system

Abstract

Provide a system. A method for collecting learner profile data; means including a generative artificial intelligence model that performs analysis based on the profile data; means for providing an individually optimized learning plan generated by the generative artificial intelligence model; means for collecting progress and feedback on said learning plan; means for analyzing said feedback to optimize said learning plan; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional learning platforms struggled to meet the needs of individual learners and were limited to providing uniform learning content. This made it difficult to identify the optimal learning path tailored to each learner's skills and interests. They also lacked a means to effectively utilize learners' progress and feedback. As a result, learners were unable to find the optimal learning plan for themselves, resulting in reduced learning efficiency. The present invention aims to solve these problems and provide a platform that allows learners to easily find the optimal learning plan. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for collecting learner profile data; means including a generative AI model that performs analysis based on the profile data; means for providing an individually optimized learning plan generated by the generative AI model; means for collecting progress and feedback on the learning plan; and means for analyzing the feedback to optimize the learning plan. Specifically, the system collects profile data including the learner's goals, interests, skill level, and learning style, and analyzes it using a generative AI model to generate and provide an optimized learning plan for the learner, and continuously optimizes the learning plan using the learner's feedback. This allows learners to easily find the learning plan that best suits them and progress efficiently in their studies.

[0006] "Learner Profile Data" is data that details individual characteristics about a learner, such as the learner's goals, interests, skill level, and learning style.

[0007] A "generative artificial intelligence model" is an artificial intelligence model that analyzes input data and generates optimized deliverables or plans.

[0008] "Learning Plan" means a plan of an individually optimized learning path, including the learning materials, courses, and schedule provided to a Learner.

[0009] "Progress" is information that indicates the progress and achievement level of a learner according to the learning plan.

[0010] "Feedback" refers to information, including evaluations, opinions, and suggestions for improvement, provided by a learner upon completing each module of the learning plan.

[0011] "Optimization" is the process of improving and adjusting the learning plan to make it more effective for the learner based on collected feedback and progress. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

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

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model, and optimizes the plans based on feedback.

[0034] User data collection

[0035] A user accesses the learning platform and creates an account. They enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server.

[0036] Data analysis

[0037] The server then passes the received user profile data to a generative AI model for analysis, which then performs a detailed analysis of the learner's learning needs based on their goals, interests, skill level, and learning style.

[0038] Learning plan generation

[0039] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. The learning plan includes recommended learning materials, courses, and schedules. This plan is then sent from the server to the user's device.

[0040] Implementing learning plans and collecting feedback

[0041] The user follows the submitted learning plan, which includes recommended videos, interactive notebook exercises, and a designated schedule. After completing each learning module, the user provides feedback and progress information to the server, including an evaluation of the learning module and progress.

[0042] Feedback analysis and plan optimization

[0043] The server receives feedback from users and passes it to a generative AI model for analysis. The generative AI model optimizes the learning plan based on the collected feedback and provides the next learning plan to the user.

[0044] Examples:

[0045] For example, consider an intermediate learner who is interested in machine learning. If the user enters profile information such as "Intermediate level machine learning student, prefers visual learning," the server passes this information to a generative AI model for analysis. Based on the analysis, the generative AI model might generate a learning plan like this:

[0046] 1. Visually rich tutorial videos

[0047] 2. Interactive notebook exercises

[0048] 3. Weekly Study Schedule

[0049] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress and feedback are sent to the server, the generative AI model analyzes it and provides the next optimized learning plan. This process allows the learner to have a continuously optimized learning experience.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[0053] Step 2:

[0054] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[0055] Step 3:

[0056] The server passes the received user profile data to a generative artificial intelligence model, which analyzes the user profile data to gain a detailed understanding of the user's learning needs.

[0057] Step 4:

[0058] The server generates an individually optimized learning plan based on the results analyzed by the generative AI model, which includes recommended learning materials, courses, and a study schedule.

[0059] Step 5:

[0060] The server sends the generated study plan to the user's device, who then checks the received study plan and begins studying.

[0061] Step 6:

[0062] Users follow a provided learning plan, which involves watching recommended videos, completing interactive notebook exercises, and following a learning schedule.

[0063] Step 7:

[0064] After completing each learning module, the user sends their evaluation and opinions on the learning module and their learning progress as feedback to the server.

[0065] Step 8:

[0066] The server passes the received feedback to a generative artificial intelligence model for further analysis based on the feedback, which enhances understanding of the user's learning experience.

[0067] Step 9:

[0068] The server then optimizes the learning plan based on the analysis results, and the new optimized learning plan incorporates user feedback and is adjusted to be more effective.

[0069] Step 10:

[0070] The server then sends the optimized learning plan to the user's device, where the user begins a new learning activity according to the optimized plan. By repeating this process, the user can continuously obtain an optimized learning experience.

[0071] Example 1

[0072] 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."

[0073] Traditional learning platforms lacked the ability to provide learning plans optimized to individual learners' needs. As a result, learners would proceed to learning content that did not match their goals or skill level, hindering efficient learning. In addition, there was a problem of learners' motivation decreasing because the plan was not re-optimized to properly reflect their learning progress and feedback.

[0074] 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.

[0075] In this invention, the server includes means for collecting user profile data, means including a generative AI model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative AI model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for using generated prompt sentences for analysis, thereby enabling the provision of a learning plan optimized to the learner's individual needs and subsequent re-optimization based on the feedback.

[0076] 1. "User" refers to an individual who accesses the Learning Platform, creates an account, enters profile data and receives a learning plan.

[0077] 2. "Profile Data" refers to data entered by a User, including personal information such as learning goals, interests, skill level, and learning style.

[0078] 3. "Generative AI Model" refers to an artificial intelligence model that analyzes received profile data and generates individually optimized learning plans and prompts.

[0079] 4. “Study Plan” means a written plan containing learning materials, courses, and schedules optimized for a User by a generative AI model.

[0080] 5. "Feedback" means information provided by a User regarding the progress and evaluation of the Study Plan, which is used to subsequently optimize the Study Plan.

[0081] 6. "Prompt" refers to a specific instruction generated for a generative AI model to analyze.

[0082] The present invention relates to a platform that provides a learner with an optimized learning plan. Specific embodiments of the present invention will be described in detail below.

[0083] User data collection

[0084] Users access the learning platform and go through the process of creating an account. Specifically, they enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server. This data collection allows the server to accumulate data based on the user's individual needs.

[0085] Data analysis

[0086] The server passes the received user profile data to the generative AI model for analysis. The generative AI model uses advanced machine learning algorithms to perform a detailed analysis of the user's learning needs based on the user's goals, interests, skill level, and learning style. This analysis prepares data for generating the optimal learning plan for the user. This process also generates a prompt as input to the generative AI model. For example, the generated prompt is, "Please create an intermediate-level machine learning learning plan. Please prefer visual learning and include a weekly schedule."

[0087] Learning plan generation

[0088] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. This plan includes recommended learning materials, courses, and schedules, such as visually rich tutorial videos, interactive notebook exercises, and weekly study schedules. This generated learning plan is then sent to the user's device.

[0089] Implementing learning plans and collecting feedback

[0090] The user follows the submitted learning plan by watching the provided videos, completing exercises in the interactive notebook, and following the specified schedule. The user then sends their learning progress and feedback for each module to the server. The feedback includes an evaluation of the learning module and comments on the difficulty of the module.

[0091] Feedback analysis and plan optimization

[0092] The server passes the feedback received from the user to the generative AI model for analysis. Based on the results of this analysis, the generative AI model optimizes the study plan. The new optimized study plan is then sent back to the user's device. This ensures that the user always receives the optimal study plan that meets their latest learning needs.

[0093] By implementing this system, it becomes possible to provide detailed learning support tailored to the individual needs of users, dramatically improving learning efficiency. In addition, by optimizing plans based on user feedback, learners' motivation is maintained and a sustainable learning environment is provided.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] User profile data collection

[0097] A user accesses the learning platform and creates an account.

[0098] Input: Basic information such as name, email address, and password

[0099] Output: Basic information data sent to the server

[0100] Users then answer questions about their learning goals, interests, skill level, and learning style.

[0101] Input: Learning goals, interests, skill level, learning style

[0102] Output: Profile data sent to the server

[0103] Step 2:

[0104] Data analysis

[0105] The server passes the received user profile data to the generative AI model.

[0106] Input: User profile data

[0107] Output: Data to be analyzed by the generative AI model

[0108] The generative AI model analyzes learners' goals, interests, skill levels, and learning styles to identify the learning needs that best suit the user.

[0109] Input: Data to be analyzed

[0110] Output: Detailed learning needs

[0111] Step 3:

[0112] Generate prompt statement

[0113] The server generates a prompt sentence based on the analysis results of the generative AI model.

[0114] Input: Detailed learning needs

[0115] Output: prompt statement

[0116] For example: "Create a study plan for intermediate-level machine learning. It should favor visual learning and include a weekly schedule."

[0117] Step 4:

[0118] Generate a learning plan

[0119] The server uses a generative AI model to generate an individually optimized learning plan based on the prompt.

[0120] Input: prompt statement

[0121] Output: Personalized learning plan

[0122] The study plan includes recommended study materials, courses, and schedules.

[0123] Step 5:

[0124] Submit your study plan

[0125] The server transmits the generated study plan to the user's terminal.

[0126] Input: Personalized learning plan

[0127] Output: The lesson plan sent to the user's device.

[0128] Step 6:

[0129] Execution of training

[0130] The user proceeds with their studies according to the provided study plan.

[0131] Input: Study Plan

[0132] Output: Training progress

[0133] Specific actions include watching videos, interactive notebook exercises, and studying according to a designated schedule.

[0134] Step 7:

[0135] Providing Feedback

[0136] Users send their learning progress and feedback to the server.

[0137] Input: Learning progress, feedback

[0138] Output: Feedback data sent to the server

[0139] The feedback includes an evaluation of the learning module and comments on the difficulty of the learning.

[0140] Step 8:

[0141] Analyze feedback and optimize plans

[0142] The server passes the received feedback to the generative AI model for analysis.

[0143] Input: Feedback data

[0144] Output: Analysis results

[0145] The generative AI model uses feedback to optimize the learning plan.

[0146] Input: Analysis results

[0147] Output: Optimized study plan

[0148] The optimized study plan is then sent back to the user's device.

[0149] (Application example 1)

[0150] 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."

[0151] Currently, most learning platforms provide uniform learning content, which does not address the individual needs and progress of each learner. In addition, the optimization of learning environments using smartphones has not progressed, making it difficult to effectively provide individually optimized learning plans.

[0152] 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.

[0153] In this invention, the server includes means for collecting learner profile data, means including a generative artificial intelligence model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for providing learning content via a smartphone application. This makes it possible to provide an optimized learning plan for each learner and to continuously optimize it based on the progress and feedback.

[0154] "Learner Profile Data" refers to information about a learner's goals, interests, skill level, and learning style.

[0155] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes collected data and generates an optimized learning plan.

[0156] "Individually Optimized Learning Plan" means a plan that includes learning materials, courses, and schedules customized for each learner.

[0157] "Learning Content" refers collectively to videos, interactive exercises, text materials, etc., provided for users to study.

[0158] "Progress" refers to information that shows the extent and level of achievement that a learner has actually made based on their learning plan.

[0159] "Feedback" refers to the learner's evaluations, comments, and progress on the learning plan.

[0160] "Smartphone application" refers to application software that runs on a smartphone and provides users with optimized learning plans and learning content.

[0161] The present invention is a system that provides an optimized learning plan to a learner and continuously optimizes the plan based on the learner's progress and feedback. Hereinafter, embodiments of the present invention will be described in detail.

[0162] System Overview

[0163] The system includes a server and a user's smartphone. The server is equipped with various software programs to collect profile data, analyze it using a generative AI model, and generate and optimize learning plans. A smartphone application is installed on the user's device to provide learning content and collect feedback.

[0164] Profile Data Collection

[0165] Users first access the smartphone application and create an account. They provide their name, email address, and password, as well as answer questions about their learning goals and interests, current skill level, and learning style. This information is then sent from the user's device to the server.

[0166] Data analysis and learning plan generation

[0167] The server then passes the received profile data to a generative AI model for analysis. The generative AI model analyzes the user's detailed learning needs based on their goals, interests, skill level, and learning style. Based on the results, an individually optimized learning plan is generated. This learning plan, including learning materials, courses, and schedules, is then sent from the server to the user's device.

[0168] Providing learning and collecting feedback

[0169] The user follows the submitted learning plan, including recommended video tutorials and interactive exercises, and progresses according to a specified schedule. After completing each learning module, the user provides feedback and progress information on their learning, including an evaluation of the learning module and progress. This information is sent from the smartphone application to the server.

[0170] Analyze feedback and optimize plans

[0171] The server receives feedback from users and passes it to the generative AI model for analysis. The generative AI model then optimizes the learning plan based on this feedback information and generates a plan for the next learning cycle. This new learning plan is then sent back to the user's device and serves as a guide for progressing through the course.

[0172] Specific examples

[0173] For example, if a user enters profile information such as "I want to learn Python programming at a beginner level," the following learning plan will be generated.

[0174] 1. Video Tutorials to Learn Python Basics

[0175] 2. Interactive coding exercises for beginners

[0176] 3. Daily study schedule

[0177] As the user progresses through the learning process, they provide feedback such as:

[0178] example:

[0179] "I have completed the video tutorial. The video was very easy to understand. I am looking forward to continuing."

[0180] Based on this feedback, the generative AI model analyzes and suggests appropriate coding exercises or new intermediate-level materials as the next learning step, providing users with a continuously optimized learning experience.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] A user accesses a smartphone application and creates an account. Input: Name, email address, password, learning goals, interests, current skill level, and information about learning style. Output: This data is sent to a server, and the user's profile data is stored in a database.

[0184] Step 2:

[0185] The server passes the saved profile data to a generative AI model for analysis. Input: User profile data. Output: The generative AI model generates an optimized learning plan based on the learner's goals, interests, skill level, and learning style. Specifically, the AI ​​model analyzes various learning resources and creates a customized learning plan.

[0186] Step 3:

[0187] The generated learning plan is sent from the server to the user's device. Input: Optimized learning plan. Output: The learning plan is displayed on the user's smartphone application. Specifically, the contents of the plan (learning materials, courses, schedule) are applied to the application interface.

[0188] Step 4:

[0189] The user progresses through the learning process according to the provided learning plan. Input: Learning materials, video tutorials, and interactive exercises included in the learning plan. Output: Completion status of each learning module and user feedback. Specifically, the user works through each learning content and enters their progress and feedback into the application.

[0190] Step 5:

[0191] User feedback and progress information is sent from the smartphone application to the server. Input: User feedback and progress data. Output: Collected by the server and stored in a database. Specifically, the application receives feedback from the user and sends it to the server.

[0192] Step 6:

[0193] The server passes the received feedback data to a generative AI model for reanalysis. Input: User feedback data. Output: A new, optimized learning plan. Specifically, the generative AI model reevaluates the learning plan based on the feedback and suggests appropriate content for the next step.

[0194] Step 7:

[0195] The new study plan is sent back to the user's device. Input: A new, optimized study plan. Output: The plan is updated and displayed on the user's smartphone application. Specifically, the updated plan is reflected in the application interface.

[0196] Through these steps, the system can provide and continuously improve a learning experience that is optimized for each user.

[0197] 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.

[0198] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model and an emotion engine, and optimizes the plans based on feedback.

[0199] User data collection

[0200] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which are then sent to the server. The user also answers questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is then sent from the user's device to the server.

[0201] Data analysis

[0202] The server passes the received user profile data to a generative AI model. The generative AI model analyzes the user profile data to gain a detailed understanding of their learning needs. The server also uses an emotion engine to obtain the user's emotional data. The emotion engine analyzes inputs such as the user's facial expressions and voice to identify their emotional state.

[0203] Emotional Data Integration

[0204] The server integrates the analysis results from the generative AI model with the emotional data from the emotion engine. The generative AI model uses all this data to generate an individually optimized learning plan based on the learner's emotional state. This learning plan includes recommended learning materials, courses, and a study schedule.

[0205] Submitting and executing your learning plan

[0206] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[0207] Learning plan progress and emotional feedback collection

[0208] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback includes the user's emotional state. The emotion engine continuously monitors the user's emotional changes during learning and collects them as feedback.

[0209] Feedback analysis and plan optimization

[0210] The server passes the user's feedback to a generative AI model, which then performs further analysis based on the feedback. The generative AI model analyzes the feedback, including emotional data, and optimizes the learning plan. The new optimized learning plan reflects the user's emotional state and is adjusted to optimize the content.

[0211] Specific examples

[0212] As an example, consider an intermediate learner who is interested in machine learning. If a user enters profile information such as "I'm studying intermediate-level machine learning and I prefer visual learning," the server passes this information to a generative AI model for analysis. The emotion engine monitors the user's emotional state while learning and detects signs of depression or stress.

[0213] Based on the analysis and sentiment data, the generative AI model generates a learning plan that looks like this:

[0214] 1. Visually rich tutorial videos

[0215] 2. Interactive notebook exercises

[0216] 3. Weekly Study Schedule

[0217] 4. Insert relaxation breaks based on the user's emotional state

[0218] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress, feedback, and emotional state are sent to the server, the generative AI model analyzes this and provides the next optimized learning plan. By repeating this process, the user can obtain a continuously optimized learning experience.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[0222] Step 2:

[0223] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[0224] Step 3:

[0225] The server then passes the received user profile data to a generative AI model, which analyzes the user profile data to gain a detailed understanding of their learning needs, forming the basis for generating an optimal learning plan for the user.

[0226] Step 4:

[0227] The server acquires emotional data from the user's device. The emotional data is collected through an emotion engine that analyzes the user's facial expressions and voice. The emotion engine recognizes the user's emotional state (e.g., excitement, stress, concentration, etc.) and transmits this as data to the server.

[0228] Step 5:

[0229] The server combines the results analyzed by the generative AI model with the emotional data from the emotion engine. Based on this, it generates an individually optimized learning plan. This learning plan includes recommended learning materials, courses, and a study schedule. It also adjusts the learning progress and break timing according to the user's emotional state.

[0230] Step 6:

[0231] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[0232] Step 7:

[0233] As the user progresses through the learning plan, the emotion engine continuously monitors the user's emotional state. The emotion engine captures changes in the user's facial expressions and voice, and transmits the emotional data to the server in real time.

[0234] Step 8:

[0235] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback also includes the user's emotional state. The emotional data reflects the user's emotional changes during the learning process.

[0236] Step 9:

[0237] The server passes the received feedback and emotional data to a generative artificial intelligence model for further analysis, which deepens understanding of the user's learning experience and improves the learning plan.

[0238] Step 10:

[0239] The server then optimizes the learning plan based on the analysis results. The new optimized learning plan reflects the user's feedback and emotional state, and is tailored to be more effective and satisfying.

[0240] Step 11:

[0241] The server sends the optimized learning plan to the user's device. The user then begins a new learning activity according to the optimized plan. This allows the user to have a continuously optimized learning experience. By repeating this process, the user's learning efficiency and satisfaction improve.

[0242] Example 2

[0243] 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."

[0244] While conventional learning plan providing systems can generate learning plans based on learner profile information, they are unable to take into account the learner's emotional state. This can lead to learners feeling stressed or their learning progress being hindered. Furthermore, since there is no way to collect learners' emotional state and feedback in real time and optimize the learning plan, it is difficult to provide an optimal learning experience for each individual learner.

[0245] 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.

[0246] In this invention, the server includes means for collecting learner profile data, means including a generative AI model that performs analysis based on the profile data, means for optimizing a study plan using an emotion engine that acquires user emotion data, means for generating an individually optimized study plan based on data obtained from the generative AI model and the emotion engine, means for transmitting the generated study plan to the learner's device, means for collecting progress and feedback on the study plan, and means for analyzing the feedback to further optimize the study plan. This makes it possible to provide an individually optimized study plan that reflects the learner's emotional state.

[0247] "Profile Data" is data that includes information about a learner's goals, interests, skill level, and learning style.

[0248] A "generative artificial intelligence model" is a type of artificial intelligence that can analyze collected profile data and generate individually optimized learning plans.

[0249] The "emotion engine" is an engine for acquiring and analyzing emotional data from the user's facial expressions, voice, etc.

[0250] A "learning plan" is a plan including learning materials, courses, and a learning schedule that is generated based on a learner's profile data and sentiment data.

[0251] "Feedback" is information provided by a learner to the server as progress, evaluation, opinion, and emotional state of the learning plan.

[0252] The "means for optimizing" is a method for analyzing the learning plan based on the collected feedback and generating a new, individually optimized learning plan.

[0253] The present invention is a system that provides an optimized learning plan to a learner. This system collects learner profile data, generates and provides an individually optimized learning plan based on the data using a generative AI model and an emotion engine, and then optimizes the learning plan based on subsequent feedback.

[0254] In this system, users first access the learning platform and create an account. They enter basic information such as their name, email address, and password, which is then sent to the server. They also answer questions about their learning goals, interests, skill level, and learning style to build an individual learning profile. This data is sent from the user's device to the server. Specific hardware used includes personal computers (PCs) and smartphones. Software used is a web browser or mobile application.

[0255] The server then analyzes the received user profile data. This is done using a generative artificial intelligence model. Examples include Google® Cloud AI and OpenAI®. These technologies are used to analyze the user profile data and perform operations to understand their learning needs. The server also uses an emotion engine (e.g., Microsoft® Azure® Emotion API) to acquire and analyze the user's emotional data. The emotion engine collects data such as the user's facial expressions and voice to determine their current emotional state.

[0256] The server integrates data from the generative artificial intelligence model and emotion engine to generate an individually optimized study plan that takes into account the user's emotional state, including recommended study materials, courses, and a study schedule, including breaks as needed.

[0257] The generated learning plan is sent from the server to the user's device. The user then reviews the received learning plan and begins learning. Specifically, the user progresses by watching recommended videos and completing interactive notebook exercises. The progress of the learning plan, feedback, and the user's emotional state are also sent to the server.

[0258] For example, consider a user who is learning intermediate-level machine learning and prefers visual learning. The user enters the following prompt into the learning platform: "I am learning intermediate-level machine learning and prefer visual learning." The server passes this information to the generative AI model for analysis. The emotion engine monitors the user for signs of stress or depression while learning. Finally, the generative AI model proposes an optimized learning plan, such as:

[0259] 1. Visually rich tutorial videos

[0260] 2. Interactive Notebook Exercises

[0261] 3. Weekly Study Schedule

[0262] 4. Appropriate break times based on the user's emotional state

[0263] This allows the user to continue following the learning plan and obtain an optimal learning experience according to their emotional state. After the learning plan is executed, the server receives user feedback again, which is analyzed by the generative AI model to further optimize the learning plan.

[0264] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0265] Step 1: Collecting user profile data

[0266] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which is then sent to the server. The user also answers questions about their learning goals, interests, skill level, and learning style. The entered information is then sent from the user's device to the server. This input data includes user information and learning profile information.

[0267] Specific behavior:

[0268] The user opens the registration page on their device and enters their name, email address, and password.

[0269] Answer study questions and enter your profile data.

[0270] Click the Send all data button to send it to the server.

[0271] Step 2: Receiving and storing your profile data

[0272] The server receives the user's profile data and stores it in a database, making the user's profile available for future study plan generation.

[0273] Specific behavior:

[0274] The server receives the transmitted data.

[0275] The received data is stored in a database.

[0276] Input: User profile data

[0277] Output: Profile information stored in a database

[0278] Step 3: Analyzing the generative AI model

[0279] The server retrieves the user's profile data from the database and passes it to the generative AI model. The generative AI model analyzes the user's profile data to gain a detailed understanding of their learning needs. Through this process, the generative AI model obtains the basic data necessary to generate a learning plan.

[0280] Specific behavior:

[0281] The server retrieves the user's profile data from the database.

[0282] The acquired data is input into a generative artificial intelligence model.

[0283] A generative AI model analyzes the data and identifies learning needs.

[0284] Input: User profile data retrieved from the database

[0285] Output: Analysis results (learning needs)

[0286] Step 4: Obtaining emotion data

[0287] The server uses an emotion engine to acquire the user's emotion data. The emotion engine analyzes the user's facial and voice data to identify the user's current emotional state. This allows the collected emotion data to be used to optimize the learning plan.

[0288] Specific behavior:

[0289] The user's device collects data from the camera and microphone.

[0290] The collected data is sent to a server.

[0291] The server passes the data to the emotion engine for emotion analysis.

[0292] Input: User facial and voice data

[0293] Output: Analysis results (emotional state)

[0294] Step 5: Generate a learning plan

[0295] The server integrates the analysis results from the generative AI model and the emotional data from the emotion engine. The generative AI model uses this data to generate an individually optimized learning plan, which includes learning materials, courses, and a learning schedule.

[0296] Specific behavior:

[0297] A generative AI model integrates analytical results with emotional data.

[0298] Generate an optimized study plan.

[0299] Input: Analysis results (learning needs), emotional data

[0300] Output: Personalized learning plan

[0301] Step 6: Submit and execute your learning plan

[0302] The server then sends the generated learning plan to the user's device, where the user can review the plan and begin learning, including watching recommended videos and completing interactive notebook exercises.

[0303] Specific behavior:

[0304] The server transmits the generated learning plan to the user's terminal.

[0305] The user checks the received learning plan and progresses with the learning.

[0306] Input: Personalized learning plan

[0307] Output: The lesson plan displayed on the user's device

[0308] Step 7: Progress and feedback gathering

[0309] After completing each learning module, the user sends feedback to the server, including their evaluation of the learning plan, their opinion, and their emotional state. The emotion engine continuously monitors the user's emotional state during learning and sends it as feedback.

[0310] Specific behavior:

[0311] A user completes a learning module and provides feedback.

[0312] An emotion engine monitors the user's emotional state.

[0313] Send data including the feedback to the server.

[0314] Input: Feedback after completing the learning module, emotional state

[0315] Output: Feedback data sent to the server

[0316] Step 8: Analyze feedback and optimize your plan

[0317] The server passes the received feedback to the generative AI model for analysis, which then further optimizes the learning plan based on the feedback data and generates a new learning plan.

[0318] Specific behavior:

[0319] The server sends the feedback data to the generative AI model.

[0320] A generative AI model analyzes the feedback data and generates a new learning plan.

[0321] Input: Feedback data

[0322] Output: A new, optimized study plan

[0323] This allows users to always be provided with a study plan that is optimized for their emotional state and learning needs, allowing them to continue studying effectively and with less stress.

[0324] (Application example 2)

[0325] 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."

[0326] Conventional learning platforms face the challenge of providing optimal learning plans that take into account the needs and emotional state of individual learners. Furthermore, they lack the means to properly analyze feedback obtained during learning and quickly optimize learning plans. This makes it difficult for learners to consistently achieve optimal learning outcomes.

[0327] The identification processing 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 collecting attribute data of learners, means including a generative artificial intelligence model that performs analysis based on the attribute data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and responses to the learning plan, means for analyzing the responses and optimizing the learning plan, and means for transmitting the optimized learning plan to a terminal. This makes it possible to provide an optimal learning plan that corresponds to the individual needs and emotional state of the learner, and to quickly optimize the plan based on continuous feedback.

[0328] "Learner demographic data" refers to individual information about a learner, such as the learner's goals, interests, ability level, and learning methods.

[0329] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes a user's profile data and generates an optimized learning plan.

[0330] "Learning Plan" means a plan containing optimized learning materials, courses, and schedules provided to a Learner.

[0331] "Progress" refers to the progress a learner makes as they progress through their studies according to their learning plan.

[0332] "Responses" refers to feedback collected from learners and data that indicates their emotional state during learning.

[0333] "Optimization" refers to improving the learning plan based on the feedback and reactions collected and adjusting it to be most effective for the learner.

[0334] "Terminal" refers to the device used by a learner to receive the learning plan and carry out the learning.

[0335] "Means of collection" refers to the methods and techniques used to collect information such as learner demographic data and responses.

[0336] "Means for providing" refers to the methods and techniques for presenting the generated lesson plan to the learner.

[0337] "Means for transmitting" refers to the method or technology for transmitting the optimized learning plan to the learner's terminal.

[0338] This invention is a system that generates an optimized learning plan based on learner attribute data and optimizes the plan in real time through feedback. This system is mainly composed of a server, a terminal, and a user, and is implemented in the following form.

[0339] System configuration and operation

[0340] server

[0341] The server is responsible for collecting learner attribute data and analyzing it using a generative artificial intelligence model. The server uses the following hardware and software:

[0342] Hardware: High-performance data server

[0343] Software: Python, Flask (server side), generative AI model, emotion engine

[0344] The server collects and analyzes learner attribute data such as the learner's name, email address, goals, interests, ability level, and learning method. It also uses an emotion engine to identify the learner's emotional state and analyzes the learner's facial and voice data in real time.

[0345] The server integrates this data and uses a generative artificial intelligence model to generate an individually optimized learning plan, which it then sends to the device.

[0346] Terminal

[0347] The terminal is the device through which the user receives and executes the lesson plan. It uses the following hardware and software:

[0348] Hardware: Smartphones, tablets, computers

[0349] Software: React Native (mobile app), Web Browser (desktop app)

[0350] The device receives the study plan sent from the server and presents it to the user, which includes visually rich study materials, an interactive notebook, and a study schedule.

[0351] User

[0352] The user follows a learning plan. Examples of specific prompts include:

[0353] The user's name is Taro Yamada and his email address is taro@example.com.

[0354] He wants to learn intermediate level machine learning to become an AI engineer.

[0355] My areas of interest are machine learning and deep learning, and I prefer visually rich teaching materials.

[0356] Generate a study plan that best suits his profile.

[0357] The user studies based on the study plan, collects the progress and reactions of the study, and provides feedback to the server, including the user's emotional state and satisfaction with the study.

[0358] The server reanalyzes the learning plan using a generative artificial intelligence model based on user feedback, optimizes the learning plan in real time, and sends the optimized learning plan back to the terminal.

[0359] By repeating this process, users can have a continually optimized learning experience.

[0360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0361] Step 1:

[0362] Collect learner attribute data. A user uses a device to access the learning platform and create an account. The user enters information such as their name, email address, goals, interests, ability level, and learning method. The device sends this data to the server. Input data: Learner's basic information, learning goals, interests, skill level, and learning style. Output data: Learner attribute data sent to the server.

[0363] Step 2:

[0364] The collected attribute data is analyzed. The server passes the received learner attribute data to a generative AI model for analysis. The generative AI model uses this data to perform a detailed analysis of the learner's needs. Input data: learner attribute data. Output data: analysis results related to the learner's needs.

[0365] Step 3:

[0366] Obtain the learner's emotional state. The server uses an emotion engine to analyze the learner's facial and voice data to identify the learner's emotional state. Input data: Data on the learner's facial and voice data. Output data: Data on the learner's emotional state.

[0367] Step 4:

[0368] Generates an optimized learning plan. The server integrates data obtained from the generative AI model and the emotion engine to generate an individually optimized learning plan based on the learner's attributes and emotional state. Input data: Analysis results regarding the learner's needs and emotional state data. Output data: Optimized learning plan.

[0369] Step 5:

[0370] The server provides the learning plan. The server sends the generated learning plan to the user's device and presents it to the user. Input data: Optimized learning plan. Output data: Learning plan sent to the device.

[0371] Step 6:

[0372] The learning progress and reactions are collected. The user proceeds with the learning according to the learning plan and feeds back the progress and reactions to the server via the terminal. Input data: User's progress and reactions. Output data: Progress and reaction data sent to the server.

[0373] Step 7:

[0374] Analyze and optimize based on feedback. The server collects feedback from users and passes it to the generative AI model for reanalysis. The server optimizes the learning plan based on the feedback and generates an updated learning plan. Input data: User progress and response data. Output data: New optimized learning plan.

[0375] Step 8:

[0376] Update the optimized learning plan. The server sends the new optimized learning plan to the user's device and presents it again. The user continues learning based on the new learning plan. By repeating this process, the user receives a continuously optimized learning experience. Input data: New optimized learning plan. Output data: New learning plan sent to the device.

[0377] 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.

[0378] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0379] 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.

[0380] [Second embodiment]

[0381] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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).

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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."

[0393] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model, and optimizes the plans based on feedback.

[0394] User data collection

[0395] A user accesses the learning platform and creates an account. They enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server.

[0396] Data analysis

[0397] The server then passes the received user profile data to a generative AI model for analysis, which then performs a detailed analysis of the learner's learning needs based on their goals, interests, skill level, and learning style.

[0398] Learning plan generation

[0399] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. The learning plan includes recommended learning materials, courses, and schedules. This plan is then sent from the server to the user's device.

[0400] Implementing learning plans and collecting feedback

[0401] The user follows the submitted learning plan, which includes recommended videos, interactive notebook exercises, and a designated schedule. After completing each learning module, the user provides feedback and progress information to the server, including an evaluation of the learning module and progress.

[0402] Feedback analysis and plan optimization

[0403] The server receives feedback from users and passes it to a generative AI model for analysis. The generative AI model optimizes the learning plan based on the collected feedback and provides the next learning plan to the user.

[0404] Examples:

[0405] For example, consider an intermediate learner who is interested in machine learning. If the user enters profile information such as "Intermediate level machine learning student, prefers visual learning," the server passes this information to a generative AI model for analysis. Based on the analysis, the generative AI model might generate a learning plan like this:

[0406] 1. Visually rich tutorial videos

[0407] 2. Interactive notebook exercises

[0408] 3. Weekly Study Schedule

[0409] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress and feedback are sent to the server, the generative AI model analyzes it and provides the next optimized learning plan. This process allows the learner to have a continuously optimized learning experience.

[0410] The processing flow will be explained below.

[0411] Step 1:

[0412] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[0413] Step 2:

[0414] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[0415] Step 3:

[0416] The server passes the received user profile data to a generative artificial intelligence model, which analyzes the user profile data to gain a detailed understanding of the user's learning needs.

[0417] Step 4:

[0418] The server generates an individually optimized learning plan based on the results analyzed by the generative AI model, which includes recommended learning materials, courses, and a study schedule.

[0419] Step 5:

[0420] The server sends the generated study plan to the user's device, who then checks the received study plan and begins studying.

[0421] Step 6:

[0422] Users follow a provided learning plan, which involves watching recommended videos, completing interactive notebook exercises, and following a learning schedule.

[0423] Step 7:

[0424] After completing each learning module, the user sends their evaluation and opinions on the learning module and their learning progress as feedback to the server.

[0425] Step 8:

[0426] The server passes the received feedback to a generative artificial intelligence model for further analysis based on the feedback, which enhances understanding of the user's learning experience.

[0427] Step 9:

[0428] The server then optimizes the learning plan based on the analysis results, and the new optimized learning plan incorporates user feedback and is adjusted to be more effective.

[0429] Step 10:

[0430] The server then sends the optimized learning plan to the user's device, where the user begins a new learning activity according to the optimized plan. By repeating this process, the user can continuously obtain an optimized learning experience.

[0431] Example 1

[0432] 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."

[0433] Traditional learning platforms lacked the ability to provide learning plans optimized to individual learners' needs. As a result, learners would proceed to learning content that did not match their goals or skill level, hindering efficient learning. In addition, there was a problem of learners' motivation decreasing because the plan was not re-optimized to properly reflect their learning progress and feedback.

[0434] 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.

[0435] In this invention, the server includes means for collecting user profile data, means including a generative AI model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative AI model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for using generated prompt sentences for analysis, thereby enabling the provision of a learning plan optimized to the learner's individual needs and subsequent re-optimization based on the feedback.

[0436] 1. "User" refers to an individual who accesses the Learning Platform, creates an account, enters profile data and receives a learning plan.

[0437] 2. "Profile Data" refers to data entered by a User, including personal information such as learning goals, interests, skill level, and learning style.

[0438] 3. "Generative AI Model" refers to an artificial intelligence model that analyzes received profile data and generates individually optimized learning plans and prompts.

[0439] 4. “Study Plan” means a written plan containing learning materials, courses, and schedules optimized for a User by a generative AI model.

[0440] 5. "Feedback" means information provided by a User regarding the progress and evaluation of the Study Plan, which is used to subsequently optimize the Study Plan.

[0441] 6. "Prompt" refers to a specific instruction generated for a generative AI model to analyze.

[0442] The present invention relates to a platform that provides a learner with an optimized learning plan. Specific embodiments of the present invention will be described in detail below.

[0443] User data collection

[0444] Users access the learning platform and go through the process of creating an account. Specifically, they enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server. This data collection allows the server to accumulate data based on the user's individual needs.

[0445] Data analysis

[0446] The server passes the received user profile data to the generative AI model for analysis. The generative AI model uses advanced machine learning algorithms to perform a detailed analysis of the user's learning needs based on the user's goals, interests, skill level, and learning style. This analysis prepares data for generating the optimal learning plan for the user. This process also generates a prompt as input to the generative AI model. For example, the generated prompt is, "Please create an intermediate-level machine learning learning plan. Please prefer visual learning and include a weekly schedule."

[0447] Learning plan generation

[0448] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. This plan includes recommended learning materials, courses, and schedules, such as visually rich tutorial videos, interactive notebook exercises, and weekly study schedules. This generated learning plan is then sent to the user's device.

[0449] Implementing learning plans and collecting feedback

[0450] The user follows the submitted learning plan by watching the provided videos, completing exercises in the interactive notebook, and following the specified schedule. The user then sends their learning progress and feedback for each module to the server. The feedback includes an evaluation of the learning module and comments on the difficulty of the module.

[0451] Feedback analysis and plan optimization

[0452] The server passes the feedback received from the user to the generative AI model for analysis. Based on the results of this analysis, the generative AI model optimizes the study plan. The new optimized study plan is then sent back to the user's device. This ensures that the user always receives the optimal study plan that meets their latest learning needs.

[0453] By implementing this system, it becomes possible to provide detailed learning support tailored to the individual needs of users, dramatically improving learning efficiency. In addition, by optimizing plans based on user feedback, learners' motivation is maintained and a sustainable learning environment is provided.

[0454] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0455] Step 1:

[0456] User profile data collection

[0457] A user accesses the learning platform and creates an account.

[0458] Input: Basic information such as name, email address, and password

[0459] Output: Basic information data sent to the server

[0460] Users then answer questions about their learning goals, interests, skill level, and learning style.

[0461] Input: Learning goals, interests, skill level, learning style

[0462] Output: Profile data sent to the server

[0463] Step 2:

[0464] Data analysis

[0465] The server passes the received user profile data to the generative AI model.

[0466] Input: User profile data

[0467] Output: Data to be analyzed by the generative AI model

[0468] The generative AI model analyzes learners' goals, interests, skill levels, and learning styles to identify the learning needs that best suit the user.

[0469] Input: Data to be analyzed

[0470] Output: Detailed learning needs

[0471] Step 3:

[0472] Generate prompt statement

[0473] The server generates a prompt sentence based on the analysis results of the generative AI model.

[0474] Input: Detailed learning needs

[0475] Output: prompt statement

[0476] For example: "Create a study plan for intermediate-level machine learning. It should favor visual learning and include a weekly schedule."

[0477] Step 4:

[0478] Generate a learning plan

[0479] The server uses a generative AI model to generate an individually optimized learning plan based on the prompt.

[0480] Input: prompt statement

[0481] Output: Personalized learning plan

[0482] The study plan includes recommended study materials, courses, and schedules.

[0483] Step 5:

[0484] Submit your study plan

[0485] The server transmits the generated study plan to the user's terminal.

[0486] Input: Personalized learning plan

[0487] Output: The lesson plan sent to the user's device.

[0488] Step 6:

[0489] Execution of training

[0490] The user proceeds with their studies according to the provided study plan.

[0491] Input: Study Plan

[0492] Output: Training progress

[0493] Specific actions include watching videos, interactive notebook exercises, and studying according to a designated schedule.

[0494] Step 7:

[0495] Providing Feedback

[0496] Users send their learning progress and feedback to the server.

[0497] Input: Learning progress, feedback

[0498] Output: Feedback data sent to the server

[0499] The feedback includes an evaluation of the learning module and comments on the difficulty of the learning.

[0500] Step 8:

[0501] Analyze feedback and optimize plans

[0502] The server passes the received feedback to the generative AI model for analysis.

[0503] Input: Feedback data

[0504] Output: Analysis results

[0505] The generative AI model uses feedback to optimize the learning plan.

[0506] Input: Analysis results

[0507] Output: Optimized study plan

[0508] The optimized study plan is then sent back to the user's device.

[0509] (Application example 1)

[0510] 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."

[0511] Currently, most learning platforms provide uniform learning content, which does not address the individual needs and progress of each learner. In addition, the optimization of learning environments using smartphones has not progressed, making it difficult to effectively provide individually optimized learning plans.

[0512] 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.

[0513] In this invention, the server includes means for collecting learner profile data, means including a generative artificial intelligence model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for providing learning content via a smartphone application. This makes it possible to provide an optimized learning plan for each learner and to continuously optimize it based on the progress and feedback.

[0514] "Learner Profile Data" refers to information about a learner's goals, interests, skill level, and learning style.

[0515] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes collected data and generates an optimized learning plan.

[0516] "Individually Optimized Learning Plan" means a plan that includes learning materials, courses, and schedules customized for each learner.

[0517] "Learning Content" refers collectively to videos, interactive exercises, text materials, etc., provided for users to study.

[0518] "Progress" refers to information that shows the extent and level of achievement that a learner has actually made based on their learning plan.

[0519] "Feedback" refers to the learner's evaluations, comments, and progress on the learning plan.

[0520] "Smartphone application" refers to application software that runs on a smartphone and provides users with optimized learning plans and learning content.

[0521] The present invention is a system that provides an optimized learning plan to a learner and continuously optimizes the plan based on the learner's progress and feedback. Hereinafter, embodiments of the present invention will be described in detail.

[0522] System Overview

[0523] The system includes a server and a user's smartphone. The server is equipped with various software programs to collect profile data, analyze it using a generative AI model, and generate and optimize learning plans. A smartphone application is installed on the user's device to provide learning content and collect feedback.

[0524] Profile Data Collection

[0525] Users first access the smartphone application and create an account. They provide their name, email address, and password, as well as answer questions about their learning goals and interests, current skill level, and learning style. This information is then sent from the user's device to the server.

[0526] Data analysis and learning plan generation

[0527] The server then passes the received profile data to a generative AI model for analysis. The generative AI model analyzes the user's detailed learning needs based on their goals, interests, skill level, and learning style. Based on the results, an individually optimized learning plan is generated. This learning plan, including learning materials, courses, and schedules, is then sent from the server to the user's device.

[0528] Providing learning and collecting feedback

[0529] The user follows the submitted learning plan, including recommended video tutorials and interactive exercises, and progresses according to a specified schedule. After completing each learning module, the user provides feedback and progress information on their learning, including an evaluation of the learning module and progress. This information is sent from the smartphone application to the server.

[0530] Analyze feedback and optimize plans

[0531] The server receives feedback from users and passes it to the generative AI model for analysis. The generative AI model then optimizes the learning plan based on this feedback information and generates a plan for the next learning cycle. This new learning plan is then sent back to the user's device and serves as a guide for progressing through the course.

[0532] Specific examples

[0533] For example, if a user enters profile information such as "I want to learn Python programming at a beginner level," the following learning plan will be generated.

[0534] 1. Video Tutorials to Learn Python Basics

[0535] 2. Interactive coding exercises for beginners

[0536] 3. Daily study schedule

[0537] As the user progresses through the learning process, they provide feedback such as:

[0538] example:

[0539] "I have completed the video tutorial. The video was very easy to understand. I am looking forward to continuing."

[0540] Based on this feedback, the generative AI model analyzes and suggests appropriate coding exercises or new intermediate-level materials as the next learning step, providing users with a continuously optimized learning experience.

[0541] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0542] Step 1:

[0543] A user accesses a smartphone application and creates an account. Input: Name, email address, password, learning goals, interests, current skill level, and information about learning style. Output: This data is sent to a server, and the user's profile data is stored in a database.

[0544] Step 2:

[0545] The server passes the saved profile data to a generative AI model for analysis. Input: User profile data. Output: The generative AI model generates an optimized learning plan based on the learner's goals, interests, skill level, and learning style. Specifically, the AI ​​model analyzes various learning resources and creates a customized learning plan.

[0546] Step 3:

[0547] The generated learning plan is sent from the server to the user's device. Input: Optimized learning plan. Output: The learning plan is displayed on the user's smartphone application. Specifically, the contents of the plan (learning materials, courses, schedule) are applied to the application interface.

[0548] Step 4:

[0549] The user progresses through the learning process according to the provided learning plan. Input: Learning materials, video tutorials, and interactive exercises included in the learning plan. Output: Completion status of each learning module and user feedback. Specifically, the user works through each learning content and enters their progress and feedback into the application.

[0550] Step 5:

[0551] User feedback and progress information is sent from the smartphone application to the server. Input: User feedback and progress data. Output: Collected by the server and stored in a database. Specifically, the application receives feedback from the user and sends it to the server.

[0552] Step 6:

[0553] The server passes the received feedback data to a generative AI model for reanalysis. Input: User feedback data. Output: A new, optimized learning plan. Specifically, the generative AI model reevaluates the learning plan based on the feedback and suggests appropriate content for the next step.

[0554] Step 7:

[0555] The new study plan is sent back to the user's device. Input: A new, optimized study plan. Output: The plan is updated and displayed on the user's smartphone application. Specifically, the updated plan is reflected in the application interface.

[0556] Through these steps, the system can provide and continuously improve a learning experience that is optimized for each user.

[0557] 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.

[0558] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model and an emotion engine, and optimizes the plans based on feedback.

[0559] User data collection

[0560] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which are then sent to the server. The user also answers questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is then sent from the user's device to the server.

[0561] Data analysis

[0562] The server passes the received user profile data to a generative AI model. The generative AI model analyzes the user profile data to gain a detailed understanding of their learning needs. The server also uses an emotion engine to obtain the user's emotional data. The emotion engine analyzes inputs such as the user's facial expressions and voice to identify their emotional state.

[0563] Emotional Data Integration

[0564] The server integrates the analysis results from the generative AI model with the emotional data from the emotion engine. The generative AI model uses all this data to generate an individually optimized learning plan based on the learner's emotional state. This learning plan includes recommended learning materials, courses, and a study schedule.

[0565] Submitting and executing your learning plan

[0566] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[0567] Learning plan progress and emotional feedback collection

[0568] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback includes the user's emotional state. The emotion engine continuously monitors the user's emotional changes during learning and collects them as feedback.

[0569] Feedback analysis and plan optimization

[0570] The server passes the user's feedback to a generative AI model, which then performs further analysis based on the feedback. The generative AI model analyzes the feedback, including emotional data, and optimizes the learning plan. The new optimized learning plan reflects the user's emotional state and is adjusted to optimize the content.

[0571] Specific examples

[0572] As an example, consider an intermediate learner who is interested in machine learning. If a user enters profile information such as "I'm studying intermediate-level machine learning and I prefer visual learning," the server passes this information to a generative AI model for analysis. The emotion engine monitors the user's emotional state while learning and detects signs of depression or stress.

[0573] Based on the analysis and sentiment data, the generative AI model generates a learning plan that looks like this:

[0574] 1. Visually rich tutorial videos

[0575] 2. Interactive notebook exercises

[0576] 3. Weekly Study Schedule

[0577] 4. Insert relaxation breaks based on the user's emotional state

[0578] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress, feedback, and emotional state are sent to the server, the generative AI model analyzes this and provides the next optimized learning plan. By repeating this process, the user can obtain a continuously optimized learning experience.

[0579] The processing flow will be explained below.

[0580] Step 1:

[0581] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[0582] Step 2:

[0583] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[0584] Step 3:

[0585] The server then passes the received user profile data to a generative AI model, which analyzes the user profile data to gain a detailed understanding of their learning needs, forming the basis for generating an optimal learning plan for the user.

[0586] Step 4:

[0587] The server acquires emotional data from the user's device. The emotional data is collected through an emotion engine that analyzes the user's facial expressions and voice. The emotion engine recognizes the user's emotional state (e.g., excitement, stress, concentration, etc.) and transmits this as data to the server.

[0588] Step 5:

[0589] The server combines the results analyzed by the generative AI model with the emotional data from the emotion engine. Based on this, it generates an individually optimized learning plan. This learning plan includes recommended learning materials, courses, and a study schedule. It also adjusts the learning progress and break timing according to the user's emotional state.

[0590] Step 6:

[0591] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[0592] Step 7:

[0593] As the user progresses through the learning plan, the emotion engine continuously monitors the user's emotional state. The emotion engine captures changes in the user's facial expressions and voice, and transmits the emotional data to the server in real time.

[0594] Step 8:

[0595] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback also includes the user's emotional state. The emotional data reflects the user's emotional changes during the learning process.

[0596] Step 9:

[0597] The server passes the received feedback and emotional data to a generative artificial intelligence model for further analysis, which deepens understanding of the user's learning experience and improves the learning plan.

[0598] Step 10:

[0599] The server then optimizes the learning plan based on the analysis results. The new optimized learning plan reflects the user's feedback and emotional state, and is tailored to be more effective and satisfying.

[0600] Step 11:

[0601] The server sends the optimized learning plan to the user's device. The user then begins a new learning activity according to the optimized plan. This allows the user to have a continuously optimized learning experience. By repeating this process, the user's learning efficiency and satisfaction improve.

[0602] Example 2

[0603] 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."

[0604] While conventional learning plan providing systems can generate learning plans based on learner profile information, they are unable to take into account the learner's emotional state. This can lead to learners feeling stressed or their learning progress being hindered. Furthermore, since there is no way to collect learners' emotional state and feedback in real time and optimize the learning plan, it is difficult to provide an optimal learning experience for each individual learner.

[0605] 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.

[0606] In this invention, the server includes means for collecting learner profile data, means including a generative AI model that performs analysis based on the profile data, means for optimizing a study plan using an emotion engine that acquires user emotion data, means for generating an individually optimized study plan based on data obtained from the generative AI model and the emotion engine, means for transmitting the generated study plan to the learner's device, means for collecting progress and feedback on the study plan, and means for analyzing the feedback to further optimize the study plan. This makes it possible to provide an individually optimized study plan that reflects the learner's emotional state.

[0607] "Profile Data" is data that includes information about a learner's goals, interests, skill level, and learning style.

[0608] A "generative artificial intelligence model" is a type of artificial intelligence that can analyze collected profile data and generate individually optimized learning plans.

[0609] The "emotion engine" is an engine for acquiring and analyzing emotional data from the user's facial expressions, voice, etc.

[0610] A "learning plan" is a plan including learning materials, courses, and a learning schedule that is generated based on a learner's profile data and sentiment data.

[0611] "Feedback" is information provided by a learner to the server as progress, evaluation, opinion, and emotional state of the learning plan.

[0612] The "means for optimizing" is a method for analyzing the learning plan based on the collected feedback and generating a new, individually optimized learning plan.

[0613] The present invention is a system that provides an optimized learning plan to a learner. This system collects learner profile data, generates and provides an individually optimized learning plan based on the data using a generative AI model and an emotion engine, and then optimizes the learning plan based on subsequent feedback.

[0614] In this system, users first access the learning platform and create an account. They enter basic information such as their name, email address, and password, which is then sent to the server. They also answer questions about their learning goals, interests, skill level, and learning style to build an individual learning profile. This data is sent from the user's device to the server. Specific hardware used includes personal computers (PCs) and smartphones. Software used is a web browser or mobile application.

[0615] The server then analyzes the received user profile data. This is done using a generative artificial intelligence model. Specific examples include Google Cloud AI and OpenAI, which use these technologies to analyze the user profile data and perform operations to understand their learning needs. The server also uses an emotion engine (e.g., Microsoft Azure's Emotion API) to obtain and analyze the user's emotional data. The emotion engine collects data such as the user's facial expressions and voice and determines their current emotional state.

[0616] The server integrates data from the generative artificial intelligence model and emotion engine to generate an individually optimized study plan that takes into account the user's emotional state, including recommended study materials, courses, and a study schedule, including breaks as needed.

[0617] The generated learning plan is sent from the server to the user's device. The user then reviews the received learning plan and begins learning. Specifically, the user progresses by watching recommended videos and completing interactive notebook exercises. The progress of the learning plan, feedback, and the user's emotional state are also sent to the server.

[0618] For example, consider a user who is learning intermediate-level machine learning and prefers visual learning. The user enters the following prompt into the learning platform: "I am learning intermediate-level machine learning and prefer visual learning." The server passes this information to the generative AI model for analysis. The emotion engine monitors the user for signs of stress or depression while learning. Finally, the generative AI model proposes an optimized learning plan, such as:

[0619] 1. Visually rich tutorial videos

[0620] 2. Interactive Notebook Exercises

[0621] 3. Weekly Study Schedule

[0622] 4. Appropriate break times based on the user's emotional state

[0623] This allows the user to continue following the learning plan and obtain an optimal learning experience according to their emotional state. After the learning plan is executed, the server receives user feedback again, which is analyzed by the generative AI model to further optimize the learning plan.

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

[0625] Step 1: Collecting user profile data

[0626] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which is then sent to the server. The user also answers questions about their learning goals, interests, skill level, and learning style. The entered information is then sent from the user's device to the server. This input data includes user information and learning profile information.

[0627] Specific behavior:

[0628] The user opens the registration page on their device and enters their name, email address, and password.

[0629] Answer study questions and enter your profile data.

[0630] Click the Send all data button to send it to the server.

[0631] Step 2: Receiving and storing your profile data

[0632] The server receives the user's profile data and stores it in a database, making the user's profile available for future study plan generation.

[0633] Specific behavior:

[0634] The server receives the transmitted data.

[0635] The received data is stored in a database.

[0636] Input: User profile data

[0637] Output: Profile information stored in a database

[0638] Step 3: Analyzing the generative AI model

[0639] The server retrieves the user's profile data from the database and passes it to the generative AI model. The generative AI model analyzes the user's profile data to gain a detailed understanding of their learning needs. Through this process, the generative AI model obtains the basic data necessary to generate a learning plan.

[0640] Specific behavior:

[0641] The server retrieves the user's profile data from the database.

[0642] The acquired data is input into a generative artificial intelligence model.

[0643] A generative AI model analyzes the data and identifies learning needs.

[0644] Input: User profile data retrieved from the database

[0645] Output: Analysis results (learning needs)

[0646] Step 4: Obtaining emotion data

[0647] The server uses an emotion engine to acquire the user's emotion data. The emotion engine analyzes the user's facial and voice data to identify the user's current emotional state. This allows the collected emotion data to be used to optimize the learning plan.

[0648] Specific behavior:

[0649] The user's device collects data from the camera and microphone.

[0650] The collected data is sent to a server.

[0651] The server passes the data to the emotion engine for emotion analysis.

[0652] Input: User facial and voice data

[0653] Output: Analysis results (emotional state)

[0654] Step 5: Generate a learning plan

[0655] The server integrates the analysis results from the generative AI model and the emotional data from the emotion engine. The generative AI model uses this data to generate an individually optimized learning plan, which includes learning materials, courses, and a learning schedule.

[0656] Specific behavior:

[0657] A generative AI model integrates analytical results with emotional data.

[0658] Generate an optimized study plan.

[0659] Input: Analysis results (learning needs), emotional data

[0660] Output: Personalized learning plan

[0661] Step 6: Submit and execute your learning plan

[0662] The server then sends the generated learning plan to the user's device, where the user can review the plan and begin learning, including watching recommended videos and completing interactive notebook exercises.

[0663] Specific behavior:

[0664] The server transmits the generated learning plan to the user's terminal.

[0665] The user checks the received learning plan and progresses with the learning.

[0666] Input: Personalized learning plan

[0667] Output: The lesson plan displayed on the user's device

[0668] Step 7: Progress and feedback gathering

[0669] After completing each learning module, the user sends feedback to the server, including their evaluation of the learning plan, their opinion, and their emotional state. The emotion engine continuously monitors the user's emotional state during learning and sends it as feedback.

[0670] Specific behavior:

[0671] A user completes a learning module and provides feedback.

[0672] An emotion engine monitors the user's emotional state.

[0673] Send data including the feedback to the server.

[0674] Input: Feedback after completing the learning module, emotional state

[0675] Output: Feedback data sent to the server

[0676] Step 8: Analyze feedback and optimize your plan

[0677] The server passes the received feedback to the generative AI model for analysis, which then further optimizes the learning plan based on the feedback data and generates a new learning plan.

[0678] Specific behavior:

[0679] The server sends the feedback data to the generative AI model.

[0680] A generative AI model analyzes the feedback data and generates a new learning plan.

[0681] Input: Feedback data

[0682] Output: A new, optimized study plan

[0683] This allows users to always be provided with a study plan that is optimized for their emotional state and learning needs, allowing them to continue studying effectively and with less stress.

[0684] (Application example 2)

[0685] 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."

[0686] Conventional learning platforms face the challenge of providing optimal learning plans that take into account the needs and emotional state of individual learners. Furthermore, they lack the means to properly analyze feedback obtained during learning and quickly optimize learning plans. This makes it difficult for learners to consistently achieve optimal learning outcomes.

[0687] The identification processing 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 collecting attribute data of learners, means including a generative artificial intelligence model that performs analysis based on the attribute data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and responses to the learning plan, means for analyzing the responses and optimizing the learning plan, and means for transmitting the optimized learning plan to a terminal. This makes it possible to provide an optimal learning plan that corresponds to the individual needs and emotional state of the learner, and to quickly optimize the plan based on continuous feedback.

[0688] "Learner demographic data" refers to individual information about a learner, such as the learner's goals, interests, ability level, and learning methods.

[0689] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes a user's profile data and generates an optimized learning plan.

[0690] "Learning Plan" means a plan containing optimized learning materials, courses, and schedules provided to a Learner.

[0691] "Progress" refers to the progress a learner makes as they progress through their studies according to their learning plan.

[0692] "Responses" refers to feedback collected from learners and data that indicates their emotional state during learning.

[0693] "Optimization" refers to improving the learning plan based on the feedback and reactions collected and adjusting it to be most effective for the learner.

[0694] "Terminal" refers to the device used by a learner to receive the learning plan and carry out the learning.

[0695] "Means of collection" refers to the methods and techniques used to collect information such as learner demographic data and responses.

[0696] "Means for providing" refers to the methods and techniques for presenting the generated lesson plan to the learner.

[0697] "Means for transmitting" refers to the method or technology for transmitting the optimized learning plan to the learner's terminal.

[0698] This invention is a system that generates an optimized learning plan based on learner attribute data and optimizes the plan in real time through feedback. This system is mainly composed of a server, a terminal, and a user, and is implemented in the following form.

[0699] System configuration and operation

[0700] server

[0701] The server is responsible for collecting learner attribute data and analyzing it using a generative artificial intelligence model. The server uses the following hardware and software:

[0702] Hardware: High-performance data server

[0703] Software: Python, Flask (server side), generative AI model, emotion engine

[0704] The server collects and analyzes learner attribute data such as the learner's name, email address, goals, interests, ability level, and learning method. It also uses an emotion engine to identify the learner's emotional state and analyzes the learner's facial and voice data in real time.

[0705] The server integrates this data and uses a generative artificial intelligence model to generate an individually optimized learning plan, which it then sends to the device.

[0706] Terminal

[0707] The terminal is the device through which the user receives and executes the lesson plan. It uses the following hardware and software:

[0708] Hardware: Smartphones, tablets, computers

[0709] Software: React Native (mobile app), Web Browser (desktop app)

[0710] The device receives the study plan sent from the server and presents it to the user, which includes visually rich study materials, an interactive notebook, and a study schedule.

[0711] User

[0712] The user follows a learning plan. Examples of specific prompts include:

[0713] The user's name is Taro Yamada and his email address is taro@example.com.

[0714] He wants to learn intermediate level machine learning to become an AI engineer.

[0715] My areas of interest are machine learning and deep learning, and I prefer visually rich teaching materials.

[0716] Generate a study plan that best suits his profile.

[0717] The user studies based on the study plan, collects the progress and reactions of the study, and provides feedback to the server, including the user's emotional state and satisfaction with the study.

[0718] The server reanalyzes the learning plan using a generative artificial intelligence model based on user feedback, optimizes the learning plan in real time, and sends the optimized learning plan back to the terminal.

[0719] By repeating this process, users can have a continually optimized learning experience.

[0720] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0721] Step 1:

[0722] Collect learner attribute data. A user uses a device to access the learning platform and create an account. The user enters information such as their name, email address, goals, interests, ability level, and learning method. The device sends this data to the server. Input data: Learner's basic information, learning goals, interests, skill level, and learning style. Output data: Learner attribute data sent to the server.

[0723] Step 2:

[0724] The collected attribute data is analyzed. The server passes the received learner attribute data to a generative AI model for analysis. The generative AI model uses this data to perform a detailed analysis of the learner's needs. Input data: learner attribute data. Output data: analysis results related to the learner's needs.

[0725] Step 3:

[0726] Obtain the learner's emotional state. The server uses an emotion engine to analyze the learner's facial and voice data to identify the learner's emotional state. Input data: Data on the learner's facial and voice data. Output data: Data on the learner's emotional state.

[0727] Step 4:

[0728] Generates an optimized learning plan. The server integrates data obtained from the generative AI model and the emotion engine to generate an individually optimized learning plan based on the learner's attributes and emotional state. Input data: Analysis results regarding the learner's needs and emotional state data. Output data: Optimized learning plan.

[0729] Step 5:

[0730] The server provides the learning plan. The server sends the generated learning plan to the user's device and presents it to the user. Input data: Optimized learning plan. Output data: Learning plan sent to the device.

[0731] Step 6:

[0732] The learning progress and reactions are collected. The user proceeds with the learning according to the learning plan and feeds back the progress and reactions to the server via the terminal. Input data: User's progress and reactions. Output data: Progress and reaction data sent to the server.

[0733] Step 7:

[0734] Analyze and optimize based on feedback. The server collects feedback from users and passes it to the generative AI model for reanalysis. The server optimizes the learning plan based on the feedback and generates an updated learning plan. Input data: User progress and response data. Output data: New optimized learning plan.

[0735] Step 8:

[0736] Update the optimized learning plan. The server sends the new optimized learning plan to the user's device and presents it again. The user continues learning based on the new learning plan. By repeating this process, the user receives a continuously optimized learning experience. Input data: New optimized learning plan. Output data: New learning plan sent to the device.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] [Third embodiment]

[0741] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0742] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0743] 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).

[0744] 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.

[0745] 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.

[0746] 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).

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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."

[0753] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model, and optimizes the plans based on feedback.

[0754] User data collection

[0755] A user accesses the learning platform and creates an account. They enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server.

[0756] Data analysis

[0757] The server then passes the received user profile data to a generative AI model for analysis, which then performs a detailed analysis of the learner's learning needs based on their goals, interests, skill level, and learning style.

[0758] Learning plan generation

[0759] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. The learning plan includes recommended learning materials, courses, and schedules. This plan is then sent from the server to the user's device.

[0760] Implementing learning plans and collecting feedback

[0761] The user follows the submitted learning plan, which includes recommended videos, interactive notebook exercises, and a designated schedule. After completing each learning module, the user provides feedback and progress information to the server, including an evaluation of the learning module and progress.

[0762] Feedback analysis and plan optimization

[0763] The server receives feedback from users and passes it to a generative AI model for analysis. The generative AI model optimizes the learning plan based on the collected feedback and provides the next learning plan to the user.

[0764] Examples:

[0765] For example, consider an intermediate learner who is interested in machine learning. If the user enters profile information such as "Intermediate level machine learning student, prefers visual learning," the server passes this information to a generative AI model for analysis. Based on the analysis, the generative AI model might generate a learning plan like this:

[0766] 1. Visually rich tutorial videos

[0767] 2. Interactive notebook exercises

[0768] 3. Weekly Study Schedule

[0769] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress and feedback are sent to the server, the generative AI model analyzes it and provides the next optimized learning plan. This process allows the learner to have a continuously optimized learning experience.

[0770] The processing flow will be explained below.

[0771] Step 1:

[0772] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[0773] Step 2:

[0774] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[0775] Step 3:

[0776] The server passes the received user profile data to a generative artificial intelligence model, which analyzes the user profile data to gain a detailed understanding of the user's learning needs.

[0777] Step 4:

[0778] The server generates an individually optimized learning plan based on the results analyzed by the generative AI model, which includes recommended learning materials, courses, and a study schedule.

[0779] Step 5:

[0780] The server sends the generated study plan to the user's device, who then checks the received study plan and begins studying.

[0781] Step 6:

[0782] Users follow a provided learning plan, which involves watching recommended videos, completing interactive notebook exercises, and following a learning schedule.

[0783] Step 7:

[0784] After completing each learning module, the user sends their evaluation and opinions on the learning module and their learning progress as feedback to the server.

[0785] Step 8:

[0786] The server passes the received feedback to a generative artificial intelligence model for further analysis based on the feedback, which enhances understanding of the user's learning experience.

[0787] Step 9:

[0788] The server then optimizes the learning plan based on the analysis results, and the new optimized learning plan incorporates user feedback and is adjusted to be more effective.

[0789] Step 10:

[0790] The server then sends the optimized learning plan to the user's device, where the user begins a new learning activity according to the optimized plan. By repeating this process, the user can continuously obtain an optimized learning experience.

[0791] Example 1

[0792] 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."

[0793] Traditional learning platforms lacked the ability to provide learning plans optimized to individual learners' needs. As a result, learners would proceed to learning content that did not match their goals or skill level, hindering efficient learning. In addition, there was a problem of learners' motivation decreasing because the plan was not re-optimized to properly reflect their learning progress and feedback.

[0794] 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.

[0795] In this invention, the server includes means for collecting user profile data, means including a generative AI model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative AI model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for using generated prompt sentences for analysis, thereby enabling the provision of a learning plan optimized to the learner's individual needs and subsequent re-optimization based on the feedback.

[0796] 1. "User" refers to an individual who accesses the Learning Platform, creates an account, enters profile data and receives a learning plan.

[0797] 2. "Profile Data" refers to data entered by a User, including personal information such as learning goals, interests, skill level, and learning style.

[0798] 3. "Generative AI Model" refers to an artificial intelligence model that analyzes received profile data and generates individually optimized learning plans and prompts.

[0799] 4. “Study Plan” means a written plan containing learning materials, courses, and schedules optimized for a User by a generative AI model.

[0800] 5. "Feedback" means information provided by a User regarding the progress and evaluation of the Study Plan, which is used to subsequently optimize the Study Plan.

[0801] 6. "Prompt" refers to a specific instruction generated for a generative AI model to analyze.

[0802] The present invention relates to a platform that provides a learner with an optimized learning plan. Specific embodiments of the present invention will be described in detail below.

[0803] User data collection

[0804] Users access the learning platform and go through the process of creating an account. Specifically, they enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server. This data collection allows the server to accumulate data based on the user's individual needs.

[0805] Data analysis

[0806] The server passes the received user profile data to the generative AI model for analysis. The generative AI model uses advanced machine learning algorithms to perform a detailed analysis of the user's learning needs based on the user's goals, interests, skill level, and learning style. This analysis prepares data for generating the optimal learning plan for the user. This process also generates a prompt as input to the generative AI model. For example, the generated prompt is, "Please create an intermediate-level machine learning learning plan. Please prefer visual learning and include a weekly schedule."

[0807] Learning plan generation

[0808] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. This plan includes recommended learning materials, courses, and schedules, such as visually rich tutorial videos, interactive notebook exercises, and weekly study schedules. This generated learning plan is then sent to the user's device.

[0809] Implementing learning plans and collecting feedback

[0810] The user follows the submitted learning plan by watching the provided videos, completing exercises in the interactive notebook, and following the specified schedule. The user then sends their learning progress and feedback for each module to the server. The feedback includes an evaluation of the learning module and comments on the difficulty of the module.

[0811] Feedback analysis and plan optimization

[0812] The server passes the feedback received from the user to the generative AI model for analysis. Based on the results of this analysis, the generative AI model optimizes the study plan. The new optimized study plan is then sent back to the user's device. This ensures that the user always receives the optimal study plan that meets their latest learning needs.

[0813] By implementing this system, it becomes possible to provide detailed learning support tailored to the individual needs of users, dramatically improving learning efficiency. In addition, by optimizing plans based on user feedback, learners' motivation is maintained and a sustainable learning environment is provided.

[0814] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0815] Step 1:

[0816] User profile data collection

[0817] A user accesses the learning platform and creates an account.

[0818] Input: Basic information such as name, email address, and password

[0819] Output: Basic information data sent to the server

[0820] Users then answer questions about their learning goals, interests, skill level, and learning style.

[0821] Input: Learning goals, interests, skill level, learning style

[0822] Output: Profile data sent to the server

[0823] Step 2:

[0824] Data analysis

[0825] The server passes the received user profile data to the generative AI model.

[0826] Input: User profile data

[0827] Output: Data to be analyzed by the generative AI model

[0828] The generative AI model analyzes learners' goals, interests, skill levels, and learning styles to identify the learning needs that best suit the user.

[0829] Input: Data to be analyzed

[0830] Output: Detailed learning needs

[0831] Step 3:

[0832] Generate prompt statement

[0833] The server generates a prompt sentence based on the analysis results of the generative AI model.

[0834] Input: Detailed learning needs

[0835] Output: prompt statement

[0836] For example: "Create a study plan for intermediate-level machine learning. It should favor visual learning and include a weekly schedule."

[0837] Step 4:

[0838] Generate a learning plan

[0839] The server uses a generative AI model to generate an individually optimized learning plan based on the prompt.

[0840] Input: prompt statement

[0841] Output: Personalized learning plan

[0842] The study plan includes recommended study materials, courses, and schedules.

[0843] Step 5:

[0844] Submit your study plan

[0845] The server transmits the generated study plan to the user's terminal.

[0846] Input: Personalized learning plan

[0847] Output: The lesson plan sent to the user's device.

[0848] Step 6:

[0849] Execution of training

[0850] The user proceeds with their studies according to the provided study plan.

[0851] Input: Study Plan

[0852] Output: Training progress

[0853] Specific actions include watching videos, interactive notebook exercises, and studying according to a designated schedule.

[0854] Step 7:

[0855] Providing Feedback

[0856] Users send their learning progress and feedback to the server.

[0857] Input: Learning progress, feedback

[0858] Output: Feedback data sent to the server

[0859] The feedback includes an evaluation of the learning module and comments on the difficulty of the learning.

[0860] Step 8:

[0861] Analyze feedback and optimize plans

[0862] The server passes the received feedback to the generative AI model for analysis.

[0863] Input: Feedback data

[0864] Output: Analysis results

[0865] The generative AI model uses feedback to optimize the learning plan.

[0866] Input: Analysis results

[0867] Output: Optimized study plan

[0868] The optimized study plan is then sent back to the user's device.

[0869] (Application example 1)

[0870] 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."

[0871] Currently, most learning platforms provide uniform learning content, which does not address the individual needs and progress of each learner. In addition, the optimization of learning environments using smartphones has not progressed, making it difficult to effectively provide individually optimized learning plans.

[0872] 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.

[0873] In this invention, the server includes means for collecting learner profile data, means including a generative artificial intelligence model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for providing learning content via a smartphone application. This makes it possible to provide an optimized learning plan for each learner and to continuously optimize it based on the progress and feedback.

[0874] "Learner Profile Data" refers to information about a learner's goals, interests, skill level, and learning style.

[0875] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes collected data and generates an optimized learning plan.

[0876] "Individually Optimized Learning Plan" means a plan that includes learning materials, courses, and schedules customized for each learner.

[0877] "Learning Content" refers collectively to videos, interactive exercises, text materials, etc., provided for users to study.

[0878] "Progress" refers to information that shows the extent and level of achievement that a learner has actually made based on their learning plan.

[0879] "Feedback" refers to the learner's evaluations, comments, and progress on the learning plan.

[0880] "Smartphone application" refers to application software that runs on a smartphone and provides users with optimized learning plans and learning content.

[0881] The present invention is a system that provides an optimized learning plan to a learner and continuously optimizes the plan based on the learner's progress and feedback. Hereinafter, embodiments of the present invention will be described in detail.

[0882] System Overview

[0883] The system includes a server and a user's smartphone. The server is equipped with various software programs to collect profile data, analyze it using a generative AI model, and generate and optimize learning plans. A smartphone application is installed on the user's device to provide learning content and collect feedback.

[0884] Profile Data Collection

[0885] Users first access the smartphone application and create an account. They provide their name, email address, and password, as well as answer questions about their learning goals and interests, current skill level, and learning style. This information is then sent from the user's device to the server.

[0886] Data analysis and learning plan generation

[0887] The server then passes the received profile data to a generative AI model for analysis. The generative AI model analyzes the user's detailed learning needs based on their goals, interests, skill level, and learning style. Based on the results, an individually optimized learning plan is generated. This learning plan, including learning materials, courses, and schedules, is then sent from the server to the user's device.

[0888] Providing learning and collecting feedback

[0889] The user follows the submitted learning plan, including recommended video tutorials and interactive exercises, and progresses according to a specified schedule. After completing each learning module, the user provides feedback and progress information on their learning, including an evaluation of the learning module and progress. This information is sent from the smartphone application to the server.

[0890] Analyze feedback and optimize plans

[0891] The server receives feedback from users and passes it to the generative AI model for analysis. The generative AI model then optimizes the learning plan based on this feedback information and generates a plan for the next learning cycle. This new learning plan is then sent back to the user's device and serves as a guide for progressing through the course.

[0892] Specific examples

[0893] For example, if a user enters profile information such as "I want to learn Python programming at a beginner level," the following learning plan will be generated.

[0894] 1. Video Tutorials to Learn Python Basics

[0895] 2. Interactive coding exercises for beginners

[0896] 3. Daily study schedule

[0897] As the user progresses through the learning process, they provide feedback such as:

[0898] example:

[0899] "I have completed the video tutorial. The video was very easy to understand. I am looking forward to continuing."

[0900] Based on this feedback, the generative AI model analyzes and suggests appropriate coding exercises or new intermediate-level materials as the next learning step, providing users with a continuously optimized learning experience.

[0901] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0902] Step 1:

[0903] A user accesses a smartphone application and creates an account. Input: Name, email address, password, learning goals, interests, current skill level, and information about learning style. Output: This data is sent to a server, and the user's profile data is stored in a database.

[0904] Step 2:

[0905] The server passes the saved profile data to a generative AI model for analysis. Input: User profile data. Output: The generative AI model generates an optimized learning plan based on the learner's goals, interests, skill level, and learning style. Specifically, the AI ​​model analyzes various learning resources and creates a customized learning plan.

[0906] Step 3:

[0907] The generated learning plan is sent from the server to the user's device. Input: Optimized learning plan. Output: The learning plan is displayed on the user's smartphone application. Specifically, the contents of the plan (learning materials, courses, schedule) are applied to the application interface.

[0908] Step 4:

[0909] The user progresses through the learning process according to the provided learning plan. Input: Learning materials, video tutorials, and interactive exercises included in the learning plan. Output: Completion status of each learning module and user feedback. Specifically, the user works through each learning content and enters their progress and feedback into the application.

[0910] Step 5:

[0911] User feedback and progress information is sent from the smartphone application to the server. Input: User feedback and progress data. Output: Collected by the server and stored in a database. Specifically, the application receives feedback from the user and sends it to the server.

[0912] Step 6:

[0913] The server passes the received feedback data to a generative AI model for reanalysis. Input: User feedback data. Output: A new, optimized learning plan. Specifically, the generative AI model reevaluates the learning plan based on the feedback and suggests appropriate content for the next step.

[0914] Step 7:

[0915] The new study plan is sent back to the user's device. Input: A new, optimized study plan. Output: The plan is updated and displayed on the user's smartphone application. Specifically, the updated plan is reflected in the application interface.

[0916] Through these steps, the system can provide and continuously improve a learning experience that is optimized for each user.

[0917] 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.

[0918] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model and an emotion engine, and optimizes the plans based on feedback.

[0919] User data collection

[0920] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which are then sent to the server. The user also answers questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is then sent from the user's device to the server.

[0921] Data analysis

[0922] The server passes the received user profile data to a generative AI model. The generative AI model analyzes the user profile data to gain a detailed understanding of their learning needs. The server also uses an emotion engine to obtain the user's emotional data. The emotion engine analyzes inputs such as the user's facial expressions and voice to identify their emotional state.

[0923] Emotional Data Integration

[0924] The server integrates the analysis results from the generative AI model with the emotional data from the emotion engine. The generative AI model uses all this data to generate an individually optimized learning plan based on the learner's emotional state. This learning plan includes recommended learning materials, courses, and a study schedule.

[0925] Submitting and executing your learning plan

[0926] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[0927] Learning plan progress and emotional feedback collection

[0928] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback includes the user's emotional state. The emotion engine continuously monitors the user's emotional changes during learning and collects them as feedback.

[0929] Feedback analysis and plan optimization

[0930] The server passes the user's feedback to a generative AI model, which then performs further analysis based on the feedback. The generative AI model analyzes the feedback, including emotional data, and optimizes the learning plan. The new optimized learning plan reflects the user's emotional state and is adjusted to optimize the content.

[0931] Specific examples

[0932] As an example, consider an intermediate learner who is interested in machine learning. If a user enters profile information such as "I'm studying intermediate-level machine learning and I prefer visual learning," the server passes this information to a generative AI model for analysis. The emotion engine monitors the user's emotional state while learning and detects signs of depression or stress.

[0933] Based on the analysis and sentiment data, the generative AI model generates a learning plan that looks like this:

[0934] 1. Visually rich tutorial videos

[0935] 2. Interactive notebook exercises

[0936] 3. Weekly Study Schedule

[0937] 4. Insert relaxation breaks based on the user's emotional state

[0938] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress, feedback, and emotional state are sent to the server, the generative AI model analyzes this and provides the next optimized learning plan. By repeating this process, the user can obtain a continuously optimized learning experience.

[0939] The processing flow will be explained below.

[0940] Step 1:

[0941] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[0942] Step 2:

[0943] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[0944] Step 3:

[0945] The server then passes the received user profile data to a generative AI model, which analyzes the user profile data to gain a detailed understanding of their learning needs, forming the basis for generating an optimal learning plan for the user.

[0946] Step 4:

[0947] The server acquires emotional data from the user's device. The emotional data is collected through an emotion engine that analyzes the user's facial expressions and voice. The emotion engine recognizes the user's emotional state (e.g., excitement, stress, concentration, etc.) and transmits this as data to the server.

[0948] Step 5:

[0949] The server combines the results analyzed by the generative AI model with the emotional data from the emotion engine. Based on this, it generates an individually optimized learning plan. This learning plan includes recommended learning materials, courses, and a study schedule. It also adjusts the learning progress and break timing according to the user's emotional state.

[0950] Step 6:

[0951] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[0952] Step 7:

[0953] As the user progresses through the learning plan, the emotion engine continuously monitors the user's emotional state. The emotion engine captures changes in the user's facial expressions and voice, and transmits the emotional data to the server in real time.

[0954] Step 8:

[0955] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback also includes the user's emotional state. The emotional data reflects the user's emotional changes during the learning process.

[0956] Step 9:

[0957] The server passes the received feedback and emotional data to a generative artificial intelligence model for further analysis, which deepens understanding of the user's learning experience and improves the learning plan.

[0958] Step 10:

[0959] The server then optimizes the learning plan based on the analysis results. The new optimized learning plan reflects the user's feedback and emotional state, and is tailored to be more effective and satisfying.

[0960] Step 11:

[0961] The server sends the optimized learning plan to the user's device. The user then begins a new learning activity according to the optimized plan. This allows the user to have a continuously optimized learning experience. By repeating this process, the user's learning efficiency and satisfaction improve.

[0962] Example 2

[0963] 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."

[0964] While conventional learning plan providing systems can generate learning plans based on learner profile information, they are unable to take into account the learner's emotional state. This can lead to learners feeling stressed or their learning progress being hindered. Furthermore, since there is no way to collect learners' emotional state and feedback in real time and optimize the learning plan, it is difficult to provide an optimal learning experience for each individual learner.

[0965] 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.

[0966] In this invention, the server includes means for collecting learner profile data, means including a generative AI model that performs analysis based on the profile data, means for optimizing a study plan using an emotion engine that acquires user emotion data, means for generating an individually optimized study plan based on data obtained from the generative AI model and the emotion engine, means for transmitting the generated study plan to the learner's device, means for collecting progress and feedback on the study plan, and means for analyzing the feedback to further optimize the study plan. This makes it possible to provide an individually optimized study plan that reflects the learner's emotional state.

[0967] "Profile Data" is data that includes information about a learner's goals, interests, skill level, and learning style.

[0968] A "generative artificial intelligence model" is a type of artificial intelligence that can analyze collected profile data and generate individually optimized learning plans.

[0969] The "emotion engine" is an engine for acquiring and analyzing emotional data from the user's facial expressions, voice, etc.

[0970] A "learning plan" is a plan including learning materials, courses, and a learning schedule that is generated based on a learner's profile data and sentiment data.

[0971] "Feedback" is information provided by a learner to the server as progress, evaluation, opinion, and emotional state of the learning plan.

[0972] The "means for optimizing" is a method for analyzing the learning plan based on the collected feedback and generating a new, individually optimized learning plan.

[0973] The present invention is a system that provides an optimized learning plan to a learner. This system collects learner profile data, generates and provides an individually optimized learning plan based on the data using a generative AI model and an emotion engine, and then optimizes the learning plan based on subsequent feedback.

[0974] In this system, users first access the learning platform and create an account. They enter basic information such as their name, email address, and password, which is then sent to the server. They also answer questions about their learning goals, interests, skill level, and learning style to build an individual learning profile. This data is sent from the user's device to the server. Specific hardware used includes personal computers (PCs) and smartphones. Software used is a web browser or mobile application.

[0975] The server then analyzes the received user profile data. This is done using a generative artificial intelligence model. Specific examples include Google Cloud AI and OpenAI, which use these technologies to analyze the user profile data and perform operations to understand their learning needs. The server also uses an emotion engine (e.g., Microsoft Azure's Emotion API) to obtain and analyze the user's emotional data. The emotion engine collects data such as the user's facial expressions and voice and determines their current emotional state.

[0976] The server integrates data from the generative artificial intelligence model and emotion engine to generate an individually optimized study plan that takes into account the user's emotional state, including recommended study materials, courses, and a study schedule, including breaks as needed.

[0977] The generated learning plan is sent from the server to the user's device. The user then reviews the received learning plan and begins learning. Specifically, the user progresses by watching recommended videos and completing interactive notebook exercises. The progress of the learning plan, feedback, and the user's emotional state are also sent to the server.

[0978] For example, consider a user who is learning intermediate-level machine learning and prefers visual learning. The user enters the following prompt into the learning platform: "I am learning intermediate-level machine learning and prefer visual learning." The server passes this information to the generative AI model for analysis. The emotion engine monitors the user for signs of stress or depression while learning. Finally, the generative AI model proposes an optimized learning plan, such as:

[0979] 1. Visually rich tutorial videos

[0980] 2. Interactive Notebook Exercises

[0981] 3. Weekly Study Schedule

[0982] 4. Appropriate break times based on the user's emotional state

[0983] This allows the user to continue following the learning plan and obtain an optimal learning experience according to their emotional state. After the learning plan is executed, the server receives user feedback again, which is analyzed by the generative AI model to further optimize the learning plan.

[0984] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0985] Step 1: Collecting user profile data

[0986] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which is then sent to the server. The user also answers questions about their learning goals, interests, skill level, and learning style. The entered information is then sent from the user's device to the server. This input data includes user information and learning profile information.

[0987] Specific behavior:

[0988] The user opens the registration page on their device and enters their name, email address, and password.

[0989] Answer study questions and enter your profile data.

[0990] Click the Send all data button to send it to the server.

[0991] Step 2: Receiving and storing your profile data

[0992] The server receives the user's profile data and stores it in a database, making the user's profile available for future study plan generation.

[0993] Specific behavior:

[0994] The server receives the transmitted data.

[0995] The received data is stored in a database.

[0996] Input: User profile data

[0997] Output: Profile information stored in a database

[0998] Step 3: Analyzing the generative AI model

[0999] The server retrieves the user's profile data from the database and passes it to the generative AI model. The generative AI model analyzes the user's profile data to gain a detailed understanding of their learning needs. Through this process, the generative AI model obtains the basic data necessary to generate a learning plan.

[1000] Specific behavior:

[1001] The server retrieves the user's profile data from the database.

[1002] The acquired data is input into a generative artificial intelligence model.

[1003] A generative AI model analyzes the data and identifies learning needs.

[1004] Input: User profile data retrieved from the database

[1005] Output: Analysis results (learning needs)

[1006] Step 4: Obtaining emotion data

[1007] The server uses an emotion engine to acquire the user's emotion data. The emotion engine analyzes the user's facial and voice data to identify the user's current emotional state. This allows the collected emotion data to be used to optimize the learning plan.

[1008] Specific behavior:

[1009] The user's device collects data from the camera and microphone.

[1010] The collected data is sent to a server.

[1011] The server passes the data to the emotion engine for emotion analysis.

[1012] Input: User facial and voice data

[1013] Output: Analysis results (emotional state)

[1014] Step 5: Generate a learning plan

[1015] The server integrates the analysis results from the generative AI model and the emotional data from the emotion engine. The generative AI model uses this data to generate an individually optimized learning plan, which includes learning materials, courses, and a learning schedule.

[1016] Specific behavior:

[1017] A generative AI model integrates analytical results with emotional data.

[1018] Generate an optimized study plan.

[1019] Input: Analysis results (learning needs), emotional data

[1020] Output: Personalized learning plan

[1021] Step 6: Submit and execute your learning plan

[1022] The server then sends the generated learning plan to the user's device, where the user can review the plan and begin learning, including watching recommended videos and completing interactive notebook exercises.

[1023] Specific behavior:

[1024] The server transmits the generated learning plan to the user's terminal.

[1025] The user checks the received learning plan and progresses with the learning.

[1026] Input: Personalized learning plan

[1027] Output: The lesson plan displayed on the user's device

[1028] Step 7: Progress and feedback gathering

[1029] After completing each learning module, the user sends feedback to the server, including their evaluation of the learning plan, their opinion, and their emotional state. The emotion engine continuously monitors the user's emotional state during learning and sends it as feedback.

[1030] Specific behavior:

[1031] A user completes a learning module and provides feedback.

[1032] An emotion engine monitors the user's emotional state.

[1033] Send data including the feedback to the server.

[1034] Input: Feedback after completing the learning module, emotional state

[1035] Output: Feedback data sent to the server

[1036] Step 8: Analyze feedback and optimize your plan

[1037] The server passes the received feedback to the generative AI model for analysis, which then further optimizes the learning plan based on the feedback data and generates a new learning plan.

[1038] Specific behavior:

[1039] The server sends the feedback data to the generative AI model.

[1040] A generative AI model analyzes the feedback data and generates a new learning plan.

[1041] Input: Feedback data

[1042] Output: A new, optimized study plan

[1043] This allows users to always be provided with a study plan that is optimized for their emotional state and learning needs, allowing them to continue studying effectively and with less stress.

[1044] (Application example 2)

[1045] 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."

[1046] Conventional learning platforms face the challenge of providing optimal learning plans that take into account the needs and emotional state of individual learners. Furthermore, they lack the means to properly analyze feedback obtained during learning and quickly optimize learning plans. This makes it difficult for learners to consistently achieve optimal learning outcomes.

[1047] The identification processing 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 collecting attribute data of learners, means including a generative artificial intelligence model that performs analysis based on the attribute data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and responses to the learning plan, means for analyzing the responses and optimizing the learning plan, and means for transmitting the optimized learning plan to a terminal. This makes it possible to provide an optimal learning plan that corresponds to the individual needs and emotional state of the learner, and to quickly optimize the plan based on continuous feedback.

[1048] "Learner demographic data" refers to individual information about a learner, such as the learner's goals, interests, ability level, and learning methods.

[1049] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes a user's profile data and generates an optimized learning plan.

[1050] "Learning Plan" means a plan containing optimized learning materials, courses, and schedules provided to a Learner.

[1051] "Progress" refers to the progress a learner makes as they progress through their studies according to their learning plan.

[1052] "Responses" refers to feedback collected from learners and data that indicates their emotional state during learning.

[1053] "Optimization" refers to improving the learning plan based on the feedback and reactions collected and adjusting it to be most effective for the learner.

[1054] "Terminal" refers to the device used by a learner to receive the learning plan and carry out the learning.

[1055] "Means of collection" refers to the methods and techniques used to collect information such as learner demographic data and responses.

[1056] "Means for providing" refers to the methods and techniques for presenting the generated lesson plan to the learner.

[1057] "Means for transmitting" refers to the method or technology for transmitting the optimized learning plan to the learner's terminal.

[1058] This invention is a system that generates an optimized learning plan based on learner attribute data and optimizes the plan in real time through feedback. This system is mainly composed of a server, a terminal, and a user, and is implemented in the following form.

[1059] System configuration and operation

[1060] server

[1061] The server is responsible for collecting learner attribute data and analyzing it using a generative artificial intelligence model. The server uses the following hardware and software:

[1062] Hardware: High-performance data server

[1063] Software: Python, Flask (server side), generative AI model, emotion engine

[1064] The server collects and analyzes learner attribute data such as the learner's name, email address, goals, interests, ability level, and learning method. It also uses an emotion engine to identify the learner's emotional state and analyzes the learner's facial and voice data in real time.

[1065] The server integrates this data and uses a generative artificial intelligence model to generate an individually optimized learning plan, which it then sends to the device.

[1066] Terminal

[1067] The terminal is the device through which the user receives and executes the lesson plan. It uses the following hardware and software:

[1068] Hardware: Smartphones, tablets, computers

[1069] Software: React Native (mobile app), Web Browser (desktop app)

[1070] The device receives the study plan sent from the server and presents it to the user, which includes visually rich study materials, an interactive notebook, and a study schedule.

[1071] User

[1072] The user follows a learning plan. Examples of specific prompts include:

[1073] The user's name is Taro Yamada and his email address is taro@example.com.

[1074] He wants to learn intermediate level machine learning to become an AI engineer.

[1075] My areas of interest are machine learning and deep learning, and I prefer visually rich teaching materials.

[1076] Generate a study plan that best suits his profile.

[1077] The user studies based on the study plan, collects the progress and reactions of the study, and provides feedback to the server, including the user's emotional state and satisfaction with the study.

[1078] The server reanalyzes the learning plan using a generative artificial intelligence model based on user feedback, optimizes the learning plan in real time, and sends the optimized learning plan back to the terminal.

[1079] By repeating this process, users can have a continually optimized learning experience.

[1080] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1081] Step 1:

[1082] Collect learner attribute data. A user uses a device to access the learning platform and create an account. The user enters information such as their name, email address, goals, interests, ability level, and learning method. The device sends this data to the server. Input data: Learner's basic information, learning goals, interests, skill level, and learning style. Output data: Learner attribute data sent to the server.

[1083] Step 2:

[1084] The collected attribute data is analyzed. The server passes the received learner attribute data to a generative AI model for analysis. The generative AI model uses this data to perform a detailed analysis of the learner's needs. Input data: learner attribute data. Output data: analysis results related to the learner's needs.

[1085] Step 3:

[1086] Obtain the learner's emotional state. The server uses an emotion engine to analyze the learner's facial and voice data to identify the learner's emotional state. Input data: Data on the learner's facial and voice data. Output data: Data on the learner's emotional state.

[1087] Step 4:

[1088] Generates an optimized learning plan. The server integrates data obtained from the generative AI model and the emotion engine to generate an individually optimized learning plan based on the learner's attributes and emotional state. Input data: Analysis results regarding the learner's needs and emotional state data. Output data: Optimized learning plan.

[1089] Step 5:

[1090] The server provides the learning plan. The server sends the generated learning plan to the user's device and presents it to the user. Input data: Optimized learning plan. Output data: Learning plan sent to the device.

[1091] Step 6:

[1092] The learning progress and reactions are collected. The user proceeds with the learning according to the learning plan and feeds back the progress and reactions to the server via the terminal. Input data: User's progress and reactions. Output data: Progress and reaction data sent to the server.

[1093] Step 7:

[1094] Analyze and optimize based on feedback. The server collects feedback from users and passes it to the generative AI model for reanalysis. The server optimizes the learning plan based on the feedback and generates an updated learning plan. Input data: User progress and response data. Output data: New optimized learning plan.

[1095] Step 8:

[1096] Update the optimized learning plan. The server sends the new optimized learning plan to the user's device and presents it again. The user continues learning based on the new learning plan. By repeating this process, the user receives a continuously optimized learning experience. Input data: New optimized learning plan. Output data: New learning plan sent to the device.

[1097] 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.

[1098] 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.

[1099] 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.

[1100] [Fourth embodiment]

[1101] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1102] 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.

[1103] 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).

[1104] 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.

[1105] 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.

[1106] 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).

[1107] 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.

[1108] 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.

[1109] 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.

[1110] 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.

[1111] 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.

[1112] 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.

[1113] 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."

[1114] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model, and optimizes the plans based on feedback.

[1115] User data collection

[1116] A user accesses the learning platform and creates an account. They enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server.

[1117] Data analysis

[1118] The server then passes the received user profile data to a generative AI model for analysis, which then performs a detailed analysis of the learner's learning needs based on their goals, interests, skill level, and learning style.

[1119] Learning plan generation

[1120] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. The learning plan includes recommended learning materials, courses, and schedules. This plan is then sent from the server to the user's device.

[1121] Implementing learning plans and collecting feedback

[1122] The user follows the submitted learning plan, which includes recommended videos, interactive notebook exercises, and a designated schedule. After completing each learning module, the user provides feedback and progress information to the server, including an evaluation of the learning module and progress.

[1123] Feedback analysis and plan optimization

[1124] The server receives feedback from users and passes it to a generative AI model for analysis. The generative AI model optimizes the learning plan based on the collected feedback and provides the next learning plan to the user.

[1125] Examples:

[1126] For example, consider an intermediate learner who is interested in machine learning. If the user enters profile information such as "Intermediate level machine learning student, prefers visual learning," the server passes this information to a generative AI model for analysis. Based on the analysis, the generative AI model might generate a learning plan like this:

[1127] 1. Visually rich tutorial videos

[1128] 2. Interactive notebook exercises

[1129] 3. Weekly Study Schedule

[1130] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress and feedback are sent to the server, the generative AI model analyzes it and provides the next optimized learning plan. This process allows the learner to have a continuously optimized learning experience.

[1131] The processing flow will be explained below.

[1132] Step 1:

[1133] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[1134] Step 2:

[1135] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[1136] Step 3:

[1137] The server passes the received user profile data to a generative artificial intelligence model, which analyzes the user profile data to gain a detailed understanding of the user's learning needs.

[1138] Step 4:

[1139] The server generates an individually optimized learning plan based on the results analyzed by the generative AI model, which includes recommended learning materials, courses, and a study schedule.

[1140] Step 5:

[1141] The server sends the generated study plan to the user's device, who then checks the received study plan and begins studying.

[1142] Step 6:

[1143] Users follow a provided learning plan, which involves watching recommended videos, completing interactive notebook exercises, and following a learning schedule.

[1144] Step 7:

[1145] After completing each learning module, the user sends their evaluation and opinions on the learning module and their learning progress as feedback to the server.

[1146] Step 8:

[1147] The server passes the received feedback to a generative artificial intelligence model for further analysis based on the feedback, which enhances understanding of the user's learning experience.

[1148] Step 9:

[1149] The server then optimizes the learning plan based on the analysis results, and the new optimized learning plan incorporates user feedback and is adjusted to be more effective.

[1150] Step 10:

[1151] The server then sends the optimized learning plan to the user's device, where the user begins a new learning activity according to the optimized plan. By repeating this process, the user can continuously obtain an optimized learning experience.

[1152] Example 1

[1153] 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."

[1154] Traditional learning platforms lacked the ability to provide learning plans optimized to individual learners' needs. As a result, learners would proceed to learning content that did not match their goals or skill level, hindering efficient learning. In addition, there was a problem of learners' motivation decreasing because the plan was not re-optimized to properly reflect their learning progress and feedback.

[1155] 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.

[1156] In this invention, the server includes means for collecting user profile data, means including a generative AI model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative AI model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for using generated prompt sentences for analysis, thereby enabling the provision of a learning plan optimized to the learner's individual needs and subsequent re-optimization based on the feedback.

[1157] 1. "User" refers to an individual who accesses the Learning Platform, creates an account, enters profile data and receives a learning plan.

[1158] 2. "Profile Data" refers to data entered by a User, including personal information such as learning goals, interests, skill level, and learning style.

[1159] 3. "Generative AI Model" refers to an artificial intelligence model that analyzes received profile data and generates individually optimized learning plans and prompts.

[1160] 4. “Study Plan” means a written plan containing learning materials, courses, and schedules optimized for a User by a generative AI model.

[1161] 5. "Feedback" means information provided by a User regarding the progress and evaluation of the Study Plan, which is used to subsequently optimize the Study Plan.

[1162] 6. "Prompt" refers to a specific instruction generated for a generative AI model to analyze.

[1163] The present invention relates to a platform that provides a learner with an optimized learning plan. Specific embodiments of the present invention will be described in detail below.

[1164] User data collection

[1165] Users access the learning platform and go through the process of creating an account. Specifically, they enter basic information such as their name, email address, and password. They also answer questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is sent from the user's device to the server. This data collection allows the server to accumulate data based on the user's individual needs.

[1166] Data analysis

[1167] The server passes the received user profile data to the generative AI model for analysis. The generative AI model uses advanced machine learning algorithms to perform a detailed analysis of the user's learning needs based on the user's goals, interests, skill level, and learning style. This analysis prepares data for generating the optimal learning plan for the user. This process also generates a prompt as input to the generative AI model. For example, the generated prompt is, "Please create an intermediate-level machine learning learning plan. Please prefer visual learning and include a weekly schedule."

[1168] Learning plan generation

[1169] The server generates an individually optimized learning plan based on the analysis results of the generative AI model. This plan includes recommended learning materials, courses, and schedules, such as visually rich tutorial videos, interactive notebook exercises, and weekly study schedules. This generated learning plan is then sent to the user's device.

[1170] Implementing learning plans and collecting feedback

[1171] The user follows the submitted learning plan by watching the provided videos, completing exercises in the interactive notebook, and following the specified schedule. The user then sends their learning progress and feedback for each module to the server. The feedback includes an evaluation of the learning module and comments on the difficulty of the module.

[1172] Feedback analysis and plan optimization

[1173] The server passes the feedback received from the user to the generative AI model for analysis. Based on the results of this analysis, the generative AI model optimizes the study plan. The new optimized study plan is then sent back to the user's device. This ensures that the user always receives the optimal study plan that meets their latest learning needs.

[1174] By implementing this system, it becomes possible to provide detailed learning support tailored to the individual needs of users, dramatically improving learning efficiency. In addition, by optimizing plans based on user feedback, learners' motivation is maintained and a sustainable learning environment is provided.

[1175] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1176] Step 1:

[1177] User profile data collection

[1178] A user accesses the learning platform and creates an account.

[1179] Input: Basic information such as name, email address, and password

[1180] Output: Basic information data sent to the server

[1181] Users then answer questions about their learning goals, interests, skill level, and learning style.

[1182] Input: Learning goals, interests, skill level, learning style

[1183] Output: Profile data sent to the server

[1184] Step 2:

[1185] Data analysis

[1186] The server passes the received user profile data to the generative AI model.

[1187] Input: User profile data

[1188] Output: Data to be analyzed by the generative AI model

[1189] The generative AI model analyzes learners' goals, interests, skill levels, and learning styles to identify the learning needs that best suit the user.

[1190] Input: Data to be analyzed

[1191] Output: Detailed learning needs

[1192] Step 3:

[1193] Generate prompt statement

[1194] The server generates a prompt sentence based on the analysis results of the generative AI model.

[1195] Input: Detailed learning needs

[1196] Output: prompt statement

[1197] For example: "Create a study plan for intermediate-level machine learning. It should favor visual learning and include a weekly schedule."

[1198] Step 4:

[1199] Generate a learning plan

[1200] The server uses a generative AI model to generate an individually optimized learning plan based on the prompt.

[1201] Input: prompt statement

[1202] Output: Personalized learning plan

[1203] The study plan includes recommended study materials, courses, and schedules.

[1204] Step 5:

[1205] Submit your study plan

[1206] The server transmits the generated study plan to the user's terminal.

[1207] Input: Personalized learning plan

[1208] Output: The lesson plan sent to the user's device.

[1209] Step 6:

[1210] Execution of training

[1211] The user proceeds with their studies according to the provided study plan.

[1212] Input: Study Plan

[1213] Output: Training progress

[1214] Specific actions include watching videos, interactive notebook exercises, and studying according to a designated schedule.

[1215] Step 7:

[1216] Providing Feedback

[1217] Users send their learning progress and feedback to the server.

[1218] Input: Learning progress, feedback

[1219] Output: Feedback data sent to the server

[1220] The feedback includes an evaluation of the learning module and comments on the difficulty of the learning.

[1221] Step 8:

[1222] Analyze feedback and optimize plans

[1223] The server passes the received feedback to the generative AI model for analysis.

[1224] Input: Feedback data

[1225] Output: Analysis results

[1226] The generative AI model uses feedback to optimize the learning plan.

[1227] Input: Analysis results

[1228] Output: Optimized study plan

[1229] The optimized study plan is then sent back to the user's device.

[1230] (Application example 1)

[1231] 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."

[1232] Currently, most learning platforms provide uniform learning content, which does not address the individual needs and progress of each learner. In addition, the optimization of learning environments using smartphones has not progressed, making it difficult to effectively provide individually optimized learning plans.

[1233] 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.

[1234] In this invention, the server includes means for collecting learner profile data, means including a generative artificial intelligence model that performs analysis based on the profile data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and feedback on the learning plan, means for analyzing the feedback to optimize the learning plan, and means for providing learning content via a smartphone application. This makes it possible to provide an optimized learning plan for each learner and to continuously optimize it based on the progress and feedback.

[1235] "Learner Profile Data" refers to information about a learner's goals, interests, skill level, and learning style.

[1236] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes collected data and generates an optimized learning plan.

[1237] "Individually Optimized Learning Plan" means a plan that includes learning materials, courses, and schedules customized for each learner.

[1238] "Learning Content" refers collectively to videos, interactive exercises, text materials, etc., provided for users to study.

[1239] "Progress" refers to information that shows the extent and level of achievement that a learner has actually made based on their learning plan.

[1240] "Feedback" refers to the learner's evaluations, comments, and progress on the learning plan.

[1241] "Smartphone application" refers to application software that runs on a smartphone and provides users with optimized learning plans and learning content.

[1242] The present invention is a system that provides an optimized learning plan to a learner and continuously optimizes the plan based on the learner's progress and feedback. Hereinafter, embodiments of the present invention will be described in detail.

[1243] System Overview

[1244] The system includes a server and a user's smartphone. The server is equipped with various software programs to collect profile data, analyze it using a generative AI model, and generate and optimize learning plans. A smartphone application is installed on the user's device to provide learning content and collect feedback.

[1245] Profile Data Collection

[1246] Users first access the smartphone application and create an account. They provide their name, email address, and password, as well as answer questions about their learning goals and interests, current skill level, and learning style. This information is then sent from the user's device to the server.

[1247] Data analysis and learning plan generation

[1248] The server then passes the received profile data to a generative AI model for analysis. The generative AI model analyzes the user's detailed learning needs based on their goals, interests, skill level, and learning style. Based on the results, an individually optimized learning plan is generated. This learning plan, including learning materials, courses, and schedules, is then sent from the server to the user's device.

[1249] Providing learning and collecting feedback

[1250] The user follows the submitted learning plan, including recommended video tutorials and interactive exercises, and progresses according to a specified schedule. After completing each learning module, the user provides feedback and progress information on their learning, including an evaluation of the learning module and progress. This information is sent from the smartphone application to the server.

[1251] Analyze feedback and optimize plans

[1252] The server receives feedback from users and passes it to the generative AI model for analysis. The generative AI model then optimizes the learning plan based on this feedback information and generates a plan for the next learning cycle. This new learning plan is then sent back to the user's device and serves as a guide for progressing through the course.

[1253] Specific examples

[1254] For example, if a user enters profile information such as "I want to learn Python programming at a beginner level," the following learning plan will be generated.

[1255] 1. Video Tutorials to Learn Python Basics

[1256] 2. Interactive coding exercises for beginners

[1257] 3. Daily study schedule

[1258] As the user progresses through the learning process, they provide feedback such as:

[1259] example:

[1260] "I have completed the video tutorial. The video was very easy to understand. I am looking forward to continuing."

[1261] Based on this feedback, the generative AI model analyzes and suggests appropriate coding exercises or new intermediate-level materials as the next learning step, providing users with a continuously optimized learning experience.

[1262] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1263] Step 1:

[1264] A user accesses a smartphone application and creates an account. Input: Name, email address, password, learning goals, interests, current skill level, and information about learning style. Output: This data is sent to a server, and the user's profile data is stored in a database.

[1265] Step 2:

[1266] The server passes the saved profile data to a generative AI model for analysis. Input: User profile data. Output: The generative AI model generates an optimized learning plan based on the learner's goals, interests, skill level, and learning style. Specifically, the AI ​​model analyzes various learning resources and creates a customized learning plan.

[1267] Step 3:

[1268] The generated learning plan is sent from the server to the user's device. Input: Optimized learning plan. Output: The learning plan is displayed on the user's smartphone application. Specifically, the contents of the plan (learning materials, courses, schedule) are applied to the application interface.

[1269] Step 4:

[1270] The user progresses through the learning process according to the provided learning plan. Input: Learning materials, video tutorials, and interactive exercises included in the learning plan. Output: Completion status of each learning module and user feedback. Specifically, the user works through each learning content and enters their progress and feedback into the application.

[1271] Step 5:

[1272] User feedback and progress information is sent from the smartphone application to the server. Input: User feedback and progress data. Output: Collected by the server and stored in a database. Specifically, the application receives feedback from the user and sends it to the server.

[1273] Step 6:

[1274] The server passes the received feedback data to a generative AI model for reanalysis. Input: User feedback data. Output: A new, optimized learning plan. Specifically, the generative AI model reevaluates the learning plan based on the feedback and suggests appropriate content for the next step.

[1275] Step 7:

[1276] The new study plan is sent back to the user's device. Input: A new, optimized study plan. Output: The plan is updated and displayed on the user's smartphone application. Specifically, the updated plan is reflected in the application interface.

[1277] Through these steps, the system can provide and continuously improve a learning experience that is optimized for each user.

[1278] 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.

[1279] The present invention relates to a platform that provides learners with optimized learning plans. It is a system that collects learner profile data, generates and provides individually optimized learning plans using a generative artificial intelligence model and an emotion engine, and optimizes the plans based on feedback.

[1280] User data collection

[1281] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which are then sent to the server. The user also answers questions about their learning goals, interests, current skill level, and learning style to build a personal learning profile. This data is then sent from the user's device to the server.

[1282] Data analysis

[1283] The server passes the received user profile data to a generative AI model. The generative AI model analyzes the user profile data to gain a detailed understanding of their learning needs. The server also uses an emotion engine to obtain the user's emotional data. The emotion engine analyzes inputs such as the user's facial expressions and voice to identify their emotional state.

[1284] Emotional Data Integration

[1285] The server integrates the analysis results from the generative AI model with the emotional data from the emotion engine. The generative AI model uses all this data to generate an individually optimized learning plan based on the learner's emotional state. This learning plan includes recommended learning materials, courses, and a study schedule.

[1286] Submitting and executing your learning plan

[1287] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[1288] Learning plan progress and emotional feedback collection

[1289] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback includes the user's emotional state. The emotion engine continuously monitors the user's emotional changes during learning and collects them as feedback.

[1290] Feedback analysis and plan optimization

[1291] The server passes the user's feedback to a generative AI model, which then performs further analysis based on the feedback. The generative AI model analyzes the feedback, including emotional data, and optimizes the learning plan. The new optimized learning plan reflects the user's emotional state and is adjusted to optimize the content.

[1292] Specific examples

[1293] As an example, consider an intermediate learner who is interested in machine learning. If a user enters profile information such as "I'm studying intermediate-level machine learning and I prefer visual learning," the server passes this information to a generative AI model for analysis. The emotion engine monitors the user's emotional state while learning and detects signs of depression or stress.

[1294] Based on the analysis and sentiment data, the generative AI model generates a learning plan that looks like this:

[1295] 1. Visually rich tutorial videos

[1296] 2. Interactive notebook exercises

[1297] 3. Weekly Study Schedule

[1298] 4. Insert relaxation breaks based on the user's emotional state

[1299] This learning plan is sent from the server to the user's device, and the user proceeds with their learning based on this plan. When the learning progress, feedback, and emotional state are sent to the server, the generative AI model analyzes this and provides the next optimized learning plan. By repeating this process, the user can obtain a continuously optimized learning experience.

[1300] The processing flow will be explained below.

[1301] Step 1:

[1302] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, and sends it to the server.

[1303] Step 2:

[1304] Users build a personal learning profile by answering questions about their learning goals, interests, current skill level, and learning style, and this data is sent from the user's device to the server.

[1305] Step 3:

[1306] The server then passes the received user profile data to a generative AI model, which analyzes the user profile data to gain a detailed understanding of their learning needs, forming the basis for generating an optimal learning plan for the user.

[1307] Step 4:

[1308] The server acquires emotional data from the user's device. The emotional data is collected through an emotion engine that analyzes the user's facial expressions and voice. The emotion engine recognizes the user's emotional state (e.g., excitement, stress, concentration, etc.) and transmits this as data to the server.

[1309] Step 5:

[1310] The server combines the results analyzed by the generative AI model with the emotional data from the emotion engine. Based on this, it generates an individually optimized learning plan. This learning plan includes recommended learning materials, courses, and a study schedule. It also adjusts the learning progress and break timing according to the user's emotional state.

[1311] Step 6:

[1312] The server then sends the generated learning plan to the user's device. The user then reviews the received learning plan and begins studying, specifically by watching recommended videos, completing interactive notebook exercises, and following the learning schedule.

[1313] Step 7:

[1314] As the user progresses through the learning plan, the emotion engine continuously monitors the user's emotional state. The emotion engine captures changes in the user's facial expressions and voice, and transmits the emotional data to the server in real time.

[1315] Step 8:

[1316] After completing each learning module, the user sends their evaluation and opinion on the learning module and their learning progress to the server. This feedback also includes the user's emotional state. The emotional data reflects the user's emotional changes during the learning process.

[1317] Step 9:

[1318] The server passes the received feedback and emotional data to a generative artificial intelligence model for further analysis, which deepens understanding of the user's learning experience and improves the learning plan.

[1319] Step 10:

[1320] The server then optimizes the learning plan based on the analysis results. The new optimized learning plan reflects the user's feedback and emotional state, and is tailored to be more effective and satisfying.

[1321] Step 11:

[1322] The server sends the optimized learning plan to the user's device. The user then begins a new learning activity according to the optimized plan. This allows the user to have a continuously optimized learning experience. By repeating this process, the user's learning efficiency and satisfaction improve.

[1323] Example 2

[1324] 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."

[1325] While conventional learning plan providing systems can generate learning plans based on learner profile information, they are unable to take into account the learner's emotional state. This can lead to learners feeling stressed or their learning progress being hindered. Furthermore, since there is no way to collect learners' emotional state and feedback in real time and optimize the learning plan, it is difficult to provide an optimal learning experience for each individual learner.

[1326] 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.

[1327] In this invention, the server includes means for collecting learner profile data, means including a generative AI model that performs analysis based on the profile data, means for optimizing a study plan using an emotion engine that acquires user emotion data, means for generating an individually optimized study plan based on data obtained from the generative AI model and the emotion engine, means for transmitting the generated study plan to the learner's device, means for collecting progress and feedback on the study plan, and means for analyzing the feedback to further optimize the study plan. This makes it possible to provide an individually optimized study plan that reflects the learner's emotional state.

[1328] "Profile Data" is data that includes information about a learner's goals, interests, skill level, and learning style.

[1329] A "generative artificial intelligence model" is a type of artificial intelligence that can analyze collected profile data and generate individually optimized learning plans.

[1330] The "emotion engine" is an engine for acquiring and analyzing emotional data from the user's facial expressions, voice, etc.

[1331] A "learning plan" is a plan including learning materials, courses, and a learning schedule that is generated based on a learner's profile data and sentiment data.

[1332] "Feedback" is information provided by a learner to the server as progress, evaluation, opinion, and emotional state of the learning plan.

[1333] The "means for optimizing" is a method for analyzing the learning plan based on the collected feedback and generating a new, individually optimized learning plan.

[1334] The present invention is a system that provides an optimized learning plan to a learner. This system collects learner profile data, generates and provides an individually optimized learning plan based on the data using a generative AI model and an emotion engine, and then optimizes the learning plan based on subsequent feedback.

[1335] In this system, users first access the learning platform and create an account. They enter basic information such as their name, email address, and password, which is then sent to the server. They also answer questions about their learning goals, interests, skill level, and learning style to build an individual learning profile. This data is sent from the user's device to the server. Specific hardware used includes personal computers (PCs) and smartphones. Software used is a web browser or mobile application.

[1336] The server then analyzes the received user profile data. This is done using a generative artificial intelligence model. Specific examples include Google Cloud AI and OpenAI, which use these technologies to analyze the user profile data and perform operations to understand their learning needs. The server also uses an emotion engine (e.g., Microsoft Azure's Emotion API) to obtain and analyze the user's emotional data. The emotion engine collects data such as the user's facial expressions and voice and determines their current emotional state.

[1337] The server integrates data from the generative artificial intelligence model and emotion engine to generate an individually optimized study plan that takes into account the user's emotional state, including recommended study materials, courses, and a study schedule, including breaks as needed.

[1338] The generated learning plan is sent from the server to the user's device. The user then reviews the received learning plan and begins learning. Specifically, the user progresses by watching recommended videos and completing interactive notebook exercises. The progress of the learning plan, feedback, and the user's emotional state are also sent to the server.

[1339] For example, consider a user who is learning intermediate-level machine learning and prefers visual learning. The user enters the following prompt into the learning platform: "I am learning intermediate-level machine learning and prefer visual learning." The server passes this information to the generative AI model for analysis. The emotion engine monitors the user for signs of stress or depression while learning. Finally, the generative AI model proposes an optimized learning plan, such as:

[1340] 1. Visually rich tutorial videos

[1341] 2. Interactive Notebook Exercises

[1342] 3. Weekly Study Schedule

[1343] 4. Appropriate break times based on the user's emotional state

[1344] This allows the user to continue following the learning plan and obtain an optimal learning experience according to their emotional state. After the learning plan is executed, the server receives user feedback again, which is analyzed by the generative AI model to further optimize the learning plan.

[1345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1346] Step 1: Collecting user profile data

[1347] A user accesses the learning platform and creates an account. The user enters basic information such as name, email address, and password, which is then sent to the server. The user also answers questions about their learning goals, interests, skill level, and learning style. The entered information is then sent from the user's device to the server. This input data includes user information and learning profile information.

[1348] Specific behavior:

[1349] The user opens the registration page on their device and enters their name, email address, and password.

[1350] Answer study questions and enter your profile data.

[1351] Click the Send all data button to send it to the server.

[1352] Step 2: Receiving and storing your profile data

[1353] The server receives the user's profile data and stores it in a database, making the user's profile available for future study plan generation.

[1354] Specific behavior:

[1355] The server receives the transmitted data.

[1356] The received data is stored in a database.

[1357] Input: User profile data

[1358] Output: Profile information stored in a database

[1359] Step 3: Analyzing the generative AI model

[1360] The server retrieves the user's profile data from the database and passes it to the generative AI model. The generative AI model analyzes the user's profile data to gain a detailed understanding of their learning needs. Through this process, the generative AI model obtains the basic data necessary to generate a learning plan.

[1361] Specific behavior:

[1362] The server retrieves the user's profile data from the database.

[1363] The acquired data is input into a generative artificial intelligence model.

[1364] A generative AI model analyzes the data and identifies learning needs.

[1365] Input: User profile data retrieved from the database

[1366] Output: Analysis results (learning needs)

[1367] Step 4: Obtaining emotion data

[1368] The server uses an emotion engine to acquire the user's emotion data. The emotion engine analyzes the user's facial and voice data to identify the user's current emotional state. This allows the collected emotion data to be used to optimize the learning plan.

[1369] Specific behavior:

[1370] The user's device collects data from the camera and microphone.

[1371] The collected data is sent to a server.

[1372] The server passes the data to the emotion engine for emotion analysis.

[1373] Input: User facial and voice data

[1374] Output: Analysis results (emotional state)

[1375] Step 5: Generate a learning plan

[1376] The server integrates the analysis results from the generative AI model and the emotional data from the emotion engine. The generative AI model uses this data to generate an individually optimized learning plan, which includes learning materials, courses, and a learning schedule.

[1377] Specific behavior:

[1378] A generative AI model integrates analytical results with emotional data.

[1379] Generate an optimized study plan.

[1380] Input: Analysis results (learning needs), emotional data

[1381] Output: Personalized learning plan

[1382] Step 6: Submit and execute your learning plan

[1383] The server then sends the generated learning plan to the user's device, where the user can review the plan and begin learning, including watching recommended videos and completing interactive notebook exercises.

[1384] Specific behavior:

[1385] The server transmits the generated learning plan to the user's terminal.

[1386] The user checks the received learning plan and progresses with the learning.

[1387] Input: Personalized learning plan

[1388] Output: The lesson plan displayed on the user's device

[1389] Step 7: Progress and feedback gathering

[1390] After completing each learning module, the user sends feedback to the server, including their evaluation of the learning plan, their opinion, and their emotional state. The emotion engine continuously monitors the user's emotional state during learning and sends it as feedback.

[1391] Specific behavior:

[1392] A user completes a learning module and provides feedback.

[1393] An emotion engine monitors the user's emotional state.

[1394] Send data including the feedback to the server.

[1395] Input: Feedback after completing the learning module, emotional state

[1396] Output: Feedback data sent to the server

[1397] Step 8: Analyze feedback and optimize your plan

[1398] The server passes the received feedback to the generative AI model for analysis, which then further optimizes the learning plan based on the feedback data and generates a new learning plan.

[1399] Specific behavior:

[1400] The server sends the feedback data to the generative AI model.

[1401] A generative AI model analyzes the feedback data and generates a new learning plan.

[1402] Input: Feedback data

[1403] Output: A new, optimized study plan

[1404] This allows users to always be provided with a study plan that is optimized for their emotional state and learning needs, allowing them to continue studying effectively and with less stress.

[1405] (Application example 2)

[1406] 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."

[1407] Conventional learning platforms face the challenge of providing optimal learning plans that take into account the needs and emotional state of individual learners. Furthermore, they lack the means to properly analyze feedback obtained during learning and quickly optimize learning plans. This makes it difficult for learners to consistently achieve optimal learning outcomes.

[1408] The identification processing 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 collecting attribute data of learners, means including a generative artificial intelligence model that performs analysis based on the attribute data, means for providing an individually optimized learning plan generated by the generative artificial intelligence model, means for collecting progress and responses to the learning plan, means for analyzing the responses and optimizing the learning plan, and means for transmitting the optimized learning plan to a terminal. This makes it possible to provide an optimal learning plan that corresponds to the individual needs and emotional state of the learner, and to quickly optimize the plan based on continuous feedback.

[1409] "Learner demographic data" refers to individual information about a learner, such as the learner's goals, interests, ability level, and learning methods.

[1410] A "generative artificial intelligence model" refers to an artificial intelligence model that analyzes a user's profile data and generates an optimized learning plan.

[1411] "Learning Plan" means a plan containing optimized learning materials, courses, and schedules provided to a Learner.

[1412] "Progress" refers to the progress a learner makes as they progress through their studies according to their learning plan.

[1413] "Responses" refers to feedback collected from learners and data that indicates their emotional state during learning.

[1414] "Optimization" refers to improving the learning plan based on the feedback and reactions collected and adjusting it to be most effective for the learner.

[1415] "Terminal" refers to the device used by a learner to receive the learning plan and carry out the learning.

[1416] "Means of collection" refers to the methods and techniques used to collect information such as learner demographic data and responses.

[1417] "Means for providing" refers to the methods and techniques for presenting the generated lesson plan to the learner.

[1418] "Means for transmitting" refers to the method or technology for transmitting the optimized learning plan to the learner's terminal.

[1419] This invention is a system that generates an optimized learning plan based on learner attribute data and optimizes the plan in real time through feedback. This system is mainly composed of a server, a terminal, and a user, and is implemented in the following form.

[1420] System configuration and operation

[1421] server

[1422] The server is responsible for collecting learner attribute data and analyzing it using a generative artificial intelligence model. The server uses the following hardware and software:

[1423] Hardware: High-performance data server

[1424] Software: Python, Flask (server side), generative AI model, emotion engine

[1425] The server collects and analyzes learner attribute data such as the learner's name, email address, goals, interests, ability level, and learning method. It also uses an emotion engine to identify the learner's emotional state and analyzes the learner's facial and voice data in real time.

[1426] The server integrates this data and uses a generative artificial intelligence model to generate an individually optimized learning plan, which it then sends to the device.

[1427] Terminal

[1428] The terminal is the device through which the user receives and executes the lesson plan. It uses the following hardware and software:

[1429] Hardware: Smartphones, tablets, computers

[1430] Software: React Native (mobile app), Web Browser (desktop app)

[1431] The device receives the study plan sent from the server and presents it to the user, which includes visually rich study materials, an interactive notebook, and a study schedule.

[1432] User

[1433] The user follows a learning plan. Examples of specific prompts include:

[1434] The user's name is Taro Yamada and his email address is taro@example.com.

[1435] He wants to learn intermediate level machine learning to become an AI engineer.

[1436] My areas of interest are machine learning and deep learning, and I prefer visually rich teaching materials.

[1437] Generate a study plan that best suits his profile.

[1438] The user studies based on the study plan, collects the progress and reactions of the study, and provides feedback to the server, including the user's emotional state and satisfaction with the study.

[1439] The server reanalyzes the learning plan using a generative artificial intelligence model based on user feedback, optimizes the learning plan in real time, and sends the optimized learning plan back to the terminal.

[1440] By repeating this process, users can have a continually optimized learning experience.

[1441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1442] Step 1:

[1443] Collect learner attribute data. A user uses a device to access the learning platform and create an account. The user enters information such as their name, email address, goals, interests, ability level, and learning method. The device sends this data to the server. Input data: Learner's basic information, learning goals, interests, skill level, and learning style. Output data: Learner attribute data sent to the server.

[1444] Step 2:

[1445] The collected attribute data is analyzed. The server passes the received learner attribute data to a generative AI model for analysis. The generative AI model uses this data to perform a detailed analysis of the learner's needs. Input data: learner attribute data. Output data: analysis results related to the learner's needs.

[1446] Step 3:

[1447] Obtain the learner's emotional state. The server uses an emotion engine to analyze the learner's facial and voice data to identify the learner's emotional state. Input data: Data on the learner's facial and voice data. Output data: Data on the learner's emotional state.

[1448] Step 4:

[1449] Generates an optimized learning plan. The server integrates data obtained from the generative AI model and the emotion engine to generate an individually optimized learning plan based on the learner's attributes and emotional state. Input data: Analysis results regarding the learner's needs and emotional state data. Output data: Optimized learning plan.

[1450] Step 5:

[1451] The server provides the learning plan. The server sends the generated learning plan to the user's device and presents it to the user. Input data: Optimized learning plan. Output data: Learning plan sent to the device.

[1452] Step 6:

[1453] The learning progress and reactions are collected. The user proceeds with the learning according to the learning plan and feeds back the progress and reactions to the server via the terminal. Input data: User's progress and reactions. Output data: Progress and reaction data sent to the server.

[1454] Step 7:

[1455] Analyze and optimize based on feedback. The server collects feedback from users and passes it to the generative AI model for reanalysis. The server optimizes the learning plan based on the feedback and generates an updated learning plan. Input data: User progress and response data. Output data: New optimized learning plan.

[1456] Step 8:

[1457] Update the optimized learning plan. The server sends the new optimized learning plan to the user's device and presents it again. The user continues learning based on the new learning plan. By repeating this process, the user receives a continuously optimized learning experience. Input data: New optimized learning plan. Output data: New learning plan sent to the device.

[1458] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1459] 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.

[1460] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1461] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1462] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1463] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1464] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1465] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1466] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1467] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1468] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1469] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1470] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1471] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1472] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1473] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1474] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1475] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1476] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1477] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1478] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1479] The following is further disclosed regarding the above embodiment.

[1480] (Claim 1)

[1481] a means of collecting learner profile data;

[1482] means including a generative artificial intelligence model that performs analysis based on the profile data;

[1483] means for providing an individually optimized learning plan generated by the generative artificial intelligence model;

[1484] means for collecting progress and feedback on said learning plan;

[1485] means for analyzing said feedback to optimize said learning plan;

[1486] A system including:

[1487] (Claim 2)

[1488] 2. The system of claim 1, further comprising means for collecting data including the learner's goals, interests, skill level, and learning style as the profile data.

[1489] (Claim 3)

[1490] 10. The system of claim 1, wherein the generative artificial intelligence model, when generating the learning plan, provides a plan including learning materials, courses, and a schedule.

[1491] "Example 1"

[1492] (Claim 1)

[1493] means for collecting user profile data;

[1494] means including a generative AI model that performs analysis based on the profile data;

[1495] means for providing an individually optimized learning plan generated by the generative AI model;

[1496] means for collecting progress and feedback on said learning plan;

[1497] means for analyzing said feedback to optimize said learning plan;

[1498] a means for using the generated prompt sentence for parsing;

[1499] A system including:

[1500] (Claim 2)

[1501] 10. The system of claim 1, further comprising means for collecting data including learner goals, interests, skill levels, and learning styles.

[1502] (Claim 3)

[1503] 10. The system of claim 1, wherein the generative AI model, in generating the learning plan, provides a plan including learning materials, courses, and a schedule.

[1504] "Application Example 1"

[1505] (Claim 1)

[1506] a means of collecting learner profile data;

[1507] means including a generative artificial intelligence model that performs analysis based on the profile data;

[1508] means for providing an individually optimized learning plan generated by the generative artificial intelligence model;

[1509] means for collecting progress and feedback on said learning plan;

[1510] means for analyzing said feedback to optimize said learning plan;

[1511] a means for providing learning content via a smartphone application;

[1512] A system including:

[1513] (Claim 2)

[1514] 2. The system of claim 1, further comprising means for collecting data including the learner's goals, interests, skill level, and learning style as the profile data.

[1515] (Claim 3)

[1516] 10. The system of claim 1, wherein the generative artificial intelligence model, when generating the learning plan, provides a plan including learning materials, courses, and a schedule.

[1517] "Example 2: Combining Emotion Engines"

[1518] (Claim 1)

[1519] a means of collecting learner profile data;

[1520] means including a generative artificial intelligence model that performs analysis based on the profile data;

[1521] a means for optimizing the learning plan using an emotion engine that captures emotion data of the user;

[1522] means for generating an individually optimized learning plan based on data obtained from the generative artificial intelligence model and emotion engine;

[1523] means for transmitting the generated learning plan to a learner's terminal;

[1524] means for collecting progress and feedback on said learning plan;

[1525] means for analyzing said feedback to further optimize said learning plan;

[1526] A system including:

[1527] (Claim 2)

[1528] 10. The system of claim 1, further comprising means for collecting data regarding learner goals, interests, skill levels, and learning styles.

[1529] (Claim 3)

[1530] 10. The system of claim 1, wherein the generative artificial intelligence model provides a plan including learning materials, courses, and a learning schedule, and inserts appropriate breaks based on emotional data.

[1531] "Application example 2 when combining emotion engines"

[1532] (Claim 1)

[1533] A means for collecting learner attribute data;

[1534] means including a generative artificial intelligence model that performs analysis based on the attribute data;

[1535] means for providing an individually optimized learning plan generated by the generative artificial intelligence model;

[1536] means for collecting progress and responses to said learning plan;

[1537] means for analyzing said responses to optimize said learning plan;

[1538] a means for transmitting the optimized learning plan to the device;

[1539] A system including:

[1540] (Claim 2)

[1541] 2. The system according to claim 1, further comprising means for collecting data including the learner's goals, interests, ability level, and learning method as the attribute data.

[1542] (Claim 3)

[1543] 10. The system of claim 1, wherein the generative artificial intelligence model, when generating the learning plan, provides a plan including learning materials, courses, and a schedule. [Explanation of symbols]

[1544] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting learner profile data; means including a generative artificial intelligence model that performs analysis based on the profile data; means for providing an individually optimized learning plan generated by the generative artificial intelligence model; means for collecting progress and feedback on said learning plan; means for analyzing said feedback to optimize said learning plan; A system including:

2. 2. The system of claim 1, further comprising means for collecting data including the learner's goals, interests, skill level, and learning style as said profile data.

3. 10. The system of claim 1, wherein the generative artificial intelligence model, in generating the learning plan, provides a plan including learning materials, courses, and a schedule.

Images