system

Abstract

We provide the system. [Solution] A memory device for accumulating information on individual learners, A processing means that generates educational tasks suitable for individual learners using a generative model, Means for providing a user interface for displaying generated educational assignments, A processing means that receives learners' answers to assignments and provides evaluation and response, A means of selecting and distributing educational content in specific fields based on users' interests, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the learning process for technicians and engineers, there is a problem that it is difficult to provide a learning plan according to individual progress and skill levels. Also, maintaining learning motivation is an issue, and it is also a problem that continuous efforts in the learning process are difficult.

Means for Solving the Problems

[0005] This invention provides a means for storing individual learner progress information in a database and dynamically generating suitable learning tasks using a generative model. Furthermore, it presents the generated learning tasks through a user interface and provides evaluation and feedback during the learner's response process. In addition, it supports the maintenance of continuous learning motivation and skill development by using a dialogue agent to communicate in natural language and flexibly respond to learner questions.

[0006] "Individual learners" refers to individual users who have different skill levels and progress.

[0007] "Progress information" refers to data that shows the extent to which learners have completed tasks and in which areas their skills have improved.

[0008] A "database" refers to a centralized record-keeping system for storing learners' progress information and history.

[0009] A "generative model" refers to an algorithm that uses machine learning and AI technologies to create tasks and content tailored to learners.

[0010] "Learning tasks" refer to specific problems or tasks that learners should work on in order to improve their skills or acquire knowledge.

[0011] "User interface" refers to the screens and methods of operation that allow a system and a learner to interact and exchange information.

[0012] A "dialogue agent" refers to a program that uses natural language processing to communicate with learners.

[0013] "Feedback" refers to the evaluation and advice given to learners regarding the results of their assignments. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a learning system that utilizes generative AI technology to provide appropriate tasks to individual learners and support continuous learning. In the implementation of this system, the server, terminal, and user each play their respective roles.

[0036] The server stores learner progress information and learning history in a database and generates individually customized learning tasks using an AI model. The server provides the generated tasks to the terminal in real time and evaluates and provides feedback on the tasks based on the learner's input. The server also handles natural language communication with the learner through a conversational agent.

[0037] The terminal displays learning assignments received from the server on the user interface, providing an environment where learners can work on the assignments. The terminal also handles the learner's input and sends progress information to the server.

[0038] Users work on tasks displayed on their device and devise solutions. They input the results of their completed tasks into the device and receive feedback. Based on this input, they can determine what task to move on to next. They can also ask questions about anything they don't understand through a conversational agent and receive additional assistance.

[0039] As a concrete example, let's say a user is learning a new programming language. The server generates tasks ranging from basic to advanced based on the user's past learning history. The terminal displays tasks such as "defining variables" and "using functions," prompting the user to solve them. Once the user completes a task, the server evaluates the result and recommends the next step, such as tasks on "conditional branching" or "loop structures." In this way, the user can gradually improve their skills.

[0040] This system aims to allow learners to learn at their own pace and to make learning enjoyable and engaging, like a game.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user logs into the system via a terminal. The terminal provides an interface for entering a username and password and sends the user's input to the server.

[0044] Step 2:

[0045] The server compares the received username and password with the database to perform authentication. If authentication is successful, it issues a session ID to the user and sends the necessary information to the terminal.

[0046] Step 3:

[0047] The server uses an AI model to generate learning tasks tailored to the user based on their learning history. The generated task information is then sent to the user's device.

[0048] Step 4:

[0049] The terminal displays learning assignments received from the server in its user interface. These assignments include detailed explanations and hints.

[0050] Step 5:

[0051] The user works on learning tasks presented on the device. If necessary, they use a conversational agent to ask questions about the learning process and think about solutions.

[0052] Step 6:

[0053] When a user enters a solution to a problem into their device, the device sends that data to the server. The user's input is recorded in a log.

[0054] Step 7:

[0055] The server evaluates the problem based on the user's solution. After analysis by an AI model, it generates feedback results and sends them to the terminal.

[0056] Step 8:

[0057] The terminal displays feedback received from the server to the user. This includes the presentation of new challenges for the next step and advice on areas that need review.

[0058] Step 9:

[0059] The user reviews the feedback and moves on to the next learning task if necessary. The device requests the server to select a new task.

[0060] Step 10:

[0061] The server updates the database with user progress information and records the overall learning status of the system. After the learning session ends, it performs the appropriate logout process.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] One challenge is that educators have difficulty receiving the most appropriate educational content tailored to each student's level of understanding, hindering effective learning. Traditional education systems lack sufficient materials to accommodate individual learning speeds and comprehension levels, making it difficult for educators to address their own weaknesses. Furthermore, the lack of automation in learning results in wasted time and effort.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for storing individual educators' progress information in an information storage device, means for generating educational tasks suitable for individual educators using a generative artificial intelligence model, and means for analyzing educators' past teaching history and adjusting tasks based on their strengths and weaknesses. This makes it possible for each educator to receive optimal educational tasks tailored to their level of understanding at the appropriate time.

[0067] "Progress information" refers to data that shows what individual educators have achieved in the learning process and the level of proficiency they have developed over time.

[0068] An "information storage device" refers to a recording medium or device that stores data on a computer and makes it accessible later.

[0069] A "generative artificial intelligence model" is a computer model based on machine learning techniques and algorithms used to generate tasks tailored to the needs of educators.

[0070] "Educational challenges" refer to specific problems or tasks that educators must address in order to facilitate learning and skill acquisition.

[0071] An "input display device" refers to a screen or device that allows a user to interact with a computer, and it visually presents tasks and information.

[0072] An "interactive information processing system" refers to a system that exchanges information and answers questions with users through natural language.

[0073] "Achievement level" is an indicator that shows the degree to which educators have gained understanding and skills regarding specific educational tasks or goals.

[0074] The following describes an embodiment for carrying out the present invention. This system involves cooperation between a server, a terminal, and a user to provide an educational program tailored to individual educators.

[0075] Server role:

[0076] The server first records the educator's progress information in an information storage device. A typical relational database system is used for this purpose. Next, it utilizes a generative artificial intelligence model to generate educational tasks suitable for the educator. The generative AI model is built using machine learning frameworks such as TENSORFLOW® or PyTorch. The generated educational tasks are sent from the server to the terminal. The server also receives responses from the educator and processes them to provide evaluation and feedback.

[0077] Terminal role:

[0078] The terminal displays educational assignments sent from the server on an input display device. This utilizes web and mobile application frameworks such as React or Flutter. It provides an interface for educators to work on the assignments and is responsible for sending responses to the server.

[0079] User roles:

[0080] The user, or educator, works on educational tasks displayed on the terminal. As a concrete example, consider a scenario where the user is learning a new programming language. In this case, the server generates tasks related to variable definition and function usage based on the user's past history. The user solves these tasks and enters their answers into the terminal. Feedback on the answers is provided in real-time from the server, allowing the user to proceed to the next step.

[0081] An example of a prompt would be, "Generate tasks that reflect the user's past learning history. For example, create a prompt that provides tasks suitable for a user learning the basics of programming." By entering this prompt, the generation AI model will generate tasks customized for the user.

[0082] This invention aims to improve the educational experience by enabling educators to learn at their own pace and according to their level of understanding.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server receives input data from educators. This input data includes basic information and past progress information of the educators. The server stores this data in an information storage device and updates the educators' learning history. In this storage process, the data is structured and stored in a database using SQL queries in order to track the educators' progress in detail.

[0086] Step 2:

[0087] The server generates optimal educational tasks using a generative AI model based on saved progress information. The server inputs prompts into the generative AI model, which then generates personalized tasks based on past learning history and current skill level. This model is pre-trained, for example, using TensorFlow, and provides optimal output based on the input prompts.

[0088] Step 3:

[0089] The server sends the generated task to the terminal. The input here is the content of the generated task, and the output is a task delivery data packet to the terminal. This packet is serialized in JSON format and securely sent to the terminal via the HTTP protocol.

[0090] Step 4:

[0091] The terminal displays assignments received from the server on its input display device. The terminal uses a user interface to visually deserialize and display the packets, making the assignments easy for educators to understand intuitively. Here, the assignments are properly displayed on the screen, allowing educators to access them.

[0092] Step 5:

[0093] Users work on tasks displayed on their devices. They input their answers into the device and then send those answers to the server. User input is typically done via a keyboard or touch interface.

[0094] Step 6:

[0095] The server evaluates the user's answers received from the terminal. The server uses an AI model to analyze these answers and determine whether they are correct or incorrect. The input here is the user's answer data, and the output is the evaluation result and any necessary feedback data. The analyzed data demonstrates the effectiveness of the learning process and serves as a basis for deciding which tasks to present in the next step.

[0096] Step 7:

[0097] The server sends the generated feedback back to the device. This is the process of providing appropriate feedback on the user's answer and delivering the feedback data to the device. The server uses natural language generation technology as needed to send feedback tailored to each user's needs.

[0098] Step 8:

[0099] The terminal displays feedback sent from the server, providing immediate feedback to the user. The terminal visually displays the feedback on the screen, providing information to help the user choose the next step. The display of feedback helps educators recognize their own progress and clarify the next learning steps.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] In modern education systems, providing individually optimized learning experiences is difficult, and there is a need to automatically generate and provide effective assignments tailored to each learner's interests and proficiency level. Furthermore, there is a desire for a system that allows learners to easily access appropriate content in areas of interest and learn in depth at their own pace.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes a storage means for accumulating information on individual learners, a processing means for generating educational tasks suitable for individual learners using a generative model, a means for providing a user interface for displaying the generated educational tasks, and a means for selecting and delivering educational content in specific fields based on the user's interests. This enables learners to progress through their learning at their own pace, step by step, while gaining a deep understanding of specific educational fields that match their interests.

[0105] "Individual learner information" refers to records that include data on a specific learner's history, progress, and interests.

[0106] "Memory means" refers to technical means of storing and managing learner information using databases and storage devices.

[0107] A "generative model" is an algorithm or program that uses generative AI technology to automatically generate the most suitable tasks and content for learners.

[0108] "Educational assignments" refer to practice problems or learning content with specific educational objectives, provided according to the learner's abilities and progress.

[0109] "Processing means" refers to functions that provide learners with tasks and information generated through calculations and data manipulation performed by servers and computer systems.

[0110] A "user interface" is an interface provided to learners for viewing and manipulating information when working on assignments.

[0111] "Means of selecting and delivering educational content in specific fields based on interests" refers to a technical mechanism that analyzes learners' past history and interests, selects highly relevant educational content based on that analysis, and delivers it to the learners.

[0112] This invention is a system for providing educational content tailored to individual learners. The core of the system is a server that stores learner information and generates appropriate tasks using a generative AI model. The server leverages Python and machine learning frameworks such as TensorFlow or PyTorch to analyze learning history and interests. The generative model automatically generates personalized learning tasks.

[0113] The device receives assignments sent from the server via an application developed in Swift (iOS) or Kotlin (Android®) and displays them in a user interface. Learners use this interface to solve the assignments and input their answers into the device. The device sends the user's input to the server in real time and updates progress information.

[0114] Users can select specific learning areas of interest (such as history or science) via the screen on their device. If they have questions, they can ask them via chat through a conversational program. The server responds to these inquiries using natural language processing and provides appropriate feedback.

[0115] As a concrete example, if a user wants to learn about "Medieval European History," the prompt would be: "The user wishes to learn history. Their current knowledge level is intermediate. Please provide content related to medieval Europe." Based on this prompt, the server would provide corresponding educational materials and quizzes. This process allows learners to gradually expand their knowledge according to their progress.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server retrieves learner information from a database. This information includes past assignment history, progress, and areas of interest. The input is the learner ID, and the output is the corresponding learner's information data. Based on this data, the server prepares to generate personalized assignments in the next step.

[0119] Step 2:

[0120] The server analyzes learner information obtained using a generative AI model and generates appropriate educational tasks. The input is the learner information obtained in step 1, and the output is a personalized set of tasks. In this process, a machine learning algorithm selects tasks that match each learner's proficiency level and interests.

[0121] Step 3:

[0122] The server sends the generated set of tasks to the terminal. The terminal receives this information and displays the tasks on the user's interface. The input is the set of tasks, and the output is the visual information displayed on the user interface. This prepares the user to work on the tasks.

[0123] Step 4:

[0124] The user works on a task provided on the device's screen and enters their answer. The input is the answer data entered by the user, and the output is the device's response completion status. In this step, once the user has completed the answer, the device automatically sends that information to the server.

[0125] Step 5:

[0126] The server evaluates the response data received from the terminal and generates feedback. The input is the user's response data, and the output is the evaluation result and feedback information. This process uses an evaluation algorithm that compares the response with correct answer data to suggest appropriate areas for improvement to the user.

[0127] Step 6:

[0128] The terminal displays the evaluation results and feedback received from the server on the user interface. The input is the evaluation results and feedback information, and the output is the information visually presented to the user. This allows the user to check their progress and decide on the next learning step.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] This invention provides a system that offers a more personalized learning experience by combining generative AI technology and an emotion recognition engine. This system evaluates the progress of each learner, generates appropriate learning tasks, and further analyzes the learner's emotional state to optimize the learning process.

[0131] The server stores and manages learner progress information in a database. Using an AI model, it generates customized learning tasks based on the learner's skill level and past learning history. These tasks are delivered to the device in real time.

[0132] The terminal displays learning assignments received from the server on its user interface, providing an environment for learners to work on the assignments. It also responds to learners' questions in natural language through an interactive agent. Furthermore, the terminal uses an emotion engine to analyze the user's emotions in real time from their facial expressions and voice, and transmits this information to the server.

[0133] The emotion engine analyzes learners' motivation, concentration, and stress levels as they work on tasks. The server receives this emotion data and generates feedback, such as adjusting the difficulty of the tasks or sending encouraging messages.

[0134] As a concrete example, let's say a user is learning a new programming language. The server generates a "loop structure" task based on the user's past learning history. The terminal displays this task, and the user works on it. If the emotion engine analyzes that the user is stuck, the server provides more hints for the task or offers encouraging messages through the terminal. In this way, the user can learn in an emotionally sensitive environment.

[0135] This system enhances the quality of learning and supports more efficient knowledge retention by taking user emotions into consideration.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user logs into the system via a terminal. The terminal displays an interface for entering a username and password, and sends the user's input to the server.

[0139] Step 2:

[0140] The server compares the received username and password with the database to authenticate the user. If authentication is successful, it issues a session ID and sends the necessary information back to the terminal.

[0141] Step 3:

[0142] The server uses an AI model to generate appropriate learning tasks based on the user's learning history and progress. This task information is then sent to the user's device.

[0143] Step 4:

[0144] The terminal displays learning assignments received from the server in the user interface. These assignments include detailed information and hints.

[0145] Step 5:

[0146] Users work on learning tasks displayed on their device. They can think of solutions and, if necessary, use a conversational agent to ask questions.

[0147] Step 6:

[0148] The device uses a built-in emotion engine to analyze emotional data in real time from the user's facial expressions and voice, and sends the user's current emotional state to the server.

[0149] Step 7:

[0150] Once the user completes the task, they enter the solution into the device. The device then sends the entered data to the server.

[0151] Step 8:

[0152] The server evaluates the user's solution and generates feedback using an AI model. It takes data from the emotion engine into account and adjusts the difficulty of the task and the content of the feedback as needed.

[0153] Step 9:

[0154] The terminal displays feedback received from the server to the user. This feedback includes advice based on learning progress and information about the next steps.

[0155] Step 10:

[0156] The user reviews the feedback and decides to proceed to the next learning task. The device notifies the server of this decision and requests a new learning task.

[0157] Step 11:

[0158] The server updates the user's progress information in the database and maintains a system-wide learning record. It terminates the user's session as needed.

[0159] (Example 2)

[0160] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0161] Conventional learning support systems have difficulty providing individualized learning experiences that fully consider the learner's progress and emotional state, and they also have the challenge of not being able to flexibly adjust the system to maximize learning effectiveness. The present invention aims to solve these problems and provide a more effective and individualized learning environment.

[0162] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0163] In this invention, the server includes means for storing individual learner progress data in a recording device, means for generating learning content suitable for individual learners using generative AI, and means for adjusting the difficulty level of the learning content and generating encouraging messages based on emotional data. This enables flexible and effective learning support for individual learners.

[0164] An "individual learner" refers to each user of the system who is identified based on specific conditions and needs.

[0165] "Progress data" refers to information that shows how far a learner has progressed with a particular task or learning content.

[0166] A "recording device" is a system component that stores, manages, and keeps data available for later use.

[0167] "Generative AI" is an artificial intelligence technology that automatically generates new data or solutions based on specific inputs or conditions.

[0168] "Learning content" refers to the specific tasks, topics, and concepts that learners are expected to study.

[0169] An "information display device" is a device or system component that presents information visually or audibly through a user interface.

[0170] "Answer" refers to the solution or response that a learner provides to a task or question.

[0171] A "report" refers to information about evaluations and feedback generated based on learners' answers.

[0172] A "sensing device" is a device that receives physical or digital stimuli and collects data on emotions and situations.

[0173] "Emotional data" refers to information recorded to represent the emotional state of learners.

[0174] "Difficulty level adjustment" is the process of changing the complexity and ease of learning content according to the learner's level.

[0175] "Messages of encouragement" are positive feedback and words of encouragement provided to improve learners' motivation.

[0176] This invention aims to provide a flexible learning environment that takes into account the learner's progress and emotional state, as an individualized learning support system. The entire system consists of a server, terminals, and a user interface.

[0177] server

[0178] The server's primary role is to manage learners' progress data. This involves using a recording device to store information in a database. The server can use generative AI to generate the most appropriate learning content based on the learner's past learning history and skill assessment. A "generative AI model" is generally used as the model for the generative AI.

[0179] As a concrete example, in a scenario where a learner is learning a new programming language, the server prompts the AI ​​with the statement, "Generate an intermediate loop problem in the programming language the user is learning," and then generates an appropriate problem.

[0180] terminal

[0181] The terminal's role is to display learning content delivered from the server to the learner. The terminal is equipped with an information display device, allowing users to work on assignments in real time. Furthermore, the terminal has the ability to respond to user questions in natural language via a conversational agent. In addition, the terminal has a built-in sensing device that collects the user's facial expressions and voice during learning, enabling real-time analysis of emotional data.

[0182] User

[0183] The user is central to this system, and can progress through their learning based on personalized learning content. The user's emotional data is analyzed by the server and used to adjust the difficulty level of the learning content and provide encouraging messages. For example, if a user is stuck on a particular task, the server provides appropriate feedback and additional support to create an environment that maximizes learning efficiency.

[0184] In this way, this system provides learners with learning support tailored to their individual needs, enabling more efficient and effective learning.

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The server receives learner progress information as input and stores it in a database. This progress information includes the learner's current level of proficiency and past learning history. By structuring the input progress data and storing it in the database, it is processed into a format that can be used to generate learning assignments later.

[0188] Step 2:

[0189] The server inputs the necessary learning content as prompts into the generating AI model based on progress information stored in the database. A specific example of a prompt is, "Generate customized tasks related to the subject the user is currently learning." The generating AI model generates learning tasks based on this prompt, and the server receives its output.

[0190] Step 3:

[0191] The server adjusts the data format of the generated learning assignments in order to send them to the device. It converts the assignment content into a format that can be delivered in real time before sending it to the device. This conversion makes the data easily receivable on the learner's device.

[0192] Step 4:

[0193] The terminal receives learning assignments sent from the server and visualizes them on the user interface using an information display device. This allows the user to view and interact with the learning assignments on the screen. The terminal also activates an interactive agent to prepare to respond to questions from the learner.

[0194] Step 5:

[0195] As users work on learning tasks, the device uses its built-in sensors to collect facial and audio data. This data is analyzed in real time by emotion analysis software within the device, and the learner's emotional state is determined from the output.

[0196] Step 6:

[0197] The device sends the analyzed emotional state information to the server. The server uses this information to adjust the difficulty level of the learning tasks as needed and to create encouraging messages as required. Based on this output adjustment, any necessary changes or additional support are made.

[0198] Step 7:

[0199] The device receives the adjusted learning content and encouraging messages resent from the server and provides them to the user again through the user interface. This optimizes the user's learning experience according to their individual needs and circumstances.

[0200] (Application Example 2)

[0201] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0202] In the field of elderly care, there is a challenge in providing appropriate care and recreation tailored to the emotional state of individual users. Current technology is insufficient to respond quickly to changes in users' emotions and select and provide appropriate activities accordingly. As a result, there is a potential decline in the quality of life for users.

[0203] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0204] In this invention, the server includes means for storing individual user progress information in a storage device, means for generating activities suitable for individual users using a generative model, and means for analyzing the user's emotional state and providing evaluation and feedback. This makes it possible to provide appropriate care and recreation according to the user's emotional state.

[0205] "Users" refer to individual individuals within the care facilities that use the system.

[0206] "Progress information" refers to a record of data that includes the history of the user's activities and emotional state.

[0207] A "storage device" is a part of physical or digital hardware used to store data.

[0208] A "generative model" is an algorithm that uses artificial intelligence technology to automatically create activities that are suitable for the user.

[0209] "Activities" refer to specific tasks or programs that are carried out as part of the recreation and care provided at nursing care facilities.

[0210] "Human interface" refers to the user interface that allows users and systems to exchange information with each other.

[0211] "Emotional state" refers to the psychological or emotional condition perceived from the user's facial expressions and voice.

[0212] "Analysis" refers to using collected data to evaluate users' emotional states and activity progress.

[0213] "Feedback" refers to providing users with information and suggestions tailored to their activities and emotional state.

[0214] To implement this invention, a robot deployed in a nursing care facility is used. The robot is equipped with a facial recognition camera and a voice recognition microphone, which collect facial expressions and voice data from the users. This data is then analyzed in real time through an emotion recognition engine to determine the users' emotional state. A specific example of the emotion recognition engine used is Affectiva.

[0215] Next, the server receives the collected data and uses a generative AI model to generate care and recreational activities that are best suited to the user's emotional state. This generative AI model may include GPT-3®, provided by OpenAI®.

[0216] The generated activities are presented on a human interface via a robot, and users participate. As users engage in the activities, emotional data is continuously collected, evaluated by a server, and adjusted as needed, or encouraging messages are provided as feedback. For example, a suggestion might be made such as, "You seem a bit down lately, so why not enjoy some tea while listening to some calming music today?"

[0217] An example of a prompt might be, "Analyze user A's current emotional state and suggest appropriate relaxation activities."

[0218] This system is expected to provide users with high-quality care that is tailored to their emotions, thereby improving the quality of life for residents in care facilities.

[0219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0220] Step 1:

[0221] The device uses a facial recognition camera and a microphone for voice recognition to collect the user's facial expressions and voice data. The input is real-time video and audio data, which is sent to an emotion recognition engine for data processing to analyze the user's emotional state. The output is evaluation data indicating the user's emotional state.

[0222] Step 2:

[0223] The server receives emotional state evaluation data sent from the terminal. The input is evaluation data, and based on this, a generative AI model is used to perform data calculations that generate care and recreational activities suitable for the user. The output is the content of the generated activity suggestions.

[0224] Step 3:

[0225] The terminal displays activity suggestions received from the server on its human interface. The input is the activity suggestions from the server, which are displayed in a visually recognizable format for the user. The output is the displayed activity suggestions.

[0226] Step 4:

[0227] The user engages in an activity based on the suggested activity. During this time, the device continuously analyzes the facial and voice data collected again using its emotion recognition engine to obtain emotion data. The input is real-time data from the activity, and the output is the latest emotion evaluation data corresponding to the activity status.

[0228] Step 5:

[0229] The server receives updated sentiment assessment data from the terminal and adjusts the activity suggestions as needed. The input is the latest sentiment assessment data, and the server uses data calculations to modify parts of the activity or generate encouraging messages. The output is the adjusted activity suggestions and feedback messages.

[0230] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0231] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0232] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0236] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0237] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0238] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0239] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0240] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0241] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0242] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0243] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0244] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0245] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0246] This invention is a learning system that utilizes generative AI technology to provide appropriate tasks to individual learners and support continuous learning. In the implementation of this system, the server, terminal, and user each play their respective roles.

[0247] The server stores learner progress information and learning history in a database and generates individually customized learning tasks using an AI model. The server provides the generated tasks to the terminal in real time and evaluates and provides feedback on the tasks based on the learner's input. The server also handles natural language communication with the learner through a conversational agent.

[0248] The terminal displays learning assignments received from the server on the user interface, providing an environment where learners can work on the assignments. The terminal also handles the learner's input and sends progress information to the server.

[0249] Users work on tasks displayed on their device and devise solutions. They input the results of their completed tasks into the device and receive feedback. Based on this input, they can determine what task to move on to next. They can also ask questions about anything they don't understand through a conversational agent and receive additional assistance.

[0250] As a concrete example, let's say a user is learning a new programming language. The server generates tasks ranging from basic to advanced based on the user's past learning history. The terminal displays tasks such as "defining variables" and "using functions," prompting the user to solve them. Once the user completes a task, the server evaluates the result and recommends the next step, such as tasks on "conditional branching" or "loop structures." In this way, the user can gradually improve their skills.

[0251] This system aims to allow learners to learn at their own pace and to make learning enjoyable and engaging, like a game.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The user logs into the system via a terminal. The terminal provides an interface for entering a username and password and sends the user's input to the server.

[0255] Step 2:

[0256] The server compares the received username and password with the database to perform authentication. If authentication is successful, it issues a session ID to the user and sends the necessary information to the terminal.

[0257] Step 3:

[0258] The server uses an AI model to generate learning tasks tailored to the user based on their learning history. The generated task information is then sent to the user's device.

[0259] Step 4:

[0260] The terminal displays learning assignments received from the server in its user interface. These assignments include detailed explanations and hints.

[0261] Step 5:

[0262] The user works on learning tasks presented on the device. If necessary, they use a conversational agent to ask questions about the learning process and think about solutions.

[0263] Step 6:

[0264] When a user enters a solution to a problem into their device, the device sends that data to the server. The user's input is recorded in a log.

[0265] Step 7:

[0266] The server evaluates the problem based on the user's solution. After analysis by an AI model, it generates feedback results and sends them to the terminal.

[0267] Step 8:

[0268] The terminal displays feedback received from the server to the user. This includes the presentation of new challenges for the next step and advice on areas that need review.

[0269] Step 9:

[0270] The user reviews the feedback and moves on to the next learning task if necessary. The device requests the server to select a new task.

[0271] Step 10:

[0272] The server updates the database with user progress information and records the overall learning status of the system. After the learning session ends, it performs the appropriate logout process.

[0273] (Example 1)

[0274] Next, we will describe Example 1. 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".

[0275] One challenge is that educators have difficulty receiving the most appropriate educational content tailored to each student's level of understanding, hindering effective learning. Traditional education systems lack sufficient materials to accommodate individual learning speeds and comprehension levels, making it difficult for educators to address their own weaknesses. Furthermore, the lack of automation in learning results in wasted time and effort.

[0276] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0277] In this invention, the server includes means for storing individual educators' progress information in an information storage device, means for generating educational tasks suitable for individual educators using a generative artificial intelligence model, and means for analyzing educators' past teaching history and adjusting tasks based on their strengths and weaknesses. This makes it possible for each educator to receive optimal educational tasks tailored to their level of understanding at the appropriate time.

[0278] "Progress information" refers to data that shows what individual educators have achieved in the learning process and the level of proficiency they have developed over time.

[0279] The "information storage device" refers to a recording medium or recording device that holds data on a computer and makes it accessible later.

[0280] The "generated artificial intelligence model" is a computer model based on machine learning techniques and algorithms used to generate tasks suitable for educators.

[0281] The "educational task" refers to specific problems or tasks that educators should engage in for learning or skill acquisition.

[0282] The "input display device" refers to a screen or device through which a user can interact with a computer, and visually presents tasks and information.

[0283] The "interactive information processing device" refers to a system for information exchange and question-and-answer with users via natural language.

[0284] The "degree of achievement" is an indicator showing how much understanding and skills an educator has obtained for specific educational tasks or goals.

[0285] The embodiments for implementing the present invention are shown below. This system coordinates among a server, a terminal, and a user to provide an educational program suitable for individual educators.

[0286] Role of the server:

[0287] The server first records the progress information of the educator in the information storage device. A general relational database system is used for this. Next, it utilizes the generated artificial intelligence model to generate educational tasks suitable for the educator. The generated artificial intelligence model is constructed using machine learning frameworks such as TensorFlow or PyTorch. The generated educational tasks are sent from the server to the terminal. The server also receives responses from the educator and performs processing to provide evaluation and feedback.

[0288] Terminal role:

[0289] The terminal displays educational assignments sent from the server on an input display device. This utilizes web and mobile application frameworks such as React or Flutter. It provides an interface for educators to work on the assignments and is responsible for sending responses to the server.

[0290] User roles:

[0291] The user, or educator, works on educational tasks displayed on the terminal. As a concrete example, consider a scenario where the user is learning a new programming language. In this case, the server generates tasks related to variable definition and function usage based on the user's past history. The user solves these tasks and enters their answers into the terminal. Feedback on the answers is provided in real-time from the server, allowing the user to proceed to the next step.

[0292] An example of a prompt would be, "Generate tasks that reflect the user's past learning history. For example, create a prompt that provides tasks suitable for a user learning the basics of programming." By entering this prompt, the generation AI model will generate tasks customized for the user.

[0293] This invention aims to improve the educational experience by enabling educators to learn at their own pace and according to their level of understanding.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The server receives input data from educators. This input data includes basic information and past progress information of the educators. The server stores this data in an information storage device and updates the educators' learning history. In this storage process, the data is structured and stored in a database using SQL queries in order to track the educators' progress in detail.

[0297] Step 2:

[0298] The server generates optimal educational tasks using a generative AI model based on saved progress information. The server inputs prompts into the generative AI model, which then generates personalized tasks based on past learning history and current skill level. This model is pre-trained, for example, using TensorFlow, and provides optimal output based on the input prompts.

[0299] Step 3:

[0300] The server sends the generated task to the terminal. The input here is the content of the generated task, and the output is a task delivery data packet to the terminal. This packet is serialized in JSON format and securely sent to the terminal via the HTTP protocol.

[0301] Step 4:

[0302] The terminal displays assignments received from the server on its input display device. The terminal uses a user interface to visually deserialize and display the packets, making the assignments easy for educators to understand intuitively. Here, the assignments are properly displayed on the screen, allowing educators to access them.

[0303] Step 5:

[0304] Users work on tasks displayed on their devices. They input their answers into the device and then send those answers to the server. User input is typically done via a keyboard or touch interface.

[0305] Step 6:

[0306] The server evaluates the user's answer received from the terminal. The server analyzes this answer using an AI model to determine whether it is correct or not. The input here is the user's answer data, and the evaluation result and necessary feedback data are generated as the output. The analyzed data indicates the effect of learning and serves as a basis for determining which issues to present in the next step.

[0307] Step 7:

[0308] The server sends back the feedback generated to the terminal. This is a process of providing appropriate feedback on the user's answer and distributing the feedback data to the terminal. The server uses natural language generation technology as needed to send feedback that suits each user's needs.

[0309] Step 8:

[0310] The terminal displays the feedback sent from the server and provides immediate feedback to the user. The terminal visually displays the feedback on the screen and provides information for the user to refer to when choosing the next step. The display of the feedback helps the educator feel their own progress and clarify the next learning step.

[0311] (Application Example 1)

[0312] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0313] In modern education systems, providing individually optimized learning experiences is difficult, and there is a need to automatically generate and provide effective assignments tailored to each learner's interests and proficiency level. Furthermore, there is a desire for a system that allows learners to easily access appropriate content in areas of interest and learn in depth at their own pace.

[0314] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0315] In this invention, the server includes a storage means for accumulating information on individual learners, a processing means for generating educational tasks suitable for individual learners using a generative model, a means for providing a user interface for displaying the generated educational tasks, and a means for selecting and delivering educational content in specific fields based on the user's interests. This enables learners to progress through their learning at their own pace, step by step, while gaining a deep understanding of specific educational fields that match their interests.

[0316] "Individual learner information" refers to records that include data on a specific learner's history, progress, and interests.

[0317] "Memory means" refers to technical means of storing and managing learner information using databases and storage devices.

[0318] A "generative model" is an algorithm or program that uses generative AI technology to automatically generate the most suitable tasks and content for learners.

[0319] "Educational assignments" refer to practice problems or learning content with specific educational objectives, provided according to the learner's abilities and progress.

[0320] "Processing means" refers to functions that provide learners with tasks and information generated through calculations and data manipulation performed by servers and computer systems.

[0321] A "user interface" is an interface provided to learners for viewing and manipulating information when working on assignments.

[0322] "Means of selecting and delivering educational content in specific fields based on interests" refers to a technical mechanism that analyzes learners' past history and interests, selects highly relevant educational content based on that analysis, and delivers it to the learners.

[0323] This invention is a system for providing educational content tailored to individual learners. The core of the system is a server that stores learner information and generates appropriate tasks using a generative AI model. The server leverages Python and machine learning frameworks such as TensorFlow or PyTorch to analyze learning history and interests. The generative model automatically generates personalized learning tasks.

[0324] The device receives assignments sent from the server via an application developed in Swift (iOS) or Kotlin (Android) and displays them in a user interface. Learners use this interface to solve the assignments and input their answers into the device. The device sends the user's input to the server in real time and updates the progress information.

[0325] Users can select specific learning areas of interest (such as history or science) via the screen on their device. If they have questions, they can ask them via chat through a conversational program. The server responds to these inquiries using natural language processing and provides appropriate feedback.

[0326] As a concrete example, if a user wants to learn about "Medieval European History," the prompt would be: "The user wishes to learn history. Their current knowledge level is intermediate. Please provide content related to medieval Europe." Based on this prompt, the server would provide corresponding educational materials and quizzes. This process allows learners to gradually expand their knowledge according to their progress.

[0327] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0328] Step 1:

[0329] The server retrieves learner information from a database. This information includes past assignment history, progress, and areas of interest. The input is the learner ID, and the output is the corresponding learner's information data. Based on this data, the server prepares to generate personalized assignments in the next step.

[0330] Step 2:

[0331] The server analyzes learner information obtained using a generative AI model and generates appropriate educational tasks. The input is the learner information obtained in step 1, and the output is a personalized set of tasks. In this process, a machine learning algorithm selects tasks that match each learner's proficiency level and interests.

[0332] Step 3:

[0333] The server sends the generated set of tasks to the terminal. The terminal receives this information and displays the tasks on the user's interface. The input is the set of tasks, and the output is the visual information displayed on the user interface. This prepares the user to work on the tasks.

[0334] Step 4:

[0335] The user works on a task provided on the device's screen and enters their answer. The input is the answer data entered by the user, and the output is the device's response completion status. In this step, once the user has completed the answer, the device automatically sends that information to the server.

[0336] Step 5:

[0337] The server evaluates the response data received from the terminal and generates feedback. The input is the user's response data, and the output is the evaluation result and feedback information. This process uses an evaluation algorithm that compares the response with correct answer data to suggest appropriate areas for improvement to the user.

[0338] Step 6:

[0339] The terminal displays the evaluation results and feedback received from the server on the user interface. The input is the evaluation results and feedback information, and the output is the information visually presented to the user. This allows the user to check their progress and decide on the next learning step.

[0340] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0341] This invention provides a system that offers a more personalized learning experience by combining generative AI technology and an emotion recognition engine. This system evaluates the progress of each learner, generates appropriate learning tasks, and further analyzes the learner's emotional state to optimize the learning process.

[0342] The server stores and manages learner progress information in a database. Using an AI model, it generates customized learning tasks based on the learner's skill level and past learning history. These tasks are delivered to the device in real time.

[0343] The terminal displays learning assignments received from the server on its user interface, providing an environment for learners to work on the assignments. It also responds to learners' questions in natural language through an interactive agent. Furthermore, the terminal uses an emotion engine to analyze the user's emotions in real time from their facial expressions and voice, and transmits this information to the server.

[0344] The emotion engine analyzes learners' motivation, concentration, and stress levels as they work on tasks. The server receives this emotion data and generates feedback, such as adjusting the difficulty of the tasks or sending encouraging messages.

[0345] As a concrete example, let's say a user is learning a new programming language. The server generates a "loop structure" task based on the user's past learning history. The terminal displays this task, and the user works on it. If the emotion engine analyzes that the user is stuck, the server provides more hints for the task or offers encouraging messages through the terminal. In this way, the user can learn in an emotionally sensitive environment.

[0346] This system enhances the quality of learning and supports more efficient knowledge retention by taking user emotions into consideration.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The user logs into the system via a terminal. The terminal displays an interface for entering a username and password, and sends the user's input to the server.

[0350] Step 2:

[0351] The server compares the received username and password with the database to authenticate the user. If authentication is successful, it issues a session ID and sends the necessary information back to the terminal.

[0352] Step 3:

[0353] The server uses an AI model to generate appropriate learning tasks based on the user's learning history and progress. This task information is then sent to the user's device.

[0354] Step 4:

[0355] The terminal displays learning assignments received from the server in the user interface. These assignments include detailed information and hints.

[0356] Step 5:

[0357] Users work on learning tasks displayed on their device. They can think of solutions and, if necessary, use a conversational agent to ask questions.

[0358] Step 6:

[0359] The device uses a built-in emotion engine to analyze emotional data in real time from the user's facial expressions and voice, and sends the user's current emotional state to the server.

[0360] Step 7:

[0361] Once the user completes the task, they enter the solution into the device. The device then sends the entered data to the server.

[0362] Step 8:

[0363] The server evaluates the user's solution and generates feedback using an AI model. It takes data from the emotion engine into account and adjusts the difficulty of the task and the content of the feedback as needed.

[0364] Step 9:

[0365] The terminal displays feedback received from the server to the user. This feedback includes advice based on learning progress and information about the next steps.

[0366] Step 10:

[0367] The user reviews the feedback and decides to proceed to the next learning task. The device notifies the server of this decision and requests a new learning task.

[0368] Step 11:

[0369] The server updates the user's progress information in the database and maintains a system-wide learning record. It terminates the user's session as needed.

[0370] (Example 2)

[0371] Next, we will describe Example 2. 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".

[0372] Conventional learning support systems have difficulty providing individualized learning experiences that fully consider the learner's progress and emotional state, and they also have the challenge of not being able to flexibly adjust the system to maximize learning effectiveness. The present invention aims to solve these problems and provide a more effective and individualized learning environment.

[0373] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0374] In this invention, the server includes means for storing individual learner progress data in a recording device, means for generating learning content suitable for individual learners using generative AI, and means for adjusting the difficulty level of the learning content and generating encouraging messages based on emotional data. This enables flexible and effective learning support for individual learners.

[0375] An "individual learner" refers to each user of the system who is identified based on specific conditions and needs.

[0376] "Progress data" refers to information that shows how far a learner has progressed with a particular task or learning content.

[0377] A "recording device" is a system component that stores, manages, and keeps data available for later use.

[0378] "Generative AI" is an artificial intelligence technology that automatically generates new data or solutions based on specific inputs or conditions.

[0379] "Learning content" refers to the specific tasks, topics, and concepts that learners are expected to study.

[0380] An "information display device" is a device or system component that presents information visually or audibly through a user interface.

[0381] "Answer" refers to the solution or response that a learner provides to a task or question.

[0382] A "report" refers to information about evaluations and feedback generated based on learners' answers.

[0383] A "sensing device" is a device that receives physical or digital stimuli and collects data on emotions and situations.

[0384] "Emotional data" refers to information recorded to represent the emotional state of learners.

[0385] "Difficulty level adjustment" is the process of changing the complexity and ease of learning content according to the learner's level.

[0386] "Messages of encouragement" are positive feedback and words of encouragement provided to improve learners' motivation.

[0387] This invention aims to provide a flexible learning environment that takes into account the learner's progress and emotional state, as an individualized learning support system. The entire system consists of a server, terminals, and a user interface.

[0388] server

[0389] The server's primary role is to manage learners' progress data. This involves using a recording device to store information in a database. The server can use generative AI to generate the most appropriate learning content based on the learner's past learning history and skill assessment. A "generative AI model" is generally used as the model for the generative AI.

[0390] As a concrete example, in a scenario where a learner is learning a new programming language, the server prompts the AI ​​with the statement, "Generate an intermediate loop problem in the programming language the user is learning," and then generates an appropriate problem.

[0391] terminal

[0392] The terminal's role is to display learning content delivered from the server to the learner. The terminal is equipped with an information display device, allowing users to work on assignments in real time. Furthermore, the terminal has the ability to respond to user questions in natural language via a conversational agent. In addition, the terminal has a built-in sensing device that collects the user's facial expressions and voice during learning, enabling real-time analysis of emotional data.

[0393] User

[0394] The user is central to this system, and can progress through their learning based on personalized learning content. The user's emotional data is analyzed by the server and used to adjust the difficulty level of the learning content and provide encouraging messages. For example, if a user is stuck on a particular task, the server provides appropriate feedback and additional support to create an environment that maximizes learning efficiency.

[0395] In this way, this system provides learners with learning support tailored to their individual needs, enabling more efficient and effective learning.

[0396] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0397] Step 1:

[0398] The server receives learner progress information as input and stores it in a database. This progress information includes the learner's current level of proficiency and past learning history. By structuring the input progress data and storing it in the database, it is processed into a format that can be used to generate learning assignments later.

[0399] Step 2:

[0400] The server inputs the necessary learning content as prompts into the generating AI model based on progress information stored in the database. A specific example of a prompt is, "Generate customized tasks related to the subject the user is currently learning." The generating AI model generates learning tasks based on this prompt, and the server receives its output.

[0401] Step 3:

[0402] The server adjusts the data format of the generated learning assignments in order to send them to the device. It converts the assignment content into a format that can be delivered in real time before sending it to the device. This conversion makes the data easily receivable on the learner's device.

[0403] Step 4:

[0404] The terminal receives learning assignments sent from the server and visualizes them on the user interface using an information display device. This allows the user to view and interact with the learning assignments on the screen. The terminal also activates an interactive agent to prepare to respond to questions from the learner.

[0405] Step 5:

[0406] As users work on learning tasks, the device uses its built-in sensors to collect facial and audio data. This data is analyzed in real time by emotion analysis software within the device, and the learner's emotional state is determined from the output.

[0407] Step 6:

[0408] The device sends the analyzed emotional state information to the server. The server uses this information to adjust the difficulty level of the learning tasks as needed and to create encouraging messages as required. Based on this output adjustment, any necessary changes or additional support are made.

[0409] Step 7:

[0410] The device receives the adjusted learning content and encouraging messages resent from the server and provides them to the user again through the user interface. This optimizes the user's learning experience according to their individual needs and circumstances.

[0411] (Application Example 2)

[0412] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0413] In the field of elderly care, there is a challenge in providing appropriate care and recreation tailored to the emotional state of individual users. Current technology is insufficient to respond quickly to changes in users' emotions and select and provide appropriate activities accordingly. As a result, there is a potential decline in the quality of life for users.

[0414] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0415] In this invention, the server includes means for storing individual user progress information in a storage device, means for generating activities suitable for individual users using a generative model, and means for analyzing the user's emotional state and providing evaluation and feedback. This makes it possible to provide appropriate care and recreation according to the user's emotional state.

[0416] "Users" refer to individual individuals within the care facilities that use the system.

[0417] "Progress information" refers to a record of data that includes the history of the user's activities and emotional state.

[0418] A "storage device" is a part of physical or digital hardware used to store data.

[0419] A "generative model" is an algorithm that uses artificial intelligence technology to automatically create activities that are suitable for the user.

[0420] "Activities" refer to specific tasks or programs that are carried out as part of the recreation and care provided at nursing care facilities.

[0421] "Human interface" refers to the user interface that allows users and systems to exchange information with each other.

[0422] "Emotional state" refers to the psychological or emotional condition perceived from the user's facial expressions and voice.

[0423] "Analysis" refers to using collected data to evaluate users' emotional states and activity progress.

[0424] "Feedback" refers to providing users with information and suggestions tailored to their activities and emotional state.

[0425] To implement this invention, a robot deployed in a nursing care facility is used. The robot is equipped with a facial recognition camera and a voice recognition microphone, which collect facial expressions and voice data from the users. This data is then analyzed in real time through an emotion recognition engine to determine the users' emotional state. A specific example of the emotion recognition engine used is Affectiva.

[0426] Next, the server receives the collected data and uses a generative AI model to generate care and recreational activities that are best suited to the user's emotional state. OpenAI's GPT-3 is sometimes used as this generative AI model.

[0427] The generated activities are presented on a human interface via a robot, and users participate. As users engage in the activities, emotional data is continuously collected, evaluated by a server, and adjusted as needed, or encouraging messages are provided as feedback. For example, a suggestion might be made such as, "You seem a bit down lately, so why not enjoy some tea while listening to some calming music today?"

[0428] An example of a prompt might be, "Analyze user A's current emotional state and suggest appropriate relaxation activities."

[0429] This system is expected to provide users with high-quality care that is tailored to their emotions, thereby improving the quality of life for residents in care facilities.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The device uses a facial recognition camera and a microphone for voice recognition to collect the user's facial expressions and voice data. The input is real-time video and audio data, which is sent to an emotion recognition engine for data processing to analyze the user's emotional state. The output is evaluation data indicating the user's emotional state.

[0433] Step 2:

[0434] The server receives emotional state evaluation data sent from the terminal. The input is evaluation data, and based on this, a generative AI model is used to perform data calculations that generate care and recreational activities suitable for the user. The output is the content of the generated activity suggestions.

[0435] Step 3:

[0436] The terminal displays activity suggestions received from the server on its human interface. The input is the activity suggestions from the server, which are displayed in a visually recognizable format for the user. The output is the displayed activity suggestions.

[0437] Step 4:

[0438] The user engages in an activity based on the suggested activity. During this time, the device continuously analyzes the facial and voice data collected again using its emotion recognition engine to obtain emotion data. The input is real-time data from the activity, and the output is the latest emotion evaluation data corresponding to the activity status.

[0439] Step 5:

[0440] The server receives updated sentiment assessment data from the terminal and adjusts the activity suggestions as needed. The input is the latest sentiment assessment data, and the server uses data calculations to modify parts of the activity or generate encouraging messages. The output is the adjusted activity suggestions and feedback messages.

[0441] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0442] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0447] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0448] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0449] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0450] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0451] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0452] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0453] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0454] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0455] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0456] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0457] This invention is a learning system that utilizes generative AI technology to provide appropriate tasks to individual learners and support continuous learning. In the implementation of this system, the server, terminal, and user each play their respective roles.

[0458] The server stores learner progress information and learning history in a database and generates individually customized learning tasks using an AI model. The server provides the generated tasks to the terminal in real time and evaluates and provides feedback on the tasks based on the learner's input. The server also handles natural language communication with the learner through a conversational agent.

[0459] The terminal displays learning assignments received from the server on the user interface, providing an environment where learners can work on the assignments. The terminal also handles the learner's input and sends progress information to the server.

[0460] Users work on tasks displayed on their device and devise solutions. They input the results of their completed tasks into the device and receive feedback. Based on this input, they can determine what task to move on to next. They can also ask questions about anything they don't understand through a conversational agent and receive additional assistance.

[0461] As a concrete example, let's say a user is learning a new programming language. The server generates tasks ranging from basic to advanced based on the user's past learning history. The terminal displays tasks such as "defining variables" and "using functions," prompting the user to solve them. Once the user completes a task, the server evaluates the result and recommends the next step, such as tasks on "conditional branching" or "loop structures." In this way, the user can gradually improve their skills.

[0462] This system aims to allow learners to learn at their own pace and to make learning enjoyable and engaging, like a game.

[0463] The following describes the processing flow.

[0464] Step 1:

[0465] The user logs into the system via a terminal. The terminal provides an interface for entering a username and password and sends the user's input to the server.

[0466] Step 2:

[0467] The server compares the received username and password with the database to perform authentication. If authentication is successful, it issues a session ID to the user and sends the necessary information to the terminal.

[0468] Step 3:

[0469] The server uses an AI model to generate learning tasks tailored to the user based on their learning history. The generated task information is then sent to the user's device.

[0470] Step 4:

[0471] The terminal displays learning assignments received from the server in its user interface. These assignments include detailed explanations and hints.

[0472] Step 5:

[0473] The user works on learning tasks presented on the device. If necessary, they use a conversational agent to ask questions about the learning process and think about solutions.

[0474] Step 6:

[0475] When a user enters a solution to a problem into their device, the device sends that data to the server. The user's input is recorded in a log.

[0476] Step 7:

[0477] The server evaluates the problem based on the user's solution. After analysis by an AI model, it generates feedback results and sends them to the terminal.

[0478] Step 8:

[0479] The terminal displays feedback received from the server to the user. This includes the presentation of new challenges for the next step and advice on areas that need review.

[0480] Step 9:

[0481] The user reviews the feedback and moves on to the next learning task if necessary. The device requests the server to select a new task.

[0482] Step 10:

[0483] The server updates the database with user progress information and records the overall learning status of the system. After the learning session ends, it performs the appropriate logout process.

[0484] (Example 1)

[0485] Next, we will describe Example 1. 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."

[0486] One challenge is that educators have difficulty receiving the most appropriate educational content tailored to each student's level of understanding, hindering effective learning. Traditional education systems lack sufficient materials to accommodate individual learning speeds and comprehension levels, making it difficult for educators to address their own weaknesses. Furthermore, the lack of automation in learning results in wasted time and effort.

[0487] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0488] In this invention, the server includes means for storing individual educators' progress information in an information storage device, means for generating educational tasks suitable for individual educators using a generative artificial intelligence model, and means for analyzing educators' past teaching history and adjusting tasks based on their strengths and weaknesses. This makes it possible for each educator to receive optimal educational tasks tailored to their level of understanding at the appropriate time.

[0489] "Progress information" refers to data that shows what individual educators have achieved in the learning process and the level of proficiency they have developed over time.

[0490] An "information storage device" refers to a recording medium or device that stores data on a computer and makes it accessible later.

[0491] A "generative artificial intelligence model" is a computer model based on machine learning techniques and algorithms used to generate tasks tailored to the needs of educators.

[0492] "Educational challenges" refer to specific problems or tasks that educators must address in order to facilitate learning and skill acquisition.

[0493] An "input display device" refers to a screen or device that allows a user to interact with a computer, and it visually presents tasks and information.

[0494] An "interactive information processing system" refers to a system that exchanges information and answers questions with users through natural language.

[0495] "Achievement level" is an indicator that shows the degree to which educators have gained understanding and skills regarding specific educational tasks or goals.

[0496] The following describes an embodiment for carrying out the present invention. This system involves cooperation between a server, a terminal, and a user to provide an educational program tailored to individual educators.

[0497] Server role:

[0498] The server first records the educator's progress information in an information storage device. A common relational database system is used for this purpose. Next, it utilizes a generative artificial intelligence model to generate educational tasks suitable for the educator. The generative AI model is built using machine learning frameworks such as TensorFlow or PyTorch. The generated educational tasks are sent from the server to the terminal. The server also receives the educator's responses and processes them to provide evaluation and feedback.

[0499] Terminal role:

[0500] The terminal displays educational assignments sent from the server on an input display device. This utilizes web and mobile application frameworks such as React or Flutter. It provides an interface for educators to work on the assignments and is responsible for sending responses to the server.

[0501] User roles:

[0502] The user, or educator, works on educational tasks displayed on the terminal. As a concrete example, consider a scenario where the user is learning a new programming language. In this case, the server generates tasks related to variable definition and function usage based on the user's past history. The user solves these tasks and enters their answers into the terminal. Feedback on the answers is provided in real-time from the server, allowing the user to proceed to the next step.

[0503] An example of a prompt would be, "Generate tasks that reflect the user's past learning history. For example, create a prompt that provides tasks suitable for a user learning the basics of programming." By entering this prompt, the generation AI model will generate tasks customized for the user.

[0504] This invention aims to improve the educational experience by enabling educators to learn at their own pace and according to their level of understanding.

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The server receives input data from educators. This input data includes basic information and past progress information of the educators. The server stores this data in an information storage device and updates the educators' learning history. In this storage process, the data is structured and stored in a database using SQL queries in order to track the educators' progress in detail.

[0508] Step 2:

[0509] The server generates optimal educational tasks using a generative AI model based on saved progress information. The server inputs prompts into the generative AI model, which then generates personalized tasks based on past learning history and current skill level. This model is pre-trained, for example, using TensorFlow, and provides optimal output based on the input prompts.

[0510] Step 3:

[0511] The server sends the generated task to the terminal. The input here is the content of the generated task, and the output is a task delivery data packet to the terminal. This packet is serialized in JSON format and securely sent to the terminal via the HTTP protocol.

[0512] Step 4:

[0513] The terminal displays assignments received from the server on its input display device. The terminal uses a user interface to visually deserialize and display the packets, making the assignments easy for educators to understand intuitively. Here, the assignments are properly displayed on the screen, allowing educators to access them.

[0514] Step 5:

[0515] Users work on tasks displayed on their devices. They input their answers into the device and then send those answers to the server. User input is typically done via a keyboard or touch interface.

[0516] Step 6:

[0517] The server evaluates the user's answers received from the terminal. The server uses an AI model to analyze these answers and determine whether they are correct or incorrect. The input here is the user's answer data, and the output is the evaluation result and any necessary feedback data. The analyzed data demonstrates the effectiveness of the learning process and serves as a basis for deciding which tasks to present in the next step.

[0518] Step 7:

[0519] The server sends the generated feedback back to the device. This is the process of providing appropriate feedback on the user's answer and delivering the feedback data to the device. The server uses natural language generation technology as needed to send feedback tailored to each user's needs.

[0520] Step 8:

[0521] The terminal displays feedback sent from the server, providing immediate feedback to the user. The terminal visually displays the feedback on the screen, providing information to help the user choose the next step. The display of feedback helps educators recognize their own progress and clarify the next learning steps.

[0522] (Application Example 1)

[0523] Next, we will explain Application Example 1. In the following explanation, 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."

[0524] In modern education systems, providing individually optimized learning experiences is difficult, and there is a need to automatically generate and provide effective assignments tailored to each learner's interests and proficiency level. Furthermore, there is a desire for a system that allows learners to easily access appropriate content in areas of interest and learn in depth at their own pace.

[0525] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0526] In this invention, the server includes a storage means for accumulating information on individual learners, a processing means for generating educational tasks suitable for individual learners using a generative model, a means for providing a user interface for displaying the generated educational tasks, and a means for selecting and delivering educational content in specific fields based on the user's interests. This enables learners to progress through their learning at their own pace, step by step, while gaining a deep understanding of specific educational fields that match their interests.

[0527] "Individual learner information" refers to records that include data on a specific learner's history, progress, and interests.

[0528] "Memory means" refers to technical means of storing and managing learner information using databases and storage devices.

[0529] A "generative model" is an algorithm or program that uses generative AI technology to automatically generate the most suitable tasks and content for learners.

[0530] "Educational assignments" refer to practice problems or learning content with specific educational objectives, provided according to the learner's abilities and progress.

[0531] "Processing means" refers to functions that provide learners with tasks and information generated through calculations and data manipulation performed by servers and computer systems.

[0532] A "user interface" is an interface provided to learners for viewing and manipulating information when working on assignments.

[0533] "Means of selecting and delivering educational content in specific fields based on interests" refers to a technical mechanism that analyzes learners' past history and interests, selects highly relevant educational content based on that analysis, and delivers it to the learners.

[0534] This invention is a system for providing educational content tailored to individual learners. The core of the system is a server that stores learner information and generates appropriate tasks using a generative AI model. The server leverages Python and machine learning frameworks such as TensorFlow or PyTorch to analyze learning history and interests. The generative model automatically generates personalized learning tasks.

[0535] The device receives assignments sent from the server via an application developed in Swift (iOS) or Kotlin (Android) and displays them in a user interface. Learners use this interface to solve the assignments and input their answers into the device. The device sends the user's input to the server in real time and updates the progress information.

[0536] Users can select specific learning areas of interest (such as history or science) via the screen on their device. If they have questions, they can ask them via chat through a conversational program. The server responds to these inquiries using natural language processing and provides appropriate feedback.

[0537] As a concrete example, if a user wants to learn about "Medieval European History," the prompt would be: "The user wishes to learn history. Their current knowledge level is intermediate. Please provide content related to medieval Europe." Based on this prompt, the server would provide corresponding educational materials and quizzes. This process allows learners to gradually expand their knowledge according to their progress.

[0538] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0539] Step 1:

[0540] The server retrieves learner information from a database. This information includes past assignment history, progress, and areas of interest. The input is the learner ID, and the output is the corresponding learner's information data. Based on this data, the server prepares to generate personalized assignments in the next step.

[0541] Step 2:

[0542] The server analyzes learner information obtained using a generative AI model and generates appropriate educational tasks. The input is the learner information obtained in step 1, and the output is a personalized set of tasks. In this process, a machine learning algorithm selects tasks that match each learner's proficiency level and interests.

[0543] Step 3:

[0544] The server sends the generated set of tasks to the terminal. The terminal receives this information and displays the tasks on the user's interface. The input is the set of tasks, and the output is the visual information displayed on the user interface. This prepares the user to work on the tasks.

[0545] Step 4:

[0546] The user works on a task provided on the device's screen and enters their answer. The input is the answer data entered by the user, and the output is the device's response completion status. In this step, once the user has completed the answer, the device automatically sends that information to the server.

[0547] Step 5:

[0548] The server evaluates the response data received from the terminal and generates feedback. The input is the user's response data, and the output is the evaluation result and feedback information. This process uses an evaluation algorithm that compares the response with correct answer data to suggest appropriate areas for improvement to the user.

[0549] Step 6:

[0550] The terminal displays the evaluation results and feedback received from the server on the user interface. The input is the evaluation results and feedback information, and the output is the information visually presented to the user. This allows the user to check their progress and decide on the next learning step.

[0551] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0552] This invention provides a system that offers a more personalized learning experience by combining generative AI technology and an emotion recognition engine. This system evaluates the progress of each learner, generates appropriate learning tasks, and further analyzes the learner's emotional state to optimize the learning process.

[0553] The server stores and manages learner progress information in a database. Using an AI model, it generates customized learning tasks based on the learner's skill level and past learning history. These tasks are delivered to the device in real time.

[0554] The terminal displays learning assignments received from the server on its user interface, providing an environment for learners to work on the assignments. It also responds to learners' questions in natural language through an interactive agent. Furthermore, the terminal uses an emotion engine to analyze the user's emotions in real time from their facial expressions and voice, and transmits this information to the server.

[0555] The emotion engine analyzes learners' motivation, concentration, and stress levels as they work on tasks. The server receives this emotion data and generates feedback, such as adjusting the difficulty of the tasks or sending encouraging messages.

[0556] As a concrete example, let's say a user is learning a new programming language. The server generates a "loop structure" task based on the user's past learning history. The terminal displays this task, and the user works on it. If the emotion engine analyzes that the user is stuck, the server provides more hints for the task or offers encouraging messages through the terminal. In this way, the user can learn in an emotionally sensitive environment.

[0557] This system enhances the quality of learning and supports more efficient knowledge retention by taking user emotions into consideration.

[0558] The following describes the processing flow.

[0559] Step 1:

[0560] The user logs into the system via a terminal. The terminal displays an interface for entering a username and password, and sends the user's input to the server.

[0561] Step 2:

[0562] The server compares the received username and password with the database to authenticate the user. If authentication is successful, it issues a session ID and sends the necessary information back to the terminal.

[0563] Step 3:

[0564] The server uses an AI model to generate appropriate learning tasks based on the user's learning history and progress. This task information is then sent to the user's device.

[0565] Step 4:

[0566] The terminal displays learning assignments received from the server in the user interface. These assignments include detailed information and hints.

[0567] Step 5:

[0568] Users work on learning tasks displayed on their device. They can think of solutions and, if necessary, use a conversational agent to ask questions.

[0569] Step 6:

[0570] The device uses a built-in emotion engine to analyze emotional data in real time from the user's facial expressions and voice, and sends the user's current emotional state to the server.

[0571] Step 7:

[0572] Once the user completes the task, they enter the solution into the device. The device then sends the entered data to the server.

[0573] Step 8:

[0574] The server evaluates the user's solution and generates feedback using an AI model. It takes data from the emotion engine into account and adjusts the difficulty of the task and the content of the feedback as needed.

[0575] Step 9:

[0576] The terminal displays feedback received from the server to the user. This feedback includes advice based on learning progress and information about the next steps.

[0577] Step 10:

[0578] The user reviews the feedback and decides to proceed to the next learning task. The device notifies the server of this decision and requests a new learning task.

[0579] Step 11:

[0580] The server updates the user's progress information in the database and maintains a system-wide learning record. It terminates the user's session as needed.

[0581] (Example 2)

[0582] Next, we will describe Example 2. 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."

[0583] Conventional learning support systems have difficulty providing individualized learning experiences that fully consider the learner's progress and emotional state, and they also have the challenge of not being able to flexibly adjust the system to maximize learning effectiveness. The present invention aims to solve these problems and provide a more effective and individualized learning environment.

[0584] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0585] In this invention, the server includes means for storing individual learner progress data in a recording device, means for generating learning content suitable for individual learners using generative AI, and means for adjusting the difficulty level of the learning content and generating encouraging messages based on emotional data. This enables flexible and effective learning support for individual learners.

[0586] An "individual learner" refers to each user of the system who is identified based on specific conditions and needs.

[0587] "Progress data" refers to information that shows how far a learner has progressed with a particular task or learning content.

[0588] A "recording device" is a system component that stores, manages, and keeps data available for later use.

[0589] "Generative AI" is an artificial intelligence technology that automatically generates new data or solutions based on specific inputs or conditions.

[0590] "Learning content" refers to the specific tasks, topics, and concepts that learners are expected to study.

[0591] An "information display device" is a device or system component that presents information visually or audibly through a user interface.

[0592] "Answer" refers to the solution or response that a learner provides to a task or question.

[0593] A "report" refers to information about evaluations and feedback generated based on learners' answers.

[0594] A "sensing device" is a device that receives physical or digital stimuli and collects data on emotions and situations.

[0595] "Emotional data" refers to information recorded to represent the emotional state of learners.

[0596] "Difficulty level adjustment" is the process of changing the complexity and ease of learning content according to the learner's level.

[0597] "Messages of encouragement" are positive feedback and words of encouragement provided to improve learners' motivation.

[0598] This invention aims to provide a flexible learning environment that takes into account the learner's progress and emotional state, as an individualized learning support system. The entire system consists of a server, terminals, and a user interface.

[0599] server

[0600] The server's primary role is to manage learners' progress data. This involves using a recording device to store information in a database. The server can use generative AI to generate the most appropriate learning content based on the learner's past learning history and skill assessment. A "generative AI model" is generally used as the model for the generative AI.

[0601] As a concrete example, in a scenario where a learner is learning a new programming language, the server prompts the AI ​​with the statement, "Generate an intermediate loop problem in the programming language the user is learning," and then generates an appropriate problem.

[0602] terminal

[0603] The terminal's role is to display learning content delivered from the server to the learner. The terminal is equipped with an information display device, allowing users to work on assignments in real time. Furthermore, the terminal has the ability to respond to user questions in natural language via a conversational agent. In addition, the terminal has a built-in sensing device that collects the user's facial expressions and voice during learning, enabling real-time analysis of emotional data.

[0604] User

[0605] The user is central to this system, and can progress through their learning based on personalized learning content. The user's emotional data is analyzed by the server and used to adjust the difficulty level of the learning content and provide encouraging messages. For example, if a user is stuck on a particular task, the server provides appropriate feedback and additional support to create an environment that maximizes learning efficiency.

[0606] In this way, this system provides learners with learning support tailored to their individual needs, enabling more efficient and effective learning.

[0607] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0608] Step 1:

[0609] The server receives learner progress information as input and stores it in a database. This progress information includes the learner's current level of proficiency and past learning history. By structuring the input progress data and storing it in the database, it is processed into a format that can be used to generate learning assignments later.

[0610] Step 2:

[0611] The server inputs the necessary learning content as prompts into the generating AI model based on progress information stored in the database. A specific example of a prompt is, "Generate customized tasks related to the subject the user is currently learning." The generating AI model generates learning tasks based on this prompt, and the server receives its output.

[0612] Step 3:

[0613] The server adjusts the data format of the generated learning assignments in order to send them to the device. It converts the assignment content into a format that can be delivered in real time before sending it to the device. This conversion makes the data easily receivable on the learner's device.

[0614] Step 4:

[0615] The terminal receives learning assignments sent from the server and visualizes them on the user interface using an information display device. This allows the user to view and interact with the learning assignments on the screen. The terminal also activates an interactive agent to prepare to respond to questions from the learner.

[0616] Step 5:

[0617] As users work on learning tasks, the device uses its built-in sensors to collect facial and audio data. This data is analyzed in real time by emotion analysis software within the device, and the learner's emotional state is determined from the output.

[0618] Step 6:

[0619] The device sends the analyzed emotional state information to the server. The server uses this information to adjust the difficulty level of the learning tasks as needed and to create encouraging messages as required. Based on this output adjustment, any necessary changes or additional support are made.

[0620] Step 7:

[0621] The device receives the adjusted learning content and encouraging messages resent from the server and provides them to the user again through the user interface. This optimizes the user's learning experience according to their individual needs and circumstances.

[0622] (Application Example 2)

[0623] Next, we will explain application example 2. In the following explanation, 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."

[0624] In the field of elderly care, there is a challenge in providing appropriate care and recreation tailored to the emotional state of individual users. Current technology is insufficient to respond quickly to changes in users' emotions and select and provide appropriate activities accordingly. As a result, there is a potential decline in the quality of life for users.

[0625] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0626] In this invention, the server includes means for storing individual user progress information in a storage device, means for generating activities suitable for individual users using a generative model, and means for analyzing the user's emotional state and providing evaluation and feedback. This makes it possible to provide appropriate care and recreation according to the user's emotional state.

[0627] "Users" refer to individual individuals within the care facilities that use the system.

[0628] "Progress information" refers to a record of data that includes the history of the user's activities and emotional state.

[0629] A "storage device" is a part of physical or digital hardware used to store data.

[0630] A "generative model" is an algorithm that uses artificial intelligence technology to automatically create activities that are suitable for the user.

[0631] "Activities" refer to specific tasks or programs that are carried out as part of the recreation and care provided at nursing care facilities.

[0632] "Human interface" refers to the user interface that allows users and systems to exchange information with each other.

[0633] "Emotional state" refers to the psychological or emotional condition perceived from the user's facial expressions and voice.

[0634] "Analysis" refers to using collected data to evaluate users' emotional states and activity progress.

[0635] "Feedback" refers to providing users with information and suggestions tailored to their activities and emotional state.

[0636] To implement this invention, a robot deployed in a nursing care facility is used. The robot is equipped with a facial recognition camera and a voice recognition microphone, which collect facial expressions and voice data from the users. This data is then analyzed in real time through an emotion recognition engine to determine the users' emotional state. A specific example of the emotion recognition engine used is Affectiva.

[0637] Next, the server receives the collected data and uses a generative AI model to generate care and recreational activities that are best suited to the user's emotional state. OpenAI's GPT-3 is sometimes used as this generative AI model.

[0638] The generated activities are presented on a human interface via a robot, and users participate. As users engage in the activities, emotional data is continuously collected, evaluated by a server, and adjusted as needed, or encouraging messages are provided as feedback. For example, a suggestion might be made such as, "You seem a bit down lately, so why not enjoy some tea while listening to some calming music today?"

[0639] An example of a prompt might be, "Analyze user A's current emotional state and suggest appropriate relaxation activities."

[0640] This system is expected to provide users with high-quality care that is tailored to their emotions, thereby improving the quality of life for residents in care facilities.

[0641] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0642] Step 1:

[0643] The device uses a facial recognition camera and a microphone for voice recognition to collect the user's facial expressions and voice data. The input is real-time video and audio data, which is sent to an emotion recognition engine for data processing to analyze the user's emotional state. The output is evaluation data indicating the user's emotional state.

[0644] Step 2:

[0645] The server receives emotional state evaluation data sent from the terminal. The input is evaluation data, and based on this, a generative AI model is used to perform data calculations that generate care and recreational activities suitable for the user. The output is the content of the generated activity suggestions.

[0646] Step 3:

[0647] The terminal displays activity suggestions received from the server on its human interface. The input is the activity suggestions from the server, which are displayed in a visually recognizable format for the user. The output is the displayed activity suggestions.

[0648] Step 4:

[0649] The user engages in an activity based on the suggested activity. During this time, the device continuously analyzes the facial and voice data collected again using its emotion recognition engine to obtain emotion data. The input is real-time data from the activity, and the output is the latest emotion evaluation data corresponding to the activity status.

[0650] Step 5:

[0651] The server receives updated sentiment assessment data from the terminal and adjusts the activity suggestions as needed. The input is the latest sentiment assessment data, and the server uses data calculations to modify parts of the activity or generate encouraging messages. The output is the adjusted activity suggestions and feedback messages.

[0652] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0653] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0654] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0655] [Fourth Embodiment]

[0656] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0657] As shown in Figure 7, the 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.

[0658] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0659] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0660] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0661] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0662] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0663] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0664] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0665] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0666] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0667] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0668] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] This invention is a learning system that utilizes generative AI technology to provide appropriate tasks to individual learners and support continuous learning. In the implementation of this system, the server, terminal, and user each play their respective roles.

[0670] The server stores learner progress information and learning history in a database and generates individually customized learning tasks using an AI model. The server provides the generated tasks to the terminal in real time and evaluates and provides feedback on the tasks based on the learner's input. The server also handles natural language communication with the learner through a conversational agent.

[0671] The terminal displays learning assignments received from the server on the user interface, providing an environment where learners can work on the assignments. The terminal also handles the learner's input and sends progress information to the server.

[0672] Users work on tasks displayed on their device and devise solutions. They input the results of their completed tasks into the device and receive feedback. Based on this input, they can determine what task to move on to next. They can also ask questions about anything they don't understand through a conversational agent and receive additional assistance.

[0673] As a concrete example, let's say a user is learning a new programming language. The server generates tasks ranging from basic to advanced based on the user's past learning history. The terminal displays tasks such as "defining variables" and "using functions," prompting the user to solve them. Once the user completes a task, the server evaluates the result and recommends the next step, such as tasks on "conditional branching" or "loop structures." In this way, the user can gradually improve their skills.

[0674] This system aims to allow learners to learn at their own pace and to make learning enjoyable and engaging, like a game.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The user logs into the system via a terminal. The terminal provides an interface for entering a username and password and sends the user's input to the server.

[0678] Step 2:

[0679] The server compares the received username and password with the database to perform authentication. If authentication is successful, it issues a session ID to the user and sends the necessary information to the terminal.

[0680] Step 3:

[0681] The server uses an AI model to generate learning tasks tailored to the user based on their learning history. The generated task information is then sent to the user's device.

[0682] Step 4:

[0683] The terminal displays learning assignments received from the server in its user interface. These assignments include detailed explanations and hints.

[0684] Step 5:

[0685] The user works on learning tasks presented on the device. If necessary, they use a conversational agent to ask questions about the learning process and think about solutions.

[0686] Step 6:

[0687] When a user enters a solution to a problem into their device, the device sends that data to the server. The user's input is recorded in a log.

[0688] Step 7:

[0689] The server evaluates the problem based on the user's solution. After analysis by an AI model, it generates feedback results and sends them to the terminal.

[0690] Step 8:

[0691] The terminal displays feedback received from the server to the user. This includes the presentation of new challenges for the next step and advice on areas that need review.

[0692] Step 9:

[0693] The user reviews the feedback and moves on to the next learning task if necessary. The device requests the server to select a new task.

[0694] Step 10:

[0695] The server updates the database with user progress information and records the overall learning status of the system. After the learning session ends, it performs the appropriate logout process.

[0696] (Example 1)

[0697] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] One challenge is that educators have difficulty receiving the most appropriate educational content tailored to each student's level of understanding, hindering effective learning. Traditional education systems lack sufficient materials to accommodate individual learning speeds and comprehension levels, making it difficult for educators to address their own weaknesses. Furthermore, the lack of automation in learning results in wasted time and effort.

[0699] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0700] In this invention, the server includes means for storing individual educators' progress information in an information storage device, means for generating educational tasks suitable for individual educators using a generative artificial intelligence model, and means for analyzing educators' past teaching history and adjusting tasks based on their strengths and weaknesses. This makes it possible for each educator to receive optimal educational tasks tailored to their level of understanding at the appropriate time.

[0701] "Progress information" refers to data that shows what individual educators have achieved in the learning process and the level of proficiency they have developed over time.

[0702] An "information storage device" refers to a recording medium or device that stores data on a computer and makes it accessible later.

[0703] A "generative artificial intelligence model" is a computer model based on machine learning techniques and algorithms used to generate tasks tailored to the needs of educators.

[0704] "Educational challenges" refer to specific problems or tasks that educators must address in order to facilitate learning and skill acquisition.

[0705] An "input display device" refers to a screen or device that allows a user to interact with a computer, and it visually presents tasks and information.

[0706] An "interactive information processing system" refers to a system that exchanges information and answers questions with users through natural language.

[0707] "Achievement level" is an indicator that shows the degree to which educators have gained understanding and skills regarding specific educational tasks or goals.

[0708] The following describes an embodiment for carrying out the present invention. This system involves cooperation between a server, a terminal, and a user to provide an educational program tailored to individual educators.

[0709] Server role:

[0710] The server first records the educator's progress information in an information storage device. A common relational database system is used for this purpose. Next, it utilizes a generative artificial intelligence model to generate educational tasks suitable for the educator. The generative AI model is built using machine learning frameworks such as TensorFlow or PyTorch. The generated educational tasks are sent from the server to the terminal. The server also receives the educator's responses and processes them to provide evaluation and feedback.

[0711] Terminal role:

[0712] The terminal displays educational assignments sent from the server on an input display device. This utilizes web and mobile application frameworks such as React or Flutter. It provides an interface for educators to work on the assignments and is responsible for sending responses to the server.

[0713] User roles:

[0714] The user, or educator, works on educational tasks displayed on the terminal. As a concrete example, consider a scenario where the user is learning a new programming language. In this case, the server generates tasks related to variable definition and function usage based on the user's past history. The user solves these tasks and enters their answers into the terminal. Feedback on the answers is provided in real-time from the server, allowing the user to proceed to the next step.

[0715] An example of a prompt would be, "Generate tasks that reflect the user's past learning history. For example, create a prompt that provides tasks suitable for a user learning the basics of programming." By entering this prompt, the generation AI model will generate tasks customized for the user.

[0716] This invention aims to improve the educational experience by enabling educators to learn at their own pace and according to their level of understanding.

[0717] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0718] Step 1:

[0719] The server receives input data from educators. This input data includes basic information and past progress information of the educators. The server stores this data in an information storage device and updates the educators' learning history. In this storage process, the data is structured and stored in a database using SQL queries in order to track the educators' progress in detail.

[0720] Step 2:

[0721] The server generates optimal educational tasks using a generative AI model based on saved progress information. The server inputs prompts into the generative AI model, which then generates personalized tasks based on past learning history and current skill level. This model is pre-trained, for example, using TensorFlow, and provides optimal output based on the input prompts.

[0722] Step 3:

[0723] The server sends the generated task to the terminal. The input here is the content of the generated task, and the output is a task delivery data packet to the terminal. This packet is serialized in JSON format and securely sent to the terminal via the HTTP protocol.

[0724] Step 4:

[0725] The terminal displays assignments received from the server on its input display device. The terminal uses a user interface to visually deserialize and display the packets, making the assignments easy for educators to understand intuitively. Here, the assignments are properly displayed on the screen, allowing educators to access them.

[0726] Step 5:

[0727] Users work on tasks displayed on their devices. They input their answers into the device and then send those answers to the server. User input is typically done via a keyboard or touch interface.

[0728] Step 6:

[0729] The server evaluates the user's answers received from the terminal. The server uses an AI model to analyze these answers and determine whether they are correct or incorrect. The input here is the user's answer data, and the output is the evaluation result and any necessary feedback data. The analyzed data demonstrates the effectiveness of the learning process and serves as a basis for deciding which tasks to present in the next step.

[0730] Step 7:

[0731] The server sends the generated feedback back to the device. This is the process of providing appropriate feedback on the user's answer and delivering the feedback data to the device. The server uses natural language generation technology as needed to send feedback tailored to each user's needs.

[0732] Step 8:

[0733] The terminal displays feedback sent from the server, providing immediate feedback to the user. The terminal visually displays the feedback on the screen, providing information to help the user choose the next step. The display of feedback helps educators recognize their own progress and clarify the next learning steps.

[0734] (Application Example 1)

[0735] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0736] In modern education systems, providing individually optimized learning experiences is difficult, and there is a need to automatically generate and provide effective assignments tailored to each learner's interests and proficiency level. Furthermore, there is a desire for a system that allows learners to easily access appropriate content in areas of interest and learn in depth at their own pace.

[0737] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0738] In this invention, the server includes a storage means for accumulating information on individual learners, a processing means for generating educational tasks suitable for individual learners using a generative model, a means for providing a user interface for displaying the generated educational tasks, and a means for selecting and delivering educational content in specific fields based on the user's interests. This enables learners to progress through their learning at their own pace, step by step, while gaining a deep understanding of specific educational fields that match their interests.

[0739] "Individual learner information" refers to records that include data on a specific learner's history, progress, and interests.

[0740] "Memory means" refers to technical means of storing and managing learner information using databases and storage devices.

[0741] A "generative model" is an algorithm or program that uses generative AI technology to automatically generate the most suitable tasks and content for learners.

[0742] "Educational assignments" refer to practice problems or learning content with specific educational objectives, provided according to the learner's abilities and progress.

[0743] "Processing means" refers to functions that provide learners with tasks and information generated through calculations and data manipulation performed by servers and computer systems.

[0744] A "user interface" is an interface provided to learners for viewing and manipulating information when working on assignments.

[0745] "Means of selecting and delivering educational content in specific fields based on interests" refers to a technical mechanism that analyzes learners' past history and interests, selects highly relevant educational content based on that analysis, and delivers it to the learners.

[0746] This invention is a system for providing educational content tailored to individual learners. The core of the system is a server that stores learner information and generates appropriate tasks using a generative AI model. The server leverages Python and machine learning frameworks such as TensorFlow or PyTorch to analyze learning history and interests. The generative model automatically generates personalized learning tasks.

[0747] The device receives assignments sent from the server via an application developed in Swift (iOS) or Kotlin (Android) and displays them in a user interface. Learners use this interface to solve the assignments and input their answers into the device. The device sends the user's input to the server in real time and updates the progress information.

[0748] Users can select specific learning areas of interest (such as history or science) via the screen on their device. If they have questions, they can ask them via chat through a conversational program. The server responds to these inquiries using natural language processing and provides appropriate feedback.

[0749] As a concrete example, if a user wants to learn about "Medieval European History," the prompt would be: "The user wishes to learn history. Their current knowledge level is intermediate. Please provide content related to medieval Europe." Based on this prompt, the server would provide corresponding educational materials and quizzes. This process allows learners to gradually expand their knowledge according to their progress.

[0750] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0751] Step 1:

[0752] The server retrieves learner information from a database. This information includes past assignment history, progress, and areas of interest. The input is the learner ID, and the output is the corresponding learner's information data. Based on this data, the server prepares to generate personalized assignments in the next step.

[0753] Step 2:

[0754] The server analyzes learner information obtained using a generative AI model and generates appropriate educational tasks. The input is the learner information obtained in step 1, and the output is a personalized set of tasks. In this process, a machine learning algorithm selects tasks that match each learner's proficiency level and interests.

[0755] Step 3:

[0756] The server sends the generated set of tasks to the terminal. The terminal receives this information and displays the tasks on the user's interface. The input is the set of tasks, and the output is the visual information displayed on the user interface. This prepares the user to work on the tasks.

[0757] Step 4:

[0758] The user works on a task provided on the device's screen and enters their answer. The input is the answer data entered by the user, and the output is the device's response completion status. In this step, once the user has completed the answer, the device automatically sends that information to the server.

[0759] Step 5:

[0760] The server evaluates the response data received from the terminal and generates feedback. The input is the user's response data, and the output is the evaluation result and feedback information. This process uses an evaluation algorithm that compares the response with correct answer data to suggest appropriate areas for improvement to the user.

[0761] Step 6:

[0762] The terminal displays the evaluation results and feedback received from the server on the user interface. The input is the evaluation results and feedback information, and the output is the information visually presented to the user. This allows the user to check their progress and decide on the next learning step.

[0763] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0764] This invention provides a system that offers a more personalized learning experience by combining generative AI technology and an emotion recognition engine. This system evaluates the progress of each learner, generates appropriate learning tasks, and further analyzes the learner's emotional state to optimize the learning process.

[0765] The server stores and manages learner progress information in a database. Using an AI model, it generates customized learning tasks based on the learner's skill level and past learning history. These tasks are delivered to the device in real time.

[0766] The terminal displays learning assignments received from the server on its user interface, providing an environment for learners to work on the assignments. It also responds to learners' questions in natural language through an interactive agent. Furthermore, the terminal uses an emotion engine to analyze the user's emotions in real time from their facial expressions and voice, and transmits this information to the server.

[0767] The emotion engine analyzes learners' motivation, concentration, and stress levels as they work on tasks. The server receives this emotion data and generates feedback, such as adjusting the difficulty of the tasks or sending encouraging messages.

[0768] As a concrete example, let's say a user is learning a new programming language. The server generates a "loop structure" task based on the user's past learning history. The terminal displays this task, and the user works on it. If the emotion engine analyzes that the user is stuck, the server provides more hints for the task or offers encouraging messages through the terminal. In this way, the user can learn in an emotionally sensitive environment.

[0769] This system enhances the quality of learning and supports more efficient knowledge retention by taking user emotions into consideration.

[0770] The following describes the processing flow.

[0771] Step 1:

[0772] The user logs into the system via a terminal. The terminal displays an interface for entering a username and password, and sends the user's input to the server.

[0773] Step 2:

[0774] The server compares the received username and password with the database to authenticate the user. If authentication is successful, it issues a session ID and sends the necessary information back to the terminal.

[0775] Step 3:

[0776] The server uses an AI model to generate appropriate learning tasks based on the user's learning history and progress. This task information is then sent to the user's device.

[0777] Step 4:

[0778] The terminal displays learning assignments received from the server in the user interface. These assignments include detailed information and hints.

[0779] Step 5:

[0780] Users work on learning tasks displayed on their device. They can think of solutions and, if necessary, use a conversational agent to ask questions.

[0781] Step 6:

[0782] The device uses a built-in emotion engine to analyze emotional data in real time from the user's facial expressions and voice, and sends the user's current emotional state to the server.

[0783] Step 7:

[0784] Once the user completes the task, they enter the solution into the device. The device then sends the entered data to the server.

[0785] Step 8:

[0786] The server evaluates the user's solution and generates feedback using an AI model. It takes data from the emotion engine into account and adjusts the difficulty of the task and the content of the feedback as needed.

[0787] Step 9:

[0788] The terminal displays feedback received from the server to the user. This feedback includes advice based on learning progress and information about the next steps.

[0789] Step 10:

[0790] The user reviews the feedback and decides to proceed to the next learning task. The device notifies the server of this decision and requests a new learning task.

[0791] Step 11:

[0792] The server updates the user's progress information in the database and maintains a system-wide learning record. It terminates the user's session as needed.

[0793] (Example 2)

[0794] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0795] Conventional learning support systems have difficulty providing individualized learning experiences that fully consider the learner's progress and emotional state, and they also have the challenge of not being able to flexibly adjust the system to maximize learning effectiveness. The present invention aims to solve these problems and provide a more effective and individualized learning environment.

[0796] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0797] In this invention, the server includes means for storing individual learner progress data in a recording device, means for generating learning content suitable for individual learners using generative AI, and means for adjusting the difficulty level of the learning content and generating encouraging messages based on emotional data. This enables flexible and effective learning support for individual learners.

[0798] An "individual learner" refers to each user of the system who is identified based on specific conditions and needs.

[0799] "Progress data" refers to information that shows how far a learner has progressed with a particular task or learning content.

[0800] A "recording device" is a system component that stores, manages, and keeps data available for later use.

[0801] "Generative AI" is an artificial intelligence technology that automatically generates new data or solutions based on specific inputs or conditions.

[0802] "Learning content" refers to the specific tasks, topics, and concepts that learners are expected to study.

[0803] An "information display device" is a device or system component that presents information visually or audibly through a user interface.

[0804] "Answer" refers to the solution or response that a learner provides to a task or question.

[0805] A "report" refers to information about evaluations and feedback generated based on learners' answers.

[0806] A "sensing device" is a device that receives physical or digital stimuli and collects data on emotions and situations.

[0807] "Emotional data" refers to information recorded to represent the emotional state of learners.

[0808] "Difficulty level adjustment" is the process of changing the complexity and ease of learning content according to the learner's level.

[0809] "Messages of encouragement" are positive feedback and words of encouragement provided to improve learners' motivation.

[0810] This invention aims to provide a flexible learning environment that takes into account the learner's progress and emotional state, as an individualized learning support system. The entire system consists of a server, terminals, and a user interface.

[0811] server

[0812] The server's primary role is to manage learners' progress data. This involves using a recording device to store information in a database. The server can use generative AI to generate the most appropriate learning content based on the learner's past learning history and skill assessment. A "generative AI model" is generally used as the model for the generative AI.

[0813] As a concrete example, in a scenario where a learner is learning a new programming language, the server prompts the AI ​​with the statement, "Generate an intermediate loop problem in the programming language the user is learning," and then generates an appropriate problem.

[0814] terminal

[0815] The terminal's role is to display learning content delivered from the server to the learner. The terminal is equipped with an information display device, allowing users to work on assignments in real time. Furthermore, the terminal has the ability to respond to user questions in natural language via a conversational agent. In addition, the terminal has a built-in sensing device that collects the user's facial expressions and voice during learning, enabling real-time analysis of emotional data.

[0816] User

[0817] The user is central to this system, and can progress through their learning based on personalized learning content. The user's emotional data is analyzed by the server and used to adjust the difficulty level of the learning content and provide encouraging messages. For example, if a user is stuck on a particular task, the server provides appropriate feedback and additional support to create an environment that maximizes learning efficiency.

[0818] In this way, this system provides learners with learning support tailored to their individual needs, enabling more efficient and effective learning.

[0819] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0820] Step 1:

[0821] The server receives learner progress information as input and stores it in a database. This progress information includes the learner's current level of proficiency and past learning history. By structuring the input progress data and storing it in the database, it is processed into a format that can be used to generate learning assignments later.

[0822] Step 2:

[0823] The server inputs the necessary learning content as prompts into the generating AI model based on progress information stored in the database. A specific example of a prompt is, "Generate customized tasks related to the subject the user is currently learning." The generating AI model generates learning tasks based on this prompt, and the server receives its output.

[0824] Step 3:

[0825] The server adjusts the data format of the generated learning assignments in order to send them to the device. It converts the assignment content into a format that can be delivered in real time before sending it to the device. This conversion makes the data easily receivable on the learner's device.

[0826] Step 4:

[0827] The terminal receives learning assignments sent from the server and visualizes them on the user interface using an information display device. This allows the user to view and interact with the learning assignments on the screen. The terminal also activates an interactive agent to prepare to respond to questions from the learner.

[0828] Step 5:

[0829] As users work on learning tasks, the device uses its built-in sensors to collect facial and audio data. This data is analyzed in real time by emotion analysis software within the device, and the learner's emotional state is determined from the output.

[0830] Step 6:

[0831] The device sends the analyzed emotional state information to the server. The server uses this information to adjust the difficulty level of the learning tasks as needed and to create encouraging messages as required. Based on this output adjustment, any necessary changes or additional support are made.

[0832] Step 7:

[0833] The device receives the adjusted learning content and encouraging messages resent from the server and provides them to the user again through the user interface. This optimizes the user's learning experience according to their individual needs and circumstances.

[0834] (Application Example 2)

[0835] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0836] In the field of elderly care, there is a challenge in providing appropriate care and recreation tailored to the emotional state of individual users. Current technology is insufficient to respond quickly to changes in users' emotions and select and provide appropriate activities accordingly. As a result, there is a potential decline in the quality of life for users.

[0837] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0838] In this invention, the server includes means for storing individual user progress information in a storage device, means for generating activities suitable for individual users using a generative model, and means for analyzing the user's emotional state and providing evaluation and feedback. This makes it possible to provide appropriate care and recreation according to the user's emotional state.

[0839] "Users" refer to individual individuals within the care facilities that use the system.

[0840] "Progress information" refers to a record of data that includes the history of the user's activities and emotional state.

[0841] A "storage device" is a part of physical or digital hardware used to store data.

[0842] A "generative model" is an algorithm that uses artificial intelligence technology to automatically create activities that are suitable for the user.

[0843] "Activities" refer to specific tasks or programs that are carried out as part of the recreation and care provided at nursing care facilities.

[0844] "Human interface" refers to the user interface that allows users and systems to exchange information with each other.

[0845] "Emotional state" refers to the psychological or emotional condition perceived from the user's facial expressions and voice.

[0846] "Analysis" refers to using collected data to evaluate users' emotional states and activity progress.

[0847] "Feedback" refers to providing users with information and suggestions tailored to their activities and emotional state.

[0848] To implement this invention, a robot deployed in a nursing care facility is used. The robot is equipped with a facial recognition camera and a voice recognition microphone, which collect facial expressions and voice data from the users. This data is then analyzed in real time through an emotion recognition engine to determine the users' emotional state. A specific example of the emotion recognition engine used is Affectiva.

[0849] Next, the server receives the collected data and uses a generative AI model to generate care and recreational activities that are best suited to the user's emotional state. OpenAI's GPT-3 is sometimes used as this generative AI model.

[0850] The generated activities are presented on a human interface via a robot, and users participate. As users engage in the activities, emotional data is continuously collected, evaluated by a server, and adjusted as needed, or encouraging messages are provided as feedback. For example, a suggestion might be made such as, "You seem a bit down lately, so why not enjoy some tea while listening to some calming music today?"

[0851] An example of a prompt might be, "Analyze user A's current emotional state and suggest appropriate relaxation activities."

[0852] This system is expected to provide users with high-quality care that is tailored to their emotions, thereby improving the quality of life for residents in care facilities.

[0853] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0854] Step 1:

[0855] The device uses a facial recognition camera and a microphone for voice recognition to collect the user's facial expressions and voice data. The input is real-time video and audio data, which is sent to an emotion recognition engine for data processing to analyze the user's emotional state. The output is evaluation data indicating the user's emotional state.

[0856] Step 2:

[0857] The server receives emotional state evaluation data sent from the terminal. The input is evaluation data, and based on this, a generative AI model is used to perform data calculations that generate care and recreational activities suitable for the user. The output is the content of the generated activity suggestions.

[0858] Step 3:

[0859] The terminal displays activity suggestions received from the server on its human interface. The input is the activity suggestions from the server, which are displayed in a visually recognizable format for the user. The output is the displayed activity suggestions.

[0860] Step 4:

[0861] The user engages in an activity based on the suggested activity. During this time, the device continuously analyzes the facial and voice data collected again using its emotion recognition engine to obtain emotion data. The input is real-time data from the activity, and the output is the latest emotion evaluation data corresponding to the activity status.

[0862] Step 5:

[0863] The server receives updated sentiment assessment data from the terminal and adjusts the activity suggestions as needed. The input is the latest sentiment assessment data, and the server uses data calculations to modify parts of the activity or generate encouraging messages. The output is the adjusted activity suggestions and feedback messages.

[0864] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0865] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0866] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0867] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0868] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0869] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0870] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0871] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0872] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0873] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0874] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0875] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0876] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0877] 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.

[0878] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0879] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0880] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0881] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0882] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0883] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0884] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0885] The following is further disclosed regarding the embodiments described above.

[0886] (Claim 1)

[0887] A means of saving individual learner progress information in a database,

[0888] A means of generating learning tasks suitable for individual learners using a generative model,

[0889] A means of providing a user interface for presenting generated learning tasks,

[0890] A means of receiving learners' responses to assignments and providing evaluation and feedback,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, comprising means for communicating with a learner in natural language using a dialogue agent and answering the learner's questions.

[0894] (Claim 3)

[0895] The system according to claim 1, comprising means for automatically selecting and providing the next learning task according to the progress of the learning task.

[0896] "Example 1"

[0897] (Claim 1)

[0898] A means for storing individual educators' progress information in an information storage device,

[0899] A means of generating educational tasks suitable for individual educators using a generative artificial intelligence model,

[0900] Means for providing an input display device for displaying generated educational tasks,

[0901] A means of receiving, evaluating, and providing information on responses to educators' challenges,

[0902] A means of analyzing educators' past teaching history and adjusting assignments based on their strengths and weaknesses,

[0903] A means of selecting and providing the following applicable educational topics based on the responses received,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, comprising means for exchanging information with an educator in natural language using an interactive information processing device and responding to the educator's questions.

[0907] (Claim 3)

[0908] The system according to claim 1, comprising means for dynamically selecting and providing the next educational task according to the degree of achievement of the educational task.

[0909] "Application Example 1"

[0910] (Claim 1)

[0911] A memory device for accumulating information on individual learners,

[0912] A processing means that generates educational tasks suitable for individual learners using a generative model,

[0913] Means for providing a user interface for displaying generated educational assignments,

[0914] A processing means that receives learners' answers to assignments and provides evaluation and response,

[0915] A means of selecting and distributing educational content in specific fields based on users' interests,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, comprising means for engaging in natural language dialogue with a learner using a conversational program and responding to the learner's questions.

[0919] (Claim 3)

[0920] The system according to claim 1, comprising means for automatically selecting and supplying the next educational task according to the degree of achievement of the educational task.

[0921] "Example 2 of combining an emotion engine"

[0922] (Claim 1)

[0923] A means for saving individual learner progress data to a recording device,

[0924] A means of generating learning content tailored to individual learners using generative AI,

[0925] A means for providing an information display device for presenting the generated learning content,

[0926] A means of receiving learners' answers to assignments and providing evaluation and reporting,

[0927] A means of collecting learner emotional data through a sensing device and analyzing that data,

[0928] A means for adjusting the difficulty level of learning content and a means for generating encouraging messages based on emotional data,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, which includes means for communicating with learners in natural language using a dialogue system and answering learners' questions.

[0932] (Claim 3)

[0933] The system according to claim 1, comprising means for dynamically selecting and providing the next learning content in accordance with the progress of the learning content.

[0934] "Application example 2 when combining with an emotional engine"

[0935] (Claim 1)

[0936] A means for storing individual user progress information in a storage device,

[0937] A means of generating activities suitable for individual users using a generative model,

[0938] A means of providing a human interface for presenting the generated activities,

[0939] A means of analyzing the emotional state of users and providing evaluation and feedback,

[0940] A system that includes this.

[0941] (Claim 2)

[0942] The system according to claim 1, which includes means for using a conversational agent to interact with a user in natural language and to answer the user's questions.

[0943] (Claim 3)

[0944] The system according to claim 1, comprising means for automatically selecting and providing the next appropriate activity according to the user's emotional state and activity progress. [Explanation of Symbols]

[0945] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A memory device for accumulating information on individual learners, A processing means that generates educational tasks suitable for individual learners using a generative model, Means for providing a user interface for displaying generated educational assignments, A processing means that receives learners' answers to assignments and provides evaluation and response, A means of selecting and distributing educational content in specific fields based on users' interests, A system that includes this.

2. The system according to claim 1, comprising means for engaging in natural language dialogue with a learner using a conversational program and responding to the learner's questions.

3. The system according to claim 1, comprising means for automatically selecting and supplying the next educational task according to the degree of achievement of the educational task.

Images