System

Abstract

A system is provided.SOLUTION: This system is provided with a means for inputting the fundamental information of a learner, and for transmitting the fundamental information to a server, a means for generating learning contents optimal to the learner by using a generation AI by the server, and a means for transmitting the generated learning contents to the learner's terminals, and for displaying them.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] There are many extremely poor people around the world who do not receive an adequate education, which creates a cycle of poverty. In particular, people who lack basic literacy and numeracy skills have limited opportunities to receive an education, making it difficult for them to become independent and improve their living environment. To solve this problem, it is necessary to develop a system that provides education optimized for each individual learner and breaks the cycle of poverty. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes a means for inputting basic information about a learner and transmitting the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's terminal and displaying it.

[0006] Furthermore, the present invention provides education tailored to the needs of individual learners by adding a means for collecting learner progress information and transmitting the progress information to a server, a means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content, and a means for transmitting and displaying the adjusted learning content to the learner's terminal.

[0007] Furthermore, the present invention realizes a system that always provides the latest and most effective education by adding a means for storing learner learning data on a server, a means for training a generation AI based on the stored data and updating the AI ​​model, a means for generating new learning content using the updated AI model, and a means for transmitting and displaying the latest generated learning content to the learner's device. This provides an environment where even the poorest people can receive an effective education, thereby breaking the cycle of poverty.

[0008] "Student" refers to an individual user receiving education, who is the target of using the learning content provided by the system.

[0009] "Basic Information" means data necessary for optimizing learning, such as the learner's age, prior education level, and area of ​​residence.

[0010] "Device" refers to a device used by a learner, such as a computer, smartphone, or tablet, that receives learning content via an internet connection.

[0011] "Server" refers to a central computer system that receives learner basic information and progress information, and generates and provides learning content using generation AI.

[0012] "Generative AI" is an algorithm that uses artificial intelligence technology to generate optimal learning content based on basic information and progress information about each individual learner.

[0013] "Learning content" refers to educational materials such as teaching materials, workbooks, and feedback aimed at basic education such as reading, writing, and arithmetic.

[0014] "Progress information" is data collected as a learner progresses with their studies, and includes the percentage of correct answers, the time it took to answer, and the progress of their studies.

[0015] "Understanding" refers to the degree to which a learner assesses how accurately they understand a particular learning content.

[0016] "Learning data" includes all data generated when learners use the system, including basic information, progress information, and evaluation results.

[0017] An "AI model" is an artificial intelligence framework trained based on accumulated learning data and used to generate new learning content. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention is a system that aims to provide the poorest people with a minimum level of education and break the cycle of poverty. This system includes a means for inputting basic information about a learner and sending the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it.

[0040] Explanation of program processing

[0041] 1. Enter and submit basic student information

[0042] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[0043] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[0044] 2. Creation and provision of learning content

[0045] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[0046] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[0047] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[0048] 3. Feedback on learning status and generation of next content

[0049] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[0050] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[0051] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[0052] The server transmits the tailored learning content to the terminal, which displays it.

[0053] 4. Data accumulation and generation AI training

[0054] The server accumulates the learning data sent by users and manages the learning history. The accumulated data is used to train the AI ​​model.

[0055] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[0056] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[0057] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress information accumulates, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The user accesses the terminal and enters basic information (age, education level, area of ​​residence, etc.). The user then launches the application and records the necessary information in the input form.

[0061] Step 2:

[0062] The device sends the basic information entered to the server. The device app then sends the input data to the server via the API.

[0063] Step 3:

[0064] The server receives the user's basic information and uses a generation AI to generate optimal learning content. The server accesses the database, customizes the content based on the received basic information, and passes it on to the generation AI to generate the learning content.

[0065] Step 4:

[0066] The server sends the generated learning content to the device. The server sends data through the API to return the generated content to the device.

[0067] Step 5:

[0068] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[0069] Step 6:

[0070] Users use learning content to solve problems and advance their learning. Progress information (correct answer rate, answer time, etc.) is collected in real time each time a problem is solved.

[0071] Step 7:

[0072] The device sends the collected learning progress information to the server. The progress data is sent to the server each time learning is completed or at a specific timing.

[0073] Step 8:

[0074] The server analyzes the progress information and evaluates the user's level of understanding. The server uses a data analysis module to analyze the received progress information and measure the user's level of understanding.

[0075] Step 9:

[0076] The server uses AI to generate the next learning content, tailored based on the level of comprehension. Based on the results of the comprehension assessment, the next learning content is customized and new content is generated by AI.

[0077] Step 10:

[0078] The server sends the tailored learning content to the device, and sends data through the API to send the generated content back to the device.

[0079] Step 11:

[0080] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[0081] Step 12:

[0082] The server accumulates learning data collected from users and stores their learning history in a database. The server uses the accumulated data to train the generative AI and update the AI ​​model.

[0083] Step 13:

[0084] The server generates new learning content using the updated AI model, and retrains the AI ​​model based on new data to generate the latest content.

[0085] Step 14:

[0086] The server sends the latest learning content to the device and displays it. Generated content is sent back to the device, allowing the user's learning to be continuously improved.

[0087] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[0088] Example 1

[0089] 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."

[0090] Providing appropriate and effective education to the poorest people is a challenge. Providing individually optimized learning content based on each learner's progress requires a great deal of effort and cost. Furthermore, there is a need for efficient management of learning data and continuous improvement of AI models.

[0091] 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.

[0092] In this invention, the server includes a means for inputting the learner's personal information and transmitting the personal information to the server, a means for the server to generate learning content optimized for the learner using a generative AI, a means for transmitting the generated learning content to the learner's terminal device and displaying it, a means for the server to analyze the learner's personal information received and format it as input data suitable for the generative AI model, a means for inputting the information as prompts to the generative AI model, a means for using the generative AI model to generate learning content based on the input requirements, and a means for converting the generated content into an appropriate format and transmitting it to the terminal device. This makes it possible to provide learning content individually optimized according to the learner's progress, thereby providing effective education. Furthermore, the accumulation of learning data and the training of the generative AI can be efficiently managed, allowing for continuous improvement in the accuracy of the AI ​​model.

[0093] "Personal information of learners" refers to information necessary to understand the learner's background and situation, such as age, educational level, and area of ​​residence.

[0094] An "information processing device" is a device used to perform various data processing operations, such as receiving, analyzing, and storing data, and training generative AI models.

[0095] "Generative AI" is an AI system that has the ability to generate new content or information based on given data or prompts.

[0096] "Learning content" refers to educational content such as teaching materials, questions, and exercises that learners should study.

[0097] A "terminal device" is a device that a user can directly access to view, operate, and respond to learning content.

[0098] A "prompt" refers to an instruction or question entered into a generative AI model to elicit an appropriate response.

[0099] "Learning data" refers to all information generated by a learner, including, for example, progress, answer history, and comprehension assessment.

[0100] "Format" refers to the state in which data or content is arranged in a specific form or structure.

[0101] "Training" refers to the learning process that uses new data to improve the accuracy of a generative AI model.

[0102] The present invention is a system aimed at providing the poorest people with a minimum level of education and breaking the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to an information processing device, a means for the information processing device to generate optimal learning content for the learner using generative AI, and a means for transmitting the generated learning content to the learner's terminal device and displaying it. The system also includes a means for collecting learner progress information and adjusting the learning content based on the progress information, and a means for accumulating learning data to train an AI model and improve the accuracy of the generative AI model.

[0103] 1. Enter and submit basic information

[0104] The first thing a user does is input basic information such as age, educational level, and area of ​​residence. This information is entered into a terminal device and transmitted to an information processing device. During this transmission process, security protocols (e.g., HTTPS) are used to ensure data security.

[0105] 2. Creation and provision of learning content

[0106] The information processing device uses generative artificial intelligence (e.g., OpenAI's GPT model) based on the received basic information to generate optimal learning content for the learner. In this process, the information processing device analyzes the received personal information, formats it as input data suitable for the generative AI model, and enters it as a prompt. For example, the prompt might be "10 years old, rural area, arithmetic and reading / writing at the third grade level." The generated learning content is then converted into an appropriate format (e.g., HTML or JSON) and sent to the terminal device. The terminal device displays the received learning content on a user interface, allowing the user to begin learning.

[0107] 3. Feedback on learning status and generation of next content

[0108] The terminal device collects the user's learning progress information in real time and transmits it to the information processing device. The information processing device analyzes the received progress information, evaluates the user's level of understanding, and adjusts the next learning content. This evaluation result is provided as a prompt to the generative artificial intelligence model, which generates the next learning content. For example, if the evaluation indicates that "the user is struggling with fraction problems," problems covering everything from basic to advanced fractions are generated. The generated new learning content is transmitted to the terminal device and displayed to the user.

[0109] 4. Data accumulation and generation AI training

[0110] The information processing device accumulates all learning data sent by users and stores it in a learning history database. The accumulated data is used to train a generative AI model (generative artificial intelligence). This process improves the accuracy of the AI ​​model and generates more effective learning content. The new trained AI model is used to generate the next learning content and is continuously updated.

[0111] Examples of specific examples and prompts

[0112] As a specific example, when a user logs in for the first time and enters basic information such as "10 years old," "able to read and write basics," and "lives in a rural area," the information processing device inputs the prompt "10 years old, rural area, arithmetic and reading / writing at the third grade level" into the generative AI model. The generated simple arithmetic problems and basic reading comprehension problems are displayed on the user's terminal device. As the user works on these problems, progress data is accumulated, and new content based on the user's progress is provided the next time they log in.

[0113] Example prompt sentence:

[0114] "Generate math and literacy learning content for 10-year-olds, rural areas, and third grade levels."

[0115] "Generate new fraction math problems based on user progress data."

[0116] As described above, this system provides effective education to learners and makes it possible to provide individually optimized learning content according to their progress.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] A user launches a learning application using a terminal device and enters basic information. This basic information includes age, educational level, and area of ​​residence. For example, the user might enter "10 years old," "can read and write basic words," and "live in a rural area." Input: User's basic information. Output: Data of the entered basic information.

[0120] Step 2:

[0121] The terminal device sends the input basic information to the information processing device (server). At this time, a security protocol (e.g., HTTPS) is used to ensure the safety of the data. Input: User's basic information. Output: Data of the basic information sent to the information processing device.

[0122] Step 3:

[0123] The server analyzes the basic information it receives and formats it as input data suitable for the generative AI model. Specifically, it summarizes information such as age and education level and converts it into a format that can be passed to the generative AI model. Input: The basic information sent. Output: Data formatted for the generative AI model.

[0124] Step 4:

[0125] The server inputs the formatted data to the generative AI model as a prompt. This prompt includes the learner's characteristics and learning requirements. For example, the requirement "10 years old, rural area, arithmetic and reading / writing at the third grade level" is used as the prompt. Input: Prompt for the generative AI model. Output: Prompt input to the generative AI model.

[0126] Step 5:

[0127] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate learning content based on the input prompt. Specifically, it generates simple math problems or basic reading comprehension questions. Input: The prompt input to the generative AI model. Output: The generated learning content.

[0128] Step 6:

[0129] The server converts the generated learning content into an appropriate format (e.g., HTML, JSON) and sends it to the terminal device. Input: Generated learning content. Output: Content converted into an appropriate format and its transmission.

[0130] Step 7:

[0131] The terminal device displays the received learning content on the user interface. The user browses this content and begins learning. Input: Received learning content. Output: Learning content displayed to the user.

[0132] Step 8:

[0133] The user engages with the learning content and answers or performs operations. Specifically, they solve displayed math problems or enter answers to reading comprehension questions. Input: User operations and answers. Output: Progress data of learning activities.

[0134] Step 9:

[0135] The terminal device collects the user's learning progress information in real time. The collected data includes the percentage of correct answers to questions and the time it took to answer them. Input: User's learning activity. Output: Collected progress data.

[0136] Step 10:

[0137] The terminal device sends the collected progress data to the server. Input: Collected progress data. Output: Progress data sent to the server.

[0138] Step 11:

[0139] The server analyzes the received progress information and evaluates the user's level of understanding. It identifies areas of strength and weakness. Input: Submitted progress data. Output: Analyzed level of understanding information.

[0140] Step 12:

[0141] The server provides the generative AI model with a prompt to generate the next learning content based on the progress data. For example, the next prompt is generated based on the evaluation that "the user is struggling with fraction problems." Input: Analyzed comprehension information. Output: Prompt to input to the generative AI model.

[0142] Step 13:

[0143] The server uses the generative AI model to generate new learning content. For example, new problems covering everything from the basics to advanced fractions are generated. Input: The prompt entered into the generative AI model. Output: New learning content.

[0144] Step 14:

[0145] The server sends the generated new learning content to the terminal device, which displays it. Input: The generated new learning content. Output: The new content displayed on the terminal device.

[0146] Step 15:

[0147] The user starts learning again with new learning content. Progress data is collected, sent, and analyzed in the same way. Input: Learning content to be re-engaged. Output: New progress data.

[0148] Step 16:

[0149] The server accumulates all the learning data sent by users and stores it in the learning history database. Input: Sent learning data. Output: Accumulated data.

[0150] Step 17:

[0151] The server trains the generative AI based on the accumulated data and updates the generative AI model, improving the accuracy of the AI ​​model. Input: Accumulated data. Output: New trained AI model.

[0152] Step 18:

[0153] The server generates new learning content using the updated generative AI model and sends it to the terminal device. Input: The trained new AI model. Output: The generated new learning content.

[0154] Step 19:

[0155] The terminal device displays the latest learning content on the user interface, allowing the user to continue learning. Input: Generated new learning content. Output: The latest learning content displayed to the user.

[0156] In this way, this system provides learning content that is individually optimized according to the learner's progress, supporting effective education. It efficiently manages the accumulation of learning data and the training of the generated AI, enabling continuous improvement of the accuracy of the AI ​​model.

[0157] (Application example 1)

[0158] 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."

[0159] For the poorest people, breaking the cycle of poverty through education is important, but the educational resources and opportunities they can access are extremely limited. Furthermore, there are no effective ways to link education with support activities such as food delivery. Furthermore, there is a need for the automatic generation and provision of educational content based on progress. There is a need to solve these problems and provide an effective educational support system for the poorest people.

[0160] 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.

[0161] In this invention, the server includes: means for inputting basic information about the learner and transmitting the basic information to the server; means for the server to generate optimal learning content for the learner using a generation AI; means for transmitting the generated learning content to the learner's device and displaying it; means for collecting progress information about the learner and transmitting the progress information to the server; means for the server to evaluate the learner's level of understanding based on the progress information and generate subsequent learning content; means for storing the learner's learning data in the server; means for training the generation AI based on the stored data and updating the AI ​​model; and means for transmitting the learning content generated using the updated AI model to the learner's device and displaying it. This makes it possible to provide optimal educational content tailored to the progress of learners from the poorest backgrounds, thereby effectively supporting efforts to break the cycle of poverty through education.

[0162] "Basic information about the learner" refers to personal information such as the learner's age, education level, and area of ​​residence.

[0163] The "server" is a system that receives basic information and progress information about learners, processes and analyzes it, and generates learning content using generation AI.

[0164] "Generative AI" is artificial intelligence that automatically generates optimal learning content based on a learner's basic information and progress information.

[0165] "Learning content" refers to educational materials such as teaching materials and problem sets that are used by learners to receive education.

[0166] "Device" means a device such as a smartphone, smart glasses, or head-mounted display that a learner uses to receive and view learning content.

[0167] "Progress information" is data that indicates the learner's learning progress and level of understanding.

[0168] "Level of understanding" is an indicator that shows how well a learner has understood the learning content provided.

[0169] "Learning data" refers to a series of data related to learning, such as basic information about the learner, progress information, and learning history.

[0170] An "updated AI model" is a generative AI model that has been retrained based on the learning data stored on the server.

[0171] The "poorest" are the most economically disadvantaged social groups, those who lack access to basic needs and education.

[0172] "Food assistance" refers to support services such as food and meals provided to the poorest people.

[0173] A "smart device" is an electronic device that allows learners to receive learning content and learn interactively.

[0174] The present invention is a system that aims to provide the poorest people with the minimum education necessary to break the cycle of poverty. This system consists of the following steps:

[0175] Hardware and software configuration

[0176] This system includes a terminal for inputting learner information, a server for utilizing the generative AI, and a smart device for displaying learning content. Specifically, the following hardware and software are used:

[0177] Devices: Smartphones, smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest)

[0178] Server: Cloud server (e.g. AWS)

[0179] Software: Custom applications (for Android / iOS), AI models (e.g., GPT-4)

[0180] Program processing explanation

[0181] 1. Enter and submit basic student information

[0182] The user accesses the terminal and enters basic information such as the learner's name, age, education level, and area of ​​residence, which is then sent to the server.

[0183] Example: A user launches an application and enters information such as "10 years old," "can read and write basic words," and "lives in a rural area."

[0184] 2. Creation and provision of learning content

[0185] The server uses the generative AI model based on the received basic information to generate optimal learning content for the learner, which is then sent to the device and displayed to the user.

[0186] Example: For a 10-year-old learner, basic math problems and reading and writing exercises are generated.

[0187] Example prompt: Generate educational content on nutrition and basic math for a 10-year-old user living in a rural area who can read and write at a basic level.

[0188] 3. Feedback on learning status and generation of next content

[0189] The device collects the user's learning progress information and sends it to the server, which analyzes the progress data and adjusts and generates the next learning content.

[0190] Example: Identify areas where the user is weak, assess their level of understanding, and automatically generate the most appropriate next learning content.

[0191] 4. Data accumulation and generation AI training

[0192] The server stores all the learning data sent by users and uses it to train the AI ​​model, which is periodically updated and retrained on new datasets.

[0193] Example: Updating AI models with newly collected data improves the accuracy of learning content.

[0194] Overall flow

[0195] By repeating this process, it is possible to continue providing effective education to the poorest learners. Furthermore, by integrating food assistance and education, this system will realize more practical and effective support. For example, it is possible to design a system that links with food delivery services so that educational content is provided at the same time as food is delivered.

[0196] In this way, the present invention can provide a practical and sustainable educational support system to break the cycle of poverty.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] Users access their devices and enter basic information such as their name, age, education level, and area of ​​residence. This basic information is sent as input data to the server, which analyzes the received data and generates a basic profile of the learner. Specific operations involve the user answering a series of questions using an app on their smartphone or smart device.

[0200] Step 2:

[0201] The server uses a generative AI model based on the received basic information to generate optimal learning content for the learner. Here, the input data is the learner's basic information, and the output data is the generated learning content. The generative AI model uses a prompt sentence based on the input data to launch a text generation algorithm (e.g., GPT-4) to generate appropriate learning content. Specifically, the AI ​​engine in the server operates and generates learning materials based on the specified prompt sentence.

[0202] Step 3:

[0203] The generated learning content is sent from the server to the terminal. The terminal receives this learning content and displays it to the user. The input data here is the generated learning content, and the output data is the learning content reflected on the user's display screen. Specifically, the new educational content is displayed to the user through the notification function.

[0204] Step 4:

[0205] The user studies the displayed learning content. During the learning process, the user's answers and activity log are automatically recorded. The input data is the user's learning behavior, and the output data is learning progress information. Specific operations include answer input and progress recording via a touch screen or input interface.

[0206] Step 5:

[0207] The device collects the user's learning progress information and sends this data to the server. The input data is the user's learning progress information, and the output data is the progress log sent to the server. Specifically, the progress data is automatically uploaded at specified intervals or for each event.

[0208] Step 6:

[0209] Based on the received learning progress information, the server uses a generative AI model to adjust and generate the next learning content. Here, the input data is the received learning progress information, and the output data is the newly generated learning content. Specifically, an analytical algorithm runs within the server, automatically generating learning materials appropriate for the next step based on the progress data.

[0210] Step 7:

[0211] All of a learner's learning data is stored on the server. The input data is past and current learning progress data, and the output data is the accumulated learning history. Specifically, data is continuously added to the server's database, and backups and database compression are performed as necessary.

[0212] Step 8:

[0213] The server trains and updates the generative AI model based on the accumulated data. The input data is the accumulated training data, and the output data is the updated generative AI model. Specifically, the machine learning algorithm runs using the new data set, and re-training is performed to improve the accuracy of the model.

[0214] Step 9:

[0215] New learning content is generated using the updated generative AI model. The generated learning content is then sent back to the device and displayed to the user. The input data is the updated generative AI model and a request for new learning content, and the output data is the latest generated learning content. Specifically, the new AI model is applied, and optimal content for the user is regenerated and displayed.

[0216] 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.

[0217] The present invention is a system designed to provide the poorest people with a basic education and break the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it. The system also includes a means for collecting progress information about the learner and transmitting the progress information to the server, and a means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content. The system also includes a means for storing the learner's learning data on the server, training the generation AI based on the stored data, and updating the AI ​​model.

[0218] In addition, the present invention includes an emotion engine that recognizes the learner's emotions, and the emotion engine has a means for analyzing the learner's emotions and transmitting the information to the server. Based on the emotion information, the server also has a means for adjusting the difficulty and type of learning content and generating appropriate encouraging and advice messages.

[0219] Explanation of program processing

[0220] 1. Enter and submit basic student information

[0221] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[0222] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[0223] 2. Creation and provision of learning content

[0224] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[0225] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[0226] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[0227] 3. Feedback on learning status and generation of next content

[0228] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[0229] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[0230] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[0231] The server transmits the tailored learning content to the terminal, which displays it.

[0232] 4. Implementing the Emotion Engine

[0233] The emotion engine evaluates the user's emotions from their facial expressions and voice and sends the data to the server. For example, it detects the user's emotional state, such as whether they are easily tired or excited while studying.

[0234] The server receives emotional information and adjusts the difficulty and type of learning content based on that information. For example, if the user is tired, the questions are switched to easier questions.

[0235] The server generates encouraging and advice messages based on the emotional information and sends them to the device. For example, when the user is about to give up, it displays a message such as "You're almost there, keep trying!"

[0236] 5. Data accumulation and generation AI training

[0237] The server accumulates learning data and emotion data collected from users and stores the learning history in a database. The accumulated data is used to train the AI ​​model.

[0238] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[0239] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[0240] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress and emotional information is accumulated, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[0241] The processing flow will be explained below.

[0242] Step 1:

[0243] A user accesses a terminal and enters basic information (age, education level, area of ​​residence, etc.). For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[0244] Step 2:

[0245] The device sends the basic information entered to the server, and the device sends the input data to the server via the API.

[0246] Step 3:

[0247] The server receives the user's basic information and generates optimal learning content using a generation AI. The server accesses a database, customizes the learning content based on the specified parameters, and passes it to the generation AI to generate the learning content.

[0248] Step 4:

[0249] The server sends the generated learning content to the device. The server sends data via API to return the generated results to the device.

[0250] Step 5:

[0251] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[0252] Step 6:

[0253] The emotion engine analyzes the user's facial expressions and voice to collect emotion data. For example, it uses the device's camera and microphone to analyze facial expressions and tone of voice to collect emotion data.

[0254] Step 7:

[0255] The device sends emotional data to the server. The collected emotional data is sent to the server in real time.

[0256] Step 8:

[0257] Users use learning content to solve problems and advance their studies. Every time a problem is solved, progress information (correct answer rate, answer time, etc.) is recorded on the device in real time.

[0258] Step 9:

[0259] The device sends the collected learning progress information to the server. The progress data is sent to the server every time learning is completed or at a specific timing.

[0260] Step 10:

[0261] The server analyzes the progress information and emotion data to evaluate the user's understanding and emotion state. The server uses a data analysis module to analyze the received progress information and emotion data to measure the user's state.

[0262] Step 11:

[0263] The server adjusts the next learning content based on the user's level of understanding and emotional data. For example, if the user is tired, it switches to questions that are easier to answer, and if the user is excited, it increases the difficulty level.

[0264] Step 12:

[0265] The server generates tailored learning content using a generative AI and sends the generated content to the device.

[0266] Step 13:

[0267] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[0268] Step 14:

[0269] The server generates messages of encouragement and advice and sends them to the device. Based on the emotion data, it generates messages such as "You're doing well, try a little harder!" and sends them to the device.

[0270] Step 15:

[0271] The device displays encouraging and advice messages to the user. The device displays messages on the user interface to improve the user's motivation.

[0272] Step 16:

[0273] The server accumulates learning data and emotion data collected from users and stores the learning history in a database, which is used to train the AI ​​model.

[0274] Step 17:

[0275] The server trains the generation AI based on the accumulated data and updates the AI ​​model. The AI ​​model trained based on new data is used to improve the accuracy of the algorithm.

[0276] Step 18:

[0277] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[0278] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[0279] Example 2

[0280] 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."

[0281] The problem that this invention aims to solve is to provide effective and efficient education to the poorest learners and break the cycle of poverty. Specifically, the objective is to generate optimal learning content and maximize learners' understanding by taking into account each learner's individual progress and emotional state.

[0282] 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.

[0283] In this invention, the server includes means for inputting basic information about the learner and transmitting the basic information to the server, means for generating optimal learning content for the learner using a generation AI, means for transmitting the generated learning content to the learner's device and displaying it, means for the server to analyze the learner's emotional information, adjust the difficulty of the learning content based on the emotional information, and generate appropriate encouragement and advice, and means for transmitting and displaying messages of encouragement and advice based on the emotional information to the learner's device. This enables effective education tailored to each individual learner, maintains their motivation to learn, and helps them develop the ability to escape poverty.

[0284] "Basic information" refers to information needed to understand the learner's background and situation, such as the learner's age, prerequisite educational level, and area of ​​residence.

[0285] "Learning content" refers to teaching materials and questions that are generated by generative AI based on the learner's basic information and progress information, in order to provide specific educational goals and challenges.

[0286] "Generative AI" is a type of artificial intelligence that uses natural language processing technology to automatically generate educational content that is optimal for learners.

[0287] "Progress information" refers to data such as correct answer rate and answer time obtained as learners progress through their studies using educational content.

[0288] "Emotional information" refers to information about the learner's emotional state during learning, obtained by analyzing the learner's facial expressions and voice.

[0289] "Encouraging and advice messages" are messages that are generated based on the learner's emotional information and contain motivation and guidance to continue learning.

[0290] An "AI model" is a collection of algorithms and structured datasets that a generative AI uses to train it to generate new educational content.

[0291] "Device" refers to an electronic device (e.g., a smartphone or tablet) on which a learner displays learning content and performs learning activities.

[0292] The "server" is a central processing unit that receives and analyzes basic information and progress information sent by learners, and generates and transmits learning content using generation AI.

[0293] The present invention is a system that aims to provide appropriate education to learners from the poorest backgrounds and break the cycle of poverty. This system inputs basic information about learners, generates learning content, collects learning progress information, analyzes emotional information, and regenerates learning content based on this information. Specific embodiments of the present invention are described below.

[0294] First, the device used by the learner is an electronic device such as a smartphone or tablet. The user accesses this device and enters basic information such as age, educational level, and area of ​​residence. For example, the user launches an application and enters information such as "10 years old," "can read and write basic language," and "lives in a rural area." The device then sends this basic information to the server.

[0295] Based on the received basic information, the server uses a generative AI model (e.g., a model using natural language processing technology) to generate learning content that is optimal for the learner. For example, a 10-year-old learner is provided with basic arithmetic problems on addition and subtraction. The generated learning content is sent from the server to the device and displayed on the device.

[0296] As a user studies using learning content, the device records learning progress information (e.g., percentage of correct answers and answer time) in real time. This progress information is sent to a server, which analyzes it to evaluate the learner's level of understanding. For example, if a learner is weak in a particular area, new learning content that focuses on that area can be generated.

[0297] Furthermore, the device is equipped with an emotion engine that evaluates the user's emotional information by analyzing their facial expressions and voice. This emotional information is also sent to the server, which then uses this information to adjust the difficulty and type of learning content. Messages of encouragement and advice based on the user's emotions are also generated and sent to the device. For example, an encouraging message such as "You're almost there, keep going!" may be displayed.

[0298] The server stores the collected learning data and emotion data and uses them to train the generative AI model. The AI ​​model is updated through training, and new data sets are used to improve the accuracy of the generative AI model. The updated AI model generates newly optimized learning content and sends it to the device, allowing learners to study more effectively.

[0299] As a concrete example, when a user uses the system for the first time, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As learning progress and emotional information are accumulated, the server uses the generative AI model to adjust the next learning content. For example, the generative AI model generates optimal learning content using a prompt such as, "Generate beginner-level arithmetic problems suitable for a 10-year-old learner. As prerequisite knowledge, the learner understands basic addition and subtraction. Please adjust the next learning content taking into account the accuracy rate and answer time."

[0300] This system allows learners to receive an education that is tailored to their individual needs and empowers them to break the cycle of poverty.

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

[0302] Step 1:

[0303] The user enters basic information into the device.

[0304] The user launches the application and enters basic information such as age, educational level, and area of ​​residence. For example, they might enter items such as "10 years old," "can read and write basic words," and "live in a rural area." This input information will later become the basis for the generative AI to generate learning content.

[0305] Input: User-entered age, education level, and area of ​​residence

[0306] Output: The basic information entered is saved on the device.

[0307] Specific behavior: The user enters the required information into the application's input form and clicks the submit button.

[0308] Step 2:

[0309] The device sends basic information to the server

[0310] The terminal sends the basic information entered by the user to the server. This sending process is performed using, for example, an HTTP POST request.

[0311] Input: Basic information stored on your device

[0312] Output: Basic information sent to the server

[0313] Specific operation: The device sends the user's basic information to the server using an HTTP POST request.

[0314] Step 3:

[0315] The server generates learning content using AI based on basic information

[0316] The server analyzes the received basic information and uses a generative AI model (e.g., a model using natural language processing technology) to generate appropriate learning content. For example, basic arithmetic addition and subtraction problems are generated for a 10-year-old learner.

[0317] Input: Basic information sent to the server

[0318] Output: Generated learning content

[0319] Specific operation: The server uses the generative AI model to input basic information as prompts and generate specific learning content (e.g., math problems). The generated learning content is temporarily stored on the server.

[0320] Step 4:

[0321] The server sends the generated learning content to the device.

[0322] The server sends the generated learning content to the terminal, for example, by returning the content as an HTTP response.

[0323] Input: Generated learning content

[0324] Output: Learning content sent to the device

[0325] Specific operation: The server sends the generated learning content to the device as an HTTP response.

[0326] Step 5:

[0327] The device displays the learning content to the user.

[0328] The device displays the received learning content to the user, who then begins learning using the content.

[0329] Input: Learning content sent to your device

[0330] Output: Learning content displayed on the device display

[0331] Specific operation: The device displays the learning content on the user interface, and the user begins solving the problems.

[0332] Step 6:

[0333] The device collects the user's learning progress information

[0334] The device records the user's learning progress, such as the percentage of correct answers and the time it takes to answer, in real time, allowing the user to understand their learning situation.

[0335] Input: User's answer data (answer time, correct answer rate, etc.)

[0336] Output: Collected learning progress information

[0337] Specific operation: The device collects and stores the user's answer data using sensors and recording functions.

[0338] Step 7:

[0339] The device sends progress data to the server

[0340] The device sends the collected progress data to the server, again using, for example, an HTTP POST request.

[0341] Input: Collected learning progress information

[0342] Output: Progress data sent to the server

[0343] What happens: The device sends the collected progress data to the server using an HTTP POST request.

[0344] Step 8:

[0345] The server analyzes the progress data and generates the next learning content.

[0346] The server uses a generative AI model based on the progress data to generate the next appropriate learning content. For example, if a learner is weak in a particular area, new questions focused on that area will be generated.

[0347] Input: Progress data sent to the server

[0348] Output: Next learning content

[0349] Specific operation: The server analyzes the progress data and uses the generative AI model to generate the next learning content (e.g., subject-specific questions).

[0350] Step 9:

[0351] The server sends the next learning content to the device.

[0352] The server sends the newly generated learning content to the terminal.

[0353] Input: Newly generated learning content

[0354] Output: The next learning content sent to the device

[0355] Specific operation: The server uses the HTTP response to send the newly generated learning content to the device.

[0356] Step 10:

[0357] The device displays the next learning content to the user.

[0358] The terminal displays the newly sent learning content to the user, allowing the user to proceed to the next learning step.

[0359] Input: Next learning content sent to your device

[0360] Output: The next learning content displayed on the device display

[0361] Specific behavior: The device displays the next learning content on the user interface, and the user continues learning.

[0362] Step 11:

[0363] Emotion engine evaluates user emotions

[0364] The emotion engine analyzes the user's facial expressions and voice to assess their emotional state. For example, it uses a camera and microphone to analyze the user's face and voice.

[0365] Input: User's facial expression and voice data

[0366] Output: Evaluated emotion information

[0367] Specific operation: The emotion engine analyzes data obtained from the camera and microphone and generates emotion information.

[0368] Step 12:

[0369] The emotion engine sends the user's emotion information to the server.

[0370] The emotion engine sends the evaluated emotion information to the server, for example, using an HTTP POST request.

[0371] Input: Evaluated emotion information

[0372] Output: Emotion information sent to the server

[0373] Specific operation: The emotion engine sends emotion information to the server using an HTTP POST request.

[0374] Step 13:

[0375] The server adjusts the difficulty and type of learning content based on emotional information.

[0376] The server analyzes the received emotional information and adjusts the difficulty and type of learning content accordingly. For example, if the user is tired, the questions will be switched to easier questions.

[0377] Input: Emotion information sent to the server

[0378] Output: Tailored learning content

[0379] How it works: The server analyzes the emotional information and uses a generative AI model to adjust the content of the learning content.

[0380] Step 14:

[0381] The server generates encouraging and advice messages based on the emotional information.

[0382] The server generates appropriate encouraging and advice messages to motivate students to learn based on the emotional information.

[0383] Input: Emotion information sent to the server

[0384] Output: A message of encouragement or advice

[0385] Specific operation: The server uses a generative AI model to generate encouraging or advice messages from emotional information.

[0386] Step 15:

[0387] The server sends encouraging and advice messages to the device.

[0388] The server generates encouraging and / or helpful messages and sends them to the device.

[0389] Input: A message of encouragement or advice

[0390] Output: Messages of encouragement or advice sent to the terminal.

[0391] Specific operation: The server sends a message of encouragement or advice to the device as an HTTP response.

[0392] Step 16:

[0393] The device displays encouraging or helpful messages to the user.

[0394] The device displays encouraging and helpful messages in the user interface, helping users stay motivated.

[0395] Input: A message of encouragement or advice sent to the device

[0396] Output: Encouraging and helpful messages displayed on the screen

[0397] What it does: Your device will display encouraging or helpful messages as pop-ups or notifications.

[0398] Step 17:

[0399] The server accumulates learning data and trains the generative AI.

[0400] The server accumulates learning data and emotion data collected from users and uses this data to train the generative AI model. Through training, the accuracy and performance of the AI ​​model improves.

[0401] Input: Learning data and emotion data stored on the server

[0402] Output: Updated AI model

[0403] What it does: The server uses the accumulated data to retrain and update the generative AI model.

[0404] Step 18:

[0405] The server uses the updated AI model to generate new learning content.

[0406] The server generates new learning content using the updated AI model, ensuring that the most up-to-date and optimal learning content is always provided.

[0407] Input: Updated AI model

[0408] Output: Newly generated learning content

[0409] Specific operation: The server uses the updated AI model to execute the process of generating new learning content.

[0410] Step 19:

[0411] The server generates new learning content and sends it to the device.

[0412] The server transmits the newly generated learning content to the terminal.

[0413] Input: Newly generated learning content

[0414] Output: Learning content sent to the device

[0415] Specific operation: The server sends new learning content to the device as an HTTP response.

[0416] Step 20:

[0417] The device displays new learning content to the user.

[0418] The terminal displays the newly transmitted learning content to the user.

[0419] Input: Learning content sent to your device

[0420] Output: Learning content displayed on the device display

[0421] Specific behavior: The device displays new learning content in the user interface, and the user continues learning.

[0422] (Application example 2)

[0423] 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."

[0424] Conventional food delivery services have difficulty in proposing meals that take into account the user's food preferences and allergy information, and do not provide personalized services that respond to the user's emotions and physical condition. This has led to the problem that they are not adequately proposing meals that satisfy the user or that are suitable for health management. Furthermore, they do not continuously improve their services based on user emotions and feedback, which makes it difficult to encourage repeat use.

[0425] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting basic information about the learner and transmitting the basic information to the server, means for the server to generate optimal learning content for the learner using a generation AI, means for transmitting the generated learning content to the learner's device and displaying it, means for inputting the user's food preferences and health-related information and transmitting the information to the server, means for the server to generate optimal meal options for the user using a generation AI, means for transmitting the generated meal options to the user's device and displaying them, means for collecting progress information about the learner and transmitting the progress information to the server, means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content, means for transmitting the adjusted learning content to the learner's device and displaying it, means for collecting the user's food order history and emotional state and transmitting them to the server, means for the server to adjust the next meal option based on the emotional information, and means for transmitting the adjusted meal options to the user's device and displaying them. This enables optimal meal suggestions based on the user's emotional state, taking into account the user's food preferences and allergy information.

[0426] "Basic information about the learner" refers to basic information about the learner, such as their age, educational background, and place of residence.

[0427] "Server" refers to the central computer system that processes the received information and uses generative AI to generate and manage learning content and dining options.

[0428] "Generative AI" is a type of artificial intelligence, an algorithm that automatically generates optimal learning content and meal options based on input information.

[0429] "Learning content" refers to learning-related information such as educational materials and workbooks created for learners to use.

[0430] "Food preferences and health-related information" refers to health-related information such as the ingredients and types of food that the user prefers when eating, allergy information, and dietary restrictions.

[0431] "Meal options" are specific food or menu choices suggested based on the user's information.

[0432] "Meal order history" refers to the user's past meal order history and detailed information about those orders.

[0433] "Emotional state" refers to the emotions and psychological state that the user is currently experiencing, and is information detected from facial expressions, voice, and the like.

[0434] A "user's device" refers to a mobile information terminal device such as a smartphone or tablet used by a learner or user.

[0435] "Progress information" is information that indicates how far a learner has progressed in their studies, and includes the percentage of correct answers and the time it took to answer.

[0436] An "AI model" is a model that is learned by artificial intelligence and generates appropriate output based on input data.

[0437] This invention is a system that generates optimal meal options based on a user's food preferences and health-related information and provides them to the user. The system includes means for inputting basic information about a learner and transmitting the basic information to a server, means for the server to generate optimal learning content for the learner using a generation AI, and means for transmitting the generated learning content to the learner's device and displaying it. The system also includes means for inputting a user's food preferences and health-related information and transmitting the information to the server, means for the server to generate optimal meal options for the user using a generation AI, and means for transmitting the generated meal options to the user's device and displaying them.

[0438] The system program performs the following processing.

[0439] First, the user uses a device such as a smartphone or tablet to input their food preferences, allergy information, and health-related information. For example, they can input information such as "I like spicy food," "I'm vegan," "I'm gluten-free," and "I prefer low-calorie foods." The input information is then sent to the server by the device.

[0440] This server uses Amazon Web Services (AWS) and, after receiving the data, uses a generative AI model to generate optimal meal options based on the user's information. TensorFlow or Pytorch is used as the generative AI model, for example. The generated meal options are then sent back to the user's device, where they can be viewed.

[0441] Once the user selects a meal option and places an order, the order history and user feedback (satisfaction level and comments) are sent back to the server. This information is stored in a cloud database (e.g., Amazon RDS). In addition, the device is equipped with a module that evaluates the user's emotional state from their facial expressions and voice, and this data is also sent to the server.

[0442] Based on the accumulated data, the server retrains and updates the generative AI model, allowing it to provide even more personalized meal options the next time you order.

[0443] For example, if a user inputs information such as "I like spicy food" and "I prefer low-calorie food," the server will recommend "spicy low-calorie dishes." Furthermore, if the user orders the dish and provides feedback that they are satisfied, that data will be saved on the server and reflected in the next recommendation. Also, if the user is feeling down, the server can suggest "mood-boosting meals."

[0444] An example of a prompt is shown below.

[0445] User information: Female in her 20s, vegetarian, low-calorie diet, currently feeling stressed.

[0446] Suggestion: Choose vegetarian, low-calorie options that are effective in relieving stress.

[0447] As a result, it becomes possible to suggest appropriate meals according to the user's health condition and emotional state, thereby improving the quality of service.

[0448] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0449] Step 1:

[0450] The user uses the terminal to input food preferences and health-related information and presses the send button.

[0451] Input: The user enters food preferences (e.g., "I like spicy food") and health-related information (e.g., "vegan" or "low-calorie conscious").

[0452] Data processing: Converting user input information into a data format within the terminal.

[0453] Output: Sends formatted data to the server.

[0454] Step 2:

[0455] The server receives and analyzes the transmitted information.

[0456] Input: User's food preferences and health-related information sent from the device.

[0457] Data processing: Store the data in a database (e.g., Amazon RDS) and prepare it as input for the generative AI.

[0458] Output: The input dataset for the generative AI model.

[0459] Step 3:

[0460] The server uses a generative AI model to generate optimal meal options based on the user's information.

[0461] Input: User's food preferences and health-related information.

[0462] Data Computing: Leverage generative AI models (e.g., TensorFlow or Pytorch) to generate personalized meal options for users.

[0463] Output: The generated meal option data.

[0464] Step 4:

[0465] The server transmits the generated meal options to the terminal.

[0466] Input: Generated meal option data.

[0467] Data processing: Converting data into a format that can be received by the user terminal.

[0468] Output: Sends the formatted meal option data to the user's device.

[0469] Step 5:

[0470] The user's device displays meal options.

[0471] Input: Meal option data sent from the server.

[0472] Data processing: Rendering the data to display meal options on the device screen.

[0473] Output: A visual representation of the meal options.

[0474] Step 6:

[0475] The user selects a meal option and places an order.

[0476] Input: Information about the meal option selected by the user.

[0477] Data processing: Prepare the selected option data as order data.

[0478] Output: Sends the order information to the server.

[0479] Step 7:

[0480] The server receives and processes the order information.

[0481] Input: Order information submitted by the user.

[0482] Data Processing: Order information is entered into the order management system and stored in a historical database.

[0483] Output: Order confirmation information.

[0484] Step 8:

[0485] The server stores order history and emotion information.

[0486] Input: Order history and emotional information from users (e.g., facial expression analysis data).

[0487] Data calculation: Analyze the accumulated data and use it as retraining data for the generative AI model.

[0488] Output: An updated generative AI model.

[0489] Step 9:

[0490] The user's device sends emotional information to the server and displays the analysis results in a timely manner.

[0491] Input: Emotional information collected by the device from the user's facial expressions and voice.

[0492] Data processing: Emotional information is analyzed, converted into a data format, and sent to the server.

[0493] Output: Data for the next proposal based on the analysis results.

[0494] In this way, a system can be realized that provides optimal meal options based on a user's food preferences, health information, and emotional state.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] [Second embodiment]

[0499] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0500] 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.

[0501] 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).

[0502] 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.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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.

[0508] 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.

[0509] 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.

[0510] 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."

[0511] The present invention is a system that aims to provide the poorest people with a minimum level of education and break the cycle of poverty. This system includes a means for inputting basic information about a learner and sending the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it.

[0512] Explanation of program processing

[0513] 1. Enter and submit basic student information

[0514] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[0515] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[0516] 2. Creation and provision of learning content

[0517] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[0518] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[0519] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[0520] 3. Feedback on learning status and generation of next content

[0521] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[0522] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[0523] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[0524] The server transmits the tailored learning content to the terminal, which displays it.

[0525] 4. Data accumulation and generation AI training

[0526] The server accumulates the learning data sent by users and manages the learning history. The accumulated data is used to train the AI ​​model.

[0527] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[0528] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[0529] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress information accumulates, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[0530] The processing flow will be explained below.

[0531] Step 1:

[0532] The user accesses the terminal and enters basic information (age, education level, area of ​​residence, etc.). The user then launches the application and records the necessary information in the input form.

[0533] Step 2:

[0534] The device sends the basic information entered to the server. The device app then sends the input data to the server via the API.

[0535] Step 3:

[0536] The server receives the user's basic information and uses a generation AI to generate optimal learning content. The server accesses the database, customizes the content based on the received basic information, and passes it on to the generation AI to generate the learning content.

[0537] Step 4:

[0538] The server sends the generated learning content to the device. The server sends data through the API to return the generated content to the device.

[0539] Step 5:

[0540] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[0541] Step 6:

[0542] Users use learning content to solve problems and advance their learning. Progress information (correct answer rate, answer time, etc.) is collected in real time each time a problem is solved.

[0543] Step 7:

[0544] The device sends the collected learning progress information to the server. The progress data is sent to the server each time learning is completed or at a specific timing.

[0545] Step 8:

[0546] The server analyzes the progress information and evaluates the user's level of understanding. The server uses a data analysis module to analyze the received progress information and measure the user's level of understanding.

[0547] Step 9:

[0548] The server uses AI to generate the next learning content, tailored based on the level of comprehension. Based on the results of the comprehension assessment, the next learning content is customized and new content is generated by AI.

[0549] Step 10:

[0550] The server sends the tailored learning content to the device, and sends data through the API to send the generated content back to the device.

[0551] Step 11:

[0552] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[0553] Step 12:

[0554] The server accumulates learning data collected from users and stores their learning history in a database. The server uses the accumulated data to train the generative AI and update the AI ​​model.

[0555] Step 13:

[0556] The server generates new learning content using the updated AI model, and retrains the AI ​​model based on new data to generate the latest content.

[0557] Step 14:

[0558] The server sends the latest learning content to the device and displays it. Generated content is sent back to the device, allowing the user's learning to be continuously improved.

[0559] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[0560] Example 1

[0561] 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."

[0562] Providing appropriate and effective education to the poorest people is a challenge. Providing individually optimized learning content based on each learner's progress requires a great deal of effort and cost. Furthermore, there is a need for efficient management of learning data and continuous improvement of AI models.

[0563] 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.

[0564] In this invention, the server includes a means for inputting the learner's personal information and transmitting the personal information to the server, a means for the server to generate learning content optimized for the learner using a generative AI, a means for transmitting the generated learning content to the learner's terminal device and displaying it, a means for the server to analyze the learner's personal information received and format it as input data suitable for the generative AI model, a means for inputting the information as prompts to the generative AI model, a means for using the generative AI model to generate learning content based on the input requirements, and a means for converting the generated content into an appropriate format and transmitting it to the terminal device. This makes it possible to provide learning content individually optimized according to the learner's progress, thereby providing effective education. Furthermore, the accumulation of learning data and the training of the generative AI can be efficiently managed, allowing for continuous improvement in the accuracy of the AI ​​model.

[0565] "Personal information of learners" refers to information necessary to understand the learner's background and situation, such as age, educational level, and area of ​​residence.

[0566] An "information processing device" is a device used to perform various data processing operations, such as receiving, analyzing, and storing data, and training generative AI models.

[0567] "Generative AI" is an AI system that has the ability to generate new content or information based on given data or prompts.

[0568] "Learning content" refers to educational content such as teaching materials, questions, and exercises that learners should study.

[0569] A "terminal device" is a device that a user can directly access to view, operate, and respond to learning content.

[0570] A "prompt" refers to an instruction or question entered into a generative AI model to elicit an appropriate response.

[0571] "Learning data" refers to all information generated by a learner, including, for example, progress, answer history, and comprehension assessment.

[0572] "Format" refers to the state in which data or content is arranged in a specific form or structure.

[0573] "Training" refers to the learning process that uses new data to improve the accuracy of a generative AI model.

[0574] The present invention is a system aimed at providing the poorest people with a minimum level of education and breaking the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to an information processing device, a means for the information processing device to generate optimal learning content for the learner using generative AI, and a means for transmitting the generated learning content to the learner's terminal device and displaying it. The system also includes a means for collecting learner progress information and adjusting the learning content based on the progress information, and a means for accumulating learning data to train an AI model and improve the accuracy of the generative AI model.

[0575] 1. Enter and submit basic information

[0576] The first thing a user does is input basic information such as age, educational level, and area of ​​residence. This information is entered into a terminal device and transmitted to an information processing device. During this transmission process, security protocols (e.g., HTTPS) are used to ensure data security.

[0577] 2. Creation and provision of learning content

[0578] The information processing device uses generative artificial intelligence (e.g., OpenAI's GPT model) based on the received basic information to generate optimal learning content for the learner. In this process, the information processing device analyzes the received personal information, formats it as input data suitable for the generative AI model, and enters it as a prompt. For example, the prompt might be "10 years old, rural area, arithmetic and reading / writing at the third grade level." The generated learning content is then converted into an appropriate format (e.g., HTML or JSON) and sent to the terminal device. The terminal device displays the received learning content on a user interface, allowing the user to begin learning.

[0579] 3. Feedback on learning status and generation of next content

[0580] The terminal device collects the user's learning progress information in real time and transmits it to the information processing device. The information processing device analyzes the received progress information, evaluates the user's level of understanding, and adjusts the next learning content. This evaluation result is provided as a prompt to the generative artificial intelligence model, which generates the next learning content. For example, if the evaluation indicates that "the user is struggling with fraction problems," problems covering everything from basic to advanced fractions are generated. The generated new learning content is transmitted to the terminal device and displayed to the user.

[0581] 4. Data accumulation and generation AI training

[0582] The information processing device accumulates all learning data sent by users and stores it in a learning history database. The accumulated data is used to train a generative AI model (generative artificial intelligence). This process improves the accuracy of the AI ​​model and generates more effective learning content. The new trained AI model is used to generate the next learning content and is continuously updated.

[0583] Examples of specific examples and prompts

[0584] As a specific example, when a user logs in for the first time and enters basic information such as "10 years old," "able to read and write basics," and "lives in a rural area," the information processing device inputs the prompt "10 years old, rural area, arithmetic and reading / writing at the third grade level" into the generative AI model. The generated simple arithmetic problems and basic reading comprehension problems are displayed on the user's terminal device. As the user works on these problems, progress data is accumulated, and new content based on the user's progress is provided the next time they log in.

[0585] Example prompt sentence:

[0586] "Generate math and literacy learning content for 10-year-olds, rural areas, and third grade levels."

[0587] "Generate new fraction math problems based on user progress data."

[0588] As described above, this system provides effective education to learners and makes it possible to provide individually optimized learning content according to their progress.

[0589] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0590] Step 1:

[0591] A user launches a learning application using a terminal device and enters basic information. This basic information includes age, educational level, and area of ​​residence. For example, the user might enter "10 years old," "can read and write basic words," and "live in a rural area." Input: User's basic information. Output: Data of the entered basic information.

[0592] Step 2:

[0593] The terminal device sends the input basic information to the information processing device (server). At this time, a security protocol (e.g., HTTPS) is used to ensure the safety of the data. Input: User's basic information. Output: Data of the basic information sent to the information processing device.

[0594] Step 3:

[0595] The server analyzes the basic information it receives and formats it as input data suitable for the generative AI model. Specifically, it summarizes information such as age and education level and converts it into a format that can be passed to the generative AI model. Input: The basic information sent. Output: Data formatted for the generative AI model.

[0596] Step 4:

[0597] The server inputs the formatted data to the generative AI model as a prompt. This prompt includes the learner's characteristics and learning requirements. For example, the requirement "10 years old, rural area, arithmetic and reading / writing at the third grade level" is used as the prompt. Input: Prompt for the generative AI model. Output: Prompt input to the generative AI model.

[0598] Step 5:

[0599] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate learning content based on the input prompt. Specifically, it generates simple math problems or basic reading comprehension questions. Input: The prompt input to the generative AI model. Output: The generated learning content.

[0600] Step 6:

[0601] The server converts the generated learning content into an appropriate format (e.g., HTML, JSON) and sends it to the terminal device. Input: Generated learning content. Output: Content converted into an appropriate format and its transmission.

[0602] Step 7:

[0603] The terminal device displays the received learning content on the user interface. The user browses this content and begins learning. Input: Received learning content. Output: Learning content displayed to the user.

[0604] Step 8:

[0605] The user engages with the learning content and answers or performs operations. Specifically, they solve displayed math problems or enter answers to reading comprehension questions. Input: User operations and answers. Output: Progress data of learning activities.

[0606] Step 9:

[0607] The terminal device collects the user's learning progress information in real time. The collected data includes the percentage of correct answers to questions and the time it took to answer them. Input: User's learning activity. Output: Collected progress data.

[0608] Step 10:

[0609] The terminal device sends the collected progress data to the server. Input: Collected progress data. Output: Progress data sent to the server.

[0610] Step 11:

[0611] The server analyzes the received progress information and evaluates the user's level of understanding. It identifies areas of strength and weakness. Input: Submitted progress data. Output: Analyzed level of understanding information.

[0612] Step 12:

[0613] The server provides the generative AI model with a prompt to generate the next learning content based on the progress data. For example, the next prompt is generated based on the evaluation that "the user is struggling with fraction problems." Input: Analyzed comprehension information. Output: Prompt to input to the generative AI model.

[0614] Step 13:

[0615] The server uses the generative AI model to generate new learning content. For example, new problems covering everything from the basics to advanced fractions are generated. Input: The prompt entered into the generative AI model. Output: New learning content.

[0616] Step 14:

[0617] The server sends the generated new learning content to the terminal device, which displays it. Input: The generated new learning content. Output: The new content displayed on the terminal device.

[0618] Step 15:

[0619] The user starts learning again with new learning content. Progress data is collected, sent, and analyzed in the same way. Input: Learning content to be re-engaged. Output: New progress data.

[0620] Step 16:

[0621] The server accumulates all the learning data sent by users and stores it in the learning history database. Input: Sent learning data. Output: Accumulated data.

[0622] Step 17:

[0623] The server trains the generative AI based on the accumulated data and updates the generative AI model, improving the accuracy of the AI ​​model. Input: Accumulated data. Output: New trained AI model.

[0624] Step 18:

[0625] The server generates new learning content using the updated generative AI model and sends it to the terminal device. Input: The trained new AI model. Output: The generated new learning content.

[0626] Step 19:

[0627] The terminal device displays the latest learning content on the user interface, allowing the user to continue learning. Input: Generated new learning content. Output: The latest learning content displayed to the user.

[0628] In this way, this system provides learning content that is individually optimized according to the learner's progress, supporting effective education. It efficiently manages the accumulation of learning data and the training of the generated AI, enabling continuous improvement of the accuracy of the AI ​​model.

[0629] (Application example 1)

[0630] 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."

[0631] For the poorest people, breaking the cycle of poverty through education is important, but the educational resources and opportunities they can access are extremely limited. Furthermore, there are no effective ways to link education with support activities such as food delivery. Furthermore, there is a need for the automatic generation and provision of educational content based on progress. There is a need to solve these problems and provide an effective educational support system for the poorest people.

[0632] 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.

[0633] In this invention, the server includes: means for inputting basic information about the learner and transmitting the basic information to the server; means for the server to generate optimal learning content for the learner using a generation AI; means for transmitting the generated learning content to the learner's device and displaying it; means for collecting progress information about the learner and transmitting the progress information to the server; means for the server to evaluate the learner's level of understanding based on the progress information and generate subsequent learning content; means for storing the learner's learning data in the server; means for training the generation AI based on the stored data and updating the AI ​​model; and means for transmitting the learning content generated using the updated AI model to the learner's device and displaying it. This makes it possible to provide optimal educational content tailored to the progress of learners from the poorest backgrounds, thereby effectively supporting efforts to break the cycle of poverty through education.

[0634] "Basic information about the learner" refers to personal information such as the learner's age, education level, and area of ​​residence.

[0635] The "server" is a system that receives basic information and progress information about learners, processes and analyzes it, and generates learning content using generation AI.

[0636] "Generative AI" is artificial intelligence that automatically generates optimal learning content based on a learner's basic information and progress information.

[0637] "Learning content" refers to educational materials such as teaching materials and problem sets that are used by learners to receive education.

[0638] "Device" means a device such as a smartphone, smart glasses, or head-mounted display that a learner uses to receive and view learning content.

[0639] "Progress information" is data that indicates the learner's learning progress and level of understanding.

[0640] "Level of understanding" is an indicator that shows how well a learner has understood the learning content provided.

[0641] "Learning data" refers to a series of data related to learning, such as basic information about the learner, progress information, and learning history.

[0642] An "updated AI model" is a generative AI model that has been retrained based on the learning data stored on the server.

[0643] The "poorest" are the most economically disadvantaged social groups, those who lack access to basic needs and education.

[0644] "Food assistance" refers to support services such as food and meals provided to the poorest people.

[0645] A "smart device" is an electronic device that allows learners to receive learning content and learn interactively.

[0646] The present invention is a system that aims to provide the poorest people with the minimum education necessary to break the cycle of poverty. This system consists of the following steps:

[0647] Hardware and software configuration

[0648] This system includes a terminal for inputting learner information, a server for utilizing the generative AI, and a smart device for displaying learning content. Specifically, the following hardware and software are used:

[0649] Devices: Smartphones, smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest)

[0650] Server: Cloud server (e.g. AWS)

[0651] Software: Custom applications (for Android / iOS), AI models (e.g., GPT-4)

[0652] Program processing explanation

[0653] 1. Enter and submit basic student information

[0654] The user accesses the terminal and enters basic information such as the learner's name, age, education level, and area of ​​residence, which is then sent to the server.

[0655] Example: A user launches an application and enters information such as "10 years old," "can read and write basic words," and "lives in a rural area."

[0656] 2. Creation and provision of learning content

[0657] The server uses the generative AI model based on the received basic information to generate optimal learning content for the learner, which is then sent to the device and displayed to the user.

[0658] Example: For a 10-year-old learner, basic math problems and reading and writing exercises are generated.

[0659] Example prompt: Generate educational content on nutrition and basic math for a 10-year-old user living in a rural area who can read and write at a basic level.

[0660] 3. Feedback on learning status and generation of next content

[0661] The device collects the user's learning progress information and sends it to the server, which analyzes the progress data and adjusts and generates the next learning content.

[0662] Example: Identify areas where the user is weak, assess their level of understanding, and automatically generate the most appropriate next learning content.

[0663] 4. Data accumulation and generation AI training

[0664] The server stores all the learning data sent by users and uses it to train the AI ​​model, which is periodically updated and retrained on new datasets.

[0665] Example: Updating AI models with newly collected data improves the accuracy of learning content.

[0666] Overall flow

[0667] By repeating this process, it is possible to continue providing effective education to the poorest learners. Furthermore, by integrating food assistance and education, this system will realize more practical and effective support. For example, it is possible to design a system that links with food delivery services so that educational content is provided at the same time as food is delivered.

[0668] In this way, the present invention can provide a practical and sustainable educational support system to break the cycle of poverty.

[0669] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0670] Step 1:

[0671] Users access their devices and enter basic information such as their name, age, education level, and area of ​​residence. This basic information is sent as input data to the server, which analyzes the received data and generates a basic profile of the learner. Specific operations involve the user answering a series of questions using an app on their smartphone or smart device.

[0672] Step 2:

[0673] The server uses a generative AI model based on the received basic information to generate optimal learning content for the learner. Here, the input data is the learner's basic information, and the output data is the generated learning content. The generative AI model uses a prompt sentence based on the input data to launch a text generation algorithm (e.g., GPT-4) to generate appropriate learning content. Specifically, the AI ​​engine in the server operates and generates learning materials based on the specified prompt sentence.

[0674] Step 3:

[0675] The generated learning content is sent from the server to the terminal. The terminal receives this learning content and displays it to the user. The input data here is the generated learning content, and the output data is the learning content reflected on the user's display screen. Specifically, the new educational content is displayed to the user through the notification function.

[0676] Step 4:

[0677] The user studies the displayed learning content. During the learning process, the user's answers and activity log are automatically recorded. The input data is the user's learning behavior, and the output data is learning progress information. Specific operations include answer input and progress recording via a touch screen or input interface.

[0678] Step 5:

[0679] The device collects the user's learning progress information and sends this data to the server. The input data is the user's learning progress information, and the output data is the progress log sent to the server. Specifically, the progress data is automatically uploaded at specified intervals or for each event.

[0680] Step 6:

[0681] Based on the received learning progress information, the server uses a generative AI model to adjust and generate the next learning content. Here, the input data is the received learning progress information, and the output data is the newly generated learning content. Specifically, an analytical algorithm runs within the server, automatically generating learning materials appropriate for the next step based on the progress data.

[0682] Step 7:

[0683] All of a learner's learning data is stored on the server. The input data is past and current learning progress data, and the output data is the accumulated learning history. Specifically, data is continuously added to the server's database, and backups and database compression are performed as necessary.

[0684] Step 8:

[0685] The server trains and updates the generative AI model based on the accumulated data. The input data is the accumulated training data, and the output data is the updated generative AI model. Specifically, the machine learning algorithm runs using the new data set, and re-training is performed to improve the accuracy of the model.

[0686] Step 9:

[0687] New learning content is generated using the updated generative AI model. The generated learning content is then sent back to the device and displayed to the user. The input data is the updated generative AI model and a request for new learning content, and the output data is the latest generated learning content. Specifically, the new AI model is applied, and optimal content for the user is regenerated and displayed.

[0688] 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.

[0689] The present invention is a system designed to provide the poorest people with a basic education and break the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it. The system also includes a means for collecting progress information about the learner and transmitting the progress information to the server, and a means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content. The system also includes a means for storing the learner's learning data on the server, training the generation AI based on the stored data, and updating the AI ​​model.

[0690] In addition, the present invention includes an emotion engine that recognizes the learner's emotions, and the emotion engine has a means for analyzing the learner's emotions and transmitting the information to the server. Based on the emotion information, the server also has a means for adjusting the difficulty and type of learning content and generating appropriate encouraging and advice messages.

[0691] Explanation of program processing

[0692] 1. Enter and submit basic student information

[0693] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[0694] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[0695] 2. Creation and provision of learning content

[0696] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[0697] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[0698] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[0699] 3. Feedback on learning status and generation of next content

[0700] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[0701] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[0702] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[0703] The server transmits the tailored learning content to the terminal, which displays it.

[0704] 4. Implementing the Emotion Engine

[0705] The emotion engine evaluates the user's emotions from their facial expressions and voice and sends the data to the server. For example, it detects the user's emotional state, such as whether they are easily tired or excited while studying.

[0706] The server receives emotional information and adjusts the difficulty and type of learning content based on that information. For example, if the user is tired, the questions are switched to easier questions.

[0707] The server generates encouraging and advice messages based on the emotional information and sends them to the device. For example, when the user is about to give up, it displays a message such as "You're almost there, keep trying!"

[0708] 5. Data accumulation and generation AI training

[0709] The server accumulates learning data and emotion data collected from users and stores the learning history in a database. The accumulated data is used to train the AI ​​model.

[0710] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[0711] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[0712] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress and emotional information is accumulated, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[0713] The processing flow will be explained below.

[0714] Step 1:

[0715] A user accesses a terminal and enters basic information (age, education level, area of ​​residence, etc.). For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[0716] Step 2:

[0717] The device sends the basic information entered to the server, and the device sends the input data to the server via the API.

[0718] Step 3:

[0719] The server receives the user's basic information and generates optimal learning content using a generation AI. The server accesses a database, customizes the learning content based on the specified parameters, and passes it to the generation AI to generate the learning content.

[0720] Step 4:

[0721] The server sends the generated learning content to the device. The server sends data via API to return the generated results to the device.

[0722] Step 5:

[0723] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[0724] Step 6:

[0725] The emotion engine analyzes the user's facial expressions and voice to collect emotion data. For example, it uses the device's camera and microphone to analyze facial expressions and tone of voice to collect emotion data.

[0726] Step 7:

[0727] The device sends emotional data to the server. The collected emotional data is sent to the server in real time.

[0728] Step 8:

[0729] Users use learning content to solve problems and advance their studies. Every time a problem is solved, progress information (correct answer rate, answer time, etc.) is recorded on the device in real time.

[0730] Step 9:

[0731] The device sends the collected learning progress information to the server. The progress data is sent to the server every time learning is completed or at a specific timing.

[0732] Step 10:

[0733] The server analyzes the progress information and emotion data to evaluate the user's understanding and emotion state. The server uses a data analysis module to analyze the received progress information and emotion data to measure the user's state.

[0734] Step 11:

[0735] The server adjusts the next learning content based on the user's level of understanding and emotional data. For example, if the user is tired, it switches to questions that are easier to answer, and if the user is excited, it increases the difficulty level.

[0736] Step 12:

[0737] The server generates tailored learning content using a generative AI and sends the generated content to the device.

[0738] Step 13:

[0739] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[0740] Step 14:

[0741] The server generates messages of encouragement and advice and sends them to the device. Based on the emotion data, it generates messages such as "You're doing well, try a little harder!" and sends them to the device.

[0742] Step 15:

[0743] The device displays encouraging and advice messages to the user. The device displays messages on the user interface to improve the user's motivation.

[0744] Step 16:

[0745] The server accumulates learning data and emotion data collected from users and stores the learning history in a database, which is used to train the AI ​​model.

[0746] Step 17:

[0747] The server trains the generation AI based on the accumulated data and updates the AI ​​model. The AI ​​model trained based on new data is used to improve the accuracy of the algorithm.

[0748] Step 18:

[0749] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[0750] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[0751] Example 2

[0752] 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."

[0753] The problem that this invention aims to solve is to provide effective and efficient education to the poorest learners and break the cycle of poverty. Specifically, the objective is to generate optimal learning content and maximize learners' understanding by taking into account each learner's individual progress and emotional state.

[0754] 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.

[0755] In this invention, the server includes means for inputting basic information about the learner and transmitting the basic information to the server, means for generating optimal learning content for the learner using a generation AI, means for transmitting the generated learning content to the learner's device and displaying it, means for the server to analyze the learner's emotional information, adjust the difficulty of the learning content based on the emotional information, and generate appropriate encouragement and advice, and means for transmitting and displaying messages of encouragement and advice based on the emotional information to the learner's device. This enables effective education tailored to each individual learner, maintains their motivation to learn, and helps them develop the ability to escape poverty.

[0756] "Basic information" refers to information needed to understand the learner's background and situation, such as the learner's age, prerequisite educational level, and area of ​​residence.

[0757] "Learning content" refers to teaching materials and questions that are generated by generative AI based on the learner's basic information and progress information, in order to provide specific educational goals and challenges.

[0758] "Generative AI" is a type of artificial intelligence that uses natural language processing technology to automatically generate educational content that is optimal for learners.

[0759] "Progress information" refers to data such as correct answer rate and answer time obtained as learners progress through their studies using educational content.

[0760] "Emotional information" refers to information about the learner's emotional state during learning, obtained by analyzing the learner's facial expressions and voice.

[0761] "Encouraging and advice messages" are messages that are generated based on the learner's emotional information and contain motivation and guidance to continue learning.

[0762] An "AI model" is a collection of algorithms and structured datasets that a generative AI uses to train it to generate new educational content.

[0763] "Device" refers to an electronic device (e.g., a smartphone or tablet) on which a learner displays learning content and performs learning activities.

[0764] The "server" is a central processing unit that receives and analyzes basic information and progress information sent by learners, and generates and transmits learning content using generation AI.

[0765] The present invention is a system that aims to provide appropriate education to learners from the poorest backgrounds and break the cycle of poverty. This system inputs basic information about learners, generates learning content, collects learning progress information, analyzes emotional information, and regenerates learning content based on this information. Specific embodiments of the present invention are described below.

[0766] First, the device used by the learner is an electronic device such as a smartphone or tablet. The user accesses this device and enters basic information such as age, educational level, and area of ​​residence. For example, the user launches an application and enters information such as "10 years old," "can read and write basic language," and "lives in a rural area." The device then sends this basic information to the server.

[0767] Based on the received basic information, the server uses a generative AI model (e.g., a model using natural language processing technology) to generate learning content that is optimal for the learner. For example, a 10-year-old learner is provided with basic arithmetic problems on addition and subtraction. The generated learning content is sent from the server to the device and displayed on the device.

[0768] As a user studies using learning content, the device records learning progress information (e.g., percentage of correct answers and answer time) in real time. This progress information is sent to a server, which analyzes it to evaluate the learner's level of understanding. For example, if a learner is weak in a particular area, new learning content that focuses on that area can be generated.

[0769] Furthermore, the device is equipped with an emotion engine that evaluates the user's emotional information by analyzing their facial expressions and voice. This emotional information is also sent to the server, which then uses this information to adjust the difficulty and type of learning content. Messages of encouragement and advice based on the user's emotions are also generated and sent to the device. For example, an encouraging message such as "You're almost there, keep going!" may be displayed.

[0770] The server stores the collected learning data and emotion data and uses them to train the generative AI model. The AI ​​model is updated through training, and new data sets are used to improve the accuracy of the generative AI model. The updated AI model generates newly optimized learning content and sends it to the device, allowing learners to study more effectively.

[0771] As a concrete example, when a user uses the system for the first time, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As learning progress and emotional information are accumulated, the server uses the generative AI model to adjust the next learning content. For example, the generative AI model generates optimal learning content using a prompt such as, "Generate beginner-level arithmetic problems suitable for a 10-year-old learner. As prerequisite knowledge, the learner understands basic addition and subtraction. Please adjust the next learning content taking into account the accuracy rate and answer time."

[0772] This system allows learners to receive an education that is tailored to their individual needs and empowers them to break the cycle of poverty.

[0773] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0774] Step 1:

[0775] The user enters basic information into the device.

[0776] The user launches the application and enters basic information such as age, educational level, and area of ​​residence. For example, they might enter items such as "10 years old," "can read and write basic words," and "live in a rural area." This input information will later become the basis for the generative AI to generate learning content.

[0777] Input: User-entered age, education level, and area of ​​residence

[0778] Output: The basic information entered is saved on the device.

[0779] Specific behavior: The user enters the required information into the application's input form and clicks the submit button.

[0780] Step 2:

[0781] The device sends basic information to the server

[0782] The terminal sends the basic information entered by the user to the server. This sending process is performed using, for example, an HTTP POST request.

[0783] Input: Basic information stored on your device

[0784] Output: Basic information sent to the server

[0785] Specific operation: The device sends the user's basic information to the server using an HTTP POST request.

[0786] Step 3:

[0787] The server generates learning content using AI based on basic information

[0788] The server analyzes the received basic information and uses a generative AI model (e.g., a model using natural language processing technology) to generate appropriate learning content. For example, basic arithmetic addition and subtraction problems are generated for a 10-year-old learner.

[0789] Input: Basic information sent to the server

[0790] Output: Generated learning content

[0791] Specific operation: The server uses the generative AI model to input basic information as prompts and generate specific learning content (e.g., math problems). The generated learning content is temporarily stored on the server.

[0792] Step 4:

[0793] The server sends the generated learning content to the device.

[0794] The server sends the generated learning content to the terminal, for example, by returning the content as an HTTP response.

[0795] Input: Generated learning content

[0796] Output: Learning content sent to the device

[0797] Specific operation: The server sends the generated learning content to the device as an HTTP response.

[0798] Step 5:

[0799] The device displays the learning content to the user.

[0800] The device displays the received learning content to the user, who then begins learning using the content.

[0801] Input: Learning content sent to your device

[0802] Output: Learning content displayed on the device display

[0803] Specific operation: The device displays the learning content on the user interface, and the user begins solving the problems.

[0804] Step 6:

[0805] The device collects the user's learning progress information

[0806] The device records the user's learning progress, such as the percentage of correct answers and the time it takes to answer, in real time, allowing the user to understand their learning situation.

[0807] Input: User's answer data (answer time, correct answer rate, etc.)

[0808] Output: Collected learning progress information

[0809] Specific operation: The device collects and stores the user's answer data using sensors and recording functions.

[0810] Step 7:

[0811] The device sends progress data to the server

[0812] The device sends the collected progress data to the server, again using, for example, an HTTP POST request.

[0813] Input: Collected learning progress information

[0814] Output: Progress data sent to the server

[0815] What happens: The device sends the collected progress data to the server using an HTTP POST request.

[0816] Step 8:

[0817] The server analyzes the progress data and generates the next learning content.

[0818] The server uses a generative AI model based on the progress data to generate the next appropriate learning content. For example, if a learner is weak in a particular area, new questions focused on that area will be generated.

[0819] Input: Progress data sent to the server

[0820] Output: Next learning content

[0821] Specific operation: The server analyzes the progress data and uses the generative AI model to generate the next learning content (e.g., subject-specific questions).

[0822] Step 9:

[0823] The server sends the next learning content to the device.

[0824] The server sends the newly generated learning content to the terminal.

[0825] Input: Newly generated learning content

[0826] Output: The next learning content sent to the device

[0827] Specific operation: The server uses the HTTP response to send the newly generated learning content to the device.

[0828] Step 10:

[0829] The device displays the next learning content to the user.

[0830] The terminal displays the newly sent learning content to the user, allowing the user to proceed to the next learning step.

[0831] Input: Next learning content sent to your device

[0832] Output: The next learning content displayed on the device display

[0833] Specific behavior: The device displays the next learning content on the user interface, and the user continues learning.

[0834] Step 11:

[0835] Emotion engine evaluates user emotions

[0836] The emotion engine analyzes the user's facial expressions and voice to assess their emotional state. For example, it uses a camera and microphone to analyze the user's face and voice.

[0837] Input: User's facial expression and voice data

[0838] Output: Evaluated emotion information

[0839] Specific operation: The emotion engine analyzes data obtained from the camera and microphone and generates emotion information.

[0840] Step 12:

[0841] The emotion engine sends the user's emotion information to the server.

[0842] The emotion engine sends the evaluated emotion information to the server, for example, using an HTTP POST request.

[0843] Input: Evaluated emotion information

[0844] Output: Emotion information sent to the server

[0845] Specific operation: The emotion engine sends emotion information to the server using an HTTP POST request.

[0846] Step 13:

[0847] The server adjusts the difficulty and type of learning content based on emotional information.

[0848] The server analyzes the received emotional information and adjusts the difficulty and type of learning content accordingly. For example, if the user is tired, the questions will be switched to easier questions.

[0849] Input: Emotion information sent to the server

[0850] Output: Tailored learning content

[0851] How it works: The server analyzes the emotional information and uses a generative AI model to adjust the content of the learning content.

[0852] Step 14:

[0853] The server generates encouraging and advice messages based on the emotional information.

[0854] The server generates appropriate encouraging and advice messages to motivate students to learn based on the emotional information.

[0855] Input: Emotion information sent to the server

[0856] Output: A message of encouragement or advice

[0857] Specific operation: The server uses a generative AI model to generate encouraging or advice messages from emotional information.

[0858] Step 15:

[0859] The server sends encouraging and advice messages to the device.

[0860] The server generates encouraging and / or helpful messages and sends them to the device.

[0861] Input: A message of encouragement or advice

[0862] Output: Messages of encouragement or advice sent to the terminal.

[0863] Specific operation: The server sends a message of encouragement or advice to the device as an HTTP response.

[0864] Step 16:

[0865] The device displays encouraging or helpful messages to the user.

[0866] The device displays encouraging and helpful messages in the user interface, helping users stay motivated.

[0867] Input: A message of encouragement or advice sent to the device

[0868] Output: Encouraging and helpful messages displayed on the screen

[0869] What it does: Your device will display encouraging or helpful messages as pop-ups or notifications.

[0870] Step 17:

[0871] The server accumulates learning data and trains the generative AI.

[0872] The server accumulates learning data and emotion data collected from users and uses this data to train the generative AI model. Through training, the accuracy and performance of the AI ​​model improves.

[0873] Input: Learning data and emotion data stored on the server

[0874] Output: Updated AI model

[0875] What it does: The server uses the accumulated data to retrain and update the generative AI model.

[0876] Step 18:

[0877] The server uses the updated AI model to generate new learning content.

[0878] The server generates new learning content using the updated AI model, ensuring that the most up-to-date and optimal learning content is always provided.

[0879] Input: Updated AI model

[0880] Output: Newly generated learning content

[0881] Specific operation: The server uses the updated AI model to execute the process of generating new learning content.

[0882] Step 19:

[0883] The server generates new learning content and sends it to the device.

[0884] The server transmits the newly generated learning content to the terminal.

[0885] Input: Newly generated learning content

[0886] Output: Learning content sent to the device

[0887] Specific operation: The server sends new learning content to the device as an HTTP response.

[0888] Step 20:

[0889] The device displays new learning content to the user.

[0890] The terminal displays the newly transmitted learning content to the user.

[0891] Input: Learning content sent to your device

[0892] Output: Learning content displayed on the device display

[0893] Specific behavior: The device displays new learning content in the user interface, and the user continues learning.

[0894] (Application example 2)

[0895] 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."

[0896] Conventional food delivery services have difficulty in proposing meals that take into account the user's food preferences and allergy information, and do not provide personalized services that respond to the user's emotions and physical condition. This has led to the problem that they are not adequately proposing meals that satisfy the user or that are suitable for health management. Furthermore, they do not continuously improve their services based on user emotions and feedback, which makes it difficult to encourage repeat use.

[0897] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting basic information about the learner and transmitting the basic information to the server, means for the server to generate optimal learning content for the learner using a generation AI, means for transmitting the generated learning content to the learner's device and displaying it, means for inputting the user's food preferences and health-related information and transmitting the information to the server, means for the server to generate optimal meal options for the user using a generation AI, means for transmitting the generated meal options to the user's device and displaying them, means for collecting progress information about the learner and transmitting the progress information to the server, means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content, means for transmitting the adjusted learning content to the learner's device and displaying it, means for collecting the user's food order history and emotional state and transmitting them to the server, means for the server to adjust the next meal option based on the emotional information, and means for transmitting the adjusted meal options to the user's device and displaying them. This enables optimal meal suggestions based on the user's emotional state, taking into account the user's food preferences and allergy information.

[0898] "Basic information about the learner" refers to basic information about the learner, such as their age, educational background, and place of residence.

[0899] "Server" refers to the central computer system that processes the received information and uses generative AI to generate and manage learning content and dining options.

[0900] "Generative AI" is a type of artificial intelligence, an algorithm that automatically generates optimal learning content and meal options based on input information.

[0901] "Learning content" refers to learning-related information such as educational materials and workbooks created for learners to use.

[0902] "Food preferences and health-related information" refers to health-related information such as the ingredients and types of food that the user prefers when eating, allergy information, and dietary restrictions.

[0903] "Meal options" are specific food or menu choices suggested based on the user's information.

[0904] "Meal order history" refers to the user's past meal order history and detailed information about those orders.

[0905] "Emotional state" refers to the emotions and psychological state that the user is currently experiencing, and is information detected from facial expressions, voice, and the like.

[0906] A "user's device" refers to a mobile information terminal device such as a smartphone or tablet used by a learner or user.

[0907] "Progress information" is information that indicates how far a learner has progressed in their studies, and includes the percentage of correct answers and the time it took to answer.

[0908] An "AI model" is a model that is learned by artificial intelligence and generates appropriate output based on input data.

[0909] This invention is a system that generates optimal meal options based on a user's food preferences and health-related information and provides them to the user. The system includes means for inputting basic information about a learner and transmitting the basic information to a server, means for the server to generate optimal learning content for the learner using a generation AI, and means for transmitting the generated learning content to the learner's device and displaying it. The system also includes means for inputting a user's food preferences and health-related information and transmitting the information to the server, means for the server to generate optimal meal options for the user using a generation AI, and means for transmitting the generated meal options to the user's device and displaying them.

[0910] The system program performs the following processing.

[0911] First, the user uses a device such as a smartphone or tablet to input their food preferences, allergy information, and health-related information. For example, they can input information such as "I like spicy food," "I'm vegan," "I'm gluten-free," and "I prefer low-calorie foods." The input information is then sent to the server by the device.

[0912] This server uses Amazon Web Services (AWS) and, after receiving the data, uses a generative AI model to generate optimal meal options based on the user's information. TensorFlow or Pytorch is used as the generative AI model, for example. The generated meal options are then sent back to the user's device, where they can be viewed.

[0913] Once the user selects a meal option and places an order, the order history and user feedback (satisfaction level and comments) are sent back to the server. This information is stored in a cloud database (e.g., Amazon RDS). In addition, the device is equipped with a module that evaluates the user's emotional state from their facial expressions and voice, and this data is also sent to the server.

[0914] Based on the accumulated data, the server retrains and updates the generative AI model, allowing it to provide even more personalized meal options the next time you order.

[0915] For example, if a user inputs information such as "I like spicy food" and "I prefer low-calorie food," the server will recommend "spicy low-calorie dishes." Furthermore, if the user orders the dish and provides feedback that they are satisfied, that data will be saved on the server and reflected in the next recommendation. Also, if the user is feeling down, the server can suggest "mood-boosting meals."

[0916] An example of a prompt is shown below.

[0917] User information: Female in her 20s, vegetarian, low-calorie diet, currently feeling stressed.

[0918] Suggestion: Choose vegetarian, low-calorie options that are effective in relieving stress.

[0919] As a result, it becomes possible to suggest appropriate meals according to the user's health condition and emotional state, thereby improving the quality of service.

[0920] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0921] Step 1:

[0922] The user uses the terminal to input food preferences and health-related information and presses the send button.

[0923] Input: The user enters food preferences (e.g., "I like spicy food") and health-related information (e.g., "vegan" or "low-calorie conscious").

[0924] Data processing: Converting user input information into a data format within the terminal.

[0925] Output: Sends formatted data to the server.

[0926] Step 2:

[0927] The server receives and analyzes the transmitted information.

[0928] Input: User's food preferences and health-related information sent from the device.

[0929] Data processing: Store the data in a database (e.g., Amazon RDS) and prepare it as input for the generative AI.

[0930] Output: The input dataset for the generative AI model.

[0931] Step 3:

[0932] The server uses a generative AI model to generate optimal meal options based on the user's information.

[0933] Input: User's food preferences and health-related information.

[0934] Data Computing: Leverage generative AI models (e.g., TensorFlow or Pytorch) to generate personalized meal options for users.

[0935] Output: The generated meal option data.

[0936] Step 4:

[0937] The server transmits the generated meal options to the terminal.

[0938] Input: Generated meal option data.

[0939] Data processing: Converting data into a format that can be received by the user terminal.

[0940] Output: Sends the formatted meal option data to the user's device.

[0941] Step 5:

[0942] The user's device displays meal options.

[0943] Input: Meal option data sent from the server.

[0944] Data processing: Rendering the data to display meal options on the device screen.

[0945] Output: A visual representation of the meal options.

[0946] Step 6:

[0947] The user selects a meal option and places an order.

[0948] Input: Information about the meal option selected by the user.

[0949] Data processing: Prepare the selected option data as order data.

[0950] Output: Sends the order information to the server.

[0951] Step 7:

[0952] The server receives and processes the order information.

[0953] Input: Order information submitted by the user.

[0954] Data Processing: Order information is entered into the order management system and stored in a historical database.

[0955] Output: Order confirmation information.

[0956] Step 8:

[0957] The server stores order history and emotion information.

[0958] Input: Order history and emotional information from users (e.g., facial expression analysis data).

[0959] Data calculation: Analyze the accumulated data and use it as retraining data for the generative AI model.

[0960] Output: An updated generative AI model.

[0961] Step 9:

[0962] The user's device sends emotional information to the server and displays the analysis results in a timely manner.

[0963] Input: Emotional information collected by the device from the user's facial expressions and voice.

[0964] Data processing: Emotional information is analyzed, converted into a data format, and sent to the server.

[0965] Output: Data for the next proposal based on the analysis results.

[0966] In this way, a system can be realized that provides optimal meal options based on a user's food preferences, health information, and emotional state.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] [Third embodiment]

[0971] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0972] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0973] 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).

[0974] 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.

[0975] 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.

[0976] 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).

[0977] 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.

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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."

[0983] The present invention is a system that aims to provide the poorest people with a minimum level of education and break the cycle of poverty. This system includes a means for inputting basic information about a learner and sending the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it.

[0984] Explanation of program processing

[0985] 1. Enter and submit basic student information

[0986] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[0987] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[0988] 2. Creation and provision of learning content

[0989] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[0990] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[0991] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[0992] 3. Feedback on learning status and generation of next content

[0993] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[0994] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[0995] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[0996] The server transmits the tailored learning content to the terminal, which displays it.

[0997] 4. Data accumulation and generation AI training

[0998] The server accumulates the learning data sent by users and manages the learning history. The accumulated data is used to train the AI ​​model.

[0999] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[1000] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[1001] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress information accumulates, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[1002] The processing flow will be explained below.

[1003] Step 1:

[1004] The user accesses the terminal and enters basic information (age, education level, area of ​​residence, etc.). The user then launches the application and records the necessary information in the input form.

[1005] Step 2:

[1006] The device sends the basic information entered to the server. The device app then sends the input data to the server via the API.

[1007] Step 3:

[1008] The server receives the user's basic information and uses a generation AI to generate optimal learning content. The server accesses the database, customizes the content based on the received basic information, and passes it on to the generation AI to generate the learning content.

[1009] Step 4:

[1010] The server sends the generated learning content to the device. The server sends data through the API to return the generated content to the device.

[1011] Step 5:

[1012] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[1013] Step 6:

[1014] Users use learning content to solve problems and advance their learning. Progress information (correct answer rate, answer time, etc.) is collected in real time each time a problem is solved.

[1015] Step 7:

[1016] The device sends the collected learning progress information to the server. The progress data is sent to the server each time learning is completed or at a specific timing.

[1017] Step 8:

[1018] The server analyzes the progress information and evaluates the user's level of understanding. The server uses a data analysis module to analyze the received progress information and measure the user's level of understanding.

[1019] Step 9:

[1020] The server uses AI to generate the next learning content, tailored based on the level of comprehension. Based on the results of the comprehension assessment, the next learning content is customized and new content is generated by AI.

[1021] Step 10:

[1022] The server sends the tailored learning content to the device, and sends data through the API to send the generated content back to the device.

[1023] Step 11:

[1024] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[1025] Step 12:

[1026] The server accumulates learning data collected from users and stores their learning history in a database. The server uses the accumulated data to train the generative AI and update the AI ​​model.

[1027] Step 13:

[1028] The server generates new learning content using the updated AI model, and retrains the AI ​​model based on new data to generate the latest content.

[1029] Step 14:

[1030] The server sends the latest learning content to the device and displays it. Generated content is sent back to the device, allowing the user's learning to be continuously improved.

[1031] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[1032] Example 1

[1033] 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."

[1034] Providing appropriate and effective education to the poorest people is a challenge. Providing individually optimized learning content based on each learner's progress requires a great deal of effort and cost. Furthermore, there is a need for efficient management of learning data and continuous improvement of AI models.

[1035] 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.

[1036] In this invention, the server includes a means for inputting the learner's personal information and transmitting the personal information to the server, a means for the server to generate learning content optimized for the learner using a generative AI, a means for transmitting the generated learning content to the learner's terminal device and displaying it, a means for the server to analyze the learner's personal information received and format it as input data suitable for the generative AI model, a means for inputting the information as prompts to the generative AI model, a means for using the generative AI model to generate learning content based on the input requirements, and a means for converting the generated content into an appropriate format and transmitting it to the terminal device. This makes it possible to provide learning content individually optimized according to the learner's progress, thereby providing effective education. Furthermore, the accumulation of learning data and the training of the generative AI can be efficiently managed, allowing for continuous improvement in the accuracy of the AI ​​model.

[1037] "Personal information of learners" refers to information necessary to understand the learner's background and situation, such as age, educational level, and area of ​​residence.

[1038] An "information processing device" is a device used to perform various data processing operations, such as receiving, analyzing, and storing data, and training generative AI models.

[1039] "Generative AI" is an AI system that has the ability to generate new content or information based on given data or prompts.

[1040] "Learning content" refers to educational content such as teaching materials, questions, and exercises that learners should study.

[1041] A "terminal device" is a device that a user can directly access to view, operate, and respond to learning content.

[1042] A "prompt" refers to an instruction or question entered into a generative AI model to elicit an appropriate response.

[1043] "Learning data" refers to all information generated by a learner, including, for example, progress, answer history, and comprehension assessment.

[1044] "Format" refers to the state in which data or content is arranged in a specific form or structure.

[1045] "Training" refers to the learning process that uses new data to improve the accuracy of a generative AI model.

[1046] The present invention is a system aimed at providing the poorest people with a minimum level of education and breaking the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to an information processing device, a means for the information processing device to generate optimal learning content for the learner using generative AI, and a means for transmitting the generated learning content to the learner's terminal device and displaying it. The system also includes a means for collecting learner progress information and adjusting the learning content based on the progress information, and a means for accumulating learning data to train an AI model and improve the accuracy of the generative AI model.

[1047] 1. Enter and submit basic information

[1048] The first thing a user does is input basic information such as age, educational level, and area of ​​residence. This information is entered into a terminal device and transmitted to an information processing device. During this transmission process, security protocols (e.g., HTTPS) are used to ensure data security.

[1049] 2. Creation and provision of learning content

[1050] The information processing device uses generative artificial intelligence (e.g., OpenAI's GPT model) based on the received basic information to generate optimal learning content for the learner. In this process, the information processing device analyzes the received personal information, formats it as input data suitable for the generative AI model, and enters it as a prompt. For example, the prompt might be "10 years old, rural area, arithmetic and reading / writing at the third grade level." The generated learning content is then converted into an appropriate format (e.g., HTML or JSON) and sent to the terminal device. The terminal device displays the received learning content on a user interface, allowing the user to begin learning.

[1051] 3. Feedback on learning status and generation of next content

[1052] The terminal device collects the user's learning progress information in real time and transmits it to the information processing device. The information processing device analyzes the received progress information, evaluates the user's level of understanding, and adjusts the next learning content. This evaluation result is provided as a prompt to the generative artificial intelligence model, which generates the next learning content. For example, if the evaluation indicates that "the user is struggling with fraction problems," problems covering everything from basic to advanced fractions are generated. The generated new learning content is transmitted to the terminal device and displayed to the user.

[1053] 4. Data accumulation and generation AI training

[1054] The information processing device accumulates all learning data sent by users and stores it in a learning history database. The accumulated data is used to train a generative AI model (generative artificial intelligence). This process improves the accuracy of the AI ​​model and generates more effective learning content. The new trained AI model is used to generate the next learning content and is continuously updated.

[1055] Examples of specific examples and prompts

[1056] As a specific example, when a user logs in for the first time and enters basic information such as "10 years old," "able to read and write basics," and "lives in a rural area," the information processing device inputs the prompt "10 years old, rural area, arithmetic and reading / writing at the third grade level" into the generative AI model. The generated simple arithmetic problems and basic reading comprehension problems are displayed on the user's terminal device. As the user works on these problems, progress data is accumulated, and new content based on the user's progress is provided the next time they log in.

[1057] Example prompt sentence:

[1058] "Generate math and literacy learning content for 10-year-olds, rural areas, and third grade levels."

[1059] "Generate new fraction math problems based on user progress data."

[1060] As described above, this system provides effective education to learners and makes it possible to provide individually optimized learning content according to their progress.

[1061] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1062] Step 1:

[1063] A user launches a learning application using a terminal device and enters basic information. This basic information includes age, educational level, and area of ​​residence. For example, the user might enter "10 years old," "can read and write basic words," and "live in a rural area." Input: User's basic information. Output: Data of the entered basic information.

[1064] Step 2:

[1065] The terminal device sends the input basic information to the information processing device (server). At this time, a security protocol (e.g., HTTPS) is used to ensure the safety of the data. Input: User's basic information. Output: Data of the basic information sent to the information processing device.

[1066] Step 3:

[1067] The server analyzes the basic information it receives and formats it as input data suitable for the generative AI model. Specifically, it summarizes information such as age and education level and converts it into a format that can be passed to the generative AI model. Input: The basic information sent. Output: Data formatted for the generative AI model.

[1068] Step 4:

[1069] The server inputs the formatted data to the generative AI model as a prompt. This prompt includes the learner's characteristics and learning requirements. For example, the requirement "10 years old, rural area, arithmetic and reading / writing at the third grade level" is used as the prompt. Input: Prompt for the generative AI model. Output: Prompt input to the generative AI model.

[1070] Step 5:

[1071] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate learning content based on the input prompt. Specifically, it generates simple math problems or basic reading comprehension questions. Input: The prompt input to the generative AI model. Output: The generated learning content.

[1072] Step 6:

[1073] The server converts the generated learning content into an appropriate format (e.g., HTML, JSON) and sends it to the terminal device. Input: Generated learning content. Output: Content converted into an appropriate format and its transmission.

[1074] Step 7:

[1075] The terminal device displays the received learning content on the user interface. The user browses this content and begins learning. Input: Received learning content. Output: Learning content displayed to the user.

[1076] Step 8:

[1077] The user engages with the learning content and answers or performs operations. Specifically, they solve displayed math problems or enter answers to reading comprehension questions. Input: User operations and answers. Output: Progress data of learning activities.

[1078] Step 9:

[1079] The terminal device collects the user's learning progress information in real time. The collected data includes the percentage of correct answers to questions and the time it took to answer them. Input: User's learning activity. Output: Collected progress data.

[1080] Step 10:

[1081] The terminal device sends the collected progress data to the server. Input: Collected progress data. Output: Progress data sent to the server.

[1082] Step 11:

[1083] The server analyzes the received progress information and evaluates the user's level of understanding. It identifies areas of strength and weakness. Input: Submitted progress data. Output: Analyzed level of understanding information.

[1084] Step 12:

[1085] The server provides the generative AI model with a prompt to generate the next learning content based on the progress data. For example, the next prompt is generated based on the evaluation that "the user is struggling with fraction problems." Input: Analyzed comprehension information. Output: Prompt to input to the generative AI model.

[1086] Step 13:

[1087] The server uses the generative AI model to generate new learning content. For example, new problems covering everything from the basics to advanced fractions are generated. Input: The prompt entered into the generative AI model. Output: New learning content.

[1088] Step 14:

[1089] The server sends the generated new learning content to the terminal device, which displays it. Input: The generated new learning content. Output: The new content displayed on the terminal device.

[1090] Step 15:

[1091] The user starts learning again with new learning content. Progress data is collected, sent, and analyzed in the same way. Input: Learning content to be re-engaged. Output: New progress data.

[1092] Step 16:

[1093] The server accumulates all the learning data sent by users and stores it in the learning history database. Input: Sent learning data. Output: Accumulated data.

[1094] Step 17:

[1095] The server trains the generative AI based on the accumulated data and updates the generative AI model, improving the accuracy of the AI ​​model. Input: Accumulated data. Output: New trained AI model.

[1096] Step 18:

[1097] The server generates new learning content using the updated generative AI model and sends it to the terminal device. Input: The trained new AI model. Output: The generated new learning content.

[1098] Step 19:

[1099] The terminal device displays the latest learning content on the user interface, allowing the user to continue learning. Input: Generated new learning content. Output: The latest learning content displayed to the user.

[1100] In this way, this system provides learning content that is individually optimized according to the learner's progress, supporting effective education. It efficiently manages the accumulation of learning data and the training of the generated AI, enabling continuous improvement of the accuracy of the AI ​​model.

[1101] (Application example 1)

[1102] 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."

[1103] For the poorest people, breaking the cycle of poverty through education is important, but the educational resources and opportunities they can access are extremely limited. Furthermore, there are no effective ways to link education with support activities such as food delivery. Furthermore, there is a need for the automatic generation and provision of educational content based on progress. There is a need to solve these problems and provide an effective educational support system for the poorest people.

[1104] 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.

[1105] In this invention, the server includes: means for inputting basic information about the learner and transmitting the basic information to the server; means for the server to generate optimal learning content for the learner using a generation AI; means for transmitting the generated learning content to the learner's device and displaying it; means for collecting progress information about the learner and transmitting the progress information to the server; means for the server to evaluate the learner's level of understanding based on the progress information and generate subsequent learning content; means for storing the learner's learning data in the server; means for training the generation AI based on the stored data and updating the AI ​​model; and means for transmitting the learning content generated using the updated AI model to the learner's device and displaying it. This makes it possible to provide optimal educational content tailored to the progress of learners from the poorest backgrounds, thereby effectively supporting efforts to break the cycle of poverty through education.

[1106] "Basic information about the learner" refers to personal information such as the learner's age, education level, and area of ​​residence.

[1107] The "server" is a system that receives basic information and progress information about learners, processes and analyzes it, and generates learning content using generation AI.

[1108] "Generative AI" is artificial intelligence that automatically generates optimal learning content based on a learner's basic information and progress information.

[1109] "Learning content" refers to educational materials such as teaching materials and problem sets that are used by learners to receive education.

[1110] "Device" means a device such as a smartphone, smart glasses, or head-mounted display that a learner uses to receive and view learning content.

[1111] "Progress information" is data that indicates the learner's learning progress and level of understanding.

[1112] "Level of understanding" is an indicator that shows how well a learner has understood the learning content provided.

[1113] "Learning data" refers to a series of data related to learning, such as basic information about the learner, progress information, and learning history.

[1114] An "updated AI model" is a generative AI model that has been retrained based on the learning data stored on the server.

[1115] The "poorest" are the most economically disadvantaged social groups, those who lack access to basic needs and education.

[1116] "Food assistance" refers to support services such as food and meals provided to the poorest people.

[1117] A "smart device" is an electronic device that allows learners to receive learning content and learn interactively.

[1118] The present invention is a system that aims to provide the poorest people with the minimum education necessary to break the cycle of poverty. This system consists of the following steps:

[1119] Hardware and software configuration

[1120] This system includes a terminal for inputting learner information, a server for utilizing the generative AI, and a smart device for displaying learning content. Specifically, the following hardware and software are used:

[1121] Devices: Smartphones, smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest)

[1122] Server: Cloud server (e.g. AWS)

[1123] Software: Custom applications (for Android / iOS), AI models (e.g., GPT-4)

[1124] Program processing explanation

[1125] 1. Enter and submit basic student information

[1126] The user accesses the terminal and enters basic information such as the learner's name, age, education level, and area of ​​residence, which is then sent to the server.

[1127] Example: A user launches an application and enters information such as "10 years old," "can read and write basic words," and "lives in a rural area."

[1128] 2. Creation and provision of learning content

[1129] The server uses the generative AI model based on the received basic information to generate optimal learning content for the learner, which is then sent to the device and displayed to the user.

[1130] Example: For a 10-year-old learner, basic math problems and reading and writing exercises are generated.

[1131] Example prompt: Generate educational content on nutrition and basic math for a 10-year-old user living in a rural area who can read and write at a basic level.

[1132] 3. Feedback on learning status and generation of next content

[1133] The device collects the user's learning progress information and sends it to the server, which analyzes the progress data and adjusts and generates the next learning content.

[1134] Example: Identify areas where the user is weak, assess their level of understanding, and automatically generate the most appropriate next learning content.

[1135] 4. Data accumulation and generation AI training

[1136] The server stores all the learning data sent by users and uses it to train the AI ​​model, which is periodically updated and retrained on new datasets.

[1137] Example: Updating AI models with newly collected data improves the accuracy of learning content.

[1138] Overall flow

[1139] By repeating this process, it is possible to continue providing effective education to the poorest learners. Furthermore, by integrating food assistance and education, this system will realize more practical and effective support. For example, it is possible to design a system that links with food delivery services so that educational content is provided at the same time as food is delivered.

[1140] In this way, the present invention can provide a practical and sustainable educational support system to break the cycle of poverty.

[1141] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1142] Step 1:

[1143] Users access their devices and enter basic information such as their name, age, education level, and area of ​​residence. This basic information is sent as input data to the server, which analyzes the received data and generates a basic profile of the learner. Specific operations involve the user answering a series of questions using an app on their smartphone or smart device.

[1144] Step 2:

[1145] The server uses a generative AI model based on the received basic information to generate optimal learning content for the learner. Here, the input data is the learner's basic information, and the output data is the generated learning content. The generative AI model uses a prompt sentence based on the input data to launch a text generation algorithm (e.g., GPT-4) to generate appropriate learning content. Specifically, the AI ​​engine in the server operates and generates learning materials based on the specified prompt sentence.

[1146] Step 3:

[1147] The generated learning content is sent from the server to the terminal. The terminal receives this learning content and displays it to the user. The input data here is the generated learning content, and the output data is the learning content reflected on the user's display screen. Specifically, the new educational content is displayed to the user through the notification function.

[1148] Step 4:

[1149] The user studies the displayed learning content. During the learning process, the user's answers and activity log are automatically recorded. The input data is the user's learning behavior, and the output data is learning progress information. Specific operations include answer input and progress recording via a touch screen or input interface.

[1150] Step 5:

[1151] The device collects the user's learning progress information and sends this data to the server. The input data is the user's learning progress information, and the output data is the progress log sent to the server. Specifically, the progress data is automatically uploaded at specified intervals or for each event.

[1152] Step 6:

[1153] Based on the received learning progress information, the server uses a generative AI model to adjust and generate the next learning content. Here, the input data is the received learning progress information, and the output data is the newly generated learning content. Specifically, an analytical algorithm runs within the server, automatically generating learning materials appropriate for the next step based on the progress data.

[1154] Step 7:

[1155] All of a learner's learning data is stored on the server. The input data is past and current learning progress data, and the output data is the accumulated learning history. Specifically, data is continuously added to the server's database, and backups and database compression are performed as necessary.

[1156] Step 8:

[1157] The server trains and updates the generative AI model based on the accumulated data. The input data is the accumulated training data, and the output data is the updated generative AI model. Specifically, the machine learning algorithm runs using the new data set, and re-training is performed to improve the accuracy of the model.

[1158] Step 9:

[1159] New learning content is generated using the updated generative AI model. The generated learning content is then sent back to the device and displayed to the user. The input data is the updated generative AI model and a request for new learning content, and the output data is the latest generated learning content. Specifically, the new AI model is applied, and optimal content for the user is regenerated and displayed.

[1160] 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.

[1161] The present invention is a system designed to provide the poorest people with a basic education and break the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it. The system also includes a means for collecting progress information about the learner and transmitting the progress information to the server, and a means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content. The system also includes a means for storing the learner's learning data on the server, training the generation AI based on the stored data, and updating the AI ​​model.

[1162] In addition, the present invention includes an emotion engine that recognizes the learner's emotions, and the emotion engine has a means for analyzing the learner's emotions and transmitting the information to the server. Based on the emotion information, the server also has a means for adjusting the difficulty and type of learning content and generating appropriate encouraging and advice messages.

[1163] Explanation of program processing

[1164] 1. Enter and submit basic student information

[1165] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[1166] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[1167] 2. Creation and provision of learning content

[1168] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[1169] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[1170] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[1171] 3. Feedback on learning status and generation of next content

[1172] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[1173] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[1174] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[1175] The server transmits the tailored learning content to the terminal, which displays it.

[1176] 4. Implementing the Emotion Engine

[1177] The emotion engine evaluates the user's emotions from their facial expressions and voice and sends the data to the server. For example, it detects the user's emotional state, such as whether they are easily tired or excited while studying.

[1178] The server receives emotional information and adjusts the difficulty and type of learning content based on that information. For example, if the user is tired, the questions are switched to easier questions.

[1179] The server generates encouraging and advice messages based on the emotional information and sends them to the device. For example, when the user is about to give up, it displays a message such as "You're almost there, keep trying!"

[1180] 5. Data accumulation and generation AI training

[1181] The server accumulates learning data and emotion data collected from users and stores the learning history in a database. The accumulated data is used to train the AI ​​model.

[1182] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[1183] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[1184] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress and emotional information is accumulated, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[1185] The processing flow will be explained below.

[1186] Step 1:

[1187] A user accesses a terminal and enters basic information (age, education level, area of ​​residence, etc.). For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[1188] Step 2:

[1189] The device sends the basic information entered to the server, and the device sends the input data to the server via the API.

[1190] Step 3:

[1191] The server receives the user's basic information and generates optimal learning content using a generation AI. The server accesses a database, customizes the learning content based on the specified parameters, and passes it to the generation AI to generate the learning content.

[1192] Step 4:

[1193] The server sends the generated learning content to the device. The server sends data via API to return the generated results to the device.

[1194] Step 5:

[1195] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[1196] Step 6:

[1197] The emotion engine analyzes the user's facial expressions and voice to collect emotion data. For example, it uses the device's camera and microphone to analyze facial expressions and tone of voice to collect emotion data.

[1198] Step 7:

[1199] The device sends emotional data to the server. The collected emotional data is sent to the server in real time.

[1200] Step 8:

[1201] Users use learning content to solve problems and advance their studies. Every time a problem is solved, progress information (correct answer rate, answer time, etc.) is recorded on the device in real time.

[1202] Step 9:

[1203] The device sends the collected learning progress information to the server. The progress data is sent to the server every time learning is completed or at a specific timing.

[1204] Step 10:

[1205] The server analyzes the progress information and emotion data to evaluate the user's understanding and emotion state. The server uses a data analysis module to analyze the received progress information and emotion data to measure the user's state.

[1206] Step 11:

[1207] The server adjusts the next learning content based on the user's level of understanding and emotional data. For example, if the user is tired, it switches to questions that are easier to answer, and if the user is excited, it increases the difficulty level.

[1208] Step 12:

[1209] The server generates tailored learning content using a generative AI and sends the generated content to the device.

[1210] Step 13:

[1211] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[1212] Step 14:

[1213] The server generates messages of encouragement and advice and sends them to the device. Based on the emotion data, it generates messages such as "You're doing well, try a little harder!" and sends them to the device.

[1214] Step 15:

[1215] The device displays encouraging and advice messages to the user. The device displays messages on the user interface to improve the user's motivation.

[1216] Step 16:

[1217] The server accumulates learning data and emotion data collected from users and stores the learning history in a database, which is used to train the AI ​​model.

[1218] Step 17:

[1219] The server trains the generation AI based on the accumulated data and updates the AI ​​model. The AI ​​model trained based on new data is used to improve the accuracy of the algorithm.

[1220] Step 18:

[1221] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[1222] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[1223] Example 2

[1224] 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."

[1225] The problem that this invention aims to solve is to provide effective and efficient education to the poorest learners and break the cycle of poverty. Specifically, the objective is to generate optimal learning content and maximize learners' understanding by taking into account each learner's individual progress and emotional state.

[1226] 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.

[1227] In this invention, the server includes means for inputting basic information about the learner and transmitting the basic information to the server, means for generating optimal learning content for the learner using a generation AI, means for transmitting the generated learning content to the learner's device and displaying it, means for the server to analyze the learner's emotional information, adjust the difficulty of the learning content based on the emotional information, and generate appropriate encouragement and advice, and means for transmitting and displaying messages of encouragement and advice based on the emotional information to the learner's device. This enables effective education tailored to each individual learner, maintains their motivation to learn, and helps them develop the ability to escape poverty.

[1228] "Basic information" refers to information needed to understand the learner's background and situation, such as the learner's age, prerequisite educational level, and area of ​​residence.

[1229] "Learning content" refers to teaching materials and questions that are generated by generative AI based on the learner's basic information and progress information, in order to provide specific educational goals and challenges.

[1230] "Generative AI" is a type of artificial intelligence that uses natural language processing technology to automatically generate educational content that is optimal for learners.

[1231] "Progress information" refers to data such as correct answer rate and answer time obtained as learners progress through their studies using educational content.

[1232] "Emotional information" refers to information about the learner's emotional state during learning, obtained by analyzing the learner's facial expressions and voice.

[1233] "Encouraging and advice messages" are messages that are generated based on the learner's emotional information and contain motivation and guidance to continue learning.

[1234] An "AI model" is a collection of algorithms and structured datasets that a generative AI uses to train it to generate new educational content.

[1235] "Device" refers to an electronic device (e.g., a smartphone or tablet) on which a learner displays learning content and performs learning activities.

[1236] The "server" is a central processing unit that receives and analyzes basic information and progress information sent by learners, and generates and transmits learning content using generation AI.

[1237] The present invention is a system that aims to provide appropriate education to learners from the poorest backgrounds and break the cycle of poverty. This system inputs basic information about learners, generates learning content, collects learning progress information, analyzes emotional information, and regenerates learning content based on this information. Specific embodiments of the present invention are described below.

[1238] First, the device used by the learner is an electronic device such as a smartphone or tablet. The user accesses this device and enters basic information such as age, educational level, and area of ​​residence. For example, the user launches an application and enters information such as "10 years old," "can read and write basic language," and "lives in a rural area." The device then sends this basic information to the server.

[1239] Based on the received basic information, the server uses a generative AI model (e.g., a model using natural language processing technology) to generate learning content that is optimal for the learner. For example, a 10-year-old learner is provided with basic arithmetic problems on addition and subtraction. The generated learning content is sent from the server to the device and displayed on the device.

[1240] As a user studies using learning content, the device records learning progress information (e.g., percentage of correct answers and answer time) in real time. This progress information is sent to a server, which analyzes it to evaluate the learner's level of understanding. For example, if a learner is weak in a particular area, new learning content that focuses on that area can be generated.

[1241] Furthermore, the device is equipped with an emotion engine that evaluates the user's emotional information by analyzing their facial expressions and voice. This emotional information is also sent to the server, which then uses this information to adjust the difficulty and type of learning content. Messages of encouragement and advice based on the user's emotions are also generated and sent to the device. For example, an encouraging message such as "You're almost there, keep going!" may be displayed.

[1242] The server stores the collected learning data and emotion data and uses them to train the generative AI model. The AI ​​model is updated through training, and new data sets are used to improve the accuracy of the generative AI model. The updated AI model generates newly optimized learning content and sends it to the device, allowing learners to study more effectively.

[1243] As a concrete example, when a user uses the system for the first time, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As learning progress and emotional information are accumulated, the server uses the generative AI model to adjust the next learning content. For example, the generative AI model generates optimal learning content using a prompt such as, "Generate beginner-level arithmetic problems suitable for a 10-year-old learner. As prerequisite knowledge, the learner understands basic addition and subtraction. Please adjust the next learning content taking into account the accuracy rate and answer time."

[1244] This system allows learners to receive an education that is tailored to their individual needs and empowers them to break the cycle of poverty.

[1245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] The user enters basic information into the device.

[1248] The user launches the application and enters basic information such as age, educational level, and area of ​​residence. For example, they might enter items such as "10 years old," "can read and write basic words," and "live in a rural area." This input information will later become the basis for the generative AI to generate learning content.

[1249] Input: User-entered age, education level, and area of ​​residence

[1250] Output: The basic information entered is saved on the device.

[1251] Specific behavior: The user enters the required information into the application's input form and clicks the submit button.

[1252] Step 2:

[1253] The device sends basic information to the server

[1254] The terminal sends the basic information entered by the user to the server. This sending process is performed using, for example, an HTTP POST request.

[1255] Input: Basic information stored on your device

[1256] Output: Basic information sent to the server

[1257] Specific operation: The device sends the user's basic information to the server using an HTTP POST request.

[1258] Step 3:

[1259] The server generates learning content using AI based on basic information

[1260] The server analyzes the received basic information and uses a generative AI model (e.g., a model using natural language processing technology) to generate appropriate learning content. For example, basic arithmetic addition and subtraction problems are generated for a 10-year-old learner.

[1261] Input: Basic information sent to the server

[1262] Output: Generated learning content

[1263] Specific operation: The server uses the generative AI model to input basic information as prompts and generate specific learning content (e.g., math problems). The generated learning content is temporarily stored on the server.

[1264] Step 4:

[1265] The server sends the generated learning content to the device.

[1266] The server sends the generated learning content to the terminal, for example, by returning the content as an HTTP response.

[1267] Input: Generated learning content

[1268] Output: Learning content sent to the device

[1269] Specific operation: The server sends the generated learning content to the device as an HTTP response.

[1270] Step 5:

[1271] The device displays the learning content to the user.

[1272] The device displays the received learning content to the user, who then begins learning using the content.

[1273] Input: Learning content sent to your device

[1274] Output: Learning content displayed on the device display

[1275] Specific operation: The device displays the learning content on the user interface, and the user begins solving the problems.

[1276] Step 6:

[1277] The device collects the user's learning progress information

[1278] The device records the user's learning progress, such as the percentage of correct answers and the time it takes to answer, in real time, allowing the user to understand their learning situation.

[1279] Input: User's answer data (answer time, correct answer rate, etc.)

[1280] Output: Collected learning progress information

[1281] Specific operation: The device collects and stores the user's answer data using sensors and recording functions.

[1282] Step 7:

[1283] The device sends progress data to the server

[1284] The device sends the collected progress data to the server, again using, for example, an HTTP POST request.

[1285] Input: Collected learning progress information

[1286] Output: Progress data sent to the server

[1287] What happens: The device sends the collected progress data to the server using an HTTP POST request.

[1288] Step 8:

[1289] The server analyzes the progress data and generates the next learning content.

[1290] The server uses a generative AI model based on the progress data to generate the next appropriate learning content. For example, if a learner is weak in a particular area, new questions focused on that area will be generated.

[1291] Input: Progress data sent to the server

[1292] Output: Next learning content

[1293] Specific operation: The server analyzes the progress data and uses the generative AI model to generate the next learning content (e.g., subject-specific questions).

[1294] Step 9:

[1295] The server sends the next learning content to the device.

[1296] The server sends the newly generated learning content to the terminal.

[1297] Input: Newly generated learning content

[1298] Output: The next learning content sent to the device

[1299] Specific operation: The server uses the HTTP response to send the newly generated learning content to the device.

[1300] Step 10:

[1301] The device displays the next learning content to the user.

[1302] The terminal displays the newly sent learning content to the user, allowing the user to proceed to the next learning step.

[1303] Input: Next learning content sent to your device

[1304] Output: The next learning content displayed on the device display

[1305] Specific behavior: The device displays the next learning content on the user interface, and the user continues learning.

[1306] Step 11:

[1307] Emotion engine evaluates user emotions

[1308] The emotion engine analyzes the user's facial expressions and voice to assess their emotional state. For example, it uses a camera and microphone to analyze the user's face and voice.

[1309] Input: User's facial expression and voice data

[1310] Output: Evaluated emotion information

[1311] Specific operation: The emotion engine analyzes data obtained from the camera and microphone and generates emotion information.

[1312] Step 12:

[1313] The emotion engine sends the user's emotion information to the server.

[1314] The emotion engine sends the evaluated emotion information to the server, for example, using an HTTP POST request.

[1315] Input: Evaluated emotion information

[1316] Output: Emotion information sent to the server

[1317] Specific operation: The emotion engine sends emotion information to the server using an HTTP POST request.

[1318] Step 13:

[1319] The server adjusts the difficulty and type of learning content based on emotional information.

[1320] The server analyzes the received emotional information and adjusts the difficulty and type of learning content accordingly. For example, if the user is tired, the questions will be switched to easier questions.

[1321] Input: Emotion information sent to the server

[1322] Output: Tailored learning content

[1323] How it works: The server analyzes the emotional information and uses a generative AI model to adjust the content of the learning content.

[1324] Step 14:

[1325] The server generates encouraging and advice messages based on the emotional information.

[1326] The server generates appropriate encouraging and advice messages to motivate students to learn based on the emotional information.

[1327] Input: Emotion information sent to the server

[1328] Output: A message of encouragement or advice

[1329] Specific operation: The server uses a generative AI model to generate encouraging or advice messages from emotional information.

[1330] Step 15:

[1331] The server sends encouraging and advice messages to the device.

[1332] The server generates encouraging and / or helpful messages and sends them to the device.

[1333] Input: A message of encouragement or advice

[1334] Output: Messages of encouragement or advice sent to the terminal.

[1335] Specific operation: The server sends a message of encouragement or advice to the device as an HTTP response.

[1336] Step 16:

[1337] The device displays encouraging or helpful messages to the user.

[1338] The device displays encouraging and helpful messages in the user interface, helping users stay motivated.

[1339] Input: A message of encouragement or advice sent to the device

[1340] Output: Encouraging and helpful messages displayed on the screen

[1341] What it does: Your device will display encouraging or helpful messages as pop-ups or notifications.

[1342] Step 17:

[1343] The server accumulates learning data and trains the generative AI.

[1344] The server accumulates learning data and emotion data collected from users and uses this data to train the generative AI model. Through training, the accuracy and performance of the AI ​​model improves.

[1345] Input: Learning data and emotion data stored on the server

[1346] Output: Updated AI model

[1347] What it does: The server uses the accumulated data to retrain and update the generative AI model.

[1348] Step 18:

[1349] The server uses the updated AI model to generate new learning content.

[1350] The server generates new learning content using the updated AI model, ensuring that the most up-to-date and optimal learning content is always provided.

[1351] Input: Updated AI model

[1352] Output: Newly generated learning content

[1353] Specific operation: The server uses the updated AI model to execute the process of generating new learning content.

[1354] Step 19:

[1355] The server generates new learning content and sends it to the device.

[1356] The server transmits the newly generated learning content to the terminal.

[1357] Input: Newly generated learning content

[1358] Output: Learning content sent to the device

[1359] Specific operation: The server sends new learning content to the device as an HTTP response.

[1360] Step 20:

[1361] The device displays new learning content to the user.

[1362] The terminal displays the newly transmitted learning content to the user.

[1363] Input: Learning content sent to your device

[1364] Output: Learning content displayed on the device display

[1365] Specific behavior: The device displays new learning content in the user interface, and the user continues learning.

[1366] (Application example 2)

[1367] 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."

[1368] Conventional food delivery services have difficulty in proposing meals that take into account the user's food preferences and allergy information, and do not provide personalized services that respond to the user's emotions and physical condition. This has led to the problem that they are not adequately proposing meals that satisfy the user or that are suitable for health management. Furthermore, they do not continuously improve their services based on user emotions and feedback, which makes it difficult to encourage repeat use.

[1369] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting basic information about the learner and transmitting the basic information to the server, means for the server to generate optimal learning content for the learner using a generation AI, means for transmitting the generated learning content to the learner's device and displaying it, means for inputting the user's food preferences and health-related information and transmitting the information to the server, means for the server to generate optimal meal options for the user using a generation AI, means for transmitting the generated meal options to the user's device and displaying them, means for collecting progress information about the learner and transmitting the progress information to the server, means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content, means for transmitting the adjusted learning content to the learner's device and displaying it, means for collecting the user's food order history and emotional state and transmitting them to the server, means for the server to adjust the next meal option based on the emotional information, and means for transmitting the adjusted meal options to the user's device and displaying them. This enables optimal meal suggestions based on the user's emotional state, taking into account the user's food preferences and allergy information.

[1370] "Basic information about the learner" refers to basic information about the learner, such as their age, educational background, and place of residence.

[1371] "Server" refers to the central computer system that processes the received information and uses generative AI to generate and manage learning content and dining options.

[1372] "Generative AI" is a type of artificial intelligence, an algorithm that automatically generates optimal learning content and meal options based on input information.

[1373] "Learning content" refers to learning-related information such as educational materials and workbooks created for learners to use.

[1374] "Food preferences and health-related information" refers to health-related information such as the ingredients and types of food that the user prefers when eating, allergy information, and dietary restrictions.

[1375] "Meal options" are specific food or menu choices suggested based on the user's information.

[1376] "Meal order history" refers to the user's past meal order history and detailed information about those orders.

[1377] "Emotional state" refers to the emotions and psychological state that the user is currently experiencing, and is information detected from facial expressions, voice, and the like.

[1378] A "user's device" refers to a mobile information terminal device such as a smartphone or tablet used by a learner or user.

[1379] "Progress information" is information that indicates how far a learner has progressed in their studies, and includes the percentage of correct answers and the time it took to answer.

[1380] An "AI model" is a model that is learned by artificial intelligence and generates appropriate output based on input data.

[1381] This invention is a system that generates optimal meal options based on a user's food preferences and health-related information and provides them to the user. The system includes means for inputting basic information about a learner and transmitting the basic information to a server, means for the server to generate optimal learning content for the learner using a generation AI, and means for transmitting the generated learning content to the learner's device and displaying it. The system also includes means for inputting a user's food preferences and health-related information and transmitting the information to the server, means for the server to generate optimal meal options for the user using a generation AI, and means for transmitting the generated meal options to the user's device and displaying them.

[1382] The system program performs the following processing.

[1383] First, the user uses a device such as a smartphone or tablet to input their food preferences, allergy information, and health-related information. For example, they can input information such as "I like spicy food," "I'm vegan," "I'm gluten-free," and "I prefer low-calorie foods." The input information is then sent to the server by the device.

[1384] This server uses Amazon Web Services (AWS) and, after receiving the data, uses a generative AI model to generate optimal meal options based on the user's information. TensorFlow or Pytorch is used as the generative AI model, for example. The generated meal options are then sent back to the user's device, where they can be viewed.

[1385] Once the user selects a meal option and places an order, the order history and user feedback (satisfaction level and comments) are sent back to the server. This information is stored in a cloud database (e.g., Amazon RDS). In addition, the device is equipped with a module that evaluates the user's emotional state from their facial expressions and voice, and this data is also sent to the server.

[1386] Based on the accumulated data, the server retrains and updates the generative AI model, allowing it to provide even more personalized meal options the next time you order.

[1387] For example, if a user inputs information such as "I like spicy food" and "I prefer low-calorie food," the server will recommend "spicy low-calorie dishes." Furthermore, if the user orders the dish and provides feedback that they are satisfied, that data will be saved on the server and reflected in the next recommendation. Also, if the user is feeling down, the server can suggest "mood-boosting meals."

[1388] An example of a prompt is shown below.

[1389] User information: Female in her 20s, vegetarian, low-calorie diet, currently feeling stressed.

[1390] Suggestion: Choose vegetarian, low-calorie options that are effective in relieving stress.

[1391] As a result, it becomes possible to suggest appropriate meals according to the user's health condition and emotional state, thereby improving the quality of service.

[1392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1393] Step 1:

[1394] The user uses the terminal to input food preferences and health-related information and presses the send button.

[1395] Input: The user enters food preferences (e.g., "I like spicy food") and health-related information (e.g., "vegan" or "low-calorie conscious").

[1396] Data processing: Converting user input information into a data format within the terminal.

[1397] Output: Sends formatted data to the server.

[1398] Step 2:

[1399] The server receives and analyzes the transmitted information.

[1400] Input: User's food preferences and health-related information sent from the device.

[1401] Data processing: Store the data in a database (e.g., Amazon RDS) and prepare it as input for the generative AI.

[1402] Output: The input dataset for the generative AI model.

[1403] Step 3:

[1404] The server uses a generative AI model to generate optimal meal options based on the user's information.

[1405] Input: User's food preferences and health-related information.

[1406] Data Computing: Leverage generative AI models (e.g., TensorFlow or Pytorch) to generate personalized meal options for users.

[1407] Output: The generated meal option data.

[1408] Step 4:

[1409] The server transmits the generated meal options to the terminal.

[1410] Input: Generated meal option data.

[1411] Data processing: Converting data into a format that can be received by the user terminal.

[1412] Output: Sends the formatted meal option data to the user's device.

[1413] Step 5:

[1414] The user's device displays meal options.

[1415] Input: Meal option data sent from the server.

[1416] Data processing: Rendering the data to display meal options on the device screen.

[1417] Output: A visual representation of the meal options.

[1418] Step 6:

[1419] The user selects a meal option and places an order.

[1420] Input: Information about the meal option selected by the user.

[1421] Data processing: Prepare the selected option data as order data.

[1422] Output: Sends the order information to the server.

[1423] Step 7:

[1424] The server receives and processes the order information.

[1425] Input: Order information submitted by the user.

[1426] Data Processing: Order information is entered into the order management system and stored in a historical database.

[1427] Output: Order confirmation information.

[1428] Step 8:

[1429] The server stores order history and emotion information.

[1430] Input: Order history and emotional information from users (e.g., facial expression analysis data).

[1431] Data calculation: Analyze the accumulated data and use it as retraining data for the generative AI model.

[1432] Output: An updated generative AI model.

[1433] Step 9:

[1434] The user's device sends emotional information to the server and displays the analysis results in a timely manner.

[1435] Input: Emotional information collected by the device from the user's facial expressions and voice.

[1436] Data processing: Emotional information is analyzed, converted into a data format, and sent to the server.

[1437] Output: Data for the next proposal based on the analysis results.

[1438] In this way, a system can be realized that provides optimal meal options based on a user's food preferences, health information, and emotional state.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] [Fourth embodiment]

[1443] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1444] 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.

[1445] 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).

[1446] 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.

[1447] 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.

[1448] 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).

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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."

[1456] The present invention is a system that aims to provide the poorest people with a minimum level of education and break the cycle of poverty. This system includes a means for inputting basic information about a learner and sending the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it.

[1457] Explanation of program processing

[1458] 1. Enter and submit basic student information

[1459] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[1460] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[1461] 2. Creation and provision of learning content

[1462] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[1463] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[1464] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[1465] 3. Feedback on learning status and generation of next content

[1466] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[1467] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[1468] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[1469] The server transmits the tailored learning content to the terminal, which displays it.

[1470] 4. Data accumulation and generation AI training

[1471] The server accumulates the learning data sent by users and manages the learning history. The accumulated data is used to train the AI ​​model.

[1472] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[1473] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[1474] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress information accumulates, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[1475] The processing flow will be explained below.

[1476] Step 1:

[1477] The user accesses the terminal and enters basic information (age, education level, area of ​​residence, etc.). The user then launches the application and records the necessary information in the input form.

[1478] Step 2:

[1479] The device sends the basic information entered to the server. The device app then sends the input data to the server via the API.

[1480] Step 3:

[1481] The server receives the user's basic information and uses a generation AI to generate optimal learning content. The server accesses the database, customizes the content based on the received basic information, and passes it on to the generation AI to generate the learning content.

[1482] Step 4:

[1483] The server sends the generated learning content to the device. The server sends data through the API to return the generated content to the device.

[1484] Step 5:

[1485] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[1486] Step 6:

[1487] Users use learning content to solve problems and advance their learning. Progress information (correct answer rate, answer time, etc.) is collected in real time each time a problem is solved.

[1488] Step 7:

[1489] The device sends the collected learning progress information to the server. The progress data is sent to the server each time learning is completed or at a specific timing.

[1490] Step 8:

[1491] The server analyzes the progress information and evaluates the user's level of understanding. The server uses a data analysis module to analyze the received progress information and measure the user's level of understanding.

[1492] Step 9:

[1493] The server uses AI to generate the next learning content, tailored based on the level of comprehension. Based on the results of the comprehension assessment, the next learning content is customized and new content is generated by AI.

[1494] Step 10:

[1495] The server sends the tailored learning content to the device, and sends data through the API to send the generated content back to the device.

[1496] Step 11:

[1497] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[1498] Step 12:

[1499] The server accumulates learning data collected from users and stores their learning history in a database. The server uses the accumulated data to train the generative AI and update the AI ​​model.

[1500] Step 13:

[1501] The server generates new learning content using the updated AI model, and retrains the AI ​​model based on new data to generate the latest content.

[1502] Step 14:

[1503] The server sends the latest learning content to the device and displays it. Generated content is sent back to the device, allowing the user's learning to be continuously improved.

[1504] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[1505] Example 1

[1506] 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."

[1507] Providing appropriate and effective education to the poorest people is a challenge. Providing individually optimized learning content based on each learner's progress requires a great deal of effort and cost. Furthermore, there is a need for efficient management of learning data and continuous improvement of AI models.

[1508] 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.

[1509] In this invention, the server includes a means for inputting the learner's personal information and transmitting the personal information to the server, a means for the server to generate learning content optimized for the learner using a generative AI, a means for transmitting the generated learning content to the learner's terminal device and displaying it, a means for the server to analyze the learner's personal information received and format it as input data suitable for the generative AI model, a means for inputting the information as prompts to the generative AI model, a means for using the generative AI model to generate learning content based on the input requirements, and a means for converting the generated content into an appropriate format and transmitting it to the terminal device. This makes it possible to provide learning content individually optimized according to the learner's progress, thereby providing effective education. Furthermore, the accumulation of learning data and the training of the generative AI can be efficiently managed, allowing for continuous improvement in the accuracy of the AI ​​model.

[1510] "Personal information of learners" refers to information necessary to understand the learner's background and situation, such as age, educational level, and area of ​​residence.

[1511] An "information processing device" is a device used to perform various data processing operations, such as receiving, analyzing, and storing data, and training generative AI models.

[1512] "Generative AI" is an AI system that has the ability to generate new content or information based on given data or prompts.

[1513] "Learning content" refers to educational content such as teaching materials, questions, and exercises that learners should study.

[1514] A "terminal device" is a device that a user can directly access to view, operate, and respond to learning content.

[1515] A "prompt" refers to an instruction or question entered into a generative AI model to elicit an appropriate response.

[1516] "Learning data" refers to all information generated by a learner, including, for example, progress, answer history, and comprehension assessment.

[1517] "Format" refers to the state in which data or content is arranged in a specific form or structure.

[1518] "Training" refers to the learning process that uses new data to improve the accuracy of a generative AI model.

[1519] The present invention is a system aimed at providing the poorest people with a minimum level of education and breaking the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to an information processing device, a means for the information processing device to generate optimal learning content for the learner using generative AI, and a means for transmitting the generated learning content to the learner's terminal device and displaying it. The system also includes a means for collecting learner progress information and adjusting the learning content based on the progress information, and a means for accumulating learning data to train an AI model and improve the accuracy of the generative AI model.

[1520] 1. Enter and submit basic information

[1521] The first thing a user does is input basic information such as age, educational level, and area of ​​residence. This information is entered into a terminal device and transmitted to an information processing device. During this transmission process, security protocols (e.g., HTTPS) are used to ensure data security.

[1522] 2. Creation and provision of learning content

[1523] The information processing device uses generative artificial intelligence (e.g., OpenAI's GPT model) based on the received basic information to generate optimal learning content for the learner. In this process, the information processing device analyzes the received personal information, formats it as input data suitable for the generative AI model, and enters it as a prompt. For example, the prompt might be "10 years old, rural area, arithmetic and reading / writing at the third grade level." The generated learning content is then converted into an appropriate format (e.g., HTML or JSON) and sent to the terminal device. The terminal device displays the received learning content on a user interface, allowing the user to begin learning.

[1524] 3. Feedback on learning status and generation of next content

[1525] The terminal device collects the user's learning progress information in real time and transmits it to the information processing device. The information processing device analyzes the received progress information, evaluates the user's level of understanding, and adjusts the next learning content. This evaluation result is provided as a prompt to the generative artificial intelligence model, which generates the next learning content. For example, if the evaluation indicates that "the user is struggling with fraction problems," problems covering everything from basic to advanced fractions are generated. The generated new learning content is transmitted to the terminal device and displayed to the user.

[1526] 4. Data accumulation and generation AI training

[1527] The information processing device accumulates all learning data sent by users and stores it in a learning history database. The accumulated data is used to train a generative AI model (generative artificial intelligence). This process improves the accuracy of the AI ​​model and generates more effective learning content. The new trained AI model is used to generate the next learning content and is continuously updated.

[1528] Examples of specific examples and prompts

[1529] As a specific example, when a user logs in for the first time and enters basic information such as "10 years old," "able to read and write basics," and "lives in a rural area," the information processing device inputs the prompt "10 years old, rural area, arithmetic and reading / writing at the third grade level" into the generative AI model. The generated simple arithmetic problems and basic reading comprehension problems are displayed on the user's terminal device. As the user works on these problems, progress data is accumulated, and new content based on the user's progress is provided the next time they log in.

[1530] Example prompt sentence:

[1531] "Generate math and literacy learning content for 10-year-olds, rural areas, and third grade levels."

[1532] "Generate new fraction math problems based on user progress data."

[1533] As described above, this system provides effective education to learners and makes it possible to provide individually optimized learning content according to their progress.

[1534] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1535] Step 1:

[1536] A user launches a learning application using a terminal device and enters basic information. This basic information includes age, educational level, and area of ​​residence. For example, the user might enter "10 years old," "can read and write basic words," and "live in a rural area." Input: User's basic information. Output: Data of the entered basic information.

[1537] Step 2:

[1538] The terminal device sends the input basic information to the information processing device (server). At this time, a security protocol (e.g., HTTPS) is used to ensure the safety of the data. Input: User's basic information. Output: Data of the basic information sent to the information processing device.

[1539] Step 3:

[1540] The server analyzes the basic information it receives and formats it as input data suitable for the generative AI model. Specifically, it summarizes information such as age and education level and converts it into a format that can be passed to the generative AI model. Input: The basic information sent. Output: Data formatted for the generative AI model.

[1541] Step 4:

[1542] The server inputs the formatted data to the generative AI model as a prompt. This prompt includes the learner's characteristics and learning requirements. For example, the requirement "10 years old, rural area, arithmetic and reading / writing at the third grade level" is used as the prompt. Input: Prompt for the generative AI model. Output: Prompt input to the generative AI model.

[1543] Step 5:

[1544] The server uses a generative AI model (e.g., OpenAI's GPT model) to generate learning content based on the input prompt. Specifically, it generates simple math problems or basic reading comprehension questions. Input: The prompt input to the generative AI model. Output: The generated learning content.

[1545] Step 6:

[1546] The server converts the generated learning content into an appropriate format (e.g., HTML, JSON) and sends it to the terminal device. Input: Generated learning content. Output: Content converted into an appropriate format and its transmission.

[1547] Step 7:

[1548] The terminal device displays the received learning content on the user interface. The user browses this content and begins learning. Input: Received learning content. Output: Learning content displayed to the user.

[1549] Step 8:

[1550] The user engages with the learning content and answers or performs operations. Specifically, they solve displayed math problems or enter answers to reading comprehension questions. Input: User operations and answers. Output: Progress data of learning activities.

[1551] Step 9:

[1552] The terminal device collects the user's learning progress information in real time. The collected data includes the percentage of correct answers to questions and the time it took to answer them. Input: User's learning activity. Output: Collected progress data.

[1553] Step 10:

[1554] The terminal device sends the collected progress data to the server. Input: Collected progress data. Output: Progress data sent to the server.

[1555] Step 11:

[1556] The server analyzes the received progress information and evaluates the user's level of understanding. It identifies areas of strength and weakness. Input: Submitted progress data. Output: Analyzed level of understanding information.

[1557] Step 12:

[1558] The server provides the generative AI model with a prompt to generate the next learning content based on the progress data. For example, the next prompt is generated based on the evaluation that "the user is struggling with fraction problems." Input: Analyzed comprehension information. Output: Prompt to input to the generative AI model.

[1559] Step 13:

[1560] The server uses the generative AI model to generate new learning content. For example, new problems covering everything from the basics to advanced fractions are generated. Input: The prompt entered into the generative AI model. Output: New learning content.

[1561] Step 14:

[1562] The server sends the generated new learning content to the terminal device, which displays it. Input: The generated new learning content. Output: The new content displayed on the terminal device.

[1563] Step 15:

[1564] The user starts learning again with new learning content. Progress data is collected, sent, and analyzed in the same way. Input: Learning content to be re-engaged. Output: New progress data.

[1565] Step 16:

[1566] The server accumulates all the learning data sent by users and stores it in the learning history database. Input: Sent learning data. Output: Accumulated data.

[1567] Step 17:

[1568] The server trains the generative AI based on the accumulated data and updates the generative AI model, improving the accuracy of the AI ​​model. Input: Accumulated data. Output: New trained AI model.

[1569] Step 18:

[1570] The server generates new learning content using the updated generative AI model and sends it to the terminal device. Input: The trained new AI model. Output: The generated new learning content.

[1571] Step 19:

[1572] The terminal device displays the latest learning content on the user interface, allowing the user to continue learning. Input: Generated new learning content. Output: The latest learning content displayed to the user.

[1573] In this way, this system provides learning content that is individually optimized according to the learner's progress, supporting effective education. It efficiently manages the accumulation of learning data and the training of the generated AI, enabling continuous improvement of the accuracy of the AI ​​model.

[1574] (Application example 1)

[1575] 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."

[1576] For the poorest people, breaking the cycle of poverty through education is important, but the educational resources and opportunities they can access are extremely limited. Furthermore, there are no effective ways to link education with support activities such as food delivery. Furthermore, there is a need for the automatic generation and provision of educational content based on progress. There is a need to solve these problems and provide an effective educational support system for the poorest people.

[1577] 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.

[1578] In this invention, the server includes: means for inputting basic information about the learner and transmitting the basic information to the server; means for the server to generate optimal learning content for the learner using a generation AI; means for transmitting the generated learning content to the learner's device and displaying it; means for collecting progress information about the learner and transmitting the progress information to the server; means for the server to evaluate the learner's level of understanding based on the progress information and generate subsequent learning content; means for storing the learner's learning data in the server; means for training the generation AI based on the stored data and updating the AI ​​model; and means for transmitting the learning content generated using the updated AI model to the learner's device and displaying it. This makes it possible to provide optimal educational content tailored to the progress of learners from the poorest backgrounds, thereby effectively supporting efforts to break the cycle of poverty through education.

[1579] "Basic information about the learner" refers to personal information such as the learner's age, education level, and area of ​​residence.

[1580] The "server" is a system that receives basic information and progress information about learners, processes and analyzes it, and generates learning content using generation AI.

[1581] "Generative AI" is artificial intelligence that automatically generates optimal learning content based on a learner's basic information and progress information.

[1582] "Learning content" refers to educational materials such as teaching materials and problem sets that are used by learners to receive education.

[1583] "Device" means a device such as a smartphone, smart glasses, or head-mounted display that a learner uses to receive and view learning content.

[1584] "Progress information" is data that indicates the learner's learning progress and level of understanding.

[1585] "Level of understanding" is an indicator that shows how well a learner has understood the learning content provided.

[1586] "Learning data" refers to a series of data related to learning, such as basic information about the learner, progress information, and learning history.

[1587] An "updated AI model" is a generative AI model that has been retrained based on the learning data stored on the server.

[1588] The "poorest" are the most economically disadvantaged social groups, those who lack access to basic needs and education.

[1589] "Food assistance" refers to support services such as food and meals provided to the poorest people.

[1590] A "smart device" is an electronic device that allows learners to receive learning content and learn interactively.

[1591] The present invention is a system that aims to provide the poorest people with the minimum education necessary to break the cycle of poverty. This system consists of the following steps:

[1592] Hardware and software configuration

[1593] This system includes a terminal for inputting learner information, a server for utilizing the generative AI, and a smart device for displaying learning content. Specifically, the following hardware and software are used:

[1594] Devices: Smartphones, smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest)

[1595] Server: Cloud server (e.g. AWS)

[1596] Software: Custom applications (for Android / iOS), AI models (e.g., GPT-4)

[1597] Program processing explanation

[1598] 1. Enter and submit basic student information

[1599] The user accesses the terminal and enters basic information such as the learner's name, age, education level, and area of ​​residence, which is then sent to the server.

[1600] Example: A user launches an application and enters information such as "10 years old," "can read and write basic words," and "lives in a rural area."

[1601] 2. Creation and provision of learning content

[1602] The server uses the generative AI model based on the received basic information to generate optimal learning content for the learner, which is then sent to the device and displayed to the user.

[1603] Example: For a 10-year-old learner, basic math problems and reading and writing exercises are generated.

[1604] Example prompt: Generate educational content on nutrition and basic math for a 10-year-old user living in a rural area who can read and write at a basic level.

[1605] 3. Feedback on learning status and generation of next content

[1606] The device collects the user's learning progress information and sends it to the server, which analyzes the progress data and adjusts and generates the next learning content.

[1607] Example: Identify areas where the user is weak, assess their level of understanding, and automatically generate the most appropriate next learning content.

[1608] 4. Data accumulation and generation AI training

[1609] The server stores all the learning data sent by users and uses it to train the AI ​​model, which is periodically updated and retrained on new datasets.

[1610] Example: Updating AI models with newly collected data improves the accuracy of learning content.

[1611] Overall flow

[1612] By repeating this process, it is possible to continue providing effective education to the poorest learners. Furthermore, by integrating food assistance and education, this system will realize more practical and effective support. For example, it is possible to design a system that links with food delivery services so that educational content is provided at the same time as food is delivered.

[1613] In this way, the present invention can provide a practical and sustainable educational support system to break the cycle of poverty.

[1614] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1615] Step 1:

[1616] Users access their devices and enter basic information such as their name, age, education level, and area of ​​residence. This basic information is sent as input data to the server, which analyzes the received data and generates a basic profile of the learner. Specific operations involve the user answering a series of questions using an app on their smartphone or smart device.

[1617] Step 2:

[1618] The server uses a generative AI model based on the received basic information to generate optimal learning content for the learner. Here, the input data is the learner's basic information, and the output data is the generated learning content. The generative AI model uses a prompt sentence based on the input data to launch a text generation algorithm (e.g., GPT-4) to generate appropriate learning content. Specifically, the AI ​​engine in the server operates and generates learning materials based on the specified prompt sentence.

[1619] Step 3:

[1620] The generated learning content is sent from the server to the terminal. The terminal receives this learning content and displays it to the user. The input data here is the generated learning content, and the output data is the learning content reflected on the user's display screen. Specifically, the new educational content is displayed to the user through the notification function.

[1621] Step 4:

[1622] The user studies the displayed learning content. During the learning process, the user's answers and activity log are automatically recorded. The input data is the user's learning behavior, and the output data is learning progress information. Specific operations include answer input and progress recording via a touch screen or input interface.

[1623] Step 5:

[1624] The device collects the user's learning progress information and sends this data to the server. The input data is the user's learning progress information, and the output data is the progress log sent to the server. Specifically, the progress data is automatically uploaded at specified intervals or for each event.

[1625] Step 6:

[1626] Based on the received learning progress information, the server uses a generative AI model to adjust and generate the next learning content. Here, the input data is the received learning progress information, and the output data is the newly generated learning content. Specifically, an analytical algorithm runs within the server, automatically generating learning materials appropriate for the next step based on the progress data.

[1627] Step 7:

[1628] All of a learner's learning data is stored on the server. The input data is past and current learning progress data, and the output data is the accumulated learning history. Specifically, data is continuously added to the server's database, and backups and database compression are performed as necessary.

[1629] Step 8:

[1630] The server trains and updates the generative AI model based on the accumulated data. The input data is the accumulated training data, and the output data is the updated generative AI model. Specifically, the machine learning algorithm runs using the new data set, and re-training is performed to improve the accuracy of the model.

[1631] Step 9:

[1632] New learning content is generated using the updated generative AI model. The generated learning content is then sent back to the device and displayed to the user. The input data is the updated generative AI model and a request for new learning content, and the output data is the latest generated learning content. Specifically, the new AI model is applied, and optimal content for the user is regenerated and displayed.

[1633] 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.

[1634] The present invention is a system designed to provide the poorest people with a basic education and break the cycle of poverty. The system includes a means for inputting basic information about a learner and transmitting the basic information to a server, a means for the server to generate optimal learning content for the learner using a generation AI, and a means for transmitting the generated learning content to the learner's device and displaying it. The system also includes a means for collecting progress information about the learner and transmitting the progress information to the server, and a means for the server to evaluate the learner's level of understanding based on the progress information and adjust the next learning content. The system also includes a means for storing the learner's learning data on the server, training the generation AI based on the stored data, and updating the AI ​​model.

[1635] In addition, the present invention includes an emotion engine that recognizes the learner's emotions, and the emotion engine has a means for analyzing the learner's emotions and transmitting the information to the server. Based on the emotion information, the server also has a means for adjusting the difficulty and type of learning content and generating appropriate encouraging and advice messages.

[1636] Explanation of program processing

[1637] 1. Enter and submit basic student information

[1638] A user accesses a terminal and enters basic information such as age, educational level, and area of ​​residence. For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[1639] The device sends the basic information entered to the server, which then understands the learner's background and is ready to generate optimal learning content.

[1640] 2. Creation and provision of learning content

[1641] Based on the basic information received by the server, the system uses generative AI to generate learning content that is optimal for the learner. For example, for a 10-year-old learner, basic math problems and reading and writing practice questions are generated.

[1642] The server transmits the generated learning content to the terminal, so that the terminal can receive the appropriate educational material.

[1643] The terminal displays the transmitted learning content to the user, and the user starts learning using it, for example, by starting to solve problems displayed on the terminal.

[1644] 3. Feedback on learning status and generation of next content

[1645] The device collects information on the user's learning progress, specifically recording the percentage of correct answers and the time it takes to answer in real time.

[1646] The device sends learning progress data to the server, which then analyzes the data, for example, to identify areas in which the user has difficulty and evaluate the user's level of understanding.

[1647] The server adjusts the next learning content based on the progress data, and the AI ​​generates appropriate learning content, providing the next content that matches the learner's level.

[1648] The server transmits the tailored learning content to the terminal, which displays it.

[1649] 4. Implementing the Emotion Engine

[1650] The emotion engine evaluates the user's emotions from their facial expressions and voice and sends the data to the server. For example, it detects the user's emotional state, such as whether they are easily tired or excited while studying.

[1651] The server receives emotional information and adjusts the difficulty and type of learning content based on that information. For example, if the user is tired, the questions are switched to easier questions.

[1652] The server generates encouraging and advice messages based on the emotional information and sends them to the device. For example, when the user is about to give up, it displays a message such as "You're almost there, keep trying!"

[1653] 5. Data accumulation and generation AI training

[1654] The server accumulates learning data and emotion data collected from users and stores the learning history in a database. The accumulated data is used to train the AI ​​model.

[1655] The server trains the generative AI based on the accumulated data and updates the AI ​​model, which allows it to be retrained using new data sets and improve the accuracy of the algorithm.

[1656] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[1657] For example, when a user first uses the system, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As progress and emotional information is accumulated, the server uses generative AI to provide a succession of problems and learning materials adjusted to the appropriate level of difficulty. By repeating this process, learners can receive an effective education and acquire the skills to break the cycle of poverty.

[1658] The processing flow will be explained below.

[1659] Step 1:

[1660] A user accesses a terminal and enters basic information (age, education level, area of ​​residence, etc.). For example, a user starts an application and enters information such as "10 years old," "can read and write basic information," and "lives in a rural area."

[1661] Step 2:

[1662] The device sends the basic information entered to the server, and the device sends the input data to the server via the API.

[1663] Step 3:

[1664] The server receives the user's basic information and generates optimal learning content using a generation AI. The server accesses a database, customizes the learning content based on the specified parameters, and passes it to the generation AI to generate the learning content.

[1665] Step 4:

[1666] The server sends the generated learning content to the device. The server sends data via API to return the generated results to the device.

[1667] Step 5:

[1668] The device displays the learning content to the user. The device app displays the received data on the user interface, and the user begins learning.

[1669] Step 6:

[1670] The emotion engine analyzes the user's facial expressions and voice to collect emotion data. For example, it uses the device's camera and microphone to analyze facial expressions and tone of voice to collect emotion data.

[1671] Step 7:

[1672] The device sends emotional data to the server. The collected emotional data is sent to the server in real time.

[1673] Step 8:

[1674] Users use learning content to solve problems and advance their studies. Every time a problem is solved, progress information (correct answer rate, answer time, etc.) is recorded on the device in real time.

[1675] Step 9:

[1676] The device sends the collected learning progress information to the server. The progress data is sent to the server every time learning is completed or at a specific timing.

[1677] Step 10:

[1678] The server analyzes the progress information and emotion data to evaluate the user's understanding and emotion state. The server uses a data analysis module to analyze the received progress information and emotion data to measure the user's state.

[1679] Step 11:

[1680] The server adjusts the next learning content based on the user's level of understanding and emotional data. For example, if the user is tired, it switches to questions that are easier to answer, and if the user is excited, it increases the difficulty level.

[1681] Step 12:

[1682] The server generates tailored learning content using a generative AI and sends the generated content to the device.

[1683] Step 13:

[1684] The terminal displays the new learning content to the user. The terminal displays the received updated learning content again on the user interface, allowing the user to continue learning.

[1685] Step 14:

[1686] The server generates messages of encouragement and advice and sends them to the device. Based on the emotion data, it generates messages such as "You're doing well, try a little harder!" and sends them to the device.

[1687] Step 15:

[1688] The device displays encouraging and advice messages to the user. The device displays messages on the user interface to improve the user's motivation.

[1689] Step 16:

[1690] The server accumulates learning data and emotion data collected from users and stores the learning history in a database, which is used to train the AI ​​model.

[1691] Step 17:

[1692] The server trains the generation AI based on the accumulated data and updates the AI ​​model. The AI ​​model trained based on new data is used to improve the accuracy of the algorithm.

[1693] Step 18:

[1694] The server uses the updated AI model to generate new learning content and sends it to the device, which then displays the latest learning content to the user, enabling continuous learning.

[1695] By repeating these steps, learners can receive an effective education and gain the ability to break the cycle of poverty.

[1696] Example 2

[1697] 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."

[1698] The problem that this invention aims to solve is to provide effective and efficient education to the poorest learners and break the cycle of poverty. Specifically, the objective is to generate optimal learning content and maximize learners' understanding by taking into account each learner's individual progress and emotional state.

[1699] 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.

[1700] In this invention, the server includes means for inputting basic information about the learner and transmitting the basic information to the server, means for generating optimal learning content for the learner using a generation AI, means for transmitting the generated learning content to the learner's device and displaying it, means for the server to analyze the learner's emotional information, adjust the difficulty of the learning content based on the emotional information, and generate appropriate encouragement and advice, and means for transmitting and displaying messages of encouragement and advice based on the emotional information to the learner's device. This enables effective education tailored to each individual learner, maintains their motivation to learn, and helps them develop the ability to escape poverty.

[1701] "Basic information" refers to information needed to understand the learner's background and situation, such as the learner's age, prerequisite educational level, and area of ​​residence.

[1702] "Learning content" refers to teaching materials and questions that are generated by generative AI based on the learner's basic information and progress information, in order to provide specific educational goals and challenges.

[1703] "Generative AI" is a type of artificial intelligence that uses natural language processing technology to automatically generate educational content that is optimal for learners.

[1704] "Progress information" refers to data such as correct answer rate and answer time obtained as learners progress through their studies using educational content.

[1705] "Emotional information" refers to information about the learner's emotional state during learning, obtained by analyzing the learner's facial expressions and voice.

[1706] "Encouraging and advice messages" are messages that are generated based on the learner's emotional information and contain motivation and guidance to continue learning.

[1707] An "AI model" is a collection of algorithms and structured datasets that a generative AI uses to train it to generate new educational content.

[1708] "Device" refers to an electronic device (e.g., a smartphone or tablet) on which a learner displays learning content and performs learning activities.

[1709] The "server" is a central processing unit that receives and analyzes basic information and progress information sent by learners, and generates and transmits learning content using generation AI.

[1710] The present invention is a system that aims to provide appropriate education to learners from the poorest backgrounds and break the cycle of poverty. This system inputs basic information about learners, generates learning content, collects learning progress information, analyzes emotional information, and regenerates learning content based on this information. Specific embodiments of the present invention are described below.

[1711] First, the device used by the learner is an electronic device such as a smartphone or tablet. The user accesses this device and enters basic information such as age, educational level, and area of ​​residence. For example, the user launches an application and enters information such as "10 years old," "can read and write basic language," and "lives in a rural area." The device then sends this basic information to the server.

[1712] Based on the received basic information, the server uses a generative AI model (e.g., a model using natural language processing technology) to generate learning content that is optimal for the learner. For example, a 10-year-old learner is provided with basic arithmetic problems on addition and subtraction. The generated learning content is sent from the server to the device and displayed on the device.

[1713] As a user studies using learning content, the device records learning progress information (e.g., percentage of correct answers and answer time) in real time. This progress information is sent to a server, which analyzes it to evaluate the learner's level of understanding. For example, if a learner is weak in a particular area, new learning content that focuses on that area can be generated.

[1714] Furthermore, the device is equipped with an emotion engine that evaluates the user's emotional information by analyzing their facial expressions and voice. This emotional information is also sent to the server, which then uses this information to adjust the difficulty and type of learning content. Messages of encouragement and advice based on the user's emotions are also generated and sent to the device. For example, an encouraging message such as "You're almost there, keep going!" may be displayed.

[1715] The server stores the collected learning data and emotion data and uses them to train the generative AI model. The AI ​​model is updated through training, and new data sets are used to improve the accuracy of the generative AI model. The updated AI model generates newly optimized learning content and sends it to the device, allowing learners to study more effectively.

[1716] As a concrete example, when a user uses the system for the first time, they enter basic information and are presented with simple reading, writing, and arithmetic problems. As learning progress and emotional information are accumulated, the server uses the generative AI model to adjust the next learning content. For example, the generative AI model generates optimal learning content using a prompt such as, "Generate beginner-level arithmetic problems suitable for a 10-year-old learner. As prerequisite knowledge, the learner understands basic addition and subtraction. Please adjust the next learning content taking into account the accuracy rate and answer time."

[1717] This system allows learners to receive an education that is tailored to their individual needs and empowers them to break the cycle of poverty.

[1718] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1719] Step 1:

[1720] The user enters basic information into the device.

[1721] The user launches the application and enters basic information such as age, educational level, and area of ​​residence. For example, they might enter items such as "10 years old," "can read and write basic words," and "live in a rural area." This input information will later become the basis for the generative AI to generate learning content.

[1722] Input: User-entered age, education level, and area of ​​residence

[1723] Output: The basic information entered is saved on the device.

[1724] Specific behavior: The user enters the required information into the application's input form and clicks the submit button.

[1725] Step 2:

[1726] The device sends basic information to the server

[1727] The terminal sends the basic information entered by the user to the server. This sending process is performed using, for example, an HTTP POST request.

[1728] Input: Basic information stored on your device

[1729] Output: Basic information sent to the server

[1730] Specific operation: The device sends the user's basic information to the server using an HTTP POST request.

[1731] Step 3:

[1732] The server generates learning content using AI based on basic information

[1733] The server analyzes the received basic information and uses a generative AI model (e.g., a model using natural language processing technology) to generate appropriate learning content. For example, basic arithmetic addition and subtraction problems are generated for a 10-year-old learner.

[1734] Input: Basic information sent to the server

[1735] Output: Generated learning content

[1736] Specific operation: The server uses the generative AI model to input basic information as prompts and generate specific learning content (e.g., math problems). The generated learning content is temporarily stored on the server.

[1737] Step 4:

[1738] The server sends the generated learning content to the device.

[1739] The server sends the generated learning content to the terminal, for example, by returning the content as an HTTP response.

[1740] Input: Generated learning content

[1741] Output: Learning content sent to the device

[1742] Specific operation: The server sends the generated learning content to the device as an HTTP response.

[1743] Step 5:

[1744] The device displays the learning content to the user.

[1745] The device displays the received learning content to the user, who then begins learning using the content.

[1746] Input: Learning content sent to your device

[1747] Output: Learning content displayed on the device display

[1748] Specific operation: The device displays the learning content on the user interface, and the user begins solving the problems.

[1749] Step 6:

[1750] The device collects the user's learning progress information

[1751] The device records the user's learning progress, such as the percentage of correct answers and the time it takes to answer, in real time, allowing the user to understand their learning situation.

[1752] Input: User's answer data (answer time, correct answer rate, etc.)

[1753] Output: Collected learning progress information

[1754] Specific operation: The device collects and stores the user's answer data using sensors and recording functions.

[1755] Step 7:

[1756] The device sends progress data to the server

[1757] The device sends the collected progress data to the server, again using, for example, an HTTP POST request.

[1758] Input: Collected learning progress information

[1759] Output: Progress data sent to the server

[1760] What happens: The device sends the collected progress data to the server using an HTTP POST request.

[1761] Step 8:

[1762] The server analyzes the progress data and generates the next learning content.

[1763] The server uses a generative AI model based on the progress data to generate the next appropriate learning content. For example, if a learner is weak in a particular area, new questions focused on that area will be generated.

[1764] Input: Progress data sent to the server

[1765] Output: Next learning content

[1766] Specific operation: The server analyzes the progress data and uses the generative AI model to generate the next learning content (e.g., subject-specific questions).

[1767] Step 9:

[1768] The server sends the next learning content to the device.

[1769] The server sends the newly generated learning content to the terminal.

[1770] Input: Newly generated learning content

[1771] Output: The next learning content sent to the device

[1772] Specific operation: The server uses the HTTP response to send the newly generated learning content to the device.

[1773] Step 10:

[1774] The device displays the next learning content to the user.

[1775] The terminal displays the newly sent learning content to the user, allowing the user to proceed to the next learning step.

[1776] Input: Next learning content sent to your device

[1777] Output: The next learning content displayed on the device display

[1778] Specific behavior: The device displays the next learning content on the user interface, and the user continues learning.

[1779] Step 11:

[1780] Emotion engine evaluates user emotions

[1781] The emotion engine analyzes the user's facial expressions and voice to assess their emotional state. For example, it uses a camera and microphone to analyze the user's face and voice.

[1782] Input: User's facial expression and voice data

[1783] Output: Evaluated emotion information

[1784] Specific operation: The emotion engine analyzes data obtained from the camera and microphone and generates emotion information.

[1785] Step 12:

[1786] The emotion engine sends the user's emotion information to the server.

[1787] The emotion engine sends the evaluated emotion information to the server, for example, using an HTTP POST request.

[1788] Input: Evaluated emotion information

[1789] Output: Emotion information sent to the server

[1790] Specific operation: The emotion engine sends emotion information to the server using an HTTP POST request.

[1791] Step 13:

[1792] The server adjusts the difficulty and type of learning content based on emotional information.

[1793] The server analyzes the received emotional information and adjusts the difficulty and type of learning content accordingly. For example, if the user is tired, the questions will be switched to easier questions.

[1794] Input: Emotion information sent to the server

[1795] Output: Tailored learning content

[1796] How it works: The server analyzes the emotional information and uses a generative AI model to adjust the content of the learning content.

[1797] Step 14:

[1798] The server generates encouraging and advice messages based on the emotional information.

[1799] The server generates appropriate encouraging and advice messages to motivate students to learn based on the emotional information.

[1800] Input: Emotion information sent to the server

[1801] Output: A message of encouragement or advice

[1802] Specific operation: The server uses a generative AI model to generate encouraging or advice messages from emotional information.

[1803] Step 15:

[1804] The server sends encouraging and advice messages to the device.

[1805] The server generates encouraging and / or helpful messages and sends them to the device.

[1806] Input: A message of encouragement or advice

[1807] Output: Messages of encouragement or advice sent to the terminal.

[1808] Specific operation: The server sends a message of encouragement or advice to the device as an HTTP response.

[1809] Step 16:

[1810] The device displays encouraging or helpful messages to the user.

[1811] The device displays encouraging and helpful messages in the user interface, helping users stay motivated.

[1812] Input: A message of encouragement or advice sent to the device

[1813] Output: Encouraging and helpful messages displayed on the screen

[1814] What it does: Your device will display encouraging or helpful messages as pop-ups or notifications.

[1815] Step 17:

[1816] The server accumulates learning data and trains the generative AI.

[1817] The server accumulates learning data and emotion data collected from users and uses this data to train the generative AI model. Through training, the accuracy and performance of the AI ​​model improves.

[1818] Input: Learning data and emotion data stored on the server

[1819] Output: Updated AI model

[1820] What it does: The server uses the accumulated data to retrain and update the generative AI model.

[1821] Step 18:

[1822] The server uses the updated AI model to generate new learning content.

[1823] The server generates new learning content using the updated AI model, ensuring that the most up-to-date and optimal learning content is always provided.

[1824] Input: Updated AI model

[1825] Output: Newly generated learning content

[1826] Specific operation: The server uses the updated AI model to execute the process of generating new learning content.

[1827] Step 19:

[1828] The server generates new learning content and sends it to the device.

[1829] The server transmits the newly generated learning content to the terminal.

[1830] Input: Newly generated learning content

[1831] Output: Learning content sent to the device

[1832] Specific operation: The server sends new learning content to the device as an HTTP response.

[1833] Step 20:

[1834] The device displays new learning content to the user.

[1835] The terminal displays the newly transmitted learning content to the user.

[1836] Input: Learning content sent to your device

[1837] Output: Learning content displayed on the device display

[1838] Specific behavior: The device displays new learning content in the user interface, and the user continues learning.

[1839] (Application example 2)

[1840] 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."

[1841] Conventional food delivery services have difficulty in proposing meals that take into account the user's food preferences and allergy information, and do not provide personalized services that respond to the user's emotions and physical condition. This has led to the problem that they are not adequately proposing meals that s...

Claims

1. a means for inputting basic information of a learner and transmitting the basic information to a server; A means for the server to use generation AI to generate optimal learning content for learners; a means for transmitting the generated learning content to a learner's terminal and displaying the content; A system including:

2. means for collecting learner progress information and transmitting the progress information to a server; A means for the server to evaluate the learner's understanding based on the progress information and adjust the next learning content; means for transmitting and displaying the tailored learning content on the learner's device; Additionally, the system of claim 1.

3. A means for storing the learning data of the learners in a server; A means to train the generative AI based on the accumulated data and update the AI ​​model; A means for generating new learning content using the updated AI model; and A means for transmitting the generated latest learning content to the learner's terminal and displaying it; Additionally, the system of claim 1.

Images