system

Abstract

Provide a system. [Solution] a means for identifying learning objectives from user input; a means of suggesting appropriate learning resources based on identified learning objectives; a means of designing a learning path based on the user's learning goals; A means to track users' learning progress and suggest next steps; A system including:

Description

[Technical Field]

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

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

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

[0004] When it comes to personal learning and skill improvement, it is difficult to set appropriate learning goals and find the appropriate learning resources. As a result, users end up spending time and effort searching for the right resource from the many resources available. Furthermore, it is not easy to design a learning path and manage learning progress on their own. This makes it difficult to study effectively and efficiently. The purpose of this invention is to solve these problems and provide a system that provides appropriate learning resources and learning paths for users to effectively achieve their learning goals, and manages their progress. [Means for solving the problem]

[0005] The system of the present invention includes a means for first identifying learning goals from user input. It also includes a means for suggesting appropriate learning resources based on the identified learning goals. It also includes a means for designing a learning path based on the user's learning goals, tracking the user's learning progress, and suggesting next steps. This system allows users to significantly improve the efficiency of their self-study. It also includes a progress management function that visualizes learning progress and supports maintaining motivation. Specifically, the system interactively sets goals with the user, suggests appropriate learning resources and learning paths, and visually displays learning progress using graphs and progress bars, helping users to consistently progress in their studies.

[0006] "User Input" means text or other form of data input by a User into a System.

[0007] "Learning objectives" refer to specific objectives of skill or knowledge that a user wants to achieve.

[0008] "Learning Resources" refers to the learning materials and information sources (e.g., online courses, tutorials, books, articles, videos, etc.) used to achieve a user's learning objectives.

[0009] A "learning path" is a plan for a user to achieve a learning goal, including specific steps and sequences.

[0010] "Progress" is information that indicates the steps or achievements a user has made toward their learning goal.

[0011] A "generative AI model" refers to an artificial intelligence algorithm that learns from large amounts of data, analyzes user input, and generates appropriate information and suggestions.

[0012] "Conversational interface" refers to a user interface that allows natural interaction between the user and the system.

[0013] "Feedback" refers to evaluation of a user's behavior or achievements and advice on the next course of action.

[0014] "Graphs and progress bars" refers to charts and indicators that visually represent a user's learning progress.

[0015] "Database" refers to the system for managing and storing user information and learning resource data. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention describes a system that provides personalized learning assistance to users by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[0038] Program processing overview

[0039] This self-learning platform includes the following key features:

[0040] 1. Goal identification

[0041] 2. Learning Resource Suggestions

[0042] 3. Learning path suggestions

[0043] 4. Progress Management

[0044] 1. Goal identification

[0045] Terminal

[0046] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[0047] user

[0048] Enter your learning goals, interests, and objectives.

[0049] server

[0050] A generative AI model analyzes user input to identify learning objectives and uses this information to provide feedback to the user.

[0051] 2. Learning Resource Suggestions

[0052] server

[0053] Based on the identified learning objectives, the database is searched for relevant learning resources and an optimal list is generated.

[0054] Terminal

[0055] Presents a list of learning resources to the user.

[0056] user

[0057] Select the learning resource that interests you from the suggested list and view more information.

[0058] 3. Learning path suggestions

[0059] server

[0060] Based on the selected learning resources and the user's learning goals, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[0061] Terminal

[0062] Visually display the learning path so users can review and correct it.

[0063] user

[0064] Accept the suggested learning path or modify it as needed.

[0065] 4. Progress Management

[0066] user

[0067] Follow the learning path and report your progress at the end of each step.

[0068] Terminal

[0069] Send progress reports to the server.

[0070] server

[0071] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[0072] Terminal

[0073] Provide users with progress visualizations and suggested next steps, such as progress bars and graphs, to help them understand their current learning situation.

[0074] Specific examples

[0075] Setting learning goals

[0076] If a user wants to learn programming, they might do the following:

[0077] user

[0078] Type in "I want to improve my programming skills."

[0079] server

[0080] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript®." The platform confirms this goal with the user and provides feedback.

[0081] Learning Resource Suggestions

[0082] server

[0083] Based on the identified goals, we suggest appropriate learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[0084] Terminal

[0085] Presents a list of learning resources to the user.

[0086] user

[0087] Select the "JavaScript Introduction Course."

[0088] Suggested learning paths

[0089] server

[0090] Based on the selected learning resources, design a learning path that:

[0091] Step 1: Complete the JavaScript Fundamentals course

[0092] Step 2: Advance to the intermediate course

[0093] Terminal

[0094] Visually display and follow the learning path for users.

[0095] user

[0096] Embrace the learning path.

[0097] Progress management

[0098] user

[0099] At the end of each step, progress is reported to the platform.

[0100] Terminal

[0101] Sends the reported progress to the server.

[0102] server

[0103] Track progress and provide next steps or additional feedback.

[0104] Terminal

[0105] Use progress bars and graphs to show progress and let users see the next step.

[0106] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[0107] The processing flow will be explained below.

[0108] Step 1:

[0109] The server sends the HTML and CSS to the device to display the platform's login page.

[0110] Step 2:

[0111] The terminal displays a login form.

[0112] Step 3:

[0113] The user enters their username and password and clicks the Login button.

[0114] Step 4:

[0115] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[0116] Step 5:

[0117] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[0118] Step 6:

[0119] The user clicks the "Set Goal" button.

[0120] Step 7:

[0121] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[0122] Step 8:

[0123] The device displays an interactive interface with the generated AI model.

[0124] Step 9:

[0125] Users enter their learning goals, interests, and objectives.

[0126] Step 10:

[0127] The device sends the user's input to the server.

[0128] Step 11:

[0129] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[0130] Step 12:

[0131] The server searches the database for relevant learning resources based on the identified learning objectives.

[0132] Step 13:

[0133] The server lists the most relevant learning resources from the search results.

[0134] Step 14:

[0135] The terminal displays a list of learning resources to the user.

[0136] Step 15:

[0137] The user selects the learning resource of interest from the suggested list and checks the details.

[0138] Step 16:

[0139] The terminal requests detailed information of the selected learning resource from the server.

[0140] Step 17:

[0141] The server sends the detailed information to the terminal.

[0142] Step 18:

[0143] The user reviews the learning resource and clicks the "Select" button.

[0144] Step 19:

[0145] Based on the server's selected learning resources and the user's learning goals, the generative AI designs the optimal learning path.

[0146] Step 20:

[0147] The server sets up a learning path step by step and sends it to the terminal.

[0148] Step 21:

[0149] The device visually displays your learning path.

[0150] Step 22:

[0151] The user reviews the proposed learning path and clicks the "Accept" button.

[0152] Step 23:

[0153] Users progress through the learning process and report their progress back to the platform at the end of each step.

[0154] Step 24:

[0155] The terminal sends a progress report to the server.

[0156] Step 25:

[0157] The server stores the progress information in a database and updates the user's learning status.

[0158] Step 26:

[0159] The server generates AI suggestions for next steps and additional feedback as needed.

[0160] Step 27:

[0161] The device displays progress visualization and suggested next steps to the user.

[0162] Step 28:

[0163] Users can see their progress using progress bars and graphs and see the next steps to take.

[0164] Example 1

[0165] 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."

[0166] Existing self-learning support systems often struggle to fully meet the individual needs of users. They also lack the support needed to help users clearly define their learning goals, find appropriate learning resources, and progress efficiently. This can lead to poor learning efficiency and the inability to find the optimal learning path.

[0167] 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.

[0168] In this invention, the server includes: [means for a user to log in using a terminal and verify authentication information; [means for identifying learning goals from the user's input and analyzing it using a generative AI model; [means for suggesting related learning resources from a database based on the identified learning goals;] [means for generating an optimal learning path based on the suggested learning resources and visually displaying it;] [means for tracking the user's learning progress and suggesting next steps using a progress bar or graph;] [means for providing detailed feedback using a generative AI model based on the identified learning goals; and [means for accepting interactive input from the user and specifying learning goals in detail using prompt sentences. This enables users to clearly set their learning goals, quickly find appropriate learning resources, and efficiently progress along the optimal learning path.

[0169] "Means for users to log in using a terminal and verify authentication information" refers to a mechanism by which users access the system using an electronic device and are authenticated based on the entered username and password.

[0170] "Means for identifying learning goals from user input and analyzing them using a generative AI model" refers to a mechanism that collects the goals and requirements that users input into the system, analyzes them using a generative AI model, and determines specific learning goals.

[0171] "Means for suggesting relevant learning resources from a database based on identified learning goals" refers to a mechanism that searches the database within the system according to the user's learning goals, and selects and presents relevant educational materials and courses.

[0172] "Means for generating and visually displaying an optimal learning path based on proposed learning resources" refers to a mechanism that takes into account a set of selected learning materials, designs an efficient sequence of learning steps based on that, and displays it on the screen in a format that is easily understandable to the user.

[0173] "Means to track a user's learning progress and suggest next steps using progress bars and graphs" refers to a system that records how far a user has progressed in their learning, visually illustrates that information, and suggests the next learning activity that should be undertaken.

[0174] "Means for providing detailed feedback using a generative AI model based on identified learning goals" refers to a mechanism that generates responses using a generative AI model according to the user's learning goals and provides specific, individualized feedback.

[0175] "Means for accepting interactive user input and using prompts to further identify learning objectives" refers to a mechanism that provides an interactive interface that responds to user input and uses appropriate questions and prompts to further explore the user's learning needs.

[0176] This invention is a system that provides users with personalized learning assistance by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[0177] This system is composed of a server, a terminal, and a user component. A specific embodiment will be described below.

[0178] 1. Hardware and Software Configuration

[0179] server

[0180] The server acts as a central control unit, processes user input, manages learning resources in conjunction with a database, and uses generative AI models to identify learning goals, design learning paths, and track progress.

[0181] Terminal

[0182] A terminal is a client device that receives user input and communicates with a server. Examples include PCs, tablets, and smartphones.

[0183] user

[0184] Users access the system using a terminal, set learning goals, and progress through their studies using suggested learning resources and learning paths.

[0185] Generative AI Models

[0186] Generative AI models analyze user input data and are used to set specific learning goals and design optimal learning paths. Specific examples of software include generative AI using natural language processing technology.

[0187] Database

[0188] A database is a system for storing learning resources, user progress data, set learning goals, etc. A specific example is a relational database management system (RDBMS).

[0189] 2. Example of a system and prompt

[0190] Specific examples of goal setting

[0191] If a user wants to learn data science, they would follow these steps:

[0192] user

[0193] A user goes to a terminal and types in, "I want to learn the basics of data science."

[0194] server

[0195] The server uses a generative AI model to analyze this input and identify the specific learning goal: "Data manipulation with Python," which is provided as feedback to the user.

[0196] Learning Resource Suggestions

[0197] Based on the identified learning objectives, the server searches its database for relevant learning resources and suggests a list such as:

[0198] 1. “Python Data Analysis Basics”

[0199] 2. “Advanced Python Data Science”

[0200] Terminal

[0201] The terminal visually displays these learning resources to the user.

[0202] user

[0203] Users can select "Python Data Analysis Basics" to view more information.

[0204] Specific learning path examples

[0205] Based on the selected learning resources, the server uses generative AI to design the following learning path:

[0206] Step 1: Learn Python Basics (online tutorial)

[0207] Step 2: Analysis using real data (practical exercise)

[0208] This learning path is visually displayed to the user through their device, allowing them to review and correct it.

[0209] Specific examples of progress management

[0210] As users complete each step along their learning path, they receive progress reports via their device.

[0211] server

[0212] The server stores progress information in a database and provides next steps and additional feedback through the generative AI, such as "The next step is to use the Python library pandas to analyze real data."

[0213] Terminal

[0214] The device visually displays progress with progress bars and graphs, allowing users to understand their current learning situation.

[0215] Prompt Sentence Examples

[0216] Examples of specific prompts that users may use to input information into the system include:

[0217] "I want to improve my programming skills"

[0218] "I want to improve my English speaking ability"

[0219] "I want to learn how to diet"

[0220] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[0221] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0222] Step 1:

[0223] User Login

[0224] Terminal

[0225] A user accesses the system using a terminal and the login screen is displayed. The user enters their username and password and presses the login button.

[0226] Input: Username and Password

[0227] server

[0228] The server checks the entered authentication information against the database, and if it matches, it generates the user's session information and returns it to the terminal. If it does not match, it returns an error message.

[0229] Data processing: Verification of authentication information and generation of session information

[0230] Output: Session information or error message

[0231] Step 2:

[0232] goal setting

[0233] Terminal

[0234] After logging in, users select "Goal Setting" from the main menu and an interactive interface is displayed.

[0235] Input: User's choice ("Goal setting")

[0236] user

[0237] Users follow interactive prompts to specify their learning goals, interests, and objectives, for example, "I want to learn the basics of data science."

[0238] Input: Learning goals or interests ("I want to learn the basics of data science")

[0239] server

[0240] The server uses a generative AI model to analyze this input and identify specific learning goals, such as "data manipulation with Python," which are then provided as feedback to the user.

[0241] Data Computation: Generative AI models analyze input data and identify learning goals

[0242] Output: Identified learning objectives (feedback)

[0243] Step 3:

[0244] Learning Resource Suggestions

[0245] server

[0246] Based on the identified learning objective, the server retrieves relevant learning resources from the database, for example, retrieve learning resources related to "Data Manipulation with Python."

[0247] Input: Identified learning objective ("Data manipulation with Python")

[0248] Data processing: Extracting appropriate learning resources through database search

[0249] Output: A list of related learning resources

[0250] Terminal

[0251] The terminal visually displays the list of learning resources sent from the server to the user.

[0252] Input: List of learning resources

[0253] user

[0254] Users can select the learning resource they are interested in from the displayed list to view more information, for example, "Python Data Analysis Basics."

[0255] Input: Selected learning resource ("Python Data Analysis Basics")

[0256] Output: Detailed information about the learning resource

[0257] Step 4:

[0258] Designing learning paths

[0259] server

[0260] Based on the selected learning resources, the server uses a generative AI model to design an optimal learning path, which consists of specific steps, such as "Step 1: Learn the basics of Python" and "Step 2: Analyze using real data."

[0261] Input: Selected learning resource ("Python Data Analysis Basics")

[0262] Data Computing: Designing Learning Paths with Generative AI Models

[0263] Output: Learning path

[0264] Terminal

[0265] It visually displays the learning path and allows users to review and correct it.

[0266] Input: Learning Path

[0267] user

[0268] The user accepts the proposed learning path or modifies it as needed. The user confirms the learning path.

[0269] Input: User confirmation and corrected learning path

[0270] Output: Confirmed learning path

[0271] Step 5:

[0272] Progress management

[0273] user

[0274] Users progress along a learning path and report their progress at the end of each step.

[0275] Input: Progress report

[0276] Terminal

[0277] The terminal sends progress reports to the server.

[0278] Input: Progress report

[0279] server

[0280] The server stores progress information in a database and provides next steps and additional feedback to the generative AI model, such as "The next step is to use the Python library pandas to analyze real data."

[0281] Data processing: storing progress information and generating feedback

[0282] Output: Next steps and additional feedback (feedback content)

[0283] Terminal

[0284] Progress is visually displayed in the form of progress bars and graphs, allowing users to understand their current learning situation.

[0285] Input: progress

[0286] Output: Visual progress indicator (progress bar and graph)

[0287] (Application example 1)

[0288] 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."

[0289] Conventional learning support systems have difficulty providing optimal learning paths for each user and managing their learning progress. Furthermore, they are limited to setting goals through text input and suggesting learning resources, resulting in a limited diversity in the user experience. Furthermore, the lack of statistical display of learning history and notification functions makes it difficult for users to efficiently grasp their learning progress.

[0290] 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.

[0291] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals;] [means for designing a learning path based on the user's learning goals;] [means for tracking the user's learning progress and suggesting next steps;] [means for accepting voice input;] [means for providing task notifications and reminders; and [means for displaying learning history statistics.] This makes it possible to provide learning support customized for each user, resulting in an efficient and diverse learning experience.

[0292] "Means for identifying learning goals from user input" refers to a function that accepts voice or text input, analyzes the content using a generative AI model, and specifically identifies the user's learning goals.

[0293] The "means for suggesting appropriate learning resources based on identified learning objectives" is a function that searches for relevant learning resources from a database based on the identified learning objectives, generates an optimal list, and suggests it to the user.

[0294] "Means for designing a learning path based on the user's learning goals" refers to a function in which the generative AI designs an optimal learning path based on the selected learning resources and the user's learning goals, and indicates the content and order of each step.

[0295] "Means for tracking the user's learning progress and suggesting next steps" refers to a function that stores the user's learning progress in a database and provides the next learning step or additional feedback depending on the situation.

[0296] The "means for accepting voice input" is a function for accepting voice input of learning goals and progress information from the user using a voice input device such as a microphone.

[0297] "Means for providing task notifications and reminders" refers to a function that provides notifications and reminders based on the learning goals and progress set by the user, encouraging them to complete a learning step or move on to the next task.

[0298] "Means for statistically displaying learning history" refers to a function that aggregates a user's learning history and displays it statistically using graphs and progress bars, allowing the user to visualize their own learning progress.

[0299] The present invention relates to a system for providing individually customized learning support to a user. Specific embodiments for carrying out the present invention are described below.

[0300] This system is configured using the following hardware and software.

[0301] Required Hardware

[0302] Smart devices (e.g. smartphones, tablets)

[0303] A microphone with voice input capabilities

[0304] Display Screen

[0305] Required software

[0306] Mobile application development frameworks (e.g., Flutter (registered trademark), React Native)

[0307] Database (e.g. Firebase Firestore)

[0308] Generative AI models (e.g., OpenAI® GPT-4®)

[0309] Serverless functions (e.g., Google Cloud Functions)

[0310] System Overview

[0311] User authentication and goal setting

[0312] Users log in to the application using their smart device. After logging in, they select "Goal Setting" from the main menu and enter their learning goals via voice or text input. This input is analyzed by a generative AI model (e.g., OpenAI GPT-4) to identify specific learning goals.

[0313] Example: A user says, "I want to learn the basics of JavaScript."

[0314] User: "I want to learn the basics of JavaScript."

[0315] AI: "So your goal is to learn the basics of JavaScript? Here are some suggested learning resources:

[0316] Learning Resource Suggestions

[0317] The server searches a database (e.g., Firebase Firestore) for relevant learning resources based on the identified learning objectives, generates an optimal list, and suggests it to the user. The user can select the learning resource of interest from the suggested list and check the detailed information.

[0318] Example: Learning resource suggestions

[0319] AI: "Which of these learning resources are you most interested in?"

[0320] User: Select "JavaScript Introduction Course"

[0321] Suggested learning paths

[0322] Based on the learning resources selected by the user, the server uses a generative AI model to design an optimal learning path. The learning path is structured into specific steps and visually displayed on the screen. The user can review the path and make any necessary adjustments.

[0323] Progress management

[0324] As the user completes each learning step, progress information is sent to the server and stored in a database. The server then provides the user with the next learning step or additional feedback, and displays progress using progress bars and graphs. Progress can also be reported via voice input.

[0325] Example: Progress management

[0326] The server statistically displays the user's learning history and helps promote learning by using task notification and reminder functions.

[0327] This makes it easier for users to visually grasp their learning progress and move on to the next step efficiently.

[0328] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0329] Step 1:

[0330] User authentication and goal setting

[0331] Input: A user logs into the application using a smart device and selects "Goal Setting" from the main menu.

[0332] Specific behavior:

[0333] 1. The device receives the user's login information and performs authentication.

[0334] 2. If authentication is successful, the "Goal Setting" screen will be displayed.

[0335] 3. The user inputs their learning goals by voice or text input.

[0336] 4. The device receives user input and sends it to the server.

[0337] Data processing and calculation:

[0338] The server passes the received voice or text input to a generative AI model (e.g., OpenAI GPT-4) for analysis.

[0339] output:

[0340] The generative AI model identifies specific learning goals as a result of the analysis and provides feedback to the user.

[0341] Step 2:

[0342] Learning Resource Suggestions

[0343] Input: User confirms identified learning objective.

[0344] Specific behavior:

[0345] 1. Based on the identified learning objectives, the server searches for relevant learning resources from a database (e.g., Firebase Firestore).

[0346] 2. Generate a list of learning resources based on the search results and send it to the terminal.

[0347] 3. The terminal displays a list of learning resources to the user.

[0348] Data processing and calculation:

[0349] The server queries the database for learning resources that match the learning objectives and lists the most suitable learning resources.

[0350] output:

[0351] Users can select the learning resource of interest from the displayed list and check the detailed information.

[0352] Step 3:

[0353] Suggested learning paths

[0354] Input: The learning resource selected by the user.

[0355] Specific behavior:

[0356] 1. The terminal sends information about the learning resource selected by the user to the server.

[0357] 2. The server uses a generative AI model to design an optimal learning path based on the selected learning resources and learning goals.

[0358] 3. Send the designed learning path to the device and display it visually.

[0359] 4. The user reviews the learning path and makes any necessary adjustments.

[0360] Data processing and calculation:

[0361] The server takes the selected learning resources and learning goals as input and performs data calculations to generate a learning path.

[0362] output:

[0363] The optimal learning path is presented to the user, who can confirm it and proceed to the next step.

[0364] Step 4:

[0365] Progress management

[0366] Input: The user progresses through the learning path.

[0367] Specific behavior:

[0368] 1. The device reports progress as the user completes each learning step.

[0369] 2. The device sends progress information to the server.

[0370] 3. The server stores the progress information in a database and suggests the next learning step.

[0371] 4. Use progress bars and graphs to show progress to the user.

[0372] Data processing and calculation:

[0373] The server receives the progress data, updates the learning progress, suggests next steps, and visualizes the progress.

[0374] output:

[0375] Users can visually see their progress and efficiently move to the next step.

[0376] 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.

[0377] This invention describes a self-learning platform that combines an emotion engine that recognizes users' emotions to improve users' learning experience. Specifically, it identifies learning goals from users' inputs, suggests appropriate learning resources, designs learning paths, manages progress, and also recognizes users' emotional states and reflects them in the learning process.

[0378] Program processing overview

[0379] This self-learning platform includes the following key features:

[0380] 1. Goal identification

[0381] 2. Learning Resource Suggestions

[0382] 3. Learning path suggestions

[0383] 4. Progress Management

[0384] 5. Emotion recognition and feedback regulation

[0385] 1. Goal identification

[0386] Terminal

[0387] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[0388] user

[0389] Enter your learning goals, interests, and objectives.

[0390] server

[0391] A generative AI model analyzes user input, and an emotion engine recognizes the user's emotional state, identifies learning goals, and provides feedback to the user based on this information.

[0392] 2. Learning Resource Suggestions

[0393] server

[0394] Based on the identified learning goals and emotional state, relevant learning resources are searched for in the database and an optimal list is generated.

[0395] Terminal

[0396] Presents a list of learning resources to the user.

[0397] user

[0398] Select the learning resource that interests you from the suggested list and view more information.

[0399] 3. Learning path suggestions

[0400] server

[0401] Based on the selected learning resources, the user's learning goals, and their emotional state, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[0402] Terminal

[0403] Visually display the learning path so users can review and correct it.

[0404] user

[0405] Accept the suggested learning path or modify it as needed.

[0406] 4. Progress Management

[0407] user

[0408] Follow the learning path and report your progress at the end of each step.

[0409] Terminal

[0410] Send progress reports to the server.

[0411] server

[0412] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[0413] Terminal

[0414] Provide users with progress visualization and suggested next steps.

[0415] 5. Emotion recognition and feedback regulation

[0416] server

[0417] The emotion engine periodically recognizes the user's emotional state while learning and generates feedback and encouraging messages to motivate the user.

[0418] Terminal

[0419] The emotion engine generates feedback and messages that are displayed to the user, and progress bars and graphs are used to provide support that takes into account the user's emotional state as they progress through the learning process.

[0420] Specific examples

[0421] Setting learning goals

[0422] If a user wants to improve their programming skills, they might do the following:

[0423] user

[0424] Type in "I want to improve my programming skills."

[0425] server

[0426] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript." At the same time, the emotion engine recognizes positive emotions from the user's text input and provides feedback to the user, such as "Your goal is great!"

[0427] Learning Resource Suggestions

[0428] server

[0429] Based on the identified goals and emotional state, it suggests the best learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[0430] Terminal

[0431] Present users with a list of learning resources and provide recommended comments that reflect the user's emotional state (e.g., "This course is beginner-friendly and fun to learn").

[0432] user

[0433] Select the "JavaScript Introduction Course."

[0434] Suggested learning paths

[0435] server

[0436] Based on the selected learning resources, design a learning path that:

[0437] Step 1: Complete the JavaScript Fundamentals course

[0438] Step 2: Advance to the intermediate course

[0439] Terminal

[0440] The learning path is visually displayed and confirmed by the user, and the emotion engine displays encouraging messages such as, "Once you've completed step 1, you'll be motivated to move on to the next step right away."

[0441] Progress management

[0442] user

[0443] At the end of each step, progress is reported to the platform.

[0444] Terminal

[0445] Sends the reported progress to the server.

[0446] server

[0447] It tracks progress and provides next steps and additional feedback, while an emotion engine periodically scans the user's emotional state and adjusts the feedback as needed.

[0448] Terminal

[0449] It displays progress using progress bars and graphs, letting users see the next steps they need to take, along with encouraging messages provided by an emotion engine.

[0450] The above is a specific embodiment of the present invention, which allows users to have an effective and efficient learning experience that takes into account their emotional state.

[0451] The processing flow will be explained below.

[0452] Step 1:

[0453] The server sends the HTML and CSS to the device to display the platform's login page.

[0454] Step 2:

[0455] The terminal displays a login form.

[0456] Step 3:

[0457] The user enters their username and password and clicks the Login button.

[0458] Step 4:

[0459] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[0460] Step 5:

[0461] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[0462] Step 6:

[0463] The user clicks the "Set Goal" button.

[0464] Step 7:

[0465] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[0466] Step 8:

[0467] The device displays an interactive interface with the generated AI model.

[0468] Step 9:

[0469] Users enter their learning goals, interests, and objectives.

[0470] Step 10:

[0471] The device sends the user's input to the server.

[0472] Step 11:

[0473] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[0474] Step 12:

[0475] The server uses an emotion engine to determine an emotional state from the user's input.

[0476] Step 13:

[0477] The server searches a database for relevant learning resources based on the identified learning goal and emotional state.

[0478] Step 14:

[0479] The server lists related learning resources and generates recommendation comments for the learning resources using an emotion engine.

[0480] Step 15:

[0481] The device displays a list of learning resources and recommended comments to the user.

[0482] Step 16:

[0483] The user selects the learning resource of interest from the suggested list and checks the details.

[0484] Step 17:

[0485] The terminal requests detailed information of the selected learning resource from the server.

[0486] Step 18:

[0487] The server sends the detailed information to the terminal.

[0488] Step 19:

[0489] The user reviews the learning resource and clicks the "Select" button.

[0490] Step 20:

[0491] Based on the learning resources selected by the server, the user's learning goals, and their emotional state, the generative AI designs the optimal learning path.

[0492] Step 20:

[0493] The server includes encouraging messages generated by the emotion engine at each step of the learning path.

[0494] Step 21:

[0495] The server sets up a learning path step by step and sends it to the terminal.

[0496] Step 22:

[0497] The device visually displays your learning path.

[0498] Step 23:

[0499] The user reviews the proposed learning path and clicks the "Accept" button.

[0500] Step 24:

[0501] Users progress through the learning process and report their progress back to the platform at the end of each step.

[0502] Step 25:

[0503] The terminal sends a progress report to the server.

[0504] Step 26:

[0505] The server stores the progress information in a database and updates the user's learning status.

[0506] Step 27:

[0507] The server generates next steps and additional feedback as needed, and the AI ​​suggests them, and generates encouraging messages using the emotion engine.

[0508] Step 28:

[0509] The device displays progress visualization and suggested next steps to the user.

[0510] Step 29:

[0511] The device displays encouraging messages generated by the emotion engine to the user, and provides support that takes into account the user's emotional state along with the learning progress using progress bars and graphs.

[0512] Step 30:

[0513] Users can see their progress using progress bars and graphs and see the next steps to take.

[0514] Example 2

[0515] 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."

[0516] While traditional self-learning systems can provide appropriate learning resources and set learning paths based on a user's learning goals, they do not take the user's emotional state into consideration. As a result, they provide insufficient support to increase user motivation and maximize learning outcomes. They also lack the ability to provide real-time feedback based on the user's progress. As a result, users often lose motivation to continue learning, hindering efficient learning.

[0517] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0518] In this invention, the server includes: [means for identifying learning goals from user input and recognizing the emotional state;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state; and [means for tracking the user's learning progress, suggesting next steps, and providing feedback based on the emotional state.] This enables learning support that takes the user's emotional state into consideration, providing an efficient and effective learning experience while increasing motivation.

[0519] "User" refers to an individual who intends to use the System to achieve their learning goals.

[0520] "Server" refers to the central processing unit that receives input from users and uses generative AI models and emotion engines to analyze data, make recommendations, and manage progress.

[0521] A "generative AI model" is a type of artificial intelligence that analyzes user input data and suggests appropriate learning goals and paths.

[0522] The "emotion engine" is a piece of software that recognizes the user's emotional state from their input data and provides feedback according to the learning process.

[0523] "Learning goals" refer to the specific learning content or skills that a user wants to achieve.

[0524] "Learning Resources" refers to the learning materials, content, courses, etc. provided to help users achieve their learning goals.

[0525] A "learning path" is a plan that includes specific learning steps and the order in which they must be undertaken to achieve a learning goal.

[0526] "Progress management" refers to the process of tracking a user's learning progress and providing next steps and feedback.

[0527] "Feedback" refers to encouraging messages and advice provided based on the user's learning progress and emotional state.

[0528] This invention provides a self-learning platform that combines an emotion engine that recognizes users' emotions to improve the user's learning experience. Specifically, the system identifies learning goals from users' input, suggests appropriate learning resources, designs learning paths, and manages progress, as well as recognizes the user's emotional state and reflects it in the learning process.

[0529] Hardware and software used

[0530] The system uses the following major hardware and software:

[0531] Server: The central processing unit that runs the generative AI models and emotion engine, and manages the database.

[0532] Terminal: A device (computer, smartphone, tablet, etc.) that provides the interface and sends user input to the server.

[0533] Generative AI model: An artificial intelligence model that analyzes user input data and suggests appropriate learning goals and paths.

[0534] Emotion engine: Software that recognizes the user's emotional state from input data and provides feedback according to the learning process.

[0535] Specific operation of the system

[0536] 1. Identify learning goals and recognize emotional states from user input

[0537] Terminal

[0538] The user logs into the platform using a terminal and opens an interactive interface for goal setting.

[0539] user

[0540] Users enter their learning goals, interests, and what they want to learn.

[0541] server

[0542] The server uses a generative AI model to analyze the user's input data and identify specific learning goals, while an emotion engine recognizes the user's emotional state from the text data.

[0543] 2. Suggest appropriate learning resources

[0544] server

[0545] The server searches the database for relevant learning resources based on the identified learning objectives and the recognized emotional state, and generates an optimal list.

[0546] Terminal

[0547] The terminal displays the generated list of learning resources to the user.

[0548] user

[0549] Users select learning resources of interest from the suggested list and view their detailed information.

[0550] 3. Design a learning path

[0551] server

[0552] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, the user's learning goals, and their emotional state. The learning path is composed of specific steps.

[0553] Terminal

[0554] The device visually displays the designed learning path for the user to review.

[0555] 4. Track learning progress, suggest next steps, and provide feedback based on emotional state

[0556] user

[0557] Users progress along a learning path and report their progress at the end of each step.

[0558] Terminal

[0559] The terminal sends progress reports from the user to the server.

[0560] server

[0561] The server stores progress information in a database, uses a generative AI model to suggest next steps and additional feedback, and uses an emotion engine to periodically recognize the user's emotional state and generate encouraging messages and advice based on that state.

[0562] Terminal

[0563] The device will then display generated feedback and encouragement messages to the user, allowing them to visually see their progress.

[0564] Examples of concrete examples and prompts

[0565] Specific examples

[0566] A user enters "I want to improve my programming skills," and the server parses this to identify "I want to learn the basics of JavaScript." The emotion engine recognizes a positive emotional state and provides feedback like, "Your goals are great!" The server then suggests learning resources, such as "Introductory JavaScript courses," and designs a learning path.

[0567] Prompt Sentence Examples

[0568] "Tell me about your learning goals."

[0569] Enter the skill you would like to improve.

[0570] As described above, the present invention is a system that provides an effective and efficient learning experience that takes into account the user's emotional state.

[0571] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0572] Step 1:

[0573] Login and User Authentication

[0574] Terminal

[0575] The terminal displays a login screen and prompts the user to enter their ID and password. The entered data is sent to the server when the login button is pressed.

[0576] user

[0577] The user enters their ID and password and clicks the login button.

[0578] server

[0579] The server verifies the received ID and password against the user data in the database. If authentication is successful, it sends the main menu to the terminal to receive the next input. If authentication fails, it generates an error message and sends it to the terminal.

[0580] Input: User ID and Password

[0581] Output: Authentication result (success / failure), main menu or error message sent

[0582] Specific operations: ID and password verification, determining next steps based on authentication results

[0583] Step 2:

[0584] Setting learning goals

[0585] Terminal

[0586] The device displays the main menu and prompts the user to click the "Goal Setting" button, and the interface displays prompts for interaction with the generative AI model.

[0587] user

[0588] Users click the "Set Goals" button, follow the prompts displayed, enter their learning goals, and then click the submit button.

[0589] server

[0590] The server receives the user's input data, analyzes it using a generative AI model, and uses an emotion engine to recognize the user's emotional state from the input data. It then generates feedback based on the analysis results and the user's emotional state and sends it to the device.

[0591] Input: User's learning goal (in text format)

[0592] Output: Specific learning goals, recognition of emotional states, generation and transmission of feedback

[0593] Specific actions: analyzing input data, recognizing emotions, generating feedback

[0594] Step 3:

[0595] Learning Resource Suggestions

[0596] server

[0597] The server searches for relevant learning resources from a database based on the identified learning objectives and the recognized emotional state, generates a list of optimal learning resources, and sends it to the terminal.

[0598] Terminal

[0599] The terminal displays a list of received learning resources to the user, including a short description of each learning resource and a recommendation comment that takes sentiment into account.

[0600] user

[0601] The user selects an item of interest from the displayed list of learning resources and clicks the Details button to view more information.

[0602] Input: Learning goals and emotional states

[0603] Output: List of learning resources, generate and display recommended comments

[0604] Specific operations: Searching and selecting related learning resources, generating data for display

[0605] Step 4:

[0606] Designing learning paths

[0607] server

[0608] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, learning goals, and emotional state. The learning path consists of multiple specific steps, and the server sends this information to the terminal.

[0609] Terminal

[0610] The device visually displays the designed learning path, showing the steps and their order, allowing the user to review and correct them.

[0611] user

[0612] The user reviews the proposed learning path, modifies it if necessary, and submits the modified learning path to the server.

[0613] Input: Learning objectives, emotional state, selected learning resources

[0614] Output: Learning path design, visual representation, and user correction data

[0615] Specific operations: generating a learning path, generating visual display data, and reflecting corrections

[0616] Step 5:

[0617] Learning progress management

[0618] user

[0619] Users progress through the learning path and report their progress at the end of each step by clicking a progress report button and entering the data into the device.

[0620] Terminal

[0621] The device receives the user's progress information and sends it to the server.

[0622] server

[0623] The server stores progress information in a database, updates the learning status, suggests next steps and additional feedback using a generative AI model, and uses an emotion engine to reassess the user's emotional state, generate feedback based on that, and send it to the device.

[0624] Input: Learning progress information

[0625] Output: Updates to progress tracking data, suggests next steps, and generates emotional feedback

[0626] Specific operations: saving and updating progress information, generating next steps, generating feedback

[0627] Step 6:

[0628] Emotion recognition and feedback regulation

[0629] server

[0630] The server's emotion engine periodically recognizes the user's emotional state during learning and uses a generative AI model to generate feedback and encouraging messages to motivate the user. The generated feedback is then sent to the device.

[0631] Terminal

[0632] The device displays generated feedback and encouragement messages to the user, and provides appropriate support based on their learning progress using progress bars and graphs.

[0633] Input: Periodic emotion data, learning progress

[0634] Output: Generate and display feedback and cheer messages

[0635] Specific behavior: Regular emotion recognition, generating and displaying appropriate feedback

[0636] As described above, this system is designed to provide feedback that takes into account the user's learning goals and emotional state, enabling them to learn efficiently while increasing their motivation.

[0637] (Application example 2)

[0638] 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."

[0639] While conventional self-learning platforms provide features for managing users' learning goals and progress, they do not adequately optimize the learning experience by taking into account the user's emotional state. As a result, users' motivation decreases and learning efficiency declines. Furthermore, the suggestion of learning resources and the design of learning paths do not reflect the user's emotional state, making it difficult to provide optimal support.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0641] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state;] [means for tracking the user's learning progress and suggesting next steps and feedback; and [means for periodically recognizing the user's emotional state and generating feedback and messages to increase motivation.] This makes it possible to optimize the learning experience taking the user's emotional state into consideration.

[0642] "Means for identifying learning objectives from user input" refers to technology that analyzes the information entered by the user into the platform and identifies the user's learning targets and goals.

[0643] The "means for suggesting appropriate learning resources based on identified learning goals and emotional state" is a technology that analyzes the user's learning goals and emotional state, and searches a database for and suggests the most suitable learning resources.

[0644] The "means for designing a learning path based on a user's learning goals and emotional state" is a technology for systematically designing optimal learning steps according to a user's learning goals and emotional state.

[0645] "Means for tracking a user's learning progress and suggesting next steps and feedback" refers to technology that monitors a user's progress as they learn and provides them with the next steps and necessary feedback.

[0646] "Means for periodically recognizing a user's emotional state and generating feedback and messages to enhance motivation" refers to a technology that periodically analyzes a user's emotional state while they are learning, and generates and provides feedback such as encouragement or advice according to that state.

[0647] This invention provides a self-learning platform that combines an emotional engine to improve users' learning experience. Specifically, the system analyzes information entered by users, identifies learning goals, suggests appropriate learning resources, designs learning paths, manages progress, recognizes emotional states, and reflects feedback on the learning process.

[0648] First, the system that realizes this invention includes the following main software components: EmotionEngine, AIModule, and ResourceDatabase. Furthermore, it is assumed that these software components will be installed on a smartphone. Specific hardware that can be used includes smartphones such as iPhone (registered trademark) and Android (registered trademark) devices.

[0649] The server uses the Emotion Engine to analyze the user's input and identify learning goals. The Emotion Engine also analyzes the user's emotional state and identifies states such as positive, negative, and neutral. The AI ​​Module then uses this information to search for appropriate learning resources from the Resource Database and suggest them to the user.

[0650] Furthermore, the server designs an optimal learning path based on the user's learning goals and emotional state. AIModule uses the user's input information and emotional analysis results to construct sequential learning steps. As the user completes each step, the device reports its progress to the server, which tracks it and provides next steps and feedback.

[0651] The emotion engine periodically recognizes the user's emotional state and generates motivational feedback and encouraging messages, which are displayed on the device along with progress bars and graphs to keep the user motivated to continue learning.

[0652] Examples:

[0653] If an employee wants to "improve their customer service skills," enter a prompt like this:

[0654] "I would like to improve my customer service skills. I have learned the basics, but I would like to gain practical application skills with specific examples. I have been feeling unsure about my customer service recently, so I would appreciate any advice on how I can improve."

[0655] The server analyzes this prompt, and the Emotion Engine recognizes the user's emotional state in a positive way. Based on this information, AIModule suggests learning resources from its Resource Database, such as a "Collection of Customer Service Scenarios to Hone Applied Skills." It then designs specific learning steps, such as "Applied Skills Training 1: Basic Scenarios" and "Applied Skills Training 2: Applied Scenarios," and provides these to the user.

[0656] After each step, the server updates the user's progress and generates next steps and encouraging messages as needed. The emotion engine also periodically scans the user's emotional state and provides feedback based on the results, maximizing the user's learning effectiveness.

[0657] In this way, the present invention is able to provide an effective and efficient learning experience while taking into account the user's emotional state.

[0658] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0659] Step 1:

[0660] The user logs into the platform using a terminal and opens an interactive input interface for goal setting.

[0661] Input: A prompt containing the user's learning goals and objectives

[0662] Data processing: The emotion engine analyzes the user's emotional state, and the generative AI model performs text analysis.

[0663] Output: Identified learning objectives and sentiment analysis results

[0664] Step 2:

[0665] The server searches and suggests appropriate learning resources from the ResourceDatabase based on the identified learning goals and emotional state.

[0666] Input: Identified learning objectives and sentiment analysis results

[0667] Data processing: Performing database queries to filter and rank relevant learning resources

[0668] Output: A list of recommended learning resources

[0669] Step 3:

[0670] The server displays recommended learning resources on the user's terminal, and the user selects the resource of interest from this list.

[0671] Input: A list of recommended learning resources

[0672] Data processing: Obtain detailed information about learning resources and generate recommended comments based on emotional states

[0673] Output: Learning resources and recommended comments displayed on the terminal

[0674] Step 4:

[0675] Based on the selected learning resources, the server designs an optimal learning path taking into account the user's learning goals and emotional state.

[0676] Input: Selected learning resources, learning objectives, sentiment analysis results

[0677] Data processing: Generative AI models design and sequence optimal learning steps

[0678] Output: Learning path (list of specific steps)

[0679] Step 5:

[0680] The device visually displays the designed learning path, allowing the user to check and correct it.

[0681] Input: Learning Path

[0682] Data processing: Generate visual learning paths and display them in the user interface

[0683] Output: A learning path display that the user can review and modify

[0684] Step 6:

[0685] The user progresses through the learning path and their progress is reported to the device at the end of each step.

[0686] Input: User progress report

[0687] Data processing: Progress data is sent to the server and learning status is saved in the database

[0688] Output: Updated progress information

[0689] Step 7:

[0690] The server generates the next step and additional feedback based on the progress information and sends it to the device.

[0691] Input: Updated progress information

[0692] Data processing: Generative AI models determine next steps and feedback

[0693] Output: Next steps and feedback displayed on the terminal

[0694] Step 8:

[0695] The emotion engine periodically recognizes the user's emotional state and provides feedback information to the server.

[0696] Input: The user's current emotional state

[0697] Data processing: Emotion recognition algorithms analyze emotional data

[0698] Output: Feedback information reflecting emotional state

[0699] Step 9:

[0700] The device displays supportive messages and feedback generated by the emotion engine to the user.

[0701] Input: Feedback information reflecting emotional state

[0702] Data processing: Determine the display format of the feedback

[0703] Output: A cheering message or feedback that is displayed to the user

[0704] 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.

[0705] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0706] 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.

[0707] [Second embodiment]

[0708] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0709] 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.

[0710] 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).

[0711] 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.

[0712] 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.

[0713] 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).

[0714] 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. 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.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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."

[0720] This invention describes a system that provides personalized learning assistance to users by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[0721] Program processing overview

[0722] This self-learning platform includes the following key features:

[0723] 1. Goal identification

[0724] 2. Learning Resource Suggestions

[0725] 3. Learning path suggestions

[0726] 4. Progress Management

[0727] 1. Goal identification

[0728] Terminal

[0729] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[0730] user

[0731] Enter your learning goals, interests, and objectives.

[0732] server

[0733] A generative AI model analyzes user input to identify learning objectives and uses this information to provide feedback to the user.

[0734] 2. Learning Resource Suggestions

[0735] server

[0736] Based on the identified learning objectives, the database is searched for relevant learning resources and an optimal list is generated.

[0737] Terminal

[0738] Presents a list of learning resources to the user.

[0739] user

[0740] Select the learning resource that interests you from the suggested list and view more information.

[0741] 3. Learning path suggestions

[0742] server

[0743] Based on the selected learning resources and the user's learning goals, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[0744] Terminal

[0745] Visually display the learning path so users can review and correct it.

[0746] user

[0747] Accept the suggested learning path or modify it as needed.

[0748] 4. Progress Management

[0749] user

[0750] Follow the learning path and report your progress at the end of each step.

[0751] Terminal

[0752] Send progress reports to the server.

[0753] server

[0754] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[0755] Terminal

[0756] Provide users with progress visualizations and suggested next steps, such as progress bars and graphs, to help them understand their current learning situation.

[0757] Specific examples

[0758] Setting learning goals

[0759] If a user wants to learn programming, they might do the following:

[0760] user

[0761] Type in "I want to improve my programming skills."

[0762] server

[0763] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript." The platform then verifies this goal and provides feedback to the user.

[0764] Learning Resource Suggestions

[0765] server

[0766] Based on the identified goals, we suggest appropriate learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[0767] Terminal

[0768] Presents a list of learning resources to the user.

[0769] user

[0770] Select the "JavaScript Introduction Course."

[0771] Suggested learning paths

[0772] server

[0773] Based on the selected learning resources, design a learning path that:

[0774] Step 1: Complete the JavaScript Fundamentals course

[0775] Step 2: Advance to the intermediate course

[0776] Terminal

[0777] Visually display and follow the learning path for users.

[0778] user

[0779] Embrace the learning path.

[0780] Progress management

[0781] user

[0782] At the end of each step, progress is reported to the platform.

[0783] Terminal

[0784] Sends the reported progress to the server.

[0785] server

[0786] Track progress and provide next steps or additional feedback.

[0787] Terminal

[0788] Use progress bars and graphs to show progress and let users see the next step.

[0789] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[0790] The processing flow will be explained below.

[0791] Step 1:

[0792] The server sends the HTML and CSS to the device to display the platform's login page.

[0793] Step 2:

[0794] The terminal displays a login form.

[0795] Step 3:

[0796] The user enters their username and password and clicks the Login button.

[0797] Step 4:

[0798] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[0799] Step 5:

[0800] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[0801] Step 6:

[0802] The user clicks the "Set Goal" button.

[0803] Step 7:

[0804] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[0805] Step 8:

[0806] The device displays an interactive interface with the generated AI model.

[0807] Step 9:

[0808] Users enter their learning goals, interests, and objectives.

[0809] Step 10:

[0810] The device sends the user's input to the server.

[0811] Step 11:

[0812] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[0813] Step 12:

[0814] The server searches the database for relevant learning resources based on the identified learning objectives.

[0815] Step 13:

[0816] The server lists the most relevant learning resources from the search results.

[0817] Step 14:

[0818] The terminal displays a list of learning resources to the user.

[0819] Step 15:

[0820] The user selects the learning resource of interest from the suggested list and checks the details.

[0821] Step 16:

[0822] The terminal requests detailed information of the selected learning resource from the server.

[0823] Step 17:

[0824] The server sends the detailed information to the terminal.

[0825] Step 18:

[0826] The user reviews the learning resource and clicks the "Select" button.

[0827] Step 19:

[0828] Based on the server's selected learning resources and the user's learning goals, the generative AI designs the optimal learning path.

[0829] Step 20:

[0830] The server sets up a learning path step by step and sends it to the terminal.

[0831] Step 21:

[0832] The device visually displays your learning path.

[0833] Step 22:

[0834] The user reviews the proposed learning path and clicks the "Accept" button.

[0835] Step 23:

[0836] Users progress through the learning process and report their progress back to the platform at the end of each step.

[0837] Step 24:

[0838] The terminal sends a progress report to the server.

[0839] Step 25:

[0840] The server stores the progress information in a database and updates the user's learning status.

[0841] Step 26:

[0842] The server generates AI suggestions for next steps and additional feedback as needed.

[0843] Step 27:

[0844] The device displays progress visualization and suggested next steps to the user.

[0845] Step 28:

[0846] Users can see their progress using progress bars and graphs and see the next steps to take.

[0847] Example 1

[0848] 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."

[0849] Existing self-learning support systems often struggle to fully meet the individual needs of users. They also lack the support needed to help users clearly define their learning goals, find appropriate learning resources, and progress efficiently. This can lead to poor learning efficiency and the inability to find the optimal learning path.

[0850] 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.

[0851] In this invention, the server includes: [means for a user to log in using a terminal and verify authentication information; [means for identifying learning goals from the user's input and analyzing it using a generative AI model; [means for suggesting related learning resources from a database based on the identified learning goals;] [means for generating an optimal learning path based on the suggested learning resources and visually displaying it;] [means for tracking the user's learning progress and suggesting next steps using a progress bar or graph;] [means for providing detailed feedback using a generative AI model based on the identified learning goals; and [means for accepting interactive input from the user and specifying learning goals in detail using prompt sentences. This enables users to clearly set their learning goals, quickly find appropriate learning resources, and efficiently progress along the optimal learning path.

[0852] "Means for users to log in using a terminal and verify authentication information" refers to a mechanism by which users access the system using an electronic device and are authenticated based on the entered username and password.

[0853] "Means for identifying learning goals from user input and analyzing them using a generative AI model" refers to a mechanism that collects the goals and requirements that users input into the system, analyzes them using a generative AI model, and determines specific learning goals.

[0854] "Means for suggesting relevant learning resources from a database based on identified learning goals" refers to a mechanism that searches the database within the system according to the user's learning goals, and selects and presents relevant educational materials and courses.

[0855] "Means for generating and visually displaying an optimal learning path based on proposed learning resources" refers to a mechanism that takes into account a set of selected learning materials, designs an efficient sequence of learning steps based on that, and displays it on the screen in a format that is easily understandable to the user.

[0856] "Means to track a user's learning progress and suggest next steps using progress bars and graphs" refers to a system that records how far a user has progressed in their learning, visually illustrates that information, and suggests the next learning activity that should be undertaken.

[0857] "Means for providing detailed feedback using a generative AI model based on identified learning goals" refers to a mechanism that generates responses using a generative AI model according to the user's learning goals and provides specific, individualized feedback.

[0858] "Means for accepting interactive user input and using prompts to further identify learning objectives" refers to a mechanism that provides an interactive interface that responds to user input and uses appropriate questions and prompts to further explore the user's learning needs.

[0859] This invention is a system that provides users with personalized learning assistance by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[0860] This system is composed of a server, a terminal, and a user component. A specific embodiment will be described below.

[0861] 1. Hardware and Software Configuration

[0862] server

[0863] The server acts as a central control unit, processes user input, manages learning resources in conjunction with a database, and uses generative AI models to identify learning goals, design learning paths, and track progress.

[0864] Terminal

[0865] A terminal is a client device that receives user input and communicates with a server. Examples include PCs, tablets, and smartphones.

[0866] user

[0867] Users access the system using a terminal, set learning goals, and progress through their studies using suggested learning resources and learning paths.

[0868] Generative AI Models

[0869] Generative AI models analyze user input data and are used to set specific learning goals and design optimal learning paths. Specific examples of software include generative AI using natural language processing technology.

[0870] Database

[0871] A database is a system for storing learning resources, user progress data, set learning goals, etc. A specific example is a relational database management system (RDBMS).

[0872] 2. Example of a system and prompt

[0873] Specific examples of goal setting

[0874] If a user wants to learn data science, they would follow these steps:

[0875] user

[0876] A user goes to a terminal and types in, "I want to learn the basics of data science."

[0877] server

[0878] The server uses a generative AI model to analyze this input and identify the specific learning goal: "Data manipulation with Python," which is provided as feedback to the user.

[0879] Learning Resource Suggestions

[0880] Based on the identified learning objectives, the server searches its database for relevant learning resources and suggests a list such as:

[0881] 1. “Python Data Analysis Basics”

[0882] 2. “Advanced Python Data Science”

[0883] Terminal

[0884] The terminal visually displays these learning resources to the user.

[0885] user

[0886] Users can select "Python Data Analysis Basics" to view more information.

[0887] Specific learning path examples

[0888] Based on the selected learning resources, the server uses generative AI to design the following learning path:

[0889] Step 1: Learn Python Basics (online tutorial)

[0890] Step 2: Analysis using real data (practical exercise)

[0891] This learning path is visually displayed to the user through their device, allowing them to review and correct it.

[0892] Specific examples of progress management

[0893] As users complete each step along their learning path, they receive progress reports via their device.

[0894] server

[0895] The server stores progress information in a database and provides next steps and additional feedback through the generative AI, such as "The next step is to use the Python library pandas to analyze real data."

[0896] Terminal

[0897] The device visually displays progress with progress bars and graphs, allowing users to understand their current learning situation.

[0898] Prompt Sentence Examples

[0899] Examples of specific prompts that users may use to input information into the system include:

[0900] "I want to improve my programming skills"

[0901] "I want to improve my English speaking ability"

[0902] "I want to learn how to diet"

[0903] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[0904] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0905] Step 1:

[0906] User Login

[0907] Terminal

[0908] A user accesses the system using a terminal and the login screen is displayed. The user enters their username and password and presses the login button.

[0909] Input: Username and Password

[0910] server

[0911] The server checks the entered authentication information against the database, and if it matches, it generates the user's session information and returns it to the terminal. If it does not match, it returns an error message.

[0912] Data processing: Verification of authentication information and generation of session information

[0913] Output: Session information or error message

[0914] Step 2:

[0915] goal setting

[0916] Terminal

[0917] After logging in, users select "Goal Setting" from the main menu and an interactive interface is displayed.

[0918] Input: User's choice ("Goal setting")

[0919] user

[0920] Users follow interactive prompts to specify their learning goals, interests, and objectives, for example, "I want to learn the basics of data science."

[0921] Input: Learning goals or interests ("I want to learn the basics of data science")

[0922] server

[0923] The server uses a generative AI model to analyze this input and identify specific learning goals, such as "data manipulation with Python," which are then provided as feedback to the user.

[0924] Data Computation: Generative AI models analyze input data and identify learning goals

[0925] Output: Identified learning objectives (feedback)

[0926] Step 3:

[0927] Learning Resource Suggestions

[0928] server

[0929] Based on the identified learning objective, the server retrieves relevant learning resources from the database, for example, retrieve learning resources related to "Data Manipulation with Python."

[0930] Input: Identified learning objective ("Data manipulation with Python")

[0931] Data processing: Extracting appropriate learning resources through database search

[0932] Output: A list of related learning resources

[0933] Terminal

[0934] The terminal visually displays the list of learning resources sent from the server to the user.

[0935] Input: List of learning resources

[0936] user

[0937] Users can select the learning resource they are interested in from the displayed list to view more information, for example, "Python Data Analysis Basics."

[0938] Input: Selected learning resource ("Python Data Analysis Basics")

[0939] Output: Detailed information about the learning resource

[0940] Step 4:

[0941] Designing learning paths

[0942] server

[0943] Based on the selected learning resources, the server uses a generative AI model to design an optimal learning path, which consists of specific steps, such as "Step 1: Learn the basics of Python" and "Step 2: Analyze using real data."

[0944] Input: Selected learning resource ("Python Data Analysis Basics")

[0945] Data Computing: Designing Learning Paths with Generative AI Models

[0946] Output: Learning path

[0947] Terminal

[0948] It visually displays the learning path and allows users to review and correct it.

[0949] Input: Learning Path

[0950] user

[0951] The user accepts the proposed learning path or modifies it as needed. The user confirms the learning path.

[0952] Input: User confirmation and corrected learning path

[0953] Output: Confirmed learning path

[0954] Step 5:

[0955] Progress management

[0956] user

[0957] Users progress along a learning path and report their progress at the end of each step.

[0958] Input: Progress report

[0959] Terminal

[0960] The terminal sends progress reports to the server.

[0961] Input: Progress report

[0962] server

[0963] The server stores progress information in a database and provides next steps and additional feedback to the generative AI model, such as "The next step is to use the Python library pandas to analyze real data."

[0964] Data processing: storing progress information and generating feedback

[0965] Output: Next steps and additional feedback (feedback content)

[0966] Terminal

[0967] Progress is visually displayed in the form of progress bars and graphs, allowing users to understand their current learning situation.

[0968] Input: progress

[0969] Output: Visual progress indicator (progress bar and graph)

[0970] (Application example 1)

[0971] 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."

[0972] Conventional learning support systems have difficulty providing optimal learning paths for each user and managing their learning progress. Furthermore, they are limited to setting goals through text input and suggesting learning resources, resulting in a limited diversity in the user experience. Furthermore, the lack of statistical display of learning history and notification functions makes it difficult for users to efficiently grasp their learning progress.

[0973] 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.

[0974] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals;] [means for designing a learning path based on the user's learning goals;] [means for tracking the user's learning progress and suggesting next steps;] [means for accepting voice input;] [means for providing task notifications and reminders; and [means for displaying learning history statistics.] This makes it possible to provide learning support customized for each user, resulting in an efficient and diverse learning experience.

[0975] "Means for identifying learning goals from user input" refers to a function that accepts voice or text input, analyzes the content using a generative AI model, and specifically identifies the user's learning goals.

[0976] The "means for suggesting appropriate learning resources based on identified learning objectives" is a function that searches for relevant learning resources from a database based on the identified learning objectives, generates an optimal list, and suggests it to the user.

[0977] "Means for designing a learning path based on the user's learning goals" refers to a function in which the generative AI designs an optimal learning path based on the selected learning resources and the user's learning goals, and indicates the content and order of each step.

[0978] "Means for tracking the user's learning progress and suggesting next steps" refers to a function that stores the user's learning progress in a database and provides the next learning step or additional feedback depending on the situation.

[0979] The "means for accepting voice input" is a function for accepting voice input of learning goals and progress information from the user using a voice input device such as a microphone.

[0980] "Means for providing task notifications and reminders" refers to a function that provides notifications and reminders based on the learning goals and progress set by the user, encouraging them to complete a learning step or move on to the next task.

[0981] "Means for statistically displaying learning history" refers to a function that aggregates a user's learning history and displays it statistically using graphs and progress bars, allowing the user to visualize their own learning progress.

[0982] The present invention relates to a system for providing individually customized learning support to a user. Specific embodiments for carrying out the present invention are described below.

[0983] This system is configured using the following hardware and software.

[0984] Required Hardware

[0985] Smart devices (e.g. smartphones, tablets)

[0986] A microphone with voice input capabilities

[0987] Display Screen

[0988] Required software

[0989] Mobile application development frameworks (e.g., Flutter, React Native)

[0990] Database (e.g. Firebase Firestore)

[0991] Generative AI models (e.g., OpenAI GPT-4)

[0992] Serverless functions (e.g., Google Cloud Functions)

[0993] System Overview

[0994] User authentication and goal setting

[0995] Users log in to the application using their smart device. After logging in, they select "Goal Setting" from the main menu and enter their learning goals via voice or text input. This input is analyzed by a generative AI model (e.g., OpenAI GPT-4) to identify specific learning goals.

[0996] Example: A user says, "I want to learn the basics of JavaScript."

[0997] User: "I want to learn the basics of JavaScript."

[0998] AI: "So your goal is to learn the basics of JavaScript? Here are some suggested learning resources:

[0999] Learning Resource Suggestions

[1000] The server searches a database (e.g., Firebase Firestore) for relevant learning resources based on the identified learning objectives, generates an optimal list, and suggests it to the user. The user can select the learning resource of interest from the suggested list and check the detailed information.

[1001] Example: Learning resource suggestions

[1002] AI: "Which of these learning resources are you most interested in?"

[1003] User: Select "JavaScript Introduction Course"

[1004] Suggested learning paths

[1005] Based on the learning resources selected by the user, the server uses a generative AI model to design an optimal learning path. The learning path is structured into specific steps and visually displayed on the screen. The user can review the path and make any necessary adjustments.

[1006] Progress management

[1007] As the user completes each learning step, progress information is sent to the server and stored in a database. The server then provides the user with the next learning step or additional feedback, and displays progress using progress bars and graphs. Progress can also be reported via voice input.

[1008] Example: Progress management

[1009] The server statistically displays the user's learning history and helps promote learning by using task notification and reminder functions.

[1010] This makes it easier for users to visually grasp their learning progress and move on to the next step efficiently.

[1011] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1012] Step 1:

[1013] User authentication and goal setting

[1014] Input: A user logs into the application using a smart device and selects "Goal Setting" from the main menu.

[1015] Specific behavior:

[1016] 1. The device receives the user's login information and performs authentication.

[1017] 2. If authentication is successful, the "Goal Setting" screen will be displayed.

[1018] 3. The user inputs their learning goals by voice or text input.

[1019] 4. The device receives user input and sends it to the server.

[1020] Data processing and calculation:

[1021] The server passes the received voice or text input to a generative AI model (e.g., OpenAI GPT-4) for analysis.

[1022] output:

[1023] The generative AI model identifies specific learning goals as a result of the analysis and provides feedback to the user.

[1024] Step 2:

[1025] Learning Resource Suggestions

[1026] Input: User confirms identified learning objective.

[1027] Specific behavior:

[1028] 1. Based on the identified learning objectives, the server searches for relevant learning resources from a database (e.g., Firebase Firestore).

[1029] 2. Generate a list of learning resources based on the search results and send it to the terminal.

[1030] 3. The terminal displays a list of learning resources to the user.

[1031] Data processing and calculation:

[1032] The server queries the database for learning resources that match the learning objectives and lists the most suitable learning resources.

[1033] output:

[1034] Users can select the learning resource of interest from the displayed list and check the detailed information.

[1035] Step 3:

[1036] Suggested learning paths

[1037] Input: The learning resource selected by the user.

[1038] Specific behavior:

[1039] 1. The terminal sends information about the learning resource selected by the user to the server.

[1040] 2. The server uses a generative AI model to design an optimal learning path based on the selected learning resources and learning goals.

[1041] 3. Send the designed learning path to the device and display it visually.

[1042] 4. The user reviews the learning path and makes any necessary adjustments.

[1043] Data processing and calculation:

[1044] The server takes the selected learning resources and learning goals as input and performs data calculations to generate a learning path.

[1045] output:

[1046] The optimal learning path is presented to the user, who can confirm it and proceed to the next step.

[1047] Step 4:

[1048] Progress management

[1049] Input: The user progresses through the learning path.

[1050] Specific behavior:

[1051] 1. The device reports progress as the user completes each learning step.

[1052] 2. The device sends progress information to the server.

[1053] 3. The server stores the progress information in a database and suggests the next learning step.

[1054] 4. Use progress bars and graphs to show progress to the user.

[1055] Data processing and calculation:

[1056] The server receives the progress data, updates the learning progress, suggests next steps, and visualizes the progress.

[1057] output:

[1058] Users can visually see their progress and efficiently move to the next step.

[1059] 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.

[1060] This invention describes a self-learning platform that combines an emotion engine that recognizes users' emotions to improve users' learning experience. Specifically, it identifies learning goals from users' inputs, suggests appropriate learning resources, designs learning paths, manages progress, and also recognizes users' emotional states and reflects them in the learning process.

[1061] Program processing overview

[1062] This self-learning platform includes the following key features:

[1063] 1. Goal identification

[1064] 2. Learning Resource Suggestions

[1065] 3. Learning path suggestions

[1066] 4. Progress Management

[1067] 5. Emotion recognition and feedback regulation

[1068] 1. Goal identification

[1069] Terminal

[1070] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[1071] user

[1072] Enter your learning goals, interests, and objectives.

[1073] server

[1074] A generative AI model analyzes user input, and an emotion engine recognizes the user's emotional state, identifies learning goals, and provides feedback to the user based on this information.

[1075] 2. Learning Resource Suggestions

[1076] server

[1077] Based on the identified learning goals and emotional state, relevant learning resources are searched for in the database and an optimal list is generated.

[1078] Terminal

[1079] Presents a list of learning resources to the user.

[1080] user

[1081] Select the learning resource that interests you from the suggested list and view more information.

[1082] 3. Learning path suggestions

[1083] server

[1084] Based on the selected learning resources, the user's learning goals, and their emotional state, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[1085] Terminal

[1086] Visually display the learning path so users can review and correct it.

[1087] user

[1088] Accept the suggested learning path or modify it as needed.

[1089] 4. Progress Management

[1090] user

[1091] Follow the learning path and report your progress at the end of each step.

[1092] Terminal

[1093] Send progress reports to the server.

[1094] server

[1095] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[1096] Terminal

[1097] Provide users with progress visualization and suggested next steps.

[1098] 5. Emotion recognition and feedback regulation

[1099] server

[1100] The emotion engine periodically recognizes the user's emotional state while learning and generates feedback and encouraging messages to motivate the user.

[1101] Terminal

[1102] The emotion engine generates feedback and messages that are displayed to the user, and progress bars and graphs are used to provide support that takes into account the user's emotional state as they progress through the learning process.

[1103] Specific examples

[1104] Setting learning goals

[1105] If a user wants to improve their programming skills, they might do the following:

[1106] user

[1107] Type in "I want to improve my programming skills."

[1108] server

[1109] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript." At the same time, the emotion engine recognizes positive emotions from the user's text input and provides feedback to the user, such as "Your goal is great!"

[1110] Learning Resource Suggestions

[1111] server

[1112] Based on the identified goals and emotional state, it suggests the best learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[1113] Terminal

[1114] Present users with a list of learning resources and provide recommended comments that reflect the user's emotional state (e.g., "This course is beginner-friendly and fun to learn").

[1115] user

[1116] Select the "JavaScript Introduction Course."

[1117] Suggested learning paths

[1118] server

[1119] Based on the selected learning resources, design a learning path that:

[1120] Step 1: Complete the JavaScript Fundamentals course

[1121] Step 2: Advance to the intermediate course

[1122] Terminal

[1123] The learning path is visually displayed and confirmed by the user, and the emotion engine displays encouraging messages such as, "Once you've completed step 1, you'll be motivated to move on to the next step right away."

[1124] Progress management

[1125] user

[1126] At the end of each step, progress is reported to the platform.

[1127] Terminal

[1128] Sends the reported progress to the server.

[1129] server

[1130] It tracks progress and provides next steps and additional feedback, while an emotion engine periodically scans the user's emotional state and adjusts the feedback as needed.

[1131] Terminal

[1132] It displays progress using progress bars and graphs, letting users see the next steps they need to take, along with encouraging messages provided by an emotion engine.

[1133] The above is a specific embodiment of the present invention, which allows users to have an effective and efficient learning experience that takes into account their emotional state.

[1134] The processing flow will be explained below.

[1135] Step 1:

[1136] The server sends the HTML and CSS to the device to display the platform's login page.

[1137] Step 2:

[1138] The terminal displays a login form.

[1139] Step 3:

[1140] The user enters their username and password and clicks the Login button.

[1141] Step 4:

[1142] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[1143] Step 5:

[1144] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[1145] Step 6:

[1146] The user clicks the "Set Goal" button.

[1147] Step 7:

[1148] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[1149] Step 8:

[1150] The device displays an interactive interface with the generated AI model.

[1151] Step 9:

[1152] Users enter their learning goals, interests, and objectives.

[1153] Step 10:

[1154] The device sends the user's input to the server.

[1155] Step 11:

[1156] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[1157] Step 12:

[1158] The server uses an emotion engine to determine an emotional state from the user's input.

[1159] Step 13:

[1160] The server searches a database for relevant learning resources based on the identified learning goal and emotional state.

[1161] Step 14:

[1162] The server lists related learning resources and generates recommendation comments for the learning resources using an emotion engine.

[1163] Step 15:

[1164] The device displays a list of learning resources and recommended comments to the user.

[1165] Step 16:

[1166] The user selects the learning resource of interest from the suggested list and checks the details.

[1167] Step 17:

[1168] The terminal requests detailed information of the selected learning resource from the server.

[1169] Step 18:

[1170] The server sends the detailed information to the terminal.

[1171] Step 19:

[1172] The user reviews the learning resource and clicks the "Select" button.

[1173] Step 20:

[1174] Based on the learning resources selected by the server, the user's learning goals, and their emotional state, the generative AI designs the optimal learning path.

[1175] Step 20:

[1176] The server includes encouraging messages generated by the emotion engine at each step of the learning path.

[1177] Step 21:

[1178] The server sets up a learning path step by step and sends it to the terminal.

[1179] Step 22:

[1180] The device visually displays your learning path.

[1181] Step 23:

[1182] The user reviews the proposed learning path and clicks the "Accept" button.

[1183] Step 24:

[1184] Users progress through the learning process and report their progress back to the platform at the end of each step.

[1185] Step 25:

[1186] The terminal sends a progress report to the server.

[1187] Step 26:

[1188] The server stores the progress information in a database and updates the user's learning status.

[1189] Step 27:

[1190] The server generates next steps and additional feedback as needed, and the AI ​​suggests them, and generates encouraging messages using the emotion engine.

[1191] Step 28:

[1192] The device displays progress visualization and suggested next steps to the user.

[1193] Step 29:

[1194] The device displays encouraging messages generated by the emotion engine to the user, and provides support that takes into account the user's emotional state along with the learning progress using progress bars and graphs.

[1195] Step 30:

[1196] Users can see their progress using progress bars and graphs and see the next steps to take.

[1197] Example 2

[1198] 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."

[1199] While traditional self-learning systems can provide appropriate learning resources and set learning paths based on a user's learning goals, they do not take the user's emotional state into consideration. As a result, they provide insufficient support to increase user motivation and maximize learning outcomes. They also lack the ability to provide real-time feedback based on the user's progress. As a result, users often lose motivation to continue learning, hindering efficient learning.

[1200] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1201] In this invention, the server includes: [means for identifying learning goals from user input and recognizing the emotional state;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state; and [means for tracking the user's learning progress, suggesting next steps, and providing feedback based on the emotional state.] This enables learning support that takes the user's emotional state into consideration, providing an efficient and effective learning experience while increasing motivation.

[1202] "User" refers to an individual who intends to use the System to achieve their learning goals.

[1203] "Server" refers to the central processing unit that receives input from users and uses generative AI models and emotion engines to analyze data, make recommendations, and manage progress.

[1204] A "generative AI model" is a type of artificial intelligence that analyzes user input data and suggests appropriate learning goals and paths.

[1205] The "emotion engine" is a piece of software that recognizes the user's emotional state from their input data and provides feedback according to the learning process.

[1206] "Learning goals" refer to the specific learning content or skills that a user wants to achieve.

[1207] "Learning Resources" refers to the learning materials, content, courses, etc. provided to help users achieve their learning goals.

[1208] A "learning path" is a plan that includes specific learning steps and the order in which they must be undertaken to achieve a learning goal.

[1209] "Progress management" refers to the process of tracking a user's learning progress and providing next steps and feedback.

[1210] "Feedback" refers to encouraging messages and advice provided based on the user's learning progress and emotional state.

[1211] This invention provides a self-learning platform that combines an emotion engine that recognizes users' emotions to improve the user's learning experience. Specifically, the system identifies learning goals from users' input, suggests appropriate learning resources, designs learning paths, and manages progress, as well as recognizes the user's emotional state and reflects it in the learning process.

[1212] Hardware and software used

[1213] The system uses the following major hardware and software:

[1214] Server: The central processing unit that runs the generative AI models and emotion engine, and manages the database.

[1215] Terminal: A device (computer, smartphone, tablet, etc.) that provides the interface and sends user input to the server.

[1216] Generative AI model: An artificial intelligence model that analyzes user input data and suggests appropriate learning goals and paths.

[1217] Emotion engine: Software that recognizes the user's emotional state from input data and provides feedback according to the learning process.

[1218] Specific operation of the system

[1219] 1. Identify learning goals and recognize emotional states from user input

[1220] Terminal

[1221] The user logs into the platform using a terminal and opens an interactive interface for goal setting.

[1222] user

[1223] Users enter their learning goals, interests, and what they want to learn.

[1224] server

[1225] The server uses a generative AI model to analyze the user's input data and identify specific learning goals, while an emotion engine recognizes the user's emotional state from the text data.

[1226] 2. Suggest appropriate learning resources

[1227] server

[1228] The server searches the database for relevant learning resources based on the identified learning objectives and the recognized emotional state, and generates an optimal list.

[1229] Terminal

[1230] The terminal displays the generated list of learning resources to the user.

[1231] user

[1232] Users select learning resources of interest from the suggested list and view their detailed information.

[1233] 3. Design a learning path

[1234] server

[1235] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, the user's learning goals, and their emotional state. The learning path is composed of specific steps.

[1236] Terminal

[1237] The device visually displays the designed learning path for the user to review.

[1238] 4. Track learning progress, suggest next steps, and provide feedback based on emotional state

[1239] user

[1240] Users progress along a learning path and report their progress at the end of each step.

[1241] Terminal

[1242] The terminal sends progress reports from the user to the server.

[1243] server

[1244] The server stores progress information in a database, uses a generative AI model to suggest next steps and additional feedback, and uses an emotion engine to periodically recognize the user's emotional state and generate encouraging messages and advice based on that state.

[1245] Terminal

[1246] The device will then display generated feedback and encouragement messages to the user, allowing them to visually see their progress.

[1247] Examples of concrete examples and prompts

[1248] Specific examples

[1249] A user enters "I want to improve my programming skills," and the server parses this to identify "I want to learn the basics of JavaScript." The emotion engine recognizes a positive emotional state and provides feedback like, "Your goals are great!" The server then suggests learning resources, such as "Introductory JavaScript courses," and designs a learning path.

[1250] Prompt Sentence Examples

[1251] "Tell me about your learning goals."

[1252] Enter the skill you would like to improve.

[1253] As described above, the present invention is a system that provides an effective and efficient learning experience that takes into account the user's emotional state.

[1254] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1255] Step 1:

[1256] Login and User Authentication

[1257] Terminal

[1258] The terminal displays a login screen and prompts the user to enter their ID and password. The entered data is sent to the server when the login button is pressed.

[1259] user

[1260] The user enters their ID and password and clicks the login button.

[1261] server

[1262] The server verifies the received ID and password against the user data in the database. If authentication is successful, it sends the main menu to the terminal to receive the next input. If authentication fails, it generates an error message and sends it to the terminal.

[1263] Input: User ID and Password

[1264] Output: Authentication result (success / failure), main menu or error message sent

[1265] Specific operations: ID and password verification, determining next steps based on authentication results

[1266] Step 2:

[1267] Setting learning goals

[1268] Terminal

[1269] The device displays the main menu and prompts the user to click the "Goal Setting" button, and the interface displays prompts for interaction with the generative AI model.

[1270] user

[1271] Users click the "Set Goals" button, follow the prompts displayed, enter their learning goals, and then click the submit button.

[1272] server

[1273] The server receives the user's input data, analyzes it using a generative AI model, and uses an emotion engine to recognize the user's emotional state from the input data. It then generates feedback based on the analysis results and the user's emotional state and sends it to the device.

[1274] Input: User's learning goal (in text format)

[1275] Output: Specific learning goals, recognition of emotional states, generation and transmission of feedback

[1276] Specific actions: analyzing input data, recognizing emotions, generating feedback

[1277] Step 3:

[1278] Learning Resource Suggestions

[1279] server

[1280] The server searches for relevant learning resources from a database based on the identified learning objectives and the recognized emotional state, generates a list of optimal learning resources, and sends it to the terminal.

[1281] Terminal

[1282] The terminal displays a list of received learning resources to the user, including a short description of each learning resource and a recommendation comment that takes sentiment into account.

[1283] user

[1284] The user selects an item of interest from the displayed list of learning resources and clicks the Details button to view more information.

[1285] Input: Learning goals and emotional states

[1286] Output: List of learning resources, generate and display recommended comments

[1287] Specific operations: Searching and selecting related learning resources, generating data for display

[1288] Step 4:

[1289] Designing learning paths

[1290] server

[1291] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, learning goals, and emotional state. The learning path consists of multiple specific steps, and the server sends this information to the terminal.

[1292] Terminal

[1293] The device visually displays the designed learning path, showing the steps and their order, allowing the user to review and correct them.

[1294] user

[1295] The user reviews the proposed learning path, modifies it if necessary, and submits the modified learning path to the server.

[1296] Input: Learning objectives, emotional state, selected learning resources

[1297] Output: Learning path design, visual representation, and user correction data

[1298] Specific operations: generating a learning path, generating visual display data, and reflecting corrections

[1299] Step 5:

[1300] Learning progress management

[1301] user

[1302] Users progress through the learning path and report their progress at the end of each step by clicking a progress report button and entering the data into the device.

[1303] Terminal

[1304] The device receives the user's progress information and sends it to the server.

[1305] server

[1306] The server stores progress information in a database, updates the learning status, suggests next steps and additional feedback using a generative AI model, and uses an emotion engine to reassess the user's emotional state, generate feedback based on that, and send it to the device.

[1307] Input: Learning progress information

[1308] Output: Updates to progress tracking data, suggests next steps, and generates emotional feedback

[1309] Specific operations: saving and updating progress information, generating next steps, generating feedback

[1310] Step 6:

[1311] Emotion recognition and feedback regulation

[1312] server

[1313] The server's emotion engine periodically recognizes the user's emotional state during learning and uses a generative AI model to generate feedback and encouraging messages to motivate the user. The generated feedback is then sent to the device.

[1314] Terminal

[1315] The device displays generated feedback and encouragement messages to the user, and provides appropriate support based on their learning progress using progress bars and graphs.

[1316] Input: Periodic emotion data, learning progress

[1317] Output: Generate and display feedback and cheer messages

[1318] Specific behavior: Regular emotion recognition, generating and displaying appropriate feedback

[1319] As described above, this system is designed to provide feedback that takes into account the user's learning goals and emotional state, enabling them to learn efficiently while increasing their motivation.

[1320] (Application example 2)

[1321] 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."

[1322] While conventional self-learning platforms provide features for managing users' learning goals and progress, they do not adequately optimize the learning experience by taking into account the user's emotional state. As a result, users' motivation decreases and learning efficiency declines. Furthermore, the suggestion of learning resources and the design of learning paths do not reflect the user's emotional state, making it difficult to provide optimal support.

[1323] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1324] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state;] [means for tracking the user's learning progress and suggesting next steps and feedback; and [means for periodically recognizing the user's emotional state and generating feedback and messages to increase motivation.] This makes it possible to optimize the learning experience taking the user's emotional state into consideration.

[1325] "Means for identifying learning objectives from user input" refers to technology that analyzes the information entered by the user into the platform and identifies the user's learning targets and goals.

[1326] The "means for suggesting appropriate learning resources based on identified learning goals and emotional state" is a technology that analyzes the user's learning goals and emotional state, and searches a database for and suggests the most suitable learning resources.

[1327] The "means for designing a learning path based on a user's learning goals and emotional state" is a technology for systematically designing optimal learning steps according to a user's learning goals and emotional state.

[1328] "Means for tracking a user's learning progress and suggesting next steps and feedback" refers to technology that monitors a user's progress as they learn and provides them with the next steps and necessary feedback.

[1329] "Means for periodically recognizing a user's emotional state and generating feedback and messages to enhance motivation" refers to a technology that periodically analyzes a user's emotional state while they are learning, and generates and provides feedback such as encouragement or advice according to that state.

[1330] This invention provides a self-learning platform that combines an emotional engine to improve users' learning experience. Specifically, the system analyzes information entered by users, identifies learning goals, suggests appropriate learning resources, designs learning paths, manages progress, recognizes emotional states, and reflects feedback on the learning process.

[1331] First, the system that realizes this invention includes the following main software components: EmotionEngine, AIModule, and ResourceDatabase. Furthermore, it is assumed that these software components will be installed on a smartphone. Specific hardware that can be used is smartphones such as iPhones and Android devices.

[1332] The server uses the Emotion Engine to analyze the user's input and identify learning goals. The Emotion Engine also analyzes the user's emotional state and identifies states such as positive, negative, and neutral. The AI ​​Module then uses this information to search for appropriate learning resources from the Resource Database and suggest them to the user.

[1333] Furthermore, the server designs an optimal learning path based on the user's learning goals and emotional state. AIModule uses the user's input information and emotional analysis results to construct sequential learning steps. As the user completes each step, the device reports its progress to the server, which tracks it and provides next steps and feedback.

[1334] The emotion engine periodically recognizes the user's emotional state and generates motivational feedback and encouraging messages, which are displayed on the device along with progress bars and graphs to keep the user motivated to continue learning.

[1335] Examples:

[1336] If an employee wants to "improve their customer service skills," enter a prompt like this:

[1337] "I would like to improve my customer service skills. I have learned the basics, but I would like to gain practical application skills with specific examples. I have been feeling unsure about my customer service recently, so I would appreciate any advice on how I can improve."

[1338] The server analyzes this prompt, and the Emotion Engine recognizes the user's emotional state in a positive way. Based on this information, AIModule suggests learning resources from its Resource Database, such as a "Collection of Customer Service Scenarios to Hone Applied Skills." It then designs specific learning steps, such as "Applied Skills Training 1: Basic Scenarios" and "Applied Skills Training 2: Applied Scenarios," and provides these to the user.

[1339] After each step, the server updates the user's progress and generates next steps and encouraging messages as needed. The emotion engine also periodically scans the user's emotional state and provides feedback based on the results, maximizing the user's learning effectiveness.

[1340] In this way, the present invention is able to provide an effective and efficient learning experience while taking into account the user's emotional state.

[1341] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1342] Step 1:

[1343] The user logs into the platform using a terminal and opens an interactive input interface for goal setting.

[1344] Input: A prompt containing the user's learning goals and objectives

[1345] Data processing: The emotion engine analyzes the user's emotional state, and the generative AI model performs text analysis.

[1346] Output: Identified learning objectives and sentiment analysis results

[1347] Step 2:

[1348] The server searches and suggests appropriate learning resources from the ResourceDatabase based on the identified learning goals and emotional state.

[1349] Input: Identified learning objectives and sentiment analysis results

[1350] Data processing: Performing database queries to filter and rank relevant learning resources

[1351] Output: A list of recommended learning resources

[1352] Step 3:

[1353] The server displays recommended learning resources on the user's terminal, and the user selects the resource of interest from this list.

[1354] Input: A list of recommended learning resources

[1355] Data processing: Obtain detailed information about learning resources and generate recommended comments based on emotional states

[1356] Output: Learning resources and recommended comments displayed on the terminal

[1357] Step 4:

[1358] Based on the selected learning resources, the server designs an optimal learning path taking into account the user's learning goals and emotional state.

[1359] Input: Selected learning resources, learning objectives, sentiment analysis results

[1360] Data processing: Generative AI models design and sequence optimal learning steps

[1361] Output: Learning path (list of specific steps)

[1362] Step 5:

[1363] The device visually displays the designed learning path, allowing the user to check and correct it.

[1364] Input: Learning Path

[1365] Data processing: Generate visual learning paths and display them in the user interface

[1366] Output: A learning path display that the user can review and modify

[1367] Step 6:

[1368] The user progresses through the learning path and their progress is reported to the device at the end of each step.

[1369] Input: User progress report

[1370] Data processing: Progress data is sent to the server and learning status is saved in the database

[1371] Output: Updated progress information

[1372] Step 7:

[1373] The server generates the next step and additional feedback based on the progress information and sends it to the device.

[1374] Input: Updated progress information

[1375] Data processing: Generative AI models determine next steps and feedback

[1376] Output: Next steps and feedback displayed on the terminal

[1377] Step 8:

[1378] The emotion engine periodically recognizes the user's emotional state and provides feedback information to the server.

[1379] Input: The user's current emotional state

[1380] Data processing: Emotion recognition algorithms analyze emotional data

[1381] Output: Feedback information reflecting emotional state

[1382] Step 9:

[1383] The device displays supportive messages and feedback generated by the emotion engine to the user.

[1384] Input: Feedback information reflecting emotional state

[1385] Data processing: Determine the display format of the feedback

[1386] Output: A cheering message or feedback that is displayed to the user

[1387] 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.

[1388] 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.

[1389] 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.

[1390] [Third embodiment]

[1391] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1392] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1393] 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).

[1394] 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.

[1395] 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.

[1396] 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).

[1397] 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. 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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."

[1403] This invention describes a system that provides personalized learning assistance to users by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[1404] Program processing overview

[1405] This self-learning platform includes the following key features:

[1406] 1. Goal identification

[1407] 2. Learning Resource Suggestions

[1408] 3. Learning path suggestions

[1409] 4. Progress Management

[1410] 1. Goal identification

[1411] Terminal

[1412] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[1413] user

[1414] Enter your learning goals, interests, and objectives.

[1415] server

[1416] A generative AI model analyzes user input to identify learning objectives and uses this information to provide feedback to the user.

[1417] 2. Learning Resource Suggestions

[1418] server

[1419] Based on the identified learning objectives, the database is searched for relevant learning resources and an optimal list is generated.

[1420] Terminal

[1421] Presents a list of learning resources to the user.

[1422] user

[1423] Select the learning resource that interests you from the suggested list and view more information.

[1424] 3. Learning path suggestions

[1425] server

[1426] Based on the selected learning resources and the user's learning goals, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[1427] Terminal

[1428] Visually display the learning path so users can review and correct it.

[1429] user

[1430] Accept the suggested learning path or modify it as needed.

[1431] 4. Progress Management

[1432] user

[1433] Follow the learning path and report your progress at the end of each step.

[1434] Terminal

[1435] Send progress reports to the server.

[1436] server

[1437] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[1438] Terminal

[1439] Provide users with progress visualizations and suggested next steps, such as progress bars and graphs, to help them understand their current learning situation.

[1440] Specific examples

[1441] Setting learning goals

[1442] If a user wants to learn programming, they might do the following:

[1443] user

[1444] Type in "I want to improve my programming skills."

[1445] server

[1446] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript." The platform then verifies this goal and provides feedback to the user.

[1447] Learning Resource Suggestions

[1448] server

[1449] Based on the identified goals, we suggest appropriate learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[1450] Terminal

[1451] Presents a list of learning resources to the user.

[1452] user

[1453] Select the "JavaScript Introduction Course."

[1454] Suggested learning paths

[1455] server

[1456] Based on the selected learning resources, design a learning path that:

[1457] Step 1: Complete the JavaScript Fundamentals course

[1458] Step 2: Advance to the intermediate course

[1459] Terminal

[1460] Visually display and follow the learning path for users.

[1461] user

[1462] Embrace the learning path.

[1463] Progress management

[1464] user

[1465] At the end of each step, progress is reported to the platform.

[1466] Terminal

[1467] Sends the reported progress to the server.

[1468] server

[1469] Track progress and provide next steps or additional feedback.

[1470] Terminal

[1471] Use progress bars and graphs to show progress and let users see the next step.

[1472] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[1473] The processing flow will be explained below.

[1474] Step 1:

[1475] The server sends the HTML and CSS to the device to display the platform's login page.

[1476] Step 2:

[1477] The terminal displays a login form.

[1478] Step 3:

[1479] The user enters their username and password and clicks the Login button.

[1480] Step 4:

[1481] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[1482] Step 5:

[1483] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[1484] Step 6:

[1485] The user clicks the "Set Goal" button.

[1486] Step 7:

[1487] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[1488] Step 8:

[1489] The device displays an interactive interface with the generated AI model.

[1490] Step 9:

[1491] Users enter their learning goals, interests, and objectives.

[1492] Step 10:

[1493] The device sends the user's input to the server.

[1494] Step 11:

[1495] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[1496] Step 12:

[1497] The server searches the database for relevant learning resources based on the identified learning objectives.

[1498] Step 13:

[1499] The server lists the most relevant learning resources from the search results.

[1500] Step 14:

[1501] The terminal displays a list of learning resources to the user.

[1502] Step 15:

[1503] The user selects the learning resource of interest from the suggested list and checks the details.

[1504] Step 16:

[1505] The terminal requests detailed information of the selected learning resource from the server.

[1506] Step 17:

[1507] The server sends the detailed information to the terminal.

[1508] Step 18:

[1509] The user reviews the learning resource and clicks the "Select" button.

[1510] Step 19:

[1511] Based on the server's selected learning resources and the user's learning goals, the generative AI designs the optimal learning path.

[1512] Step 20:

[1513] The server sets up a learning path step by step and sends it to the terminal.

[1514] Step 21:

[1515] The device visually displays your learning path.

[1516] Step 22:

[1517] The user reviews the proposed learning path and clicks the "Accept" button.

[1518] Step 23:

[1519] Users progress through the learning process and report their progress back to the platform at the end of each step.

[1520] Step 24:

[1521] The terminal sends a progress report to the server.

[1522] Step 25:

[1523] The server stores the progress information in a database and updates the user's learning status.

[1524] Step 26:

[1525] The server generates AI suggestions for next steps and additional feedback as needed.

[1526] Step 27:

[1527] The device displays progress visualization and suggested next steps to the user.

[1528] Step 28:

[1529] Users can see their progress using progress bars and graphs and see the next steps to take.

[1530] Example 1

[1531] 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."

[1532] Existing self-learning support systems often struggle to fully meet the individual needs of users. They also lack the support needed to help users clearly define their learning goals, find appropriate learning resources, and progress efficiently. This can lead to poor learning efficiency and the inability to find the optimal learning path.

[1533] 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.

[1534] In this invention, the server includes: [means for a user to log in using a terminal and verify authentication information; [means for identifying learning goals from the user's input and analyzing it using a generative AI model; [means for suggesting related learning resources from a database based on the identified learning goals;] [means for generating an optimal learning path based on the suggested learning resources and visually displaying it;] [means for tracking the user's learning progress and suggesting next steps using a progress bar or graph;] [means for providing detailed feedback using a generative AI model based on the identified learning goals; and [means for accepting interactive input from the user and specifying learning goals in detail using prompt sentences. This enables users to clearly set their learning goals, quickly find appropriate learning resources, and efficiently progress along the optimal learning path.

[1535] "Means for users to log in using a terminal and verify authentication information" refers to a mechanism by which users access the system using an electronic device and are authenticated based on the entered username and password.

[1536] "Means for identifying learning goals from user input and analyzing them using a generative AI model" refers to a mechanism that collects the goals and requirements that users input into the system, analyzes them using a generative AI model, and determines specific learning goals.

[1537] "Means for suggesting relevant learning resources from a database based on identified learning goals" refers to a mechanism that searches the database within the system according to the user's learning goals, and selects and presents relevant educational materials and courses.

[1538] "Means for generating and visually displaying an optimal learning path based on proposed learning resources" refers to a mechanism that takes into account a set of selected learning materials, designs an efficient sequence of learning steps based on that, and displays it on the screen in a format that is easily understandable to the user.

[1539] "Means to track a user's learning progress and suggest next steps using progress bars and graphs" refers to a system that records how far a user has progressed in their learning, visually illustrates that information, and suggests the next learning activity that should be undertaken.

[1540] "Means for providing detailed feedback using a generative AI model based on identified learning goals" refers to a mechanism that generates responses using a generative AI model according to the user's learning goals and provides specific, individualized feedback.

[1541] "Means for accepting interactive user input and using prompts to further identify learning objectives" refers to a mechanism that provides an interactive interface that responds to user input and uses appropriate questions and prompts to further explore the user's learning needs.

[1542] This invention is a system that provides users with personalized learning assistance by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[1543] This system is composed of a server, a terminal, and a user component. A specific embodiment will be described below.

[1544] 1. Hardware and Software Configuration

[1545] server

[1546] The server acts as a central control unit, processes user input, manages learning resources in conjunction with a database, and uses generative AI models to identify learning goals, design learning paths, and track progress.

[1547] Terminal

[1548] A terminal is a client device that receives user input and communicates with a server. Examples include PCs, tablets, and smartphones.

[1549] user

[1550] Users access the system using a terminal, set learning goals, and progress through their studies using suggested learning resources and learning paths.

[1551] Generative AI Models

[1552] Generative AI models analyze user input data and are used to set specific learning goals and design optimal learning paths. Specific examples of software include generative AI using natural language processing technology.

[1553] Database

[1554] A database is a system for storing learning resources, user progress data, set learning goals, etc. A specific example is a relational database management system (RDBMS).

[1555] 2. Example of a system and prompt

[1556] Specific examples of goal setting

[1557] If a user wants to learn data science, they would follow these steps:

[1558] user

[1559] A user goes to a terminal and types in, "I want to learn the basics of data science."

[1560] server

[1561] The server uses a generative AI model to analyze this input and identify the specific learning goal: "Data manipulation with Python," which is provided as feedback to the user.

[1562] Learning Resource Suggestions

[1563] Based on the identified learning objectives, the server searches its database for relevant learning resources and suggests a list such as:

[1564] 1. “Python Data Analysis Basics”

[1565] 2. “Advanced Python Data Science”

[1566] Terminal

[1567] The terminal visually displays these learning resources to the user.

[1568] user

[1569] Users can select "Python Data Analysis Basics" to view more information.

[1570] Specific learning path examples

[1571] Based on the selected learning resources, the server uses generative AI to design the following learning path:

[1572] Step 1: Learn Python Basics (online tutorial)

[1573] Step 2: Analysis using real data (practical exercise)

[1574] This learning path is visually displayed to the user through their device, allowing them to review and correct it.

[1575] Specific examples of progress management

[1576] As users complete each step along their learning path, they receive progress reports via their device.

[1577] server

[1578] The server stores progress information in a database and provides next steps and additional feedback through the generative AI, such as "The next step is to use the Python library pandas to analyze real data."

[1579] Terminal

[1580] The device visually displays progress with progress bars and graphs, allowing users to understand their current learning situation.

[1581] Prompt Sentence Examples

[1582] Examples of specific prompts that users may use to input information into the system include:

[1583] "I want to improve my programming skills"

[1584] "I want to improve my English speaking ability"

[1585] "I want to learn how to diet"

[1586] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[1587] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1588] Step 1:

[1589] User Login

[1590] Terminal

[1591] A user accesses the system using a terminal and the login screen is displayed. The user enters their username and password and presses the login button.

[1592] Input: Username and Password

[1593] server

[1594] The server checks the entered authentication information against the database, and if it matches, it generates the user's session information and returns it to the terminal. If it does not match, it returns an error message.

[1595] Data processing: Verification of authentication information and generation of session information

[1596] Output: Session information or error message

[1597] Step 2:

[1598] goal setting

[1599] Terminal

[1600] After logging in, users select "Goal Setting" from the main menu and an interactive interface is displayed.

[1601] Input: User's choice ("Goal setting")

[1602] user

[1603] Users follow interactive prompts to specify their learning goals, interests, and objectives, for example, "I want to learn the basics of data science."

[1604] Input: Learning goals or interests ("I want to learn the basics of data science")

[1605] server

[1606] The server uses a generative AI model to analyze this input and identify specific learning goals, such as "data manipulation with Python," which are then provided as feedback to the user.

[1607] Data Computation: Generative AI models analyze input data and identify learning goals

[1608] Output: Identified learning objectives (feedback)

[1609] Step 3:

[1610] Learning Resource Suggestions

[1611] server

[1612] Based on the identified learning objective, the server retrieves relevant learning resources from the database, for example, retrieve learning resources related to "Data Manipulation with Python."

[1613] Input: Identified learning objective ("Data manipulation with Python")

[1614] Data processing: Extracting appropriate learning resources through database search

[1615] Output: A list of related learning resources

[1616] Terminal

[1617] The terminal visually displays the list of learning resources sent from the server to the user.

[1618] Input: List of learning resources

[1619] user

[1620] Users can select the learning resource they are interested in from the displayed list to view more information, for example, "Python Data Analysis Basics."

[1621] Input: Selected learning resource ("Python Data Analysis Basics")

[1622] Output: Detailed information about the learning resource

[1623] Step 4:

[1624] Designing learning paths

[1625] server

[1626] Based on the selected learning resources, the server uses a generative AI model to design an optimal learning path, which consists of specific steps, such as "Step 1: Learn the basics of Python" and "Step 2: Analyze using real data."

[1627] Input: Selected learning resource ("Python Data Analysis Basics")

[1628] Data Computing: Designing Learning Paths with Generative AI Models

[1629] Output: Learning path

[1630] Terminal

[1631] It visually displays the learning path and allows users to review and correct it.

[1632] Input: Learning Path

[1633] user

[1634] The user accepts the proposed learning path or modifies it as needed. The user confirms the learning path.

[1635] Input: User confirmation and corrected learning path

[1636] Output: Confirmed learning path

[1637] Step 5:

[1638] Progress management

[1639] user

[1640] Users progress along a learning path and report their progress at the end of each step.

[1641] Input: Progress report

[1642] Terminal

[1643] The terminal sends progress reports to the server.

[1644] Input: Progress report

[1645] server

[1646] The server stores progress information in a database and provides next steps and additional feedback to the generative AI model, such as "The next step is to use the Python library pandas to analyze real data."

[1647] Data processing: storing progress information and generating feedback

[1648] Output: Next steps and additional feedback (feedback content)

[1649] Terminal

[1650] Progress is visually displayed in the form of progress bars and graphs, allowing users to understand their current learning situation.

[1651] Input: progress

[1652] Output: Visual progress indicator (progress bar and graph)

[1653] (Application example 1)

[1654] 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."

[1655] Conventional learning support systems have difficulty providing optimal learning paths for each user and managing their learning progress. Furthermore, they are limited to setting goals through text input and suggesting learning resources, resulting in a limited diversity in the user experience. Furthermore, the lack of statistical display of learning history and notification functions makes it difficult for users to efficiently grasp their learning progress.

[1656] 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.

[1657] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals;] [means for designing a learning path based on the user's learning goals;] [means for tracking the user's learning progress and suggesting next steps;] [means for accepting voice input;] [means for providing task notifications and reminders; and [means for displaying learning history statistics.] This makes it possible to provide learning support customized for each user, resulting in an efficient and diverse learning experience.

[1658] "Means for identifying learning goals from user input" refers to a function that accepts voice or text input, analyzes the content using a generative AI model, and specifically identifies the user's learning goals.

[1659] The "means for suggesting appropriate learning resources based on identified learning objectives" is a function that searches for relevant learning resources from a database based on the identified learning objectives, generates an optimal list, and suggests it to the user.

[1660] "Means for designing a learning path based on the user's learning goals" refers to a function in which the generative AI designs an optimal learning path based on the selected learning resources and the user's learning goals, and indicates the content and order of each step.

[1661] "Means for tracking the user's learning progress and suggesting next steps" refers to a function that stores the user's learning progress in a database and provides the next learning step or additional feedback depending on the situation.

[1662] The "means for accepting voice input" is a function for accepting voice input of learning goals and progress information from the user using a voice input device such as a microphone.

[1663] "Means for providing task notifications and reminders" refers to a function that provides notifications and reminders based on the learning goals and progress set by the user, encouraging them to complete a learning step or move on to the next task.

[1664] "Means for statistically displaying learning history" refers to a function that aggregates a user's learning history and displays it statistically using graphs and progress bars, allowing the user to visualize their own learning progress.

[1665] The present invention relates to a system for providing individually customized learning support to a user. Specific embodiments for carrying out the present invention are described below.

[1666] This system is configured using the following hardware and software.

[1667] Required Hardware

[1668] Smart devices (e.g. smartphones, tablets)

[1669] A microphone with voice input capabilities

[1670] Display Screen

[1671] Required software

[1672] Mobile application development frameworks (e.g., Flutter, React Native)

[1673] Database (e.g. Firebase Firestore)

[1674] Generative AI models (e.g., OpenAI GPT-4)

[1675] Serverless functions (e.g., Google Cloud Functions)

[1676] System Overview

[1677] User authentication and goal setting

[1678] Users log in to the application using their smart device. After logging in, they select "Goal Setting" from the main menu and enter their learning goals via voice or text input. This input is analyzed by a generative AI model (e.g., OpenAI GPT-4) to identify specific learning goals.

[1679] Example: A user says, "I want to learn the basics of JavaScript."

[1680] User: "I want to learn the basics of JavaScript."

[1681] AI: "So your goal is to learn the basics of JavaScript? Here are some suggested learning resources:

[1682] Learning Resource Suggestions

[1683] The server searches a database (e.g., Firebase Firestore) for relevant learning resources based on the identified learning objectives, generates an optimal list, and suggests it to the user. The user can select the learning resource of interest from the suggested list and check the detailed information.

[1684] Example: Learning resource suggestions

[1685] AI: "Which of these learning resources are you most interested in?"

[1686] User: Select "JavaScript Introduction Course"

[1687] Suggested learning paths

[1688] Based on the learning resources selected by the user, the server uses a generative AI model to design an optimal learning path. The learning path is structured into specific steps and visually displayed on the screen. The user can review the path and make any necessary adjustments.

[1689] Progress management

[1690] As the user completes each learning step, progress information is sent to the server and stored in a database. The server then provides the user with the next learning step or additional feedback, and displays progress using progress bars and graphs. Progress can also be reported via voice input.

[1691] Example: Progress management

[1692] The server statistically displays the user's learning history and helps promote learning by using task notification and reminder functions.

[1693] This makes it easier for users to visually grasp their learning progress and move on to the next step efficiently.

[1694] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1695] Step 1:

[1696] User authentication and goal setting

[1697] Input: A user logs into the application using a smart device and selects "Goal Setting" from the main menu.

[1698] Specific behavior:

[1699] 1. The device receives the user's login information and performs authentication.

[1700] 2. If authentication is successful, the "Goal Setting" screen will be displayed.

[1701] 3. The user inputs their learning goals by voice or text input.

[1702] 4. The device receives user input and sends it to the server.

[1703] Data processing and calculation:

[1704] The server passes the received voice or text input to a generative AI model (e.g., OpenAI GPT-4) for analysis.

[1705] output:

[1706] The generative AI model identifies specific learning goals as a result of the analysis and provides feedback to the user.

[1707] Step 2:

[1708] Learning Resource Suggestions

[1709] Input: User confirms identified learning objective.

[1710] Specific behavior:

[1711] 1. Based on the identified learning objectives, the server searches for relevant learning resources from a database (e.g., Firebase Firestore).

[1712] 2. Generate a list of learning resources based on the search results and send it to the terminal.

[1713] 3. The terminal displays a list of learning resources to the user.

[1714] Data processing and calculation:

[1715] The server queries the database for learning resources that match the learning objectives and lists the most suitable learning resources.

[1716] output:

[1717] Users can select the learning resource of interest from the displayed list and check the detailed information.

[1718] Step 3:

[1719] Suggested learning paths

[1720] Input: The learning resource selected by the user.

[1721] Specific behavior:

[1722] 1. The terminal sends information about the learning resource selected by the user to the server.

[1723] 2. The server uses a generative AI model to design an optimal learning path based on the selected learning resources and learning goals.

[1724] 3. Send the designed learning path to the device and display it visually.

[1725] 4. The user reviews the learning path and makes any necessary adjustments.

[1726] Data processing and calculation:

[1727] The server takes the selected learning resources and learning goals as input and performs data calculations to generate a learning path.

[1728] output:

[1729] The optimal learning path is presented to the user, who can confirm it and proceed to the next step.

[1730] Step 4:

[1731] Progress management

[1732] Input: The user progresses through the learning path.

[1733] Specific behavior:

[1734] 1. The device reports progress as the user completes each learning step.

[1735] 2. The device sends progress information to the server.

[1736] 3. The server stores the progress information in a database and suggests the next learning step.

[1737] 4. Use progress bars and graphs to show progress to the user.

[1738] Data processing and calculation:

[1739] The server receives the progress data, updates the learning progress, suggests next steps, and visualizes the progress.

[1740] output:

[1741] Users can visually see their progress and efficiently move to the next step.

[1742] 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.

[1743] This invention describes a self-learning platform that combines an emotion engine that recognizes users' emotions to improve users' learning experience. Specifically, it identifies learning goals from users' inputs, suggests appropriate learning resources, designs learning paths, manages progress, and also recognizes users' emotional states and reflects them in the learning process.

[1744] Program processing overview

[1745] This self-learning platform includes the following key features:

[1746] 1. Goal identification

[1747] 2. Learning Resource Suggestions

[1748] 3. Learning path suggestions

[1749] 4. Progress Management

[1750] 5. Emotion recognition and feedback regulation

[1751] 1. Goal identification

[1752] Terminal

[1753] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[1754] user

[1755] Enter your learning goals, interests, and objectives.

[1756] server

[1757] A generative AI model analyzes user input, and an emotion engine recognizes the user's emotional state, identifies learning goals, and provides feedback to the user based on this information.

[1758] 2. Learning Resource Suggestions

[1759] server

[1760] Based on the identified learning goals and emotional state, relevant learning resources are searched for in the database and an optimal list is generated.

[1761] Terminal

[1762] Presents a list of learning resources to the user.

[1763] user

[1764] Select the learning resource that interests you from the suggested list and view more information.

[1765] 3. Learning path suggestions

[1766] server

[1767] Based on the selected learning resources, the user's learning goals, and their emotional state, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[1768] Terminal

[1769] Visually display the learning path so users can review and correct it.

[1770] user

[1771] Accept the suggested learning path or modify it as needed.

[1772] 4. Progress Management

[1773] user

[1774] Follow the learning path and report your progress at the end of each step.

[1775] Terminal

[1776] Send progress reports to the server.

[1777] server

[1778] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[1779] Terminal

[1780] Provide users with progress visualization and suggested next steps.

[1781] 5. Emotion recognition and feedback regulation

[1782] server

[1783] The emotion engine periodically recognizes the user's emotional state while learning and generates feedback and encouraging messages to motivate the user.

[1784] Terminal

[1785] The emotion engine generates feedback and messages that are displayed to the user, and progress bars and graphs are used to provide support that takes into account the user's emotional state as they progress through the learning process.

[1786] Specific examples

[1787] Setting learning goals

[1788] If a user wants to improve their programming skills, they might do the following:

[1789] user

[1790] Type in "I want to improve my programming skills."

[1791] server

[1792] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript." At the same time, the emotion engine recognizes positive emotions from the user's text input and provides feedback to the user, such as "Your goal is great!"

[1793] Learning Resource Suggestions

[1794] server

[1795] Based on the identified goals and emotional state, it suggests the best learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[1796] Terminal

[1797] Present users with a list of learning resources and provide recommended comments that reflect the user's emotional state (e.g., "This course is beginner-friendly and fun to learn").

[1798] user

[1799] Select the "JavaScript Introduction Course."

[1800] Suggested learning paths

[1801] server

[1802] Based on the selected learning resources, design a learning path that:

[1803] Step 1: Complete the JavaScript Fundamentals course

[1804] Step 2: Advance to the intermediate course

[1805] Terminal

[1806] The learning path is visually displayed and confirmed by the user, and the emotion engine displays encouraging messages such as, "Once you've completed step 1, you'll be motivated to move on to the next step right away."

[1807] Progress management

[1808] user

[1809] At the end of each step, progress is reported to the platform.

[1810] Terminal

[1811] Sends the reported progress to the server.

[1812] server

[1813] It tracks progress and provides next steps and additional feedback, while an emotion engine periodically scans the user's emotional state and adjusts the feedback as needed.

[1814] Terminal

[1815] It displays progress using progress bars and graphs, letting users see the next steps they need to take, along with encouraging messages provided by an emotion engine.

[1816] The above is a specific embodiment of the present invention, which allows users to have an effective and efficient learning experience that takes into account their emotional state.

[1817] The processing flow will be explained below.

[1818] Step 1:

[1819] The server sends the HTML and CSS to the device to display the platform's login page.

[1820] Step 2:

[1821] The terminal displays a login form.

[1822] Step 3:

[1823] The user enters their username and password and clicks the Login button.

[1824] Step 4:

[1825] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[1826] Step 5:

[1827] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[1828] Step 6:

[1829] The user clicks the "Set Goal" button.

[1830] Step 7:

[1831] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[1832] Step 8:

[1833] The device displays an interactive interface with the generated AI model.

[1834] Step 9:

[1835] Users enter their learning goals, interests, and objectives.

[1836] Step 10:

[1837] The device sends the user's input to the server.

[1838] Step 11:

[1839] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[1840] Step 12:

[1841] The server uses an emotion engine to determine an emotional state from the user's input.

[1842] Step 13:

[1843] The server searches a database for relevant learning resources based on the identified learning goal and emotional state.

[1844] Step 14:

[1845] The server lists related learning resources and generates recommendation comments for the learning resources using an emotion engine.

[1846] Step 15:

[1847] The device displays a list of learning resources and recommended comments to the user.

[1848] Step 16:

[1849] The user selects the learning resource of interest from the suggested list and checks the details.

[1850] Step 17:

[1851] The terminal requests detailed information of the selected learning resource from the server.

[1852] Step 18:

[1853] The server sends the detailed information to the terminal.

[1854] Step 19:

[1855] The user reviews the learning resource and clicks the "Select" button.

[1856] Step 20:

[1857] Based on the learning resources selected by the server, the user's learning goals, and their emotional state, the generative AI designs the optimal learning path.

[1858] Step 20:

[1859] The server includes encouraging messages generated by the emotion engine at each step of the learning path.

[1860] Step 21:

[1861] The server sets up a learning path step by step and sends it to the terminal.

[1862] Step 22:

[1863] The device visually displays your learning path.

[1864] Step 23:

[1865] The user reviews the proposed learning path and clicks the "Accept" button.

[1866] Step 24:

[1867] Users progress through the learning process and report their progress back to the platform at the end of each step.

[1868] Step 25:

[1869] The terminal sends a progress report to the server.

[1870] Step 26:

[1871] The server stores the progress information in a database and updates the user's learning status.

[1872] Step 27:

[1873] The server generates next steps and additional feedback as needed, and the AI ​​suggests them, and generates encouraging messages using the emotion engine.

[1874] Step 28:

[1875] The device displays progress visualization and suggested next steps to the user.

[1876] Step 29:

[1877] The device displays encouraging messages generated by the emotion engine to the user, and provides support that takes into account the user's emotional state along with the learning progress using progress bars and graphs.

[1878] Step 30:

[1879] Users can see their progress using progress bars and graphs and see the next steps to take.

[1880] Example 2

[1881] 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."

[1882] While traditional self-learning systems can provide appropriate learning resources and set learning paths based on a user's learning goals, they do not take the user's emotional state into consideration. As a result, they provide insufficient support to increase user motivation and maximize learning outcomes. They also lack the ability to provide real-time feedback based on the user's progress. As a result, users often lose motivation to continue learning, hindering efficient learning.

[1883] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1884] In this invention, the server includes: [means for identifying learning goals from user input and recognizing the emotional state;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state; and [means for tracking the user's learning progress, suggesting next steps, and providing feedback based on the emotional state.] This enables learning support that takes the user's emotional state into consideration, providing an efficient and effective learning experience while increasing motivation.

[1885] "User" refers to an individual who intends to use the System to achieve their learning goals.

[1886] "Server" refers to the central processing unit that receives input from users and uses generative AI models and emotion engines to analyze data, make recommendations, and manage progress.

[1887] A "generative AI model" is a type of artificial intelligence that analyzes user input data and suggests appropriate learning goals and paths.

[1888] The "emotion engine" is a piece of software that recognizes the user's emotional state from their input data and provides feedback according to the learning process.

[1889] "Learning goals" refer to the specific learning content or skills that a user wants to achieve.

[1890] "Learning Resources" refers to the learning materials, content, courses, etc. provided to help users achieve their learning goals.

[1891] A "learning path" is a plan that includes specific learning steps and the order in which they must be undertaken to achieve a learning goal.

[1892] "Progress management" refers to the process of tracking a user's learning progress and providing next steps and feedback.

[1893] "Feedback" refers to encouraging messages and advice provided based on the user's learning progress and emotional state.

[1894] This invention provides a self-learning platform that combines an emotion engine that recognizes users' emotions to improve the user's learning experience. Specifically, the system identifies learning goals from users' input, suggests appropriate learning resources, designs learning paths, and manages progress, as well as recognizes the user's emotional state and reflects it in the learning process.

[1895] Hardware and software used

[1896] The system uses the following major hardware and software:

[1897] Server: The central processing unit that runs the generative AI models and emotion engine, and manages the database.

[1898] Terminal: A device (computer, smartphone, tablet, etc.) that provides the interface and sends user input to the server.

[1899] Generative AI model: An artificial intelligence model that analyzes user input data and suggests appropriate learning goals and paths.

[1900] Emotion engine: Software that recognizes the user's emotional state from input data and provides feedback according to the learning process.

[1901] Specific operation of the system

[1902] 1. Identify learning goals and recognize emotional states from user input

[1903] Terminal

[1904] The user logs into the platform using a terminal and opens an interactive interface for goal setting.

[1905] user

[1906] Users enter their learning goals, interests, and what they want to learn.

[1907] server

[1908] The server uses a generative AI model to analyze the user's input data and identify specific learning goals, while an emotion engine recognizes the user's emotional state from the text data.

[1909] 2. Suggest appropriate learning resources

[1910] server

[1911] The server searches the database for relevant learning resources based on the identified learning objectives and the recognized emotional state, and generates an optimal list.

[1912] Terminal

[1913] The terminal displays the generated list of learning resources to the user.

[1914] user

[1915] Users select learning resources of interest from the suggested list and view their detailed information.

[1916] 3. Design a learning path

[1917] server

[1918] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, the user's learning goals, and their emotional state. The learning path is composed of specific steps.

[1919] Terminal

[1920] The device visually displays the designed learning path for the user to review.

[1921] 4. Track learning progress, suggest next steps, and provide feedback based on emotional state

[1922] user

[1923] Users progress along a learning path and report their progress at the end of each step.

[1924] Terminal

[1925] The terminal sends progress reports from the user to the server.

[1926] server

[1927] The server stores progress information in a database, uses a generative AI model to suggest next steps and additional feedback, and uses an emotion engine to periodically recognize the user's emotional state and generate encouraging messages and advice based on that state.

[1928] Terminal

[1929] The device will then display generated feedback and encouragement messages to the user, allowing them to visually see their progress.

[1930] Examples of concrete examples and prompts

[1931] Specific examples

[1932] A user enters "I want to improve my programming skills," and the server parses this to identify "I want to learn the basics of JavaScript." The emotion engine recognizes a positive emotional state and provides feedback like, "Your goals are great!" The server then suggests learning resources, such as "Introductory JavaScript courses," and designs a learning path.

[1933] Prompt Sentence Examples

[1934] "Tell me about your learning goals."

[1935] Enter the skill you would like to improve.

[1936] As described above, the present invention is a system that provides an effective and efficient learning experience that takes into account the user's emotional state.

[1937] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1938] Step 1:

[1939] Login and User Authentication

[1940] Terminal

[1941] The terminal displays a login screen and prompts the user to enter their ID and password. The entered data is sent to the server when the login button is pressed.

[1942] user

[1943] The user enters their ID and password and clicks the login button.

[1944] server

[1945] The server verifies the received ID and password against the user data in the database. If authentication is successful, it sends the main menu to the terminal to receive the next input. If authentication fails, it generates an error message and sends it to the terminal.

[1946] Input: User ID and Password

[1947] Output: Authentication result (success / failure), main menu or error message sent

[1948] Specific operations: ID and password verification, determining next steps based on authentication results

[1949] Step 2:

[1950] Setting learning goals

[1951] Terminal

[1952] The device displays the main menu and prompts the user to click the "Goal Setting" button, and the interface displays prompts for interaction with the generative AI model.

[1953] user

[1954] Users click the "Set Goals" button, follow the prompts displayed, enter their learning goals, and then click the submit button.

[1955] server

[1956] The server receives the user's input data, analyzes it using a generative AI model, and uses an emotion engine to recognize the user's emotional state from the input data. It then generates feedback based on the analysis results and the user's emotional state and sends it to the device.

[1957] Input: User's learning goal (in text format)

[1958] Output: Specific learning goals, recognition of emotional states, generation and transmission of feedback

[1959] Specific actions: analyzing input data, recognizing emotions, generating feedback

[1960] Step 3:

[1961] Learning Resource Suggestions

[1962] server

[1963] The server searches for relevant learning resources from a database based on the identified learning objectives and the recognized emotional state, generates a list of optimal learning resources, and sends it to the terminal.

[1964] Terminal

[1965] The terminal displays a list of received learning resources to the user, including a short description of each learning resource and a recommendation comment that takes sentiment into account.

[1966] user

[1967] The user selects an item of interest from the displayed list of learning resources and clicks the Details button to view more information.

[1968] Input: Learning goals and emotional states

[1969] Output: List of learning resources, generate and display recommended comments

[1970] Specific operations: Searching and selecting related learning resources, generating data for display

[1971] Step 4:

[1972] Designing learning paths

[1973] server

[1974] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, learning goals, and emotional state. The learning path consists of multiple specific steps, and the server sends this information to the terminal.

[1975] Terminal

[1976] The device visually displays the designed learning path, showing the steps and their order, allowing the user to review and correct them.

[1977] user

[1978] The user reviews the proposed learning path, modifies it if necessary, and submits the modified learning path to the server.

[1979] Input: Learning objectives, emotional state, selected learning resources

[1980] Output: Learning path design, visual representation, and user correction data

[1981] Specific operations: generating a learning path, generating visual display data, and reflecting corrections

[1982] Step 5:

[1983] Learning progress management

[1984] user

[1985] Users progress through the learning path and report their progress at the end of each step by clicking a progress report button and entering the data into the device.

[1986] Terminal

[1987] The device receives the user's progress information and sends it to the server.

[1988] server

[1989] The server stores progress information in a database, updates the learning status, suggests next steps and additional feedback using a generative AI model, and uses an emotion engine to reassess the user's emotional state, generate feedback based on that, and send it to the device.

[1990] Input: Learning progress information

[1991] Output: Updates to progress tracking data, suggests next steps, and generates emotional feedback

[1992] Specific operations: saving and updating progress information, generating next steps, generating feedback

[1993] Step 6:

[1994] Emotion recognition and feedback regulation

[1995] server

[1996] The server's emotion engine periodically recognizes the user's emotional state during learning and uses a generative AI model to generate feedback and encouraging messages to motivate the user. The generated feedback is then sent to the device.

[1997] Terminal

[1998] The device displays generated feedback and encouragement messages to the user, and provides appropriate support based on their learning progress using progress bars and graphs.

[1999] Input: Periodic emotion data, learning progress

[2000] Output: Generate and display feedback and cheer messages

[2001] Specific behavior: Regular emotion recognition, generating and displaying appropriate feedback

[2002] As described above, this system is designed to provide feedback that takes into account the user's learning goals and emotional state, enabling them to learn efficiently while increasing their motivation.

[2003] (Application example 2)

[2004] 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."

[2005] While conventional self-learning platforms provide features for managing users' learning goals and progress, they do not adequately optimize the learning experience by taking into account the user's emotional state. As a result, users' motivation decreases and learning efficiency declines. Furthermore, the suggestion of learning resources and the design of learning paths do not reflect the user's emotional state, making it difficult to provide optimal support.

[2006] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2007] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state;] [means for tracking the user's learning progress and suggesting next steps and feedback; and [means for periodically recognizing the user's emotional state and generating feedback and messages to increase motivation.] This makes it possible to optimize the learning experience taking the user's emotional state into consideration.

[2008] "Means for identifying learning objectives from user input" refers to technology that analyzes the information entered by the user into the platform and identifies the user's learning targets and goals.

[2009] The "means for suggesting appropriate learning resources based on identified learning goals and emotional state" is a technology that analyzes the user's learning goals and emotional state, and searches a database for and suggests the most suitable learning resources.

[2010] The "means for designing a learning path based on a user's learning goals and emotional state" is a technology for systematically designing optimal learning steps according to a user's learning goals and emotional state.

[2011] "Means for tracking a user's learning progress and suggesting next steps and feedback" refers to technology that monitors a user's progress as they learn and provides them with the next steps and necessary feedback.

[2012] "Means for periodically recognizing a user's emotional state and generating feedback and messages to enhance motivation" refers to a technology that periodically analyzes a user's emotional state while they are learning, and generates and provides feedback such as encouragement or advice according to that state.

[2013] This invention provides a self-learning platform that combines an emotional engine to improve users' learning experience. Specifically, the system analyzes information entered by users, identifies learning goals, suggests appropriate learning resources, designs learning paths, manages progress, recognizes emotional states, and reflects feedback on the learning process.

[2014] First, the system that realizes this invention includes the following main software components: EmotionEngine, AIModule, and ResourceDatabase. Furthermore, it is assumed that these software components will be installed on a smartphone. Specific hardware that can be used is smartphones such as iPhones and Android devices.

[2015] The server uses the Emotion Engine to analyze the user's input and identify learning goals. The Emotion Engine also analyzes the user's emotional state and identifies states such as positive, negative, and neutral. The AI ​​Module then uses this information to search for appropriate learning resources from the Resource Database and suggest them to the user.

[2016] Furthermore, the server designs an optimal learning path based on the user's learning goals and emotional state. AIModule uses the user's input information and emotional analysis results to construct sequential learning steps. As the user completes each step, the device reports its progress to the server, which tracks it and provides next steps and feedback.

[2017] The emotion engine periodically recognizes the user's emotional state and generates motivational feedback and encouraging messages, which are displayed on the device along with progress bars and graphs to keep the user motivated to continue learning.

[2018] Examples:

[2019] If an employee wants to "improve their customer service skills," enter a prompt like this:

[2020] "I would like to improve my customer service skills. I have learned the basics, but I would like to gain practical application skills with specific examples. I have been feeling unsure about my customer service recently, so I would appreciate any advice on how I can improve."

[2021] The server analyzes this prompt, and the Emotion Engine recognizes the user's emotional state in a positive way. Based on this information, AIModule suggests learning resources from its Resource Database, such as a "Collection of Customer Service Scenarios to Hone Applied Skills." It then designs specific learning steps, such as "Applied Skills Training 1: Basic Scenarios" and "Applied Skills Training 2: Applied Scenarios," and provides these to the user.

[2022] After each step, the server updates the user's progress and generates next steps and encouraging messages as needed. The emotion engine also periodically scans the user's emotional state and provides feedback based on the results, maximizing the user's learning effectiveness.

[2023] In this way, the present invention is able to provide an effective and efficient learning experience while taking into account the user's emotional state.

[2024] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2025] Step 1:

[2026] The user logs into the platform using a terminal and opens an interactive input interface for goal setting.

[2027] Input: A prompt containing the user's learning goals and objectives

[2028] Data processing: The emotion engine analyzes the user's emotional state, and the generative AI model performs text analysis.

[2029] Output: Identified learning objectives and sentiment analysis results

[2030] Step 2:

[2031] The server searches and suggests appropriate learning resources from the ResourceDatabase based on the identified learning goals and emotional state.

[2032] Input: Identified learning objectives and sentiment analysis results

[2033] Data processing: Performing database queries to filter and rank relevant learning resources

[2034] Output: A list of recommended learning resources

[2035] Step 3:

[2036] The server displays recommended learning resources on the user's terminal, and the user selects the resource of interest from this list.

[2037] Input: A list of recommended learning resources

[2038] Data processing: Obtain detailed information about learning resources and generate recommended comments based on emotional states

[2039] Output: Learning resources and recommended comments displayed on the terminal

[2040] Step 4:

[2041] Based on the selected learning resources, the server designs an optimal learning path taking into account the user's learning goals and emotional state.

[2042] Input: Selected learning resources, learning objectives, sentiment analysis results

[2043] Data processing: Generative AI models design and sequence optimal learning steps

[2044] Output: Learning path (list of specific steps)

[2045] Step 5:

[2046] The device visually displays the designed learning path, allowing the user to check and correct it.

[2047] Input: Learning Path

[2048] Data processing: Generate visual learning paths and display them in the user interface

[2049] Output: A learning path display that the user can review and modify

[2050] Step 6:

[2051] The user progresses through the learning path and their progress is reported to the device at the end of each step.

[2052] Input: User progress report

[2053] Data processing: Progress data is sent to the server and learning status is saved in the database

[2054] Output: Updated progress information

[2055] Step 7:

[2056] The server generates the next step and additional feedback based on the progress information and sends it to the device.

[2057] Input: Updated progress information

[2058] Data processing: Generative AI models determine next steps and feedback

[2059] Output: Next steps and feedback displayed on the terminal

[2060] Step 8:

[2061] The emotion engine periodically recognizes the user's emotional state and provides feedback information to the server.

[2062] Input: The user's current emotional state

[2063] Data processing: Emotion recognition algorithms analyze emotional data

[2064] Output: Feedback information reflecting emotional state

[2065] Step 9:

[2066] The device displays supportive messages and feedback generated by the emotion engine to the user.

[2067] Input: Feedback information reflecting emotional state

[2068] Data processing: Determine the display format of the feedback

[2069] Output: A cheering message or feedback that is displayed to the user

[2070] 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.

[2071] 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.

[2072] 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.

[2073] [Fourth embodiment]

[2074] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2075] 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.

[2076] 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).

[2077] 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.

[2078] 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.

[2079] 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).

[2080] 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. 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.

[2081] 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.

[2082] 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.

[2083] 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.

[2084] 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.

[2085] 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.

[2086] 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."

[2087] This invention describes a system that provides personalized learning assistance to users by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[2088] Program processing overview

[2089] This self-learning platform includes the following key features:

[2090] 1. Goal identification

[2091] 2. Learning Resource Suggestions

[2092] 3. Learning path suggestions

[2093] 4. Progress Management

[2094] 1. Goal identification

[2095] Terminal

[2096] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[2097] user

[2098] Enter your learning goals, interests, and objectives.

[2099] server

[2100] A generative AI model analyzes user input to identify learning objectives and uses this information to provide feedback to the user.

[2101] 2. Learning Resource Suggestions

[2102] server

[2103] Based on the identified learning objectives, the database is searched for relevant learning resources and an optimal list is generated.

[2104] Terminal

[2105] Presents a list of learning resources to the user.

[2106] user

[2107] Select the learning resource that interests you from the suggested list and view more information.

[2108] 3. Learning path suggestions

[2109] server

[2110] Based on the selected learning resources and the user's learning goals, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[2111] Terminal

[2112] Visually display the learning path so users can review and correct it.

[2113] user

[2114] Accept the suggested learning path or modify it as needed.

[2115] 4. Progress Management

[2116] user

[2117] Follow the learning path and report your progress at the end of each step.

[2118] Terminal

[2119] Send progress reports to the server.

[2120] server

[2121] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[2122] Terminal

[2123] Provide users with progress visualizations and suggested next steps, such as progress bars and graphs, to help them understand their current learning situation.

[2124] Specific examples

[2125] Setting learning goals

[2126] If a user wants to learn programming, they might do the following:

[2127] user

[2128] Type in "I want to improve my programming skills."

[2129] server

[2130] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript." The platform then verifies this goal and provides feedback to the user.

[2131] Learning Resource Suggestions

[2132] server

[2133] Based on the identified goals, we suggest appropriate learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[2134] Terminal

[2135] Presents a list of learning resources to the user.

[2136] user

[2137] Select the "JavaScript Introduction Course."

[2138] Suggested learning paths

[2139] server

[2140] Based on the selected learning resources, design a learning path that:

[2141] Step 1: Complete the JavaScript Fundamentals course

[2142] Step 2: Advance to the intermediate course

[2143] Terminal

[2144] Visually display and follow the learning path for users.

[2145] user

[2146] Embrace the learning path.

[2147] Progress management

[2148] user

[2149] At the end of each step, progress is reported to the platform.

[2150] Terminal

[2151] Sends the reported progress to the server.

[2152] server

[2153] Track progress and provide next steps or additional feedback.

[2154] Terminal

[2155] Use progress bars and graphs to show progress and let users see the next step.

[2156] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[2157] The processing flow will be explained below.

[2158] Step 1:

[2159] The server sends the HTML and CSS to the device to display the platform's login page.

[2160] Step 2:

[2161] The terminal displays a login form.

[2162] Step 3:

[2163] The user enters their username and password and clicks the Login button.

[2164] Step 4:

[2165] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[2166] Step 5:

[2167] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[2168] Step 6:

[2169] The user clicks the "Set Goal" button.

[2170] Step 7:

[2171] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[2172] Step 8:

[2173] The device displays an interactive interface with the generated AI model.

[2174] Step 9:

[2175] Users enter their learning goals, interests, and objectives.

[2176] Step 10:

[2177] The device sends the user's input to the server.

[2178] Step 11:

[2179] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[2180] Step 12:

[2181] The server searches the database for relevant learning resources based on the identified learning objectives.

[2182] Step 13:

[2183] The server lists the most relevant learning resources from the search results.

[2184] Step 14:

[2185] The terminal displays a list of learning resources to the user.

[2186] Step 15:

[2187] The user selects the learning resource of interest from the suggested list and checks the details.

[2188] Step 16:

[2189] The terminal requests detailed information of the selected learning resource from the server.

[2190] Step 17:

[2191] The server sends the detailed information to the terminal.

[2192] Step 18:

[2193] The user reviews the learning resource and clicks the "Select" button.

[2194] Step 19:

[2195] Based on the server's selected learning resources and the user's learning goals, the generative AI designs the optimal learning path.

[2196] Step 20:

[2197] The server sets up a learning path step by step and sends it to the terminal.

[2198] Step 21:

[2199] The device visually displays your learning path.

[2200] Step 22:

[2201] The user reviews the proposed learning path and clicks the "Accept" button.

[2202] Step 23:

[2203] Users progress through the learning process and report their progress back to the platform at the end of each step.

[2204] Step 24:

[2205] The terminal sends a progress report to the server.

[2206] Step 25:

[2207] The server stores the progress information in a database and updates the user's learning status.

[2208] Step 26:

[2209] The server generates AI suggestions for next steps and additional feedback as needed.

[2210] Step 27:

[2211] The device displays progress visualization and suggested next steps to the user.

[2212] Step 28:

[2213] Users can see their progress using progress bars and graphs and see the next steps to take.

[2214] Example 1

[2215] 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."

[2216] Existing self-learning support systems often struggle to fully meet the individual needs of users. They also lack the support needed to help users clearly define their learning goals, find appropriate learning resources, and progress efficiently. This can lead to poor learning efficiency and the inability to find the optimal learning path.

[2217] 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.

[2218] In this invention, the server includes: [means for a user to log in using a terminal and verify authentication information; [means for identifying learning goals from the user's input and analyzing it using a generative AI model; [means for suggesting related learning resources from a database based on the identified learning goals;] [means for generating an optimal learning path based on the suggested learning resources and visually displaying it;] [means for tracking the user's learning progress and suggesting next steps using a progress bar or graph;] [means for providing detailed feedback using a generative AI model based on the identified learning goals; and [means for accepting interactive input from the user and specifying learning goals in detail using prompt sentences. This enables users to clearly set their learning goals, quickly find appropriate learning resources, and efficiently progress along the optimal learning path.

[2219] "Means for users to log in using a terminal and verify authentication information" refers to a mechanism by which users access the system using an electronic device and are authenticated based on the entered username and password.

[2220] "Means for identifying learning goals from user input and analyzing them using a generative AI model" refers to a mechanism that collects the goals and requirements that users input into the system, analyzes them using a generative AI model, and determines specific learning goals.

[2221] "Means for suggesting relevant learning resources from a database based on identified learning goals" refers to a mechanism that searches the database within the system according to the user's learning goals, and selects and presents relevant educational materials and courses.

[2222] "Means for generating and visually displaying an optimal learning path based on proposed learning resources" refers to a mechanism that takes into account a set of selected learning materials, designs an efficient sequence of learning steps based on that, and displays it on the screen in a format that is easily understandable to the user.

[2223] "Means to track a user's learning progress and suggest next steps using progress bars and graphs" refers to a system that records how far a user has progressed in their learning, visually illustrates that information, and suggests the next learning activity that should be undertaken.

[2224] "Means for providing detailed feedback using a generative AI model based on identified learning goals" refers to a mechanism that generates responses using a generative AI model according to the user's learning goals and provides specific, individualized feedback.

[2225] "Means for accepting interactive user input and using prompts to further identify learning objectives" refers to a mechanism that provides an interactive interface that responds to user input and uses appropriate questions and prompts to further explore the user's learning needs.

[2226] This invention is a system that provides users with personalized learning assistance by utilizing a generative AI model to identify learning goals based on user input, suggest appropriate learning resources, design learning paths, and monitor progress.

[2227] This system is composed of a server, a terminal, and a user component. A specific embodiment will be described below.

[2228] 1. Hardware and Software Configuration

[2229] server

[2230] The server acts as a central control unit, processes user input, manages learning resources in conjunction with a database, and uses generative AI models to identify learning goals, design learning paths, and track progress.

[2231] Terminal

[2232] A terminal is a client device that receives user input and communicates with a server. Examples include PCs, tablets, and smartphones.

[2233] user

[2234] Users access the system using a terminal, set learning goals, and progress through their studies using suggested learning resources and learning paths.

[2235] Generative AI Models

[2236] Generative AI models analyze user input data and are used to set specific learning goals and design optimal learning paths. Specific examples of software include generative AI using natural language processing technology.

[2237] Database

[2238] A database is a system for storing learning resources, user progress data, set learning goals, etc. A specific example is a relational database management system (RDBMS).

[2239] 2. Example of a system and prompt

[2240] Specific examples of goal setting

[2241] If a user wants to learn data science, they would follow these steps:

[2242] user

[2243] A user goes to a terminal and types in, "I want to learn the basics of data science."

[2244] server

[2245] The server uses a generative AI model to analyze this input and identify the specific learning goal: "Data manipulation with Python," which is provided as feedback to the user.

[2246] Learning Resource Suggestions

[2247] Based on the identified learning objectives, the server searches its database for relevant learning resources and suggests a list such as:

[2248] 1. “Python Data Analysis Basics”

[2249] 2. “Advanced Python Data Science”

[2250] Terminal

[2251] The terminal visually displays these learning resources to the user.

[2252] user

[2253] Users can select "Python Data Analysis Basics" to view more information.

[2254] Specific learning path examples

[2255] Based on the selected learning resources, the server uses generative AI to design the following learning path:

[2256] Step 1: Learn Python Basics (online tutorial)

[2257] Step 2: Analysis using real data (practical exercise)

[2258] This learning path is visually displayed to the user through their device, allowing them to review and correct it.

[2259] Specific examples of progress management

[2260] As users complete each step along their learning path, they receive progress reports via their device.

[2261] server

[2262] The server stores progress information in a database and provides next steps and additional feedback through the generative AI, such as "The next step is to use the Python library pandas to analyze real data."

[2263] Terminal

[2264] The device visually displays progress with progress bars and graphs, allowing users to understand their current learning situation.

[2265] Prompt Sentence Examples

[2266] Examples of specific prompts that users may use to input information into the system include:

[2267] "I want to improve my programming skills"

[2268] "I want to improve my English speaking ability"

[2269] "I want to learn how to diet"

[2270] The above is a specific embodiment of the present invention, which allows users to achieve their learning goals effectively and efficiently.

[2271] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2272] Step 1:

[2273] User Login

[2274] Terminal

[2275] A user accesses the system using a terminal and the login screen is displayed. The user enters their username and password and presses the login button.

[2276] Input: Username and Password

[2277] server

[2278] The server checks the entered authentication information against the database, and if it matches, it generates the user's session information and returns it to the terminal. If it does not match, it returns an error message.

[2279] Data processing: Verification of authentication information and generation of session information

[2280] Output: Session information or error message

[2281] Step 2:

[2282] goal setting

[2283] Terminal

[2284] After logging in, users select "Goal Setting" from the main menu and an interactive interface is displayed.

[2285] Input: User's choice ("Goal setting")

[2286] user

[2287] Users follow interactive prompts to specify their learning goals, interests, and objectives, for example, "I want to learn the basics of data science."

[2288] Input: Learning goals or interests ("I want to learn the basics of data science")

[2289] server

[2290] The server uses a generative AI model to analyze this input and identify specific learning goals, such as "data manipulation with Python," which are then provided as feedback to the user.

[2291] Data Computation: Generative AI models analyze input data and identify learning goals

[2292] Output: Identified learning objectives (feedback)

[2293] Step 3:

[2294] Learning Resource Suggestions

[2295] server

[2296] Based on the identified learning objective, the server retrieves relevant learning resources from the database, for example, retrieve learning resources related to "Data Manipulation with Python."

[2297] Input: Identified learning objective ("Data manipulation with Python")

[2298] Data processing: Extracting appropriate learning resources through database search

[2299] Output: A list of related learning resources

[2300] Terminal

[2301] The terminal visually displays the list of learning resources sent from the server to the user.

[2302] Input: List of learning resources

[2303] user

[2304] Users can select the learning resource they are interested in from the displayed list to view more information, for example, "Python Data Analysis Basics."

[2305] Input: Selected learning resource ("Python Data Analysis Basics")

[2306] Output: Detailed information about the learning resource

[2307] Step 4:

[2308] Designing learning paths

[2309] server

[2310] Based on the selected learning resources, the server uses a generative AI model to design an optimal learning path, which consists of specific steps, such as "Step 1: Learn the basics of Python" and "Step 2: Analyze using real data."

[2311] Input: Selected learning resource ("Python Data Analysis Basics")

[2312] Data Computing: Designing Learning Paths with Generative AI Models

[2313] Output: Learning path

[2314] Terminal

[2315] It visually displays the learning path and allows users to review and correct it.

[2316] Input: Learning Path

[2317] user

[2318] The user accepts the proposed learning path or modifies it as needed. The user confirms the learning path.

[2319] Input: User confirmation and corrected learning path

[2320] Output: Confirmed learning path

[2321] Step 5:

[2322] Progress management

[2323] user

[2324] Users progress along a learning path and report their progress at the end of each step.

[2325] Input: Progress report

[2326] Terminal

[2327] The terminal sends progress reports to the server.

[2328] Input: Progress report

[2329] server

[2330] The server stores progress information in a database and provides next steps and additional feedback to the generative AI model, such as "The next step is to use the Python library pandas to analyze real data."

[2331] Data processing: storing progress information and generating feedback

[2332] Output: Next steps and additional feedback (feedback content)

[2333] Terminal

[2334] Progress is visually displayed in the form of progress bars and graphs, allowing users to understand their current learning situation.

[2335] Input: progress

[2336] Output: Visual progress indicator (progress bar and graph)

[2337] (Application example 1)

[2338] 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."

[2339] Conventional learning support systems have difficulty providing optimal learning paths for each user and managing their learning progress. Furthermore, they are limited to setting goals through text input and suggesting learning resources, resulting in a limited diversity in the user experience. Furthermore, the lack of statistical display of learning history and notification functions makes it difficult for users to efficiently grasp their learning progress.

[2340] 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.

[2341] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals;] [means for designing a learning path based on the user's learning goals;] [means for tracking the user's learning progress and suggesting next steps;] [means for accepting voice input;] [means for providing task notifications and reminders; and [means for displaying learning history statistics.] This makes it possible to provide learning support customized for each user, resulting in an efficient and diverse learning experience.

[2342] "Means for identifying learning goals from user input" refers to a function that accepts voice or text input, analyzes the content using a generative AI model, and specifically identifies the user's learning goals.

[2343] The "means for suggesting appropriate learning resources based on identified learning objectives" is a function that searches for relevant learning resources from a database based on the identified learning objectives, generates an optimal list, and suggests it to the user.

[2344] "Means for designing a learning path based on the user's learning goals" refers to a function in which the generative AI designs an optimal learning path based on the selected learning resources and the user's learning goals, and indicates the content and order of each step.

[2345] "Means for tracking the user's learning progress and suggesting next steps" refers to a function that stores the user's learning progress in a database and provides the next learning step or additional feedback depending on the situation.

[2346] The "means for accepting voice input" is a function for accepting voice input of learning goals and progress information from the user using a voice input device such as a microphone.

[2347] "Means for providing task notifications and reminders" refers to a function that provides notifications and reminders based on the learning goals and progress set by the user, encouraging them to complete a learning step or move on to the next task.

[2348] "Means for statistically displaying learning history" refers to a function that aggregates a user's learning history and displays it statistically using graphs and progress bars, allowing the user to visualize their own learning progress.

[2349] The present invention relates to a system for providing individually customized learning support to a user. Specific embodiments for carrying out the present invention are described below.

[2350] This system is configured using the following hardware and software.

[2351] Required Hardware

[2352] Smart devices (e.g. smartphones, tablets)

[2353] A microphone with voice input capabilities

[2354] Display Screen

[2355] Required software

[2356] Mobile application development frameworks (e.g., Flutter, React Native)

[2357] Database (e.g. Firebase Firestore)

[2358] Generative AI models (e.g., OpenAI GPT-4)

[2359] Serverless functions (e.g., Google Cloud Functions)

[2360] System Overview

[2361] User authentication and goal setting

[2362] Users log in to the application using their smart device. After logging in, they select "Goal Setting" from the main menu and enter their learning goals via voice or text input. This input is analyzed by a generative AI model (e.g., OpenAI GPT-4) to identify specific learning goals.

[2363] Example: A user says, "I want to learn the basics of JavaScript."

[2364] User: "I want to learn the basics of JavaScript."

[2365] AI: "So your goal is to learn the basics of JavaScript? Here are some suggested learning resources:

[2366] Learning Resource Suggestions

[2367] The server searches a database (e.g., Firebase Firestore) for relevant learning resources based on the identified learning objectives, generates an optimal list, and suggests it to the user. The user can select the learning resource of interest from the suggested list and check the detailed information.

[2368] Example: Learning resource suggestions

[2369] AI: "Which of these learning resources are you most interested in?"

[2370] User: Select "JavaScript Introduction Course"

[2371] Suggested learning paths

[2372] Based on the learning resources selected by the user, the server uses a generative AI model to design an optimal learning path. The learning path is structured into specific steps and visually displayed on the screen. The user can review the path and make any necessary adjustments.

[2373] Progress management

[2374] As the user completes each learning step, progress information is sent to the server and stored in a database. The server then provides the user with the next learning step or additional feedback, and displays progress using progress bars and graphs. Progress can also be reported via voice input.

[2375] Example: Progress management

[2376] The server statistically displays the user's learning history and helps promote learning by using task notification and reminder functions.

[2377] This makes it easier for users to visually grasp their learning progress and move on to the next step efficiently.

[2378] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2379] Step 1:

[2380] User authentication and goal setting

[2381] Input: A user logs into the application using a smart device and selects "Goal Setting" from the main menu.

[2382] Specific behavior:

[2383] 1. The device receives the user's login information and performs authentication.

[2384] 2. If authentication is successful, the "Goal Setting" screen will be displayed.

[2385] 3. The user inputs their learning goals by voice or text input.

[2386] 4. The device receives user input and sends it to the server.

[2387] Data processing and calculation:

[2388] The server passes the received voice or text input to a generative AI model (e.g., OpenAI GPT-4) for analysis.

[2389] output:

[2390] The generative AI model identifies specific learning goals as a result of the analysis and provides feedback to the user.

[2391] Step 2:

[2392] Learning Resource Suggestions

[2393] Input: User confirms identified learning objective.

[2394] Specific behavior:

[2395] 1. Based on the identified learning objectives, the server searches for relevant learning resources from a database (e.g., Firebase Firestore).

[2396] 2. Generate a list of learning resources based on the search results and send it to the terminal.

[2397] 3. The terminal displays a list of learning resources to the user.

[2398] Data processing and calculation:

[2399] The server queries the database for learning resources that match the learning objectives and lists the most suitable learning resources.

[2400] output:

[2401] Users can select the learning resource of interest from the displayed list and check the detailed information.

[2402] Step 3:

[2403] Suggested learning paths

[2404] Input: The learning resource selected by the user.

[2405] Specific behavior:

[2406] 1. The terminal sends information about the learning resource selected by the user to the server.

[2407] 2. The server uses a generative AI model to design an optimal learning path based on the selected learning resources and learning goals.

[2408] 3. Send the designed learning path to the device and display it visually.

[2409] 4. The user reviews the learning path and makes any necessary adjustments.

[2410] Data processing and calculation:

[2411] The server takes the selected learning resources and learning goals as input and performs data calculations to generate a learning path.

[2412] output:

[2413] The optimal learning path is presented to the user, who can confirm it and proceed to the next step.

[2414] Step 4:

[2415] Progress management

[2416] Input: The user progresses through the learning path.

[2417] Specific behavior:

[2418] 1. The device reports progress as the user completes each learning step.

[2419] 2. The device sends progress information to the server.

[2420] 3. The server stores the progress information in a database and suggests the next learning step.

[2421] 4. Use progress bars and graphs to show progress to the user.

[2422] Data processing and calculation:

[2423] The server receives the progress data, updates the learning progress, suggests next steps, and visualizes the progress.

[2424] output:

[2425] Users can visually see their progress and efficiently move to the next step.

[2426] 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.

[2427] This invention describes a self-learning platform that combines an emotion engine that recognizes users' emotions to improve users' learning experience. Specifically, it identifies learning goals from users' inputs, suggests appropriate learning resources, designs learning paths, manages progress, and also recognizes users' emotional states and reflects them in the learning process.

[2428] Program processing overview

[2429] This self-learning platform includes the following key features:

[2430] 1. Goal identification

[2431] 2. Learning Resource Suggestions

[2432] 3. Learning path suggestions

[2433] 4. Progress Management

[2434] 5. Emotion recognition and feedback regulation

[2435] 1. Goal identification

[2436] Terminal

[2437] A user logs into the platform using a device and selects "Goal Setting" from the main menu, which displays an interactive interface with the generative AI model.

[2438] user

[2439] Enter your learning goals, interests, and objectives.

[2440] server

[2441] A generative AI model analyzes user input, and an emotion engine recognizes the user's emotional state, identifies learning goals, and provides feedback to the user based on this information.

[2442] 2. Learning Resource Suggestions

[2443] server

[2444] Based on the identified learning goals and emotional state, relevant learning resources are searched for in the database and an optimal list is generated.

[2445] Terminal

[2446] Presents a list of learning resources to the user.

[2447] user

[2448] Select the learning resource that interests you from the suggested list and view more information.

[2449] 3. Learning path suggestions

[2450] server

[2451] Based on the selected learning resources, the user's learning goals, and their emotional state, generative AI designs an optimal learning path, which consists of specific steps and indicates the order and content of each step.

[2452] Terminal

[2453] Visually display the learning path so users can review and correct it.

[2454] user

[2455] Accept the suggested learning path or modify it as needed.

[2456] 4. Progress Management

[2457] user

[2458] Follow the learning path and report your progress at the end of each step.

[2459] Terminal

[2460] Send progress reports to the server.

[2461] server

[2462] Progress information is stored in a database, updating the user's learning status. The AI ​​will suggest next steps and additional feedback as needed.

[2463] Terminal

[2464] Provide users with progress visualization and suggested next steps.

[2465] 5. Emotion recognition and feedback regulation

[2466] server

[2467] The emotion engine periodically recognizes the user's emotional state while learning and generates feedback and encouraging messages to motivate the user.

[2468] Terminal

[2469] The emotion engine generates feedback and messages that are displayed to the user, and progress bars and graphs are used to provide support that takes into account the user's emotional state as they progress through the learning process.

[2470] Specific examples

[2471] Setting learning goals

[2472] If a user wants to improve their programming skills, they might do the following:

[2473] user

[2474] Type in "I want to improve my programming skills."

[2475] server

[2476] The generative AI identifies a specific learning goal, such as "I want to learn the basics of JavaScript." At the same time, the emotion engine recognizes positive emotions from the user's text input and provides feedback to the user, such as "Your goal is great!"

[2477] Learning Resource Suggestions

[2478] server

[2479] Based on the identified goals and emotional state, it suggests the best learning resources, such as "JavaScript introductory courses" or "beginner tutorials."

[2480] Terminal

[2481] Present users with a list of learning resources and provide recommended comments that reflect the user's emotional state (e.g., "This course is beginner-friendly and fun to learn").

[2482] user

[2483] Select the "JavaScript Introduction Course."

[2484] Suggested learning paths

[2485] server

[2486] Based on the selected learning resources, design a learning path that:

[2487] Step 1: Complete the JavaScript Fundamentals course

[2488] Step 2: Advance to the intermediate course

[2489] Terminal

[2490] The learning path is visually displayed and confirmed by the user, and the emotion engine displays encouraging messages such as, "Once you've completed step 1, you'll be motivated to move on to the next step right away."

[2491] Progress management

[2492] user

[2493] At the end of each step, progress is reported to the platform.

[2494] Terminal

[2495] Sends the reported progress to the server.

[2496] server

[2497] It tracks progress and provides next steps and additional feedback, while an emotion engine periodically scans the user's emotional state and adjusts the feedback as needed.

[2498] Terminal

[2499] It displays progress using progress bars and graphs, letting users see the next steps they need to take, along with encouraging messages provided by an emotion engine.

[2500] The above is a specific embodiment of the present invention, which allows users to have an effective and efficient learning experience that takes into account their emotional state.

[2501] The processing flow will be explained below.

[2502] Step 1:

[2503] The server sends the HTML and CSS to the device to display the platform's login page.

[2504] Step 2:

[2505] The terminal displays a login form.

[2506] Step 3:

[2507] The user enters their username and password and clicks the Login button.

[2508] Step 4:

[2509] The server checks the user's credentials against its database and, if successful, redirects the user to the home screen.

[2510] Step 5:

[2511] The device displays an interface for selecting "Goal Setting" from the home screen menu.

[2512] Step 6:

[2513] The user clicks the "Set Goal" button.

[2514] Step 7:

[2515] The server sends HTML and JavaScript for the "Goal Setting" screen to the device.

[2516] Step 8:

[2517] The device displays an interactive interface with the generated AI model.

[2518] Step 9:

[2519] Users enter their learning goals, interests, and objectives.

[2520] Step 10:

[2521] The device sends the user's input to the server.

[2522] Step 11:

[2523] The server uses a generative AI model to analyze the user's input and identify learning objectives.

[2524] Step 12:

[2525] The server uses an emotion engine to determine an emotional state from the user's input.

[2526] Step 13:

[2527] The server searches a database for relevant learning resources based on the identified learning goal and emotional state.

[2528] Step 14:

[2529] The server lists related learning resources and generates recommendation comments for the learning resources using an emotion engine.

[2530] Step 15:

[2531] The device displays a list of learning resources and recommended comments to the user.

[2532] Step 16:

[2533] The user selects the learning resource of interest from the suggested list and checks the details.

[2534] Step 17:

[2535] The terminal requests detailed information of the selected learning resource from the server.

[2536] Step 18:

[2537] The server sends the detailed information to the terminal.

[2538] Step 19:

[2539] The user reviews the learning resource and clicks the "Select" button.

[2540] Step 20:

[2541] Based on the learning resources selected by the server, the user's learning goals, and their emotional state, the generative AI designs the optimal learning path.

[2542] Step 20:

[2543] The server includes encouraging messages generated by the emotion engine at each step of the learning path.

[2544] Step 21:

[2545] The server sets up a learning path step by step and sends it to the terminal.

[2546] Step 22:

[2547] The device visually displays your learning path.

[2548] Step 23:

[2549] The user reviews the proposed learning path and clicks the "Accept" button.

[2550] Step 24:

[2551] Users progress through the learning process and report their progress back to the platform at the end of each step.

[2552] Step 25:

[2553] The terminal sends a progress report to the server.

[2554] Step 26:

[2555] The server stores the progress information in a database and updates the user's learning status.

[2556] Step 27:

[2557] The server generates next steps and additional feedback as needed, and the AI ​​suggests them, and generates encouraging messages using the emotion engine.

[2558] Step 28:

[2559] The device displays progress visualization and suggested next steps to the user.

[2560] Step 29:

[2561] The device displays encouraging messages generated by the emotion engine to the user, and provides support that takes into account the user's emotional state along with the learning progress using progress bars and graphs.

[2562] Step 30:

[2563] Users can see their progress using progress bars and graphs and see the next steps to take.

[2564] Example 2

[2565] 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."

[2566] While traditional self-learning systems can provide appropriate learning resources and set learning paths based on a user's learning goals, they do not take the user's emotional state into consideration. As a result, they provide insufficient support to increase user motivation and maximize learning outcomes. They also lack the ability to provide real-time feedback based on the user's progress. As a result, users often lose motivation to continue learning, hindering efficient learning.

[2567] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2568] In this invention, the server includes: [means for identifying learning goals from user input and recognizing the emotional state;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state; and [means for tracking the user's learning progress, suggesting next steps, and providing feedback based on the emotional state.] This enables learning support that takes the user's emotional state into consideration, providing an efficient and effective learning experience while increasing motivation.

[2569] "User" refers to an individual who intends to use the System to achieve their learning goals.

[2570] "Server" refers to the central processing unit that receives input from users and uses generative AI models and emotion engines to analyze data, make recommendations, and manage progress.

[2571] A "generative AI model" is a type of artificial intelligence that analyzes user input data and suggests appropriate learning goals and paths.

[2572] The "emotion engine" is a piece of software that recognizes the user's emotional state from their input data and provides feedback according to the learning process.

[2573] "Learning goals" refer to the specific learning content or skills that a user wants to achieve.

[2574] "Learning Resources" refers to the learning materials, content, courses, etc. provided to help users achieve their learning goals.

[2575] A "learning path" is a plan that includes specific learning steps and the order in which they must be undertaken to achieve a learning goal.

[2576] "Progress management" refers to the process of tracking a user's learning progress and providing next steps and feedback.

[2577] "Feedback" refers to encouraging messages and advice provided based on the user's learning progress and emotional state.

[2578] This invention provides a self-learning platform that combines an emotion engine that recognizes users' emotions to improve the user's learning experience. Specifically, the system identifies learning goals from users' input, suggests appropriate learning resources, designs learning paths, and manages progress, as well as recognizes the user's emotional state and reflects it in the learning process.

[2579] Hardware and software used

[2580] The system uses the following major hardware and software:

[2581] Server: The central processing unit that runs the generative AI models and emotion engine, and manages the database.

[2582] Terminal: A device (computer, smartphone, tablet, etc.) that provides the interface and sends user input to the server.

[2583] Generative AI model: An artificial intelligence model that analyzes user input data and suggests appropriate learning goals and paths.

[2584] Emotion engine: Software that recognizes the user's emotional state from input data and provides feedback according to the learning process.

[2585] Specific operation of the system

[2586] 1. Identify learning goals and recognize emotional states from user input

[2587] Terminal

[2588] The user logs into the platform using a terminal and opens an interactive interface for goal setting.

[2589] user

[2590] Users enter their learning goals, interests, and what they want to learn.

[2591] server

[2592] The server uses a generative AI model to analyze the user's input data and identify specific learning goals, while an emotion engine recognizes the user's emotional state from the text data.

[2593] 2. Suggest appropriate learning resources

[2594] server

[2595] The server searches the database for relevant learning resources based on the identified learning objectives and the recognized emotional state, and generates an optimal list.

[2596] Terminal

[2597] The terminal displays the generated list of learning resources to the user.

[2598] user

[2599] Users select learning resources of interest from the suggested list and view their detailed information.

[2600] 3. Design a learning path

[2601] server

[2602] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, the user's learning goals, and their emotional state. The learning path is composed of specific steps.

[2603] Terminal

[2604] The device visually displays the designed learning path for the user to review.

[2605] 4. Track learning progress, suggest next steps, and provide feedback based on emotional state

[2606] user

[2607] Users progress along a learning path and report their progress at the end of each step.

[2608] Terminal

[2609] The terminal sends progress reports from the user to the server.

[2610] server

[2611] The server stores progress information in a database, uses a generative AI model to suggest next steps and additional feedback, and uses an emotion engine to periodically recognize the user's emotional state and generate encouraging messages and advice based on that state.

[2612] Terminal

[2613] The device will then display generated feedback and encouragement messages to the user, allowing them to visually see their progress.

[2614] Examples of concrete examples and prompts

[2615] Specific examples

[2616] A user enters "I want to improve my programming skills," and the server parses this to identify "I want to learn the basics of JavaScript." The emotion engine recognizes a positive emotional state and provides feedback like, "Your goals are great!" The server then suggests learning resources, such as "Introductory JavaScript courses," and designs a learning path.

[2617] Prompt Sentence Examples

[2618] "Tell me about your learning goals."

[2619] Enter the skill you would like to improve.

[2620] As described above, the present invention is a system that provides an effective and efficient learning experience that takes into account the user's emotional state.

[2621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2622] Step 1:

[2623] Login and User Authentication

[2624] Terminal

[2625] The terminal displays a login screen and prompts the user to enter their ID and password. The entered data is sent to the server when the login button is pressed.

[2626] user

[2627] The user enters their ID and password and clicks the login button.

[2628] server

[2629] The server verifies the received ID and password against the user data in the database. If authentication is successful, it sends the main menu to the terminal to receive the next input. If authentication fails, it generates an error message and sends it to the terminal.

[2630] Input: User ID and Password

[2631] Output: Authentication result (success / failure), main menu or error message sent

[2632] Specific operations: ID and password verification, determining next steps based on authentication results

[2633] Step 2:

[2634] Setting learning goals

[2635] Terminal

[2636] The device displays the main menu and prompts the user to click the "Goal Setting" button, and the interface displays prompts for interaction with the generative AI model.

[2637] user

[2638] Users click the "Set Goals" button, follow the prompts displayed, enter their learning goals, and then click the submit button.

[2639] server

[2640] The server receives the user's input data, analyzes it using a generative AI model, and uses an emotion engine to recognize the user's emotional state from the input data. It then generates feedback based on the analysis results and the user's emotional state and sends it to the device.

[2641] Input: User's learning goal (in text format)

[2642] Output: Specific learning goals, recognition of emotional states, generation and transmission of feedback

[2643] Specific actions: analyzing input data, recognizing emotions, generating feedback

[2644] Step 3:

[2645] Learning Resource Suggestions

[2646] server

[2647] The server searches for relevant learning resources from a database based on the identified learning objectives and the recognized emotional state, generates a list of optimal learning resources, and sends it to the terminal.

[2648] Terminal

[2649] The terminal displays a list of received learning resources to the user, including a short description of each learning resource and a recommendation comment that takes sentiment into account.

[2650] user

[2651] The user selects an item of interest from the displayed list of learning resources and clicks the Details button to view more information.

[2652] Input: Learning goals and emotional states

[2653] Output: List of learning resources, generate and display recommended comments

[2654] Specific operations: Searching and selecting related learning resources, generating data for display

[2655] Step 4:

[2656] Designing learning paths

[2657] server

[2658] The server uses a generative AI model to design an optimal learning path based on the selected learning resources, learning goals, and emotional state. The learning path consists of multiple specific steps, and the server sends this information to the terminal.

[2659] Terminal

[2660] The device visually displays the designed learning path, showing the steps and their order, allowing the user to review and correct them.

[2661] user

[2662] The user reviews the proposed learning path, modifies it if necessary, and submits the modified learning path to the server.

[2663] Input: Learning objectives, emotional state, selected learning resources

[2664] Output: Learning path design, visual representation, and user correction data

[2665] Specific operations: generating a learning path, generating visual display data, and reflecting corrections

[2666] Step 5:

[2667] Learning progress management

[2668] user

[2669] Users progress through the learning path and report their progress at the end of each step by clicking a progress report button and entering the data into the device.

[2670] Terminal

[2671] The device receives the user's progress information and sends it to the server.

[2672] server

[2673] The server stores progress information in a database, updates the learning status, suggests next steps and additional feedback using a generative AI model, and uses an emotion engine to reassess the user's emotional state, generate feedback based on that, and send it to the device.

[2674] Input: Learning progress information

[2675] Output: Updates to progress tracking data, suggests next steps, and generates emotional feedback

[2676] Specific operations: saving and updating progress information, generating next steps, generating feedback

[2677] Step 6:

[2678] Emotion recognition and feedback regulation

[2679] server

[2680] The server's emotion engine periodically recognizes the user's emotional state during learning and uses a generative AI model to generate feedback and encouraging messages to motivate the user. The generated feedback is then sent to the device.

[2681] Terminal

[2682] The device displays generated feedback and encouragement messages to the user, and provides appropriate support based on their learning progress using progress bars and graphs.

[2683] Input: Periodic emotion data, learning progress

[2684] Output: Generate and display feedback and cheer messages

[2685] Specific behavior: Regular emotion recognition, generating and displaying appropriate feedback

[2686] As described above, this system is designed to provide feedback that takes into account the user's learning goals and emotional state, enabling them to learn efficiently while increasing their motivation.

[2687] (Application example 2)

[2688] 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."

[2689] While conventional self-learning platforms provide features for managing users' learning goals and progress, they do not adequately optimize the learning experience by taking into account the user's emotional state. As a result, users' motivation decreases and learning efficiency declines. Furthermore, the suggestion of learning resources and the design of learning paths do not reflect the user's emotional state, making it difficult to provide optimal support.

[2690] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2691] In this invention, the server includes: [means for identifying learning goals from user input;] [means for suggesting appropriate learning resources based on the identified learning goals and emotional state;] [means for designing a learning path based on the user's learning goals and emotional state;] [means for tracking the user's learning progress and suggesting next steps and feedback; and [means for periodically recognizing the user's emotional state and generating feedback and messages to increase motivation.] This makes it possible to optimize the learning experience taking the user's emotional state into consideration.

[2692] "Means for identifying learning objectives from user input" refers to technology that analyzes the information entered by the user into the platform and identifies the user's learning targets and goals.

[2693] The "means for suggesting appropriate learning resources based on identified learning goals and emotional state" is a technology that analyzes the user's learning goals and emotional state, and searches a database for and suggests the most suitable learning resources.

[2694] The "means for designing a learning path based on a user's learning goals and emotional state" is a technology for systematically designing optimal learning steps according to a user's learning goals and emotional state.

[2695] "Means for tracking a user's learning progress and suggesting next steps and feedback" refers to technology that monitors a user's progress as they learn and provides them with the next steps and necessary feedback.

[2696] "Means for periodically recognizing a user's emotional state and generating feedback and messages to enhance motivation" refers to a technology that periodically analyzes a user's emotional state while they are learning, and generates and provides feedback such as encouragement or advice according to that state.

[2697] This invention provides a self-learning platform that combines an emotional engine to improve users' learning experience. Specifically, the system analyzes information entered by users, identifies learning goals, suggests appropriate learning resources, designs learning paths, manages progress, recognizes emotional states, and reflects feedback on the learning process.

[2698] First, the system that realizes this invention includes the following main software components: EmotionEngine, AIModule, and ResourceDatabase. Furthermore, it is assumed that these software components will be installed on a smartphone. Specific hardware that can be used is smartphones such as iPhones and Android devices.

[2699] The server uses the Emotion Engine to analyze the user's input and identify learning goals. The Emotion Engine also analyzes the user's emotional state and identifies states such as positive, negative, and neutral. The AI ​​Module then uses this information to search for appropriate learning resources from the Resource Database and suggest them to the user.

[2700] Furthermore, the server designs an optimal learning path based on the user's learning goals and emotional state. AIModule uses the user's input information and emotional analysis results to construct sequential learning steps. As the user completes each step, the device reports its progress to the server, which tracks it and provides next steps and feedback.

[2701] The emotion engine periodically recognizes the user's emotional state and generates motivational feedback and encouraging messages, which are displayed on the device along with progress bars and graphs to keep the user motivated to continue learning.

[2702] Examples:

[2703] If an employee wants to "improve their customer service skills," enter a prompt like this:

[2704] "I would like to improve my customer service skills. I have learned the basics, but I would like to gain practical application skills with specific examples. I have been feeling unsure about my customer service recently, so I would appreciate any advice on how I can improve."

[2705] The server analyzes this prompt, and the Emotion Engine recognizes the user's emotional state in a positive way. Based on this information, AIModule suggests learning resources from its Resource Database, such as a "Collection of Customer Service Scenarios to Hone Applied Skills." It then designs specific learning steps, such as "Applied Skills Training 1: Basic Scenarios" and "Applied Skills Training 2: Applied Scenarios," and provides these to the user.

[2706] After each step, the server updates the user's progress and generates next steps and encouraging messages as needed. The emotion engine also periodically scans the user's emotional state and provides feedback based on the results, maximizing the user's learning effectiveness.

[2707] In this way, the present invention is able to provide an effective and efficient learning experience while taking into account the user's emotional state.

[2708] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2709] Step 1:

[2710] The user logs into the platform using a terminal and opens an interactive input interface for goal setting.

[2711] Input: A prompt containing the user's learning goals and objectives

[2712] Data processing: The emotion engine analyzes the user's emotional state, and the generative AI model performs text analysis.

[2713] Output: Identified learning objectives and sentiment analysis results

[2714] Step 2:

[2715] The server searches and suggests appropriate learning resources from the ResourceDatabase based on the identified learning goals and emotional state.

[2716] Input: Identified learning objectives and sentiment analysis results

[2717] Data processing: Performing database queries to filter and rank relevant learning resources

[2718] Output: A list of recommended learning resources

[2719] Step 3:

[2720] The server displays recommended learning resources on the user's terminal, and the user selects the resource of interest from this list.

[2721] Input: A list of recommended learning resources

[2722] Data processing: Obtain detailed information about learning resources and generate recommended comments based on emotional states

[2723] Output: Learning resources and recommended comments displayed on the terminal

[2724] Step 4:

[2725] Based on the selected learning resources, the server designs an optimal learning path taking into account the user's learning goals and emotional state.

[2726] Input: Selected learning resources, learning objectives, sentiment analysis results

[2727] Data processing: Generative AI models design and sequence optimal learning steps

[2728] Output: Learning path (list of specific steps)

[2729] Step 5:

[2730] The device visually displays the designed learning path, allowing the user to check and correct it.

[2731] Input: Learning Path

[2732] Data processing: Generate visual learning paths and display them in the user interface

[2733] Output: A learning path display that the user can review and modify

[2734] Step 6:

[2735] The user progresses through the learning path and their progress is reported to the device at the end of each step.

[2736] Input: User progress report

[2737] Data processing: Progress data is sent to the server and learning status is saved in the database

[2738] Output: Updated progress information

[2739] Step 7:

[2740] The server generates the next step and additional feedback based on the progress information and sends it to the device.

[2741] Input: Updated progress information

[2742] Data processing: Generative AI models determine next steps and feedback

[2743] Output: Next steps and feedback displayed on the terminal

[2744] Step 8:

[2745] The emotion engine periodically recognizes the user's emotional state and provides feedback information to the server.

[2746] Input: The user's current emotional state

[2747] Data processing: Emotion recognition algorithms analyze emotional data

[2748] Output: Feedback information reflecting emotional state

[2749] Step 9:

[2750] The device displays supportive messages and feedback generated by the emotion engine to the user.

[2751] Input: Feedback information reflecting emotional state

[2752] Data processing: Determine the display format of the feedback

[2753] Output: A cheering message or feedback that is displayed to the user

[2754] 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.

[2755] 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.

[2756] 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.

[2757] 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.

[2758] 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.

[2759] 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.

[2760] 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).

[2761] 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.

[2762] 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."

[2763] 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.

[2764] 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).

[2765] 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.

[2766] 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.

[2767] 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.

[2768] 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.

[2769] 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.

[2770] 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.

[2771] 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.

[2772] 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.

[2773] 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.

[2774] 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.

[2775] The following is further disclosed regarding the above embodiment.

[2776] (Claim 1)

[2777] [Means for identifying learning objectives from user input; and

[2778] [Means of suggesting appropriate learning resources based on identified learning objectives; and

[2779] [Means of designing learning paths based on users' learning goals;

[2780] [Means of tracking users' learning progress and suggesting next steps;

[2781] A system including:

[2782] (Claim 2)

[2783] 10. The system of claim 1, further comprising: means for accepting interactive input from a user to identify learning objectives.

[2784] (Claim 3)

[2785] The system of claim 1, including means for visually displaying the suggested learning resources to a user.

[2786] (Claim 4)

[2787] [The system of claim 1, including means for allowing a user to review and correct each step of the learning path.

[2788] (Claim 5)

[2789] [The system of claim 1, including means for visualizing a user's progress in the form of a graph or progress bar.]

[2790] "Example 1"

[2791] (Claim 1)

[2792] [A means for users to log in using their device and verify their credentials;

[2793] [Means for identifying learning objectives from user input and analyzing them using a generative AI model; and

[2794] [Means for suggesting relevant learning resources from a database based on identified learning objectives; and

[2795] [means for generating and visually displaying an optimal learning path based on the proposed learning resources;

[2796] [Means of tracking the user's learning progress and suggesting next steps using progress bars and graphs; and

[2797] A system including:

[2798] (Claim 2)

[2799] [The system of claim 1, including means for providing detailed feedback using a generative AI model based on identified learning goals.]

[2800] (Claim 3)

[2801] [The system of claim 1, including means for accepting interactive input from a user and further specifying a learning objective using prompt sentences.

[2802] "Application Example 1"

[2803] (Claim 1)

[2804] [Means for identifying learning objectives from user input; and

[2805] [Means of suggesting appropriate learning resources based on identified learning objectives; and

[2806] [Means of designing learning paths based on users' learning goals;

[2807] [Means of tracking users' learning progress and suggesting next steps;

[2808] [means for accepting voice input;

[2809] [Means of providing task notifications and reminders;

[2810] [Means for displaying statistics of learning history;

[2811] A system including:

[2812] (Claim 2)

[2813] 10. The system of claim 1, further comprising: means for accepting interactive input from a user to identify learning objectives.

[2814] (Claim 3)

[2815] The system of claim 1, including means for visually displaying the suggested learning resources to a user.

[2816] "Example 2: Combining Emotion Engines"

[2817] (Claim 1)

[2818] [Means for identifying learning goals and recognizing emotional states from user input;

[2819] [Means of s...

Claims

1. a means for identifying learning objectives from user input; a means of suggesting appropriate learning resources based on identified learning objectives; a means of designing a learning path based on the user's learning goals; A means to track users' learning progress and suggest next steps; A system including:

2. 10. The system of claim 1, further comprising means for accepting interactive input from a user to identify learning objectives.

3. The system of claim 1 , further comprising means for visually displaying the suggested learning resources to a user.

4. 10. The system of claim 1, further comprising means for enabling a user to review and modify each step of the learning path.

5. The system of claim 1 , further comprising means for visualizing a user's progress in the form of a graph or progress bar.

Images