:

[0289] The server designs a learning plan using a generative AI model

[0290] The server retrieves the latest learning data from the database and inputs it into the generative AI model, which then generates an optimal learning plan based on the input data. For example, if a student's math test score is below average, the system will suggest special practice sets and video lectures to strengthen their foundations in that area.

[0291] Specific behavior:

[0292] The server executes SQL queries to retrieve the latest training data from the database, inputs the retrieved data into the generative AI model, and performs calculations to generate a learning plan. The generated learning plan is embodied as a problem set, recommended learning materials, and a learning schedule.

[0293] Input: Training data obtained from the database

[0294] Output: A learning plan generated by the generative AI model

[0295] Step 4:

[0296] The sentiment analysis engine analyzes the user's emotions

[0297] Emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[0298] Specific behavior:

[0299] The user uses the device's camera and microphone to collect emotional data such as facial expressions and tone of voice. The server receives the emotional data and passes it to the emotion analysis engine. The emotion analysis engine analyzes the data and identifies the user's emotional state (fatigue, stress, etc.).

[0300] Input: Emotion data collected from the user

[0301] Output: Emotional state analyzed by the emotion analysis engine

[0302] Step 5:

[0303] Generative AI models adjust learning plans

[0304] The server feeds the results of the emotion analysis engine back to the generative AI model, and adjusts the study plan according to the user's emotional state. For example, if the user feels tired, it will add breaks and lighter learning content to the study plan to help them relax.

[0305] Specific behavior:

[0306] The server retrieves the generated learning plan and feeds back the results of the sentiment analysis engine. The generative AI model receives the feedback and readjusts the learning plan, updating it to the optimal content.

[0307] Input: Emotional state analyzed by the emotion analysis engine and existing learning plan

[0308] Output: Adjusted learning plan

[0309] Step 6:

[0310] The server provides the study plan to the user.

[0311] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view the latest study plan on their dashboard, which displays exercises, recommended study materials, study schedules, and more.

[0312] Specific behavior:

[0313] The server stores the learning plan on the platform. When a user logs in to the platform, the latest learning plan is displayed on the dashboard. Users can check the learning plan through a browser or app and proceed with their studies according to the plan.

[0314] Input: Adjusted Study Plan

[0315] Output: The lesson plan displayed on the user's dashboard

[0316] Step 7:

[0317] Implementing the PDCA cycle

[0318] The server continuously collects new learning and emotion data and retrains the generative AI model, improving its accuracy so that future learning plans are more tailored to the user's needs.

[0319] Specific behavior:

[0320] The server periodically collects new data and stores it in a database. The generative AI model is retrained based on the collected data. The effectiveness of the learning plan is evaluated and the model is updated based on feedback. The next learning plan is revised to be more optimal based on the user's learning progress and emotional state.

[0321] Input: New training data and emotion data

[0322] Output: Next learning plan provided by an improved generative AI model

[0323] (Application example 2)

[0324] 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."

[0325] Conventional educational systems lacked individual optimization based on the user's learning progress and test results, limiting the effectiveness of learning. Furthermore, learning plans were not adjusted based on the user's emotional state, making efficient learning difficult. Furthermore, providing high-quality education to students from low-income families was also a challenge.

[0326] 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 a means for users to post learning data, a server means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, an emotion engine means for analyzing the user's emotional state, a means for adjusting the learning plan based on the user's emotional state, and a PDCA cycle means for improving the generative AI model based on the collected data. This enables individual optimization according to the user's learning progress and emotional state, resulting in efficient and effective learning. It also makes it possible to provide high-quality educational instruction equally to students from low-income families.

[0327] "Study data" refers to data that users post to the system about their own study progress and test results.

[0328] The "server" is a central device that collects and stores submitted learning data and performs further analysis.

[0329] A "generative AI model" is an artificial intelligence algorithm that analyzes collected learning data and designs the optimal learning plan for each user.

[0330] A "study plan" is a specific schedule and content designed by a generative AI model to help users study efficiently and effectively.

[0331] The "emotion engine" is a system that analyzes the user's emotional state and provides feedback to the generative AI model based on that information.

[0332] The PDCA cycle is a process of improving the accuracy of generative AI models by repeating the cycle of Plan, Do, Check, and Act.

[0333] This invention is a system that allows users to post learning data and collect, store, and analyze that data. The system has the following main components:

[0334] 1. User terminal: A device on which a user inputs and posts learning data. Examples include a PC, smartphone, or tablet.

[0335] 2. Server: This is the central device that collects, stores, and analyzes the submitted training data and executes the generative AI model. The server has a database and centrally manages each user's training data.

[0336] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data. For example, machine learning models and deep learning models using Python are often used.

[0337] 4. Emotion Engine: This system analyzes the user's emotional state and reflects the results in the learning plan. Emotion analysis utilizes facial recognition software using cameras and sensors, or voice analysis software.

[0338] 5. PDCA Cycle: This is the process of continuously collecting training data and improving the generative AI model. The PDCA cycle is performed using Python scripts and automation tools.

[0339] In this system, learning data is first posted from the user's device to the server. The server receives and analyzes this data and uses a generative AI model to generate an optimal learning plan. Next, the user's emotional data is also collected and analyzed by the emotion engine. The learning plan is adjusted based on the analysis results, and the final learning plan is provided to the user.

[0340] Furthermore, the collected data is continuously analyzed based on the PDCA cycle to improve the performance of the generative AI model, ensuring that users always receive an effective learning plan tailored to their learning progress.

[0341] Examples:

[0342] For example, imagine a high school student using the system. The user enters their physics test score of 60 into the system. The server then receives that information and stores it in a database. The generative AI model uses that data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area.

[0343] In addition, the emotion engine analyzes the user's emotional data, and if the user is feeling high stress, the generative AI model adjusts the study plan and adds relaxation menus and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[0344] Example prompt sentence:

[0345] User ID: student123,

[0346] Points: 75,

[0347] Subject: Mathematics,

[0348] Test date: 2023-10-15

[0349] Generate the best learning plan for this user.

[0350] This example makes high-quality educational instruction widely available, including to students from low-income families, and provides personalized optimization based on the user's emotional state.

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Program processing flow

[0353] Step 1:

[0354] The user submits their learning data to the system through an input form. The input data includes the user ID, subject, test score, and test date. For example, the information might be "User ID: student123, Subject: Mathematics, Score: 75, Test Date: 2023-10-15."

[0355] Step 2:

[0356] The server receives the submitted training data and stores it in a database. It analyzes the input data and accumulates it in the database in a format that allows for centralized management of data for each user. The output is the training data stored in the database.

[0357] Step 3:

[0358] The server then retrieves the stored training data from the database and inputs it into the generative AI model. The input is the entire training data, and the output is the optimal training plan for the user. Specifically, the generative AI model uses a machine learning algorithm to generate the optimal training plan.

[0359] Step 4:

[0360] The server collects emotional data from the user's device. The input is facial recognition data obtained using a camera or sensor, or voice recognition data. The output is the emotional state analyzed by the emotion engine. For example, the user's state may be analyzed as "tired" or "stressed."

[0361] Step 5:

[0362] The server provides feedback to the generative AI model based on the analysis results of the emotion engine and adjusts the learning plan. The input is the output data of the emotion engine, and the output is an adjusted learning plan. Specifically, this includes adding breaks and relaxation menus to reduce the user's burden.

[0363] Step 6:

[0364] The server provides the final study plan to the user. The input is the adjusted study plan, and the output is a study plan displayed on the user's dashboard, where the user can proceed with their studies.

[0365] Step 7:

[0366] The server continuously collects new learning data and emotion data from users and retrains the generative AI model. The input is new learning data and emotion data, and the output is an improved generative AI model. Specifically, the PDCA cycle is run based on the new data to improve the model.

[0367] These steps enable individual optimization tailored to the user's learning progress and emotional state, resulting in efficient and effective learning.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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."

[0384] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. This system allows users to submit study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle.

[0385] System Overview

[0386] The system includes the following elements:

[0387] 1. User terminal: A device for users to input and post learning data.

[0388] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[0389] 3. Generative AI model: An algorithm that generates an optimal learning plan based on each user's data.

[0390] 4. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[0391] Program processing overview

[0392] 1. User submits training data:

[0393] A user submits their learning progress and test results to the system through an input form. For example, a junior high school student enters their math test score as "75 points" and submits the test date as "2023-10-15." The server receives the data.

[0394] 2. The server collects and stores the data:

[0395] The server stores the learning data posted by users in a database, allowing all users' learning data to be managed centrally.

[0396] 3. Designing lesson plans using generative AI models:

[0397] Based on the data stored on the server, the generative AI model designs a study plan for each user. For example, if a user's math test reveals that they have weak areas, the model will recommend additional practice problems and explanatory videos.

[0398] 4. Provide users with a learning plan:

[0399] The server provides the generated study plan to the user, who can then log in to view their own study plan and proceed with their studies according to the recommended study content.

[0400] 5. Implementing the PDCA cycle:

[0401] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan.

[0402] Specific examples

[0403] For example, imagine a high school student is using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need improvement (e.g., basic electromagnetism) and generates a study plan that includes practice problems and reference videos specific to that area. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[0404] This system of the present invention makes it possible to provide high-quality educational instruction at low cost, especially to students from low-income families. Furthermore, by implementing the PDCA cycle, the accuracy of the generative AI model is continuously improved, enabling the provision of learning plans that are more tailored to individual needs.

[0405] The processing flow will be explained below.

[0406] Step 1: User submits training data

[0407] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[0408] Step 2: The server receives and stores the data

[0409] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0410] Step 3: The server uses the generative AI model to design a learning plan

[0411] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0412] Step 4: The server provides the lesson plan to the user

[0413] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0414] Step 5: The server executes the PDCA cycle to improve the model

[0415] Every time a user periodically submits new learning data, that data is collected and stored in a database. The server retrains the generative AI model using the latest learning data, improving the model's accuracy. This ensures that future learning plans are more suited to the user's needs. The effectiveness of the plan is evaluated, and insights gained from the data are reflected to continuously improve the model.

[0416] Example 1

[0417] 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."

[0418] In modern society, income disparities cause educational disparities, making it difficult for students from low-income families to access high-quality education. The present invention aims to provide a system that reduces this educational disparity and enables all students to learn effectively.

[0419] 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.

[0420] In this invention, the server includes a means for users to post learning data, a database means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, a means for providing the designed learning plan to the user, and a PDCA cycle means for improving the generative AI model based on the collected data, which makes it possible to provide an optimal learning plan based on individual learning progress and needs.

[0421] "User" means an individual or organization that uses the System to input and post learning data.

[0422] "Study data" refers to data such as study progress and test results that users enter and post into the system.

[0423] "Means for posting" refers to an interface or device that allows a user to input and transmit learning data into the system.

[0424] The "database means for collecting and storing" is a database system for receiving and centrally managing submitted learning data.

[0425] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[0426] The "means of designing a learning plan" is the process of using a generative AI model to create an optimal learning plan for each user.

[0427] The "means of providing" refers to an interface or system that allows users to view the designed learning plan.

[0428] The "PDCA cycle method" is a process for continuously improving the generative AI model based on collected data.

[0429] The "system" refers to the overall mechanism for eliminating educational disparities, including the measures mentioned above.

[0430] This invention is a system designed to eliminate educational disparities, particularly those caused by income disparities. This system allows users to input and post learning data, and a generative AI model then proposes an optimal learning plan based on that data. Furthermore, it includes a mechanism for improving the accuracy of the generative AI model through the PDCA cycle.

[0431] Hardware and software used

[0432] Hardware

[0433] 1. User terminal: A device used by users to input and post learning data. Specifically, this includes PCs, smartphones, tablets, etc.

[0434] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. It uses a high-performance server machine.

[0435] software

[0436] 1. Database system: A database for centrally managing the submitted learning data. A relational database management system such as MySQL or PostgreSQL is used.

[0437] 2. Generative AI model: An algorithm that generates the optimal learning plan based on user data. In this case, we use GPT-4, a generative natural language model.

[0438] 3. Web application: An interface for users to input learning data and a platform for displaying the generated learning plan. It uses a front-end framework such as React or Vue.js and a back-end framework such as Django or Flask.

[0439] Data processing and calculation

[0440] 1. Users submit their training data

[0441] The user enters their learning progress and test results into the form and presses the send button. This data is sent from the user's device to the server.

[0442] Example: A junior high school student user enters the math test result "75 points" and the test date "2023-10-15" and submits it.

[0443] 2. The server collects and stores data

[0444] The server stores the received data in a database, where all user learning data is managed in a unified manner.

[0445] Software used: MySQL

[0446] Example: Insert data into the database using the SQL query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[0447] 3. The server designs a learning plan using the generative AI model

[0448] Based on the data stored on the server, the generative AI model designs the optimal learning plan for each user. The generative AI model calls the GPT-4 model using a Python script.

[0449] Software used: GPT-4

[0450] Example: Send the prompt "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user."

[0451] 4. The server provides the study plan to the user

[0452] The generated learning plan is displayed on the user's dashboard, where the user can log in and view their own learning plan.

[0453] Software used: React, Django

[0454] Example: Displaying the following on the dashboard: "Your study plan for the next week: We provide practice questions and helpful video links to help you focus on 'Fundamentals of Electromagnetism.'"

[0455] 5. The server executes the PDCA cycle

[0456] The server continuously collects new training data and retrains the generative AI model to improve the accuracy of its learning plans, using machine learning libraries such as TensorFlow and PyTorch.

[0457] Software used: TensorFlow, PyTorch

[0458] Example: Once a month, run a script called "train.py" that retrains your AI model based on newly collected data.

[0459] In this way, the system provides a customized learning plan for each user, making it a powerful tool for narrowing educational gaps.

[0460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0461] Step 1:

[0462] Users post training data.

[0463] Input: Users enter their learning progress and test results into an input form.

[0464] Data processing: The contents of the input form are sent from the user's terminal to the server.

[0465] Output: The training data is sent to the server.

[0466] Specific operation: A user accesses a web application and navigates to a form page for learning management. For example, a junior high school student enters their math test score (75 points) and the test date (2023-10-15), and clicks the submit button.

[0467] Step 2:

[0468] The server collects and stores the data.

[0469] Input: Training data submitted by the user.

[0470] Data processing: Sanitize the received data and insert it into the database using SQL queries.

[0471] Output: Training data stored in a database.

[0472] What it does: The server formats the data it receives and inserts it into the MySQL database using the query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[0473] Step 3:

[0474] The server designs a learning plan using a generative AI model.

[0475] Input: User learning data stored in a database.

[0476] Data processing: Send prompts to the generative AI model based on data retrieved from the database.

[0477] Output: The generated learning plan.

[0478] Specific operation: The server runs a Python script and sends the prompt message "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user" to the generative AI model (GPT-4), and the AI ​​model then generates a study plan.

[0479] Step 4:

[0480] The server provides the lesson plan to the user.

[0481] Input: The generated learning plan.

[0482] Data processing: Embed the learning plan into an HTML template and render it as a web page.

[0483] Output: The lesson plan provided to the user.

[0484] Specific operation: The server embeds the generated study plan on the user's dashboard page, and the user can log in and check their own study plan. For example, the dashboard will display "Your study plan for the next week: We will provide practice questions and reference video links to focus on studying 'Fundamentals of Electromagnetism'."

[0485] Step 5:

[0486] The server executes the PDCA cycle.

[0487] Input: New training data.

[0488] Data processing: Add new data to the dataset and retrain the AI ​​model using machine learning libraries.

[0489] Output: A generative AI model with improved accuracy.

[0490] What it does: The server periodically runs a Python script to add newly collected data to the dataset and retrain the model with a script called “train.py.”

[0491] (Application example 1)

[0492] 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."

[0493] The challenge is to eliminate the educational disparity caused by income disparity and provide high-quality educational instruction, especially to students from low-income families. Furthermore, it is necessary to create an environment in which students can study efficiently by providing easy-to-use study plans on smartphones.

[0494] 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.

[0495] In this invention, the server includes a means for users to post study data, a server means for collecting and storing the posted study data, a means for a generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a PDCA cycle means for improving the generative AI model based on the collected data, a means for users to post study data from a smartphone, and a means for presenting the generated study plan on the smartphone. This makes it possible to eliminate educational disparities and provide an efficient learning environment where students can concentrate on their studies.

[0496] We have created definitions for the following important words:

[0497] The "means for users to post learning data" refers to an interface that allows users to input learning data such as their own learning progress and test results and send it to the system.

[0498] The "server means for collecting and storing submitted learning data" refers to a server device and database mechanism for receiving and centrally managing learning data sent by users.

[0499] The "means by which the generative AI model designs a learning plan using collected data" refers to the AI ​​algorithms and calculation mechanisms that analyze the accumulated learning data and generate an optimal learning plan for each user.

[0500] The "means for providing the designed lesson plan to the user" is an interface and notification system that informs the user of the created lesson plan and allows them to execute it.

[0501] The "PDCA cycle method for improving generative AI models based on collected data" is a process of continuously collecting new training data and repeating the cycle of planning (Plan), doing (Do), evaluating (Check), and improving (Act) to improve the accuracy of generative AI models.

[0502] "Means for users to post learning data from their smartphones" refers to applications and interfaces for inputting and sending learning data using a smartphone.

[0503] The "means for presenting the generated study plan on a smartphone" refers to an application and an interface for visually displaying the study plan generated on the smartphone to the user.

[0504] This invention is a system for eliminating educational disparities, particularly reducing inequalities in educational opportunities due to income disparities. This system allows users to upload their own learning data using their smartphones, and a generative AI model then designs an optimal learning plan based on that data and provides it to the user. It also has a function for improving the accuracy of the generative AI model using the PDCA cycle.

[0505] System Overview

[0506] The system is broadly composed of the following elements:

[0507] 1. User device: A smartphone used by the user to input and post learning data.

[0508] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a cloud server is used to host the database and AI models.

[0509] 3. Generative AI models: Algorithms that generate optimal learning plans based on each user's data. These typically use Python and scikit-learn.

[0510] 4. PDCA cycle: The process of continuously collecting learning data and retraining the AI ​​model.

[0511] Program processing

[0512] 1. User Data Submission:

[0513] Users can submit their study progress and test results to the system via an input form on their smartphones. This data includes test scores, study time, weak areas, etc.

[0514] 2. Data collection and storage:

[0515] The server receives the data posted by users and stores it in a database, allowing all users' learning data to be managed centrally.

[0516] 3. Designing a learning plan:

[0517] Using data stored on the server, the generative AI model designs an optimal learning plan for each individual user, for example, recommending additional practice problems or explanatory videos to users who struggle with math.

[0518] 4. Providing a study plan:

[0519] The server then sends the generated study plan to the user's smartphone, where the user can review it and proceed with their studies according to the suggested study content.

[0520] 5. Implementing the PDCA cycle:

[0521] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan and providing more personalized learning.

[0522] Specific examples

[0523] For example, if a student scores 45 points on a physics test, they can submit that data from their smartphone. The server receives the information and stores it in a database. The generative AI model uses this data to generate recommendations, such as "Watch a video on the basics of electromagnetism." This recommendation is then sent to the user's smartphone, allowing them to proceed with their studies according to the submitted study plan.

[0524] An example of a prompt is:

[0525] "Please generate a study plan based on the following user data: User ID: 1, Subject: Physics, Score: 45 points, Date: 2023-10-20."

[0526] The text format is used.

[0527] In this way, this system aims to correct educational disparities and can provide a comfortable and efficient learning environment by using users' smartphones.

[0528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0529] Step 1:

[0530] The user posts their study data from their smartphone. Specifically, the user launches the application, enters their study progress and test results into the input form, and presses the submit button. At this time, input includes test scores, subjects, date and time, etc. The submitted data is sent from the smartphone to the server.

[0531] Step 2:

[0532] The server collects the learning data sent by the user and stores it in a database. The server analyzes the received data and converts it into an appropriate format for saving in the database. For example, data such as "User ID: 1, Subject: Physics, Score: 45 points, Date and Time: 2023-10-20" is saved in the corresponding field in the database. In this process, the input is the submitted raw data, and the output is the data stored in the database.

[0533] Step 3:

[0534] The server uses a generative AI model to design a learning plan based on the accumulated data. Specifically, it analyzes the collected learning data and recommends additional learning resources based on each user's grades and progress. For example, for a user who received a 45 in physics, a recommendation to "watch basic physics videos" is generated. The input here is the learning data stored in the database, and the output is a learning plan for the user.

[0535] Step 4:

[0536] To provide the generated study plan to the user, the server sends a notification to the user's smartphone. The user can then check the generated study plan through their smartphone. Specifically, the recommended study content is displayed on the application's dashboard. The input here is the generated study plan, and the output is the recommended content displayed on the user's smartphone.

[0537] Step 5:

[0538] The server continues to collect new training data and executes a PDCA cycle to improve the generative AI model. In this cycle, the AI ​​model is retrained based on the new data collected, improving its accuracy. For example, data from users with new test results is added, and the model's performance is evaluated and improved against previous recommendations. The input is new training data, and the output is an improved generative AI model.

[0539] Through the above steps, the system of the present invention provides users with efficient and personalized learning plans, contributing to the elimination of educational disparities. Furthermore, the system's simple operation on a smartphone improves user convenience.

[0540] 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.

[0541] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users post their study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention realizes adjustments to the study plan according to the user's emotional state.

[0542] System Overview

[0543] The system includes the following elements:

[0544] 1. User terminal: A device for users to input and post learning data.

[0545] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[0546] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data.

[0547] 4. Emotion Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan.

[0548] 5. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[0549] Program processing overview

[0550] 1. User submits training data:

[0551] Users submit their learning progress and test results to the system through an input form. For example, if a middle school student user gets 75 points on a math test, they enter the score and the test date (2023-10-15) and submit. When the user presses the submit button, the data is sent to the server.

[0552] 2. The server receives and stores the data:

[0553] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0554] 3. The server designs a learning plan using the generative AI model:

[0555] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0556] 4. Emotion engine analyzes user emotions:

[0557] Emotional data is collected while the user is studying, and the emotion engine analyzes the data. For example, if the user feels tired after studying for a long time, the system will recognize that emotional state.

[0558] 5. Generative AI models adjust learning plans:

[0559] The server takes into account the analysis results of the emotion engine and provides feedback to the generative AI model to adjust the study plan according to the user's emotional state. For example, if the user feels tired, the study plan will include breaks for relaxation and lighter learning content.

[0560] 6. The server provides the study plan to the user:

[0561] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0562] 7. Implementing the PDCA cycle:

[0563] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[0564] Specific examples

[0565] For example, consider a high school student using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. The emotion engine also analyzes the user's emotional data. If the user indicates high stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently. This system can provide high-quality educational instruction at low cost, especially for students from low-income families, and also enables personalized learning based on the user's emotional state.

[0566] The processing flow will be explained below.

[0567] Step 1: User submits training data

[0568] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[0569] Step 2: The server receives and stores the data

[0570] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0571] Step 3: The server uses the generative AI model to design a learning plan

[0572] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0573] Step 4: The device collects emotion data

[0574] The user's device is equipped with an emotion engine that uses sensors to collect the user's facial expressions, input speed, voice, etc. The emotion engine uses the collected data to estimate the user's emotional state. For example, if the user's face remains expressionless for a long period of time, it is determined that the user is tired.

[0575] Step 5: The server receives the analysis results of the emotion engine.

[0576] The analysis results of the emotion engine are sent to the server. The server receives this data and records it in a database as the user's emotional state. For example, it might record a state such as "highly tired" or "highly focused."

[0577] Step 6: The server adjusts the learning plan

[0578] Based on the analysis results of the emotion engine, the server provides feedback to the generative AI model and adjusts the study plan according to the user's emotional state. For example, if the user is tired, it will add lighter study content that does not require much concentration and intervals for relaxation to the study plan.

[0579] Step 7: The server provides the lesson plan to the user

[0580] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0581] Step 8: The server executes the PDCA cycle to improve the model

[0582] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[0583] Example 2

[0584] 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."

[0585] Conventional educational systems provided study plans based on a user's learning progress and test results, but were unable to provide individualized study plans that took the user's emotional state into account. Furthermore, there were limited means of improving the accuracy of generative AI models using the PDCA cycle. This made it difficult to provide appropriate study plans, especially for users who were feeling stressed or fatigued, resulting in issues with learning continuity and efficiency. Furthermore, there was a need to automate the process of accumulating and analyzing learning data and flexibly provide optimal study plans for individual users.

[0586] 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.

[0587] In this invention, the server includes a means for users to post study data, a means for collecting and storing the posted study data, a means for the generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a sentiment analysis means for analyzing the user's emotional data, a means for adjusting the study plan based on the results of the sentiment analysis means, and a PDCA cycle means for improving the generative AI model based on the collected data. This makes it possible to provide an individual study plan that takes into account not only the user's study progress and test results but also their emotional state, significantly improving the continuity and efficiency of learning. Furthermore, the accuracy of the generative AI model can be continuously improved using the PDCA cycle, making it possible to always provide the latest and most optimal study plans.

[0588] "User" means a person who uses the system to input and post learning data.

[0589] "Learning data" refers to information related to learning, such as a user's learning progress and test results.

[0590] The "server" is a central device for collecting, storing, and analyzing submitted learning data.

[0591] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[0592] A "study plan" is a specific plan created by a generative AI model that includes learning procedures, study materials, and problem sets provided to the user.

[0593] "Emotion analysis means" refers to techniques and devices for analyzing a user's emotional state.

[0594] The PDCA cycle is a process of improving the accuracy of generative AI models through a cycle of planning (Plan), execution (Do), evaluation (Check), and improvement (Act).

[0595] A "database" is a system that centrally stores and manages collected learning data.

[0596] "Emotion data" is information about the user's emotional state, including, for example, stress and fatigue.

[0597] "Feedback" is the action of improving systems and processes based on information derived from analysis and evaluation results.

[0598] This invention is a system for resolving educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users input and post study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the study plan according to the user's emotional state.

[0599] System configuration

[0600] The system includes the following elements:

[0601] 1. User device: The device on which the user inputs and posts learning data. Typically, a PC, tablet, or smartphone is used.

[0602] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a high-performance database server or cloud computing platform is often used.

[0603] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data, using, for example, machine learning or deep learning techniques.

[0604] 4. Emotion Analysis Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan. It uses facial recognition and voice analysis technologies.

[0605] 5. PDCA cycle: The process of continuously collecting training data and improving generative AI models.

[0606] Overview of program processing

[0607] 1. The user posts their learning data. The user posts their learning progress and test results to the system through a dedicated input form. For example, they enter data such as "I got 75 points on the math test, and the test date was 2023-10-15."

[0608] 2. The server receives and stores the data. The server receives the learning data sent by the user and stores it in a database. The data includes the user ID, subject, score, test date, etc.

[0609] 3. The server designs a study plan using a generative AI model. The server retrieves the user's latest study data from the database and inputs this data into the generative AI model. For example, if the user's math test score is below average, the server will suggest special practice sets and video lectures to strengthen the foundations of that subject.

[0610] 4. The emotion analysis engine analyzes the user's emotions. The emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[0611] 5. The generative AI model adjusts the study plan. The server feeds back the results of the emotion analysis engine's analysis to the generative AI model, which then adjusts the study plan according to the user's emotional state. For example, "If the user feels tired, add breaks and lighter learning content to the study plan to help them relax."

[0612] 6. The server provides the user with the study plan. The server updates the platform with the generated study plan. The user can then log in to the platform via their device and check the latest study plan on their dashboard. Specifically, the plan displays exercises, recommended learning materials, study schedules, and more.

[0613] 7. Implement the PDCA cycle. The server continuously collects new learning data and emotion data, and retrains the generative AI model to improve its accuracy. This allows future learning plans to be more tailored to the user's needs.

[0614] Specific examples

[0615] For example, a high school student user could enter their physics test score of 60 into the system. The server receives this information and stores it in a database. The generative AI model uses this data to identify areas that need reinforcement (for example, the basics of electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. An emotion analysis engine also analyzes the user's emotional data, and if the user is experiencing high levels of stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce stress. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently.

[0616] Prompt Sentence Examples

[0617] Here is an example of a prompt to input to a generative AI model:

[0618] User ID: A12345

[0619] Subject: Mathematics

[0620] Points scored: 75

[0621] Test date: 2023-10-15

[0622] Emotional state: Tired

[0623] When this prompt is fed into a generative AI model, it generates an optimal learning plan for the user, taking into account the user's emotional state, providing a flexible learning plan tailored to the user's situation.

[0624] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0625] Step 1:

[0626] Users post training data

[0627] The user enters their learning progress and test results into the input form and sends the data to the server by pressing the send button. For example, they enter data such as "I got 75 points on the math test, and the test was held on 2023-10-15." The data entered includes the user ID, subject, score, and test date.

[0628] Specific behavior:

[0629] The user operates a device (PC or smartphone) to enter data into an input form. When the send button is pressed, the data is sent to the server via an HTTP request.

[0630] Input: Study progress and test results (e.g., subjects, scores, test dates)

[0631] Output: Training data sent to the server

[0632] Step 2:

[0633] The server receives and stores the data

[0634] The server receives learning data sent by users in real time and stores it in a database. The received data includes user ID, subjects, scores, test dates, etc. This data is organized for each user and managed centrally.

[0635] Specific behavior:

[0636] The server receives the HTTP request, extracts the data, connects to the database and inserts the data into the appropriate tables, and performs validation checks to ensure data consistency.

[0637] Input: Training data submitted by the user

[0638] Output: Training data stored in a database

[0639] Step 3:

[0640] The server designs a learning plan using a generative AI model

[0641] The server retrieves the latest learning data from the database and inputs it into the generative AI model, which then generates an optimal learning plan based on the input data. For example, if a student's math test score is below average, the system will suggest special practice sets and video lectures to strengthen their foundations in that area.

[0642] Specific behavior:

[0643] The server executes SQL queries to retrieve the latest training data from the database, inputs the retrieved data into the generative AI model, and performs calculations to generate a learning plan. The generated learning plan is embodied as a problem set, recommended learning materials, and a learning schedule.

[0644] Input: Training data obtained from the database

[0645] Output: A learning plan generated by the generative AI model

[0646] Step 4:

[0647] The sentiment analysis engine analyzes the user's emotions

[0648] Emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[0649] Specific behavior:

[0650] The user uses the device's camera and microphone to collect emotional data such as facial expressions and tone of voice. The server receives the emotional data and passes it to the emotion analysis engine. The emotion analysis engine analyzes the data and identifies the user's emotional state (fatigue, stress, etc.).

[0651] Input: Emotion data collected from the user

[0652] Output: Emotional state analyzed by the emotion analysis engine

[0653] Step 5:

[0654] Generative AI models adjust learning plans

[0655] The server feeds the results of the emotion analysis engine back to the generative AI model, and adjusts the study plan according to the user's emotional state. For example, if the user feels tired, it will add breaks and lighter learning content to the study plan to help them relax.

[0656] Specific behavior:

[0657] The server retrieves the generated learning plan and feeds back the results of the sentiment analysis engine. The generative AI model receives the feedback and readjusts the learning plan, updating it to the optimal content.

[0658] Input: Emotional state analyzed by the emotion analysis engine and existing learning plan

[0659] Output: Adjusted learning plan

[0660] Step 6:

[0661] The server provides the study plan to the user.

[0662] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view the latest study plan on their dashboard, which displays exercises, recommended study materials, study schedules, and more.

[0663] Specific behavior:

[0664] The server stores the learning plan on the platform. When a user logs in to the platform, the latest learning plan is displayed on the dashboard. Users can check the learning plan through a browser or app and proceed with their studies according to the plan.

[0665] Input: Adjusted Study Plan

[0666] Output: The lesson plan displayed on the user's dashboard

[0667] Step 7:

[0668] Implementing the PDCA cycle

[0669] The server continuously collects new learning and emotion data and retrains the generative AI model, improving its accuracy so that future learning plans are more tailored to the user's needs.

[0670] Specific behavior:

[0671] The server periodically collects new data and stores it in a database. The generative AI model is retrained based on the collected data. The effectiveness of the learning plan is evaluated and the model is updated based on feedback. The next learning plan is revised to be more optimal based on the user's learning progress and emotional state.

[0672] Input: New training data and emotion data

[0673] Output: Next learning plan provided by an improved generative AI model

[0674] (Application example 2)

[0675] 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."

[0676] Conventional educational systems lacked individual optimization based on the user's learning progress and test results, limiting the effectiveness of learning. Furthermore, learning plans were not adjusted based on the user's emotional state, making efficient learning difficult. Furthermore, providing high-quality education to students from low-income families was also a challenge.

[0677] 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 a means for users to post learning data, a server means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, an emotion engine means for analyzing the user's emotional state, a means for adjusting the learning plan based on the user's emotional state, and a PDCA cycle means for improving the generative AI model based on the collected data. This enables individual optimization according to the user's learning progress and emotional state, resulting in efficient and effective learning. It also makes it possible to provide high-quality educational instruction equally to students from low-income families.

[0678] "Study data" refers to data that users post to the system about their own study progress and test results.

[0679] The "server" is a central device that collects and stores submitted learning data and performs further analysis.

[0680] A "generative AI model" is an artificial intelligence algorithm that analyzes collected learning data and designs the optimal learning plan for each user.

[0681] A "study plan" is a specific schedule and content designed by a generative AI model to help users study efficiently and effectively.

[0682] The "emotion engine" is a system that analyzes the user's emotional state and provides feedback to the generative AI model based on that information.

[0683] The PDCA cycle is a process of improving the accuracy of generative AI models by repeating the cycle of Plan, Do, Check, and Act.

[0684] This invention is a system that allows users to post learning data and collect, store, and analyze that data. The system has the following main components:

[0685] 1. User terminal: A device on which a user inputs and posts learning data. Examples include a PC, smartphone, or tablet.

[0686] 2. Server: This is the central device that collects, stores, and analyzes the submitted training data and executes the generative AI model. The server has a database and centrally manages each user's training data.

[0687] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data. For example, machine learning models and deep learning models using Python are often used.

[0688] 4. Emotion Engine: This system analyzes the user's emotional state and reflects the results in the learning plan. Emotion analysis utilizes facial recognition software using cameras and sensors, or voice analysis software.

[0689] 5. PDCA Cycle: This is the process of continuously collecting training data and improving the generative AI model. The PDCA cycle is performed using Python scripts and automation tools.

[0690] In this system, learning data is first posted from the user's device to the server. The server receives and analyzes this data and uses a generative AI model to generate an optimal learning plan. Next, the user's emotional data is also collected and analyzed by the emotion engine. The learning plan is adjusted based on the analysis results, and the final learning plan is provided to the user.

[0691] Furthermore, the collected data is continuously analyzed based on the PDCA cycle to improve the performance of the generative AI model, ensuring that users always receive an effective learning plan tailored to their learning progress.

[0692] Examples:

[0693] For example, imagine a high school student using the system. The user enters their physics test score of 60 into the system. The server then receives that information and stores it in a database. The generative AI model uses that data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area.

[0694] In addition, the emotion engine analyzes the user's emotional data, and if the user is feeling high stress, the generative AI model adjusts the study plan and adds relaxation menus and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[0695] Example prompt sentence:

[0696] User ID: student123,

[0697] Points: 75,

[0698] Subject: Mathematics,

[0699] Test date: 2023-10-15

[0700] Generate the best learning plan for this user.

[0701] This example makes high-quality educational instruction widely available, including to students from low-income families, and provides personalized optimization based on the user's emotional state.

[0702] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0703] Program processing flow

[0704] Step 1:

[0705] The user submits their learning data to the system through an input form. The input data includes the user ID, subject, test score, and test date. For example, the information might be "User ID: student123, Subject: Mathematics, Score: 75, Test Date: 2023-10-15."

[0706] Step 2:

[0707] The server receives the submitted training data and stores it in a database. It analyzes the input data and accumulates it in the database in a format that allows for centralized management of data for each user. The output is the training data stored in the database.

[0708] Step 3:

[0709] The server then retrieves the stored training data from the database and inputs it into the generative AI model. The input is the entire training data, and the output is the optimal training plan for the user. Specifically, the generative AI model uses a machine learning algorithm to generate the optimal training plan.

[0710] Step 4:

[0711] The server collects emotional data from the user's device. The input is facial recognition data obtained using a camera or sensor, or voice recognition data. The output is the emotional state analyzed by the emotion engine. For example, the user's state may be analyzed as "tired" or "stressed."

[0712] Step 5:

[0713] The server provides feedback to the generative AI model based on the analysis results of the emotion engine and adjusts the learning plan. The input is the output data of the emotion engine, and the output is an adjusted learning plan. Specifically, this includes adding breaks and relaxation menus to reduce the user's burden.

[0714] Step 6:

[0715] The server provides the final study plan to the user. The input is the adjusted study plan, and the output is a study plan displayed on the user's dashboard, where the user can proceed with their studies.

[0716] Step 7:

[0717] The server continuously collects new learning data and emotion data from users and retrains the generative AI model. The input is new learning data and emotion data, and the output is an improved generative AI model. Specifically, the PDCA cycle is run based on the new data to improve the model.

[0718] These steps enable individual optimization tailored to the user's learning progress and emotional state, resulting in efficient and effective learning.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] [Third embodiment]

[0723] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0724] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0725] 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).

[0726] 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.

[0727] 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.

[0728] 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).

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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."

[0735] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. This system allows users to submit study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle.

[0736] System Overview

[0737] The system includes the following elements:

[0738] 1. User terminal: A device for users to input and post learning data.

[0739] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[0740] 3. Generative AI model: An algorithm that generates an optimal learning plan based on each user's data.

[0741] 4. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[0742] Program processing overview

[0743] 1. User submits training data:

[0744] A user submits their learning progress and test results to the system through an input form. For example, a junior high school student enters their math test score as "75 points" and submits the test date as "2023-10-15." The server receives the data.

[0745] 2. The server collects and stores the data:

[0746] The server stores the learning data posted by users in a database, allowing all users' learning data to be managed centrally.

[0747] 3. Designing lesson plans using generative AI models:

[0748] Based on the data stored on the server, the generative AI model designs a study plan for each user. For example, if a user's math test reveals that they have weak areas, the model will recommend additional practice problems and explanatory videos.

[0749] 4. Provide users with a learning plan:

[0750] The server provides the generated study plan to the user, who can then log in to view their own study plan and proceed with their studies according to the recommended study content.

[0751] 5. Implementing the PDCA cycle:

[0752] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan.

[0753] Specific examples

[0754] For example, imagine a high school student is using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need improvement (e.g., basic electromagnetism) and generates a study plan that includes practice problems and reference videos specific to that area. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[0755] This system of the present invention makes it possible to provide high-quality educational instruction at low cost, especially to students from low-income families. Furthermore, by implementing the PDCA cycle, the accuracy of the generative AI model is continuously improved, enabling the provision of learning plans that are more tailored to individual needs.

[0756] The processing flow will be explained below.

[0757] Step 1: User submits training data

[0758] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[0759] Step 2: The server receives and stores the data

[0760] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0761] Step 3: The server uses the generative AI model to design a learning plan

[0762] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0763] Step 4: The server provides the lesson plan to the user

[0764] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0765] Step 5: The server executes the PDCA cycle to improve the model

[0766] Every time a user periodically submits new learning data, that data is collected and stored in a database. The server retrains the generative AI model using the latest learning data, improving the model's accuracy. This ensures that future learning plans are more suited to the user's needs. The effectiveness of the plan is evaluated, and insights gained from the data are reflected to continuously improve the model.

[0767] Example 1

[0768] 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."

[0769] In modern society, income disparities cause educational disparities, making it difficult for students from low-income families to access high-quality education. The present invention aims to provide a system that reduces this educational disparity and enables all students to learn effectively.

[0770] 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.

[0771] In this invention, the server includes a means for users to post learning data, a database means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, a means for providing the designed learning plan to the user, and a PDCA cycle means for improving the generative AI model based on the collected data, which makes it possible to provide an optimal learning plan based on individual learning progress and needs.

[0772] "User" means an individual or organization that uses the System to input and post learning data.

[0773] "Study data" refers to data such as study progress and test results that users enter and post into the system.

[0774] "Means for posting" refers to an interface or device that allows a user to input and transmit learning data into the system.

[0775] The "database means for collecting and storing" is a database system for receiving and centrally managing submitted learning data.

[0776] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[0777] The "means of designing a learning plan" is the process of using a generative AI model to create an optimal learning plan for each user.

[0778] The "means of providing" refers to an interface or system that allows users to view the designed learning plan.

[0779] The "PDCA cycle method" is a process for continuously improving the generative AI model based on collected data.

[0780] The "system" refers to the overall mechanism for eliminating educational disparities, including the measures mentioned above.

[0781] This invention is a system designed to eliminate educational disparities, particularly those caused by income disparities. This system allows users to input and post learning data, and a generative AI model then proposes an optimal learning plan based on that data. Furthermore, it includes a mechanism for improving the accuracy of the generative AI model through the PDCA cycle.

[0782] Hardware and software used

[0783] Hardware

[0784] 1. User terminal: A device used by users to input and post learning data. Specifically, this includes PCs, smartphones, tablets, etc.

[0785] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. It uses a high-performance server machine.

[0786] software

[0787] 1. Database system: A database for centrally managing the submitted learning data. A relational database management system such as MySQL or PostgreSQL is used.

[0788] 2. Generative AI model: An algorithm that generates the optimal learning plan based on user data. In this case, we use GPT-4, a generative natural language model.

[0789] 3. Web application: An interface for users to input learning data and a platform for displaying the generated learning plan. It uses a front-end framework such as React or Vue.js and a back-end framework such as Django or Flask.

[0790] Data processing and calculation

[0791] 1. Users submit their training data

[0792] The user enters their learning progress and test results into the form and presses the send button. This data is sent from the user's device to the server.

[0793] Example: A junior high school student user enters the math test result "75 points" and the test date "2023-10-15" and submits it.

[0794] 2. The server collects and stores data

[0795] The server stores the received data in a database, where all user learning data is managed in a unified manner.

[0796] Software used: MySQL

[0797] Example: Insert data into the database using the SQL query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[0798] 3. The server designs a learning plan using the generative AI model

[0799] Based on the data stored on the server, the generative AI model designs the optimal learning plan for each user. The generative AI model calls the GPT-4 model using a Python script.

[0800] Software used: GPT-4

[0801] Example: Send the prompt "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user."

[0802] 4. The server provides the study plan to the user

[0803] The generated learning plan is displayed on the user's dashboard, where the user can log in and view their own learning plan.

[0804] Software used: React, Django

[0805] Example: Displaying the following on the dashboard: "Your study plan for the next week: We provide practice questions and helpful video links to help you focus on 'Fundamentals of Electromagnetism.'"

[0806] 5. The server executes the PDCA cycle

[0807] The server continuously collects new training data and retrains the generative AI model to improve the accuracy of its learning plans, using machine learning libraries such as TensorFlow and PyTorch.

[0808] Software used: TensorFlow, PyTorch

[0809] Example: Once a month, run a script called "train.py" that retrains your AI model based on newly collected data.

[0810] In this way, the system provides a customized learning plan for each user, making it a powerful tool for narrowing educational gaps.

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

[0812] Step 1:

[0813] Users post training data.

[0814] Input: Users enter their learning progress and test results into an input form.

[0815] Data processing: The contents of the input form are sent from the user's terminal to the server.

[0816] Output: The training data is sent to the server.

[0817] Specific operation: A user accesses a web application and navigates to a form page for learning management. For example, a junior high school student enters their math test score (75 points) and the test date (2023-10-15), and clicks the submit button.

[0818] Step 2:

[0819] The server collects and stores the data.

[0820] Input: Training data submitted by the user.

[0821] Data processing: Sanitize the received data and insert it into the database using SQL queries.

[0822] Output: Training data stored in a database.

[0823] What it does: The server formats the data it receives and inserts it into the MySQL database using the query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[0824] Step 3:

[0825] The server designs a learning plan using a generative AI model.

[0826] Input: User learning data stored in a database.

[0827] Data processing: Send prompts to the generative AI model based on data retrieved from the database.

[0828] Output: The generated learning plan.

[0829] Specific operation: The server runs a Python script and sends the prompt message "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user" to the generative AI model (GPT-4), and the AI ​​model then generates a study plan.

[0830] Step 4:

[0831] The server provides the lesson plan to the user.

[0832] Input: The generated learning plan.

[0833] Data processing: Embed the learning plan into an HTML template and render it as a web page.

[0834] Output: The lesson plan provided to the user.

[0835] Specific operation: The server embeds the generated study plan on the user's dashboard page, and the user can log in and check their own study plan. For example, the dashboard will display "Your study plan for the next week: We will provide practice questions and reference video links to focus on studying 'Fundamentals of Electromagnetism'."

[0836] Step 5:

[0837] The server executes the PDCA cycle.

[0838] Input: New training data.

[0839] Data processing: Add new data to the dataset and retrain the AI ​​model using machine learning libraries.

[0840] Output: A generative AI model with improved accuracy.

[0841] What it does: The server periodically runs a Python script to add newly collected data to the dataset and retrain the model with a script called “train.py.”

[0842] (Application example 1)

[0843] 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."

[0844] The challenge is to eliminate the educational disparity caused by income disparity and provide high-quality educational instruction, especially to students from low-income families. Furthermore, it is necessary to create an environment in which students can study efficiently by providing easy-to-use study plans on smartphones.

[0845] 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.

[0846] In this invention, the server includes a means for users to post study data, a server means for collecting and storing the posted study data, a means for a generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a PDCA cycle means for improving the generative AI model based on the collected data, a means for users to post study data from a smartphone, and a means for presenting the generated study plan on the smartphone. This makes it possible to eliminate educational disparities and provide an efficient learning environment where students can concentrate on their studies.

[0847] We have created definitions for the following important words:

[0848] The "means for users to post learning data" refers to an interface that allows users to input learning data such as their own learning progress and test results and send it to the system.

[0849] The "server means for collecting and storing submitted learning data" refers to a server device and database mechanism for receiving and centrally managing learning data sent by users.

[0850] The "means by which the generative AI model designs a learning plan using collected data" refers to the AI ​​algorithms and calculation mechanisms that analyze the accumulated learning data and generate an optimal learning plan for each user.

[0851] The "means for providing the designed lesson plan to the user" is an interface and notification system that informs the user of the created lesson plan and allows them to execute it.

[0852] The "PDCA cycle method for improving generative AI models based on collected data" is a process of continuously collecting new training data and repeating the cycle of planning (Plan), doing (Do), evaluating (Check), and improving (Act) to improve the accuracy of generative AI models.

[0853] "Means for users to post learning data from their smartphones" refers to applications and interfaces for inputting and sending learning data using a smartphone.

[0854] The "means for presenting the generated study plan on a smartphone" refers to an application and an interface for visually displaying the study plan generated on the smartphone to the user.

[0855] This invention is a system for eliminating educational disparities, particularly reducing inequalities in educational opportunities due to income disparities. This system allows users to upload their own learning data using their smartphones, and a generative AI model then designs an optimal learning plan based on that data and provides it to the user. It also has a function for improving the accuracy of the generative AI model using the PDCA cycle.

[0856] System Overview

[0857] The system is broadly composed of the following elements:

[0858] 1. User device: A smartphone used by the user to input and post learning data.

[0859] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a cloud server is used to host the database and AI models.

[0860] 3. Generative AI models: Algorithms that generate optimal learning plans based on each user's data. These typically use Python and scikit-learn.

[0861] 4. PDCA cycle: The process of continuously collecting learning data and retraining the AI ​​model.

[0862] Program processing

[0863] 1. User Data Submission:

[0864] Users can submit their study progress and test results to the system via an input form on their smartphones. This data includes test scores, study time, weak areas, etc.

[0865] 2. Data collection and storage:

[0866] The server receives the data posted by users and stores it in a database, allowing all users' learning data to be managed centrally.

[0867] 3. Designing a learning plan:

[0868] Using data stored on the server, the generative AI model designs an optimal learning plan for each individual user, for example, recommending additional practice problems or explanatory videos to users who struggle with math.

[0869] 4. Providing a study plan:

[0870] The server then sends the generated study plan to the user's smartphone, where the user can review it and proceed with their studies according to the suggested study content.

[0871] 5. Implementing the PDCA cycle:

[0872] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan and providing more personalized learning.

[0873] Specific examples

[0874] For example, if a student scores 45 points on a physics test, they can submit that data from their smartphone. The server receives the information and stores it in a database. The generative AI model uses this data to generate recommendations, such as "Watch a video on the basics of electromagnetism." This recommendation is then sent to the user's smartphone, allowing them to proceed with their studies according to the submitted study plan.

[0875] An example of a prompt is:

[0876] "Please generate a study plan based on the following user data: User ID: 1, Subject: Physics, Score: 45 points, Date: 2023-10-20."

[0877] The text format is used.

[0878] In this way, this system aims to correct educational disparities and can provide a comfortable and efficient learning environment by using users' smartphones.

[0879] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0880] Step 1:

[0881] The user posts their study data from their smartphone. Specifically, the user launches the application, enters their study progress and test results into the input form, and presses the submit button. At this time, input includes test scores, subjects, date and time, etc. The submitted data is sent from the smartphone to the server.

[0882] Step 2:

[0883] The server collects the learning data sent by the user and stores it in a database. The server analyzes the received data and converts it into an appropriate format for saving in the database. For example, data such as "User ID: 1, Subject: Physics, Score: 45 points, Date and Time: 2023-10-20" is saved in the corresponding field in the database. In this process, the input is the submitted raw data, and the output is the data stored in the database.

[0884] Step 3:

[0885] The server uses a generative AI model to design a learning plan based on the accumulated data. Specifically, it analyzes the collected learning data and recommends additional learning resources based on each user's grades and progress. For example, for a user who received a 45 in physics, a recommendation to "watch basic physics videos" is generated. The input here is the learning data stored in the database, and the output is a learning plan for the user.

[0886] Step 4:

[0887] To provide the generated study plan to the user, the server sends a notification to the user's smartphone. The user can then check the generated study plan through their smartphone. Specifically, the recommended study content is displayed on the application's dashboard. The input here is the generated study plan, and the output is the recommended content displayed on the user's smartphone.

[0888] Step 5:

[0889] The server continues to collect new training data and executes a PDCA cycle to improve the generative AI model. In this cycle, the AI ​​model is retrained based on the new data collected, improving its accuracy. For example, data from users with new test results is added, and the model's performance is evaluated and improved against previous recommendations. The input is new training data, and the output is an improved generative AI model.

[0890] Through the above steps, the system of the present invention provides users with efficient and personalized learning plans, contributing to the elimination of educational disparities. Furthermore, the system's simple operation on a smartphone improves user convenience.

[0891] 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.

[0892] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users post their study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention realizes adjustments to the study plan according to the user's emotional state.

[0893] System Overview

[0894] The system includes the following elements:

[0895] 1. User terminal: A device for users to input and post learning data.

[0896] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[0897] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data.

[0898] 4. Emotion Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan.

[0899] 5. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[0900] Program processing overview

[0901] 1. User submits training data:

[0902] Users submit their learning progress and test results to the system through an input form. For example, if a middle school student user gets 75 points on a math test, they enter the score and the test date (2023-10-15) and submit. When the user presses the submit button, the data is sent to the server.

[0903] 2. The server receives and stores the data:

[0904] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0905] 3. The server designs a learning plan using the generative AI model:

[0906] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0907] 4. Emotion engine analyzes user emotions:

[0908] Emotional data is collected while the user is studying, and the emotion engine analyzes the data. For example, if the user feels tired after studying for a long time, the system will recognize that emotional state.

[0909] 5. Generative AI models adjust learning plans:

[0910] The server takes into account the analysis results of the emotion engine and provides feedback to the generative AI model to adjust the study plan according to the user's emotional state. For example, if the user feels tired, the study plan will include breaks for relaxation and lighter learning content.

[0911] 6. The server provides the study plan to the user:

[0912] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0913] 7. Implementing the PDCA cycle:

[0914] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[0915] Specific examples

[0916] For example, consider a high school student using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. The emotion engine also analyzes the user's emotional data. If the user indicates high stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently. This system can provide high-quality educational instruction at low cost, especially for students from low-income families, and also enables personalized learning based on the user's emotional state.

[0917] The processing flow will be explained below.

[0918] Step 1: User submits training data

[0919] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[0920] Step 2: The server receives and stores the data

[0921] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[0922] Step 3: The server uses the generative AI model to design a learning plan

[0923] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[0924] Step 4: The device collects emotion data

[0925] The user's device is equipped with an emotion engine that uses sensors to collect the user's facial expressions, input speed, voice, etc. The emotion engine uses the collected data to estimate the user's emotional state. For example, if the user's face remains expressionless for a long period of time, it is determined that the user is tired.

[0926] Step 5: The server receives the analysis results of the emotion engine.

[0927] The analysis results of the emotion engine are sent to the server. The server receives this data and records it in a database as the user's emotional state. For example, it might record a state such as "highly tired" or "highly focused."

[0928] Step 6: The server adjusts the learning plan

[0929] Based on the analysis results of the emotion engine, the server provides feedback to the generative AI model and adjusts the study plan according to the user's emotional state. For example, if the user is tired, it will add lighter study content that does not require much concentration and intervals for relaxation to the study plan.

[0930] Step 7: The server provides the lesson plan to the user

[0931] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[0932] Step 8: The server executes the PDCA cycle to improve the model

[0933] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[0934] Example 2

[0935] 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."

[0936] Conventional educational systems provided study plans based on a user's learning progress and test results, but were unable to provide individualized study plans that took the user's emotional state into account. Furthermore, there were limited means of improving the accuracy of generative AI models using the PDCA cycle. This made it difficult to provide appropriate study plans, especially for users who were feeling stressed or fatigued, resulting in issues with learning continuity and efficiency. Furthermore, there was a need to automate the process of accumulating and analyzing learning data and flexibly provide optimal study plans for individual users.

[0937] 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.

[0938] In this invention, the server includes a means for users to post study data, a means for collecting and storing the posted study data, a means for the generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a sentiment analysis means for analyzing the user's emotional data, a means for adjusting the study plan based on the results of the sentiment analysis means, and a PDCA cycle means for improving the generative AI model based on the collected data. This makes it possible to provide an individual study plan that takes into account not only the user's study progress and test results but also their emotional state, significantly improving the continuity and efficiency of learning. Furthermore, the accuracy of the generative AI model can be continuously improved using the PDCA cycle, making it possible to always provide the latest and most optimal study plans.

[0939] "User" means a person who uses the system to input and post learning data.

[0940] "Learning data" refers to information related to learning, such as a user's learning progress and test results.

[0941] The "server" is a central device for collecting, storing, and analyzing submitted learning data.

[0942] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[0943] A "study plan" is a specific plan created by a generative AI model that includes learning procedures, study materials, and problem sets provided to the user.

[0944] "Emotion analysis means" refers to techniques and devices for analyzing a user's emotional state.

[0945] The PDCA cycle is a process of improving the accuracy of generative AI models through a cycle of planning (Plan), execution (Do), evaluation (Check), and improvement (Act).

[0946] A "database" is a system that centrally stores and manages collected learning data.

[0947] "Emotion data" is information about the user's emotional state, including, for example, stress and fatigue.

[0948] "Feedback" is the action of improving systems and processes based on information derived from analysis and evaluation results.

[0949] This invention is a system for resolving educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users input and post study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the study plan according to the user's emotional state.

[0950] System configuration

[0951] The system includes the following elements:

[0952] 1. User device: The device on which the user inputs and posts learning data. Typically, a PC, tablet, or smartphone is used.

[0953] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a high-performance database server or cloud computing platform is often used.

[0954] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data, using, for example, machine learning or deep learning techniques.

[0955] 4. Emotion Analysis Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan. It uses facial recognition and voice analysis technologies.

[0956] 5. PDCA cycle: The process of continuously collecting training data and improving generative AI models.

[0957] Overview of program processing

[0958] 1. The user posts their learning data. The user posts their learning progress and test results to the system through a dedicated input form. For example, they enter data such as "I got 75 points on the math test, and the test date was 2023-10-15."

[0959] 2. The server receives and stores the data. The server receives the learning data sent by the user and stores it in a database. The data includes the user ID, subject, score, test date, etc.

[0960] 3. The server designs a study plan using a generative AI model. The server retrieves the user's latest study data from the database and inputs this data into the generative AI model. For example, if the user's math test score is below average, the server will suggest special practice sets and video lectures to strengthen the foundations of that subject.

[0961] 4. The emotion analysis engine analyzes the user's emotions. The emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[0962] 5. The generative AI model adjusts the study plan. The server feeds back the results of the emotion analysis engine's analysis to the generative AI model, which then adjusts the study plan according to the user's emotional state. For example, "If the user feels tired, add breaks and lighter learning content to the study plan to help them relax."

[0963] 6. The server provides the user with the study plan. The server updates the platform with the generated study plan. The user can then log in to the platform via their device and check the latest study plan on their dashboard. Specifically, the plan displays exercises, recommended learning materials, study schedules, and more.

[0964] 7. Implement the PDCA cycle. The server continuously collects new learning data and emotion data, and retrains the generative AI model to improve its accuracy. This allows future learning plans to be more tailored to the user's needs.

[0965] Specific examples

[0966] For example, a high school student user could enter their physics test score of 60 into the system. The server receives this information and stores it in a database. The generative AI model uses this data to identify areas that need reinforcement (for example, the basics of electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. An emotion analysis engine also analyzes the user's emotional data, and if the user is experiencing high levels of stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce stress. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently.

[0967] Prompt Sentence Examples

[0968] Here is an example of a prompt to input to a generative AI model:

[0969] User ID: A12345

[0970] Subject: Mathematics

[0971] Points scored: 75

[0972] Test date: 2023-10-15

[0973] Emotional state: Tired

[0974] When this prompt is fed into a generative AI model, it generates an optimal learning plan for the user, taking into account the user's emotional state, providing a flexible learning plan tailored to the user's situation.

[0975] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0976] Step 1:

[0977] Users post training data

[0978] The user enters their learning progress and test results into the input form and sends the data to the server by pressing the send button. For example, they enter data such as "I got 75 points on the math test, and the test was held on 2023-10-15." The data entered includes the user ID, subject, score, and test date.

[0979] Specific behavior:

[0980] The user operates a device (PC or smartphone) to enter data into an input form. When the send button is pressed, the data is sent to the server via an HTTP request.

[0981] Input: Study progress and test results (e.g., subjects, scores, test dates)

[0982] Output: Training data sent to the server

[0983] Step 2:

[0984] The server receives and stores the data

[0985] The server receives learning data sent by users in real time and stores it in a database. The received data includes user ID, subjects, scores, test dates, etc. This data is organized for each user and managed centrally.

[0986] Specific behavior:

[0987] The server receives the HTTP request, extracts the data, connects to the database and inserts the data into the appropriate tables, and performs validation checks to ensure data consistency.

[0988] Input: Training data submitted by the user

[0989] Output: Training data stored in a database

[0990] Step 3:

[0991] The server designs a learning plan using a generative AI model

[0992] The server retrieves the latest learning data from the database and inputs it into the generative AI model, which then generates an optimal learning plan based on the input data. For example, if a student's math test score is below average, the system will suggest special practice sets and video lectures to strengthen their foundations in that area.

[0993] Specific behavior:

[0994] The server executes SQL queries to retrieve the latest training data from the database, inputs the retrieved data into the generative AI model, and performs calculations to generate a learning plan. The generated learning plan is embodied as a problem set, recommended learning materials, and a learning schedule.

[0995] Input: Training data obtained from the database

[0996] Output: A learning plan generated by the generative AI model

[0997] Step 4:

[0998] The sentiment analysis engine analyzes the user's emotions

[0999] Emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[1000] Specific behavior:

[1001] The user uses the device's camera and microphone to collect emotional data such as facial expressions and tone of voice. The server receives the emotional data and passes it to the emotion analysis engine. The emotion analysis engine analyzes the data and identifies the user's emotional state (fatigue, stress, etc.).

[1002] Input: Emotion data collected from the user

[1003] Output: Emotional state analyzed by the emotion analysis engine

[1004] Step 5:

[1005] Generative AI models adjust learning plans

[1006] The server feeds the results of the emotion analysis engine back to the generative AI model, and adjusts the study plan according to the user's emotional state. For example, if the user feels tired, it will add breaks and lighter learning content to the study plan to help them relax.

[1007] Specific behavior:

[1008] The server retrieves the generated learning plan and feeds back the results of the sentiment analysis engine. The generative AI model receives the feedback and readjusts the learning plan, updating it to the optimal content.

[1009] Input: Emotional state analyzed by the emotion analysis engine and existing learning plan

[1010] Output: Adjusted learning plan

[1011] Step 6:

[1012] The server provides the study plan to the user.

[1013] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view the latest study plan on their dashboard, which displays exercises, recommended study materials, study schedules, and more.

[1014] Specific behavior:

[1015] The server stores the learning plan on the platform. When a user logs in to the platform, the latest learning plan is displayed on the dashboard. Users can check the learning plan through a browser or app and proceed with their studies according to the plan.

[1016] Input: Adjusted Study Plan

[1017] Output: The lesson plan displayed on the user's dashboard

[1018] Step 7:

[1019] Implementing the PDCA cycle

[1020] The server continuously collects new learning and emotion data and retrains the generative AI model, improving its accuracy so that future learning plans are more tailored to the user's needs.

[1021] Specific behavior:

[1022] The server periodically collects new data and stores it in a database. The generative AI model is retrained based on the collected data. The effectiveness of the learning plan is evaluated and the model is updated based on feedback. The next learning plan is revised to be more optimal based on the user's learning progress and emotional state.

[1023] Input: New training data and emotion data

[1024] Output: Next learning plan provided by an improved generative AI model

[1025] (Application example 2)

[1026] 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."

[1027] Conventional educational systems lacked individual optimization based on the user's learning progress and test results, limiting the effectiveness of learning. Furthermore, learning plans were not adjusted based on the user's emotional state, making efficient learning difficult. Furthermore, providing high-quality education to students from low-income families was also a challenge.

[1028] 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 a means for users to post learning data, a server means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, an emotion engine means for analyzing the user's emotional state, a means for adjusting the learning plan based on the user's emotional state, and a PDCA cycle means for improving the generative AI model based on the collected data. This enables individual optimization according to the user's learning progress and emotional state, resulting in efficient and effective learning. It also makes it possible to provide high-quality educational instruction equally to students from low-income families.

[1029] "Study data" refers to data that users post to the system about their own study progress and test results.

[1030] The "server" is a central device that collects and stores submitted learning data and performs further analysis.

[1031] A "generative AI model" is an artificial intelligence algorithm that analyzes collected learning data and designs the optimal learning plan for each user.

[1032] A "study plan" is a specific schedule and content designed by a generative AI model to help users study efficiently and effectively.

[1033] The "emotion engine" is a system that analyzes the user's emotional state and provides feedback to the generative AI model based on that information.

[1034] The PDCA cycle is a process of improving the accuracy of generative AI models by repeating the cycle of Plan, Do, Check, and Act.

[1035] This invention is a system that allows users to post learning data and collect, store, and analyze that data. The system has the following main components:

[1036] 1. User terminal: A device on which a user inputs and posts learning data. Examples include a PC, smartphone, or tablet.

[1037] 2. Server: This is the central device that collects, stores, and analyzes the submitted training data and executes the generative AI model. The server has a database and centrally manages each user's training data.

[1038] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data. For example, machine learning models and deep learning models using Python are often used.

[1039] 4. Emotion Engine: This system analyzes the user's emotional state and reflects the results in the learning plan. Emotion analysis utilizes facial recognition software using cameras and sensors, or voice analysis software.

[1040] 5. PDCA Cycle: This is the process of continuously collecting training data and improving the generative AI model. The PDCA cycle is performed using Python scripts and automation tools.

[1041] In this system, learning data is first posted from the user's device to the server. The server receives and analyzes this data and uses a generative AI model to generate an optimal learning plan. Next, the user's emotional data is also collected and analyzed by the emotion engine. The learning plan is adjusted based on the analysis results, and the final learning plan is provided to the user.

[1042] Furthermore, the collected data is continuously analyzed based on the PDCA cycle to improve the performance of the generative AI model, ensuring that users always receive an effective learning plan tailored to their learning progress.

[1043] Examples:

[1044] For example, imagine a high school student using the system. The user enters their physics test score of 60 into the system. The server then receives that information and stores it in a database. The generative AI model uses that data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area.

[1045] In addition, the emotion engine analyzes the user's emotional data, and if the user is feeling high stress, the generative AI model adjusts the study plan and adds relaxation menus and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[1046] Example prompt sentence:

[1047] User ID: student123,

[1048] Points: 75,

[1049] Subject: Mathematics,

[1050] Test date: 2023-10-15

[1051] Generate the best learning plan for this user.

[1052] This example makes high-quality educational instruction widely available, including to students from low-income families, and provides personalized optimization based on the user's emotional state.

[1053] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1054] Program processing flow

[1055] Step 1:

[1056] The user submits their learning data to the system through an input form. The input data includes the user ID, subject, test score, and test date. For example, the information might be "User ID: student123, Subject: Mathematics, Score: 75, Test Date: 2023-10-15."

[1057] Step 2:

[1058] The server receives the submitted training data and stores it in a database. It analyzes the input data and accumulates it in the database in a format that allows for centralized management of data for each user. The output is the training data stored in the database.

[1059] Step 3:

[1060] The server then retrieves the stored training data from the database and inputs it into the generative AI model. The input is the entire training data, and the output is the optimal training plan for the user. Specifically, the generative AI model uses a machine learning algorithm to generate the optimal training plan.

[1061] Step 4:

[1062] The server collects emotional data from the user's device. The input is facial recognition data obtained using a camera or sensor, or voice recognition data. The output is the emotional state analyzed by the emotion engine. For example, the user's state may be analyzed as "tired" or "stressed."

[1063] Step 5:

[1064] The server provides feedback to the generative AI model based on the analysis results of the emotion engine and adjusts the learning plan. The input is the output data of the emotion engine, and the output is an adjusted learning plan. Specifically, this includes adding breaks and relaxation menus to reduce the user's burden.

[1065] Step 6:

[1066] The server provides the final study plan to the user. The input is the adjusted study plan, and the output is a study plan displayed on the user's dashboard, where the user can proceed with their studies.

[1067] Step 7:

[1068] The server continuously collects new learning data and emotion data from users and retrains the generative AI model. The input is new learning data and emotion data, and the output is an improved generative AI model. Specifically, the PDCA cycle is run based on the new data to improve the model.

[1069] These steps enable individual optimization tailored to the user's learning progress and emotional state, resulting in efficient and effective learning.

[1070] 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.

[1071] 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.

[1072] 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.

[1073] [Fourth embodiment]

[1074] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1075] 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.

[1076] 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).

[1077] 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.

[1078] 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.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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.

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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."

[1087] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. This system allows users to submit study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle.

[1088] System Overview

[1089] The system includes the following elements:

[1090] 1. User terminal: A device for users to input and post learning data.

[1091] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[1092] 3. Generative AI model: An algorithm that generates an optimal learning plan based on each user's data.

[1093] 4. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[1094] Program processing overview

[1095] 1. User submits training data:

[1096] A user submits their learning progress and test results to the system through an input form. For example, a junior high school student enters their math test score as "75 points" and submits the test date as "2023-10-15." The server receives the data.

[1097] 2. The server collects and stores the data:

[1098] The server stores the learning data posted by users in a database, allowing all users' learning data to be managed centrally.

[1099] 3. Designing lesson plans using generative AI models:

[1100] Based on the data stored on the server, the generative AI model designs a study plan for each user. For example, if a user's math test reveals that they have weak areas, the model will recommend additional practice problems and explanatory videos.

[1101] 4. Provide users with a learning plan:

[1102] The server provides the generated study plan to the user, who can then log in to view their own study plan and proceed with their studies according to the recommended study content.

[1103] 5. Implementing the PDCA cycle:

[1104] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan.

[1105] Specific examples

[1106] For example, imagine a high school student is using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need improvement (e.g., basic electromagnetism) and generates a study plan that includes practice problems and reference videos specific to that area. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[1107] This system of the present invention makes it possible to provide high-quality educational instruction at low cost, especially to students from low-income families. Furthermore, by implementing the PDCA cycle, the accuracy of the generative AI model is continuously improved, enabling the provision of learning plans that are more tailored to individual needs.

[1108] The processing flow will be explained below.

[1109] Step 1: User submits training data

[1110] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[1111] Step 2: The server receives and stores the data

[1112] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[1113] Step 3: The server uses the generative AI model to design a learning plan

[1114] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[1115] Step 4: The server provides the lesson plan to the user

[1116] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[1117] Step 5: The server executes the PDCA cycle to improve the model

[1118] Every time a user periodically submits new learning data, that data is collected and stored in a database. The server retrains the generative AI model using the latest learning data, improving the model's accuracy. This ensures that future learning plans are more suited to the user's needs. The effectiveness of the plan is evaluated, and insights gained from the data are reflected to continuously improve the model.

[1119] Example 1

[1120] 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."

[1121] In modern society, income disparities cause educational disparities, making it difficult for students from low-income families to access high-quality education. The present invention aims to provide a system that reduces this educational disparity and enables all students to learn effectively.

[1122] 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.

[1123] In this invention, the server includes a means for users to post learning data, a database means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, a means for providing the designed learning plan to the user, and a PDCA cycle means for improving the generative AI model based on the collected data, which makes it possible to provide an optimal learning plan based on individual learning progress and needs.

[1124] "User" means an individual or organization that uses the System to input and post learning data.

[1125] "Study data" refers to data such as study progress and test results that users enter and post into the system.

[1126] "Means for posting" refers to an interface or device that allows a user to input and transmit learning data into the system.

[1127] The "database means for collecting and storing" is a database system for receiving and centrally managing submitted learning data.

[1128] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[1129] The "means of designing a learning plan" is the process of using a generative AI model to create an optimal learning plan for each user.

[1130] The "means of providing" refers to an interface or system that allows users to view the designed learning plan.

[1131] The "PDCA cycle method" is a process for continuously improving the generative AI model based on collected data.

[1132] The "system" refers to the overall mechanism for eliminating educational disparities, including the measures mentioned above.

[1133] This invention is a system designed to eliminate educational disparities, particularly those caused by income disparities. This system allows users to input and post learning data, and a generative AI model then proposes an optimal learning plan based on that data. Furthermore, it includes a mechanism for improving the accuracy of the generative AI model through the PDCA cycle.

[1134] Hardware and software used

[1135] Hardware

[1136] 1. User terminal: A device used by users to input and post learning data. Specifically, this includes PCs, smartphones, tablets, etc.

[1137] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. It uses a high-performance server machine.

[1138] software

[1139] 1. Database system: A database for centrally managing the submitted learning data. A relational database management system such as MySQL or PostgreSQL is used.

[1140] 2. Generative AI model: An algorithm that generates the optimal learning plan based on user data. In this case, we use GPT-4, a generative natural language model.

[1141] 3. Web application: An interface for users to input learning data and a platform for displaying the generated learning plan. It uses a front-end framework such as React or Vue.js and a back-end framework such as Django or Flask.

[1142] Data processing and calculation

[1143] 1. Users submit their training data

[1144] The user enters their learning progress and test results into the form and presses the send button. This data is sent from the user's device to the server.

[1145] Example: A junior high school student user enters the math test result "75 points" and the test date "2023-10-15" and submits it.

[1146] 2. The server collects and stores data

[1147] The server stores the received data in a database, where all user learning data is managed in a unified manner.

[1148] Software used: MySQL

[1149] Example: Insert data into the database using the SQL query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[1150] 3. The server designs a learning plan using the generative AI model

[1151] Based on the data stored on the server, the generative AI model designs the optimal learning plan for each user. The generative AI model calls the GPT-4 model using a Python script.

[1152] Software used: GPT-4

[1153] Example: Send the prompt "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user."

[1154] 4. The server provides the study plan to the user

[1155] The generated learning plan is displayed on the user's dashboard, where the user can log in and view their own learning plan.

[1156] Software used: React, Django

[1157] Example: Displaying the following on the dashboard: "Your study plan for the next week: We provide practice questions and helpful video links to help you focus on 'Fundamentals of Electromagnetism.'"

[1158] 5. The server executes the PDCA cycle

[1159] The server continuously collects new training data and retrains the generative AI model to improve the accuracy of its learning plans, using machine learning libraries such as TensorFlow and PyTorch.

[1160] Software used: TensorFlow, PyTorch

[1161] Example: Once a month, run a script called "train.py" that retrains your AI model based on newly collected data.

[1162] In this way, the system provides a customized learning plan for each user, making it a powerful tool for narrowing educational gaps.

[1163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1164] Step 1:

[1165] Users post training data.

[1166] Input: Users enter their learning progress and test results into an input form.

[1167] Data processing: The contents of the input form are sent from the user's terminal to the server.

[1168] Output: The training data is sent to the server.

[1169] Specific operation: A user accesses a web application and navigates to a form page for learning management. For example, a junior high school student enters their math test score (75 points) and the test date (2023-10-15), and clicks the submit button.

[1170] Step 2:

[1171] The server collects and stores the data.

[1172] Input: Training data submitted by the user.

[1173] Data processing: Sanitize the received data and insert it into the database using SQL queries.

[1174] Output: Training data stored in a database.

[1175] What it does: The server formats the data it receives and inserts it into the MySQL database using the query "INSERT INTO test_data (user_id, subject, score, date) VALUES ...".

[1176] Step 3:

[1177] The server designs a learning plan using a generative AI model.

[1178] Input: User learning data stored in a database.

[1179] Data processing: Send prompts to the generative AI model based on data retrieved from the database.

[1180] Output: The generated learning plan.

[1181] Specific operation: The server runs a Python script and sends the prompt message "The user's past test results are as follows: [75 points, 65 points...]. Please generate the optimal study plan for the user" to the generative AI model (GPT-4), and the AI ​​model then generates a study plan.

[1182] Step 4:

[1183] The server provides the lesson plan to the user.

[1184] Input: The generated learning plan.

[1185] Data processing: Embed the learning plan into an HTML template and render it as a web page.

[1186] Output: The lesson plan provided to the user.

[1187] Specific operation: The server embeds the generated study plan on the user's dashboard page, and the user can log in and check their own study plan. For example, the dashboard will display "Your study plan for the next week: We will provide practice questions and reference video links to focus on studying 'Fundamentals of Electromagnetism'."

[1188] Step 5:

[1189] The server executes the PDCA cycle.

[1190] Input: New training data.

[1191] Data processing: Add new data to the dataset and retrain the AI ​​model using machine learning libraries.

[1192] Output: A generative AI model with improved accuracy.

[1193] What it does: The server periodically runs a Python script to add newly collected data to the dataset and retrain the model with a script called “train.py.”

[1194] (Application example 1)

[1195] 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."

[1196] The challenge is to eliminate the educational disparity caused by income disparity and provide high-quality educational instruction, especially to students from low-income families. Furthermore, it is necessary to create an environment in which students can study efficiently by providing easy-to-use study plans on smartphones.

[1197] 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.

[1198] In this invention, the server includes a means for users to post study data, a server means for collecting and storing the posted study data, a means for a generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a PDCA cycle means for improving the generative AI model based on the collected data, a means for users to post study data from a smartphone, and a means for presenting the generated study plan on the smartphone. This makes it possible to eliminate educational disparities and provide an efficient learning environment where students can concentrate on their studies.

[1199] We have created definitions for the following important words:

[1200] The "means for users to post learning data" refers to an interface that allows users to input learning data such as their own learning progress and test results and send it to the system.

[1201] The "server means for collecting and storing submitted learning data" refers to a server device and database mechanism for receiving and centrally managing learning data sent by users.

[1202] The "means by which the generative AI model designs a learning plan using collected data" refers to the AI ​​algorithms and calculation mechanisms that analyze the accumulated learning data and generate an optimal learning plan for each user.

[1203] The "means for providing the designed lesson plan to the user" is an interface and notification system that informs the user of the created lesson plan and allows them to execute it.

[1204] The "PDCA cycle method for improving generative AI models based on collected data" is a process of continuously collecting new training data and repeating the cycle of planning (Plan), doing (Do), evaluating (Check), and improving (Act) to improve the accuracy of generative AI models.

[1205] "Means for users to post learning data from their smartphones" refers to applications and interfaces for inputting and sending learning data using a smartphone.

[1206] The "means for presenting the generated study plan on a smartphone" refers to an application and an interface for visually displaying the study plan generated on the smartphone to the user.

[1207] This invention is a system for eliminating educational disparities, particularly reducing inequalities in educational opportunities due to income disparities. This system allows users to upload their own learning data using their smartphones, and a generative AI model then designs an optimal learning plan based on that data and provides it to the user. It also has a function for improving the accuracy of the generative AI model using the PDCA cycle.

[1208] System Overview

[1209] The system is broadly composed of the following elements:

[1210] 1. User device: A smartphone used by the user to input and post learning data.

[1211] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a cloud server is used to host the database and AI models.

[1212] 3. Generative AI models: Algorithms that generate optimal learning plans based on each user's data. These typically use Python and scikit-learn.

[1213] 4. PDCA cycle: The process of continuously collecting learning data and retraining the AI ​​model.

[1214] Program processing

[1215] 1. User Data Submission:

[1216] Users can submit their study progress and test results to the system via an input form on their smartphones. This data includes test scores, study time, weak areas, etc.

[1217] 2. Data collection and storage:

[1218] The server receives the data posted by users and stores it in a database, allowing all users' learning data to be managed centrally.

[1219] 3. Designing a learning plan:

[1220] Using data stored on the server, the generative AI model designs an optimal learning plan for each individual user, for example, recommending additional practice problems or explanatory videos to users who struggle with math.

[1221] 4. Providing a study plan:

[1222] The server then sends the generated study plan to the user's smartphone, where the user can review it and proceed with their studies according to the suggested study content.

[1223] 5. Implementing the PDCA cycle:

[1224] The server continuously collects new learning data and retrains the generative AI model, improving the accuracy of the learning plan and providing more personalized learning.

[1225] Specific examples

[1226] For example, if a student scores 45 points on a physics test, they can submit that data from their smartphone. The server receives the information and stores it in a database. The generative AI model uses this data to generate recommendations, such as "Watch a video on the basics of electromagnetism." This recommendation is then sent to the user's smartphone, allowing them to proceed with their studies according to the submitted study plan.

[1227] An example of a prompt is:

[1228] "Please generate a study plan based on the following user data: User ID: 1, Subject: Physics, Score: 45 points, Date: 2023-10-20."

[1229] The text format is used.

[1230] In this way, this system aims to correct educational disparities and can provide a comfortable and efficient learning environment by using users' smartphones.

[1231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1232] Step 1:

[1233] The user posts their study data from their smartphone. Specifically, the user launches the application, enters their study progress and test results into the input form, and presses the submit button. At this time, input includes test scores, subjects, date and time, etc. The submitted data is sent from the smartphone to the server.

[1234] Step 2:

[1235] The server collects the learning data sent by the user and stores it in a database. The server analyzes the received data and converts it into an appropriate format for saving in the database. For example, data such as "User ID: 1, Subject: Physics, Score: 45 points, Date and Time: 2023-10-20" is saved in the corresponding field in the database. In this process, the input is the submitted raw data, and the output is the data stored in the database.

[1236] Step 3:

[1237] The server uses a generative AI model to design a learning plan based on the accumulated data. Specifically, it analyzes the collected learning data and recommends additional learning resources based on each user's grades and progress. For example, for a user who received a 45 in physics, a recommendation to "watch basic physics videos" is generated. The input here is the learning data stored in the database, and the output is a learning plan for the user.

[1238] Step 4:

[1239] To provide the generated study plan to the user, the server sends a notification to the user's smartphone. The user can then check the generated study plan through their smartphone. Specifically, the recommended study content is displayed on the application's dashboard. The input here is the generated study plan, and the output is the recommended content displayed on the user's smartphone.

[1240] Step 5:

[1241] The server continues to collect new training data and executes a PDCA cycle to improve the generative AI model. In this cycle, the AI ​​model is retrained based on the new data collected, improving its accuracy. For example, data from users with new test results is added, and the model's performance is evaluated and improved against previous recommendations. The input is new training data, and the output is an improved generative AI model.

[1242] Through the above steps, the system of the present invention provides users with efficient and personalized learning plans, contributing to the elimination of educational disparities. Furthermore, the system's simple operation on a smartphone improves user convenience.

[1243] 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.

[1244] This invention is a system that solves educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users post their study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention realizes adjustments to the study plan according to the user's emotional state.

[1245] System Overview

[1246] The system includes the following elements:

[1247] 1. User terminal: A device for users to input and post learning data.

[1248] 2. Server: The central device that collects, stores, and analyzes submitted data and runs the generative AI model.

[1249] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data.

[1250] 4. Emotion Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan.

[1251] 5. PDCA cycle: The process of continuously collecting learning data and improving the AI ​​model.

[1252] Program processing overview

[1253] 1. User submits training data:

[1254] Users submit their learning progress and test results to the system through an input form. For example, if a middle school student user gets 75 points on a math test, they enter the score and the test date (2023-10-15) and submit. When the user presses the submit button, the data is sent to the server.

[1255] 2. The server receives and stores the data:

[1256] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[1257] 3. The server designs a learning plan using the generative AI model:

[1258] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[1259] 4. Emotion engine analyzes user emotions:

[1260] Emotional data is collected while the user is studying, and the emotion engine analyzes the data. For example, if the user feels tired after studying for a long time, the system will recognize that emotional state.

[1261] 5. Generative AI models adjust learning plans:

[1262] The server takes into account the analysis results of the emotion engine and provides feedback to the generative AI model to adjust the study plan according to the user's emotional state. For example, if the user feels tired, the study plan will include breaks for relaxation and lighter learning content.

[1263] 6. The server provides the study plan to the user:

[1264] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[1265] 7. Implementing the PDCA cycle:

[1266] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[1267] Specific examples

[1268] For example, consider a high school student using the system. The user enters their physics test score of 60 into the system. The server receives the information and stores it in a database. The generative AI model uses the data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. The emotion engine also analyzes the user's emotional data. If the user indicates high stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently. This system can provide high-quality educational instruction at low cost, especially for students from low-income families, and also enables personalized learning based on the user's emotional state.

[1269] The processing flow will be explained below.

[1270] Step 1: User submits training data

[1271] Users access the platform using their devices and enter their learning progress and test results into the learning data input form. For example, if a junior high school student gets 75 points on a math test, they enter the score and the test date along with "2023-10-15" and submit. When the user presses the submit button, the data is sent to the system.

[1272] Step 2: The server receives and stores the data

[1273] The server receives the learning data sent by the user. This data includes the user ID, subject, score, test date, etc. By storing the received data in a database, the learning data for each user can be managed centrally.

[1274] Step 3: The server uses the generative AI model to design a learning plan

[1275] The server retrieves the user's most recent learning data from the database, inputs that data into a generative AI model, and generates an optimal learning plan for each user. For example, if a user scores below 70 on a math test, the server suggests special practice sets and video lectures to deepen their understanding of the fundamentals of that subject.

[1276] Step 4: The device collects emotion data

[1277] The user's device is equipped with an emotion engine that uses sensors to collect the user's facial expressions, input speed, voice, etc. The emotion engine uses the collected data to estimate the user's emotional state. For example, if the user's face remains expressionless for a long period of time, it is determined that the user is tired.

[1278] Step 5: The server receives the analysis results of the emotion engine.

[1279] The analysis results of the emotion engine are sent to the server. The server receives this data and records it in a database as the user's emotional state. For example, it might record a state such as "highly tired" or "highly focused."

[1280] Step 6: The server adjusts the learning plan

[1281] Based on the analysis results of the emotion engine, the server provides feedback to the generative AI model and adjusts the study plan according to the user's emotional state. For example, if the user is tired, it will add lighter study content that does not require much concentration and intervals for relaxation to the study plan.

[1282] Step 7: The server provides the lesson plan to the user

[1283] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view their latest study plan on their dashboard, which displays details such as practice questions, recommended study materials, and study schedules.

[1284] Step 8: The server executes the PDCA cycle to improve the model

[1285] The server continuously collects new learning and emotion data and retrains the generative AI model to improve its accuracy. This ensures that future learning plans are more tailored to the user's needs. The effectiveness of the plans is evaluated, and insights gained from the data are reflected in the model's continuous improvement.

[1286] Example 2

[1287] 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."

[1288] Conventional educational systems provided study plans based on a user's learning progress and test results, but were unable to provide individualized study plans that took the user's emotional state into account. Furthermore, there were limited means of improving the accuracy of generative AI models using the PDCA cycle. This made it difficult to provide appropriate study plans, especially for users who were feeling stressed or fatigued, resulting in issues with learning continuity and efficiency. Furthermore, there was a need to automate the process of accumulating and analyzing learning data and flexibly provide optimal study plans for individual users.

[1289] 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.

[1290] In this invention, the server includes a means for users to post study data, a means for collecting and storing the posted study data, a means for the generative AI model to design a study plan using the collected data, a means for providing the designed study plan to the user, a sentiment analysis means for analyzing the user's emotional data, a means for adjusting the study plan based on the results of the sentiment analysis means, and a PDCA cycle means for improving the generative AI model based on the collected data. This makes it possible to provide an individual study plan that takes into account not only the user's study progress and test results but also their emotional state, significantly improving the continuity and efficiency of learning. Furthermore, the accuracy of the generative AI model can be continuously improved using the PDCA cycle, making it possible to always provide the latest and most optimal study plans.

[1291] "User" means a person who uses the system to input and post learning data.

[1292] "Learning data" refers to information related to learning, such as a user's learning progress and test results.

[1293] The "server" is a central device for collecting, storing, and analyzing submitted learning data.

[1294] A "generative AI model" is an artificial intelligence algorithm that designs optimal learning plans based on collected learning data.

[1295] A "study plan" is a specific plan created by a generative AI model that includes learning procedures, study materials, and problem sets provided to the user.

[1296] "Emotion analysis means" refers to techniques and devices for analyzing a user's emotional state.

[1297] The PDCA cycle is a process of improving the accuracy of generative AI models through a cycle of planning (Plan), execution (Do), evaluation (Check), and improvement (Act).

[1298] A "database" is a system that centrally stores and manages collected learning data.

[1299] "Emotion data" is information about the user's emotional state, including, for example, stress and fatigue.

[1300] "Feedback" is the action of improving systems and processes based on information derived from analysis and evaluation results.

[1301] This invention is a system for resolving educational disparities, and is designed in particular to reduce educational disparities caused by income disparities. In this system, users input and post study data, and a generative AI model analyzes the collected data to design an optimal study plan and provide it to the user. It also has a mechanism for improving the accuracy of the generative AI model by implementing a PDCA cycle. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the study plan according to the user's emotional state.

[1302] System configuration

[1303] The system includes the following elements:

[1304] 1. User device: The device on which the user inputs and posts learning data. Typically, a PC, tablet, or smartphone is used.

[1305] 2. Server: A central device that collects, stores, and analyzes submitted data and runs generative AI models. Specifically, a high-performance database server or cloud computing platform is often used.

[1306] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data, using, for example, machine learning or deep learning techniques.

[1307] 4. Emotion Analysis Engine: A system that analyzes the user's emotional state and reflects the results in the learning plan. It uses facial recognition and voice analysis technologies.

[1308] 5. PDCA cycle: The process of continuously collecting training data and improving generative AI models.

[1309] Overview of program processing

[1310] 1. The user posts their learning data. The user posts their learning progress and test results to the system through a dedicated input form. For example, they enter data such as "I got 75 points on the math test, and the test date was 2023-10-15."

[1311] 2. The server receives and stores the data. The server receives the learning data sent by the user and stores it in a database. The data includes the user ID, subject, score, test date, etc.

[1312] 3. The server designs a study plan using a generative AI model. The server retrieves the user's latest study data from the database and inputs this data into the generative AI model. For example, if the user's math test score is below average, the server will suggest special practice sets and video lectures to strengthen the foundations of that subject.

[1313] 4. The emotion analysis engine analyzes the user's emotions. The emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[1314] 5. The generative AI model adjusts the study plan. The server feeds back the results of the emotion analysis engine's analysis to the generative AI model, which then adjusts the study plan according to the user's emotional state. For example, "If the user feels tired, add breaks and lighter learning content to the study plan to help them relax."

[1315] 6. The server provides the user with the study plan. The server updates the platform with the generated study plan. The user can then log in to the platform via their device and check the latest study plan on their dashboard. Specifically, the plan displays exercises, recommended learning materials, study schedules, and more.

[1316] 7. Implement the PDCA cycle. The server continuously collects new learning data and emotion data, and retrains the generative AI model to improve its accuracy. This allows future learning plans to be more tailored to the user's needs.

[1317] Specific examples

[1318] For example, a high school student user could enter their physics test score of 60 into the system. The server receives this information and stores it in a database. The generative AI model uses this data to identify areas that need reinforcement (for example, the basics of electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area. An emotion analysis engine also analyzes the user's emotional data, and if the user is experiencing high levels of stress, the generative AI model adjusts the study plan, adding relaxation activities and light review materials to reduce stress. This study plan is displayed on the user's dashboard, allowing the user to follow the instructions to study efficiently.

[1319] Prompt Sentence Examples

[1320] Here is an example of a prompt to input to a generative AI model:

[1321] User ID: A12345

[1322] Subject: Mathematics

[1323] Points scored: 75

[1324] Test date: 2023-10-15

[1325] Emotional state: Tired

[1326] When this prompt is fed into a generative AI model, it generates an optimal learning plan for the user, taking into account the user's emotional state, providing a flexible learning plan tailored to the user's situation.

[1327] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1328] Step 1:

[1329] Users post training data

[1330] The user enters their learning progress and test results into the input form and sends the data to the server by pressing the send button. For example, they enter data such as "I got 75 points on the math test, and the test was held on 2023-10-15." The data entered includes the user ID, subject, score, and test date.

[1331] Specific behavior:

[1332] The user operates a device (PC or smartphone) to enter data into an input form. When the send button is pressed, the data is sent to the server via an HTTP request.

[1333] Input: Study progress and test results (e.g., subjects, scores, test dates)

[1334] Output: Training data sent to the server

[1335] Step 2:

[1336] The server receives and stores the data

[1337] The server receives learning data sent by users in real time and stores it in a database. The received data includes user ID, subjects, scores, test dates, etc. This data is organized for each user and managed centrally.

[1338] Specific behavior:

[1339] The server receives the HTTP request, extracts the data, connects to the database and inserts the data into the appropriate tables, and performs validation checks to ensure data consistency.

[1340] Input: Training data submitted by the user

[1341] Output: Training data stored in a database

[1342] Step 3:

[1343] The server designs a learning plan using a generative AI model

[1344] The server retrieves the latest learning data from the database and inputs it into the generative AI model, which then generates an optimal learning plan based on the input data. For example, if a student's math test score is below average, the system will suggest special practice sets and video lectures to strengthen their foundations in that area.

[1345] Specific behavior:

[1346] The server executes SQL queries to retrieve the latest training data from the database, inputs the retrieved data into the generative AI model, and performs calculations to generate a learning plan. The generated learning plan is embodied as a problem set, recommended learning materials, and a learning schedule.

[1347] Input: Training data obtained from the database

[1348] Output: A learning plan generated by the generative AI model

[1349] Step 4:

[1350] The sentiment analysis engine analyzes the user's emotions

[1351] Emotional data collected while the user is studying is analyzed in real time. For example, "if the user feels tired after studying for a long time, the system will recognize that emotional state."

[1352] Specific behavior:

[1353] The user uses the device's camera and microphone to collect emotional data such as facial expressions and tone of voice. The server receives the emotional data and passes it to the emotion analysis engine. The emotion analysis engine analyzes the data and identifies the user's emotional state (fatigue, stress, etc.).

[1354] Input: Emotion data collected from the user

[1355] Output: Emotional state analyzed by the emotion analysis engine

[1356] Step 5:

[1357] Generative AI models adjust learning plans

[1358] The server feeds the results of the emotion analysis engine back to the generative AI model, and adjusts the study plan according to the user's emotional state. For example, if the user feels tired, it will add breaks and lighter learning content to the study plan to help them relax.

[1359] Specific behavior:

[1360] The server retrieves the generated learning plan and feeds back the results of the sentiment analysis engine. The generative AI model receives the feedback and readjusts the learning plan, updating it to the optimal content.

[1361] Input: Emotional state analyzed by the emotion analysis engine and existing learning plan

[1362] Output: Adjusted learning plan

[1363] Step 6:

[1364] The server provides the study plan to the user.

[1365] The server then updates the platform with the generated study plan. Users can then log in to the platform via their device and view the latest study plan on their dashboard, which displays exercises, recommended study materials, study schedules, and more.

[1366] Specific behavior:

[1367] The server stores the learning plan on the platform. When a user logs in to the platform, the latest learning plan is displayed on the dashboard. Users can check the learning plan through a browser or app and proceed with their studies according to the plan.

[1368] Input: Adjusted Study Plan

[1369] Output: The lesson plan displayed on the user's dashboard

[1370] Step 7:

[1371] Implementing the PDCA cycle

[1372] The server continuously collects new learning and emotion data and retrains the generative AI model, improving its accuracy so that future learning plans are more tailored to the user's needs.

[1373] Specific behavior:

[1374] The server periodically collects new data and stores it in a database. The generative AI model is retrained based on the collected data. The effectiveness of the learning plan is evaluated and the model is updated based on feedback. The next learning plan is revised to be more optimal based on the user's learning progress and emotional state.

[1375] Input: New training data and emotion data

[1376] Output: Next learning plan provided by an improved generative AI model

[1377] (Application example 2)

[1378] 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."

[1379] Conventional educational systems lacked individual optimization based on the user's learning progress and test results, limiting the effectiveness of learning. Furthermore, learning plans were not adjusted based on the user's emotional state, making efficient learning difficult. Furthermore, providing high-quality education to students from low-income families was also a challenge.

[1380] 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 a means for users to post learning data, a server means for collecting and storing the posted learning data, a means for the generative AI model to design a learning plan using the collected data, an emotion engine means for analyzing the user's emotional state, a means for adjusting the learning plan based on the user's emotional state, and a PDCA cycle means for improving the generative AI model based on the collected data. This enables individual optimization according to the user's learning progress and emotional state, resulting in efficient and effective learning. It also makes it possible to provide high-quality educational instruction equally to students from low-income families.

[1381] "Study data" refers to data that users post to the system about their own study progress and test results.

[1382] The "server" is a central device that collects and stores submitted learning data and performs further analysis.

[1383] A "generative AI model" is an artificial intelligence algorithm that analyzes collected learning data and designs the optimal learning plan for each user.

[1384] A "study plan" is a specific schedule and content designed by a generative AI model to help users study efficiently and effectively.

[1385] The "emotion engine" is a system that analyzes the user's emotional state and provides feedback to the generative AI model based on that information.

[1386] The PDCA cycle is a process of improving the accuracy of generative AI models by repeating the cycle of Plan, Do, Check, and Act.

[1387] This invention is a system that allows users to post learning data and collect, store, and analyze that data. The system has the following main components:

[1388] 1. User terminal: A device on which a user inputs and posts learning data. Examples include a PC, smartphone, or tablet.

[1389] 2. Server: This is the central device that collects, stores, and analyzes the submitted training data and executes the generative AI model. The server has a database and centrally manages each user's training data.

[1390] 3. Generative AI model: An artificial intelligence algorithm that generates an optimal learning plan based on each user's data. For example, machine learning models and deep learning models using Python are often used.

[1391] 4. Emotion Engine: This system analyzes the user's emotional state and reflects the results in the learning plan. Emotion analysis utilizes facial recognition software using cameras and sensors, or voice analysis software.

[1392] 5. PDCA Cycle: This is the process of continuously collecting training data and improving the generative AI model. The PDCA cycle is performed using Python scripts and automation tools.

[1393] In this system, learning data is first posted from the user's device to the server. The server receives and analyzes this data and uses a generative AI model to generate an optimal learning plan. Next, the user's emotional data is also collected and analyzed by the emotion engine. The learning plan is adjusted based on the analysis results, and the final learning plan is provided to the user.

[1394] Furthermore, the collected data is continuously analyzed based on the PDCA cycle to improve the performance of the generative AI model, ensuring that users always receive an effective learning plan tailored to their learning progress.

[1395] Examples:

[1396] For example, imagine a high school student using the system. The user enters their physics test score of 60 into the system. The server then receives that information and stores it in a database. The generative AI model uses that data to identify areas that need reinforcement (e.g., basic electromagnetism) and generates a study plan that includes practice questions and reference videos specific to that area.

[1397] In addition, the emotion engine analyzes the user's emotional data, and if the user is feeling high stress, the generative AI model adjusts the study plan and adds relaxation menus and light review materials to reduce the user's burden. This study plan is displayed on the user's dashboard, and the user can follow the instructions to study efficiently.

[1398] Example prompt sentence:

[1399] User ID: student123,

[1400] Points: 75,

[1401] Subject: Mathematics,

[1402] Test date: 2023-10-15

[1403] Generate the best learning plan for this user.

[1404] This example makes high-quality educational instruction widely available, including to students from low-income families, and provides personalized optimization based on the user's emotional state.

[1405] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1406] Program processing flow

[1407] Step 1:

[1408] The user submits their learning data to the system through an input form. The input data includes the user ID, subject, test score, and test date. For example, the information might be "User ID: student123, Subject: Mathematics, Score: 75, Test Date: 2023-10-15."

[1409] Step 2:

[1410] The server receives the submitted training data and stores it in a database. It analyzes the input data and accumulates it in the database in a format that allows for centralized management of data for each user. The output is the training data stored in the database.

[1411] Step 3:

[1412] The server then retrieves the stored training data from the database and inputs it into the generative AI model. The input is the entire training data, and the output is the optimal training plan for the user. Specifically, the generative AI model uses a machine learning algorithm to generate the optimal training plan.

[1413] Step 4:

[1414] The server collects emotional data from the user's device. The input is facial recognition data obtained using a camera or sensor, or voice recognition data. The output is the emotional state analyzed by the emotion engine. For example, the user's state may be analyzed as "tired" or "stressed."

[1415] Step 5:

[1416] The server provides feedback to the generative AI model based on the analysis results of the emotion engine and adjusts the learning plan. The input is the output data of the emotion engine, and the output is an adjusted learning plan. Specifically, this includes adding breaks and relaxation menus to reduce the user's burden.

[1417] Step 6:

[1418] The server provides the final study plan to the user. The input is the adjusted study plan, and the output is a study plan displayed on the user's dashboard, where the user can proceed with their studies.

[1419] Step 7:

[1420] The server continuously collects new learning data and emotion data from users and retrains the generative AI model. The input is new learning data and emotion data, and the output is an improved generative AI model. Specifically, the PDCA cycle is run based on the new data to improve the model.

[1421] These steps enable individual optimization tailored to the user's learning progress and emotional state, resulting in efficient and effective learning.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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).

[1429] 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.

[1430] 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."

[1431] 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.

[1432] 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).

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] The following is further disclosed regarding the above embodiment.

[1444] (Claim 1)

[1445] A means for users to post learning data;

[1446] a server means for collecting and storing the submitted learning data;

[1447] A means by which the generative AI model uses the collected data to design a learning plan; and

[1448] a means for providing the designed lesson plan to the user;

[1449] A PDCA cycle method to improve the generative AI model based on collected data;

[1450] A system including:

[1451] (Claim 2)

[1452] 2. The system according to claim 1, wherein the learning data posted by the user is learning progress and test results.

[1453] (Claim 3)

[1454] 2. The system of claim 1, wherein the generative AI model comprises means for designing a learning plan based on the user's past learning data.

[1455] "Example 1"

[1456] (Claim 1)

[1457] A means for users to post learning data;

[1458] a database means for collecting and storing the submitted learning data;

[1459] A means by which the generative AI model uses the collected data to design a learning plan; and

[1460] a means for providing the designed lesson plan to the user;

[1461] A PDCA cycle method to improve the generative AI model based on collected data;

[1462] A system including:

[1463] (Claim 2)

[1464] 2. The system according to claim 1, wherein the learning data posted by the user is learning progress and test results.

[1465] (Claim 3)

[1466] 2. The system of claim 1, wherein the generative AI model comprises means for designing a learning plan based on the user's past learning data.

[1467] "Application Example 1"

[1468] (Claim 1)

[1469] A means for users to post learning data;

[1470] a server means for collecting and storing the submitted learning data;

[1471] A means by which the generative AI model uses the collected data to design a learning plan; and

[1472] a means for providing the designed lesson plan to the user;

[1473] A PDCA cycle method to improve the generative AI model based on collected data;

[1474] A means for users to post learning data from their smartphones;

[1475] A means for presenting the generated learning plan on a smartphone;

[1476] A system including:

[1477] (Claim 2)

[1478] 2. The system according to claim 1, wherein the learning data posted by the user is learning progress and test results.

[1479] (Claim 3)

[1480] 2. The system of claim 1, wherein the generative AI model comprises means for designing a learning plan based on the user's past learning data.

[1481] "Example 2: Combining Emotion Engines"

[1482] (Claim 1)

[1483] A means for users to post learning data;

[1484] a server means for collecting and storing the submitted learning data;

[1485] A means by which the generative AI model uses the collected data to design a learning plan; and

[1486] a means for providing the designed lesson plan to the user;

[1487] emotion analysis means for analyzing emotion data of a user;

[1488] means for adjusting the learning plan based on the results of the sentiment analysis means;

[1489] A PDCA cycle method to improve the generative AI model based on collected data;

[1490] A system including:

[1491] (Claim 2)

[1492] 2. The system according to claim 1, wherein the learning data posted by the user is learning progress and test results.

[1493] (Claim 3)

[1494] 2. The system of claim 1, wherein the generative AI model comprises means for designing a learning plan based on the user's past learning data.

[1495] "Application example 2 when combining emotion engines"

[1496] (Claim 1)

[1497] A means for users to post learning data;

[1498] a server means for collecting and storing the submitted learning data;

[1499] A means by which the generative AI model uses the collected data to design a learning plan; and

[1500] a means for providing the designed lesson plan to the user;

[1501] emotion engine means for analyzing the user's emotional state;

[1502] means for adjusting a study plan based on the user's emotional state;

[1503] A PDCA cycle method to improve the generative AI model based on collected data;

[1504] A system including:

[1505] (Claim 2)

[1506] 2. The system according to claim 1, wherein the learning data posted by the user is learning progress and test results.

[1507] (Claim 3)

[1508] 2. The system of claim 1, wherein the generative AI model comprises means for designing a learning plan based on the user's past learning data. [Explanation of symbols]

[1509] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to post learning data; a server means for collecting and storing the submitted learning data; A means by which the generative AI model uses the collected data to design a learning plan; and a means for providing the designed lesson plan to the user; A PDCA cycle method to improve the generative AI model based on collected data; A system including:

2. The system according to claim 1, wherein the learning data posted by the user is learning progress and test results.

3. 10. The system of claim 1, wherein the generative AI model comprises means for designing a learning plan based on the user's past learning data.

Images