system

Abstract

We provide the system. [Solution] Means for collecting learner progress information and learning history, A means for generating personalized problems based on collected learner progress information and learning history, A means of providing learners with generated problems, analyzing their answers, and giving feedback, A means of providing community support features for learners to interact with other learners, 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 method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional learning materials have the problem that customized learning support corresponding to the individual needs of learners cannot be provided, and the learning effect cannot be fully obtained. In addition, it is difficult for learners to accurately grasp their own understanding level and obtain effective feedback, and a learning environment for continuously deepening knowledge is not established. Furthermore, since the communication between learners is promoted and the opportunity to receive mutual support is limited, isolated learning tends to occur.

Means for Solving the Problems

[0005] This invention provides means for collecting learner progress information and learning history, and based on this, generates personalized problems to provide learners with appropriate feedback. Furthermore, it ensures the quality of the learning content provided by having experts review the generated problems. In addition, it enables learners to comprehensively solve the problems they face by providing a function that allows them to interact with other learners through a community and support each other.

[0006] "Learner progress information" refers to data that shows the learner's own learning status and changes in their level of understanding.

[0007] "Learning history" refers to a record of past learning activities, including which materials and problems were studied, when, and how.

[0008] "Individualized questions" are questions that are automatically generated in a format and difficulty level that is optimal for the learner, based on the learner's progress information and learning history.

[0009] "Feedback" refers to information, including evaluations and explanations, that learners receive in response to their answers, and is important for deepening their understanding.

[0010] "Expert review" refers to a post-processing verification conducted by a person with expertise to confirm whether the generated learning content is appropriate and to maintain its quality.

[0011] The "community support function" is a service that provides a space for learners to interact with each other, promoting information sharing and mutual support. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential 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

[0013] [[ID=‎40]] 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.

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

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First Embodiment]

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

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0027] 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.

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

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system that provides a customized learning experience tailored to the individual needs of each learner. This system is primarily operated by a server, terminals, and users, with each function working together to support learning.

[0034] The server first collects learning history and progress information provided by the user. This information is crucial because it is used for subsequent problem generation and feedback. Next, the server uses a generative AI based on the collected data to generate personalized problems tailored to the learner's understanding and progress. These problems are not simply automatically generated; their quality and reliability are guaranteed through expert review.

[0035] The terminal presents the user with personalized problems provided by the server. The user answers these problems and inputs the results into the terminal. The terminal sends the user's answers to the server and receives feedback in real time. Through the feedback, the user can check their level of understanding and get direction for their next learning.

[0036] As a concrete example, consider a scenario where a user is studying a particular unit of mathematics. In this case, the server generates basic and applied problems for that unit based on the user's progress. The terminal displays these problems and provides the user with detailed explanations after they are solved. Furthermore, additional, more advanced problems can be provided as needed to help the user understand the problems. This allows the user to deepen their knowledge step by step and continue learning efficiently.

[0037] Furthermore, the server incorporates community support features, providing a platform where users can interact with other learners and share information. This feature allows users to post questions and receive advice and answers from other users and AI assistants. This enables learners to support each other and promotes a richer learning experience.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user selects the unit or subject to study and enters that information into the device. The device then sends the entered information to the server.

[0041] Step 2:

[0042] The server analyzes the user's understanding and weaknesses based on their selections, past learning history, and progress. It then uses these analysis results to generate personalized problems.

[0043] Step 3:

[0044] The server generates a problem and sends it to the terminal. The terminal displays it to the user and asks for an answer.

[0045] Step 4:

[0046] The user answers the questions displayed on the device and enters the answers into the device. The device then sends the answers to the server.

[0047] Step 5:

[0048] The server analyzes the user's answers and generates feedback based on the accuracy rate and answer trends. This feedback may include explanations for incorrect answers.

[0049] Step 6:

[0050] The terminal displays feedback received from the server to the user. The user reviews this feedback and evaluates their level of understanding.

[0051] Step 7:

[0052] The server generates additional problems as needed based on the analysis results, thereby reinforcing the user's learning.

[0053] Step 8:

[0054] If a user wants to deepen their understanding, they can ask questions to other learners through the community support feature. The device's support for this feature facilitates smooth communication.

[0055] Step 9:

[0056] The server posts the user's question to the community forum and waits for answers and advice from other users and AI assistants. The device then displays the received answers to the user.

[0057] This series of processes allows users to learn in a step-by-step and efficient manner.

[0058] (Example 1)

[0059] 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."

[0060] There is a need for a system that can provide an efficient and effective learning experience tailored to the progress and understanding of individual learners. Such a system should not only allow learners to progress at their own pace, but also promote interaction among learners and provide support for achieving a deeper understanding.

[0061] 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.

[0062] In this invention, the server includes means for accumulating progress data and learning history of learners, means for generating personalized tasks based on the accumulated data using a generative AI model, and means for displaying the generated tasks to learners and providing immediate feedback. This makes it possible to provide learners with a personalized learning experience and immediate feedback according to their level of understanding. Furthermore, it becomes possible to provide a more effective learning environment by enabling learners to share information and deepen their interactions with each other.

[0063] "Target learners" are individuals who engage with individual learning content with the aim of improving their skills and knowledge.

[0064] "Progress data" refers to information that shows the results and progress achieved by educated individuals during the learning process.

[0065] "Learning history" refers to a record that includes past learning activities, problems solved, and related results.

[0066] A "generative AI model" is a mathematical model that uses artificial intelligence algorithms to generate output data, such as tasks or content, based on specific input information.

[0067] "Individualized assignments" are problems or learning content that are tailored to the specific needs and level of understanding of the learner, taking into account their progress data and learning history.

[0068] "Immediate feedback" refers to information provided immediately after an educator completes an assignment, pointing out whether their work is correct or incorrect, and identifying areas for improvement.

[0069] "Sharing information and deepening interaction" refers to activities in which educators exchange learning experiences and knowledge with each other, thereby improving their understanding of the learning content and working together to solve problems.

[0070] This invention is a system that provides individualized learning experiences to educators. This system mainly consists of a server, terminals, and users, each providing learning support according to its respective role.

[0071] Server Embodiment

[0072] The server first collects the progress data and learning history of the students. A database management system is often used for this process. Based on the collected data, the server utilizes a generative AI model to create personalized tasks optimized for each student. The generative AI model can use open-source AI tools or models provided by commercial AI providers. The server generates real-time feedback along with the tasks and sends it to the terminal.

[0073] Terminal embodiment

[0074] The device displays personalized assignments provided by the server to the learner. A web application or mobile application could be provided as a useful interface. The device displays real-time feedback to improve the learner's understanding and guide their learning direction.

[0075] User Embodiment

[0076] Users work on problems displayed via their devices and advance their learning through solutions and feedback. If needed, users can share information and interact with other users by utilizing the server's community support features.

[0077] Specific example

[0078] Specifically, consider a scenario where a user is studying calculus (differentiation) in high school mathematics. The server generates application problems related to differentiation based on past exam results and the user's learning history. The terminal displays these problems to the user and provides detailed feedback after they complete them. Based on this information, the user can also solve additional problems tailored to their specific weaknesses.

[0079] Example of a prompt

[0080] "To deepen the understanding of differential calculus among students, please generate problems that cover everything from basic concepts to advanced applications."

[0081] These elements of the system enable learners to have an efficient educational experience and strengthen the support system for deepening their learning.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server collects learning progress data and learning history from the user. This input data includes the types of questions the user has answered in the past, their accuracy rate, and learning time. The server stores this data in a database and organizes it using a standard database management system. This prepares the foundational data needed to understand the user's learning patterns.

[0085] Step 2:

[0086] The server analyzes the collected data to identify the user's level of understanding and weaknesses. This process involves data aggregation and visualization using data analysis tools. Based on the analysis results, the server generates prompts to utilize the generated AI model. For example, a prompt might be output such as, "Evaluate the user's understanding of differential calculus and generate a suitable application problem."

[0087] Step 3:

[0088] The server inputs prompts and analysis results into a generative AI model to generate problems optimized for each user. The generative AI model used here adjusts the problem content and difficulty level to match the user's skill level. As a result, the output provides material tailored to the user's learning needs.

[0089] Step 4:

[0090] When the terminal receives a problem generated from the server, it creates an interface to display that problem to the user. The terminal presents the problem, for example, in the form of a web browser or mobile app, providing an environment that makes it easy for the user to answer. The output at this stage is a set of problems presented visually to the user.

[0091] Step 5:

[0092] The user answers the questions presented on the device. The user's answers are entered into the device, and the device sends this data to the server, preparing it for further processing. The input data includes the user's answers and the time taken after answering.

[0093] Step 6:

[0094] Upon receiving user response data, the server generates immediate feedback. This feedback generation process includes analysis of accuracy and areas for improvement. The server utilizes an AI model to generate detailed explanations and advice for the next steps, which are then sent to the user's device. The output is provided as real-time feedback to the user.

[0095] Step 7:

[0096] Users receive feedback through their devices to confirm their understanding. This information serves as a guide for determining their next learning plan. Users can also access community support features through their devices and interact with other learners to further develop their knowledge and resolve questions.

[0097] (Application Example 1)

[0098] 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."

[0099] Traditional learning systems struggle to provide effective learning experiences tailored to individual learners' needs. Furthermore, they often lack real-time feedback and expert quality assurance. Additionally, limited interaction with other learners through community support hinders the depth and effectiveness of learning.

[0100] 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.

[0101] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems based on the collected learner progress information and learning history, and means for delivering progress-based educational content to learners in streaming format. This makes it possible to provide learning content that reflects the individual needs of learners in real time and to provide smooth feedback.

[0102] "Learner progress information" refers to the state and progress of learning that a learner has achieved to date.

[0103] "Learning history" refers to a record of past learning activities, including information such as what content was studied and when.

[0104] "Individualized problems" are practice problems that are tailored to a specific learner's level of understanding and needs, and are personalized for that particular learner.

[0105] "Feedback" refers to evaluations and advice regarding learners' answers, and is information that helps learners understand their own learning achievements and decide on their next actions.

[0106] The "community support function" is a feature designed to help learners interact with each other, share information, and help one another.

[0107] "Streaming educational content" is a method of continuously providing learning materials to learners in real time via the internet.

[0108] "Expert review" is a process in which experts with knowledge and experience verify the content of problems and feedback to ensure that they are appropriate and effective.

[0109] "Supplementary questions" are additional questions provided on a particular learning topic, intended to deepen the learner's understanding.

[0110] This invention realizes a system that provides a personalized learning experience based on learner progress information and learning history. It consists of a server, terminals, and users.

[0111] The server is built using backend technologies such as Python and Django, and collects and manages learner progress information and learning history. Furthermore, it utilizes generative AI models (using TENSORFLOW® and PyTorch) based on the collected data to generate personalized problems suited to each learner. In this process, the generated problems are reviewed by experts to ensure their quality.

[0112] The device operates via a smartphone or head-mounted display as its user interface. It displays personalized problems provided by a server and offers real-time feedback to the user. Furthermore, based on the learner's answers, it can stream educational content to support subsequent learning.

[0113] Users answer learning questions via their devices and receive feedback based on their answers. Furthermore, through the community support function, they can interact with other learners, post questions, and receive advice from an AI assistant.

[0114] For example, if a learner is acquiring a new language, the server provides them with targeted questions on specific grammatical points and timely feedback. This aims to facilitate understanding of the questions and maximize learning effectiveness.

[0115] Example prompt: "Please generate practice exercises to help me learn the following topics, focusing on grammar points that I've been struggling with recently."

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

[0117] Step 1:

[0118] The server collects learning history and progress information from the learner's device. This information includes the problems the learner has worked on, their answers, and past feedback. Based on this, it is recorded in a database and processed as basic data for generating the next problems.

[0119] Step 2:

[0120] The server uses collected progress information and learning history to generate personalized problems using a generative AI model. The input here is the learner's history data and progress, and the AI ​​model is applied to generate problems. The output is a set of problems tailored to the learner's level of understanding. The model generates appropriate problems based on prompt statements.

[0121] Step 3:

[0122] The server sends the generated individualized problems to the terminal. The terminal receives them and displays them on the user interface. Here, the input is the set of problems received from the server, and the output is showing the problems to the learner. This allows the learner to work on the problems through the terminal.

[0123] Step 4:

[0124] The user enters their answer to a question via a terminal. The terminal then sends this answer to the server. The input is the learner's answer, and the output is the data to be sent to the server. This ensures that the answer results are delivered to the server quickly.

[0125] Step 5:

[0126] The server analyzes the received answers and quickly generates feedback. This process involves making judgments based on the correctness of the answers and generating additional supplementary explanations as needed. The input is the learner's answer data, and the output is feedback information.

[0127] Step 6:

[0128] Feedback generated from the server is sent to the terminal, allowing the user to confirm their learning understanding. The input is the feedback data, and the output is displaying the feedback to the user. This enables the user to decide on the next learning step.

[0129] Step 7:

[0130] Users can utilize community support features as needed to interact with other learners. They can post questions and receive answers through their devices. Input consists of questions and posts from users, while output consists of answers from other learners and AI.

[0131] 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.

[0132] This invention introduces emotion recognition technology into learning systems to further personalize the learning experience. The system consists of server, terminal, and user interaction, and optimizes the learning process with an emotion engine at its core.

[0133] The server collects user progress information, learning history, and emotional data. The emotion engine uses the device's camera and sensors to monitor the user's facial expressions, tone of voice, posture, etc., and analyzes the user's emotional state in real time. This allows the system to recognize the stress, excitement, and level of concentration the user experiences while solving problems.

[0134] Based on the collected data, the server generates personalized problems that reflect the user's emotional state. For example, if the system detects that the user is stressed, it adjusts the difficulty of the problem to provide a more relaxed experience. It can also provide inspiring feedback and advice to boost motivation.

[0135] The device presents the user with adaptive problems and feedback sent from the server. The user can continuously adjust the learning process by answering these and accepting feedback as needed.

[0136] For example, if a user is learning a language and the emotion engine detects fatigue from prolonged learning, the server will reduce the user's burden by presenting lighter quiz-style questions instead of listening comprehension exercises. It will also help maintain an efficient learning cycle by providing the user with appropriate break advice.

[0137] This system allows learners to have a flexible learning experience based on their own emotions and progress, and is expected to improve learning efficiency.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The user selects the subject to study and enters it into the terminal. The terminal then sends the selection information to the server.

[0141] Step 2:

[0142] The device uses cameras and sensors to monitor the user's emotional state in real time and collect emotional data.

[0143] Step 3:

[0144] The server analyzes the user's level of understanding and current emotional state based on learning progress, learning history, and sentiment data received from the user.

[0145] Step 4:

[0146] Based on the analysis results, the server generates personalized problems tailored to the user's emotional state and learning needs. For example, if the user is feeling stressed, it will generate easier problems.

[0147] Step 5:

[0148] The server sends the generated problems to the terminal. The terminal displays these problems to the user and prompts them to answer.

[0149] Step 6:

[0150] The user submits an answer and enters it into the device. The device then sends the answer to the server.

[0151] Step 7:

[0152] The server analyzes the user's answers and generates feedback based on the results. This feedback may include explanations to improve understanding and positive, encouraging messages.

[0153] Step 8:

[0154] The server sends the generated feedback to the terminal. The terminal presents the feedback to the user and instructs them on the next step.

[0155] Step 9:

[0156] The user reviews the feedback provided and decides on actions to take to proceed with the next learning step as needed. The emotion engine continuously monitors emotional data, allowing the learning process to be dynamically adjusted.

[0157] (Example 2)

[0158] 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 as the "terminal".

[0159] In conventional learning systems, it has been difficult to provide individualized learning experiences that take into account the learner's emotional state. A challenge is that learning efficiency is impaired because the learning content cannot be appropriately adjusted when learners experience stress or a decline in concentration.

[0160] 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.

[0161] In this invention, the server includes means for collecting learner progress information, learning history, and emotional information; means for analyzing the learner's emotional state using a terminal input device; and means for generating personalized problems based on the collected and analyzed information. This enables the provision of problems that take the learner's emotional state into consideration and adaptive feedback.

[0162] "Progress information" refers to data that shows how much progress a learner has made in relation to a specific learning topic.

[0163] "Learning history" refers to records of learning activities that a learner has undertaken in the past and the results thereof.

[0164] "Emotional information" refers to data about the learner's emotional state, including stress levels, excitement, and concentration levels.

[0165] A "terminal" refers to an electronic device used by learners that is equipped with a camera and microphone and can sense the user's state.

[0166] "Individualized problems" refer to learning tasks and problems that are tailored based on the individual progress and emotional state of each learner.

[0167] "Feedback" refers to advice and evaluations provided to learners to improve their learning process.

[0168] "Analysis" refers to the process of analyzing data collected by terminals and servers to understand the learner's emotional state and learning tendencies.

[0169] This invention aims to provide an individualized learning experience by considering the learner's emotional state in a learning system. The system is built on the interaction between the server, terminal, and user, and optimizes the learning process by utilizing emotion recognition technology.

[0170] The server first collects user progress information, learning history, and sentiment data. For this purpose, learning applications and platforms are used, and progress information such as the number of problems solved, accuracy rate, and learning time is regularly recorded. The collected data is stored in a database and used for subsequent analysis and problem generation.

[0171] The device uses its camera and microphone to analyze the user's emotional state in real time. Video data collected through the built-in camera and audio data from the microphone are processed using AI libraries such as OpenCV and TensorFlow to estimate the user's emotions from their facial expressions and tone of voice. This analysis provides feedback to the server regarding the user's emotional state, such as whether they are stressed or highly focused.

[0172] The server generates personalized problems tailored to the user based on collected progress and sentiment data. It utilizes generative AI models and Python libraries such as NLTK and Transformers to create problems that match the user's characteristics. For example, if analysis indicates a user is feeling tired, it supports the learner by providing problems of lower difficulty.

[0173] For example, if a user is learning a language and emotion analysis determines that their concentration is declining, the system will present them with a light quiz-style question and display advice on the device suggesting they take a break. An example of a prompt message could be, "Analyze the user's facial expression data and suggest appropriate learning content."

[0174] This system allows users to continuously receive learning content and feedback tailored to their individual circumstances, which is expected to improve learning efficiency.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The server collects user progress information, learning history, and sentiment data. Inputs include user task completion status, learning time, and accuracy rates obtained from the learning platform. This data is stored in a database, and output is obtained to prepare for future analysis. Specifically, the server defines a process for periodically acquiring data by setting collection times.

[0178] Step 2:

[0179] The device analyzes the user's emotional state based on video and audio input. It acquires data in real time through the camera and microphone and receives it as input. This data is processed by an emotion analysis algorithm using OpenCV or TensorFlow to obtain an output that estimates the user's emotional state from their facial expressions and tone of voice. Specifically, it recognizes facial features such as whether the user is smiling or frowning, and classifies the emotion.

[0180] Step 3:

[0181] The server generates personalized problems based on collected progress information and sentiment data. It uses sentiment state data and learning progress data obtained in the previous step as input. A generative AI model is used to adjust the difficulty and content of the problems, outputting the most appropriate problems for the user. For example, if the sentiment state is recognized as "fatigue," a problem with a lower difficulty level is generated to reduce the learning load.

[0182] Step 4:

[0183] The server generates feedback for the user and sends it to the terminal. It receives sentiment data and the answer to a problem as input and produces output that creates feedback to improve the user's learning motivation. Specifically, it takes the form of an encouraging message if the user answers correctly and suggestions for improvement if they answer incorrectly.

[0184] Step 5:

[0185] Users work on personalized problems provided on their devices and receive feedback. As input, they answer a set of problems sent from the server and send their results back to the server. This triggers a process where learning progress and sentiment data are collected again, yielding new output to adjust the next learning cycle. Specifically, this involves solving problems on the device screen and uploading the answers to the server.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0188] Conventional learning systems and product recommendation systems do not adequately consider the user's emotional state during optimization, resulting in a failure to improve user experience and purchase intent.

[0189] 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.

[0190] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems, and means for analyzing the user's video and audio data and evaluating their emotional state. This enables flexible learning and product recommendations based on the user's individual emotional state.

[0191] "Learner progress information" refers to data that shows the extent to which learners have completed assignments and learning materials.

[0192] "Learning history" refers to data that records the history of learning materials and problems that a learner has studied so far.

[0193] "Individualized questions" are questions created specifically for learners, based on their progress information and emotional state.

[0194] "Feedback" refers to advice and evaluations provided based on a learner's answers, designed to improve the learning process.

[0195] The "community support function" provides a feature that allows learners to interact with each other and share information.

[0196] "Video data" refers to visual information that captures the learner's facial expressions and movements.

[0197] "Audio data" refers to acoustic information that records the learner's voice.

[0198] "Means for evaluating emotional state" refers to techniques that analyze collected video and audio data to determine the emotional state of learners.

[0199] "Methods for recommending products" refers to the process of selecting and suggesting appropriate products based on the analyzed emotional state of the learner.

[0200] To implement this invention, the user uses a device such as a smartphone or smart glasses. The device is equipped with a camera and microphone, which capture the user's video and audio data in real time. The server is equipped with facial recognition software (e.g., OpenCV) and speech analysis software (e.g., Google's Speech-to-Text API) to process this data. Furthermore, IBM's Watson® is used as a technology to analyze emotional states.

[0201] The server stores user progress information and learning history in a database and implements algorithms to generate personalized problems. User emotional state data is analyzed by the server and used as data to recommend products based on the individual's emotional state. This provides a learning and product selection experience that is adapted to the user's emotional state.

[0202] For example, if the device detects a user's stress level, an algorithm running on the server generates and recommends a list of products with relaxing effects. In another example, if the system analyzes the user as agitated, products related to active activities will be presented. This analysis and recommendation process achieves greater accuracy and personalization by utilizing generative AI models to generate prompts. Examples of prompts include, "Please recommend products that will help the user relax," and "How can we suggest products suitable for an agitated user?"

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] When a user begins browsing an e-commerce site on their device, the device uses its camera and microphone to collect video and audio data of the user. This data, which includes the user's facial expressions and tone of voice, is sent to the server as input.

[0206] Step 2:

[0207] The server processes the acquired video data using facial recognition software (OpenCV) and simultaneously analyzes the audio data using speech analysis software (Google's Speech-to-Text API). This identifies the user's emotional state (e.g., relaxed, stressed, excited). This identified emotional state becomes the output.

[0208] Step 3:

[0209] Based on the identified emotional state, the server uses an emotion analysis engine (IBM Watson) to perform a detailed analysis of the user's emotional state. Based on this analysis, it utilizes a generative AI model to generate prompt messages recommending specific products. These prompt messages become the output.

[0210] Step 4:

[0211] Based on the prompt, the server searches the product database for products that match the user's emotional state and creates a list of appropriate products. This product list is the output and serves as the recommended products for the user.

[0212] Step 5:

[0213] The server sends the generated product list to the terminal, where it is displayed to the user on the terminal screen. The user can then select products based on this list. This selection generates user feedback data, which is used to improve the accuracy of recommendations in the future.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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".

[0230] This invention is a system that provides a customized learning experience tailored to the individual needs of each learner. This system is primarily operated by a server, terminals, and users, with each function working together to support learning.

[0231] The server first collects learning history and progress information provided by the user. This information is crucial because it is used for subsequent problem generation and feedback. Next, the server uses a generative AI based on the collected data to generate personalized problems tailored to the learner's understanding and progress. These problems are not simply automatically generated; their quality and reliability are guaranteed through expert review.

[0232] The terminal presents the user with personalized problems provided by the server. The user answers these problems and inputs the results into the terminal. The terminal sends the user's answers to the server and receives feedback in real time. Through the feedback, the user can check their level of understanding and get direction for their next learning.

[0233] As a concrete example, consider a scenario where a user is studying a particular unit of mathematics. In this case, the server generates basic and applied problems for that unit based on the user's progress. The terminal displays these problems and provides the user with detailed explanations after they are solved. Furthermore, additional, more advanced problems can be provided as needed to help the user understand the problems. This allows the user to deepen their knowledge step by step and continue learning efficiently.

[0234] Furthermore, the server incorporates community support features, providing a platform where users can interact with other learners and share information. This feature allows users to post questions and receive advice and answers from other users and AI assistants. This enables learners to support each other and promotes a richer learning experience.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The user selects the unit or subject to study and enters that information into the device. The device then sends the entered information to the server.

[0238] Step 2:

[0239] The server analyzes the user's understanding and weaknesses based on their selections, past learning history, and progress. It then uses these analysis results to generate personalized problems.

[0240] Step 3:

[0241] The server generates a problem and sends it to the terminal. The terminal displays it to the user and asks for an answer.

[0242] Step 4:

[0243] The user answers the questions displayed on the device and enters the answers into the device. The device then sends the answers to the server.

[0244] Step 5:

[0245] The server analyzes the user's answers and generates feedback based on the accuracy rate and answer trends. This feedback may include explanations for incorrect answers.

[0246] Step 6:

[0247] The terminal displays feedback received from the server to the user. The user reviews this feedback and evaluates their level of understanding.

[0248] Step 7:

[0249] The server generates additional problems as needed based on the analysis results, thereby reinforcing the user's learning.

[0250] Step 8:

[0251] If a user wants to deepen their understanding, they can ask questions to other learners through the community support feature. The device's support for this feature facilitates smooth communication.

[0252] Step 9:

[0253] The server posts the user's question to the community forum and waits for answers and advice from other users and AI assistants. The device then displays the received answers to the user.

[0254] This series of processes allows users to learn in a step-by-step and efficient manner.

[0255] (Example 1)

[0256] 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."

[0257] There is a need for a system that can provide an efficient and effective learning experience tailored to the progress and understanding of individual learners. Such a system should not only allow learners to progress at their own pace, but also promote interaction among learners and provide support for achieving a deeper understanding.

[0258] 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.

[0259] In this invention, the server includes means for accumulating progress data and learning history of learners, means for generating personalized tasks based on the accumulated data using a generative AI model, and means for displaying the generated tasks to learners and providing immediate feedback. This makes it possible to provide learners with a personalized learning experience and immediate feedback according to their level of understanding. Furthermore, it becomes possible to provide a more effective learning environment by enabling learners to share information and deepen their interactions with each other.

[0260] "Target learners" are individuals who engage with individual learning content with the aim of improving their skills and knowledge.

[0261] "Progress data" refers to information that shows the results and progress achieved by educated individuals during the learning process.

[0262] "Learning history" refers to a record that includes past learning activities, problems solved, and related results.

[0263] A "generative AI model" is a mathematical model that uses artificial intelligence algorithms to generate output data, such as tasks or content, based on specific input information.

[0264] "Individualized assignments" are problems or learning content that are tailored to the specific needs and level of understanding of the learner, taking into account their progress data and learning history.

[0265] "Immediate feedback" refers to information provided immediately after an educator completes an assignment, pointing out whether their work is correct or incorrect, and identifying areas for improvement.

[0266] "Sharing information and deepening interaction" refers to activities in which educators exchange learning experiences and knowledge with each other, thereby improving their understanding of the learning content and working together to solve problems.

[0267] This invention is a system that provides individualized learning experiences to educators. This system mainly consists of a server, terminals, and users, each providing learning support according to its respective role.

[0268] Server Embodiment

[0269] The server first collects the progress data and learning history of the students. A database management system is often used for this process. Based on the collected data, the server utilizes a generative AI model to create personalized tasks optimized for each student. The generative AI model can use open-source AI tools or models provided by commercial AI providers. The server generates real-time feedback along with the tasks and sends it to the terminal.

[0270] Terminal embodiment

[0271] The device displays personalized assignments provided by the server to the learner. A web application or mobile application could be provided as a useful interface. The device displays real-time feedback to improve the learner's understanding and guide their learning direction.

[0272] User Embodiment

[0273] Users work on problems displayed via their devices and advance their learning through solutions and feedback. If needed, users can share information and interact with other users by utilizing the server's community support features.

[0274] Specific example

[0275] Specifically, consider a scenario where a user is studying calculus (differentiation) in high school mathematics. The server generates application problems related to differentiation based on past exam results and the user's learning history. The terminal displays these problems to the user and provides detailed feedback after they complete them. Based on this information, the user can also solve additional problems tailored to their specific weaknesses.

[0276] Example of a prompt

[0277] "To deepen the understanding of differential calculus among students, please generate problems that cover everything from basic concepts to advanced applications."

[0278] These elements of the system enable learners to have an efficient educational experience and strengthen the support system for deepening their learning.

[0279] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0280] Step 1:

[0281] The server collects learning progress data and learning history from the user. This input data includes the types of questions the user has answered in the past, the correct answer rate, the learning time, etc. The server stores these data in a database and organizes them using a standard database management system. This prepares the basic data for understanding the user's learning pattern.

[0282] Step 2:

[0283] The server analyzes the collected data to identify the user's understanding level and weaknesses. In this process, data analysis tools are used to aggregate and visualize the data. Based on the analysis results, the server generates prompt sentences for utilizing the generative AI model. For example, a prompt sentence such as "Evaluate the user's understanding of differentiation and generate suitable application questions" is output.

[0284] Step 3:

[0285] The server inputs the prompt sentences and analysis results into the generative AI model to generate questions optimized for each user. The generative AI model used here adjusts the content and difficulty level of the questions according to the user's skill level. As a result, topics suitable for the user's learning needs are output.

[0286] Step 4:

[0287] When the terminal receives the questions generated by the server, it generates an interface for displaying the questions to the user. The terminal presents the questions in the form of, for example, a web browser or a mobile app, providing an environment where the user can easily answer. The output at this stage is a set of questions visually presented to the user.

[0288] Step 5:

[0289] The user answers the questions presented on the device. The user's answers are entered into the device, and the device sends this data to the server, preparing it for further processing. The input data includes the user's answers and the time taken after answering.

[0290] Step 6:

[0291] Upon receiving user response data, the server generates immediate feedback. This feedback generation process includes analysis of accuracy and areas for improvement. The server utilizes an AI model to generate detailed explanations and advice for the next steps, which are then sent to the user's device. The output is provided as real-time feedback to the user.

[0292] Step 7:

[0293] Users receive feedback through their devices to confirm their understanding. This information serves as a guide for determining their next learning plan. Users can also access community support features through their devices and interact with other learners to further develop their knowledge and resolve questions.

[0294] (Application Example 1)

[0295] 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 glasses 214 will be referred to as the "terminal."

[0296] Traditional learning systems struggle to provide effective learning experiences tailored to individual learners' needs. Furthermore, they often lack real-time feedback and expert quality assurance. Additionally, limited interaction with other learners through community support hinders the depth and effectiveness of learning.

[0297] 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.

[0298] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems based on the collected learner progress information and learning history, and means for delivering progress-based educational content to learners in streaming format. This makes it possible to provide learning content that reflects the individual needs of learners in real time and to provide smooth feedback.

[0299] "Learner progress information" refers to the state and progress of learning that a learner has achieved to date.

[0300] "Learning history" refers to a record of past learning activities, including information such as what content was studied and when.

[0301] "Individualized problems" are practice problems that are tailored to a specific learner's level of understanding and needs, and are personalized for that particular learner.

[0302] "Feedback" refers to evaluations and advice regarding learners' answers, and is information that helps learners understand their own learning achievements and decide on their next actions.

[0303] The "community support function" is a feature designed to help learners interact with each other, share information, and help one another.

[0304] "Streaming educational content" is a method of continuously providing learning materials to learners in real time via the internet.

[0305] "Expert review" is a process in which experts with knowledge and experience verify the content of problems and feedback to ensure that they are appropriate and effective.

[0306] A "supplementary question" is a question additionally provided in a learning theme, aiming to deepen the learner's understanding.

[0307] This invention realizes a system that provides an individualized learning experience based on the learner's progress information and learning history. It is composed of a server, a terminal, and a user.

[0308] The server is constructed by backend technologies such as Python and Django, collects and manages the learner's progress information and learning history. Furthermore, it utilizes a generated AI model (using TensorFlow or PyTorch) based on the collected data to generate individualized questions suitable for each learner. In this process, in order to ensure the quality of the questions, the generated questions are reviewed by experts.

[0309] The terminal operates via a smartphone or a head-mounted display as a user interface. The terminal displays the individualized questions provided by the server and provides real-time feedback to the user. Also, based on the learner's answer results, educational content for supporting the next learning can be delivered in a streaming format.

[0310] The user answers learning questions via the terminal and receives feedback based on the answer results. Furthermore, through the community support function, it is possible to communicate with other learners, post questions, and receive advice from the AI assistant.

[0311] As a specific example, when a learner is acquiring a new language, the server provides pinpoint questions regarding specific grammar items to that learner and gives timely feedback, aiming to promote problem understanding and maximize the learning effect.

[0312] Example of a prompt sentence: "Generate practice questions for learning the following items, focusing on the grammar items that have recently become difficult for you."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The server collects learning history and progress information from the learner's device. This information includes the problems the learner has worked on, their answers, and past feedback. Based on this, it is recorded in a database and processed as basic data for generating the next problems.

[0316] Step 2:

[0317] The server uses collected progress information and learning history to generate personalized problems using a generative AI model. The input here is the learner's history data and progress, and the AI ​​model is applied to generate problems. The output is a set of problems tailored to the learner's level of understanding. The model generates appropriate problems based on prompt statements.

[0318] Step 3:

[0319] The server sends the generated individualized problems to the terminal. The terminal receives them and displays them on the user interface. Here, the input is the set of problems received from the server, and the output is showing the problems to the learner. This allows the learner to work on the problems through the terminal.

[0320] Step 4:

[0321] The user enters their answer to a question via a terminal. The terminal then sends this answer to the server. The input is the learner's answer, and the output is the data to be sent to the server. This ensures that the answer results are delivered to the server quickly.

[0322] Step 5:

[0323] The server analyzes the received answers and quickly generates feedback. This process involves making judgments based on the correctness of the answers and generating additional supplementary explanations as needed. The input is the learner's answer data, and the output is feedback information.

[0324] Step 6:

[0325] Feedback generated from the server is sent to the terminal, allowing the user to confirm their learning understanding. The input is the feedback data, and the output is displaying the feedback to the user. This enables the user to decide on the next learning step.

[0326] Step 7:

[0327] Users can utilize community support features as needed to interact with other learners. They can post questions and receive answers through their devices. Input consists of questions and posts from users, while output consists of answers from other learners and AI.

[0328] 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.

[0329] This invention introduces emotion recognition technology into learning systems to further personalize the learning experience. The system consists of server, terminal, and user interaction, and optimizes the learning process with an emotion engine at its core.

[0330] The server collects user progress information, learning history, and emotional data. The emotion engine uses the device's camera and sensors to monitor the user's facial expressions, tone of voice, posture, etc., and analyzes the user's emotional state in real time. This allows the system to recognize the stress, excitement, and level of concentration the user experiences while solving problems.

[0331] Based on the collected data, the server generates personalized problems that reflect the user's emotional state. For example, if the system detects that the user is stressed, it adjusts the difficulty of the problem to provide a more relaxed experience. It can also provide inspiring feedback and advice to boost motivation.

[0332] The device presents the user with adaptive problems and feedback sent from the server. The user can continuously adjust the learning process by answering these and accepting feedback as needed.

[0333] For example, if a user is learning a language and the emotion engine detects fatigue from prolonged learning, the server will reduce the user's burden by presenting lighter quiz-style questions instead of listening comprehension exercises. It will also help maintain an efficient learning cycle by providing the user with appropriate break advice.

[0334] This system allows learners to have a flexible learning experience based on their own emotions and progress, and is expected to improve learning efficiency.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The user selects the subject to study and enters it into the terminal. The terminal then sends the selection information to the server.

[0338] Step 2:

[0339] The device uses cameras and sensors to monitor the user's emotional state in real time and collect emotional data.

[0340] Step 3:

[0341] The server analyzes the user's level of understanding and current emotional state based on learning progress, learning history, and sentiment data received from the user.

[0342] Step 4:

[0343] Based on the analysis results, the server generates personalized problems tailored to the user's emotional state and learning needs. For example, if the user is feeling stressed, it will generate easier problems.

[0344] Step 5:

[0345] The server sends the generated problems to the terminal. The terminal displays these problems to the user and prompts them to answer.

[0346] Step 6:

[0347] The user submits an answer and enters it into the device. The device then sends the answer to the server.

[0348] Step 7:

[0349] The server analyzes the user's answers and generates feedback based on the results. This feedback may include explanations to improve understanding and positive, encouraging messages.

[0350] Step 8:

[0351] The server sends the generated feedback to the terminal. The terminal presents the feedback to the user and instructs them on the next step.

[0352] Step 9:

[0353] The user reviews the feedback provided and decides on actions to take to proceed with the next learning step as needed. The emotion engine continuously monitors emotional data, allowing the learning process to be dynamically adjusted.

[0354] (Example 2)

[0355] 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".

[0356] In conventional learning systems, it has been difficult to provide individualized learning experiences that take into account the learner's emotional state. A challenge is that learning efficiency is impaired because the learning content cannot be appropriately adjusted when learners experience stress or a decline in concentration.

[0357] 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.

[0358] In this invention, the server includes means for collecting learner progress information, learning history, and emotional information; means for analyzing the learner's emotional state using a terminal input device; and means for generating personalized problems based on the collected and analyzed information. This enables the provision of problems that take the learner's emotional state into consideration and adaptive feedback.

[0359] "Progress information" refers to data that shows how much progress a learner has made in relation to a specific learning topic.

[0360] "Learning history" refers to records of learning activities that a learner has undertaken in the past and the results thereof.

[0361] "Emotional information" refers to data about the learner's emotional state, including stress levels, excitement, and concentration levels.

[0362] A "terminal" refers to an electronic device used by learners that is equipped with a camera and microphone and can sense the user's state.

[0363] "Individualized problems" refer to learning tasks and problems that are tailored based on the individual progress and emotional state of each learner.

[0364] "Feedback" refers to advice and evaluations provided to learners to improve their learning process.

[0365] "Analysis" refers to the process of analyzing data collected by terminals and servers to understand the learner's emotional state and learning tendencies.

[0366] This invention aims to provide an individualized learning experience by considering the learner's emotional state in a learning system. The system is built on the interaction between the server, terminal, and user, and optimizes the learning process by utilizing emotion recognition technology.

[0367] The server first collects user progress information, learning history, and sentiment data. For this purpose, learning applications and platforms are used, and progress information such as the number of problems solved, accuracy rate, and learning time is regularly recorded. The collected data is stored in a database and used for subsequent analysis and problem generation.

[0368] The device uses its camera and microphone to analyze the user's emotional state in real time. Video data collected through the built-in camera and audio data from the microphone are processed using AI libraries such as OpenCV and TensorFlow to estimate the user's emotions from their facial expressions and tone of voice. This analysis provides feedback to the server regarding the user's emotional state, such as whether they are stressed or highly focused.

[0369] The server generates personalized problems tailored to the user based on collected progress and sentiment data. It utilizes generative AI models and Python libraries such as NLTK and Transformers to create problems that match the user's characteristics. For example, if analysis indicates a user is feeling tired, it supports the learner by providing problems of lower difficulty.

[0370] For example, if a user is learning a language and emotion analysis determines that their concentration is declining, the system will present them with a light quiz-style question and display advice on the device suggesting they take a break. An example of a prompt message could be, "Analyze the user's facial expression data and suggest appropriate learning content."

[0371] This system allows users to continuously receive learning content and feedback tailored to their individual circumstances, which is expected to improve learning efficiency.

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] The server collects user progress information, learning history, and sentiment data. Inputs include user task completion status, learning time, and accuracy rates obtained from the learning platform. This data is stored in a database, and output is obtained to prepare for future analysis. Specifically, the server defines a process for periodically acquiring data by setting collection times.

[0375] Step 2:

[0376] The device analyzes the user's emotional state based on video and audio input. It acquires data in real time through the camera and microphone and receives it as input. This data is processed by an emotion analysis algorithm using OpenCV or TensorFlow to obtain an output that estimates the user's emotional state from their facial expressions and tone of voice. Specifically, it recognizes facial features such as whether the user is smiling or frowning, and classifies the emotion.

[0377] Step 3:

[0378] The server generates personalized problems based on collected progress information and sentiment data. It uses sentiment state data and learning progress data obtained in the previous step as input. A generative AI model is used to adjust the difficulty and content of the problems, outputting the most appropriate problems for the user. For example, if the sentiment state is recognized as "fatigue," a problem with a lower difficulty level is generated to reduce the learning load.

[0379] Step 4:

[0380] The server generates feedback for the user and sends it to the terminal. It receives sentiment data and the answer to a problem as input and produces output that creates feedback to improve the user's learning motivation. Specifically, it takes the form of an encouraging message if the user answers correctly and suggestions for improvement if they answer incorrectly.

[0381] Step 5:

[0382] Users work on personalized problems provided on their devices and receive feedback. As input, they answer a set of problems sent from the server and send their results back to the server. This triggers a process where learning progress and sentiment data are collected again, yielding new output to adjust the next learning cycle. Specifically, this involves solving problems on the device screen and uploading the answers to the server.

[0383] (Application Example 2)

[0384] 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."

[0385] Conventional learning systems and product recommendation systems do not adequately consider the user's emotional state during optimization, resulting in a failure to improve user experience and purchase intent.

[0386] 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.

[0387] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems, and means for analyzing the user's video and audio data and evaluating their emotional state. This enables flexible learning and product recommendations based on the user's individual emotional state.

[0388] "Learner progress information" refers to data that shows the extent to which learners have completed assignments and learning materials.

[0389] "Learning history" refers to data that records the history of learning materials and problems that a learner has studied so far.

[0390] "Individualized questions" are questions created specifically for learners, based on their progress information and emotional state.

[0391] "Feedback" refers to advice and evaluations provided based on a learner's answers, designed to improve the learning process.

[0392] The "community support function" provides a feature that allows learners to interact with each other and share information.

[0393] "Video data" refers to visual information that captures the learner's facial expressions and movements.

[0394] "Audio data" refers to acoustic information that records the learner's voice.

[0395] "Means for evaluating emotional state" refers to techniques that analyze collected video and audio data to determine the emotional state of learners.

[0396] "Methods for recommending products" refers to the process of selecting and suggesting appropriate products based on the analyzed emotional state of the learner.

[0397] To implement this invention, the user uses a device such as a smartphone or smart glasses. The device is equipped with a camera and microphone, which capture the user's video and audio data in real time. The server is equipped with facial recognition software (e.g., OpenCV) and speech analysis software (e.g., Google's Speech-to-Text API) to process this data. Furthermore, IBM's Watson is used as a technology to analyze emotional states.

[0398] The server stores user progress information and learning history in a database and implements algorithms to generate personalized problems. User emotional state data is analyzed by the server and used as data to recommend products based on the individual's emotional state. This provides a learning and product selection experience that is adapted to the user's emotional state.

[0399] For example, if the device detects a user's stress level, an algorithm running on the server generates and recommends a list of products with relaxing effects. In another example, if the system analyzes the user as agitated, products related to active activities will be presented. This analysis and recommendation process achieves greater accuracy and personalization by utilizing generative AI models to generate prompts. Examples of prompts include, "Please recommend products that will help the user relax," and "How can we suggest products suitable for an agitated user?"

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] When a user begins browsing an e-commerce site on their device, the device uses its camera and microphone to collect video and audio data of the user. This data, which includes the user's facial expressions and tone of voice, is sent to the server as input.

[0403] Step 2:

[0404] The server processes the acquired video data using facial recognition software (OpenCV) and simultaneously analyzes the audio data using speech analysis software (Google's Speech-to-Text API). This identifies the user's emotional state (e.g., relaxed, stressed, excited). This identified emotional state becomes the output.

[0405] Step 3:

[0406] Based on the identified emotional state, the server uses an emotion analysis engine (IBM Watson) to perform a detailed analysis of the user's emotional state. Based on this analysis, it utilizes a generative AI model to generate prompt messages recommending specific products. These prompt messages become the output.

[0407] Step 4:

[0408] Based on the prompt, the server searches the product database for products that match the user's emotional state and creates a list of appropriate products. This product list is the output and serves as the recommended products for the user.

[0409] Step 5:

[0410] The server sends the generated product list to the terminal, where it is displayed to the user on the terminal screen. The user can then select products based on this list. This selection generates user feedback data, which is used to improve the accuracy of recommendations in the future.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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".

[0427] This invention is a system that provides a customized learning experience tailored to the individual needs of each learner. This system is primarily operated by a server, terminals, and users, with each function working together to support learning.

[0428] The server first collects learning history and progress information provided by the user. This information is crucial because it is used for subsequent problem generation and feedback. Next, the server uses a generative AI based on the collected data to generate personalized problems tailored to the learner's understanding and progress. These problems are not simply automatically generated; their quality and reliability are guaranteed through expert review.

[0429] The terminal presents the user with personalized problems provided by the server. The user answers these problems and inputs the results into the terminal. The terminal sends the user's answers to the server and receives feedback in real time. Through the feedback, the user can check their level of understanding and get direction for their next learning.

[0430] As a concrete example, consider a scenario where a user is studying a particular unit of mathematics. In this case, the server generates basic and applied problems for that unit based on the user's progress. The terminal displays these problems and provides the user with detailed explanations after they are solved. Furthermore, additional, more advanced problems can be provided as needed to help the user understand the problems. This allows the user to deepen their knowledge step by step and continue learning efficiently.

[0431] Furthermore, the server incorporates community support features, providing a platform where users can interact with other learners and share information. This feature allows users to post questions and receive advice and answers from other users and AI assistants. This enables learners to support each other and promotes a richer learning experience.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The user selects the unit or subject to study and enters that information into the device. The device then sends the entered information to the server.

[0435] Step 2:

[0436] The server analyzes the user's understanding and weaknesses based on their selections, past learning history, and progress. It then uses these analysis results to generate personalized problems.

[0437] Step 3:

[0438] The server generates a problem and sends it to the terminal. The terminal displays it to the user and asks for an answer.

[0439] Step 4:

[0440] The user answers the questions displayed on the device and enters the answers into the device. The device then sends the answers to the server.

[0441] Step 5:

[0442] The server analyzes the user's answers and generates feedback based on the accuracy rate and answer trends. This feedback may include explanations for incorrect answers.

[0443] Step 6:

[0444] The terminal displays feedback received from the server to the user. The user reviews this feedback and evaluates their level of understanding.

[0445] Step 7:

[0446] The server generates additional problems as needed based on the analysis results, thereby reinforcing the user's learning.

[0447] Step 8:

[0448] If a user wants to deepen their understanding, they can ask questions to other learners through the community support feature. The device's support for this feature facilitates smooth communication.

[0449] Step 9:

[0450] The server posts the user's question to the community forum and waits for answers and advice from other users and AI assistants. The device then displays the received answers to the user.

[0451] This series of processes allows users to learn in a step-by-step and efficient manner.

[0452] (Example 1)

[0453] 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."

[0454] There is a need for a system that can provide an efficient and effective learning experience tailored to the progress and understanding of individual learners. Such a system should not only allow learners to progress at their own pace, but also promote interaction among learners and provide support for achieving a deeper understanding.

[0455] 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.

[0456] In this invention, the server includes means for accumulating progress data and learning history of learners, means for generating personalized tasks based on the accumulated data using a generative AI model, and means for displaying the generated tasks to learners and providing immediate feedback. This makes it possible to provide learners with a personalized learning experience and immediate feedback according to their level of understanding. Furthermore, it becomes possible to provide a more effective learning environment by enabling learners to share information and deepen their interactions with each other.

[0457] "Target learners" are individuals who engage with individual learning content with the aim of improving their skills and knowledge.

[0458] "Progress data" refers to information that shows the results and progress achieved by educated individuals during the learning process.

[0459] "Learning history" refers to a record that includes past learning activities, problems solved, and related results.

[0460] A "generative AI model" is a mathematical model that uses artificial intelligence algorithms to generate output data, such as tasks or content, based on specific input information.

[0461] "Individualized assignments" are problems or learning content that are tailored to the specific needs and level of understanding of the learner, taking into account their progress data and learning history.

[0462] "Immediate feedback" refers to information provided immediately after an educator completes an assignment, pointing out whether their work is correct or incorrect, and identifying areas for improvement.

[0463] "Sharing information and deepening interaction" refers to activities in which educators exchange learning experiences and knowledge with each other, thereby improving their understanding of the learning content and working together to solve problems.

[0464] This invention is a system that provides individualized learning experiences to educators. This system mainly consists of a server, terminals, and users, each providing learning support according to its respective role.

[0465] Server Embodiment

[0466] The server first collects the progress data and learning history of the students. A database management system is often used for this process. Based on the collected data, the server utilizes a generative AI model to create personalized tasks optimized for each student. The generative AI model can use open-source AI tools or models provided by commercial AI providers. The server generates real-time feedback along with the tasks and sends it to the terminal.

[0467] Terminal embodiment

[0468] The device displays personalized assignments provided by the server to the learner. A web application or mobile application could be provided as a useful interface. The device displays real-time feedback to improve the learner's understanding and guide their learning direction.

[0469] User Embodiment

[0470] Users work on problems displayed via their devices and advance their learning through solutions and feedback. If needed, users can share information and interact with other users by utilizing the server's community support features.

[0471] Specific example

[0472] Specifically, consider a scenario where a user is studying calculus (differentiation) in high school mathematics. The server generates application problems related to differentiation based on past exam results and the user's learning history. The terminal displays these problems to the user and provides detailed feedback after they complete them. Based on this information, the user can also solve additional problems tailored to their specific weaknesses.

[0473] Example of a prompt

[0474] "To deepen the understanding of differential calculus among students, please generate problems that cover everything from basic concepts to advanced applications."

[0475] These elements of the system enable learners to have an efficient educational experience and strengthen the support system for deepening their learning.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The server collects learning progress data and learning history from the user. This input data includes the types of questions the user has answered in the past, their accuracy rate, and learning time. The server stores this data in a database and organizes it using a standard database management system. This prepares the foundational data needed to understand the user's learning patterns.

[0479] Step 2:

[0480] The server analyzes the collected data to identify the user's level of understanding and weaknesses. This process involves data aggregation and visualization using data analysis tools. Based on the analysis results, the server generates prompts to utilize the generated AI model. For example, a prompt might be output such as, "Evaluate the user's understanding of differential calculus and generate a suitable application problem."

[0481] Step 3:

[0482] The server inputs prompts and analysis results into a generative AI model to generate problems optimized for each user. The generative AI model used here adjusts the problem content and difficulty level to match the user's skill level. As a result, the output provides material tailored to the user's learning needs.

[0483] Step 4:

[0484] When the terminal receives a problem generated from the server, it creates an interface to display that problem to the user. The terminal presents the problem, for example, in the form of a web browser or mobile app, providing an environment that makes it easy for the user to answer. The output at this stage is a set of problems presented visually to the user.

[0485] Step 5:

[0486] The user answers the questions presented on the device. The user's answers are entered into the device, and the device sends this data to the server, preparing it for further processing. The input data includes the user's answers and the time taken after answering.

[0487] Step 6:

[0488] Upon receiving user response data, the server generates immediate feedback. This feedback generation process includes analysis of accuracy and areas for improvement. The server utilizes an AI model to generate detailed explanations and advice for the next steps, which are then sent to the user's device. The output is provided as real-time feedback to the user.

[0489] Step 7:

[0490] Users receive feedback through their devices to confirm their understanding. This information serves as a guide for determining their next learning plan. Users can also access community support features through their devices and interact with other learners to further develop their knowledge and resolve questions.

[0491] (Application Example 1)

[0492] 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."

[0493] Traditional learning systems struggle to provide effective learning experiences tailored to individual learners' needs. Furthermore, they often lack real-time feedback and expert quality assurance. Additionally, limited interaction with other learners through community support hinders the depth and effectiveness of learning.

[0494] 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.

[0495] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems based on the collected learner progress information and learning history, and means for delivering progress-based educational content to learners in streaming format. This makes it possible to provide learning content that reflects the individual needs of learners in real time and to provide smooth feedback.

[0496] "Learner progress information" refers to the state and progress of learning that a learner has achieved to date.

[0497] "Learning history" refers to a record of past learning activities, including information such as what content was studied and when.

[0498] "Individualized problems" are practice problems that are tailored to a specific learner's level of understanding and needs, and are personalized for that particular learner.

[0499] "Feedback" refers to evaluations and advice regarding learners' answers, and is information that helps learners understand their own learning achievements and decide on their next actions.

[0500] The "community support function" is a feature designed to help learners interact with each other, share information, and help one another.

[0501] "Streaming educational content" is a method of continuously providing learning materials to learners in real time via the internet.

[0502] "Expert review" is a process in which experts with knowledge and experience verify the content of problems and feedback to ensure that they are appropriate and effective.

[0503] "Supplementary questions" are additional questions provided on a particular learning topic, intended to deepen the learner's understanding.

[0504] This invention realizes a system that provides a personalized learning experience based on learner progress information and learning history. It consists of a server, terminals, and users.

[0505] The server is built using backend technologies such as Python and Django, and collects and manages learner progress information and learning history. Furthermore, it utilizes generative AI models (using TensorFlow and PyTorch) based on the collected data to generate personalized problems suited to each learner. In this process, the generated problems are reviewed by experts to ensure their quality.

[0506] The device operates via a smartphone or head-mounted display as its user interface. It displays personalized problems provided by a server and offers real-time feedback to the user. Furthermore, based on the learner's answers, it can stream educational content to support subsequent learning.

[0507] Users answer learning questions via their devices and receive feedback based on their answers. Furthermore, through the community support function, they can interact with other learners, post questions, and receive advice from an AI assistant.

[0508] For example, if a learner is acquiring a new language, the server provides them with targeted questions on specific grammatical points and timely feedback. This aims to facilitate understanding of the questions and maximize learning effectiveness.

[0509] Example prompt: "Please generate practice exercises to help me learn the following topics, focusing on grammar points that I've been struggling with recently."

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The server collects learning history and progress information from the learner's device. This information includes the problems the learner has worked on, their answers, and past feedback. Based on this, it is recorded in a database and processed as basic data for generating the next problems.

[0513] Step 2:

[0514] The server uses collected progress information and learning history to generate personalized problems using a generative AI model. The input here is the learner's history data and progress, and the AI ​​model is applied to generate problems. The output is a set of problems tailored to the learner's level of understanding. The model generates appropriate problems based on prompt statements.

[0515] Step 3:

[0516] The server sends the generated individualized problems to the terminal. The terminal receives them and displays them on the user interface. Here, the input is the set of problems received from the server, and the output is showing the problems to the learner. This allows the learner to work on the problems through the terminal.

[0517] Step 4:

[0518] The user enters their answer to a question via a terminal. The terminal then sends this answer to the server. The input is the learner's answer, and the output is the data to be sent to the server. This ensures that the answer results are delivered to the server quickly.

[0519] Step 5:

[0520] The server analyzes the received answers and quickly generates feedback. This process involves making judgments based on the correctness of the answers and generating additional supplementary explanations as needed. The input is the learner's answer data, and the output is feedback information.

[0521] Step 6:

[0522] Feedback generated from the server is sent to the terminal, allowing the user to confirm their learning understanding. The input is the feedback data, and the output is displaying the feedback to the user. This enables the user to decide on the next learning step.

[0523] Step 7:

[0524] Users can utilize community support features as needed to interact with other learners. They can post questions and receive answers through their devices. Input consists of questions and posts from users, while output consists of answers from other learners and AI.

[0525] 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.

[0526] This invention introduces emotion recognition technology into learning systems to further personalize the learning experience. The system consists of server, terminal, and user interaction, and optimizes the learning process with an emotion engine at its core.

[0527] The server collects user progress information, learning history, and emotional data. The emotion engine uses the device's camera and sensors to monitor the user's facial expressions, tone of voice, posture, etc., and analyzes the user's emotional state in real time. This allows the system to recognize the stress, excitement, and level of concentration the user experiences while solving problems.

[0528] Based on the collected data, the server generates personalized problems that reflect the user's emotional state. For example, if the system detects that the user is stressed, it adjusts the difficulty of the problem to provide a more relaxed experience. It can also provide inspiring feedback and advice to boost motivation.

[0529] The device presents the user with adaptive problems and feedback sent from the server. The user can continuously adjust the learning process by answering these and accepting feedback as needed.

[0530] For example, if a user is learning a language and the emotion engine detects fatigue from prolonged learning, the server will reduce the user's burden by presenting lighter quiz-style questions instead of listening comprehension exercises. It will also help maintain an efficient learning cycle by providing the user with appropriate break advice.

[0531] This system allows learners to have a flexible learning experience based on their own emotions and progress, and is expected to improve learning efficiency.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The user selects the subject to study and enters it into the terminal. The terminal then sends the selection information to the server.

[0535] Step 2:

[0536] The device uses cameras and sensors to monitor the user's emotional state in real time and collect emotional data.

[0537] Step 3:

[0538] The server analyzes the user's level of understanding and current emotional state based on learning progress, learning history, and sentiment data received from the user.

[0539] Step 4:

[0540] Based on the analysis results, the server generates personalized problems tailored to the user's emotional state and learning needs. For example, if the user is feeling stressed, it will generate easier problems.

[0541] Step 5:

[0542] The server sends the generated problems to the terminal. The terminal displays these problems to the user and prompts them to answer.

[0543] Step 6:

[0544] The user submits an answer and enters it into the device. The device then sends the answer to the server.

[0545] Step 7:

[0546] The server analyzes the user's answers and generates feedback based on the results. This feedback may include explanations to improve understanding and positive, encouraging messages.

[0547] Step 8:

[0548] The server sends the generated feedback to the terminal. The terminal presents the feedback to the user and instructs them on the next step.

[0549] Step 9:

[0550] The user reviews the feedback provided and decides on actions to take to proceed with the next learning step as needed. The emotion engine continuously monitors emotional data, allowing the learning process to be dynamically adjusted.

[0551] (Example 2)

[0552] 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."

[0553] In conventional learning systems, it has been difficult to provide individualized learning experiences that take into account the learner's emotional state. A challenge is that learning efficiency is impaired because the learning content cannot be appropriately adjusted when learners experience stress or a decline in concentration.

[0554] 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.

[0555] In this invention, the server includes means for collecting learner progress information, learning history, and emotional information; means for analyzing the learner's emotional state using a terminal input device; and means for generating personalized problems based on the collected and analyzed information. This enables the provision of problems that take the learner's emotional state into consideration and adaptive feedback.

[0556] "Progress information" refers to data that shows how much progress a learner has made in relation to a specific learning topic.

[0557] "Learning history" refers to records of learning activities that a learner has undertaken in the past and the results thereof.

[0558] "Emotional information" refers to data about the learner's emotional state, including stress levels, excitement, and concentration levels.

[0559] A "terminal" refers to an electronic device used by learners that is equipped with a camera and microphone and can sense the user's state.

[0560] "Individualized problems" refer to learning tasks and problems that are tailored based on the individual progress and emotional state of each learner.

[0561] "Feedback" refers to advice and evaluations provided to learners to improve their learning process.

[0562] "Analysis" refers to the process of analyzing data collected by terminals and servers to understand the learner's emotional state and learning tendencies.

[0563] This invention aims to provide an individualized learning experience by considering the learner's emotional state in a learning system. The system is built on the interaction between the server, terminal, and user, and optimizes the learning process by utilizing emotion recognition technology.

[0564] The server first collects user progress information, learning history, and sentiment data. For this purpose, learning applications and platforms are used, and progress information such as the number of problems solved, accuracy rate, and learning time is regularly recorded. The collected data is stored in a database and used for subsequent analysis and problem generation.

[0565] The device uses its camera and microphone to analyze the user's emotional state in real time. Video data collected through the built-in camera and audio data from the microphone are processed using AI libraries such as OpenCV and TensorFlow to estimate the user's emotions from their facial expressions and tone of voice. This analysis provides feedback to the server regarding the user's emotional state, such as whether they are stressed or highly focused.

[0566] The server generates personalized problems tailored to the user based on collected progress and sentiment data. It utilizes generative AI models and Python libraries such as NLTK and Transformers to create problems that match the user's characteristics. For example, if analysis indicates a user is feeling tired, it supports the learner by providing problems of lower difficulty.

[0567] For example, if a user is learning a language and emotion analysis determines that their concentration is declining, the system will present them with a light quiz-style question and display advice on the device suggesting they take a break. An example of a prompt message could be, "Analyze the user's facial expression data and suggest appropriate learning content."

[0568] This system allows users to continuously receive learning content and feedback tailored to their individual circumstances, which is expected to improve learning efficiency.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The server collects user progress information, learning history, and sentiment data. Inputs include user task completion status, learning time, and accuracy rates obtained from the learning platform. This data is stored in a database, and output is obtained to prepare for future analysis. Specifically, the server defines a process for periodically acquiring data by setting collection times.

[0572] Step 2:

[0573] The device analyzes the user's emotional state based on video and audio input. It acquires data in real time through the camera and microphone and receives it as input. This data is processed by an emotion analysis algorithm using OpenCV or TensorFlow to obtain an output that estimates the user's emotional state from their facial expressions and tone of voice. Specifically, it recognizes facial features such as whether the user is smiling or frowning, and classifies the emotion.

[0574] Step 3:

[0575] The server generates personalized problems based on collected progress information and sentiment data. It uses sentiment state data and learning progress data obtained in the previous step as input. A generative AI model is used to adjust the difficulty and content of the problems, outputting the most appropriate problems for the user. For example, if the sentiment state is recognized as "fatigue," a problem with a lower difficulty level is generated to reduce the learning load.

[0576] Step 4:

[0577] The server generates feedback for the user and sends it to the terminal. It receives sentiment data and the answer to a problem as input and produces output that creates feedback to improve the user's learning motivation. Specifically, it takes the form of an encouraging message if the user answers correctly and suggestions for improvement if they answer incorrectly.

[0578] Step 5:

[0579] Users work on personalized problems provided on their devices and receive feedback. As input, they answer a set of problems sent from the server and send their results back to the server. This triggers a process where learning progress and sentiment data are collected again, yielding new output to adjust the next learning cycle. Specifically, this involves solving problems on the device screen and uploading the answers to the server.

[0580] (Application Example 2)

[0581] 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."

[0582] Conventional learning systems and product recommendation systems do not adequately consider the user's emotional state during optimization, resulting in a failure to improve user experience and purchase intent.

[0583] 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.

[0584] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems, and means for analyzing the user's video and audio data and evaluating their emotional state. This enables flexible learning and product recommendations based on the user's individual emotional state.

[0585] "Learner progress information" refers to data that shows the extent to which learners have completed assignments and learning materials.

[0586] "Learning history" refers to data that records the history of learning materials and problems that a learner has studied so far.

[0587] "Individualized questions" are questions created specifically for learners, based on their progress information and emotional state.

[0588] "Feedback" refers to advice and evaluations provided based on a learner's answers, designed to improve the learning process.

[0589] The "community support function" provides a feature that allows learners to interact with each other and share information.

[0590] "Video data" refers to visual information that captures the learner's facial expressions and movements.

[0591] "Audio data" refers to acoustic information that records the learner's voice.

[0592] "Means for evaluating emotional state" refers to techniques that analyze collected video and audio data to determine the emotional state of learners.

[0593] "Methods for recommending products" refers to the process of selecting and suggesting appropriate products based on the analyzed emotional state of the learner.

[0594] To implement this invention, the user uses a device such as a smartphone or smart glasses. The device is equipped with a camera and microphone, which capture the user's video and audio data in real time. The server is equipped with facial recognition software (e.g., OpenCV) and speech analysis software (e.g., Google's Speech-to-Text API) to process this data. Furthermore, IBM's Watson is used as a technology to analyze emotional states.

[0595] The server stores user progress information and learning history in a database and implements algorithms to generate personalized problems. User emotional state data is analyzed by the server and used as data to recommend products based on the individual's emotional state. This provides a learning and product selection experience that is adapted to the user's emotional state.

[0596] For example, if the device detects a user's stress level, an algorithm running on the server generates and recommends a list of products with relaxing effects. In another example, if the system analyzes the user as agitated, products related to active activities will be presented. This analysis and recommendation process achieves greater accuracy and personalization by utilizing generative AI models to generate prompts. Examples of prompts include, "Please recommend products that will help the user relax," and "How can we suggest products suitable for an agitated user?"

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1:

[0599] When a user begins browsing an e-commerce site on their device, the device uses its camera and microphone to collect video and audio data of the user. This data, which includes the user's facial expressions and tone of voice, is sent to the server as input.

[0600] Step 2:

[0601] The server processes the acquired video data using facial recognition software (OpenCV) and simultaneously analyzes the audio data using speech analysis software (Google's Speech-to-Text API). This identifies the user's emotional state (e.g., relaxed, stressed, excited). This identified emotional state becomes the output.

[0602] Step 3:

[0603] Based on the identified emotional state, the server uses an emotion analysis engine (IBM Watson) to perform a detailed analysis of the user's emotional state. Based on this analysis, it utilizes a generative AI model to generate prompt messages recommending specific products. These prompt messages become the output.

[0604] Step 4:

[0605] Based on the prompt, the server searches the product database for products that match the user's emotional state and creates a list of appropriate products. This product list is the output and serves as the recommended products for the user.

[0606] Step 5:

[0607] The server sends the generated product list to the terminal, where it is displayed to the user on the terminal screen. The user can then select products based on this list. This selection generates user feedback data, which is used to improve the accuracy of recommendations in the future.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] [Fourth Embodiment]

[0612] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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".

[0625] This invention is a system that provides a customized learning experience tailored to the individual needs of each learner. This system is primarily operated by a server, terminals, and users, with each function working together to support learning.

[0626] The server first collects learning history and progress information provided by the user. This information is crucial because it is used for subsequent problem generation and feedback. Next, the server uses a generative AI based on the collected data to generate personalized problems tailored to the learner's understanding and progress. These problems are not simply automatically generated; their quality and reliability are guaranteed through expert review.

[0627] The terminal presents the user with personalized problems provided by the server. The user answers these problems and inputs the results into the terminal. The terminal sends the user's answers to the server and receives feedback in real time. Through the feedback, the user can check their level of understanding and get direction for their next learning.

[0628] As a concrete example, consider a scenario where a user is studying a particular unit of mathematics. In this case, the server generates basic and applied problems for that unit based on the user's progress. The terminal displays these problems and provides the user with detailed explanations after they are solved. Furthermore, additional, more advanced problems can be provided as needed to help the user understand the problems. This allows the user to deepen their knowledge step by step and continue learning efficiently.

[0629] Furthermore, the server incorporates community support features, providing a platform where users can interact with other learners and share information. This feature allows users to post questions and receive advice and answers from other users and AI assistants. This enables learners to support each other and promotes a richer learning experience.

[0630] The following describes the processing flow.

[0631] Step 1:

[0632] The user selects the unit or subject to study and enters that information into the device. The device then sends the entered information to the server.

[0633] Step 2:

[0634] The server analyzes the user's understanding and weaknesses based on their selections, past learning history, and progress. It then uses these analysis results to generate personalized problems.

[0635] Step 3:

[0636] The server generates a problem and sends it to the terminal. The terminal displays it to the user and asks for an answer.

[0637] Step 4:

[0638] The user answers the questions displayed on the device and enters the answers into the device. The device then sends the answers to the server.

[0639] Step 5:

[0640] The server analyzes the user's answers and generates feedback based on the accuracy rate and answer trends. This feedback may include explanations for incorrect answers.

[0641] Step 6:

[0642] The terminal displays feedback received from the server to the user. The user reviews this feedback and evaluates their level of understanding.

[0643] Step 7:

[0644] The server generates additional problems as needed based on the analysis results, thereby reinforcing the user's learning.

[0645] Step 8:

[0646] If a user wants to deepen their understanding, they can ask questions to other learners through the community support feature. The device's support for this feature facilitates smooth communication.

[0647] Step 9:

[0648] The server posts the user's question to the community forum and waits for answers and advice from other users and AI assistants. The device then displays the received answers to the user.

[0649] This series of processes allows users to learn in a step-by-step and efficient manner.

[0650] (Example 1)

[0651] 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".

[0652] There is a need for a system that can provide an efficient and effective learning experience tailored to the progress and understanding of individual learners. Such a system should not only allow learners to progress at their own pace, but also promote interaction among learners and provide support for achieving a deeper understanding.

[0653] 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.

[0654] In this invention, the server includes means for accumulating progress data and learning history of learners, means for generating personalized tasks based on the accumulated data using a generative AI model, and means for displaying the generated tasks to learners and providing immediate feedback. This makes it possible to provide learners with a personalized learning experience and immediate feedback according to their level of understanding. Furthermore, it becomes possible to provide a more effective learning environment by enabling learners to share information and deepen their interactions with each other.

[0655] "Target learners" are individuals who engage with individual learning content with the aim of improving their skills and knowledge.

[0656] "Progress data" refers to information that shows the results and progress achieved by educated individuals during the learning process.

[0657] "Learning history" refers to a record that includes past learning activities, problems solved, and related results.

[0658] A "generative AI model" is a mathematical model that uses artificial intelligence algorithms to generate output data, such as tasks or content, based on specific input information.

[0659] "Individualized assignments" are problems or learning content that are tailored to the specific needs and level of understanding of the learner, taking into account their progress data and learning history.

[0660] "Immediate feedback" refers to information provided immediately after an educator completes an assignment, pointing out whether their work is correct or incorrect, and identifying areas for improvement.

[0661] "Sharing information and deepening interaction" refers to activities in which educators exchange learning experiences and knowledge with each other, thereby improving their understanding of the learning content and working together to solve problems.

[0662] This invention is a system that provides individualized learning experiences to educators. This system mainly consists of a server, terminals, and users, each providing learning support according to its respective role.

[0663] Server Embodiment

[0664] The server first collects the progress data and learning history of the students. A database management system is often used for this process. Based on the collected data, the server utilizes a generative AI model to create personalized tasks optimized for each student. The generative AI model can use open-source AI tools or models provided by commercial AI providers. The server generates real-time feedback along with the tasks and sends it to the terminal.

[0665] Terminal embodiment

[0666] The device displays personalized assignments provided by the server to the learner. A web application or mobile application could be provided as a useful interface. The device displays real-time feedback to improve the learner's understanding and guide their learning direction.

[0667] User Embodiment

[0668] Users work on problems displayed via their devices and advance their learning through solutions and feedback. If needed, users can share information and interact with other users by utilizing the server's community support features.

[0669] Specific example

[0670] Specifically, consider a scenario where a user is studying calculus (differentiation) in high school mathematics. The server generates application problems related to differentiation based on past exam results and the user's learning history. The terminal displays these problems to the user and provides detailed feedback after they complete them. Based on this information, the user can also solve additional problems tailored to their specific weaknesses.

[0671] Example of a prompt

[0672] "To deepen the understanding of differential calculus among students, please generate problems that cover everything from basic concepts to advanced applications."

[0673] These elements of the system enable learners to have an efficient educational experience and strengthen the support system for deepening their learning.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The server collects learning progress data and learning history from the user. This input data includes the types of questions the user has answered in the past, their accuracy rate, and learning time. The server stores this data in a database and organizes it using a standard database management system. This prepares the foundational data needed to understand the user's learning patterns.

[0677] Step 2:

[0678] The server analyzes the collected data to identify the user's level of understanding and weaknesses. This process involves data aggregation and visualization using data analysis tools. Based on the analysis results, the server generates prompts to utilize the generated AI model. For example, a prompt might be output such as, "Evaluate the user's understanding of differential calculus and generate a suitable application problem."

[0679] Step 3:

[0680] The server inputs prompts and analysis results into a generative AI model to generate problems optimized for each user. The generative AI model used here adjusts the problem content and difficulty level to match the user's skill level. As a result, the output provides material tailored to the user's learning needs.

[0681] Step 4:

[0682] When the terminal receives a problem generated from the server, it creates an interface to display that problem to the user. The terminal presents the problem, for example, in the form of a web browser or mobile app, providing an environment that makes it easy for the user to answer. The output at this stage is a set of problems presented visually to the user.

[0683] Step 5:

[0684] The user answers the questions presented on the device. The user's answers are entered into the device, and the device sends this data to the server, preparing it for further processing. The input data includes the user's answers and the time taken after answering.

[0685] Step 6:

[0686] Upon receiving user response data, the server generates immediate feedback. This feedback generation process includes analysis of accuracy and areas for improvement. The server utilizes an AI model to generate detailed explanations and advice for the next steps, which are then sent to the user's device. The output is provided as real-time feedback to the user.

[0687] Step 7:

[0688] Users receive feedback through their devices to confirm their understanding. This information serves as a guide for determining their next learning plan. Users can also access community support features through their devices and interact with other learners to further develop their knowledge and resolve questions.

[0689] (Application Example 1)

[0690] 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".

[0691] Traditional learning systems struggle to provide effective learning experiences tailored to individual learners' needs. Furthermore, they often lack real-time feedback and expert quality assurance. Additionally, limited interaction with other learners through community support hinders the depth and effectiveness of learning.

[0692] 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.

[0693] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems based on the collected learner progress information and learning history, and means for delivering progress-based educational content to learners in streaming format. This makes it possible to provide learning content that reflects the individual needs of learners in real time and to provide smooth feedback.

[0694] "Learner progress information" refers to the state and progress of learning that a learner has achieved to date.

[0695] "Learning history" refers to a record of past learning activities, including information such as what content was studied and when.

[0696] "Individualized problems" are practice problems that are tailored to a specific learner's level of understanding and needs, and are personalized for that particular learner.

[0697] "Feedback" refers to evaluations and advice regarding learners' answers, and is information that helps learners understand their own learning achievements and decide on their next actions.

[0698] The "community support function" is a feature designed to help learners interact with each other, share information, and help one another.

[0699] "Streaming educational content" is a method of continuously providing learning materials to learners in real time via the internet.

[0700] "Expert review" is a process in which experts with knowledge and experience verify the content of problems and feedback to ensure that they are appropriate and effective.

[0701] "Supplementary questions" are additional questions provided on a particular learning topic, intended to deepen the learner's understanding.

[0702] This invention realizes a system that provides a personalized learning experience based on learner progress information and learning history. It consists of a server, terminals, and users.

[0703] The server is built using backend technologies such as Python and Django, and collects and manages learner progress information and learning history. Furthermore, it utilizes generative AI models (using TensorFlow and PyTorch) based on the collected data to generate personalized problems suited to each learner. In this process, the generated problems are reviewed by experts to ensure their quality.

[0704] The device operates via a smartphone or head-mounted display as its user interface. It displays personalized problems provided by a server and offers real-time feedback to the user. Furthermore, based on the learner's answers, it can stream educational content to support subsequent learning.

[0705] Users answer learning questions via their devices and receive feedback based on their answers. Furthermore, through the community support function, they can interact with other learners, post questions, and receive advice from an AI assistant.

[0706] For example, if a learner is acquiring a new language, the server provides them with targeted questions on specific grammatical points and timely feedback. This aims to facilitate understanding of the questions and maximize learning effectiveness.

[0707] Example prompt: "Please generate practice exercises to help me learn the following topics, focusing on grammar points that I've been struggling with recently."

[0708] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0709] Step 1:

[0710] The server collects learning history and progress information from the learner's device. This information includes the problems the learner has worked on, their answers, and past feedback. Based on this, it is recorded in a database and processed as basic data for generating the next problems.

[0711] Step 2:

[0712] The server uses collected progress information and learning history to generate personalized problems using a generative AI model. The input here is the learner's history data and progress, and the AI ​​model is applied to generate problems. The output is a set of problems tailored to the learner's level of understanding. The model generates appropriate problems based on prompt statements.

[0713] Step 3:

[0714] The server sends the generated individualized problems to the terminal. The terminal receives them and displays them on the user interface. Here, the input is the set of problems received from the server, and the output is showing the problems to the learner. This allows the learner to work on the problems through the terminal.

[0715] Step 4:

[0716] The user enters their answer to a question via a terminal. The terminal then sends this answer to the server. The input is the learner's answer, and the output is the data to be sent to the server. This ensures that the answer results are delivered to the server quickly.

[0717] Step 5:

[0718] The server analyzes the received answers and quickly generates feedback. This process involves making judgments based on the correctness of the answers and generating additional supplementary explanations as needed. The input is the learner's answer data, and the output is feedback information.

[0719] Step 6:

[0720] Feedback generated from the server is sent to the terminal, allowing the user to confirm their learning understanding. The input is the feedback data, and the output is displaying the feedback to the user. This enables the user to decide on the next learning step.

[0721] Step 7:

[0722] Users can utilize community support features as needed to interact with other learners. They can post questions and receive answers through their devices. Input consists of questions and posts from users, while output consists of answers from other learners and AI.

[0723] 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.

[0724] This invention introduces emotion recognition technology into learning systems to further personalize the learning experience. The system consists of server, terminal, and user interaction, and optimizes the learning process with an emotion engine at its core.

[0725] The server collects user progress information, learning history, and emotional data. The emotion engine uses the device's camera and sensors to monitor the user's facial expressions, tone of voice, posture, etc., and analyzes the user's emotional state in real time. This allows the system to recognize the stress, excitement, and level of concentration the user experiences while solving problems.

[0726] Based on the collected data, the server generates personalized problems that reflect the user's emotional state. For example, if the system detects that the user is stressed, it adjusts the difficulty of the problem to provide a more relaxed experience. It can also provide inspiring feedback and advice to boost motivation.

[0727] The device presents the user with adaptive problems and feedback sent from the server. The user can continuously adjust the learning process by answering these and accepting feedback as needed.

[0728] For example, if a user is learning a language and the emotion engine detects fatigue from prolonged learning, the server will reduce the user's burden by presenting lighter quiz-style questions instead of listening comprehension exercises. It will also help maintain an efficient learning cycle by providing the user with appropriate break advice.

[0729] This system allows learners to have a flexible learning experience based on their own emotions and progress, and is expected to improve learning efficiency.

[0730] The following describes the processing flow.

[0731] Step 1:

[0732] The user selects the subject to study and enters it into the terminal. The terminal then sends the selection information to the server.

[0733] Step 2:

[0734] The device uses cameras and sensors to monitor the user's emotional state in real time and collect emotional data.

[0735] Step 3:

[0736] The server analyzes the user's level of understanding and current emotional state based on learning progress, learning history, and sentiment data received from the user.

[0737] Step 4:

[0738] Based on the analysis results, the server generates personalized problems tailored to the user's emotional state and learning needs. For example, if the user is feeling stressed, it will generate easier problems.

[0739] Step 5:

[0740] The server sends the generated problems to the terminal. The terminal displays these problems to the user and prompts them to answer.

[0741] Step 6:

[0742] The user submits an answer and enters it into the device. The device then sends the answer to the server.

[0743] Step 7:

[0744] The server analyzes the user's answers and generates feedback based on the results. This feedback may include explanations to improve understanding and positive, encouraging messages.

[0745] Step 8:

[0746] The server sends the generated feedback to the terminal. The terminal presents the feedback to the user and instructs them on the next step.

[0747] Step 9:

[0748] The user reviews the feedback provided and decides on actions to take to proceed with the next learning step as needed. The emotion engine continuously monitors emotional data, allowing the learning process to be dynamically adjusted.

[0749] (Example 2)

[0750] 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".

[0751] In conventional learning systems, it has been difficult to provide individualized learning experiences that take into account the learner's emotional state. A challenge is that learning efficiency is impaired because the learning content cannot be appropriately adjusted when learners experience stress or a decline in concentration.

[0752] 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.

[0753] In this invention, the server includes means for collecting learner progress information, learning history, and emotional information; means for analyzing the learner's emotional state using a terminal input device; and means for generating personalized problems based on the collected and analyzed information. This enables the provision of problems that take the learner's emotional state into consideration and adaptive feedback.

[0754] "Progress information" refers to data that shows how much progress a learner has made in relation to a specific learning topic.

[0755] "Learning history" refers to records of learning activities that a learner has undertaken in the past and the results thereof.

[0756] "Emotional information" refers to data about the learner's emotional state, including stress levels, excitement, and concentration levels.

[0757] A "terminal" refers to an electronic device used by learners that is equipped with a camera and microphone and can sense the user's state.

[0758] "Individualized problems" refer to learning tasks and problems that are tailored based on the individual progress and emotional state of each learner.

[0759] "Feedback" refers to advice and evaluations provided to learners to improve their learning process.

[0760] "Analysis" refers to the process of analyzing data collected by terminals and servers to understand the learner's emotional state and learning tendencies.

[0761] This invention aims to provide an individualized learning experience by considering the learner's emotional state in a learning system. The system is built on the interaction between the server, terminal, and user, and optimizes the learning process by utilizing emotion recognition technology.

[0762] The server first collects user progress information, learning history, and sentiment data. For this purpose, learning applications and platforms are used, and progress information such as the number of problems solved, accuracy rate, and learning time is regularly recorded. The collected data is stored in a database and used for subsequent analysis and problem generation.

[0763] The device uses its camera and microphone to analyze the user's emotional state in real time. Video data collected through the built-in camera and audio data from the microphone are processed using AI libraries such as OpenCV and TensorFlow to estimate the user's emotions from their facial expressions and tone of voice. This analysis provides feedback to the server regarding the user's emotional state, such as whether they are stressed or highly focused.

[0764] The server generates personalized problems tailored to the user based on collected progress and sentiment data. It utilizes generative AI models and Python libraries such as NLTK and Transformers to create problems that match the user's characteristics. For example, if analysis indicates a user is feeling tired, it supports the learner by providing problems of lower difficulty.

[0765] For example, if a user is learning a language and emotion analysis determines that their concentration is declining, the system will present them with a light quiz-style question and display advice on the device suggesting they take a break. An example of a prompt message could be, "Analyze the user's facial expression data and suggest appropriate learning content."

[0766] This system allows users to continuously receive learning content and feedback tailored to their individual circumstances, which is expected to improve learning efficiency.

[0767] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0768] Step 1:

[0769] The server collects user progress information, learning history, and sentiment data. Inputs include user task completion status, learning time, and accuracy rates obtained from the learning platform. This data is stored in a database, and output is obtained to prepare for future analysis. Specifically, the server defines a process for periodically acquiring data by setting collection times.

[0770] Step 2:

[0771] The device analyzes the user's emotional state based on video and audio input. It acquires data in real time through the camera and microphone and receives it as input. This data is processed by an emotion analysis algorithm using OpenCV or TensorFlow to obtain an output that estimates the user's emotional state from their facial expressions and tone of voice. Specifically, it recognizes facial features such as whether the user is smiling or frowning, and classifies the emotion.

[0772] Step 3:

[0773] The server generates personalized problems based on collected progress information and sentiment data. It uses sentiment state data and learning progress data obtained in the previous step as input. A generative AI model is used to adjust the difficulty and content of the problems, outputting the most appropriate problems for the user. For example, if the sentiment state is recognized as "fatigue," a problem with a lower difficulty level is generated to reduce the learning load.

[0774] Step 4:

[0775] The server generates feedback for the user and sends it to the terminal. It receives sentiment data and the answer to a problem as input and produces output that creates feedback to improve the user's learning motivation. Specifically, it takes the form of an encouraging message if the user answers correctly and suggestions for improvement if they answer incorrectly.

[0776] Step 5:

[0777] Users work on personalized problems provided on their devices and receive feedback. As input, they answer a set of problems sent from the server and send their results back to the server. This triggers a process where learning progress and sentiment data are collected again, yielding new output to adjust the next learning cycle. Specifically, this involves solving problems on the device screen and uploading the answers to the server.

[0778] (Application Example 2)

[0779] 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".

[0780] Conventional learning systems and product recommendation systems do not adequately consider the user's emotional state during optimization, resulting in a failure to improve user experience and purchase intent.

[0781] 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.

[0782] In this invention, the server includes means for collecting learner progress information and learning history, means for generating personalized problems, and means for analyzing the user's video and audio data and evaluating their emotional state. This enables flexible learning and product recommendations based on the user's individual emotional state.

[0783] "Learner progress information" refers to data that shows the extent to which learners have completed assignments and learning materials.

[0784] "Learning history" refers to data that records the history of learning materials and problems that a learner has studied so far.

[0785] "Individualized questions" are questions created specifically for learners, based on their progress information and emotional state.

[0786] "Feedback" refers to advice and evaluations provided based on a learner's answers, designed to improve the learning process.

[0787] The "community support function" provides a feature that allows learners to interact with each other and share information.

[0788] "Video data" refers to visual information that captures the learner's facial expressions and movements.

[0789] "Audio data" refers to acoustic information that records the learner's voice.

[0790] "Means for evaluating emotional state" refers to techniques that analyze collected video and audio data to determine the emotional state of learners.

[0791] "Methods for recommending products" refers to the process of selecting and suggesting appropriate products based on the analyzed emotional state of the learner.

[0792] To implement this invention, the user uses a device such as a smartphone or smart glasses. The device is equipped with a camera and microphone, which capture the user's video and audio data in real time. The server is equipped with facial recognition software (e.g., OpenCV) and speech analysis software (e.g., Google's Speech-to-Text API) to process this data. Furthermore, IBM's Watson is used as a technology to analyze emotional states.

[0793] The server stores user progress information and learning history in a database and implements algorithms to generate personalized problems. User emotional state data is analyzed by the server and used as data to recommend products based on the individual's emotional state. This provides a learning and product selection experience that is adapted to the user's emotional state.

[0794] For example, if the device detects a user's stress level, an algorithm running on the server generates and recommends a list of products with relaxing effects. In another example, if the system analyzes the user as agitated, products related to active activities will be presented. This analysis and recommendation process achieves greater accuracy and personalization by utilizing generative AI models to generate prompts. Examples of prompts include, "Please recommend products that will help the user relax," and "How can we suggest products suitable for an agitated user?"

[0795] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0796] Step 1:

[0797] When a user begins browsing an e-commerce site on their device, the device uses its camera and microphone to collect video and audio data of the user. This data, which includes the user's facial expressions and tone of voice, is sent to the server as input.

[0798] Step 2:

[0799] The server processes the acquired video data using facial recognition software (OpenCV) and simultaneously analyzes the audio data using speech analysis software (Google's Speech-to-Text API). This identifies the user's emotional state (e.g., relaxed, stressed, excited). This identified emotional state becomes the output.

[0800] Step 3:

[0801] Based on the identified emotional state, the server uses an emotion analysis engine (IBM Watson) to perform a detailed analysis of the user's emotional state. Based on this analysis, it utilizes a generative AI model to generate prompt messages recommending specific products. These prompt messages become the output.

[0802] Step 4:

[0803] Based on the prompt, the server searches the product database for products that match the user's emotional state and creates a list of appropriate products. This product list is the output and serves as the recommended products for the user.

[0804] Step 5:

[0805] The server sends the generated product list to the terminal, where it is displayed to the user on the terminal screen. The user can then select products based on this list. This selection generates user feedback data, which is used to improve the accuracy of recommendations in the future.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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."

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] Means for collecting learner progress information and learning history,

[0830] A means for generating personalized problems based on collected learner progress information and learning history,

[0831] A means of providing learners with generated problems, analyzing their answers, and giving feedback,

[0832] A means of providing community support features for learners to interact with other learners,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, wherein the generated questions are reviewed by experts in order to ensure the quality of the questions and feedback provided to learners.

[0836] (Claim 3)

[0837] The system according to claim 1, which automatically adjusts and provides supplementary questions suitable for the next learning session based on an analysis of the learner's answers.

[0838] "Example 1"

[0839] (Claim 1)

[0840] A means of collecting progress data and learning history of educated individuals,

[0841] A means of using a generative AI model to generate individualized tasks based on the accumulated progress data and learning history of educated individuals,

[0842] A means of displaying the generated assignments to the target audience, analyzing their response data, and providing immediate feedback,

[0843] A means of providing support functions for educated individuals to share information and interact with other educated individuals,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, wherein the generated assignments are evaluated by experts in order to maintain the quality of the assignments and feedback provided to the educators.

[0847] (Claim 3)

[0848] The system according to claim 1, which automatically adjusts and provides appropriate additional assignments for the next student to learn, based on an analysis of the student's response results.

[0849] "Application Example 1"

[0850] (Claim 1)

[0851] Means for collecting learner progress information and learning history,

[0852] A means for generating personalized problems based on collected learner progress information and learning history,

[0853] A means of providing learners with generated problems, analyzing their answers, and giving feedback,

[0854] A means of providing community support features for learners to interact with other learners,

[0855] A means of delivering progress-based educational content to learners via streaming,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein the generated questions are reviewed by experts in order to ensure the quality of the questions and feedback provided to learners.

[0859] (Claim 3)

[0860] The system according to claim 1, which automatically adjusts and provides supplementary questions and additional resources suitable for the next learning session based on an analysis of the learner's answers.

[0861] "Example 2 of combining an emotion engine"

[0862] (Claim 1)

[0863] A means of collecting learner progress information, learning history, and sentiment information,

[0864] A means of analyzing the learner's emotional state using the terminal's input device,

[0865] Means for generating personalized problems based on collected and analyzed information,

[0866] A means of providing learners with generated problems and adaptive feedback, and making adjustments based on the learners' emotional state based on their answers,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, comprising an algorithm for analyzing emotional information.

[0870] (Claim 3)

[0871] The system according to claim 1, comprising a function to automatically adjust questions and feedback based on the learner's emotional state.

[0872] "Application example 2 when combining with an emotional engine"

[0873] (Claim 1)

[0874] Means for collecting learner progress information and learning history,

[0875] A means for generating personalized problems based on collected learner progress information and learning history,

[0876] A means of providing learners with generated problems, analyzing their answers, and giving feedback,

[0877] A means of providing community support features for learners to interact with other learners,

[0878] A means for analyzing a user's video and audio data to evaluate their emotional state,

[0879] A method for recommending products based on the user's emotional state,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, wherein the generated questions are reviewed by experts in order to ensure the quality of the questions and feedback provided to learners.

[0883] (Claim 3)

[0884] The system according to claim 1, which automatically adjusts and provides supplementary questions suitable for the next learning session based on an analysis of the learner's answers. [Explanation of Symbols]

[0885] 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. Means for collecting learner progress information and learning history, A means for generating personalized problems based on collected learner progress information and learning history, A means of providing learners with generated problems, analyzing their answers, and giving feedback, A means of providing community support features for learners to interact with other learners, A system that includes this.

2. The system according to claim 1, wherein the generated problems are reviewed by experts in order to ensure the quality of the problems and feedback provided to learners.

3. The system according to claim 1, which automatically adjusts and provides supplementary questions suitable for the next learning session based on an analysis of the learner's answers.

Images