System

Abstract

A system is provided.SOLUTION: A system comprising: means for customizing a learning path based on a user's interests and current skill level; means for analyzing the user's learning history and questionnaire responses to provide optimal learning content; and means for monitoring the user's learning progress and dynamically updating the learning path based on the data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Rapid technological advances in modern society have created a growing need to efficiently acquire new knowledge and skills. However, individual learning styles and skill levels vary, making it difficult to provide an effective learning path for all users. Furthermore, there is a lack of opportunities to go beyond simply acquiring knowledge and turn it into practical skills, and there is also a lack of support information for obtaining qualifications. It is also necessary to design systems that promote collaboration between users and increase their motivation to learn. [Means for solving the problem]

[0005] The present invention is a system that includes a means for customizing a learning path based on a user's interests and current skill level, a means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, and a means for monitoring the user's learning progress and dynamically updating the learning path based on that data. It also includes a means for proposing practical projects based on the user's skill level, monitoring their progress, and providing feedback as needed. It also includes a means for matching users with the same learning goals to promote collaboration and support communication, and a means for providing information on events and seminars related to qualification acquisition. This makes it possible to provide an optimized learning environment for each user and support efficient knowledge acquisition and skill acquisition.

[0006] "User" refers to an individual who uses the system to learn or obtain qualifications.

[0007] "Interests" refer to areas or topics that a user is interested in.

[0008] "Skill level" refers to a user's current level of technical ability and knowledge.

[0009] A "learning path" refers to a series of learning content or activities that a user progresses through sequentially.

[0010] "Customization" refers to optimizing learning content based on each user's different conditions and needs.

[0011] "Generative AI" refers to artificial intelligence technology that generates optimal learning paths and content based on user information.

[0012] "Learning content" refers to learning materials, resources, question sets, etc. that users use to study.

[0013] "Learning history" refers to data that records the learning content and progress a user has made to date.

[0014] "Dynamic updates" refers to changing the content in real time in response to changes in information or circumstances.

[0015] "Practical projects" refer to specific tasks or projects that allow students to test the knowledge and skills they have learned in real-world applications.

[0016] A "progress" system is one that includes the ability to monitor and record data as users progress through their studies or projects.

[0017] "Feedback" refers to the evaluation and advice users receive as they progress through their studies and projects.

[0018] "Users with the same learning goals" refers to multiple users who have a common learning objective or are aiming to obtain a qualification.

[0019] "Matching" refers to optimally connecting users with common learning goals and needs.

[0020] "Collaboration" refers to multiple users working together to advance learning or work on a project.

[0021] "Means to support communication" refers to methods that provide functionality for users to exchange messages and information.

[0022] "Information about events and seminars related to obtaining qualifications" refers to information about qualification exams and related courses and seminars. [Brief explanation of the drawings]

[0023] [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

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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."

[0044] The present invention is a system that proposes optimal learning paths based on a user's interests and skill level, providing effective and practical learning. This system uses generative AI to provide optimal learning content for each user while exchanging data between a server, terminals, and users. Specific embodiments are described below.

[0045] Basic system configuration

[0046] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI module. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI module, located within the server, is responsible for analyzing user data and generating the optimal learning path.

[0047] User interest and skill level settings

[0048] When a user starts learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an AI module to generate an initial learning path.

[0049] Creating and delivering learning paths

[0050] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface, where the user can proceed sequentially through the presented learning content and activities.

[0051] Learning progress management

[0052] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI module to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[0053] Providing practical projects

[0054] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes the user's skill level and learning progress and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[0055] Supporting collaboration and communication

[0056] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[0057] Support for obtaining qualifications and providing event information

[0058] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[0059] Specific examples

[0060] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[0061] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] User registration and profile settings

[0065] User: Visits the app, registers, and fills out a form about their interests and current skill level.

[0066] Terminal: The entered user information is encrypted and sent to the server.

[0067] Step 2:

[0068] Receiving and storing profile data

[0069] Server: Stores the received user data in a database.

[0070] Server: Analyzes the user's interests and skill level and sends requests to the Generative AI module to generate an initial learning path.

[0071] Step 3:

[0072] Generate a learning path

[0073] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[0074] Server: Sends the generated learning path in JSON format to the user's device.

[0075] Step 4:

[0076] View Learning Paths

[0077] Terminal: Parses the received learning path and displays it in the user interface.

[0078] Users: Review suggested learning paths and select learning content to get started.

[0079] Step 5:

[0080] Learning progress and progress management

[0081] Users: View selected learning content and take quizzes and tests.

[0082] Device: Sends the user's answers and progress to the server.

[0083] Server: Stores the received progress data in a database and checks with the generation AI module whether the next step learning path is appropriate.

[0084] Step 6:

[0085] Dynamic Update Implementation

[0086] Server: Based on the progress data, the generative AI module decides whether to dynamically update the learning path.

[0087] Server: Generates new learning paths as needed and sends them to the user device.

[0088] Step 7:

[0089] Practical project proposals

[0090] Server: Searches for suitable hands-on projects based on the user's progress and skill level.

[0091] Server: Sends recommended projects to the user's device in JSON format.

[0092] Terminal: Display project details in the interface.

[0093] User: Select a proposed project and get started.

[0094] Step 8:

[0095] Project progress management

[0096] User: Manages projects and records deliverables and progress.

[0097] Terminal: Sends user record data to the server.

[0098] Server: Analyzes the progress data and generates and sends feedback to the user as needed.

[0099] Step 9:

[0100] Supporting communication and collaboration

[0101] Server: Matches users with the same learning goals and notifies the user's device of this information.

[0102] On your device: View matched user information and group chat options.

[0103] Users: Join the community and share information in chats and forums.

[0104] Step 10:

[0105] Support and information for obtaining qualifications

[0106] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[0107] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[0108] Users: Participate in credentials and events and feed progress and results back into the system.

[0109] This process step ensures that users learn efficiently, always enjoying a personalized learning path, and develop their skills through hands-on projects and community activities.

[0110] Example 1

[0111] 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."

[0112] Conventional learning systems do not adequately provide personalized learning paths tailored to each user's interests and skill level. It is also difficult to dynamically update the learning path based on the user's learning progress, making it difficult to provide effective learning. Furthermore, they lack practical project suggestions, information related to qualification acquisition, and support for collaboration between users. It is necessary to solve these issues and provide users with the optimal learning environment.

[0113] 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.

[0114] In this invention, the server

[0115] A means to customize a learning path based on the user's interests and current skill level;

[0116] A means for storing data sent from the user device on a server and analyzing it using a generative AI model;

[0117] a means for dynamically updating the learning path based on the generative AI model; and

[0118] a means for providing a customized learning path to a user device;

[0119] and a means for managing the user's learning progress on a server and analyzing it in real time.

[0120] This allows for personalized learning paths, real-time learning progress management, dynamic learning path updates, and more. It also effectively proposes practical projects tailored to each user's skill level, promotes collaboration between users, and provides information related to qualification acquisition.

[0121] "User" refers to an individual who uses the System to receive Learning Paths and Content.

[0122] "Server" refers to the central system that processes data submitted by users and generates and provides learning paths.

[0123] "Terminal" means a hardware device used by a user to access the system, including a PC or smartphone.

[0124] "Generative AI model" refers to an artificial intelligence model used to analyze a user's interests and skill level to generate an optimal learning path.

[0125] "Learning Path" refers to a learning path or course that is customized based on a user's individual skill level and interests.

[0126] "Customization" refers to the process of tailoring specific learning paths and content to meet a user's individual requirements and requirements.

[0127] "Real-time" refers to the time characteristic of instantly processing and reflecting the user's learning progress and data.

[0128] "Analysis" refers to the process by which our servers process the data submitted by users and extract the information needed to generate learning paths and content.

[0129] "Dynamic updates" refers to changing and optimizing the learning path in real time according to the user's learning progress.

[0130] "Practical projects" refer to assignments or tasks that are based on what the user has learned and are directly related to specific applications or practical work.

[0131] "Communication" refers to the process of exchanging information, opinions, and feedback between users. This feature includes methods such as chat and forums.

[0132] "Certification assistance" refers to the process of providing users with appropriate information and resources to prepare for a specific certification exam or qualification.

[0133] "Event information" refers to information about seminars, training courses, exams, etc. that are relevant to the user's interests and goals.

[0134] This invention relates to a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system features a mechanism that uses a generative AI model to provide optimal learning content for each user while exchanging data between a server, terminals, and users.

[0135] Basic system configuration

[0136] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI model. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI model, located on the server, is responsible for analyzing user data and generating the optimal learning path.

[0137] The specific hardware and software used

[0138] 1. User Device

[0139] Users access the system using a PC or smartphone. The user device sends initial setup information and learning progress information to the server and displays the received learning paths and content. The front end is built using HTML, CSS, and JavaScript.

[0140] 2. Server

[0141] The server processes the data sent by the user, stores it in a database, and then requests a generative AI model to generate a user-specific learning path and sends the generated path to the user's device. The backend is primarily written in Python and either Flask or Django.

[0142] 3. Generative AI Models

[0143] The generative AI model resides on a server and uses machine learning libraries such as Python and TensorFlow to analyze a user's interests and skill level and generate an optimal learning path.

[0144] Data processing and calculation

[0145] 1. User Interest and Skill Level Settings

[0146] When a user begins learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an initial learning path from the generative AI model.

[0147] 2. Creating and providing learning paths

[0148] The server uses the generative AI model to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on an interface, where the user can progress through the presented learning content and activities.

[0149] 3. Learning progress management

[0150] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI model to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[0151] 4. Providing practical projects

[0152] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes and evaluates the user's skill level and learning progress, and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[0153] 5. Supporting collaboration and communication

[0154] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[0155] 6. Support for obtaining qualifications and provision of event information

[0156] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[0157] Specific examples

[0158] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generative AI model. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[0159] Prompt Sentence Examples

[0160] To develop a system that generates a customized learning path based on a user's interests and skill level, and dynamically updates it as they progress, follow these steps:

[0161] 1. Provide a screen where users can enter their areas of interest and skill level.

[0162] 2. The input data is sent to the server and saved in the database.

[0163] 3. Generate a learning path based on the generative AI model and send it back to the user device.

[0164] 4. Manage users' learning progress in real time and update their learning paths as needed.

[0165] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[0166] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0167] Step 1: User Registration

[0168] Users access the system and enter their field of interest and current skill level. The information entered by the user is sent from the terminal to the server. This input data includes information such as "data science" or "beginner." This information is sent to the server and stored in a database.

[0169] Step 2: Data analysis

[0170] The server sends an analysis request to the generative AI model based on the user's stored interest and skill level data. The generative AI model uses Python and TensorFlow to generate an optimal learning path based on the user's profile. This involves data preprocessing, feature extraction, and model analysis. The analysis results include the optimal learning plan and course structure for the user.

[0171] Step 3: Providing a learning path

[0172] The learning path generated by the generative AI model is sent back to the server, which then sends it to the user's device. The user's device displays the received learning path on its screen, and the user begins learning by clicking the "Start" button. This output data includes the specific learning course names and order.

[0173] Step 4: Track your progress

[0174] As a user progresses with their studies, their progress and answer data are sent from their device to the server. The server stores this data in a database in real time and analyzes their progress and learning effectiveness. Progress data includes the ID of the completed task, the score, and the content of the answers.

[0175] Step 5: Update a Dynamic Learning Path

[0176] The server then requests the generative AI model to analyze the user's progress data again. The generative AI model dynamically updates the learning path based on the latest progress information and generates a new learning plan. The updated learning path is then sent back to the server, which then sends it to the user's device. This ensures that the user always receives optimally updated learning content.

[0177] Step 6: Propose a practical project

[0178] Once a user has completed a certain amount of learning, the server analyzes the user's skill level and progress data and suggests practical projects. The proposed projects are sent to the user's device along with information such as project details, required skills, and goals, and the user can then start the project based on this information.

[0179] Step 7: Providing community features

[0180] The server matches users with other users who have the same learning goals and promotes collaboration within the community. Users can communicate with other members through chat and forums and collaborate on their learning.

[0181] Step 8: Providing support for qualification acquisition and event information

[0182] The server collects information about related events and seminars and notifies the user's device in a timely manner based on the user's interests and goals. Based on this information, users can participate in qualification exams and related events to broaden their learning horizons.

[0183] The above is the specific program processing flow of the system. This system allows users to efficiently progress through individually customized learning paths and effectively acquire practical skills and knowledge.

[0184] (Application example 1)

[0185] 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."

[0186] While traditional learning systems can provide learning paths based on a user's interests and skill level, they lack the ability to personalize the learning process for specific product information and provide appropriate product learning content based on the user's progress. Furthermore, there are insufficient means to provide effective learning paths to promote purchasing decisions in physical and virtual stores. Furthermore, the lack of a mechanism for dynamically suggesting related product information and special offers makes it difficult to provide an optimal purchasing experience for users.

[0187] 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.

[0188] In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, and a means for providing product information based on the product category selected by the user and generating a personalized learning path, thereby enabling the user to deepen their product knowledge while receiving optimal product information and benefits in a timely manner.

[0189] definition statement

[0190] "User Interest" refers to the level of interest a user has in a particular topic or field.

[0191] "Skill level" indicates a user's level of knowledge or ability in a particular field or topic.

[0192] A "learning path" is a customized set of learning steps that a user must take to achieve a specific goal or skill.

[0193] "Learning history" refers to records of a user's past learning activities and their results.

[0194] "Survey Responses" represent information provided by users about their individual learning needs and interests.

[0195] "Analysis" refers to the process of using user-provided data to derive meaning and determine learning paths and content.

[0196] "Optimal learning content" refers to learning materials and learning materials that are presented in a format that best suits a user's interests and skill level.

[0197] "Dynamic updates" means that learning paths and content are revised and changed at any time based on real-time data such as the user's progress.

[0198] "Product category" refers to a specific product group and refers to the product classification that the user is learning about.

[0199] "Product Information" means details about a particular product, including its description, uses, and benefits.

[0200] "Personalized learning path" means learning steps that are customized based on an individual user's interests and skill level.

[0201] "Learning progress" refers to how far a user has progressed in the process of acquiring a targeted skill or knowledge.

[0202] "Relevant Product Information and Special Offers" refers to relevant product details and special offers that are tailored to your interests and educational progression.

[0203] "Project Progress" refers to how well a user has accomplished a given task or assignment.

[0204] "Feedback" refers to evaluations and advice provided to users regarding their actions and progress.

[0205] MODE FOR CARRYING OUT THE INVENTION

[0206] This invention is a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system consists of a user terminal, a server, and a generation AI module.

[0207] Basic system configuration

[0208] This system consists of a user device (such as a smartphone or PC), a server, and a generative AI module. The user device provides the interface that allows users to access the system and progress through their studies. The server processes data sent by users and generates learning paths and content. The generative AI module is located within the server and is used to analyze user data and generate optimal learning paths.

[0209] Hardware and software used

[0210] Hardware: Smartphone (iOS / Android), PC.

[0211] Software: Mobile application frameworks (e.g., Flutter), backends (e.g., Firebase, Node.js), generative AI modules (e.g., GPT-3.5, BERT), databases (e.g., MongoDB).

[0212] User interest and skill level settings

[0213] When starting learning, users first input the product categories they are interested in and their current skill level. This input is sent to the server via the user's device and stored in a database.

[0214] Example prompt sentence:

[0215] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[0216] Creating and delivering learning paths

[0217] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[0218] Learning progress management

[0219] As the user progresses with their learning, their progress and answer data are sent from their device to the server, where it is recorded in a database. The server monitors this in real time and dynamically updates the learning path as needed by requesting the generative AI module.

[0220] Product information and learning

[0221] Based on the product category selected by the user, it provides the most suitable product information, including product promotional videos, usage guides, and review information.

[0222] Providing practical projects

[0223] As users progress through their learning, they are given the opportunity to take on practical projects. The server analyzes the user's skill level and learning progress and suggests appropriate projects.

[0224] Providing community features

[0225] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device of this match.

[0226] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0227] Program processing flow

[0228] Step 1: Enter your user information

[0229] The user terminal provides an interface for the user to input the product categories of interest and current skill level. The user fills in the necessary information in this form and presses the submit button. The input data includes the categories of interest and skill level. The terminal sends this data to the server.

[0230] Input: User's product interest category, skill level

[0231] Output: User data sent to the server

[0232] Step 2: Save user data

[0233] The server stores the user's product interest and skill level in a database (e.g., Firebase Firestore), which is used to generate a learning path.

[0234] Input: User's product interest category, skill level

[0235] Output: User data records in the database

[0236] Step 3: Generate a learning path

[0237] The server calls a generation AI module (e.g., GPT-3.5) based on the saved user data to generate a learning path. The generation AI module is provided with the following prompt:

[0238] Example prompt sentence:

[0239] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[0240] Input: User data, prompt

[0241] Output: The generated training path

[0242] Step 4: Providing learning paths

[0243] The server sends the learning path received from the generation AI module to the user device, which displays the learning path on its interface, allowing the user to proceed with the learning.

[0244] Input: Generated learning path

[0245] Output: The learning path displayed on the user's device

[0246] Step 5: Monitor your progress

[0247] As a user progresses through their studies, their device sends their progress status to the server, which monitors it in real time and records it in a database as progress data.

[0248] Input: User's learning progress data

[0249] Output: Progress record in database

[0250] Step 6: Dynamically Update Learning Paths

[0251] The server analyzes the progress data and dynamically updates the learning path by resubmitting the AI ​​generation module as needed. The updated learning path is then sent back to the user's device for display.

[0252] Input: Progress data

[0253] Output: Updated learning path

[0254] Step 7: Provide product information

[0255] Based on the product category selected by the user, the server collects related product information (such as promotional videos, usage guides, reviews, etc.) and provides it to the user's terminal.

[0256] Input: Product categories that the user is interested in

[0257] Output: Related product information

[0258] Step 8: Propose a practical project

[0259] Once the user has progressed to a certain level in their learning, the server will suggest an appropriate practical project based on the user's skill level and progress data, and the project details will be displayed on the user's device.

[0260] Input: Skill level, progress data

[0261] Output: Proposed project details

[0262] Step 9: Providing community features

[0263] The server matches users with other users who have the same learning goals based on their progress and learning goals, and notifications are sent to users' devices, allowing them to join the community and communicate.

[0264] Input: progress data, learning goals

[0265] Output: Matching notification

[0266] Through each of these steps, users receive the optimal learning path and relevant content, enabling them to learn more effectively.

[0267] 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.

[0268] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[0269] Basic system configuration

[0270] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[0271] User interests, skill level and emotional preferences

[0272] When users register for the app, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[0273] Creating and delivering learning paths

[0274] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[0275] Learning progress management and emotion analysis

[0276] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[0277] Providing hands-on projects and emotional feedback

[0278] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[0279] Supporting collaboration and communication

[0280] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[0281] Support and information for obtaining qualifications

[0282] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[0283] Specific examples

[0284] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[0285] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[0286] The processing flow will be explained below.

[0287] Step 1:

[0288] User registration and profile settings

[0289] User: Visits the app and registers, providing their interests, current skill level, and active sentiment data.

[0290] Terminal: The entered user information and emotional data are encrypted and sent to the server.

[0291] Step 2:

[0292] Receiving and storing profile data and emotional data

[0293] Server: Stores the received user data and emotion data in a database.

[0294] Server: Analyzes user interests, skill level, and emotional data and asks the AI ​​module to generate an initial learning path.

[0295] Step 3:

[0296] Generating learning paths and analyzing emotion data

[0297] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[0298] Server: The emotion engine analyzes the emotion data and adjusts the learning path based on the user's emotional state.

[0299] Server: Sends the generated learning path in JSON format to the user's device.

[0300] Step 4:

[0301] View Learning Paths

[0302] Terminal: Parses the received learning path and displays it in the user interface.

[0303] Users: Review suggested learning paths and select learning content to get started.

[0304] Step 5:

[0305] Learning progress and progress management and emotional data collection

[0306] Users: View selected learning content and take quizzes and tests.

[0307] Device: Sends the user's answers, progress, and real-time emotional data to the server.

[0308] Server: Stores the received progress data and emotion data in a database, and checks with the generative AI module and emotion engine whether the next learning step is appropriate.

[0309] Step 6:

[0310] Dynamic learning paths and content updates

[0311] Server: Based on progress and emotion data, the generative AI module dynamically updates the learning path.

[0312] Server: The emotion engine adjusts learning content based on the emotional state.

[0313] Server: Sends updated learning paths and content to user devices.

[0314] Step 7:

[0315] Practical project proposals

[0316] Server: Searches for suitable practical projects based on the user's progress data, skill level, and sentiment data.

[0317] Server: Sends recommended projects to the user's device in JSON format.

[0318] Terminal: Display project details in the interface.

[0319] User: Select a proposed project and get started.

[0320] Step 8:

[0321] Project Progression and Emotional Feedback

[0322] User: Work on projects and record deliverables, progress, and sentiment data.

[0323] Terminal: Sends the user's recorded data and emotional data to the server.

[0324] Server: Analyzes progress and emotion data, generates feedback as needed, and sends it to the user.

[0325] Step 9:

[0326] Supporting communication and collaboration

[0327] Server: Matches users with the same learning goals and notifies the user's device of this information.

[0328] On your device: View matched user information and group chat options.

[0329] Users: Join the community and share information in chats and forums.

[0330] Step 10:

[0331] Support and information for obtaining qualifications

[0332] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[0333] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[0334] Users: Participate in credentials and events and feed progress and results back into the system.

[0335] Example 2

[0336] 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."

[0337] Conventional learning systems are unable to provide learning paths based on the user's interests and skill level, or to take real-time emotional data into account. As a result, they are unable to optimally control fluctuations in learning efficiency due to the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features such as dynamically updating learning paths based on learning progress and emotional data, or suggesting appropriate practical projects, making it difficult to maximize users' learning goals and motivation.

[0338] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and real-time emotional data to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, a means for generating and updating an appropriate learning path using a generative AI model, and a means for analyzing the user's emotional state using an emotional engine. This makes it possible to provide an optimal learning path for each individual's learning progress and skill level while taking into account the user's real-time emotional data, thereby maximizing the effectiveness of learning.

[0339] "User" refers to an individual or group who uses a learning system to carry out learning activities.

[0340] "Server" refers to the computer system that processes data sent by users and generates and provides learning paths and content.

[0341] "User device" refers to the device used by a user to access the learning system and display and operate the learning path and content, including, for example, a PC or smartphone.

[0342] A "learning path" refers to a learning progression or content that is customized based on a user's interests and skill level.

[0343] A "generative AI model" refers to an artificial intelligence algorithm that generates an optimal learning path based on user data.

[0344] An "emotion engine" is a system that analyzes users' real-time emotional data and feeds the results back into learning paths and content generation.

[0345] "Real-time emotional data" refers to data that measures and analyzes a user's emotional state in real time.

[0346] "Learning Content" refers to the materials, activities, questions, and other content that guide users through their learning path.

[0347] "Study progress data" refers to data that records the progress and results of a user's studies.

[0348] "Dynamic learning path updating" refers to the process of changing and optimizing the learning path in real time according to the user's progress and emotional state.

[0349] "Hands-on projects" refer to tasks or activities that are close to real-world applications or work that are offered as part of a learning path.

[0350] "Feedback" refers to information such as advice, suggestions for improvement, and evaluations provided based on the user's learning progress and emotional data.

[0351] "Communication functions" refers to functions such as chat and forums that allow users to exchange information, consult, and learn collaboratively with other users.

[0352] "Event and seminar information" refers to information on courses and information sessions related to obtaining qualifications and improving skills.

[0353] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[0354] Basic system configuration

[0355] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[0356] User interests, skill level and emotional preferences

[0357] When users register for the application, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[0358] Creating and delivering learning paths

[0359] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[0360] Learning progress management and emotion analysis

[0361] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[0362] Providing hands-on projects and emotional feedback

[0363] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[0364] Supporting collaboration and communication

[0365] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[0366] Support and information for obtaining qualifications

[0367] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[0368] Specific examples

[0369] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[0370] Prompt Sentence Examples

[0371] Example prompts to input to a generative AI model:

[0372] "User A is interested in data science. His current skill level is beginner. What learning path should I suggest to him to advance his learning? Also, his real-time sentiment data shows that he is currently highly motivated."

[0373] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[0374] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0375] Step 1: User registration and data provision

[0376] Input: Users access the system using a PC or smartphone and enter their areas of interest, current skill level, and real-time emotional data.

[0377] Data processing: The user terminal converts the input data into a data structure such as JSON format.

[0378] Output: The user terminal sends the converted data to the server.

[0379] Specific operation: The user enters data into the input form and presses the "Submit" button, which sends the data to the server.

[0380] Step 2: The server saves the data to the database

[0381] Input: User interests, skill level, and emotional data sent from the device.

[0382] Data processing: The server parses the received data and splits it into the required fields.

[0383] Output: The server stores the split data in the database.

[0384] What happens: The server receives the data and stores it in the database as a new user.

[0385] Step 3: Generate an initial learning path

[0386] Input: User interests, skill level, and sentiment data stored in a database.

[0387] Data calculation: The server sends these data to the generative AI model and asks it to generate an initial learning path.

[0388] Output: The initial training path returned by the generative AI model.

[0389] How it works: The generative AI model analyzes user data and generates an optimal learning path, which is then sent back to the server.

[0390] Step 4: Providing learning paths

[0391] Input: The initial training path returned from the generative AI model.

[0392] Data processing: The server converts the learning path into a format that can be displayed on the user's device.

[0393] Output: The server sends the converted learning path to the user device.

[0394] Specific operation: The user device receives the learning path and displays it on the screen. The user confirms the displayed content and begins learning.

[0395] Step 5: Tracking learning progress and analyzing emotions

[0396] Input: User learning progress data, answer data, and real-time sentiment data.

[0397] Data calculation: The user device collects progress data and emotion data and sends them to the server, which monitors them in real time and requests analysis.

[0398] Output: Based on the analysis results, the server dynamically updates the learning path.

[0399] Specific operation: The server requests the emotion engine and generative AI model to update the learning path based on the analysis results. The updated learning path is then sent to the user's device.

[0400] Step 6: Providing practical projects and feedback

[0401] Input: User skill level, learning progress, and emotional data.

[0402] Data calculation: The server proposes appropriate practical projects based on this data and sends them to the user's device.

[0403] Output: A user initiates a project and sends progress and emotional feedback to the server, which then provides feedback based on that data.

[0404] Specific operation: The user starts the proposed project, and the device collects progress data and emotion data and sends them to the server, which analyzes the data and sends appropriate feedback back to the user device.

[0405] Step 7: Support collaboration and communication

[0406] Input: User's learning goals, progress data, and sentiment data.

[0407] Data calculation: The server matches the optimal learning group based on this data and notifies the user device.

[0408] Output: Provides an interface for users to join learning groups and communicate with other users.

[0409] Specific operation: The user's device displays learning group information and provides chat and forum functions, allowing users to exchange information with other users.

[0410] Step 8: Support and information for obtaining qualifications

[0411] Input: Event and seminar information related to qualification acquisition, user learning progress data.

[0412] Data calculation: The server collects relevant information and notifies the user terminal in a timely manner.

[0413] Output: User access to qualification exam information and related events.

[0414] Specific operation: The user's device displays qualification acquisition information and event information, and the user adjusts their study plan based on that information.

[0415] (Application example 2)

[0416] 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."

[0417] Conventional learning systems have been inadequate in providing learning paths that take into account the user's interests and skill level. Furthermore, they do not utilize real-time emotional data to provide optimal learning content or personalize the user's purchasing experience. This makes it difficult to improve the efficiency of learning and the quality of the purchasing experience.

[0418] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for customizing a learning path based on the user's interests and current skill level, means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, means for monitoring the user's learning progress and dynamically updating the learning path based on that data, means for collecting and analyzing the user's emotional data in real time and recommending products and services based on the analysis results, and means for suggesting optimal products and services based on the user's purchasing history and interests. This makes it possible to provide a more personalized learning experience and purchasing experience by utilizing the user's emotional data and purchasing history.

[0419] "User interests" refers to the areas or topics that interest users.

[0420] "Current skill level" refers to the level of ability and knowledge that the user currently possesses.

[0421] A "learning path" is a plan of optimal learning order and content based on a user's interests and skill level.

[0422] "Customization" means adjusting a system or content to suit a specific user.

[0423] "Learning history" is data that records what a user has learned in the past and their progress.

[0424] "Survey responses" are data that record the opinions and feelings provided by users.

[0425] "Optimal learning content" refers to the educational materials and learning activities that best suit a user's interests and skill level.

[0426] "Dynamic updating" means analyzing information in real time and making changes to systems and plans as needed.

[0427] "Emotional data" refers to data that represents a user's psychological state or emotions.

[0428] "Real-time collection and analysis" means instantly acquiring and analyzing data as it occurs in the present moment.

[0429] "Recommendation" means suggesting a particular product or service to a user.

[0430] "Purchase history" is a record of products and services a user has purchased in the past.

[0431] "Personalization" means customizing something to suit each individual user.

[0432] "Learning content" is the collection of information, knowledge, and skills that users need to learn.

[0433] "Dynamic adjustment" means instantly changing content or plans according to the current situation.

[0434] This invention is a system for providing optimal learning and shopping experiences by utilizing a user's interests, current skill level, purchase history, and real-time emotional data. The system is composed of a server, a user terminal, an emotional engine, and a generative AI module.

[0435] First, the user device (smartphone) provides an interface for users to access the system and proceed with learning and shopping. The user's interests, current skill level, purchasing history, and real-time emotional data are sent from the user device to the server.

[0436] The server receives this information and stores it in a database. The generative AI module analyzes the stored data and generates optimal learning paths and product recommendations for the user. At this time, the emotion engine analyzes the user's emotional data in real time and also feeds the analysis results back to the generative AI module.

[0437] For example, by using a smartphone camera, users can provide emotional data in real time. This emotional data is analyzed by the emotion engine, and the analysis results are fed back to the generative AI module. The generative AI module dynamically adjusts the learning content and products based on the analysis results and provides them to the user.

[0438] When a user is looking at a particular product in a store, the system will recognize the product through the smartphone camera and recommend related products and services based on past purchase history and current emotional data. For example, if the user is in the clothing section, the system will suggest related accessories and outfits based on past purchase history and current emotional state.

[0439] Below are some example prompts to input to a generative AI model:

[0440] "When a user visits a store and views products through the camera, recommend related products based on their past purchase history and real-time sentiment data. User's interest area: {Interest area} User's purchase history: {Purchase history} Current sentiment: {Sentiment} Display recommended products in a list format, along with reviews and ratings for each product."

[0441] The system not only enables users to efficiently progress through personalized learning paths, but also provides interest- and emotion-based product recommendations, improving the quality of the learning and shopping experience and increasing user satisfaction.

[0442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0443] Step 1:

[0444] The user terminal receives data on user interests, current skill level, and purchase history as input. This data is sent from the user terminal to the server. The data processing performed on the terminal is normalization of the input data and sending it to the database. The output is the normalized data and its sending status.

[0445] Step 2:

[0446] The server receives data sent from the user terminal and stores it in the database. The specific operations of the server are to receive data, write it to the database, and confirm the success status of the write. The input is the data from the user terminal, and the output is the data stored in the database and its storage status.

[0447] Step 3:

[0448] The user device captures the user's face through a camera and obtains emotional data in real time. This emotional data is preprocessed on the device and sent to the server. The specific operations are to start the camera, detect the face, analyze the emotional data, and send the data to the server. The input is the video data from the camera, and the output is the analyzed emotional data.

[0449] Step 4:

[0450] Emotion data received by the server is analyzed by the emotion engine. The emotion engine's operation is to analyze the received data and feed the results back to the generation AI module. The input is real-time emotion data, and the output is analyzed emotional state data.

[0451] Step 5:

[0452] The server uses a generative AI module to generate optimal learning paths and product recommendations based on the user's interests, skill level, purchase history, and real-time emotional data. Specific operations include inputting data into the generative AI model, analyzing the data using the generative model, and generating results. The input is all user-related data, and the output is a customized learning path or product recommendation list.

[0453] Step 6:

[0454] The server sends the generated learning path and product recommendations to the user's device. Specific operations include sending data and checking the transmission status. The input is the generated learning path and recommendation list, and the output is the display data for the user's device.

[0455] Step 7:

[0456] The user device displays the received learning path and product recommendations on its interface, helping users to smoothly progress through their learning and shopping. Specific operations include receiving data, updating the display interface, and accepting user operations. The input is the display data from the server, and the output is the displayed interface and the user operation log.

[0457] Step 8:

[0458] As the user continues their learning or shopping, progress data, purchasing status, and emotional data are collected again and sent to the server. The specific operations on the device are to record progress and purchasing status, reacquire emotional data, and resend the data to the server. The input is the user's operation data, and the output is the raw data to be analyzed again.

[0459] Step 9:

[0460] The server dynamically updates the learning path and product recommendations based on the received progress data, purchasing status, and emotion data. Specific operations include reanalyzing the data, regenerating the learning path and recommendation list, and retransmitting it to the user device. The input is the updated usage data, and the output is the updated learning path and recommendation list.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] [Second embodiment]

[0465] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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).

[0471] 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.

[0472] 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.

[0473] 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.

[0474] 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.

[0475] In the smart glasses 214, 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.

[0476] 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."

[0477] The present invention is a system that proposes optimal learning paths based on a user's interests and skill level, providing effective and practical learning. This system uses generative AI to provide optimal learning content for each user while exchanging data between a server, terminals, and users. Specific embodiments are described below.

[0478] Basic system configuration

[0479] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI module. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI module, located within the server, is responsible for analyzing user data and generating the optimal learning path.

[0480] User interest and skill level settings

[0481] When a user starts learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an AI module to generate an initial learning path.

[0482] Creating and delivering learning paths

[0483] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface, where the user can proceed sequentially through the presented learning content and activities.

[0484] Learning progress management

[0485] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI module to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[0486] Providing practical projects

[0487] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes the user's skill level and learning progress and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[0488] Supporting collaboration and communication

[0489] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[0490] Support for obtaining qualifications and providing event information

[0491] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[0492] Specific examples

[0493] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[0494] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[0495] The processing flow will be explained below.

[0496] Step 1:

[0497] User registration and profile settings

[0498] User: Visits the app, registers, and fills out a form about their interests and current skill level.

[0499] Terminal: The entered user information is encrypted and sent to the server.

[0500] Step 2:

[0501] Receiving and storing profile data

[0502] Server: Stores the received user data in a database.

[0503] Server: Analyzes the user's interests and skill level and sends requests to the Generative AI module to generate an initial learning path.

[0504] Step 3:

[0505] Generate a learning path

[0506] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[0507] Server: Sends the generated learning path in JSON format to the user's device.

[0508] Step 4:

[0509] View Learning Paths

[0510] Terminal: Parses the received learning path and displays it in the user interface.

[0511] Users: Review suggested learning paths and select learning content to get started.

[0512] Step 5:

[0513] Learning progress and progress management

[0514] Users: View selected learning content and take quizzes and tests.

[0515] Device: Sends the user's answers and progress to the server.

[0516] Server: Stores the received progress data in a database and checks with the generation AI module whether the next step learning path is appropriate.

[0517] Step 6:

[0518] Dynamic Update Implementation

[0519] Server: Based on the progress data, the generative AI module decides whether to dynamically update the learning path.

[0520] Server: Generates new learning paths as needed and sends them to the user device.

[0521] Step 7:

[0522] Practical project proposals

[0523] Server: Searches for suitable hands-on projects based on the user's progress and skill level.

[0524] Server: Sends recommended projects to the user's device in JSON format.

[0525] Terminal: Display project details in the interface.

[0526] User: Select a proposed project and get started.

[0527] Step 8:

[0528] Project progress management

[0529] User: Manages projects and records deliverables and progress.

[0530] Terminal: Sends user record data to the server.

[0531] Server: Analyzes the progress data and generates and sends feedback to the user as needed.

[0532] Step 9:

[0533] Supporting communication and collaboration

[0534] Server: Matches users with the same learning goals and notifies the user's device of this information.

[0535] On your device: View matched user information and group chat options.

[0536] Users: Join the community and share information in chats and forums.

[0537] Step 10:

[0538] Support and information for obtaining qualifications

[0539] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[0540] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[0541] Users: Participate in credentials and events and feed progress and results back into the system.

[0542] This process step ensures that users learn efficiently, always enjoying a personalized learning path, and develop their skills through hands-on projects and community activities.

[0543] Example 1

[0544] 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."

[0545] Conventional learning systems do not adequately provide personalized learning paths tailored to each user's interests and skill level. It is also difficult to dynamically update the learning path based on the user's learning progress, making it difficult to provide effective learning. Furthermore, they lack practical project suggestions, information related to qualification acquisition, and support for collaboration between users. It is necessary to solve these issues and provide users with the optimal learning environment.

[0546] 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.

[0547] In this invention, the server

[0548] A means to customize a learning path based on the user's interests and current skill level;

[0549] A means for storing data sent from the user device on a server and analyzing it using a generative AI model;

[0550] a means for dynamically updating the learning path based on the generative AI model; and

[0551] a means for providing a customized learning path to a user device;

[0552] and a means for managing the user's learning progress on a server and analyzing it in real time.

[0553] This allows for personalized learning paths, real-time learning progress management, dynamic learning path updates, and more. It also effectively proposes practical projects tailored to each user's skill level, promotes collaboration between users, and provides information related to qualification acquisition.

[0554] "User" refers to an individual who uses the System to receive Learning Paths and Content.

[0555] "Server" refers to the central system that processes data submitted by users and generates and provides learning paths.

[0556] "Terminal" means a hardware device used by a user to access the system, including a PC or smartphone.

[0557] "Generative AI model" refers to an artificial intelligence model used to analyze a user's interests and skill level to generate an optimal learning path.

[0558] "Learning Path" refers to a learning path or course that is customized based on a user's individual skill level and interests.

[0559] "Customization" refers to the process of tailoring specific learning paths and content to meet a user's individual requirements and requirements.

[0560] "Real-time" refers to the time characteristic of instantly processing and reflecting the user's learning progress and data.

[0561] "Analysis" refers to the process by which our servers process the data submitted by users and extract the information needed to generate learning paths and content.

[0562] "Dynamic updates" refers to changing and optimizing the learning path in real time according to the user's learning progress.

[0563] "Practical projects" refer to assignments or tasks that are based on what the user has learned and are directly related to specific applications or practical work.

[0564] "Communication" refers to the process of exchanging information, opinions, and feedback between users. This feature includes methods such as chat and forums.

[0565] "Certification assistance" refers to the process of providing users with appropriate information and resources to prepare for a specific certification exam or qualification.

[0566] "Event information" refers to information about seminars, training courses, exams, etc. that are relevant to the user's interests and goals.

[0567] This invention relates to a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system features a mechanism that uses a generative AI model to provide optimal learning content for each user while exchanging data between a server, terminals, and users.

[0568] Basic system configuration

[0569] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI model. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI model, located on the server, is responsible for analyzing user data and generating the optimal learning path.

[0570] The specific hardware and software used

[0571] 1. User Device

[0572] Users access the system using a PC or smartphone. The user device sends initial setup information and learning progress information to the server and displays the received learning paths and content. The front end is built using HTML, CSS, and JavaScript.

[0573] 2. Server

[0574] The server processes the data sent by the user, stores it in a database, and then requests a generative AI model to generate a user-specific learning path and sends the generated path to the user's device. The backend is primarily written in Python and either Flask or Django.

[0575] 3. Generative AI Models

[0576] The generative AI model resides on a server and uses machine learning libraries such as Python and TensorFlow to analyze a user's interests and skill level and generate an optimal learning path.

[0577] Data processing and calculation

[0578] 1. User Interest and Skill Level Settings

[0579] When a user begins learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an initial learning path from the generative AI model.

[0580] 2. Creating and providing learning paths

[0581] The server uses the generative AI model to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on an interface, where the user can progress through the presented learning content and activities.

[0582] 3. Learning progress management

[0583] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI model to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[0584] 4. Providing practical projects

[0585] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes and evaluates the user's skill level and learning progress, and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[0586] 5. Supporting collaboration and communication

[0587] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[0588] 6. Support for obtaining qualifications and provision of event information

[0589] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[0590] Specific examples

[0591] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generative AI model. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[0592] Prompt Sentence Examples

[0593] To develop a system that generates a customized learning path based on a user's interests and skill level, and dynamically updates it as they progress, follow these steps:

[0594] 1. Provide a screen where users can enter their areas of interest and skill level.

[0595] 2. The input data is sent to the server and saved in the database.

[0596] 3. Generate a learning path based on the generative AI model and send it back to the user device.

[0597] 4. Manage users' learning progress in real time and update their learning paths as needed.

[0598] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[0599] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0600] Step 1: User Registration

[0601] Users access the system and enter their field of interest and current skill level. The information entered by the user is sent from the terminal to the server. This input data includes information such as "data science" or "beginner." This information is sent to the server and stored in a database.

[0602] Step 2: Data analysis

[0603] The server sends an analysis request to the generative AI model based on the user's stored interest and skill level data. The generative AI model uses Python and TensorFlow to generate an optimal learning path based on the user's profile. This involves data preprocessing, feature extraction, and model analysis. The analysis results include the optimal learning plan and course structure for the user.

[0604] Step 3: Providing a learning path

[0605] The learning path generated by the generative AI model is sent back to the server, which then sends it to the user's device. The user's device displays the received learning path on its screen, and the user begins learning by clicking the "Start" button. This output data includes the specific learning course names and order.

[0606] Step 4: Track your progress

[0607] As a user progresses with their studies, their progress and answer data are sent from their device to the server. The server stores this data in a database in real time and analyzes their progress and learning effectiveness. Progress data includes the ID of the completed task, the score, and the content of the answers.

[0608] Step 5: Update a Dynamic Learning Path

[0609] The server then requests the generative AI model to analyze the user's progress data again. The generative AI model dynamically updates the learning path based on the latest progress information and generates a new learning plan. The updated learning path is then sent back to the server, which then sends it to the user's device. This ensures that the user always receives optimally updated learning content.

[0610] Step 6: Propose a practical project

[0611] Once a user has completed a certain amount of learning, the server analyzes the user's skill level and progress data and suggests practical projects. The proposed projects are sent to the user's device along with information such as project details, required skills, and goals, and the user can then start the project based on this information.

[0612] Step 7: Providing community features

[0613] The server matches users with other users who have the same learning goals and promotes collaboration within the community. Users can communicate with other members through chat and forums and collaborate on their learning.

[0614] Step 8: Providing support for qualification acquisition and event information

[0615] The server collects information about related events and seminars and notifies the user's device in a timely manner based on the user's interests and goals. Based on this information, users can participate in qualification exams and related events to broaden their learning horizons.

[0616] The above is the specific program processing flow of the system. This system allows users to efficiently progress through individually customized learning paths and effectively acquire practical skills and knowledge.

[0617] (Application example 1)

[0618] 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."

[0619] While traditional learning systems can provide learning paths based on a user's interests and skill level, they lack the ability to personalize the learning process for specific product information and provide appropriate product learning content based on the user's progress. Furthermore, there are insufficient means to provide effective learning paths to promote purchasing decisions in physical and virtual stores. Furthermore, the lack of a mechanism for dynamically suggesting related product information and special offers makes it difficult to provide an optimal purchasing experience for users.

[0620] 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.

[0621] In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, and a means for providing product information based on the product category selected by the user and generating a personalized learning path, thereby enabling the user to deepen their product knowledge while receiving optimal product information and benefits in a timely manner.

[0622] definition statement

[0623] "User Interest" refers to the level of interest a user has in a particular topic or field.

[0624] "Skill level" indicates a user's level of knowledge or ability in a particular field or topic.

[0625] A "learning path" is a customized set of learning steps that a user must take to achieve a specific goal or skill.

[0626] "Learning history" refers to records of a user's past learning activities and their results.

[0627] "Survey Responses" represent information provided by users about their individual learning needs and interests.

[0628] "Analysis" refers to the process of using user-provided data to derive meaning and determine learning paths and content.

[0629] "Optimal learning content" refers to learning materials and learning materials that are presented in a format that best suits a user's interests and skill level.

[0630] "Dynamic updates" means that learning paths and content are revised and changed at any time based on real-time data such as the user's progress.

[0631] "Product category" refers to a specific product group and refers to the product classification that the user is learning about.

[0632] "Product Information" means details about a particular product, including its description, uses, and benefits.

[0633] "Personalized learning path" means learning steps that are customized based on an individual user's interests and skill level.

[0634] "Learning progress" refers to how far a user has progressed in the process of acquiring a targeted skill or knowledge.

[0635] "Relevant Product Information and Special Offers" refers to relevant product details and special offers that are tailored to your interests and educational progression.

[0636] "Project Progress" refers to how well a user has accomplished a given task or assignment.

[0637] "Feedback" refers to evaluations and advice provided to users regarding their actions and progress.

[0638] MODE FOR CARRYING OUT THE INVENTION

[0639] This invention is a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system consists of a user terminal, a server, and a generation AI module.

[0640] Basic system configuration

[0641] This system consists of a user device (such as a smartphone or PC), a server, and a generative AI module. The user device provides the interface that allows users to access the system and progress through their studies. The server processes data sent by users and generates learning paths and content. The generative AI module is located within the server and is used to analyze user data and generate optimal learning paths.

[0642] Hardware and software used

[0643] Hardware: Smartphone (iOS / Android), PC.

[0644] Software: Mobile application frameworks (e.g., Flutter), backends (e.g., Firebase, Node.js), generative AI modules (e.g., GPT-3.5, BERT), databases (e.g., MongoDB).

[0645] User interest and skill level settings

[0646] When starting learning, users first input the product categories they are interested in and their current skill level. This input is sent to the server via the user's device and stored in a database.

[0647] Example prompt sentence:

[0648] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[0649] Creating and delivering learning paths

[0650] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[0651] Learning progress management

[0652] As the user progresses with their learning, their progress and answer data are sent from their device to the server, where it is recorded in a database. The server monitors this in real time and dynamically updates the learning path as needed by requesting the generative AI module.

[0653] Product information and learning

[0654] Based on the product category selected by the user, it provides the most suitable product information, including product promotional videos, usage guides, and review information.

[0655] Providing practical projects

[0656] As users progress through their learning, they are given the opportunity to take on practical projects. The server analyzes the user's skill level and learning progress and suggests appropriate projects.

[0657] Providing community features

[0658] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device of this match.

[0659] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0660] Program processing flow

[0661] Step 1: Enter your user information

[0662] The user terminal provides an interface for the user to input the product categories of interest and current skill level. The user fills in the necessary information in this form and presses the submit button. The input data includes the categories of interest and skill level. The terminal sends this data to the server.

[0663] Input: User's product interest category, skill level

[0664] Output: User data sent to the server

[0665] Step 2: Save user data

[0666] The server stores the user's product interest and skill level in a database (e.g., Firebase Firestore), which is used to generate a learning path.

[0667] Input: User's product interest category, skill level

[0668] Output: User data records in the database

[0669] Step 3: Generate a learning path

[0670] The server calls a generation AI module (e.g., GPT-3.5) based on the saved user data to generate a learning path. The generation AI module is provided with the following prompt:

[0671] Example prompt sentence:

[0672] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[0673] Input: User data, prompt

[0674] Output: The generated training path

[0675] Step 4: Providing learning paths

[0676] The server sends the learning path received from the generation AI module to the user device, which displays the learning path on its interface, allowing the user to proceed with the learning.

[0677] Input: Generated learning path

[0678] Output: The learning path displayed on the user's device

[0679] Step 5: Monitor your progress

[0680] As a user progresses through their studies, their device sends their progress status to the server, which monitors it in real time and records it in a database as progress data.

[0681] Input: User's learning progress data

[0682] Output: Progress record in database

[0683] Step 6: Dynamically Update Learning Paths

[0684] The server analyzes the progress data and dynamically updates the learning path by resubmitting the AI ​​generation module as needed. The updated learning path is then sent back to the user's device for display.

[0685] Input: Progress data

[0686] Output: Updated learning path

[0687] Step 7: Provide product information

[0688] Based on the product category selected by the user, the server collects related product information (such as promotional videos, usage guides, reviews, etc.) and provides it to the user's terminal.

[0689] Input: Product categories that the user is interested in

[0690] Output: Related product information

[0691] Step 8: Propose a practical project

[0692] Once the user has progressed to a certain level in their learning, the server will suggest an appropriate practical project based on the user's skill level and progress data, and the project details will be displayed on the user's device.

[0693] Input: Skill level, progress data

[0694] Output: Proposed project details

[0695] Step 9: Providing community features

[0696] The server matches users with other users who have the same learning goals based on their progress and learning goals, and notifications are sent to users' devices, allowing them to join the community and communicate.

[0697] Input: progress data, learning goals

[0698] Output: Matching notification

[0699] Through each of these steps, users receive the optimal learning path and relevant content, enabling them to learn more effectively.

[0700] 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.

[0701] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[0702] Basic system configuration

[0703] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[0704] User interests, skill level and emotional preferences

[0705] When users register for the app, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[0706] Creating and delivering learning paths

[0707] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[0708] Learning progress management and emotion analysis

[0709] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[0710] Providing hands-on projects and emotional feedback

[0711] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[0712] Supporting collaboration and communication

[0713] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[0714] Support and information for obtaining qualifications

[0715] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[0716] Specific examples

[0717] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[0718] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[0719] The processing flow will be explained below.

[0720] Step 1:

[0721] User registration and profile settings

[0722] User: Visits the app and registers, providing their interests, current skill level, and active sentiment data.

[0723] Terminal: The entered user information and emotional data are encrypted and sent to the server.

[0724] Step 2:

[0725] Receiving and storing profile data and emotional data

[0726] Server: Stores the received user data and emotion data in a database.

[0727] Server: Analyzes user interests, skill level, and emotional data and asks the AI ​​module to generate an initial learning path.

[0728] Step 3:

[0729] Generating learning paths and analyzing emotion data

[0730] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[0731] Server: The emotion engine analyzes the emotion data and adjusts the learning path based on the user's emotional state.

[0732] Server: Sends the generated learning path in JSON format to the user's device.

[0733] Step 4:

[0734] View Learning Paths

[0735] Terminal: Parses the received learning path and displays it in the user interface.

[0736] Users: Review suggested learning paths and select learning content to get started.

[0737] Step 5:

[0738] Learning progress and progress management and emotional data collection

[0739] Users: View selected learning content and take quizzes and tests.

[0740] Device: Sends the user's answers, progress, and real-time emotional data to the server.

[0741] Server: Stores the received progress data and emotion data in a database, and checks with the generative AI module and emotion engine whether the next learning step is appropriate.

[0742] Step 6:

[0743] Dynamic learning paths and content updates

[0744] Server: Based on progress and emotion data, the generative AI module dynamically updates the learning path.

[0745] Server: The emotion engine adjusts learning content based on the emotional state.

[0746] Server: Sends updated learning paths and content to user devices.

[0747] Step 7:

[0748] Practical project proposals

[0749] Server: Searches for suitable practical projects based on the user's progress data, skill level, and sentiment data.

[0750] Server: Sends recommended projects to the user's device in JSON format.

[0751] Terminal: Display project details in the interface.

[0752] User: Select a proposed project and get started.

[0753] Step 8:

[0754] Project Progression and Emotional Feedback

[0755] User: Work on projects and record deliverables, progress, and sentiment data.

[0756] Terminal: Sends the user's recorded data and emotional data to the server.

[0757] Server: Analyzes progress and emotion data, generates feedback as needed, and sends it to the user.

[0758] Step 9:

[0759] Supporting communication and collaboration

[0760] Server: Matches users with the same learning goals and notifies the user's device of this information.

[0761] On your device: View matched user information and group chat options.

[0762] Users: Join the community and share information in chats and forums.

[0763] Step 10:

[0764] Support and information for obtaining qualifications

[0765] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[0766] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[0767] Users: Participate in credentials and events and feed progress and results back into the system.

[0768] Example 2

[0769] 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."

[0770] Conventional learning systems are unable to provide learning paths based on the user's interests and skill level, or to take real-time emotional data into account. As a result, they are unable to optimally control fluctuations in learning efficiency due to the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features such as dynamically updating learning paths based on learning progress and emotional data, or suggesting appropriate practical projects, making it difficult to maximize users' learning goals and motivation.

[0771] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and real-time emotional data to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, a means for generating and updating an appropriate learning path using a generative AI model, and a means for analyzing the user's emotional state using an emotional engine. This makes it possible to provide an optimal learning path for each individual's learning progress and skill level while taking into account the user's real-time emotional data, thereby maximizing the effectiveness of learning.

[0772] "User" refers to an individual or group who uses a learning system to carry out learning activities.

[0773] "Server" refers to the computer system that processes data sent by users and generates and provides learning paths and content.

[0774] "User device" refers to the device used by a user to access the learning system and display and operate the learning path and content, including, for example, a PC or smartphone.

[0775] A "learning path" refers to a learning progression or content that is customized based on a user's interests and skill level.

[0776] A "generative AI model" refers to an artificial intelligence algorithm that generates an optimal learning path based on user data.

[0777] An "emotion engine" is a system that analyzes users' real-time emotional data and feeds the results back into learning paths and content generation.

[0778] "Real-time emotional data" refers to data that measures and analyzes a user's emotional state in real time.

[0779] "Learning Content" refers to the materials, activities, questions, and other content that guide users through their learning path.

[0780] "Study progress data" refers to data that records the progress and results of a user's studies.

[0781] "Dynamic learning path updating" refers to the process of changing and optimizing the learning path in real time according to the user's progress and emotional state.

[0782] "Hands-on projects" refer to tasks or activities that are close to real-world applications or work that are offered as part of a learning path.

[0783] "Feedback" refers to information such as advice, suggestions for improvement, and evaluations provided based on the user's learning progress and emotional data.

[0784] "Communication functions" refers to functions such as chat and forums that allow users to exchange information, consult, and learn collaboratively with other users.

[0785] "Event and seminar information" refers to information on courses and information sessions related to obtaining qualifications and improving skills.

[0786] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[0787] Basic system configuration

[0788] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[0789] User interests, skill level and emotional preferences

[0790] When users register for the application, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[0791] Creating and delivering learning paths

[0792] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[0793] Learning progress management and emotion analysis

[0794] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[0795] Providing hands-on projects and emotional feedback

[0796] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[0797] Supporting collaboration and communication

[0798] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[0799] Support and information for obtaining qualifications

[0800] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[0801] Specific examples

[0802] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[0803] Prompt Sentence Examples

[0804] Example prompts to input to a generative AI model:

[0805] "User A is interested in data science. His current skill level is beginner. What learning path should I suggest to him to advance his learning? Also, his real-time sentiment data shows that he is currently highly motivated."

[0806] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[0807] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0808] Step 1: User registration and data provision

[0809] Input: Users access the system using a PC or smartphone and enter their areas of interest, current skill level, and real-time emotional data.

[0810] Data processing: The user terminal converts the input data into a data structure such as JSON format.

[0811] Output: The user terminal sends the converted data to the server.

[0812] Specific operation: The user enters data into the input form and presses the "Submit" button, which sends the data to the server.

[0813] Step 2: The server saves the data to the database

[0814] Input: User interests, skill level, and emotional data sent from the device.

[0815] Data processing: The server parses the received data and splits it into the required fields.

[0816] Output: The server stores the split data in the database.

[0817] What happens: The server receives the data and stores it in the database as a new user.

[0818] Step 3: Generate an initial learning path

[0819] Input: User interests, skill level, and sentiment data stored in a database.

[0820] Data calculation: The server sends these data to the generative AI model and asks it to generate an initial learning path.

[0821] Output: The initial training path returned by the generative AI model.

[0822] How it works: The generative AI model analyzes user data and generates an optimal learning path, which is then sent back to the server.

[0823] Step 4: Providing learning paths

[0824] Input: The initial training path returned from the generative AI model.

[0825] Data processing: The server converts the learning path into a format that can be displayed on the user's device.

[0826] Output: The server sends the converted learning path to the user device.

[0827] Specific operation: The user device receives the learning path and displays it on the screen. The user confirms the displayed content and begins learning.

[0828] Step 5: Tracking learning progress and analyzing emotions

[0829] Input: User learning progress data, answer data, and real-time sentiment data.

[0830] Data calculation: The user device collects progress data and emotion data and sends them to the server, which monitors them in real time and requests analysis.

[0831] Output: Based on the analysis results, the server dynamically updates the learning path.

[0832] Specific operation: The server requests the emotion engine and generative AI model to update the learning path based on the analysis results. The updated learning path is then sent to the user's device.

[0833] Step 6: Providing practical projects and feedback

[0834] Input: User skill level, learning progress, and emotional data.

[0835] Data calculation: The server proposes appropriate practical projects based on this data and sends them to the user's device.

[0836] Output: A user initiates a project and sends progress and emotional feedback to the server, which then provides feedback based on that data.

[0837] Specific operation: The user starts the proposed project, and the device collects progress data and emotion data and sends them to the server, which analyzes the data and sends appropriate feedback back to the user device.

[0838] Step 7: Support collaboration and communication

[0839] Input: User's learning goals, progress data, and sentiment data.

[0840] Data calculation: The server matches the optimal learning group based on this data and notifies the user device.

[0841] Output: Provides an interface for users to join learning groups and communicate with other users.

[0842] Specific operation: The user's device displays learning group information and provides chat and forum functions, allowing users to exchange information with other users.

[0843] Step 8: Support and information for obtaining qualifications

[0844] Input: Event and seminar information related to qualification acquisition, user learning progress data.

[0845] Data calculation: The server collects relevant information and notifies the user terminal in a timely manner.

[0846] Output: User access to qualification exam information and related events.

[0847] Specific operation: The user's device displays qualification acquisition information and event information, and the user adjusts their study plan based on that information.

[0848] (Application example 2)

[0849] 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."

[0850] Conventional learning systems have been inadequate in providing learning paths that take into account the user's interests and skill level. Furthermore, they do not utilize real-time emotional data to provide optimal learning content or personalize the user's purchasing experience. This makes it difficult to improve the efficiency of learning and the quality of the purchasing experience.

[0851] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for customizing a learning path based on the user's interests and current skill level, means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, means for monitoring the user's learning progress and dynamically updating the learning path based on that data, means for collecting and analyzing the user's emotional data in real time and recommending products and services based on the analysis results, and means for suggesting optimal products and services based on the user's purchasing history and interests. This makes it possible to provide a more personalized learning experience and purchasing experience by utilizing the user's emotional data and purchasing history.

[0852] "User interests" refers to the areas or topics that interest users.

[0853] "Current skill level" refers to the level of ability and knowledge that the user currently possesses.

[0854] A "learning path" is a plan of optimal learning order and content based on a user's interests and skill level.

[0855] "Customization" means adjusting a system or content to suit a specific user.

[0856] "Learning history" is data that records what a user has learned in the past and their progress.

[0857] "Survey responses" are data that record the opinions and feelings provided by users.

[0858] "Optimal learning content" refers to the educational materials and learning activities that best suit a user's interests and skill level.

[0859] "Dynamic updating" means analyzing information in real time and making changes to systems and plans as needed.

[0860] "Emotional data" refers to data that represents a user's psychological state or emotions.

[0861] "Real-time collection and analysis" means instantly acquiring and analyzing data as it occurs in the present moment.

[0862] "Recommendation" means suggesting a particular product or service to a user.

[0863] "Purchase history" is a record of products and services a user has purchased in the past.

[0864] "Personalization" means customizing something to suit each individual user.

[0865] "Learning content" is the collection of information, knowledge, and skills that users need to learn.

[0866] "Dynamic adjustment" means instantly changing content or plans according to the current situation.

[0867] This invention is a system for providing optimal learning and shopping experiences by utilizing a user's interests, current skill level, purchase history, and real-time emotional data. The system is composed of a server, a user terminal, an emotional engine, and a generative AI module.

[0868] First, the user device (smartphone) provides an interface for users to access the system and proceed with learning and shopping. The user's interests, current skill level, purchasing history, and real-time emotional data are sent from the user device to the server.

[0869] The server receives this information and stores it in a database. The generative AI module analyzes the stored data and generates optimal learning paths and product recommendations for the user. At this time, the emotion engine analyzes the user's emotional data in real time and also feeds the analysis results back to the generative AI module.

[0870] For example, by using a smartphone camera, users can provide emotional data in real time. This emotional data is analyzed by the emotion engine, and the analysis results are fed back to the generative AI module. The generative AI module dynamically adjusts the learning content and products based on the analysis results and provides them to the user.

[0871] When a user is looking at a particular product in a store, the system will recognize the product through the smartphone camera and recommend related products and services based on past purchase history and current emotional data. For example, if the user is in the clothing section, the system will suggest related accessories and outfits based on past purchase history and current emotional state.

[0872] Below are some example prompts to input to a generative AI model:

[0873] "When a user visits a store and views products through the camera, recommend related products based on their past purchase history and real-time sentiment data. User's interest area: {Interest area} User's purchase history: {Purchase history} Current sentiment: {Sentiment} Display recommended products in a list format, along with reviews and ratings for each product."

[0874] The system not only enables users to efficiently progress through personalized learning paths, but also provides interest- and emotion-based product recommendations, improving the quality of the learning and shopping experience and increasing user satisfaction.

[0875] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0876] Step 1:

[0877] The user terminal receives data on user interests, current skill level, and purchase history as input. This data is sent from the user terminal to the server. The data processing performed on the terminal is normalization of the input data and sending it to the database. The output is the normalized data and its sending status.

[0878] Step 2:

[0879] The server receives data sent from the user terminal and stores it in the database. The specific operations of the server are to receive data, write it to the database, and confirm the success status of the write. The input is the data from the user terminal, and the output is the data stored in the database and its storage status.

[0880] Step 3:

[0881] The user device captures the user's face through a camera and obtains emotional data in real time. This emotional data is preprocessed on the device and sent to the server. The specific operations are to start the camera, detect the face, analyze the emotional data, and send the data to the server. The input is the video data from the camera, and the output is the analyzed emotional data.

[0882] Step 4:

[0883] Emotion data received by the server is analyzed by the emotion engine. The emotion engine's operation is to analyze the received data and feed the results back to the generation AI module. The input is real-time emotion data, and the output is analyzed emotional state data.

[0884] Step 5:

[0885] The server uses a generative AI module to generate optimal learning paths and product recommendations based on the user's interests, skill level, purchase history, and real-time emotional data. Specific operations include inputting data into the generative AI model, analyzing the data using the generative model, and generating results. The input is all user-related data, and the output is a customized learning path or product recommendation list.

[0886] Step 6:

[0887] The server sends the generated learning path and product recommendations to the user's device. Specific operations include sending data and checking the transmission status. The input is the generated learning path and recommendation list, and the output is the display data for the user's device.

[0888] Step 7:

[0889] The user device displays the received learning path and product recommendations on its interface, helping users to smoothly progress through their learning and shopping. Specific operations include receiving data, updating the display interface, and accepting user operations. The input is the display data from the server, and the output is the displayed interface and the user operation log.

[0890] Step 8:

[0891] As the user continues their learning or shopping, progress data, purchasing status, and emotional data are collected again and sent to the server. The specific operations on the device are to record progress and purchasing status, reacquire emotional data, and resend the data to the server. The input is the user's operation data, and the output is the raw data to be analyzed again.

[0892] Step 9:

[0893] The server dynamically updates the learning path and product recommendations based on the received progress data, purchasing status, and emotion data. Specific operations include reanalyzing the data, regenerating the learning path and recommendation list, and retransmitting it to the user device. The input is the updated usage data, and the output is the updated learning path and recommendation list.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] [Third embodiment]

[0898] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0899] 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.

[0900] 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).

[0901] 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.

[0902] 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.

[0903] 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).

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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."

[0910] The present invention is a system that proposes optimal learning paths based on a user's interests and skill level, providing effective and practical learning. This system uses generative AI to provide optimal learning content for each user while exchanging data between a server, terminals, and users. Specific embodiments are described below.

[0911] Basic system configuration

[0912] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI module. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI module, located within the server, is responsible for analyzing user data and generating the optimal learning path.

[0913] User interest and skill level settings

[0914] When a user starts learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an AI module to generate an initial learning path.

[0915] Creating and delivering learning paths

[0916] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface, where the user can proceed sequentially through the presented learning content and activities.

[0917] Learning progress management

[0918] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI module to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[0919] Providing practical projects

[0920] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes the user's skill level and learning progress and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[0921] Supporting collaboration and communication

[0922] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[0923] Support for obtaining qualifications and providing event information

[0924] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[0925] Specific examples

[0926] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[0927] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[0928] The processing flow will be explained below.

[0929] Step 1:

[0930] User registration and profile settings

[0931] User: Visits the app, registers, and fills out a form about their interests and current skill level.

[0932] Terminal: The entered user information is encrypted and sent to the server.

[0933] Step 2:

[0934] Receiving and storing profile data

[0935] Server: Stores the received user data in a database.

[0936] Server: Analyzes the user's interests and skill level and sends requests to the Generative AI module to generate an initial learning path.

[0937] Step 3:

[0938] Generate a learning path

[0939] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[0940] Server: Sends the generated learning path in JSON format to the user's device.

[0941] Step 4:

[0942] View Learning Paths

[0943] Terminal: Parses the received learning path and displays it in the user interface.

[0944] Users: Review suggested learning paths and select learning content to get started.

[0945] Step 5:

[0946] Learning progress and progress management

[0947] Users: View selected learning content and take quizzes and tests.

[0948] Device: Sends the user's answers and progress to the server.

[0949] Server: Stores the received progress data in a database and checks with the generation AI module whether the next step learning path is appropriate.

[0950] Step 6:

[0951] Dynamic Update Implementation

[0952] Server: Based on the progress data, the generative AI module decides whether to dynamically update the learning path.

[0953] Server: Generates new learning paths as needed and sends them to the user device.

[0954] Step 7:

[0955] Practical project proposals

[0956] Server: Searches for suitable hands-on projects based on the user's progress and skill level.

[0957] Server: Sends recommended projects to the user's device in JSON format.

[0958] Terminal: Display project details in the interface.

[0959] User: Select a proposed project and get started.

[0960] Step 8:

[0961] Project progress management

[0962] User: Manages projects and records deliverables and progress.

[0963] Terminal: Sends user record data to the server.

[0964] Server: Analyzes the progress data and generates and sends feedback to the user as needed.

[0965] Step 9:

[0966] Supporting communication and collaboration

[0967] Server: Matches users with the same learning goals and notifies the user's device of this information.

[0968] On your device: View matched user information and group chat options.

[0969] Users: Join the community and share information in chats and forums.

[0970] Step 10:

[0971] Support and information for obtaining qualifications

[0972] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[0973] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[0974] Users: Participate in credentials and events and feed progress and results back into the system.

[0975] This process step ensures that users learn efficiently, always enjoying a personalized learning path, and develop their skills through hands-on projects and community activities.

[0976] Example 1

[0977] 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."

[0978] Conventional learning systems do not adequately provide personalized learning paths tailored to each user's interests and skill level. It is also difficult to dynamically update the learning path based on the user's learning progress, making it difficult to provide effective learning. Furthermore, they lack practical project suggestions, information related to qualification acquisition, and support for collaboration between users. It is necessary to solve these issues and provide users with the optimal learning environment.

[0979] 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.

[0980] In this invention, the server

[0981] A means to customize a learning path based on the user's interests and current skill level;

[0982] A means for storing data sent from the user device on a server and analyzing it using a generative AI model;

[0983] a means for dynamically updating the learning path based on the generative AI model; and

[0984] a means for providing a customized learning path to a user device;

[0985] and a means for managing the user's learning progress on a server and analyzing it in real time.

[0986] This allows for personalized learning paths, real-time learning progress management, dynamic learning path updates, and more. It also effectively proposes practical projects tailored to each user's skill level, promotes collaboration between users, and provides information related to qualification acquisition.

[0987] "User" refers to an individual who uses the System to receive Learning Paths and Content.

[0988] "Server" refers to the central system that processes data submitted by users and generates and provides learning paths.

[0989] "Terminal" means a hardware device used by a user to access the system, including a PC or smartphone.

[0990] "Generative AI model" refers to an artificial intelligence model used to analyze a user's interests and skill level to generate an optimal learning path.

[0991] "Learning Path" refers to a learning path or course that is customized based on a user's individual skill level and interests.

[0992] "Customization" refers to the process of tailoring specific learning paths and content to meet a user's individual requirements and requirements.

[0993] "Real-time" refers to the time characteristic of instantly processing and reflecting the user's learning progress and data.

[0994] "Analysis" refers to the process by which our servers process the data submitted by users and extract the information needed to generate learning paths and content.

[0995] "Dynamic updates" refers to changing and optimizing the learning path in real time according to the user's learning progress.

[0996] "Practical projects" refer to assignments or tasks that are based on what the user has learned and are directly related to specific applications or practical work.

[0997] "Communication" refers to the process of exchanging information, opinions, and feedback between users. This feature includes methods such as chat and forums.

[0998] "Certification assistance" refers to the process of providing users with appropriate information and resources to prepare for a specific certification exam or qualification.

[0999] "Event information" refers to information about seminars, training courses, exams, etc. that are relevant to the user's interests and goals.

[1000] This invention relates to a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system features a mechanism that uses a generative AI model to provide optimal learning content for each user while exchanging data between a server, terminals, and users.

[1001] Basic system configuration

[1002] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI model. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI model, located on the server, is responsible for analyzing user data and generating the optimal learning path.

[1003] The specific hardware and software used

[1004] 1. User Device

[1005] Users access the system using a PC or smartphone. The user device sends initial setup information and learning progress information to the server and displays the received learning paths and content. The front end is built using HTML, CSS, and JavaScript.

[1006] 2. Server

[1007] The server processes the data sent by the user, stores it in a database, and then requests a generative AI model to generate a user-specific learning path and sends the generated path to the user's device. The backend is primarily written in Python and either Flask or Django.

[1008] 3. Generative AI Models

[1009] The generative AI model resides on a server and uses machine learning libraries such as Python and TensorFlow to analyze a user's interests and skill level and generate an optimal learning path.

[1010] Data processing and calculation

[1011] 1. User Interest and Skill Level Settings

[1012] When a user begins learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an initial learning path from the generative AI model.

[1013] 2. Creating and providing learning paths

[1014] The server uses the generative AI model to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on an interface, where the user can progress through the presented learning content and activities.

[1015] 3. Learning progress management

[1016] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI model to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[1017] 4. Providing practical projects

[1018] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes and evaluates the user's skill level and learning progress, and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[1019] 5. Supporting collaboration and communication

[1020] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[1021] 6. Support for obtaining qualifications and provision of event information

[1022] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[1023] Specific examples

[1024] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generative AI model. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[1025] Prompt Sentence Examples

[1026] To develop a system that generates a customized learning path based on a user's interests and skill level, and dynamically updates it as they progress, follow these steps:

[1027] 1. Provide a screen where users can enter their areas of interest and skill level.

[1028] 2. The input data is sent to the server and saved in the database.

[1029] 3. Generate a learning path based on the generative AI model and send it back to the user device.

[1030] 4. Manage users' learning progress in real time and update their learning paths as needed.

[1031] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[1032] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1033] Step 1: User Registration

[1034] Users access the system and enter their field of interest and current skill level. The information entered by the user is sent from the terminal to the server. This input data includes information such as "data science" or "beginner." This information is sent to the server and stored in a database.

[1035] Step 2: Data analysis

[1036] The server sends an analysis request to the generative AI model based on the user's stored interest and skill level data. The generative AI model uses Python and TensorFlow to generate an optimal learning path based on the user's profile. This involves data preprocessing, feature extraction, and model analysis. The analysis results include the optimal learning plan and course structure for the user.

[1037] Step 3: Providing a learning path

[1038] The learning path generated by the generative AI model is sent back to the server, which then sends it to the user's device. The user's device displays the received learning path on its screen, and the user begins learning by clicking the "Start" button. This output data includes the specific learning course names and order.

[1039] Step 4: Track your progress

[1040] As a user progresses with their studies, their progress and answer data are sent from their device to the server. The server stores this data in a database in real time and analyzes their progress and learning effectiveness. Progress data includes the ID of the completed task, the score, and the content of the answers.

[1041] Step 5: Update a Dynamic Learning Path

[1042] The server then requests the generative AI model to analyze the user's progress data again. The generative AI model dynamically updates the learning path based on the latest progress information and generates a new learning plan. The updated learning path is then sent back to the server, which then sends it to the user's device. This ensures that the user always receives optimally updated learning content.

[1043] Step 6: Propose a practical project

[1044] Once a user has completed a certain amount of learning, the server analyzes the user's skill level and progress data and suggests practical projects. The proposed projects are sent to the user's device along with information such as project details, required skills, and goals, and the user can then start the project based on this information.

[1045] Step 7: Providing community features

[1046] The server matches users with other users who have the same learning goals and promotes collaboration within the community. Users can communicate with other members through chat and forums and collaborate on their learning.

[1047] Step 8: Providing support for qualification acquisition and event information

[1048] The server collects information about related events and seminars and notifies the user's device in a timely manner based on the user's interests and goals. Based on this information, users can participate in qualification exams and related events to broaden their learning horizons.

[1049] The above is the specific program processing flow of the system. This system allows users to efficiently progress through individually customized learning paths and effectively acquire practical skills and knowledge.

[1050] (Application example 1)

[1051] 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."

[1052] While traditional learning systems can provide learning paths based on a user's interests and skill level, they lack the ability to personalize the learning process for specific product information and provide appropriate product learning content based on the user's progress. Furthermore, there are insufficient means to provide effective learning paths to promote purchasing decisions in physical and virtual stores. Furthermore, the lack of a mechanism for dynamically suggesting related product information and special offers makes it difficult to provide an optimal purchasing experience for users.

[1053] 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.

[1054] In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, and a means for providing product information based on the product category selected by the user and generating a personalized learning path, thereby enabling the user to deepen their product knowledge while receiving optimal product information and benefits in a timely manner.

[1055] definition statement

[1056] "User Interest" refers to the level of interest a user has in a particular topic or field.

[1057] "Skill level" indicates a user's level of knowledge or ability in a particular field or topic.

[1058] A "learning path" is a customized set of learning steps that a user must take to achieve a specific goal or skill.

[1059] "Learning history" refers to records of a user's past learning activities and their results.

[1060] "Survey Responses" represent information provided by users about their individual learning needs and interests.

[1061] "Analysis" refers to the process of using user-provided data to derive meaning and determine learning paths and content.

[1062] "Optimal learning content" refers to learning materials and learning materials that are presented in a format that best suits a user's interests and skill level.

[1063] "Dynamic updates" means that learning paths and content are revised and changed at any time based on real-time data such as the user's progress.

[1064] "Product category" refers to a specific product group and refers to the product classification that the user is learning about.

[1065] "Product Information" means details about a particular product, including its description, uses, and benefits.

[1066] "Personalized learning path" means learning steps that are customized based on an individual user's interests and skill level.

[1067] "Learning progress" refers to how far a user has progressed in the process of acquiring a targeted skill or knowledge.

[1068] "Relevant Product Information and Special Offers" refers to relevant product details and special offers that are tailored to your interests and educational progression.

[1069] "Project Progress" refers to how well a user has accomplished a given task or assignment.

[1070] "Feedback" refers to evaluations and advice provided to users regarding their actions and progress.

[1071] MODE FOR CARRYING OUT THE INVENTION

[1072] This invention is a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system consists of a user terminal, a server, and a generation AI module.

[1073] Basic system configuration

[1074] This system consists of a user device (such as a smartphone or PC), a server, and a generative AI module. The user device provides the interface that allows users to access the system and progress through their studies. The server processes data sent by users and generates learning paths and content. The generative AI module is located within the server and is used to analyze user data and generate optimal learning paths.

[1075] Hardware and software used

[1076] Hardware: Smartphone (iOS / Android), PC.

[1077] Software: Mobile application frameworks (e.g., Flutter), backends (e.g., Firebase, Node.js), generative AI modules (e.g., GPT-3.5, BERT), databases (e.g., MongoDB).

[1078] User interest and skill level settings

[1079] When starting learning, users first input the product categories they are interested in and their current skill level. This input is sent to the server via the user's device and stored in a database.

[1080] Example prompt sentence:

[1081] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[1082] Creating and delivering learning paths

[1083] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[1084] Learning progress management

[1085] As the user progresses with their learning, their progress and answer data are sent from their device to the server, where it is recorded in a database. The server monitors this in real time and dynamically updates the learning path as needed by requesting the generative AI module.

[1086] Product information and learning

[1087] Based on the product category selected by the user, it provides the most suitable product information, including product promotional videos, usage guides, and review information.

[1088] Providing practical projects

[1089] As users progress through their learning, they are given the opportunity to take on practical projects. The server analyzes the user's skill level and learning progress and suggests appropriate projects.

[1090] Providing community features

[1091] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device of this match.

[1092] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1093] Program processing flow

[1094] Step 1: Enter your user information

[1095] The user terminal provides an interface for the user to input the product categories of interest and current skill level. The user fills in the necessary information in this form and presses the submit button. The input data includes the categories of interest and skill level. The terminal sends this data to the server.

[1096] Input: User's product interest category, skill level

[1097] Output: User data sent to the server

[1098] Step 2: Save user data

[1099] The server stores the user's product interest and skill level in a database (e.g., Firebase Firestore), which is used to generate a learning path.

[1100] Input: User's product interest category, skill level

[1101] Output: User data records in the database

[1102] Step 3: Generate a learning path

[1103] The server calls a generation AI module (e.g., GPT-3.5) based on the saved user data to generate a learning path. The generation AI module is provided with the following prompt:

[1104] Example prompt sentence:

[1105] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[1106] Input: User data, prompt

[1107] Output: The generated training path

[1108] Step 4: Providing learning paths

[1109] The server sends the learning path received from the generation AI module to the user device, which displays the learning path on its interface, allowing the user to proceed with the learning.

[1110] Input: Generated learning path

[1111] Output: The learning path displayed on the user's device

[1112] Step 5: Monitor your progress

[1113] As a user progresses through their studies, their device sends their progress status to the server, which monitors it in real time and records it in a database as progress data.

[1114] Input: User's learning progress data

[1115] Output: Progress record in database

[1116] Step 6: Dynamically Update Learning Paths

[1117] The server analyzes the progress data and dynamically updates the learning path by resubmitting the AI ​​generation module as needed. The updated learning path is then sent back to the user's device for display.

[1118] Input: Progress data

[1119] Output: Updated learning path

[1120] Step 7: Provide product information

[1121] Based on the product category selected by the user, the server collects related product information (such as promotional videos, usage guides, reviews, etc.) and provides it to the user's terminal.

[1122] Input: Product categories that the user is interested in

[1123] Output: Related product information

[1124] Step 8: Propose a practical project

[1125] Once the user has progressed to a certain level in their learning, the server will suggest an appropriate practical project based on the user's skill level and progress data, and the project details will be displayed on the user's device.

[1126] Input: Skill level, progress data

[1127] Output: Proposed project details

[1128] Step 9: Providing community features

[1129] The server matches users with other users who have the same learning goals based on their progress and learning goals, and notifications are sent to users' devices, allowing them to join the community and communicate.

[1130] Input: progress data, learning goals

[1131] Output: Matching notification

[1132] Through each of these steps, users receive the optimal learning path and relevant content, enabling them to learn more effectively.

[1133] 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.

[1134] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[1135] Basic system configuration

[1136] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[1137] User interests, skill level and emotional preferences

[1138] When users register for the app, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[1139] Creating and delivering learning paths

[1140] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[1141] Learning progress management and emotion analysis

[1142] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[1143] Providing hands-on projects and emotional feedback

[1144] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[1145] Supporting collaboration and communication

[1146] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[1147] Support and information for obtaining qualifications

[1148] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[1149] Specific examples

[1150] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[1151] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[1152] The processing flow will be explained below.

[1153] Step 1:

[1154] User registration and profile settings

[1155] User: Visits the app and registers, providing their interests, current skill level, and active sentiment data.

[1156] Terminal: The entered user information and emotional data are encrypted and sent to the server.

[1157] Step 2:

[1158] Receiving and storing profile data and emotional data

[1159] Server: Stores the received user data and emotion data in a database.

[1160] Server: Analyzes user interests, skill level, and emotional data and asks the AI ​​module to generate an initial learning path.

[1161] Step 3:

[1162] Generating learning paths and analyzing emotion data

[1163] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[1164] Server: The emotion engine analyzes the emotion data and adjusts the learning path based on the user's emotional state.

[1165] Server: Sends the generated learning path in JSON format to the user's device.

[1166] Step 4:

[1167] View Learning Paths

[1168] Terminal: Parses the received learning path and displays it in the user interface.

[1169] Users: Review suggested learning paths and select learning content to get started.

[1170] Step 5:

[1171] Learning progress and progress management and emotional data collection

[1172] Users: View selected learning content and take quizzes and tests.

[1173] Device: Sends the user's answers, progress, and real-time emotional data to the server.

[1174] Server: Stores the received progress data and emotion data in a database, and checks with the generative AI module and emotion engine whether the next learning step is appropriate.

[1175] Step 6:

[1176] Dynamic learning paths and content updates

[1177] Server: Based on progress and emotion data, the generative AI module dynamically updates the learning path.

[1178] Server: The emotion engine adjusts learning content based on the emotional state.

[1179] Server: Sends updated learning paths and content to user devices.

[1180] Step 7:

[1181] Practical project proposals

[1182] Server: Searches for suitable practical projects based on the user's progress data, skill level, and sentiment data.

[1183] Server: Sends recommended projects to the user's device in JSON format.

[1184] Terminal: Display project details in the interface.

[1185] User: Select a proposed project and get started.

[1186] Step 8:

[1187] Project Progression and Emotional Feedback

[1188] User: Work on projects and record deliverables, progress, and sentiment data.

[1189] Terminal: Sends the user's recorded data and emotional data to the server.

[1190] Server: Analyzes progress and emotion data, generates feedback as needed, and sends it to the user.

[1191] Step 9:

[1192] Supporting communication and collaboration

[1193] Server: Matches users with the same learning goals and notifies the user's device of this information.

[1194] On your device: View matched user information and group chat options.

[1195] Users: Join the community and share information in chats and forums.

[1196] Step 10:

[1197] Support and information for obtaining qualifications

[1198] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[1199] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[1200] Users: Participate in credentials and events and feed progress and results back into the system.

[1201] Example 2

[1202] 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."

[1203] Conventional learning systems are unable to provide learning paths based on the user's interests and skill level, or to take real-time emotional data into account. As a result, they are unable to optimally control fluctuations in learning efficiency due to the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features such as dynamically updating learning paths based on learning progress and emotional data, or suggesting appropriate practical projects, making it difficult to maximize users' learning goals and motivation.

[1204] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and real-time emotional data to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, a means for generating and updating an appropriate learning path using a generative AI model, and a means for analyzing the user's emotional state using an emotional engine. This makes it possible to provide an optimal learning path for each individual's learning progress and skill level while taking into account the user's real-time emotional data, thereby maximizing the effectiveness of learning.

[1205] "User" refers to an individual or group who uses a learning system to carry out learning activities.

[1206] "Server" refers to the computer system that processes data sent by users and generates and provides learning paths and content.

[1207] "User device" refers to the device used by a user to access the learning system and display and operate the learning path and content, including, for example, a PC or smartphone.

[1208] A "learning path" refers to a learning progression or content that is customized based on a user's interests and skill level.

[1209] A "generative AI model" refers to an artificial intelligence algorithm that generates an optimal learning path based on user data.

[1210] An "emotion engine" is a system that analyzes users' real-time emotional data and feeds the results back into learning paths and content generation.

[1211] "Real-time emotional data" refers to data that measures and analyzes a user's emotional state in real time.

[1212] "Learning Content" refers to the materials, activities, questions, and other content that guide users through their learning path.

[1213] "Study progress data" refers to data that records the progress and results of a user's studies.

[1214] "Dynamic learning path updating" refers to the process of changing and optimizing the learning path in real time according to the user's progress and emotional state.

[1215] "Hands-on projects" refer to tasks or activities that are close to real-world applications or work that are offered as part of a learning path.

[1216] "Feedback" refers to information such as advice, suggestions for improvement, and evaluations provided based on the user's learning progress and emotional data.

[1217] "Communication functions" refers to functions such as chat and forums that allow users to exchange information, consult, and learn collaboratively with other users.

[1218] "Event and seminar information" refers to information on courses and information sessions related to obtaining qualifications and improving skills.

[1219] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[1220] Basic system configuration

[1221] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[1222] User interests, skill level and emotional preferences

[1223] When users register for the application, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[1224] Creating and delivering learning paths

[1225] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[1226] Learning progress management and emotion analysis

[1227] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[1228] Providing hands-on projects and emotional feedback

[1229] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[1230] Supporting collaboration and communication

[1231] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[1232] Support and information for obtaining qualifications

[1233] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[1234] Specific examples

[1235] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[1236] Prompt Sentence Examples

[1237] Example prompts to input to a generative AI model:

[1238] "User A is interested in data science. His current skill level is beginner. What learning path should I suggest to him to advance his learning? Also, his real-time sentiment data shows that he is currently highly motivated."

[1239] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[1240] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1241] Step 1: User registration and data provision

[1242] Input: Users access the system using a PC or smartphone and enter their areas of interest, current skill level, and real-time emotional data.

[1243] Data processing: The user terminal converts the input data into a data structure such as JSON format.

[1244] Output: The user terminal sends the converted data to the server.

[1245] Specific operation: The user enters data into the input form and presses the "Submit" button, which sends the data to the server.

[1246] Step 2: The server saves the data to the database

[1247] Input: User interests, skill level, and emotional data sent from the device.

[1248] Data processing: The server parses the received data and splits it into the required fields.

[1249] Output: The server stores the split data in the database.

[1250] What happens: The server receives the data and stores it in the database as a new user.

[1251] Step 3: Generate an initial learning path

[1252] Input: User interests, skill level, and sentiment data stored in a database.

[1253] Data calculation: The server sends these data to the generative AI model and asks it to generate an initial learning path.

[1254] Output: The initial training path returned by the generative AI model.

[1255] How it works: The generative AI model analyzes user data and generates an optimal learning path, which is then sent back to the server.

[1256] Step 4: Providing learning paths

[1257] Input: The initial training path returned from the generative AI model.

[1258] Data processing: The server converts the learning path into a format that can be displayed on the user's device.

[1259] Output: The server sends the converted learning path to the user device.

[1260] Specific operation: The user device receives the learning path and displays it on the screen. The user confirms the displayed content and begins learning.

[1261] Step 5: Tracking learning progress and analyzing emotions

[1262] Input: User learning progress data, answer data, and real-time sentiment data.

[1263] Data calculation: The user device collects progress data and emotion data and sends them to the server, which monitors them in real time and requests analysis.

[1264] Output: Based on the analysis results, the server dynamically updates the learning path.

[1265] Specific operation: The server requests the emotion engine and generative AI model to update the learning path based on the analysis results. The updated learning path is then sent to the user's device.

[1266] Step 6: Providing practical projects and feedback

[1267] Input: User skill level, learning progress, and emotional data.

[1268] Data calculation: The server proposes appropriate practical projects based on this data and sends them to the user's device.

[1269] Output: A user initiates a project and sends progress and emotional feedback to the server, which then provides feedback based on that data.

[1270] Specific operation: The user starts the proposed project, and the device collects progress data and emotion data and sends them to the server, which analyzes the data and sends appropriate feedback back to the user device.

[1271] Step 7: Support collaboration and communication

[1272] Input: User's learning goals, progress data, and sentiment data.

[1273] Data calculation: The server matches the optimal learning group based on this data and notifies the user device.

[1274] Output: Provides an interface for users to join learning groups and communicate with other users.

[1275] Specific operation: The user's device displays learning group information and provides chat and forum functions, allowing users to exchange information with other users.

[1276] Step 8: Support and information for obtaining qualifications

[1277] Input: Event and seminar information related to qualification acquisition, user learning progress data.

[1278] Data calculation: The server collects relevant information and notifies the user terminal in a timely manner.

[1279] Output: User access to qualification exam information and related events.

[1280] Specific operation: The user's device displays qualification acquisition information and event information, and the user adjusts their study plan based on that information.

[1281] (Application example 2)

[1282] 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."

[1283] Conventional learning systems have been inadequate in providing learning paths that take into account the user's interests and skill level. Furthermore, they do not utilize real-time emotional data to provide optimal learning content or personalize the user's purchasing experience. This makes it difficult to improve the efficiency of learning and the quality of the purchasing experience.

[1284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for customizing a learning path based on the user's interests and current skill level, means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, means for monitoring the user's learning progress and dynamically updating the learning path based on that data, means for collecting and analyzing the user's emotional data in real time and recommending products and services based on the analysis results, and means for suggesting optimal products and services based on the user's purchasing history and interests. This makes it possible to provide a more personalized learning experience and purchasing experience by utilizing the user's emotional data and purchasing history.

[1285] "User interests" refers to the areas or topics that interest users.

[1286] "Current skill level" refers to the level of ability and knowledge that the user currently possesses.

[1287] A "learning path" is a plan of optimal learning order and content based on a user's interests and skill level.

[1288] "Customization" means adjusting a system or content to suit a specific user.

[1289] "Learning history" is data that records what a user has learned in the past and their progress.

[1290] "Survey responses" are data that record the opinions and feelings provided by users.

[1291] "Optimal learning content" refers to the educational materials and learning activities that best suit a user's interests and skill level.

[1292] "Dynamic updating" means analyzing information in real time and making changes to systems and plans as needed.

[1293] "Emotional data" refers to data that represents a user's psychological state or emotions.

[1294] "Real-time collection and analysis" means instantly acquiring and analyzing data as it occurs in the present moment.

[1295] "Recommendation" means suggesting a particular product or service to a user.

[1296] "Purchase history" is a record of products and services a user has purchased in the past.

[1297] "Personalization" means customizing something to suit each individual user.

[1298] "Learning content" is the collection of information, knowledge, and skills that users need to learn.

[1299] "Dynamic adjustment" means instantly changing content or plans according to the current situation.

[1300] This invention is a system for providing optimal learning and shopping experiences by utilizing a user's interests, current skill level, purchase history, and real-time emotional data. The system is composed of a server, a user terminal, an emotional engine, and a generative AI module.

[1301] First, the user device (smartphone) provides an interface for users to access the system and proceed with learning and shopping. The user's interests, current skill level, purchasing history, and real-time emotional data are sent from the user device to the server.

[1302] The server receives this information and stores it in a database. The generative AI module analyzes the stored data and generates optimal learning paths and product recommendations for the user. At this time, the emotion engine analyzes the user's emotional data in real time and also feeds the analysis results back to the generative AI module.

[1303] For example, by using a smartphone camera, users can provide emotional data in real time. This emotional data is analyzed by the emotion engine, and the analysis results are fed back to the generative AI module. The generative AI module dynamically adjusts the learning content and products based on the analysis results and provides them to the user.

[1304] When a user is looking at a particular product in a store, the system will recognize the product through the smartphone camera and recommend related products and services based on past purchase history and current emotional data. For example, if the user is in the clothing section, the system will suggest related accessories and outfits based on past purchase history and current emotional state.

[1305] Below are some example prompts to input to a generative AI model:

[1306] "When a user visits a store and views products through the camera, recommend related products based on their past purchase history and real-time sentiment data. User's interest area: {Interest area} User's purchase history: {Purchase history} Current sentiment: {Sentiment} Display recommended products in a list format, along with reviews and ratings for each product."

[1307] The system not only enables users to efficiently progress through personalized learning paths, but also provides interest- and emotion-based product recommendations, improving the quality of the learning and shopping experience and increasing user satisfaction.

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1:

[1310] The user terminal receives data on user interests, current skill level, and purchase history as input. This data is sent from the user terminal to the server. The data processing performed on the terminal is normalization of the input data and sending it to the database. The output is the normalized data and its sending status.

[1311] Step 2:

[1312] The server receives data sent from the user terminal and stores it in the database. The specific operations of the server are to receive data, write it to the database, and confirm the success status of the write. The input is the data from the user terminal, and the output is the data stored in the database and its storage status.

[1313] Step 3:

[1314] The user device captures the user's face through a camera and obtains emotional data in real time. This emotional data is preprocessed on the device and sent to the server. The specific operations are to start the camera, detect the face, analyze the emotional data, and send the data to the server. The input is the video data from the camera, and the output is the analyzed emotional data.

[1315] Step 4:

[1316] Emotion data received by the server is analyzed by the emotion engine. The emotion engine's operation is to analyze the received data and feed the results back to the generation AI module. The input is real-time emotion data, and the output is analyzed emotional state data.

[1317] Step 5:

[1318] The server uses a generative AI module to generate optimal learning paths and product recommendations based on the user's interests, skill level, purchase history, and real-time emotional data. Specific operations include inputting data into the generative AI model, analyzing the data using the generative model, and generating results. The input is all user-related data, and the output is a customized learning path or product recommendation list.

[1319] Step 6:

[1320] The server sends the generated learning path and product recommendations to the user's device. Specific operations include sending data and checking the transmission status. The input is the generated learning path and recommendation list, and the output is the display data for the user's device.

[1321] Step 7:

[1322] The user device displays the received learning path and product recommendations on its interface, helping users to smoothly progress through their learning and shopping. Specific operations include receiving data, updating the display interface, and accepting user operations. The input is the display data from the server, and the output is the displayed interface and the user operation log.

[1323] Step 8:

[1324] As the user continues their learning or shopping, progress data, purchasing status, and emotional data are collected again and sent to the server. The specific operations on the device are to record progress and purchasing status, reacquire emotional data, and resend the data to the server. The input is the user's operation data, and the output is the raw data to be analyzed again.

[1325] Step 9:

[1326] The server dynamically updates the learning path and product recommendations based on the received progress data, purchasing status, and emotion data. Specific operations include reanalyzing the data, regenerating the learning path and recommendation list, and retransmitting it to the user device. The input is the updated usage data, and the output is the updated learning path and recommendation list.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] [Fourth embodiment]

[1331] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1332] 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.

[1333] 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).

[1334] 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.

[1335] 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.

[1336] 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).

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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."

[1344] The present invention is a system that proposes optimal learning paths based on a user's interests and skill level, providing effective and practical learning. This system uses generative AI to provide optimal learning content for each user while exchanging data between a server, terminals, and users. Specific embodiments are described below.

[1345] Basic system configuration

[1346] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI module. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI module, located within the server, is responsible for analyzing user data and generating the optimal learning path.

[1347] User interest and skill level settings

[1348] When a user starts learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an AI module to generate an initial learning path.

[1349] Creating and delivering learning paths

[1350] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface, where the user can proceed sequentially through the presented learning content and activities.

[1351] Learning progress management

[1352] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI module to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[1353] Providing practical projects

[1354] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes the user's skill level and learning progress and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[1355] Supporting collaboration and communication

[1356] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[1357] Support for obtaining qualifications and providing event information

[1358] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[1359] Specific examples

[1360] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[1361] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[1362] The processing flow will be explained below.

[1363] Step 1:

[1364] User registration and profile settings

[1365] User: Visits the app, registers, and fills out a form about their interests and current skill level.

[1366] Terminal: The entered user information is encrypted and sent to the server.

[1367] Step 2:

[1368] Receiving and storing profile data

[1369] Server: Stores the received user data in a database.

[1370] Server: Analyzes the user's interests and skill level and sends requests to the Generative AI module to generate an initial learning path.

[1371] Step 3:

[1372] Generate a learning path

[1373] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[1374] Server: Sends the generated learning path in JSON format to the user's device.

[1375] Step 4:

[1376] View Learning Paths

[1377] Terminal: Parses the received learning path and displays it in the user interface.

[1378] Users: Review suggested learning paths and select learning content to get started.

[1379] Step 5:

[1380] Learning progress and progress management

[1381] Users: View selected learning content and take quizzes and tests.

[1382] Device: Sends the user's answers and progress to the server.

[1383] Server: Stores the received progress data in a database and checks with the generation AI module whether the next step learning path is appropriate.

[1384] Step 6:

[1385] Dynamic Update Implementation

[1386] Server: Based on the progress data, the generative AI module decides whether to dynamically update the learning path.

[1387] Server: Generates new learning paths as needed and sends them to the user device.

[1388] Step 7:

[1389] Practical project proposals

[1390] Server: Searches for suitable hands-on projects based on the user's progress and skill level.

[1391] Server: Sends recommended projects to the user's device in JSON format.

[1392] Terminal: Display project details in the interface.

[1393] User: Select a proposed project and get started.

[1394] Step 8:

[1395] Project progress management

[1396] User: Manages projects and records deliverables and progress.

[1397] Terminal: Sends user record data to the server.

[1398] Server: Analyzes the progress data and generates and sends feedback to the user as needed.

[1399] Step 9:

[1400] Supporting communication and collaboration

[1401] Server: Matches users with the same learning goals and notifies the user's device of this information.

[1402] On your device: View matched user information and group chat options.

[1403] Users: Join the community and share information in chats and forums.

[1404] Step 10:

[1405] Support and information for obtaining qualifications

[1406] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[1407] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[1408] Users: Participate in credentials and events and feed progress and results back into the system.

[1409] This process step ensures that users learn efficiently, always enjoying a personalized learning path, and develop their skills through hands-on projects and community activities.

[1410] Example 1

[1411] 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."

[1412] Conventional learning systems do not adequately provide personalized learning paths tailored to each user's interests and skill level. It is also difficult to dynamically update the learning path based on the user's learning progress, making it difficult to provide effective learning. Furthermore, they lack practical project suggestions, information related to qualification acquisition, and support for collaboration between users. It is necessary to solve these issues and provide users with the optimal learning environment.

[1413] 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.

[1414] In this invention, the server

[1415] A means to customize a learning path based on the user's interests and current skill level;

[1416] A means for storing data sent from the user device on a server and analyzing it using a generative AI model;

[1417] a means for dynamically updating the learning path based on the generative AI model; and

[1418] a means for providing a customized learning path to a user device;

[1419] and a means for managing the user's learning progress on a server and analyzing it in real time.

[1420] This allows for personalized learning paths, real-time learning progress management, dynamic learning path updates, and more. It also effectively proposes practical projects tailored to each user's skill level, promotes collaboration between users, and provides information related to qualification acquisition.

[1421] "User" refers to an individual who uses the System to receive Learning Paths and Content.

[1422] "Server" refers to the central system that processes data submitted by users and generates and provides learning paths.

[1423] "Terminal" means a hardware device used by a user to access the system, including a PC or smartphone.

[1424] "Generative AI model" refers to an artificial intelligence model used to analyze a user's interests and skill level to generate an optimal learning path.

[1425] "Learning Path" refers to a learning path or course that is customized based on a user's individual skill level and interests.

[1426] "Customization" refers to the process of tailoring specific learning paths and content to meet a user's individual requirements and requirements.

[1427] "Real-time" refers to the time characteristic of instantly processing and reflecting the user's learning progress and data.

[1428] "Analysis" refers to the process by which our servers process the data submitted by users and extract the information needed to generate learning paths and content.

[1429] "Dynamic updates" refers to changing and optimizing the learning path in real time according to the user's learning progress.

[1430] "Practical projects" refer to assignments or tasks that are based on what the user has learned and are directly related to specific applications or practical work.

[1431] "Communication" refers to the process of exchanging information, opinions, and feedback between users. This feature includes methods such as chat and forums.

[1432] "Certification assistance" refers to the process of providing users with appropriate information and resources to prepare for a specific certification exam or qualification.

[1433] "Event information" refers to information about seminars, training courses, exams, etc. that are relevant to the user's interests and goals.

[1434] This invention relates to a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system features a mechanism that uses a generative AI model to provide optimal learning content for each user while exchanging data between a server, terminals, and users.

[1435] Basic system configuration

[1436] This system consists of a user device (e.g., a PC or smartphone), a server, and a generative AI model. The user device provides an interface for users to access the system and progress through their learning. Meanwhile, the server functions as a back-end system for processing data sent by users and generating learning paths and content. The generative AI model, located on the server, is responsible for analyzing user data and generating the optimal learning path.

[1437] The specific hardware and software used

[1438] 1. User Device

[1439] Users access the system using a PC or smartphone. The user device sends initial setup information and learning progress information to the server and displays the received learning paths and content. The front end is built using HTML, CSS, and JavaScript.

[1440] 2. Server

[1441] The server processes the data sent by the user, stores it in a database, and then requests a generative AI model to generate a user-specific learning path and sends the generated path to the user's device. The backend is primarily written in Python and either Flask or Django.

[1442] 3. Generative AI Models

[1443] The generative AI model resides on a server and uses machine learning libraries such as Python and TensorFlow to analyze a user's interests and skill level and generate an optimal learning path.

[1444] Data processing and calculation

[1445] 1. User Interest and Skill Level Settings

[1446] When a user begins learning, they enter their areas of interest and current skill level on the initial registration screen. This data is sent from the user's device to the server and stored in a database. Based on this information, the server requests an initial learning path from the generative AI model.

[1447] 2. Creating and providing learning paths

[1448] The server uses the generative AI model to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on an interface, where the user can progress through the presented learning content and activities.

[1449] 3. Learning progress management

[1450] As a user progresses through their studies, their progress and answer data are sent from their device to the server and recorded in a database. The server monitors this in real time and, if necessary, requests the generative AI model to dynamically update the learning path. This dynamic update ensures that users always have access to the most appropriate learning content.

[1451] 4. Providing practical projects

[1452] Once a user has progressed to a certain level in their learning, they are given the opportunity to take on a practical project. The server analyzes and evaluates the user's skill level and learning progress, and suggests appropriate projects. Based on the project details displayed on the user's device, the user can start the project and provide feedback on their progress to the system.

[1453] 5. Supporting collaboration and communication

[1454] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device. Based on this, users can join study groups and communicate through chat and forums.

[1455] 6. Support for obtaining qualifications and provision of event information

[1456] In addition, for users who are aiming to obtain qualifications, the server collects information on related events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and further strengthen their study plans.

[1457] Specific examples

[1458] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generative AI model. The generated learning path is displayed on User A's device, and User A starts by learning the basics of data science. As User A progresses, practical projects will be suggested, and User A can complete the projects together with other users. As User A continues to learn, they will also be provided with timely information on exams and related events to obtain qualifications.

[1459] Prompt Sentence Examples

[1460] To develop a system that generates a customized learning path based on a user's interests and skill level, and dynamically updates it as they progress, follow these steps:

[1461] 1. Provide a screen where users can enter their areas of interest and skill level.

[1462] 2. The input data is sent to the server and saved in the database.

[1463] 3. Generate a learning path based on the generative AI model and send it back to the user device.

[1464] 4. Manage users' learning progress in real time and update their learning paths as needed.

[1465] The system allows users to efficiently progress through the learning path that is best suited to them, effectively acquiring both practical skills and knowledge.

[1466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1467] Step 1: User Registration

[1468] Users access the system and enter their field of interest and current skill level. The information entered by the user is sent from the terminal to the server. This input data includes information such as "data science" or "beginner." This information is sent to the server and stored in a database.

[1469] Step 2: Data analysis

[1470] The server sends an analysis request to the generative AI model based on the user's stored interest and skill level data. The generative AI model uses Python and TensorFlow to generate an optimal learning path based on the user's profile. This involves data preprocessing, feature extraction, and model analysis. The analysis results include the optimal learning plan and course structure for the user.

[1471] Step 3: Providing a learning path

[1472] The learning path generated by the generative AI model is sent back to the server, which then sends it to the user's device. The user's device displays the received learning path on its screen, and the user begins learning by clicking the "Start" button. This output data includes the specific learning course names and order.

[1473] Step 4: Track your progress

[1474] As a user progresses with their studies, their progress and answer data are sent from their device to the server. The server stores this data in a database in real time and analyzes their progress and learning effectiveness. Progress data includes the ID of the completed task, the score, and the content of the answers.

[1475] Step 5: Update a Dynamic Learning Path

[1476] The server then requests the generative AI model to analyze the user's progress data again. The generative AI model dynamically updates the learning path based on the latest progress information and generates a new learning plan. The updated learning path is then sent back to the server, which then sends it to the user's device. This ensures that the user always receives optimally updated learning content.

[1477] Step 6: Propose a practical project

[1478] Once a user has completed a certain amount of learning, the server analyzes the user's skill level and progress data and suggests practical projects. The proposed projects are sent to the user's device along with information such as project details, required skills, and goals, and the user can then start the project based on this information.

[1479] Step 7: Providing community features

[1480] The server matches users with other users who have the same learning goals and promotes collaboration within the community. Users can communicate with other members through chat and forums and collaborate on their learning.

[1481] Step 8: Providing support for qualification acquisition and event information

[1482] The server collects information about related events and seminars and notifies the user's device in a timely manner based on the user's interests and goals. Based on this information, users can participate in qualification exams and related events to broaden their learning horizons.

[1483] The above is the specific program processing flow of the system. This system allows users to efficiently progress through individually customized learning paths and effectively acquire practical skills and knowledge.

[1484] (Application example 1)

[1485] 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."

[1486] While traditional learning systems can provide learning paths based on a user's interests and skill level, they lack the ability to personalize the learning process for specific product information and provide appropriate product learning content based on the user's progress. Furthermore, there are insufficient means to provide effective learning paths to promote purchasing decisions in physical and virtual stores. Furthermore, the lack of a mechanism for dynamically suggesting related product information and special offers makes it difficult to provide an optimal purchasing experience for users.

[1487] 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.

[1488] In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, and a means for providing product information based on the product category selected by the user and generating a personalized learning path, thereby enabling the user to deepen their product knowledge while receiving optimal product information and benefits in a timely manner.

[1489] definition statement

[1490] "User Interest" refers to the level of interest a user has in a particular topic or field.

[1491] "Skill level" indicates a user's level of knowledge or ability in a particular field or topic.

[1492] A "learning path" is a customized set of learning steps that a user must take to achieve a specific goal or skill.

[1493] "Learning history" refers to records of a user's past learning activities and their results.

[1494] "Survey Responses" represent information provided by users about their individual learning needs and interests.

[1495] "Analysis" refers to the process of using user-provided data to derive meaning and determine learning paths and content.

[1496] "Optimal learning content" refers to learning materials and learning materials that are presented in a format that best suits a user's interests and skill level.

[1497] "Dynamic updates" means that learning paths and content are revised and changed at any time based on real-time data such as the user's progress.

[1498] "Product category" refers to a specific product group and refers to the product classification that the user is learning about.

[1499] "Product Information" means details about a particular product, including its description, uses, and benefits.

[1500] "Personalized learning path" means learning steps that are customized based on an individual user's interests and skill level.

[1501] "Learning progress" refers to how far a user has progressed in the process of acquiring a targeted skill or knowledge.

[1502] "Relevant Product Information and Special Offers" refers to relevant product details and special offers that are tailored to your interests and educational progression.

[1503] "Project Progress" refers to how well a user has accomplished a given task or assignment.

[1504] "Feedback" refers to evaluations and advice provided to users regarding their actions and progress.

[1505] MODE FOR CARRYING OUT THE INVENTION

[1506] This invention is a system that proposes optimal learning paths based on a user's interests and skill level, and provides effective and practical learning. This system consists of a user terminal, a server, and a generation AI module.

[1507] Basic system configuration

[1508] This system consists of a user device (such as a smartphone or PC), a server, and a generative AI module. The user device provides the interface that allows users to access the system and progress through their studies. The server processes data sent by users and generates learning paths and content. The generative AI module is located within the server and is used to analyze user data and generate optimal learning paths.

[1509] Hardware and software used

[1510] Hardware: Smartphone (iOS / Android), PC.

[1511] Software: Mobile application frameworks (e.g., Flutter), backends (e.g., Firebase, Node.js), generative AI modules (e.g., GPT-3.5, BERT), databases (e.g., MongoDB).

[1512] User interest and skill level settings

[1513] When starting learning, users first input the product categories they are interested in and their current skill level. This input is sent to the server via the user's device and stored in a database.

[1514] Example prompt sentence:

[1515] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[1516] Creating and delivering learning paths

[1517] The server uses a generative AI module to generate a customized learning path based on the user's interests and skill level. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[1518] Learning progress management

[1519] As the user progresses with their learning, their progress and answer data are sent from their device to the server, where it is recorded in a database. The server monitors this in real time and dynamically updates the learning path as needed by requesting the generative AI module.

[1520] Product information and learning

[1521] Based on the product category selected by the user, it provides the most suitable product information, including product promotional videos, usage guides, and review information.

[1522] Providing practical projects

[1523] As users progress through their learning, they are given the opportunity to take on practical projects. The server analyzes the user's skill level and learning progress and suggests appropriate projects.

[1524] Providing community features

[1525] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals and progress data, and notifies the user's device of this match.

[1526] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1527] Program processing flow

[1528] Step 1: Enter your user information

[1529] The user terminal provides an interface for the user to input the product categories of interest and current skill level. The user fills in the necessary information in this form and presses the submit button. The input data includes the categories of interest and skill level. The terminal sends this data to the server.

[1530] Input: User's product interest category, skill level

[1531] Output: User data sent to the server

[1532] Step 2: Save user data

[1533] The server stores the user's product interest and skill level in a database (e.g., Firebase Firestore), which is used to generate a learning path.

[1534] Input: User's product interest category, skill level

[1535] Output: User data records in the database

[1536] Step 3: Generate a learning path

[1537] The server calls a generation AI module (e.g., GPT-3.5) based on the saved user data to generate a learning path. The generation AI module is provided with the following prompt:

[1538] Example prompt sentence:

[1539] "User is currently interested in [product category] and has a knowledge level of [beginner / intermediate / advanced]. Generate the optimal learning path for this user and provide them with relevant content."

[1540] Input: User data, prompt

[1541] Output: The generated training path

[1542] Step 4: Providing learning paths

[1543] The server sends the learning path received from the generation AI module to the user device, which displays the learning path on its interface, allowing the user to proceed with the learning.

[1544] Input: Generated learning path

[1545] Output: The learning path displayed on the user's device

[1546] Step 5: Monitor your progress

[1547] As a user progresses through their studies, their device sends their progress status to the server, which monitors it in real time and records it in a database as progress data.

[1548] Input: User's learning progress data

[1549] Output: Progress record in database

[1550] Step 6: Dynamically Update Learning Paths

[1551] The server analyzes the progress data and dynamically updates the learning path by resubmitting the AI ​​generation module as needed. The updated learning path is then sent back to the user's device for display.

[1552] Input: Progress data

[1553] Output: Updated learning path

[1554] Step 7: Provide product information

[1555] Based on the product category selected by the user, the server collects related product information (such as promotional videos, usage guides, reviews, etc.) and provides it to the user's terminal.

[1556] Input: Product categories that the user is interested in

[1557] Output: Related product information

[1558] Step 8: Propose a practical project

[1559] Once the user has progressed to a certain level in their learning, the server will suggest an appropriate practical project based on the user's skill level and progress data, and the project details will be displayed on the user's device.

[1560] Input: Skill level, progress data

[1561] Output: Proposed project details

[1562] Step 9: Providing community features

[1563] The server matches users with other users who have the same learning goals based on their progress and learning goals, and notifications are sent to users' devices, allowing them to join the community and communicate.

[1564] Input: progress data, learning goals

[1565] Output: Matching notification

[1566] Through each of these steps, users receive the optimal learning path and relevant content, enabling them to learn more effectively.

[1567] 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.

[1568] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[1569] Basic system configuration

[1570] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[1571] User interests, skill level and emotional preferences

[1572] When users register for the app, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[1573] Creating and delivering learning paths

[1574] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[1575] Learning progress management and emotion analysis

[1576] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[1577] Providing hands-on projects and emotional feedback

[1578] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[1579] Supporting collaboration and communication

[1580] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[1581] Support and information for obtaining qualifications

[1582] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[1583] Specific examples

[1584] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[1585] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[1586] The processing flow will be explained below.

[1587] Step 1:

[1588] User registration and profile settings

[1589] User: Visits the app and registers, providing their interests, current skill level, and active sentiment data.

[1590] Terminal: The entered user information and emotional data are encrypted and sent to the server.

[1591] Step 2:

[1592] Receiving and storing profile data and emotional data

[1593] Server: Stores the received user data and emotion data in a database.

[1594] Server: Analyzes user interests, skill level, and emotional data and asks the AI ​​module to generate an initial learning path.

[1595] Step 3:

[1596] Generating learning paths and analyzing emotion data

[1597] Server: The generative AI module generates the optimal learning path based on the user's interests and skill level.

[1598] Server: The emotion engine analyzes the emotion data and adjusts the learning path based on the user's emotional state.

[1599] Server: Sends the generated learning path in JSON format to the user's device.

[1600] Step 4:

[1601] View Learning Paths

[1602] Terminal: Parses the received learning path and displays it in the user interface.

[1603] Users: Review suggested learning paths and select learning content to get started.

[1604] Step 5:

[1605] Learning progress and progress management and emotional data collection

[1606] Users: View selected learning content and take quizzes and tests.

[1607] Device: Sends the user's answers, progress, and real-time emotional data to the server.

[1608] Server: Stores the received progress data and emotion data in a database, and checks with the generative AI module and emotion engine whether the next learning step is appropriate.

[1609] Step 6:

[1610] Dynamic learning paths and content updates

[1611] Server: Based on progress and emotion data, the generative AI module dynamically updates the learning path.

[1612] Server: The emotion engine adjusts learning content based on the emotional state.

[1613] Server: Sends updated learning paths and content to user devices.

[1614] Step 7:

[1615] Practical project proposals

[1616] Server: Searches for suitable practical projects based on the user's progress data, skill level, and sentiment data.

[1617] Server: Sends recommended projects to the user's device in JSON format.

[1618] Terminal: Display project details in the interface.

[1619] User: Select a proposed project and get started.

[1620] Step 8:

[1621] Project Progression and Emotional Feedback

[1622] User: Work on projects and record deliverables, progress, and sentiment data.

[1623] Terminal: Sends the user's recorded data and emotional data to the server.

[1624] Server: Analyzes progress and emotion data, generates feedback as needed, and sends it to the user.

[1625] Step 9:

[1626] Supporting communication and collaboration

[1627] Server: Matches users with the same learning goals and notifies the user's device of this information.

[1628] On your device: View matched user information and group chat options.

[1629] Users: Join the community and share information in chats and forums.

[1630] Step 10:

[1631] Support and information for obtaining qualifications

[1632] Server: Collects information about events and seminars related to qualification acquisition and notifies users in a timely manner.

[1633] Terminal: Display detailed entitlement-related notifications and event information in the interface.

[1634] Users: Participate in credentials and events and feed progress and results back into the system.

[1635] Example 2

[1636] 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."

[1637] Conventional learning systems are unable to provide learning paths based on the user's interests and skill level, or to take real-time emotional data into account. As a result, they are unable to optimally control fluctuations in learning efficiency due to the user's emotional state, resulting in insufficient learning effectiveness. Furthermore, they lack features such as dynamically updating learning paths based on learning progress and emotional data, or suggesting appropriate practical projects, making it difficult to maximize users' learning goals and motivation.

[1638] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for customizing a learning path based on the user's interests and current skill level, a means for analyzing the user's learning history and real-time emotional data to provide optimal learning content, a means for monitoring the user's learning progress and dynamically updating the learning path based on that data, a means for generating and updating an appropriate learning path using a generative AI model, and a means for analyzing the user's emotional state using an emotional engine. This makes it possible to provide an optimal learning path for each individual's learning progress and skill level while taking into account the user's real-time emotional data, thereby maximizing the effectiveness of learning.

[1639] "User" refers to an individual or group who uses a learning system to carry out learning activities.

[1640] "Server" refers to the computer system that processes data sent by users and generates and provides learning paths and content.

[1641] "User device" refers to the device used by a user to access the learning system and display and operate the learning path and content, including, for example, a PC or smartphone.

[1642] A "learning path" refers to a learning progression or content that is customized based on a user's interests and skill level.

[1643] A "generative AI model" refers to an artificial intelligence algorithm that generates an optimal learning path based on user data.

[1644] An "emotion engine" is a system that analyzes users' real-time emotional data and feeds the results back into learning paths and content generation.

[1645] "Real-time emotional data" refers to data that measures and analyzes a user's emotional state in real time.

[1646] "Learning Content" refers to the materials, activities, questions, and other content that guide users through their learning path.

[1647] "Study progress data" refers to data that records the progress and results of a user's studies.

[1648] "Dynamic learning path updating" refers to the process of changing and optimizing the learning path in real time according to the user's progress and emotional state.

[1649] "Hands-on projects" refer to tasks or activities that are close to real-world applications or work that are offered as part of a learning path.

[1650] "Feedback" refers to information such as advice, suggestions for improvement, and evaluations provided based on the user's learning progress and emotional data.

[1651] "Communication functions" refers to functions such as chat and forums that allow users to exchange information, consult, and learn collaboratively with other users.

[1652] "Event and seminar information" refers to information on courses and information sessions related to obtaining qualifications and improving skills.

[1653] This invention is a system that recognizes a user's interests, current skill level, and emotions, and provides an optimal learning path based on this data. The system consists of a server, a user terminal, an emotion engine, and a generative AI module. By recognizing a user's emotions in real time and optimizing learning progress based on those emotions, it provides a more effective learning experience.

[1654] Basic system configuration

[1655] The system consists of a user device (e.g., a PC or smartphone), a server, a generative AI module, and an emotion engine. The user device provides an interface for users to access the system and progress through their learning. The server processes data sent by users and functions as a backend for generating learning paths and content. The emotion engine analyzes user emotions and provides feedback on the results to the generative AI module.

[1656] User interests, skill level and emotional preferences

[1657] When users register for the application, they provide their areas of interest, current skill level, and real-time emotional data. This data is sent from the user's device to the server and stored in a database. The server then uses this information to request an initial learning path from the AI ​​generation module.

[1658] Creating and delivering learning paths

[1659] The server uses a generative AI module to generate a customized learning path based on the user's interests, skill level, and emotional data. The generated learning path is sent to the user's device and displayed on the interface. The user can then proceed through the presented learning content and activities.

[1660] Learning progress management and emotion analysis

[1661] As a user progresses through their studies, their progress, answer data, and emotional data are sent from their device to the server and recorded in a database. The server monitors this data in real time and requests analysis from the generative AI module and emotion engine as needed. Based on the results of this analysis, the learning path is dynamically updated, ensuring that users always have access to the most appropriate learning content.

[1662] Providing hands-on projects and emotional feedback

[1663] As the user progresses through their learning, the server analyzes their skill level, learning progress, and emotional data to suggest appropriate practical projects. Based on the project details displayed on their device, the user can start the project and send progress and emotional feedback to the system. The server receives this information and provides feedback based on the project's progress.

[1664] Supporting collaboration and communication

[1665] The system also provides a community function that allows users to learn from each other with the same learning goals. The server performs optimal matching based on the user's learning goals, progress data, and emotional data, and notifies the user's device. Users can join learning groups and communicate through chat and forums.

[1666] Support and information for obtaining qualifications

[1667] In addition, for users who are aiming to obtain qualifications, the server collects information on relevant events and seminars and notifies the user's device in a timely manner, allowing users to collect all the information they need about the qualification exams and strengthen their study plans.

[1668] Specific examples

[1669] For example, if User A is interested in data science and registers with the system, the process will proceed as follows: The data entered by User A is sent to the server, where it is analyzed by the generation AI module and emotion engine. The generated learning path is displayed on User A's device, and User A starts by learning basic data science. The emotion engine analyzes the user's emotion data and adjusts the difficulty of the learning content. Practical projects are suggested based on progress, and the user can complete the projects together with other users. As the user progresses with their studies, they will also be provided with timely information on qualification exams and related events.

[1670] Prompt Sentence Examples

[1671] Example prompts to input to a generative AI model:

[1672] "User A is interested in data science. His current skill level is beginner. What learning path should I suggest to him to advance his learning? Also, his real-time sentiment data shows that he is currently highly motivated."

[1673] The system not only allows users to efficiently progress through a personalized learning path, but also utilizes real-time emotional feedback to help them learn effectively, and allows them to improve their skills through hands-on projects and community activities.

[1674] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1675] Step 1: User registration and data provision

[1676] Input: Users access the system using a PC or smartphone and enter their areas of interest, current skill level, and real-time emotional data.

[1677] Data processing: The user terminal converts the input data into a data structure such as JSON format.

[1678] Output: The user terminal sends the converted data to the server.

[1679] Specific operation: The user enters data into the input form and presses the "Submit" button, which sends the data to the server.

[1680] Step 2: The server saves the data to the database

[1681] Input: User interests, skill level, and emotional data sent from the device.

[1682] Data processing: The server parses the received data and splits it into the required fields.

[1683] Output: The server stores the split data in the database.

[1684] What happens: The server receives the data and stores it in the database as a new user.

[1685] Step 3: Generate an initial learning path

[1686] Input: User interests, skill level, and sentiment data stored in a database.

[1687] Data calculation: The server sends these data to the generative AI model and asks it to generate an initial learning path.

[1688] Output: The initial training path returned by the generative AI model.

[1689] How it works: The generative AI model analyzes user data and generates an optimal learning path, which is then sent back to the server.

[1690] Step 4: Providing learning paths

[1691] Input: The initial training path returned from the generative AI model.

[1692] Data processing: The server converts the learning path into a format that can be displayed on the user's device.

[1693] Output: The server sends the converted learning path to the user device.

[1694] Specific operation: The user device receives the learning path and displays it on the screen. The user confirms the displayed content and begins learning.

[1695] Step 5: Tracking learning progress and analyzing emotions

[1696] Input: User learning progress data, answer data, and real-time sentiment data.

[1697] Data calculation: The user device collects progress data and emotion data and sends them to the server, which monitors them in real time and requests analysis.

[1698] Output: Based on the analysis results, the server dynamically updates the learning path.

[1699] Specific operation: The server requests the emotion engine and generative AI model to update the learning path based on the analysis results. The updated learning path is then sent to the user's device.

[1700] Step 6: Providing practical projects and feedback

[1701] Input: User skill level, learning progress, and emotional data.

[1702] Data calculation: The server proposes appropriate practical projects based on this data and sends them to the user's device.

[1703] Output: A user initiates a project and sends progress and emotional feedback to the server, which then provides feedback based on that data.

[1704] Specific operation: The user starts the proposed project, and the device collects progress data and emotion data and sends them to the server, which analyzes the data and sends appropriate feedback back to the user device.

[1705] Step 7: Support collaboration and communication

[1706] Input: User's learning goals, progress data, and sentiment data.

[1707] Data calculation: The server matches the optimal learning group based on this data and notifies the user device.

[1708] Output: Provides an interface for users to join learning groups and communicate with other users.

[1709] Specific operation: The user's device displays learning group information and provides chat and forum functions, allowing users to exchange information with other users.

[1710] Step 8: Support and information for obtaining qualifications

[1711] Input: Event and seminar information related to qualification acquisition, user learning progress data.

[1712] Data calculation: The server collects relevant information and notifies the user terminal in a timely manner.

[1713] Output: User access to qualification exam information and related events.

[1714] Specific operation: The user's device displays qualification acquisition information and event information, and the user adjusts their study plan based on that information.

[1715] (Application example 2)

[1716] 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."

[1717] Conventional learning systems have been inadequate in providing learning paths that take into account the user's interests and skill level. Furthermore, they do not utilize real-time emotional data to provide optimal learning content or personalize the user's purchasing experience. This makes it difficult to improve the efficiency of learning and the quality of the purchasing experience.

[1718] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for customizing a learning path based on the user's interests and current skill level, means for analyzing the user's learning history and questionnaire responses to provide optimal learning content, means for monitoring the user's learning progress and dynamically updating the learning path based on that data, means for collecting and analyzing the user's emotional data in real time and recommending products and services based on the analysis results, and means for suggesting optimal products and services based on the user's purchasing history and interests. This makes it possible to provide a more personalized learning experience and purchasing experience by utilizing the user's emotional data and purchasing history.

[1719] "User interests" refers to the areas or topics that interest users.

[1720] "Current skill level" refers to the level of ability and knowledge that the user currently possesses.

[1721] A "learning path" is a plan of optimal learning order and content based on a user's interests and skill level.

[1722] "Customization" means adjusting a system or content to suit a specific user.

[1723] "Learning history" is data that records what a user has learned in the past and their progress.

[1724] "Survey responses" are data that record the opinions and feelings provided by users.

[1725] "Optimal learning content" refers to the educational materials and learning activities that best suit a user's interests and skill level.

[1726] "Dynamic updating" means analyzing information in real time and making changes to systems and plans as needed.

[1727] "Emotional data" refers to data that represents a user's psychological state or emotions.

[1728] "Real-time collection and analysis" means instantly acquiring and analyzing data as it occurs in the present moment.

[1729] "Recommendation" means suggesting a particular product or service to a user.

[1730] "Purchase history" is a record of products and services a user has purchased in the past.

[1731] "Personalization" means customizing something to suit each individual user.

[1732] "Learning content" is the collection of information, knowledge, and skills that users need to learn.

[1733] "Dynamic adjustment" means instantly changing content or plans according to the current situation.

[1734] This invention is a system for providing optimal learning and shopping experiences by utilizing a user's interests, current skill level, purchase history, and real-time emotional data. The system is composed of a server, a user terminal, an emotional engine, and a generative AI module.

[1735] First, the user device (smartphone) provides an interface for users to access the system and proceed with learning and shopping. The user's interests, current skill level, purchasing history, and real-time emotional data are sent from the user device to the server.

[1736] The server receives this information and stores it in a database. The generative AI module analyzes the stored data and generates optimal learning paths and product recommendations for the user. At this time, the emotion engine analyzes the user's emotional data in real time and also feeds the analysis results back to the generative AI module.

[1737] For example, by using a smartphone camera, users can provide emotional data in real time. This emotional data is analyzed by the emotion engine, and the analysis results are fed back to the generative AI module. The generative AI module dynamically adjusts the learning content and products based on the analysis results and provides them to the user.

[1738] When a user is looking at a particular product in a store, the system will recognize the product through the smartphone camera and recommend related products and services based on past purchase history and current emotional data. For example, if the user is in the clothing section, the system will suggest related accessories and outfits based on past purchase history and current emotional state.

[1739] Below are some example prompts to input to a generative AI model:

[1740] "When a user visits a store and views products through the camera, recommend related products based on their past purchase history and real-time sentiment data. User's interest area: {Interest area} User's purchase history: {Purchase history} Current sentiment: {Sentiment} Display recommended products in a list format, along with reviews and ratings for each product."

[1741] The system not only enables users to efficiently progress through personalized learning paths, but also provides interest- and emotion-based product recommendations, improving the quality of the learning and shopping experience and increasing user satisfaction.

[1742] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1743] Step 1:

[1744] The user terminal receives data on user interests, current skill level, and purchase history as input. This data is sent from the user terminal to the server. The data processing performed on the terminal is normalization of the input data and sending it to the database. The output is the normalized data and its sending status.

[1745] Step 2:

[1746] The server receives data sent from the user terminal and stores it in the database. The specific operations of the server are to receive data, write it to the database, and confirm the success status of the write. The input is the data from the user terminal, and the output is the data stored in the database and its storage status.

[1747] Step 3:

[1748] The user device captures the user's face through a camera and obtains emotional data in real time. This emotional data is preprocessed on the device and sent to the server. The specific operations are to start the camera, detect the face, analyze the emotional data, and send the data to the server. The input is the video data from the camera, and the output is the analyzed emotional data.

[1749] Step 4:

[1750] Emotion data received by the server is analyzed by the emotion engine. The emotion engine's operation is to analyze the received data and feed the results back to the generation AI module. The input is real-time emotion data, and the output is analyzed emotional state data.

[1751] Step 5:

[1752] The server uses a generative AI module to generate optimal learning paths and product recommendations based on the user's interests, skill level, purchase history, and real-time emotional data. Specific operations include inputting data into the generative AI model, analyzing the data using the generative model, and generating results. The input is all user-related data, and the output is a customized learning path or product recommendation list.

[1753] Step 6:

[1754] The server sends the generated learning path and product recommendations to the user's device. Specific operations include sending data and checking the transmission status. The input is the generated learning path and recommendation list, and the output is the display data for the user's device.

[1755] Step 7:

[1756] The user device displays the received learning path and product recommendations on its interface, helping users to smoothly progress through their learning and shopping. Specific operations include receiving data, updating the display interface, and accepting user operations. The input is the display data from the server, and the output is the displayed interface and the user operation log.

[1757] Step 8:

[1758] As the user continues their learning or shopping, progress data, purchasing status, and emotional data are collected again and sent to the server. The specific operations on the device are to record progress and purchasing status, reacquire emotional data, and resend the data to the server. The input is the user's operation data, and the output is the raw data to be analyzed again.

[1759] Step 9:

[1760] The server dynamically updates the learning path and product recommendations based on the received progress data, purchasing status, and emotion data. Specific operations include reanalyzing the data, regenerating the learning path and recommendation list, and retransmitting it to the user device. The input is the updated usage data, and the output is the updated learning path and recommendation list.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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).

[1768] 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.

[1769] 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."

[1770] 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.

[1771] 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).

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] The following is further disclosed regarding the above embodiment.

[1783] (Claim 1)

[1784] A means to customize a learning path based on the user's interests and current skill level;

[1785] A means of analyzing users' learning history and survey responses to provide optimal learning content;

[1786] A means to monitor users' learning progress and dynamically update their learning paths based on that data;

[1787] A system including:

[1788] (Claim 2)

[1789] A way to suggest practical projects based on the user's skill level;

[1790] A means to monitor users' project progress and provide feedback as needed;

[1791] 10. The system of claim 1, further comprising:

[1792] (Claim 3)

[1793] A means to match users with similar learning goals and promote collaboration;

[1794] A means to support communication between users;

[1795] A means of providing information about events and seminars related to qualification acquisition, and

[1796] 10. The system of claim 1, further comprising:

[1797] "Example 1"

[1798] (Claim 1)

[1799] A means to customize a learning path based on the user's interests and current skill level;

[1800] A means for storing data sent from the user device on a server and analyzing it using a generative AI model;

[1801] a means for dynamically updating the learning path based on the generative AI model; and

[1802] a means for providing a customized learning path to a user device;

[1803] A means to manage users' learning progress on a server and analyze it in real time,

[1804] A system including:

[1805] (Claim 2)

[1806] A way to suggest practical projects based on the user's skill level;

[1807] a means for monitoring the user's project progress via a server and providing dynamic feedback using a generative AI model as needed;

[1808] 10. The system of claim 1, further comprising:

[1809] (Claim 3)

[1810] A means to match users with similar learning goals and promote collaboration;

[1811] A means for supporting communication between users through a server;

[1812] A means of providing timely information on events and seminars related to qualification acquisition;

[1813] 10. The system of claim 1, further comprising:

[1814] "Application Example 1"

[1815] Newly rewritten claims

[1816] (Claim 1)

[1817] A means to customize a learning path based on the user's interests and current skill level;

[1818] A means of analyzing users' learning history and survey responses to provide optimal learning content;

[1819] A means to monitor users' learning progress and dynamically update their learning paths based on that data;

[1820] a means for providing product information and generating a personalized learning path based on a user's selected product category;

[1821] A system including:

[1822] (Claim 2)

[1823] A way to suggest practical projects based on the user's skill level;

[1824] A means to monitor users' project progress and provide feedback as needed;

[1825] A means of suggesting relevant product information and offers based on the user's interests and learning progress;

[1826] 10. The system of claim 1, further comprising:

[1827] (Claim 3)

[1828] A means to match users with similar learning goals and promote collaboration;

[1829] A means to support communication between users;

[1830] A means of providing information about events and seminars related to qualification acquisition, and 【...

Claims

1. A means to customize a learning path based on the user's interests and current skill level; A means of analyzing users' learning history and survey responses to provide optimal learning content; A means to monitor users' learning progress and dynamically update their learning paths based on that data; A system including:

2. A way to suggest practical projects based on the user's skill level; A means to monitor users' project progress and provide feedback as needed; The system of claim 1 further comprising:

3. A means to match users with similar learning goals and promote collaboration; A means to support communication between users; A means of providing information about events and seminars related to qualification acquisition, and The system of claim 1 further comprising:

Images