system

Abstract

Provide a system. 【Solution means】 Means for collecting learner data and storing it in a cloud environment, Means for analyzing the stored learner data to identify individual learning styles and tendencies, Means for generating a learning curriculum optimized for the learner based on the analysis results, Means for presenting teaching materials and tasks to the learner according to the generated curriculum, Means for automatically creating a draft for the output made by the learner, Means for monitoring the learner's progress in real time and providing feedback on areas for improvement, Means for responding to the learner's questions using virtual education staff, Means for visualizing and presenting the learner's progress status, Means for interacting with the learner within the home and dynamically adjusting the learning difficulty, Means for adjusting the learning content based on the learner's reaction speed and correct answer rate, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern learning environments, since learners have different learning styles and ways of skill growth, there is a problem that a uniform educational method cannot sufficiently enhance the learning effect. Also, especially in remote or rural areas, access to high - quality educational resources may be limited, raising concerns about educational disparities. Furthermore, due to insufficient learning progress management, there is also a problem that it is difficult for learners to maintain motivation.

Means for Solving the Problems

[0005] This invention provides a means for collecting learner data and analyzing individual learning styles and tendencies based on that data. It also includes a system that generates an optimized learning curriculum for each learner based on the analysis results and presents corresponding learning materials and tasks. Furthermore, this system has a means for automatically creating drafts of learner outputs and also features real-time progress monitoring and feedback functions. In particular, a response mechanism using a virtual teacher immediately resolves learner questions and maintains motivation through the visualization of progress. This makes it possible to achieve a high-quality individualized learning experience and improve the efficiency of education.

[0006] "Learner data" refers to a collection of information that includes records of the learning materials used online by the learner, the questions answered, and the time spent studying.

[0007] A "cloud environment" is a system that provides virtual data storage and computing resources for managing and accessing data and applications via the internet.

[0008] "Learning style" refers to the way learners tend to understand, process, and retain information, and is closely related to senses such as hearing, sight, and touch.

[0009] A "learning curriculum" is a systematically planned set of learning materials, resources, and activities designed to help learners achieve their learning objectives.

[0010] "Output" refers to the deliverables or performances created by learners to express to the outside world the knowledge and understanding they have gained through learning.

[0011] "Feedback" refers to information and evaluations provided regarding a learner's behavior and results, intended to promote learning improvement and motivation.

[0012] A "virtual teacher" is a software agent that answers learners' questions and provides educational support through an artificially constructed interface.

[0013] "Visualizing progress" refers to presenting information clearly using tables, graphs, and other visual aids so that learners can understand their current learning outcomes and progress. [Brief explanation of the drawing]

[0014] [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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This 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 Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

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

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

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

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

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

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention is a system for providing learners with an individualized learning experience. It collects and analyzes data from each learner and automatically generates an optimal learning curriculum. This system mainly consists of three elements: a server, a terminal, and a user.

[0036] The server is located in a cloud environment and aggregates and stores learner data. It analyzes each learner's log information and learning history to update their personalized learning profile. This analysis applies machine learning algorithms to identify the learner's strengths and weaknesses, as well as their learning style. Based on the analysis results, a personalized learning curriculum is built by a generation AI and sent to the user's device.

[0037] The terminal is a digital device that learners use on a daily basis. It receives the curriculum sent from the server and presents it to the user. When learners work on output tasks, the terminal supports them by automatically generating drafts of documents and materials using generative AI. For example, when a user is preparing a presentation, the terminal can initially present the basic structure and main content of the slides, allowing them to work more efficiently.

[0038] Users operate the system through their terminals and progress through their learning according to the curriculum provided by the server. Furthermore, if users encounter questions during their learning, they can send them to a virtual teacher via their terminal. The virtual teacher uses AI to generate answers to these questions and promptly replies to the user. This ensures that users can continue learning while resolving any questions they may have.

[0039] Thus, the system according to the present invention is equipped with advanced analytical functions based on learner data and flexible curriculum generation functions using generative AI, and is novel and innovative in that it automatically provides learning support tailored to individual needs. This system dramatically improves efficiency and effectiveness in the educational environment and is particularly capable of universally providing high-quality learning opportunities.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server receives data related to each user's learning activities from their device and stores it in the cloud environment. This includes the learning materials used, the questions answered, and the study time.

[0043] Step 2:

[0044] The server analyzes the accumulated training data. Using machine learning algorithms, it identifies patterns to pinpoint the user's learning style, strengths, and weaknesses.

[0045] Step 3:

[0046] Based on the analysis results, the server automatically generates a personalized learning curriculum optimized for the user using AI. This curriculum is structured to combine learning materials and tasks according to the user's learning goals.

[0047] Step 4:

[0048] The server sends the generated curriculum to the terminal. The terminal displays this curriculum to the user through an interface.

[0049] Step 5:

[0050] Users begin learning through their terminals, following the curriculum provided by the server. If questions arise during their learning, they can send them to a virtual instructor.

[0051] Step 6:

[0052] The device suggests draft creation using AI generation for the user's output tasks (e.g., reports, presentation materials). This allows the user to complete deliverables efficiently.

[0053] Step 7:

[0054] The server monitors the user's progress in real time, generates feedback on areas for improvement and what to learn next, and sends it to the user's device.

[0055] Step 8:

[0056] The device provides a dashboard to visualize the learner's progress, showing the user their current status and guidance for future learning.

[0057] Step 9:

[0058] Based on the feedback and visualized data displayed on the device, users adjust their learning pace and methods, and then move on to the next step.

[0059] (Example 1)

[0060] 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."

[0061] The current education system makes it difficult to provide optimal educational support in real time, tailored to the individual learning needs and progress of each student. There is a lack of flexible means to provide effective learning plans for learners with diverse learning styles and characteristics, resulting in challenges in maximizing learning efficiency and outcomes.

[0062] 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.

[0063] In this invention, the server includes means for collecting learner information and storing it in distributed data storage, means for analyzing the stored learner information and identifying individual learning styles and tendencies, and means for generating a learning plan adapted to the learner based on the analysis results. This makes it possible to quickly and efficiently provide personalized learning plans and materials tailored to the characteristics of each learner, and to maximize learning outcomes through appropriate feedback.

[0064] "Learner information" refers to all data generated during the learning process, and specifically includes information such as learning history, answer results, and login times.

[0065] "Distributed data storage" is a data storage technology that efficiently stores and manages learner information, allowing for flexible access as needed. It is a system that manages information in a distributed manner across multiple servers or cloud services.

[0066] "Analysis" refers to methods used to identify and understand learners' characteristics and tendencies using collected data, and involves the use of machine learning algorithms and statistical techniques.

[0067] "Learning format" refers to the method or style in which learners can learn most effectively, and includes different learning tendencies such as visual, auditory, and tactile.

[0068] A "learning plan" refers to a curriculum or learning roadmap constructed based on analysis results and tailored to the individual needs of learners, outlining specific learning objectives and learning sequences.

[0069] A "virtual instructor" is an AI-based interactive support system that responds to learners' questions and is a virtual educational support system designed to assist with learning.

[0070] "Real-time monitoring" refers to a process that instantly tracks learning progress data and status, provides feedback as needed, and supports learning based on the latest information at all times.

[0071] An "initial draft" is a draft of a document or material that is automatically generated when a learner produces output, and it serves as basic supplementary material to support and facilitate the learner's work.

[0072] "Visualization" is a technique that presents learners' progress and data in a graphical format, making information easy to understand in order to facilitate data comprehension.

[0073] This system consists of three elements—server, terminal, and user—to provide a personalized learning experience.

[0074] First, the server is installed in a cloud environment, collects information about learners, and stores it in distributed data storage. The server uses the Python programming language and the TENSORFLOW® library to analyze this learner information by applying machine learning algorithms. This identifies individual learning styles and tendencies. Using the analysis results, the server constructs a learning plan adapted to the learner using generative AI (e.g., a natural language generation model). This plan specifically includes an individual curriculum, including learning objectives and learning sequence. The generated learning plan is transmitted to the terminal using a secure communication protocol.

[0075] Next, the terminal is a digital device that learners use on a daily basis. It receives learning plans sent from the server and presents them to the user. To support the user's learning activities, the terminal automatically generates initial drafts of documents and materials using generative AI. This functionality is provided via an AI plugin integrated into the terminal. For example, when a user is giving a presentation, the terminal initially presents the basic structure and main content of the slides, helping the user work efficiently.

[0076] Users interact with the system through their devices and progress through their learning according to the provided learning plan. If questions arise during learning, they can send them to a virtual instructor via their device. This virtual instructor utilizes generative AI to quickly generate answers to the user's questions and display them on the device. This allows users to continue learning while resolving their questions in real time.

[0077] As a concrete example, the server collects user A's math learning data and identifies areas where user A struggles. Based on the analysis, a curriculum focusing on algebra topics is generated and provided to user A. Also, when user A asks a question such as "Please explain how to expand an equation," the virtual instructor uses a generative AI to carefully generate an explanation and provides it through the terminal.

[0078] Examples of prompts include "Generate the next learning plan based on user X's past learning history" and "Create a step-by-step explanation for a specific math problem."

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects log information and learning history from learners via digital devices. Inputs include learners' access history and problem-solving data, while outputs are organized and stored in a database. Real-time data stream technology is used for this data collection.

[0082] Step 2:

[0083] The server applies machine learning algorithms to the collected data and performs data analysis. It identifies the learner's strengths and weaknesses, as well as their learning progress, from the input log information and learning history. The output is an individual learning profile obtained as a result of the analysis. Specifically, it trains and applies a neural network model using the Python library TensorFlow.

[0084] Step 3:

[0085] The server generates a personalized learning plan using a generative AI model based on the analysis results. The input is a prompt to the generative AI model, for example, "Create next week's curriculum based on the obtained profile." The output is the learning plan constructed in text format. In this process, a natural language generation algorithm is applied, and the learning content is automatically generated.

[0086] Step 4:

[0087] The server sends the generated training plan to the terminal. The input is the generated training plan, and the output is the plan data that arrives in the terminal's inbox. Secure data transfer technology (HTTPS) is used to send the data.

[0088] Step 5:

[0089] The terminal presents the user with a learning plan received from the server. The input is the learning plan data, and the output is content that is visually displayed to the user. The terminal's display and user interface are used for this presentation.

[0090] Step 6:

[0091] The terminal automatically generates initial drafts of documents using generative AI to support the user's output activities. The input is an overview of the task the user is working on, and the output is a draft of that task. In terms of operation, middleware is used to suggest slide structures when the user is creating presentation materials.

[0092] Step 7:

[0093] During the learning process, the user submits questions to a virtual instructor. The input is the user's question, and the output is a data request sent to the server via the terminal. An example of a prompt might be "Please explain the difference between these grammatical points."

[0094] Step 8:

[0095] The server uses a virtual instructor module to generate answers to received questions using a generative AI. The input is the question, and the output is the generated answer. A deep learning model in natural language processing operates during this process.

[0096] Step 9:

[0097] The device presents the generated answer to the user. The input is the answer text sent from the server, and the output is what is displayed on the user interface. Specifically, information is delivered to learners quickly using mobile notification functionality.

[0098] (Application Example 1)

[0099] 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."

[0100] Traditional learning systems have faced the challenge of providing a learning experience optimized for individual learners. In particular, they lacked the ability to generate dynamic curricula tailored to learners' circumstances at home and to automatically adjust to learning activities. As a result, it was difficult for learners to engage in independent, efficient, and effective learning.

[0101] 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.

[0102] In this invention, the server includes means for collecting learner data and storing it in a cloud environment, means for analyzing the stored data and identifying individual learning styles and tendencies, and means for generating an optimized learning curriculum based on the analysis results. This enables dynamic adjustment of learning difficulty through interaction with learners at home. This allows for flexible adaptation of learning content based on the learner's reaction speed and accuracy rate, enabling the provision of a more personalized and efficient learning experience.

[0103] "Learner data" refers to information about individual learners, including learning history, performance, and comprehension, and is a variety of information used to support learning.

[0104] A "cloud environment" is a server network accessed via the internet where data is stored and analyzed, and it serves as a technological foundation for providing various services.

[0105] "Learning style and tendencies" refer to the characteristics of a learner's learning methods, including areas they find easy to understand and areas they struggle with; they are individual learning habits and patterns.

[0106] An "optimized learning curriculum" is educational content and a learning plan designed to meet the abilities and needs of learners and enable them to learn efficiently.

[0107] A "virtual teacher" is a virtual teacher or educational support system that uses AI technology to answer learners' questions and provide educational support.

[0108] "Dialogue with learners at home" refers to two-way communication aimed at supporting learning, conducted by learners at home through educational robots or digital devices.

[0109] "Dynamic adjustment of learning difficulty" is a process that adjusts the difficulty level of learning in real time according to the learner's level of understanding and response.

[0110] "Reaction speed and accuracy" are indicators that show how quickly learners react to presented learning tasks and how accurately they can answer them.

[0111] "Flexible adaptation of learning content" refers to the ability of learning content and materials to be adapted to suit the learner.

[0112] This invention constructs a system that provides learners with an individualized educational experience. Its main components are a server, a terminal, and a learner (user). The server collects learner data in a cloud environment and analyzes the data using machine learning algorithms. Based on the analysis results, an AI model automatically generates a learning curriculum optimized for the learner. The generated curriculum is provided to the learner via the terminal, supporting their learning process.

[0113] The server is built on a cloud computing platform and implements machine learning algorithms using Python. TensorFlow and PyTorch are used to analyze learner data and identify individual learning styles. The resulting learning curriculum is then sent to the terminal via the HTTP protocol.

[0114] The terminal is implemented using devices such as Raspberry Pi and NVIDIA Jetson, and the user interface is built using MIT App Inventor. Generative AI automatically generates drafts based on the learner's output, and the terminal also monitors the learner's response speed and accuracy in real time, dynamically adjusting the learning content as needed.

[0115] As a concrete example, consider a scenario where a device interacts with a 10-year-old child at home, providing multiplication learning in a quiz format. Based on the analysis results, the device can instantly adjust the difficulty level of the questions to match the child's level of understanding. A virtual educator plays a role in quickly responding to the child's questions and facilitating learning retention.

[0116] The following is an example of a prompt statement passed to a generative AI model:

[0117] "Please generate a multiplication quiz suitable for a 10-year-old child. Please also include a simple explanation of subtraction."

[0118] This structure allows learners to receive individualized learning support at home, enabling them to learn efficiently at their own pace.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server collects learner data in a cloud environment and stores it in a database. The input requires learner progress information and learning logs. This data is analyzed using machine learning algorithms to identify learning styles and trends. The output generates individual learning profiles.

[0122] Step 2:

[0123] The server uses a generative AI model to create a learning curriculum optimized for the learner, based on the obtained learning profile. Here, prompts are passed to the generative AI to generate the curriculum. The inputs required are the individual learning profile and prompts, and the output is the generated learning curriculum.

[0124] Step 3:

[0125] The terminal receives the learning curriculum sent from the server and presents it to the learner through a user interface. This allows learning materials and tasks to be displayed in response to the learner's input, assisting in the creation of output. The input requires learning curriculum data from the server, and the output is the presentation of learning materials to the user.

[0126] Step 4:

[0127] The device automatically creates drafts using generative AI as learners work on the presented tasks. When learners begin outputting, their text and answers are required as input, and a draft is generated as output.

[0128] Step 5:

[0129] The device monitors the learner's response speed and accuracy in real time and sends feedback to the server. Based on this information, the difficulty and content of the learning are dynamically adjusted. The input requires learner response data, and the output is an adapted learning task.

[0130] Step 6:

[0131] Users submit questions to a virtual educator and receive immediate answers. This process requires the learner's question as input, generates an answer using a generative AI, and presents it to the learner as output.

[0132] 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.

[0133] This invention integrates an emotion engine into a learning support system to recognize the learner's emotional state and provide an optimal learning experience. This system consists of three main elements: a server, a terminal, and a user.

[0134] The server is located in a cloud environment and stores data sent from learners, which is then analyzed by an emotion engine. This engine has the technology to estimate emotions from the user's facial expressions, voice, and operation patterns, enabling it to grasp the user's emotional state in real time. The server analyzes this emotional information in combination with training data to form a user-specific learning profile. Based on this profile, it generates a learning curriculum optimized for each individual user.

[0135] The device provides feedback to user actions and displays the learning curriculum sent from the server. If the user is emotionally stressed, the device presents relaxation content to create a more comfortable learning environment. Furthermore, when working on output tasks, it uses generative AI to automatically create drafts. Emotional data at this stage is fed back to the server for further optimization of learning.

[0136] Users can engage in learning activities using their devices and ask questions to a virtual teacher as they arise during their studies. The virtual teacher provides automatically generated answers in real time, helping to deepen the user's understanding. Furthermore, by considering the impact of the user's emotions on learning and adjusting the difficulty level and content of the assignments, a more personalized learning experience is possible.

[0137] For example, if a user repeatedly makes mistakes while solving a math problem, the device uses an emotion engine to detect the user's frustration and provides clearer explanatory videos or guided exercises. In this way, the present invention incorporates emotional data into the learning process, enabling flexible educational support tailored to the learner's needs and ultimately maximizing learning effectiveness.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The user begins learning using the device. The device monitors the user's facial expressions and voice, collecting data to input into the emotion engine.

[0141] Step 2:

[0142] The device sends the collected emotional data to the server. The server analyzes this data using an emotion engine to identify the user's current emotional state.

[0143] Step 3:

[0144] The server analyzes the analyzed emotional state in combination with the learner's past learning data. This allows it to update the profile to match the individual's learning style and needs.

[0145] Step 4:

[0146] The server generates a learning curriculum optimized for the user based on the latest profile. It adjusts the difficulty and content of the curriculum according to the user's learning progress and emotional state.

[0147] Step 5:

[0148] The server delivers the generated curriculum to the terminal. The terminal presents the curriculum to the user and supports their learning.

[0149] Step 6:

[0150] Users progress through the curriculum via their devices. Any questions or issues during their studies can be immediately addressed to a virtual teacher.

[0151] Step 7:

[0152] The device automatically creates drafts for user output tasks using generation AI, assisting users in easily editing the content.

[0153] Step 8:

[0154] If the emotion engine detects the user's stress level during learning, the device will present relaxation content or adaptive learning content to alleviate the user's tension.

[0155] Step 9:

[0156] The server periodically updates the user's learning and sentiment data and provides a dashboard on the device that visualizes their progress. Users refer to this dashboard to adjust their learning pace and strategy.

[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] Conventional learning support systems have struggled to adequately understand and reflect learners' emotional states in their learning content, making it difficult to provide individually optimized learning experiences. Furthermore, they have lacked the flexibility to provide educational content tailored to learners' weaknesses and progress. Therefore, to maximize learning effectiveness, there is a need for a system that considers learners' emotional states and individual learning tendencies.

[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 information and storing it in a network environment, means for analyzing the stored learner information and identifying individual learning tendencies and emotional states, and means for generating a learning method optimized for the learner based on the analysis results and emotional states. This makes it possible to grasp the emotional state of each learner in real time and provide an optimal learning method based on that.

[0162] "Learner information" refers to data about learners, including information related to their behavior, emotional state, and learning progress.

[0163] A "network environment" refers to the infrastructure for sending and receiving digital information, and includes cloud technology and communication networks.

[0164] "Analysis" refers to the process and methods used to extract useful information and find meaning in collected data.

[0165] "Learning tendencies" refer to specific learning approaches identified as a result of analyzing the learning styles and patterns exhibited by learners.

[0166] "Emotional state" refers to the emotions and psychological state that a learner is experiencing at a particular moment.

[0167] "Learning methods" refer to the structure and procedures of a series of educational activities, including the curriculum, materials, and support provided to learners.

[0168] "Real-time" refers to the attribute of processing where data and information are processed immediately without delay, and a response is provided to the user.

[0169] "Optimization" refers to the process of adjusting resources and conditions to achieve the greatest possible results for a specific purpose.

[0170] This invention is a system that supports online learning and consists of three main elements: a server, a terminal, and a user.

[0171] The server is located in a cloud computing environment and plays the role of storing data collected from users. The collected data includes facial expressions, voice, and operation patterns, and this data is processed using facial recognition and speech recognition technologies. The server analyzes the data to identify the learner's emotional state and learning tendencies, and executes an algorithm that generates a learning method optimized for each user based on this information. Technologies used include, for example, open-source image processing libraries for facial recognition and cloud service speech analysis APIs for speech recognition.

[0172] The terminal is a device that the user directly interacts with, and includes smartphones, tablets, and computers. The terminal displays personalized learning methods transmitted from the server on its screen. Furthermore, when a reaction is required, it uses a built-in feedback function to present appropriate content to the user. For example, if the terminal detects that the user is losing focus during learning, it will automatically play relaxation music or break content.

[0173] The user is the central figure in the learning process, operating the device to conduct their studies. During learning, users can receive support through a virtual instructor. The virtual instructor system utilizes a generative AI model to instantly generate responses to user questions. By using prompts such as, "I would like a more detailed explanation of this math problem," users can receive specific feedback.

[0174] For example, if a user makes repeated mistakes while solving a math problem, the server will assess the user's stress level and provide explanatory videos or guided exercises from the terminal. This allows the user to continue learning with peace of mind, resulting in improved learning efficiency.

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

[0176] Step 1:

[0177] The server receives data sent from the user via the terminal. Inputs include facial image data, audio clips, and logs of operation patterns. This data is stored in a database. The server preprocesses this data using facial recognition and audio analysis technologies to extract features for determining emotional states. The output is a categorized dataset for emotion analysis.

[0178] Step 2:

[0179] The server uses the dataset obtained in Step 1 to perform analysis with its emotion engine. The input is the organized dataset, and the output is the analysis result indicating the user's emotional state. Specifically, it applies a machine learning algorithm to output emotion labels such as "concentrated" or "stressed."

[0180] Step 3:

[0181] The server integrates analyzed emotional states with past learning data to analyze the user's learning tendencies. The input consists of the results of the emotional analysis and learning history data, while the output is the learner's profile information. Based on this, the server generates an optimized learning method and constructs the learning curriculum to be displayed next. It utilizes a generative AI model to determine the most suitable learning materials and assignments for the user.

[0182] Step 4:

[0183] A personalized learning curriculum is transferred from the server to the terminal. The terminal receives this learning curriculum and displays it in the user interface. The input is the curriculum data from the server, and the output is the screen display that the user can see. Specific operations include selecting and ordering learning content and displaying it in the UI.

[0184] Step 5:

[0185] Users progress through the learning process using their devices. When questions arise, they send prompt messages to a virtual instructor. The input is a question such as "I want to know more about this topic," and the virtual instructor generates a response using a generative AI model. The output is explanations and support information that are immediately displayed on the user's screen.

[0186] Step 6:

[0187] The device then collects response data to the user's interactions and feeds it back to the server. The input consists of user action data and newly collected sentiment data, while the output is an updated dataset for the next cycle. The server uses this data to further optimize the learning experience.

[0188] (Application Example 2)

[0189] 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".

[0190] Conventional learning support systems have a problem in that they do not adjust learning content to take into account the learner's emotional state, and therefore do not adequately reduce the stress and frustration that learners feel. Furthermore, there is a lack of means to analyze emotions in real time and quantitatively evaluate emotional factors that affect learning progress, making it difficult to optimize the learning experience.

[0191] 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.

[0192] In this invention, the server includes means for analyzing the learner's emotions and adjusting learning content based on their emotional state; means for identifying the learner's areas of weakness and prioritizing the provision of learning content to overcome them; means for providing encouragement and support based on the learner's emotional state; and means for providing the learner with specialized courses according to a generated plan and supporting the acquisition of practical skills. This enables more effective and personalized learning support for learners.

[0193] "Learner data" refers to all information related to a learner's learning process, including data on performance, learning style, and emotional state.

[0194] "Information processing environment" refers to systems used to collect, store, analyze, and manage digital information, and specifically includes cloud-based platforms.

[0195] A "learning plan" refers to a learning progress program designed according to the learner's characteristics and goals, and includes a curriculum structure to provide an optimal learning experience.

[0196] "Teaching materials and activities" refer to specific learning materials and activities provided to learners in order to acquire knowledge and skills.

[0197] "Deliverables" refer to the output that learners produce during the learning process, and include essays, reports, presentations, etc.

[0198] A "virtual instructor" refers to a digital educational support system that uses artificial intelligence to automatically provide answers to learners' questions.

[0199] "Emotional analysis" refers to the process of inferring a learner's psychological state from their facial expressions, words, actions, and behavior, and evaluating it as data.

[0200] "Means of adjusting learning content based on emotional state" refers to a system that changes the learning content and difficulty level provided according to the learner's emotions.

[0201] "Encouragement and support" refers to positive feedback and guidance given in accordance with the learner's emotions and learning content.

[0202] A "specialized course" refers to a learning course designed to acquire advanced knowledge and skills in a specific field.

[0203] This invention is a system for recognizing the emotional state of learners and providing an optimized learning experience. This system mainly consists of three elements: a server, a terminal, and a user.

[0204] The server functions as an information processing environment, storing learner data in the cloud. The emotion analysis system within the server analyzes the learner's facial expressions, tone of voice, and movements to evaluate their emotional state. This allows for data processing and emotion estimation necessary to identify each learner's learning style. The main technologies used here include the image processing library OpenCV and a generative AI model for emotion estimation (e.g., TensorFlow).

[0205] The terminal acts as a user interface, displaying an optimized learning plan generated from the server. It monitors the learner's emotional state in real time, providing encouraging and relaxing content when the learner faces difficulties, for example. It also assists in automatically creating drafts of the learner's output.

[0206] Users can engage in learning activities via their devices and resolve questions in real time using a virtual instructor. This virtual instructor is a generative AI-based system that automatically generates answers to user questions. By using prompts, it provides personalized feedback tailored to the user's specific needs and emotions.

[0207] A concrete example is when a user is practicing speaking English; the robot can sense their level of tension and offer encouragement such as, "It's okay, relax," to support smooth learning. An example of a prompt to the generative AI model is, "Analyze the user's facial expression and voice data, and generate appropriate dialogue messages and encouragement when signs of stress are detected."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server receives learner data from the user's terminal. This data includes facial expression images, audio clips, and operation logs. The input data is stored in a cloud-based database. The server performs data preprocessing, such as format conversion and noise reduction, as needed to analyze this data.

[0211] Step 2:

[0212] The server processes received facial image and audio clips using an emotion analysis system. It applies a face recognition algorithm to extract features for estimating the learner's emotional state. Image processing libraries such as OpenCV are used in this process. The generated features are input into an emotion model, which evaluates the learner's emotional state in real time and outputs an emotion score.

[0213] Step 3:

[0214] The server inputs the emotion score into a learning plan generation module and generates a learning plan optimized for the user's current emotional state. This process integrates the user's past learning history and current emotional state, and optimizes the curriculum using an optimization algorithm. The resulting curriculum is then sent to the terminal.

[0215] Step 4:

[0216] The device displays an optimized learning plan received from the server to the user. The device prepares to address any questions or problems the user may encounter during their learning process, via a virtual instructor. Specifically, it uses a generative AI model to automatically generate answers based on prompts and displays them on the screen.

[0217] Step 5:

[0218] As users progress through the learning process using their devices, they can ask questions to the virtual instructor as needed. In response to user input, the device uses the question as a prompt to call up a generative AI model that provides appropriate answers and instructions. By using these responses to advance their learning, users can gain a deeper understanding.

[0219] Step 6:

[0220] The device continuously monitors the learner's emotional state and learning progress, and sends feedback as needed. It provides relaxation content and encouraging messages to stabilize the user's emotional state. This feedback is also effective for the user because it is generated based on the results of emotion analysis.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention is a system for providing learners with an individualized learning experience. It collects and analyzes data from each learner and automatically generates an optimal learning curriculum. This system mainly consists of three elements: a server, a terminal, and a user.

[0238] The server is located in a cloud environment and aggregates and stores learner data. It analyzes each learner's log information and learning history to update their personalized learning profile. This analysis applies machine learning algorithms to identify the learner's strengths and weaknesses, as well as their learning style. Based on the analysis results, a personalized learning curriculum is built by a generation AI and sent to the user's device.

[0239] The terminal is a digital device that learners use on a daily basis. It receives the curriculum sent from the server and presents it to the user. When learners work on output tasks, the terminal supports them by automatically generating drafts of documents and materials using generative AI. For example, when a user is preparing a presentation, the terminal can initially present the basic structure and main content of the slides, allowing them to work more efficiently.

[0240] Users operate the system through their terminals and progress through their learning according to the curriculum provided by the server. Furthermore, if users encounter questions during their learning, they can send them to a virtual teacher via their terminal. The virtual teacher uses AI to generate answers to these questions and promptly replies to the user. This ensures that users can continue learning while resolving any questions they may have.

[0241] Thus, the system according to the present invention is equipped with advanced analytical functions based on learner data and flexible curriculum generation functions using generative AI, and is novel and innovative in that it automatically provides learning support tailored to individual needs. This system dramatically improves efficiency and effectiveness in the educational environment and is particularly capable of universally providing high-quality learning opportunities.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server receives data related to each user's learning activities from their device and stores it in the cloud environment. This includes the learning materials used, the questions answered, and the study time.

[0245] Step 2:

[0246] The server analyzes the accumulated training data. Using machine learning algorithms, it identifies patterns to pinpoint the user's learning style, strengths, and weaknesses.

[0247] Step 3:

[0248] Based on the analysis results, the server automatically generates a personalized learning curriculum optimized for the user using AI. This curriculum is structured to combine learning materials and tasks according to the user's learning goals.

[0249] Step 4:

[0250] The server sends the generated curriculum to the terminal. The terminal displays this curriculum to the user through an interface.

[0251] Step 5:

[0252] Users begin learning through their terminals, following the curriculum provided by the server. If questions arise during their learning, they can send them to a virtual instructor.

[0253] Step 6:

[0254] The device suggests draft creation using AI generation for the user's output tasks (e.g., reports, presentation materials). This allows the user to complete deliverables efficiently.

[0255] Step 7:

[0256] The server monitors the user's progress in real time, generates feedback on areas for improvement and what to learn next, and sends it to the user's device.

[0257] Step 8:

[0258] The device provides a dashboard to visualize the learner's progress, showing the user their current status and guidance for future learning.

[0259] Step 9:

[0260] Based on the feedback and visualized data displayed on the device, users adjust their learning pace and methods, and then move on to the next step.

[0261] (Example 1)

[0262] 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".

[0263] The current education system makes it difficult to provide optimal educational support in real time, tailored to the individual learning needs and progress of each student. There is a lack of flexible means to provide effective learning plans for learners with diverse learning styles and characteristics, resulting in challenges in maximizing learning efficiency and outcomes.

[0264] 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.

[0265] In this invention, the server includes means for collecting learner information and storing it in distributed data storage, means for analyzing the stored learner information and identifying individual learning styles and tendencies, and means for generating a learning plan adapted to the learner based on the analysis results. This makes it possible to quickly and efficiently provide personalized learning plans and materials tailored to the characteristics of each learner, and to maximize learning outcomes through appropriate feedback.

[0266] "Learner information" refers to all data generated during the learning process, and specifically includes information such as learning history, answer results, and login times.

[0267] "Distributed data storage" is a data storage technology that efficiently stores and manages learner information, allowing for flexible access as needed. It is a system that manages information in a distributed manner across multiple servers or cloud services.

[0268] "Analysis" refers to methods used to identify and understand learners' characteristics and tendencies using collected data, and involves the use of machine learning algorithms and statistical techniques.

[0269] "Learning format" refers to the method or style in which learners can learn most effectively, and includes different learning tendencies such as visual, auditory, and tactile.

[0270] A "learning plan" refers to a curriculum or learning roadmap constructed based on analysis results and tailored to the individual needs of learners, outlining specific learning objectives and learning sequences.

[0271] A "virtual instructor" is an AI-based interactive support system that responds to learners' questions and is a virtual educational support system designed to assist with learning.

[0272] "Real-time monitoring" refers to a process that instantly tracks learning progress data and status, provides feedback as needed, and supports learning based on the latest information at all times.

[0273] An "initial draft" is a draft of a document or material that is automatically generated when a learner produces output, and it serves as basic supplementary material to support and facilitate the learner's work.

[0274] "Visualization" is a technique that presents learners' progress and data in a graphical format, making information easy to understand in order to facilitate data comprehension.

[0275] This system consists of three elements—server, terminal, and user—to provide a personalized learning experience.

[0276] First, the server is located in a cloud environment, collects information about learners, and stores it in distributed data storage. The server uses the Python programming language and the TensorFlow library to analyze this learner information by applying machine learning algorithms. This identifies individual learning styles and tendencies. Using the analysis results, the server constructs a learning plan adapted to the learner using generative AI (e.g., a natural language generation model). This plan specifically includes an individual curriculum, including learning objectives and learning sequence. The generated learning plan is sent to the terminal using a secure communication protocol.

[0277] Next, the terminal is a digital device that learners use on a daily basis. It receives learning plans sent from the server and presents them to the user. To support the user's learning activities, the terminal automatically generates initial drafts of documents and materials using generative AI. This functionality is provided via an AI plugin integrated into the terminal. For example, when a user is giving a presentation, the terminal initially presents the basic structure and main content of the slides, helping the user work efficiently.

[0278] Users interact with the system through their devices and progress through their learning according to the provided learning plan. If questions arise during learning, they can send them to a virtual instructor via their device. This virtual instructor utilizes generative AI to quickly generate answers to the user's questions and display them on the device. This allows users to continue learning while resolving their questions in real time.

[0279] As a specific example, the server collects the learning data of User A and identifies the areas where the user is weak. As a result of the analysis, a curriculum focused on algebraic themes is generated and provided to User A. Also, when User A asks a question such as "Please teach me how to expand equations", the virtual instructor uses the generative AI to carefully generate the explanation and provide it through the terminal.

[0280] Examples of prompt sentences include "Based on the past learning history of User X, generate the following learning plan" and "Create a step-by-step explanation for a specific math problem".

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The server collects the log information and learning history from the learner via a digital device. The input is the learner's access history and problem-solving data, and the output is saved in a format where these data are organized and stored in a database. Real-time data stream technology is used for this data collection.

[0284] Step 2:

[0285] The server applies a machine learning algorithm to the collected data for data analysis. From the input log information and learning history, the learner's strong subjects, weak subjects, and learning progress are identified. The output is an individual learning profile obtained as the analysis result. As a specific operation, training and application of a neural network model using the Python library TensorFlow are performed.

[0286] Step 3:

[0287] The server generates a personalized learning plan using a generative AI model based on the analysis results. The input is a prompt to the generative AI model, for example, "Create next week's curriculum based on the obtained profile." The output is the learning plan constructed in text format. In this process, a natural language generation algorithm is applied, and the learning content is automatically generated.

[0288] Step 4:

[0289] The server sends the generated training plan to the terminal. The input is the generated training plan, and the output is the plan data that arrives in the terminal's inbox. Secure data transfer technology (HTTPS) is used to send the data.

[0290] Step 5:

[0291] The terminal presents the user with a learning plan received from the server. The input is the learning plan data, and the output is content that is visually displayed to the user. The terminal's display and user interface are used for this presentation.

[0292] Step 6:

[0293] The terminal automatically generates initial drafts of documents using generative AI to support the user's output activities. The input is an overview of the task the user is working on, and the output is a draft of that task. In terms of operation, middleware is used to suggest slide structures when the user is creating presentation materials.

[0294] Step 7:

[0295] During the learning process, the user submits questions to a virtual instructor. The input is the user's question, and the output is a data request sent to the server via the terminal. An example of a prompt might be "Please explain the difference between these grammatical points."

[0296] Step 8:

[0297] The server uses a virtual instructor module to generate answers to received questions using a generative AI. The input is the question, and the output is the generated answer. A deep learning model in natural language processing operates during this process.

[0298] Step 9:

[0299] The device presents the generated answer to the user. The input is the answer text sent from the server, and the output is what is displayed on the user interface. Specifically, information is delivered to learners quickly using mobile notification functionality.

[0300] (Application Example 1)

[0301] 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."

[0302] Traditional learning systems have faced the challenge of providing a learning experience optimized for individual learners. In particular, they lacked the ability to generate dynamic curricula tailored to learners' circumstances at home and to automatically adjust to learning activities. As a result, it was difficult for learners to engage in independent, efficient, and effective learning.

[0303] 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.

[0304] In this invention, the server includes means for collecting learner data and storing it in a cloud environment, means for analyzing the stored data and identifying individual learning styles and tendencies, and means for generating an optimized learning curriculum based on the analysis results. This enables dynamic adjustment of learning difficulty through interaction with learners at home. This allows for flexible adaptation of learning content based on the learner's reaction speed and accuracy rate, enabling the provision of a more personalized and efficient learning experience.

[0305] "Learner data" refers to information about individual learners, including various types of information used for learning support, such as learning history, performance, and understanding level.

[0306] "Cloud environment" refers to a server network via the Internet where data storage and analysis are performed, and is a technical infrastructure that provides various services.

[0307] "Learning styles and tendencies" refer to individual learning habits and patterns that indicate the characteristics of a learner's learning method, as well as the fields that are easy or difficult to understand.

[0308] "Optimized learning curriculum" refers to educational content and learning plans designed to correspond to the abilities and needs of learners and enable efficient learning.

[0309] "Virtual education staff" refers to virtual teachers or educational supporters, which is a system that utilizes AI technology to respond to learners' questions and provide educational support.

[0310] "Interaction with learners within the family" refers to two-way communication for learning support that learners conduct via educational robots or digital devices at home.

[0311] "Dynamic adjustment of learning difficulty" refers to a process of adjusting the learning difficulty in real time according to the understanding level and reaction of learners.

[0312] "Reaction speed and correct answer rate" are indicators that represent how quickly a learner responds to a presented learning task and how accurately they can answer.

[0313] "Adaptation of flexible learning content" refers to the adaptability of learning content and teaching materials that can be changed to suit learners.

[0314] This invention constructs a system that provides learners with an individualized educational experience. Its main components are a server, a terminal, and a learner (user). The server collects learner data in a cloud environment and analyzes the data using machine learning algorithms. Based on the analysis results, an AI model automatically generates a learning curriculum optimized for the learner. The generated curriculum is provided to the learner via the terminal, supporting their learning process.

[0315] The server is built on a cloud computing platform and implements machine learning algorithms using Python. TensorFlow and PyTorch are used to analyze learner data and identify individual learning styles. The resulting learning curriculum is then sent to the terminal via the HTTP protocol.

[0316] The terminal is implemented using devices such as Raspberry Pi and NVIDIA Jetson, and the user interface is built using MIT App Inventor. Generative AI automatically generates drafts based on the learner's output, and the terminal also monitors the learner's response speed and accuracy in real time, dynamically adjusting the learning content as needed.

[0317] As a concrete example, consider a scenario where a device interacts with a 10-year-old child at home, providing multiplication learning in a quiz format. Based on the analysis results, the device can instantly adjust the difficulty level of the questions to match the child's level of understanding. A virtual educator plays a role in quickly responding to the child's questions and facilitating learning retention.

[0318] The following is an example of a prompt statement passed to a generative AI model:

[0319] "Please generate a multiplication quiz suitable for a 10-year-old child. Please also include a simple explanation of subtraction."

[0320] This structure allows learners to receive individualized learning support at home, enabling them to learn efficiently at their own pace.

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The server collects learner data in a cloud environment and stores it in a database. The input requires learner progress information and learning logs. This data is analyzed using machine learning algorithms to identify learning styles and trends. The output generates individual learning profiles.

[0324] Step 2:

[0325] The server uses a generative AI model to create a learning curriculum optimized for the learner, based on the obtained learning profile. Here, prompts are passed to the generative AI to generate the curriculum. The inputs required are the individual learning profile and prompts, and the output is the generated learning curriculum.

[0326] Step 3:

[0327] The terminal receives the learning curriculum sent from the server and presents it to the learner through a user interface. This allows learning materials and tasks to be displayed in response to the learner's input, assisting in the creation of output. The input requires learning curriculum data from the server, and the output is the presentation of learning materials to the user.

[0328] Step 4:

[0329] The device automatically creates drafts using generative AI as learners work on the presented tasks. When learners begin outputting, their text and answers are required as input, and a draft is generated as output.

[0330] Step 5:

[0331] The device monitors the learner's response speed and accuracy in real time and sends feedback to the server. Based on this information, the difficulty and content of the learning are dynamically adjusted. The input requires learner response data, and the output is an adapted learning task.

[0332] Step 6:

[0333] Users submit questions to a virtual educator and receive immediate answers. This process requires the learner's question as input, generates an answer using a generative AI, and presents it to the learner as output.

[0334] 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.

[0335] This invention integrates an emotion engine into a learning support system to recognize the learner's emotional state and provide an optimal learning experience. This system consists of three main elements: a server, a terminal, and a user.

[0336] The server is located in a cloud environment and stores data sent from learners, which is then analyzed by an emotion engine. This engine has the technology to estimate emotions from the user's facial expressions, voice, and operation patterns, enabling it to grasp the user's emotional state in real time. The server analyzes this emotional information in combination with training data to form a user-specific learning profile. Based on this profile, it generates a learning curriculum optimized for each individual user.

[0337] The device provides feedback to user actions and displays the learning curriculum sent from the server. If the user is emotionally stressed, the device presents relaxation content to create a more comfortable learning environment. Furthermore, when working on output tasks, it uses generative AI to automatically create drafts. Emotional data at this stage is fed back to the server for further optimization of learning.

[0338] Users can engage in learning activities using their devices and ask questions to a virtual teacher as they arise during their studies. The virtual teacher provides automatically generated answers in real time, helping to deepen the user's understanding. Furthermore, by considering the impact of the user's emotions on learning and adjusting the difficulty level and content of the assignments, a more personalized learning experience is possible.

[0339] For example, if a user repeatedly makes mistakes while solving a math problem, the device uses an emotion engine to detect the user's frustration and provides clearer explanatory videos or guided exercises. In this way, the present invention incorporates emotional data into the learning process, enabling flexible educational support tailored to the learner's needs and ultimately maximizing learning effectiveness.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The user begins learning using the device. The device monitors the user's facial expressions and voice, collecting data to input into the emotion engine.

[0343] Step 2:

[0344] The device sends the collected emotional data to the server. The server analyzes this data using an emotion engine to identify the user's current emotional state.

[0345] Step 3:

[0346] The server analyzes the analyzed emotional state in combination with the learner's past learning data. This allows it to update the profile to match the individual's learning style and needs.

[0347] Step 4:

[0348] The server generates a learning curriculum optimized for the user based on the latest profile. It adjusts the difficulty and content of the curriculum according to the user's learning progress and emotional state.

[0349] Step 5:

[0350] The server delivers the generated curriculum to the terminal. The terminal presents the curriculum to the user and supports their learning.

[0351] Step 6:

[0352] Users progress through the curriculum via their devices. Any questions or issues during their studies can be immediately addressed to a virtual teacher.

[0353] Step 7:

[0354] The device automatically creates drafts for user output tasks using generation AI, assisting users in easily editing the content.

[0355] Step 8:

[0356] If the emotion engine detects the user's stress level during learning, the device will present relaxation content or adaptive learning content to alleviate the user's tension.

[0357] Step 9:

[0358] The server periodically updates the user's learning and sentiment data and provides a dashboard on the device that visualizes their progress. Users refer to this dashboard to adjust their learning pace and strategy.

[0359] (Example 2)

[0360] 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".

[0361] Conventional learning support systems have struggled to adequately understand and reflect learners' emotional states in their learning content, making it difficult to provide individually optimized learning experiences. Furthermore, they have lacked the flexibility to provide educational content tailored to learners' weaknesses and progress. Therefore, to maximize learning effectiveness, there is a need for a system that considers learners' emotional states and individual learning tendencies.

[0362] 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.

[0363] In this invention, the server includes means for collecting learner information and storing it in a network environment, means for analyzing the stored learner information and identifying individual learning tendencies and emotional states, and means for generating a learning method optimized for the learner based on the analysis results and emotional states. This makes it possible to grasp the emotional state of each learner in real time and provide an optimal learning method based on that.

[0364] "Learner information" refers to data about learners, including information related to their behavior, emotional state, and learning progress.

[0365] A "network environment" refers to the infrastructure for sending and receiving digital information, and includes cloud technology and communication networks.

[0366] "Analysis" refers to the process and methods used to extract useful information and find meaning in collected data.

[0367] "Learning tendencies" refer to specific learning approaches identified as a result of analyzing the learning styles and patterns exhibited by learners.

[0368] "Emotional state" refers to the emotions and psychological state that a learner is experiencing at a particular moment.

[0369] "Learning methods" refer to the structure and procedures of a series of educational activities, including the curriculum, materials, and support provided to learners.

[0370] "Real-time" refers to the attribute of processing where data and information are processed immediately without delay, and a response is provided to the user.

[0371] "Optimization" refers to the process of adjusting resources and conditions to achieve the greatest possible results for a specific purpose.

[0372] This invention is a system that supports online learning and consists of three main elements: a server, a terminal, and a user.

[0373] The server is located in a cloud computing environment and plays the role of storing data collected from users. The collected data includes facial expressions, voice, and operation patterns, and this data is processed using facial recognition and speech recognition technologies. The server analyzes the data to identify the learner's emotional state and learning tendencies, and executes an algorithm that generates a learning method optimized for each user based on this information. Technologies used include, for example, open-source image processing libraries for facial recognition and cloud service speech analysis APIs for speech recognition.

[0374] The terminal is a device that the user directly interacts with, and includes smartphones, tablets, and computers. The terminal displays personalized learning methods transmitted from the server on its screen. Furthermore, when a reaction is required, it uses a built-in feedback function to present appropriate content to the user. For example, if the terminal detects that the user is losing focus during learning, it will automatically play relaxation music or break content.

[0375] The user is the central figure in the learning process, operating the device to conduct their studies. During learning, users can receive support through a virtual instructor. The virtual instructor system utilizes a generative AI model to instantly generate responses to user questions. By using prompts such as, "I would like a more detailed explanation of this math problem," users can receive specific feedback.

[0376] For example, if a user makes repeated mistakes while solving a math problem, the server will assess the user's stress level and provide explanatory videos or guided exercises from the terminal. This allows the user to continue learning with peace of mind, resulting in improved learning efficiency.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The server receives data sent from the user via the terminal. Inputs include facial image data, audio clips, and logs of operation patterns. This data is stored in a database. The server preprocesses this data using facial recognition and audio analysis technologies to extract features for determining emotional states. The output is a categorized dataset for emotion analysis.

[0380] Step 2:

[0381] The server uses the dataset obtained in Step 1 to perform analysis with its emotion engine. The input is the organized dataset, and the output is the analysis result indicating the user's emotional state. Specifically, it applies a machine learning algorithm to output emotion labels such as "concentrated" or "stressed."

[0382] Step 3:

[0383] The server integrates analyzed emotional states with past learning data to analyze the user's learning tendencies. The input consists of the results of the emotional analysis and learning history data, while the output is the learner's profile information. Based on this, the server generates an optimized learning method and constructs the learning curriculum to be displayed next. It utilizes a generative AI model to determine the most suitable learning materials and assignments for the user.

[0384] Step 4:

[0385] A personalized learning curriculum is transferred from the server to the terminal. The terminal receives this learning curriculum and displays it in the user interface. The input is the curriculum data from the server, and the output is the screen display that the user can see. Specific operations include selecting and ordering learning content and displaying it in the UI.

[0386] Step 5:

[0387] Users progress through the learning process using their devices. When questions arise, they send prompt messages to a virtual instructor. The input is a question such as "I want to know more about this topic," and the virtual instructor generates a response using a generative AI model. The output is explanations and support information that are immediately displayed on the user's screen.

[0388] Step 6:

[0389] The device then collects response data to the user's interactions and feeds it back to the server. The input consists of user action data and newly collected sentiment data, while the output is an updated dataset for the next cycle. The server uses this data to further optimize the learning experience.

[0390] (Application Example 2)

[0391] 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."

[0392] Conventional learning support systems have a problem in that they do not adjust learning content to take into account the learner's emotional state, and therefore do not adequately reduce the stress and frustration that learners feel. Furthermore, there is a lack of means to analyze emotions in real time and quantitatively evaluate emotional factors that affect learning progress, making it difficult to optimize the learning experience.

[0393] 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.

[0394] In this invention, the server includes means for analyzing the learner's emotions and adjusting learning content based on their emotional state; means for identifying the learner's areas of weakness and prioritizing the provision of learning content to overcome them; means for providing encouragement and support based on the learner's emotional state; and means for providing the learner with specialized courses according to a generated plan and supporting the acquisition of practical skills. This enables more effective and personalized learning support for learners.

[0395] "Learner data" refers to all information related to a learner's learning process, including data on performance, learning style, and emotional state.

[0396] "Information processing environment" refers to systems used to collect, store, analyze, and manage digital information, and specifically includes cloud-based platforms.

[0397] A "learning plan" refers to a learning progress program designed according to the learner's characteristics and goals, and includes a curriculum structure to provide an optimal learning experience.

[0398] "Teaching materials and activities" refer to specific learning materials and activities provided to learners in order to acquire knowledge and skills.

[0399] "Deliverables" refer to the output that learners produce during the learning process, and include essays, reports, presentations, etc.

[0400] A "virtual instructor" refers to a digital educational support system that uses artificial intelligence to automatically provide answers to learners' questions.

[0401] "Emotional analysis" refers to the process of inferring a learner's psychological state from their facial expressions, words, actions, and behavior, and evaluating it as data.

[0402] "Means of adjusting learning content based on emotional state" refers to a system that changes the learning content and difficulty level provided according to the learner's emotions.

[0403] "Encouragement and support" refers to positive feedback and guidance given in accordance with the learner's emotions and learning content.

[0404] A "specialized course" refers to a learning course designed to acquire advanced knowledge and skills in a specific field.

[0405] This invention is a system for recognizing the emotional state of learners and providing an optimized learning experience. This system mainly consists of three elements: a server, a terminal, and a user.

[0406] The server functions as an information processing environment, storing learner data in the cloud. The emotion analysis system within the server analyzes the learner's facial expressions, tone of voice, and movements to evaluate their emotional state. This allows for data processing and emotion estimation necessary to identify each learner's learning style. The main technologies used here include the image processing library OpenCV and a generative AI model for emotion estimation (e.g., TensorFlow).

[0407] The terminal acts as a user interface, displaying an optimized learning plan generated from the server. It monitors the learner's emotional state in real time, providing encouraging and relaxing content when the learner faces difficulties, for example. It also assists in automatically creating drafts of the learner's output.

[0408] Users can engage in learning activities via their devices and resolve questions in real time using a virtual instructor. This virtual instructor is a generative AI-based system that automatically generates answers to user questions. By using prompts, it provides personalized feedback tailored to the user's specific needs and emotions.

[0409] A concrete example is when a user is practicing speaking English; the robot can sense their level of tension and offer encouragement such as, "It's okay, relax," to support smooth learning. An example of a prompt to the generative AI model is, "Analyze the user's facial expression and voice data, and generate appropriate dialogue messages and encouragement when signs of stress are detected."

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The server receives learner data from the user's terminal. This data includes facial expression images, audio clips, and operation logs. The input data is stored in a cloud-based database. The server performs data preprocessing, such as format conversion and noise reduction, as needed to analyze this data.

[0413] Step 2:

[0414] The server processes received facial image and audio clips using an emotion analysis system. It applies a face recognition algorithm to extract features for estimating the learner's emotional state. Image processing libraries such as OpenCV are used in this process. The generated features are input into an emotion model, which evaluates the learner's emotional state in real time and outputs an emotion score.

[0415] Step 3:

[0416] The server inputs the emotion score into a learning plan generation module and generates a learning plan optimized for the user's current emotional state. This process integrates the user's past learning history and current emotional state, and optimizes the curriculum using an optimization algorithm. The resulting curriculum is then sent to the terminal.

[0417] Step 4:

[0418] The device displays an optimized learning plan received from the server to the user. The device prepares to address any questions or problems the user may encounter during their learning process, via a virtual instructor. Specifically, it uses a generative AI model to automatically generate answers based on prompts and displays them on the screen.

[0419] Step 5:

[0420] As users progress through the learning process using their devices, they can ask questions to the virtual instructor as needed. In response to user input, the device uses the question as a prompt to call up a generative AI model that provides appropriate answers and instructions. By using these responses to advance their learning, users can gain a deeper understanding.

[0421] Step 6:

[0422] The device continuously monitors the learner's emotional state and learning progress, and sends feedback as needed. It provides relaxation content and encouraging messages to stabilize the user's emotional state. This feedback is also effective for the user because it is generated based on the results of emotion analysis.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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".

[0439] This invention is a system for providing learners with an individualized learning experience. It collects and analyzes data from each learner and automatically generates an optimal learning curriculum. This system mainly consists of three elements: a server, a terminal, and a user.

[0440] The server is located in a cloud environment and aggregates and stores learner data. It analyzes each learner's log information and learning history to update their personalized learning profile. This analysis applies machine learning algorithms to identify the learner's strengths and weaknesses, as well as their learning style. Based on the analysis results, a personalized learning curriculum is built by a generation AI and sent to the user's device.

[0441] The terminal is a digital device that learners use on a daily basis. It receives the curriculum sent from the server and presents it to the user. When learners work on output tasks, the terminal supports them by automatically generating drafts of documents and materials using generative AI. For example, when a user is preparing a presentation, the terminal can initially present the basic structure and main content of the slides, allowing them to work more efficiently.

[0442] Users operate the system through their terminals and progress through their learning according to the curriculum provided by the server. Furthermore, if users encounter questions during their learning, they can send them to a virtual teacher via their terminal. The virtual teacher uses AI to generate answers to these questions and promptly replies to the user. This ensures that users can continue learning while resolving any questions they may have.

[0443] Thus, the system according to the present invention is equipped with advanced analytical functions based on learner data and flexible curriculum generation functions using generative AI, and is novel and innovative in that it automatically provides learning support tailored to individual needs. This system dramatically improves efficiency and effectiveness in the educational environment and is particularly capable of universally providing high-quality learning opportunities.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The server receives data related to each user's learning activities from their device and stores it in the cloud environment. This includes the learning materials used, the questions answered, and the study time.

[0447] Step 2:

[0448] The server analyzes the accumulated training data. Using machine learning algorithms, it identifies patterns to pinpoint the user's learning style, strengths, and weaknesses.

[0449] Step 3:

[0450] Based on the analysis results, the server automatically generates a personalized learning curriculum optimized for the user using AI. This curriculum is structured to combine learning materials and tasks according to the user's learning goals.

[0451] Step 4:

[0452] The server sends the generated curriculum to the terminal. The terminal displays this curriculum to the user through an interface.

[0453] Step 5:

[0454] Users begin learning through their terminals, following the curriculum provided by the server. If questions arise during their learning, they can send them to a virtual instructor.

[0455] Step 6:

[0456] The device suggests draft creation using AI generation for the user's output tasks (e.g., reports, presentation materials). This allows the user to complete deliverables efficiently.

[0457] Step 7:

[0458] The server monitors the user's progress in real time, generates feedback on areas for improvement and what to learn next, and sends it to the user's device.

[0459] Step 8:

[0460] The device provides a dashboard to visualize the learner's progress, showing the user their current status and guidance for future learning.

[0461] Step 9:

[0462] Based on the feedback and visualized data displayed on the device, users adjust their learning pace and methods, and then move on to the next step.

[0463] (Example 1)

[0464] 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."

[0465] The current education system makes it difficult to provide optimal educational support in real time, tailored to the individual learning needs and progress of each student. There is a lack of flexible means to provide effective learning plans for learners with diverse learning styles and characteristics, resulting in challenges in maximizing learning efficiency and outcomes.

[0466] 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.

[0467] In this invention, the server includes means for collecting learner information and storing it in distributed data storage, means for analyzing the stored learner information and identifying individual learning styles and tendencies, and means for generating a learning plan adapted to the learner based on the analysis results. This makes it possible to quickly and efficiently provide personalized learning plans and materials tailored to the characteristics of each learner, and to maximize learning outcomes through appropriate feedback.

[0468] "Learner information" refers to all data generated during the learning process, and specifically includes information such as learning history, answer results, and login times.

[0469] "Distributed data storage" is a data storage technology that efficiently stores and manages learner information, allowing for flexible access as needed. It is a system that manages information in a distributed manner across multiple servers or cloud services.

[0470] "Analysis" refers to methods used to identify and understand learners' characteristics and tendencies using collected data, and involves the use of machine learning algorithms and statistical techniques.

[0471] "Learning format" refers to the method or style in which learners can learn most effectively, and includes different learning tendencies such as visual, auditory, and tactile.

[0472] A "learning plan" refers to a curriculum or learning roadmap constructed based on analysis results and tailored to the individual needs of learners, outlining specific learning objectives and learning sequences.

[0473] A "virtual instructor" is an AI-based interactive support system that responds to learners' questions and is a virtual educational support system designed to assist with learning.

[0474] "Real-time monitoring" refers to a process that instantly tracks learning progress data and status, provides feedback as needed, and supports learning based on the latest information at all times.

[0475] An "initial draft" is a draft of a document or material that is automatically generated when a learner produces output, and it serves as basic supplementary material to support and facilitate the learner's work.

[0476] "Visualization" is a technique that presents learners' progress and data in a graphical format, making information easy to understand in order to facilitate data comprehension.

[0477] This system consists of three elements—server, terminal, and user—to provide a personalized learning experience.

[0478] First, the server is located in a cloud environment, collects information about learners, and stores it in distributed data storage. The server uses the Python programming language and the TensorFlow library to analyze this learner information by applying machine learning algorithms. This identifies individual learning styles and tendencies. Using the analysis results, the server constructs a learning plan adapted to the learner using generative AI (e.g., a natural language generation model). This plan specifically includes an individual curriculum, including learning objectives and learning sequence. The generated learning plan is sent to the terminal using a secure communication protocol.

[0479] Next, the terminal is a digital device that learners use on a daily basis. It receives learning plans sent from the server and presents them to the user. To support the user's learning activities, the terminal automatically generates initial drafts of documents and materials using generative AI. This functionality is provided via an AI plugin integrated into the terminal. For example, when a user is giving a presentation, the terminal initially presents the basic structure and main content of the slides, helping the user work efficiently.

[0480] Users interact with the system through their devices and progress through their learning according to the provided learning plan. If questions arise during learning, they can send them to a virtual instructor via their device. This virtual instructor utilizes generative AI to quickly generate answers to the user's questions and display them on the device. This allows users to continue learning while resolving their questions in real time.

[0481] As a concrete example, the server collects user A's math learning data and identifies areas where user A struggles. Based on the analysis, a curriculum focusing on algebra topics is generated and provided to user A. Also, when user A asks a question such as "Please explain how to expand an equation," the virtual instructor uses a generative AI to carefully generate an explanation and provides it through the terminal.

[0482] Examples of prompts include "Generate the next learning plan based on user X's past learning history" and "Create a step-by-step explanation for a specific math problem."

[0483] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0484] Step 1:

[0485] The server collects log information and learning history from learners via digital devices. Inputs include learners' access history and problem-solving data, while outputs are organized and stored in a database. Real-time data stream technology is used for this data collection.

[0486] Step 2:

[0487] The server applies machine learning algorithms to the collected data and performs data analysis. It identifies the learner's strengths and weaknesses, as well as their learning progress, from the input log information and learning history. The output is an individual learning profile obtained as a result of the analysis. Specifically, it trains and applies a neural network model using the Python library TensorFlow.

[0488] Step 3:

[0489] The server generates a personalized learning plan using a generative AI model based on the analysis results. The input is a prompt to the generative AI model, for example, "Create next week's curriculum based on the obtained profile." The output is the learning plan constructed in text format. In this process, a natural language generation algorithm is applied, and the learning content is automatically generated.

[0490] Step 4:

[0491] The server sends the generated training plan to the terminal. The input is the generated training plan, and the output is the plan data that arrives in the terminal's inbox. Secure data transfer technology (HTTPS) is used to send the data.

[0492] Step 5:

[0493] The terminal presents the user with a learning plan received from the server. The input is the learning plan data, and the output is content that is visually displayed to the user. The terminal's display and user interface are used for this presentation.

[0494] Step 6:

[0495] The terminal automatically generates initial drafts of documents using generative AI to support the user's output activities. The input is an overview of the task the user is working on, and the output is a draft of that task. In terms of operation, middleware is used to suggest slide structures when the user is creating presentation materials.

[0496] Step 7:

[0497] During the learning process, the user submits questions to a virtual instructor. The input is the user's question, and the output is a data request sent to the server via the terminal. An example of a prompt might be "Please explain the difference between these grammatical points."

[0498] Step 8:

[0499] The server uses a virtual instructor module to generate answers to received questions using a generative AI. The input is the question, and the output is the generated answer. A deep learning model in natural language processing operates during this process.

[0500] Step 9:

[0501] The device presents the generated answer to the user. The input is the answer text sent from the server, and the output is what is displayed on the user interface. Specifically, information is delivered to learners quickly using mobile notification functionality.

[0502] (Application Example 1)

[0503] 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."

[0504] Traditional learning systems have faced the challenge of providing a learning experience optimized for individual learners. In particular, they lacked the ability to generate dynamic curricula tailored to learners' circumstances at home and to automatically adjust to learning activities. As a result, it was difficult for learners to engage in independent, efficient, and effective learning.

[0505] 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.

[0506] In this invention, the server includes means for collecting learner data and storing it in a cloud environment, means for analyzing the stored data and identifying individual learning styles and tendencies, and means for generating an optimized learning curriculum based on the analysis results. This enables dynamic adjustment of learning difficulty through interaction with learners at home. This allows for flexible adaptation of learning content based on the learner's reaction speed and accuracy rate, enabling the provision of a more personalized and efficient learning experience.

[0507] "Learner data" refers to information about individual learners, including learning history, performance, and comprehension, and is a variety of information used to support learning.

[0508] A "cloud environment" is a server network accessed via the internet where data is stored and analyzed, and it serves as a technological foundation for providing various services.

[0509] "Learning style and tendencies" refer to the characteristics of a learner's learning methods, including areas they find easy to understand and areas they struggle with; they are individual learning habits and patterns.

[0510] An "optimized learning curriculum" is educational content and a learning plan designed to meet the abilities and needs of learners and enable them to learn efficiently.

[0511] A "virtual teacher" is a virtual teacher or educational support system that uses AI technology to answer learners' questions and provide educational support.

[0512] "Dialogue with learners at home" refers to two-way communication aimed at supporting learning, conducted by learners at home through educational robots or digital devices.

[0513] "Dynamic adjustment of learning difficulty" is a process that adjusts the difficulty level of learning in real time according to the learner's level of understanding and response.

[0514] "Reaction speed and accuracy" are indicators that show how quickly learners react to presented learning tasks and how accurately they can answer them.

[0515] "Flexible adaptation of learning content" refers to the ability of learning content and materials to be adapted to suit the learner.

[0516] This invention constructs a system that provides learners with an individualized educational experience. Its main components are a server, a terminal, and a learner (user). The server collects learner data in a cloud environment and analyzes the data using machine learning algorithms. Based on the analysis results, an AI model automatically generates a learning curriculum optimized for the learner. The generated curriculum is provided to the learner via the terminal, supporting their learning process.

[0517] The server is built on a cloud computing platform and implements machine learning algorithms using Python. TensorFlow and PyTorch are used to analyze learner data and identify individual learning styles. The resulting learning curriculum is then sent to the terminal via the HTTP protocol.

[0518] The terminal is implemented using devices such as Raspberry Pi and NVIDIA Jetson, and the user interface is built using MIT App Inventor. Generative AI automatically generates drafts based on the learner's output, and the terminal also monitors the learner's response speed and accuracy in real time, dynamically adjusting the learning content as needed.

[0519] As a concrete example, consider a scenario where a device interacts with a 10-year-old child at home, providing multiplication learning in a quiz format. Based on the analysis results, the device can instantly adjust the difficulty level of the questions to match the child's level of understanding. A virtual educator plays a role in quickly responding to the child's questions and facilitating learning retention.

[0520] The following is an example of a prompt statement passed to a generative AI model:

[0521] "Please generate a multiplication quiz suitable for a 10-year-old child. Please also include a simple explanation of subtraction."

[0522] This structure allows learners to receive individualized learning support at home, enabling them to learn efficiently at their own pace.

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The server collects learner data in a cloud environment and stores it in a database. The input requires learner progress information and learning logs. This data is analyzed using machine learning algorithms to identify learning styles and trends. The output generates individual learning profiles.

[0526] Step 2:

[0527] The server uses a generative AI model to create a learning curriculum optimized for the learner, based on the obtained learning profile. Here, prompts are passed to the generative AI to generate the curriculum. The inputs required are the individual learning profile and prompts, and the output is the generated learning curriculum.

[0528] Step 3:

[0529] The terminal receives the learning curriculum sent from the server and presents it to the learner through a user interface. This allows learning materials and tasks to be displayed in response to the learner's input, assisting in the creation of output. The input requires learning curriculum data from the server, and the output is the presentation of learning materials to the user.

[0530] Step 4:

[0531] The device automatically creates drafts using generative AI as learners work on the presented tasks. When learners begin outputting, their text and answers are required as input, and a draft is generated as output.

[0532] Step 5:

[0533] The device monitors the learner's response speed and accuracy in real time and sends feedback to the server. Based on this information, the difficulty and content of the learning are dynamically adjusted. The input requires learner response data, and the output is an adapted learning task.

[0534] Step 6:

[0535] Users submit questions to a virtual educator and receive immediate answers. This process requires the learner's question as input, generates an answer using a generative AI, and presents it to the learner as output.

[0536] 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.

[0537] This invention integrates an emotion engine into a learning support system to recognize the learner's emotional state and provide an optimal learning experience. This system consists of three main elements: a server, a terminal, and a user.

[0538] The server is located in a cloud environment and stores data sent from learners, which is then analyzed by an emotion engine. This engine has the technology to estimate emotions from the user's facial expressions, voice, and operation patterns, enabling it to grasp the user's emotional state in real time. The server analyzes this emotional information in combination with training data to form a user-specific learning profile. Based on this profile, it generates a learning curriculum optimized for each individual user.

[0539] The device provides feedback to user actions and displays the learning curriculum sent from the server. If the user is emotionally stressed, the device presents relaxation content to create a more comfortable learning environment. Furthermore, when working on output tasks, it uses generative AI to automatically create drafts. Emotional data at this stage is fed back to the server for further optimization of learning.

[0540] Users can engage in learning activities using their devices and ask questions to a virtual teacher as they arise during their studies. The virtual teacher provides automatically generated answers in real time, helping to deepen the user's understanding. Furthermore, by considering the impact of the user's emotions on learning and adjusting the difficulty level and content of the assignments, a more personalized learning experience is possible.

[0541] For example, if a user repeatedly makes mistakes while solving a math problem, the device uses an emotion engine to detect the user's frustration and provides clearer explanatory videos or guided exercises. In this way, the present invention incorporates emotional data into the learning process, enabling flexible educational support tailored to the learner's needs and ultimately maximizing learning effectiveness.

[0542] The following describes the processing flow.

[0543] Step 1:

[0544] The user begins learning using the device. The device monitors the user's facial expressions and voice, collecting data to input into the emotion engine.

[0545] Step 2:

[0546] The device sends the collected emotional data to the server. The server analyzes this data using an emotion engine to identify the user's current emotional state.

[0547] Step 3:

[0548] The server analyzes the analyzed emotional state in combination with the learner's past learning data. This allows it to update the profile to match the individual's learning style and needs.

[0549] Step 4:

[0550] The server generates a learning curriculum optimized for the user based on the latest profile. It adjusts the difficulty and content of the curriculum according to the user's learning progress and emotional state.

[0551] Step 5:

[0552] The server delivers the generated curriculum to the terminal. The terminal presents the curriculum to the user and supports their learning.

[0553] Step 6:

[0554] Users progress through the curriculum via their devices. Any questions or issues during their studies can be immediately addressed to a virtual teacher.

[0555] Step 7:

[0556] The device automatically creates drafts for user output tasks using generation AI, assisting users in easily editing the content.

[0557] Step 8:

[0558] If the emotion engine detects the user's stress level during learning, the device will present relaxation content or adaptive learning content to alleviate the user's tension.

[0559] Step 9:

[0560] The server periodically updates the user's learning and sentiment data and provides a dashboard on the device that visualizes their progress. Users refer to this dashboard to adjust their learning pace and strategy.

[0561] (Example 2)

[0562] 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."

[0563] Conventional learning support systems have struggled to adequately understand and reflect learners' emotional states in their learning content, making it difficult to provide individually optimized learning experiences. Furthermore, they have lacked the flexibility to provide educational content tailored to learners' weaknesses and progress. Therefore, to maximize learning effectiveness, there is a need for a system that considers learners' emotional states and individual learning tendencies.

[0564] 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.

[0565] In this invention, the server includes means for collecting learner information and storing it in a network environment, means for analyzing the stored learner information and identifying individual learning tendencies and emotional states, and means for generating a learning method optimized for the learner based on the analysis results and emotional states. This makes it possible to grasp the emotional state of each learner in real time and provide an optimal learning method based on that.

[0566] "Learner information" refers to data about learners, including information related to their behavior, emotional state, and learning progress.

[0567] A "network environment" refers to the infrastructure for sending and receiving digital information, and includes cloud technology and communication networks.

[0568] "Analysis" refers to the process and methods used to extract useful information and find meaning in collected data.

[0569] "Learning tendencies" refer to specific learning approaches identified as a result of analyzing the learning styles and patterns exhibited by learners.

[0570] "Emotional state" refers to the emotions and psychological state that a learner is experiencing at a particular moment.

[0571] "Learning methods" refer to the structure and procedures of a series of educational activities, including the curriculum, materials, and support provided to learners.

[0572] "Real-time" refers to the attribute of processing where data and information are processed immediately without delay, and a response is provided to the user.

[0573] "Optimization" refers to the process of adjusting resources and conditions to achieve the greatest possible results for a specific purpose.

[0574] This invention is a system that supports online learning and consists of three main elements: a server, a terminal, and a user.

[0575] The server is located in a cloud computing environment and plays the role of storing data collected from users. The collected data includes facial expressions, voice, and operation patterns, and this data is processed using facial recognition and speech recognition technologies. The server analyzes the data to identify the learner's emotional state and learning tendencies, and executes an algorithm that generates a learning method optimized for each user based on this information. Technologies used include, for example, open-source image processing libraries for facial recognition and cloud service speech analysis APIs for speech recognition.

[0576] The terminal is a device that the user directly interacts with, and includes smartphones, tablets, and computers. The terminal displays personalized learning methods transmitted from the server on its screen. Furthermore, when a reaction is required, it uses a built-in feedback function to present appropriate content to the user. For example, if the terminal detects that the user is losing focus during learning, it will automatically play relaxation music or break content.

[0577] The user is the central figure in the learning process, operating the device to conduct their studies. During learning, users can receive support through a virtual instructor. The virtual instructor system utilizes a generative AI model to instantly generate responses to user questions. By using prompts such as, "I would like a more detailed explanation of this math problem," users can receive specific feedback.

[0578] For example, if a user makes repeated mistakes while solving a math problem, the server will assess the user's stress level and provide explanatory videos or guided exercises from the terminal. This allows the user to continue learning with peace of mind, resulting in improved learning efficiency.

[0579] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0580] Step 1:

[0581] The server receives data sent from the user via the terminal. Inputs include facial image data, audio clips, and logs of operation patterns. This data is stored in a database. The server preprocesses this data using facial recognition and audio analysis technologies to extract features for determining emotional states. The output is a categorized dataset for emotion analysis.

[0582] Step 2:

[0583] The server uses the dataset obtained in Step 1 to perform analysis with its emotion engine. The input is the organized dataset, and the output is the analysis result indicating the user's emotional state. Specifically, it applies a machine learning algorithm to output emotion labels such as "concentrated" or "stressed."

[0584] Step 3:

[0585] The server integrates analyzed emotional states with past learning data to analyze the user's learning tendencies. The input consists of the results of the emotional analysis and learning history data, while the output is the learner's profile information. Based on this, the server generates an optimized learning method and constructs the learning curriculum to be displayed next. It utilizes a generative AI model to determine the most suitable learning materials and assignments for the user.

[0586] Step 4:

[0587] A personalized learning curriculum is transferred from the server to the terminal. The terminal receives this learning curriculum and displays it in the user interface. The input is the curriculum data from the server, and the output is the screen display that the user can see. Specific operations include selecting and ordering learning content and displaying it in the UI.

[0588] Step 5:

[0589] Users progress through the learning process using their devices. When questions arise, they send prompt messages to a virtual instructor. The input is a question such as "I want to know more about this topic," and the virtual instructor generates a response using a generative AI model. The output is explanations and support information that are immediately displayed on the user's screen.

[0590] Step 6:

[0591] The device then collects response data to the user's interactions and feeds it back to the server. The input consists of user action data and newly collected sentiment data, while the output is an updated dataset for the next cycle. The server uses this data to further optimize the learning experience.

[0592] (Application Example 2)

[0593] 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."

[0594] Conventional learning support systems have a problem in that they do not adjust learning content to take into account the learner's emotional state, and therefore do not adequately reduce the stress and frustration that learners feel. Furthermore, there is a lack of means to analyze emotions in real time and quantitatively evaluate emotional factors that affect learning progress, making it difficult to optimize the learning experience.

[0595] 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.

[0596] In this invention, the server includes means for analyzing the learner's emotions and adjusting learning content based on their emotional state; means for identifying the learner's areas of weakness and prioritizing the provision of learning content to overcome them; means for providing encouragement and support based on the learner's emotional state; and means for providing the learner with specialized courses according to a generated plan and supporting the acquisition of practical skills. This enables more effective and personalized learning support for learners.

[0597] "Learner data" refers to all information related to a learner's learning process, including data on performance, learning style, and emotional state.

[0598] "Information processing environment" refers to systems used to collect, store, analyze, and manage digital information, and specifically includes cloud-based platforms.

[0599] A "learning plan" refers to a learning progress program designed according to the learner's characteristics and goals, and includes a curriculum structure to provide an optimal learning experience.

[0600] "Teaching materials and activities" refer to specific learning materials and activities provided to learners in order to acquire knowledge and skills.

[0601] "Deliverables" refer to the output that learners produce during the learning process, and include essays, reports, presentations, etc.

[0602] A "virtual instructor" refers to a digital educational support system that uses artificial intelligence to automatically provide answers to learners' questions.

[0603] "Emotional analysis" refers to the process of inferring a learner's psychological state from their facial expressions, words, actions, and behavior, and evaluating it as data.

[0604] "Means of adjusting learning content based on emotional state" refers to a system that changes the learning content and difficulty level provided according to the learner's emotions.

[0605] "Encouragement and support" refers to positive feedback and guidance given in accordance with the learner's emotions and learning content.

[0606] A "specialized course" refers to a learning course designed to acquire advanced knowledge and skills in a specific field.

[0607] This invention is a system for recognizing the emotional state of learners and providing an optimized learning experience. This system mainly consists of three elements: a server, a terminal, and a user.

[0608] The server functions as an information processing environment, storing learner data in the cloud. The emotion analysis system within the server analyzes the learner's facial expressions, tone of voice, and movements to evaluate their emotional state. This allows for data processing and emotion estimation necessary to identify each learner's learning style. The main technologies used here include the image processing library OpenCV and a generative AI model for emotion estimation (e.g., TensorFlow).

[0609] The terminal acts as a user interface, displaying an optimized learning plan generated from the server. It monitors the learner's emotional state in real time, providing encouraging and relaxing content when the learner faces difficulties, for example. It also assists in automatically creating drafts of the learner's output.

[0610] Users can engage in learning activities via their devices and resolve questions in real time using a virtual instructor. This virtual instructor is a generative AI-based system that automatically generates answers to user questions. By using prompts, it provides personalized feedback tailored to the user's specific needs and emotions.

[0611] A concrete example is when a user is practicing speaking English; the robot can sense their level of tension and offer encouragement such as, "It's okay, relax," to support smooth learning. An example of a prompt to the generative AI model is, "Analyze the user's facial expression and voice data, and generate appropriate dialogue messages and encouragement when signs of stress are detected."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The server receives learner data from the user's terminal. This data includes facial expression images, audio clips, and operation logs. The input data is stored in a cloud-based database. The server performs data preprocessing, such as format conversion and noise reduction, as needed to analyze this data.

[0615] Step 2:

[0616] The server processes received facial image and audio clips using an emotion analysis system. It applies a face recognition algorithm to extract features for estimating the learner's emotional state. Image processing libraries such as OpenCV are used in this process. The generated features are input into an emotion model, which evaluates the learner's emotional state in real time and outputs an emotion score.

[0617] Step 3:

[0618] The server inputs the emotion score into a learning plan generation module and generates a learning plan optimized for the user's current emotional state. This process integrates the user's past learning history and current emotional state, and optimizes the curriculum using an optimization algorithm. The resulting curriculum is then sent to the terminal.

[0619] Step 4:

[0620] The device displays an optimized learning plan received from the server to the user. The device prepares to address any questions or problems the user may encounter during their learning process, via a virtual instructor. Specifically, it uses a generative AI model to automatically generate answers based on prompts and displays them on the screen.

[0621] Step 5:

[0622] As users progress through the learning process using their devices, they can ask questions to the virtual instructor as needed. In response to user input, the device uses the question as a prompt to call up a generative AI model that provides appropriate answers and instructions. By using these responses to advance their learning, users can gain a deeper understanding.

[0623] Step 6:

[0624] The device continuously monitors the learner's emotional state and learning progress, and sends feedback as needed. It provides relaxation content and encouraging messages to stabilize the user's emotional state. This feedback is also effective for the user because it is generated based on the results of emotion analysis.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] [Fourth Embodiment]

[0629] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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).

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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".

[0642] This invention is a system for providing learners with an individualized learning experience. It collects and analyzes data from each learner and automatically generates an optimal learning curriculum. This system mainly consists of three elements: a server, a terminal, and a user.

[0643] The server is located in a cloud environment and aggregates and stores learner data. It analyzes each learner's log information and learning history to update their personalized learning profile. This analysis applies machine learning algorithms to identify the learner's strengths and weaknesses, as well as their learning style. Based on the analysis results, a personalized learning curriculum is built by a generation AI and sent to the user's device.

[0644] The terminal is a digital device that learners use on a daily basis. It receives the curriculum sent from the server and presents it to the user. When learners work on output tasks, the terminal supports them by automatically generating drafts of documents and materials using generative AI. For example, when a user is preparing a presentation, the terminal can initially present the basic structure and main content of the slides, allowing them to work more efficiently.

[0645] Users operate the system through their terminals and progress through their learning according to the curriculum provided by the server. Furthermore, if users encounter questions during their learning, they can send them to a virtual teacher via their terminal. The virtual teacher uses AI to generate answers to these questions and promptly replies to the user. This ensures that users can continue learning while resolving any questions they may have.

[0646] Thus, the system according to the present invention is equipped with advanced analytical functions based on learner data and flexible curriculum generation functions using generative AI, and is novel and innovative in that it automatically provides learning support tailored to individual needs. This system dramatically improves efficiency and effectiveness in the educational environment and is particularly capable of universally providing high-quality learning opportunities.

[0647] The following describes the processing flow.

[0648] Step 1:

[0649] The server receives data related to each user's learning activities from their device and stores it in the cloud environment. This includes the learning materials used, the questions answered, and the study time.

[0650] Step 2:

[0651] The server analyzes the accumulated training data. Using machine learning algorithms, it identifies patterns to pinpoint the user's learning style, strengths, and weaknesses.

[0652] Step 3:

[0653] Based on the analysis results, the server automatically generates a personalized learning curriculum optimized for the user using AI. This curriculum is structured to combine learning materials and tasks according to the user's learning goals.

[0654] Step 4:

[0655] The server sends the generated curriculum to the terminal. The terminal displays this curriculum to the user through an interface.

[0656] Step 5:

[0657] Users begin learning through their terminals, following the curriculum provided by the server. If questions arise during their learning, they can send them to a virtual instructor.

[0658] Step 6:

[0659] The device suggests draft creation using AI generation for the user's output tasks (e.g., reports, presentation materials). This allows the user to complete deliverables efficiently.

[0660] Step 7:

[0661] The server monitors the user's progress in real time, generates feedback on areas for improvement and what to learn next, and sends it to the user's device.

[0662] Step 8:

[0663] The device provides a dashboard to visualize the learner's progress, showing the user their current status and guidance for future learning.

[0664] Step 9:

[0665] Based on the feedback and visualized data displayed on the device, users adjust their learning pace and methods, and then move on to the next step.

[0666] (Example 1)

[0667] 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".

[0668] The current education system makes it difficult to provide optimal educational support in real time, tailored to the individual learning needs and progress of each student. There is a lack of flexible means to provide effective learning plans for learners with diverse learning styles and characteristics, resulting in challenges in maximizing learning efficiency and outcomes.

[0669] 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.

[0670] In this invention, the server includes means for collecting learner information and storing it in distributed data storage, means for analyzing the stored learner information and identifying individual learning styles and tendencies, and means for generating a learning plan adapted to the learner based on the analysis results. This makes it possible to quickly and efficiently provide personalized learning plans and materials tailored to the characteristics of each learner, and to maximize learning outcomes through appropriate feedback.

[0671] "Learner information" refers to all data generated during the learning process, and specifically includes information such as learning history, answer results, and login times.

[0672] "Distributed data storage" is a data storage technology that efficiently stores and manages learner information, allowing for flexible access as needed. It is a system that manages information in a distributed manner across multiple servers or cloud services.

[0673] "Analysis" refers to methods used to identify and understand learners' characteristics and tendencies using collected data, and involves the use of machine learning algorithms and statistical techniques.

[0674] "Learning format" refers to the method or style in which learners can learn most effectively, and includes different learning tendencies such as visual, auditory, and tactile.

[0675] A "learning plan" refers to a curriculum or learning roadmap constructed based on analysis results and tailored to the individual needs of learners, outlining specific learning objectives and learning sequences.

[0676] A "virtual instructor" is an AI-based interactive support system that responds to learners' questions and is a virtual educational support system designed to assist with learning.

[0677] "Real-time monitoring" refers to a process that instantly tracks learning progress data and status, provides feedback as needed, and supports learning based on the latest information at all times.

[0678] An "initial draft" is a draft of a document or material that is automatically generated when a learner produces output, and it serves as basic supplementary material to support and facilitate the learner's work.

[0679] "Visualization" is a technique that presents learners' progress and data in a graphical format, making information easy to understand in order to facilitate data comprehension.

[0680] This system consists of three elements—server, terminal, and user—to provide a personalized learning experience.

[0681] First, the server is located in a cloud environment, collects information about learners, and stores it in distributed data storage. The server uses the Python programming language and the TensorFlow library to analyze this learner information by applying machine learning algorithms. This identifies individual learning styles and tendencies. Using the analysis results, the server constructs a learning plan adapted to the learner using generative AI (e.g., a natural language generation model). This plan specifically includes an individual curriculum, including learning objectives and learning sequence. The generated learning plan is sent to the terminal using a secure communication protocol.

[0682] Next, the terminal is a digital device that learners use on a daily basis. It receives learning plans sent from the server and presents them to the user. To support the user's learning activities, the terminal automatically generates initial drafts of documents and materials using generative AI. This functionality is provided via an AI plugin integrated into the terminal. For example, when a user is giving a presentation, the terminal initially presents the basic structure and main content of the slides, helping the user work efficiently.

[0683] Users interact with the system through their devices and progress through their learning according to the provided learning plan. If questions arise during learning, they can send them to a virtual instructor via their device. This virtual instructor utilizes generative AI to quickly generate answers to the user's questions and display them on the device. This allows users to continue learning while resolving their questions in real time.

[0684] As a concrete example, the server collects user A's math learning data and identifies areas where user A struggles. Based on the analysis, a curriculum focusing on algebra topics is generated and provided to user A. Also, when user A asks a question such as "Please explain how to expand an equation," the virtual instructor uses a generative AI to carefully generate an explanation and provides it through the terminal.

[0685] Examples of prompts include "Generate the next learning plan based on user X's past learning history" and "Create a step-by-step explanation for a specific math problem."

[0686] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0687] Step 1:

[0688] The server collects log information and learning history from learners via digital devices. Inputs include learners' access history and problem-solving data, while outputs are organized and stored in a database. Real-time data stream technology is used for this data collection.

[0689] Step 2:

[0690] The server applies machine learning algorithms to the collected data and performs data analysis. It identifies the learner's strengths and weaknesses, as well as their learning progress, from the input log information and learning history. The output is an individual learning profile obtained as a result of the analysis. Specifically, it trains and applies a neural network model using the Python library TensorFlow.

[0691] Step 3:

[0692] The server generates a personalized learning plan using a generative AI model based on the analysis results. The input is a prompt to the generative AI model, for example, "Create next week's curriculum based on the obtained profile." The output is the learning plan constructed in text format. In this process, a natural language generation algorithm is applied, and the learning content is automatically generated.

[0693] Step 4:

[0694] The server sends the generated training plan to the terminal. The input is the generated training plan, and the output is the plan data that arrives in the terminal's inbox. Secure data transfer technology (HTTPS) is used to send the data.

[0695] Step 5:

[0696] The terminal presents the user with a learning plan received from the server. The input is the learning plan data, and the output is content that is visually displayed to the user. The terminal's display and user interface are used for this presentation.

[0697] Step 6:

[0698] The terminal automatically generates initial drafts of documents using generative AI to support the user's output activities. The input is an overview of the task the user is working on, and the output is a draft of that task. In terms of operation, middleware is used to suggest slide structures when the user is creating presentation materials.

[0699] Step 7:

[0700] During the learning process, the user submits questions to a virtual instructor. The input is the user's question, and the output is a data request sent to the server via the terminal. An example of a prompt might be "Please explain the difference between these grammatical points."

[0701] Step 8:

[0702] The server uses a virtual instructor module to generate answers to received questions using a generative AI. The input is the question, and the output is the generated answer. A deep learning model in natural language processing operates during this process.

[0703] Step 9:

[0704] The device presents the generated answer to the user. The input is the answer text sent from the server, and the output is what is displayed on the user interface. Specifically, information is delivered to learners quickly using mobile notification functionality.

[0705] (Application Example 1)

[0706] 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".

[0707] Traditional learning systems have faced the challenge of providing a learning experience optimized for individual learners. In particular, they lacked the ability to generate dynamic curricula tailored to learners' circumstances at home and to automatically adjust to learning activities. As a result, it was difficult for learners to engage in independent, efficient, and effective learning.

[0708] 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.

[0709] In this invention, the server includes means for collecting learner data and storing it in a cloud environment, means for analyzing the stored data and identifying individual learning styles and tendencies, and means for generating an optimized learning curriculum based on the analysis results. This enables dynamic adjustment of learning difficulty through interaction with learners at home. This allows for flexible adaptation of learning content based on the learner's reaction speed and accuracy rate, enabling the provision of a more personalized and efficient learning experience.

[0710] "Learner data" refers to information about individual learners, including learning history, performance, and comprehension, and is a variety of information used to support learning.

[0711] A "cloud environment" is a server network accessed via the internet where data is stored and analyzed, and it serves as a technological foundation for providing various services.

[0712] "Learning style and tendencies" refer to the characteristics of a learner's learning methods, including areas they find easy to understand and areas they struggle with; they are individual learning habits and patterns.

[0713] An "optimized learning curriculum" is educational content and a learning plan designed to meet the abilities and needs of learners and enable them to learn efficiently.

[0714] A "virtual teacher" is a virtual teacher or educational support system that uses AI technology to answer learners' questions and provide educational support.

[0715] "Dialogue with learners at home" refers to two-way communication aimed at supporting learning, conducted by learners at home through educational robots or digital devices.

[0716] "Dynamic adjustment of learning difficulty" is a process that adjusts the difficulty level of learning in real time according to the learner's level of understanding and response.

[0717] "Reaction speed and accuracy" are indicators that show how quickly learners react to presented learning tasks and how accurately they can answer them.

[0718] "Flexible adaptation of learning content" refers to the ability of learning content and materials to be adapted to suit the learner.

[0719] This invention constructs a system that provides learners with an individualized educational experience. Its main components are a server, a terminal, and a learner (user). The server collects learner data in a cloud environment and analyzes the data using machine learning algorithms. Based on the analysis results, an AI model automatically generates a learning curriculum optimized for the learner. The generated curriculum is provided to the learner via the terminal, supporting their learning process.

[0720] The server is built on a cloud computing platform and implements machine learning algorithms using Python. TensorFlow and PyTorch are used to analyze learner data and identify individual learning styles. The resulting learning curriculum is then sent to the terminal via the HTTP protocol.

[0721] The terminal is implemented using devices such as Raspberry Pi and NVIDIA Jetson, and the user interface is built using MIT App Inventor. Generative AI automatically generates drafts based on the learner's output, and the terminal also monitors the learner's response speed and accuracy in real time, dynamically adjusting the learning content as needed.

[0722] As a concrete example, consider a scenario where a device interacts with a 10-year-old child at home, providing multiplication learning in a quiz format. Based on the analysis results, the device can instantly adjust the difficulty level of the questions to match the child's level of understanding. A virtual educator plays a role in quickly responding to the child's questions and facilitating learning retention.

[0723] The following is an example of a prompt statement passed to a generative AI model:

[0724] "Please generate a multiplication quiz suitable for a 10-year-old child. Please also include a simple explanation of subtraction."

[0725] This structure allows learners to receive individualized learning support at home, enabling them to learn efficiently at their own pace.

[0726] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0727] Step 1:

[0728] The server collects learner data in a cloud environment and stores it in a database. The input requires learner progress information and learning logs. This data is analyzed using machine learning algorithms to identify learning styles and trends. The output generates individual learning profiles.

[0729] Step 2:

[0730] The server uses a generative AI model to create a learning curriculum optimized for the learner, based on the obtained learning profile. Here, prompts are passed to the generative AI to generate the curriculum. The inputs required are the individual learning profile and prompts, and the output is the generated learning curriculum.

[0731] Step 3:

[0732] The terminal receives the learning curriculum sent from the server and presents it to the learner through a user interface. This allows learning materials and tasks to be displayed in response to the learner's input, assisting in the creation of output. The input requires learning curriculum data from the server, and the output is the presentation of learning materials to the user.

[0733] Step 4:

[0734] The device automatically creates drafts using generative AI as learners work on the presented tasks. When learners begin outputting, their text and answers are required as input, and a draft is generated as output.

[0735] Step 5:

[0736] The device monitors the learner's response speed and accuracy in real time and sends feedback to the server. Based on this information, the difficulty and content of the learning are dynamically adjusted. The input requires learner response data, and the output is an adapted learning task.

[0737] Step 6:

[0738] Users submit questions to a virtual educator and receive immediate answers. This process requires the learner's question as input, generates an answer using a generative AI, and presents it to the learner as output.

[0739] 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.

[0740] This invention integrates an emotion engine into a learning support system to recognize the learner's emotional state and provide an optimal learning experience. This system consists of three main elements: a server, a terminal, and a user.

[0741] The server is located in a cloud environment and stores data sent from learners, which is then analyzed by an emotion engine. This engine has the technology to estimate emotions from the user's facial expressions, voice, and operation patterns, enabling it to grasp the user's emotional state in real time. The server analyzes this emotional information in combination with training data to form a user-specific learning profile. Based on this profile, it generates a learning curriculum optimized for each individual user.

[0742] The device provides feedback to user actions and displays the learning curriculum sent from the server. If the user is emotionally stressed, the device presents relaxation content to create a more comfortable learning environment. Furthermore, when working on output tasks, it uses generative AI to automatically create drafts. Emotional data at this stage is fed back to the server for further optimization of learning.

[0743] Users can engage in learning activities using their devices and ask questions to a virtual teacher as they arise during their studies. The virtual teacher provides automatically generated answers in real time, helping to deepen the user's understanding. Furthermore, by considering the impact of the user's emotions on learning and adjusting the difficulty level and content of the assignments, a more personalized learning experience is possible.

[0744] For example, if a user repeatedly makes mistakes while solving a math problem, the device uses an emotion engine to detect the user's frustration and provides clearer explanatory videos or guided exercises. In this way, the present invention incorporates emotional data into the learning process, enabling flexible educational support tailored to the learner's needs and ultimately maximizing learning effectiveness.

[0745] The following describes the processing flow.

[0746] Step 1:

[0747] The user begins learning using the device. The device monitors the user's facial expressions and voice, collecting data to input into the emotion engine.

[0748] Step 2:

[0749] The device sends the collected emotional data to the server. The server analyzes this data using an emotion engine to identify the user's current emotional state.

[0750] Step 3:

[0751] The server analyzes the analyzed emotional state in combination with the learner's past learning data. This allows it to update the profile to match the individual's learning style and needs.

[0752] Step 4:

[0753] The server generates a learning curriculum optimized for the user based on the latest profile. It adjusts the difficulty and content of the curriculum according to the user's learning progress and emotional state.

[0754] Step 5:

[0755] The server delivers the generated curriculum to the terminal. The terminal presents the curriculum to the user and supports their learning.

[0756] Step 6:

[0757] Users progress through the curriculum via their devices. Any questions or issues during their studies can be immediately addressed to a virtual teacher.

[0758] Step 7:

[0759] The device automatically creates drafts for user output tasks using generation AI, assisting users in easily editing the content.

[0760] Step 8:

[0761] If the emotion engine detects the user's stress level during learning, the device will present relaxation content or adaptive learning content to alleviate the user's tension.

[0762] Step 9:

[0763] The server periodically updates the user's learning and sentiment data and provides a dashboard on the device that visualizes their progress. Users refer to this dashboard to adjust their learning pace and strategy.

[0764] (Example 2)

[0765] 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".

[0766] Conventional learning support systems have struggled to adequately understand and reflect learners' emotional states in their learning content, making it difficult to provide individually optimized learning experiences. Furthermore, they have lacked the flexibility to provide educational content tailored to learners' weaknesses and progress. Therefore, to maximize learning effectiveness, there is a need for a system that considers learners' emotional states and individual learning tendencies.

[0767] 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.

[0768] In this invention, the server includes means for collecting learner information and storing it in a network environment, means for analyzing the stored learner information and identifying individual learning tendencies and emotional states, and means for generating a learning method optimized for the learner based on the analysis results and emotional states. This makes it possible to grasp the emotional state of each learner in real time and provide an optimal learning method based on that.

[0769] "Learner information" refers to data about learners, including information related to their behavior, emotional state, and learning progress.

[0770] A "network environment" refers to the infrastructure for sending and receiving digital information, and includes cloud technology and communication networks.

[0771] "Analysis" refers to the process and methods used to extract useful information and find meaning in collected data.

[0772] "Learning tendencies" refer to specific learning approaches identified as a result of analyzing the learning styles and patterns exhibited by learners.

[0773] "Emotional state" refers to the emotions and psychological state that a learner is experiencing at a particular moment.

[0774] "Learning methods" refer to the structure and procedures of a series of educational activities, including the curriculum, materials, and support provided to learners.

[0775] "Real-time" refers to the attribute of processing where data and information are processed immediately without delay, and a response is provided to the user.

[0776] "Optimization" refers to the process of adjusting resources and conditions to achieve the greatest possible results for a specific purpose.

[0777] This invention is a system that supports online learning and consists of three main elements: a server, a terminal, and a user.

[0778] The server is located in a cloud computing environment and plays the role of storing data collected from users. The collected data includes facial expressions, voice, and operation patterns, and this data is processed using facial recognition and speech recognition technologies. The server analyzes the data to identify the learner's emotional state and learning tendencies, and executes an algorithm that generates a learning method optimized for each user based on this information. Technologies used include, for example, open-source image processing libraries for facial recognition and cloud service speech analysis APIs for speech recognition.

[0779] The terminal is a device that the user directly interacts with, and includes smartphones, tablets, and computers. The terminal displays personalized learning methods transmitted from the server on its screen. Furthermore, when a reaction is required, it uses a built-in feedback function to present appropriate content to the user. For example, if the terminal detects that the user is losing focus during learning, it will automatically play relaxation music or break content.

[0780] The user is the central figure in the learning process, operating the device to conduct their studies. During learning, users can receive support through a virtual instructor. The virtual instructor system utilizes a generative AI model to instantly generate responses to user questions. By using prompts such as, "I would like a more detailed explanation of this math problem," users can receive specific feedback.

[0781] For example, if a user makes repeated mistakes while solving a math problem, the server will assess the user's stress level and provide explanatory videos or guided exercises from the terminal. This allows the user to continue learning with peace of mind, resulting in improved learning efficiency.

[0782] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0783] Step 1:

[0784] The server receives data sent from the user via the terminal. Inputs include facial image data, audio clips, and logs of operation patterns. This data is stored in a database. The server preprocesses this data using facial recognition and audio analysis technologies to extract features for determining emotional states. The output is a categorized dataset for emotion analysis.

[0785] Step 2:

[0786] The server uses the dataset obtained in Step 1 to perform analysis with its emotion engine. The input is the organized dataset, and the output is the analysis result indicating the user's emotional state. Specifically, it applies a machine learning algorithm to output emotion labels such as "concentrated" or "stressed."

[0787] Step 3:

[0788] The server integrates analyzed emotional states with past learning data to analyze the user's learning tendencies. The input consists of the results of the emotional analysis and learning history data, while the output is the learner's profile information. Based on this, the server generates an optimized learning method and constructs the learning curriculum to be displayed next. It utilizes a generative AI model to determine the most suitable learning materials and assignments for the user.

[0789] Step 4:

[0790] A personalized learning curriculum is transferred from the server to the terminal. The terminal receives this learning curriculum and displays it in the user interface. The input is the curriculum data from the server, and the output is the screen display that the user can see. Specific operations include selecting and ordering learning content and displaying it in the UI.

[0791] Step 5:

[0792] Users progress through the learning process using their devices. When questions arise, they send prompt messages to a virtual instructor. The input is a question such as "I want to know more about this topic," and the virtual instructor generates a response using a generative AI model. The output is explanations and support information that are immediately displayed on the user's screen.

[0793] Step 6:

[0794] The device then collects response data to the user's interactions and feeds it back to the server. The input consists of user action data and newly collected sentiment data, while the output is an updated dataset for the next cycle. The server uses this data to further optimize the learning experience.

[0795] (Application Example 2)

[0796] 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".

[0797] Conventional learning support systems have a problem in that they do not adjust learning content to take into account the learner's emotional state, and therefore do not adequately reduce the stress and frustration that learners feel. Furthermore, there is a lack of means to analyze emotions in real time and quantitatively evaluate emotional factors that affect learning progress, making it difficult to optimize the learning experience.

[0798] 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.

[0799] In this invention, the server includes means for analyzing the learner's emotions and adjusting learning content based on their emotional state; means for identifying the learner's areas of weakness and prioritizing the provision of learning content to overcome them; means for providing encouragement and support based on the learner's emotional state; and means for providing the learner with specialized courses according to a generated plan and supporting the acquisition of practical skills. This enables more effective and personalized learning support for learners.

[0800] "Learner data" refers to all information related to a learner's learning process, including data on performance, learning style, and emotional state.

[0801] "Information processing environment" refers to systems used to collect, store, analyze, and manage digital information, and specifically includes cloud-based platforms.

[0802] A "learning plan" refers to a learning progress program designed according to the learner's characteristics and goals, and includes a curriculum structure to provide an optimal learning experience.

[0803] "Teaching materials and activities" refer to specific learning materials and activities provided to learners in order to acquire knowledge and skills.

[0804] "Deliverables" refer to the output that learners produce during the learning process, and include essays, reports, presentations, etc.

[0805] A "virtual instructor" refers to a digital educational support system that uses artificial intelligence to automatically provide answers to learners' questions.

[0806] "Emotional analysis" refers to the process of inferring a learner's psychological state from their facial expressions, words, actions, and behavior, and evaluating it as data.

[0807] "Means of adjusting learning content based on emotional state" refers to a system that changes the learning content and difficulty level provided according to the learner's emotions.

[0808] "Encouragement and support" refers to positive feedback and guidance given in accordance with the learner's emotions and learning content.

[0809] A "specialized course" refers to a learning course designed to acquire advanced knowledge and skills in a specific field.

[0810] This invention is a system for recognizing the emotional state of learners and providing an optimized learning experience. This system mainly consists of three elements: a server, a terminal, and a user.

[0811] The server functions as an information processing environment, storing learner data in the cloud. The emotion analysis system within the server analyzes the learner's facial expressions, tone of voice, and movements to evaluate their emotional state. This allows for data processing and emotion estimation necessary to identify each learner's learning style. The main technologies used here include the image processing library OpenCV and a generative AI model for emotion estimation (e.g., TensorFlow).

[0812] The terminal acts as a user interface, displaying an optimized learning plan generated from the server. It monitors the learner's emotional state in real time, providing encouraging and relaxing content when the learner faces difficulties, for example. It also assists in automatically creating drafts of the learner's output.

[0813] Users can engage in learning activities via their devices and resolve questions in real time using a virtual instructor. This virtual instructor is a generative AI-based system that automatically generates answers to user questions. By using prompts, it provides personalized feedback tailored to the user's specific needs and emotions.

[0814] A concrete example is when a user is practicing speaking English; the robot can sense their level of tension and offer encouragement such as, "It's okay, relax," to support smooth learning. An example of a prompt to the generative AI model is, "Analyze the user's facial expression and voice data, and generate appropriate dialogue messages and encouragement when signs of stress are detected."

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The server receives learner data from the user's terminal. This data includes facial expression images, audio clips, and operation logs. The input data is stored in a cloud-based database. The server performs data preprocessing, such as format conversion and noise reduction, as needed to analyze this data.

[0818] Step 2:

[0819] The server processes received facial image and audio clips using an emotion analysis system. It applies a face recognition algorithm to extract features for estimating the learner's emotional state. Image processing libraries such as OpenCV are used in this process. The generated features are input into an emotion model, which evaluates the learner's emotional state in real time and outputs an emotion score.

[0820] Step 3:

[0821] The server inputs the emotion score into a learning plan generation module and generates a learning plan optimized for the user's current emotional state. This process integrates the user's past learning history and current emotional state, and optimizes the curriculum using an optimization algorithm. The resulting curriculum is then sent to the terminal.

[0822] Step 4:

[0823] The device displays an optimized learning plan received from the server to the user. The device prepares to address any questions or problems the user may encounter during their learning process, via a virtual instructor. Specifically, it uses a generative AI model to automatically generate answers based on prompts and displays them on the screen.

[0824] Step 5:

[0825] As users progress through the learning process using their devices, they can ask questions to the virtual instructor as needed. In response to user input, the device uses the question as a prompt to call up a generative AI model that provides appropriate answers and instructions. By using these responses to advance their learning, users can gain a deeper understanding.

[0826] Step 6:

[0827] The device continuously monitors the learner's emotional state and learning progress, and sends feedback as needed. It provides relaxation content and encouraging messages to stabilize the user's emotional state. This feedback is also effective for the user because it is generated based on the results of emotion analysis.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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."

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] The following is further disclosed regarding the embodiments described above.

[0850] (Claim 1)

[0851] A means of collecting learner data and storing it in a cloud environment,

[0852] A means for analyzing the accumulated learner data and identifying individual learning styles and tendencies,

[0853] A means for generating a learning curriculum optimized for learners based on the analysis results,

[0854] A means of presenting learning materials and tasks to learners according to a generated curriculum,

[0855] A means of automatically creating drafts for the output produced by learners,

[0856] A means to monitor learners' progress in real time and provide feedback on areas for improvement,

[0857] A means of responding to learners' questions using a virtual teacher,

[0858] A means of visualizing and presenting the learner's progress,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, further comprising means for identifying areas of weakness for learners and prioritizing the provision of learning content to overcome those weaknesses.

[0862] (Claim 3)

[0863] The system according to claim 1, further comprising means for providing learners with specialized courses in accordance with a generated curriculum and for assisting them in acquiring practical skills.

[0864] "Example 1"

[0865] (Claim 1)

[0866] A means of collecting learner information and storing it in a distributed data storage,

[0867] A means for analyzing the accumulated learner information and identifying individual learning styles and trends,

[0868] A means for generating a learning plan adapted to the learner based on the analysis results,

[0869] A means of presenting learning materials and tasks to learners according to a generated learning plan,

[0870] A means of automatically generating an initial draft based on the output produced by the learner,

[0871] A means to monitor learners' progress in real time and provide feedback on areas for improvement,

[0872] A means of responding to learners' questions using a virtual instructor,

[0873] A means of visualizing and presenting the learner's progress,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, further comprising means for identifying areas in which learners are weak and prioritizing the provision of learning content to overcome those areas.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for providing learners with specialized courses in accordance with a generated learning plan and for assisting them in acquiring practical skills.

[0879] "Application Example 1"

[0880] (Claim 1)

[0881] A means of collecting learner data and storing it in a cloud environment,

[0882] A means for analyzing the accumulated learner data and identifying individual learning styles and tendencies,

[0883] A means for generating a learning curriculum optimized for learners based on the analysis results,

[0884] A means of presenting learning materials and tasks to learners according to a generated curriculum,

[0885] A means of automatically creating drafts for the output produced by learners,

[0886] A means to monitor learners' progress in real time and provide feedback on areas for improvement,

[0887] A means of responding to learners' questions using a virtual teacher,

[0888] A means of visualizing and presenting the learner's progress,

[0889] A means of interacting with learners at home and dynamically adjusting the learning difficulty level,

[0890] A means of adjusting learning content based on learners' reaction speed and accuracy,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, further comprising means for identifying areas of weakness for learners and prioritizing the provision of learning content to overcome those weaknesses.

[0894] (Claim 3)

[0895] The system according to claim 1, further comprising means for providing learners with specialized educational content in accordance with a generated curriculum and for supporting the acquisition of practical skills.

[0896] "Example 2 of combining an emotion engine"

[0897] (Claim 1)

[0898] A means of collecting learner information and storing it in a network environment,

[0899] A means for analyzing the accumulated learner information and identifying individual learning tendencies and emotional states,

[0900] A means for generating a learning method optimized for the learner based on analysis results and emotional state,

[0901] A means of presenting materials and assignments to learners according to the generated learning method,

[0902] A means of providing relaxation content according to the learner's emotional state,

[0903] A means of automatically creating a draft based on the output produced by the learner,

[0904] A means of monitoring learners' progress in real time and providing feedback on areas for improvement,

[0905] A means of answering learners' questions using a virtual instructor,

[0906] A means of visualizing and presenting the learner's progress,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, further comprising means for identifying areas in which learners are weak and prioritizing the provision of learning content to overcome those areas.

[0910] (Claim 3)

[0911] The system according to claim 1, further comprising means for providing learners with specialized courses in accordance with a generated learning method and for assisting them in acquiring practical skills.

[0912] "Application example 2 when combining with an emotional engine"

[0913] (Claim 1)

[0914] A means of collecting learner data and storing it in an information processing environment,

[0915] A means for analyzing the accumulated learner data and identifying individual learning styles and tendencies,

[0916] A means for generating a learning plan optimized for the learner based on the analysis results,

[0917] A means of presenting learning materials and tasks to learners according to the generated plan,

[0918] A means of automatically creating a draft for the deliverables produced by learners,

[0919] A means to monitor learners' progress in real time and provide feedback on areas for improvement,

[0920] A means of answering learners' questions using a virtual instructor,

[0921] A means of visualizing and presenting the learner's progress,

[0922] A means of analyzing learners' emotions and adjusting learning content based on their emotional state,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, further comprising means for identifying areas of difficulty for learners and prioritizing the provision of learning content to overcome those areas, and means for providing encouragement and support based on the learner's emotional state.

[0926] (Claim 3)

[0927] The system according to claim 1, further comprising means for providing learners with a specialized course in accordance with a generated plan and for assisting them in acquiring practical skills. [Explanation of symbols]

[0928] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting learner data and storing it in a cloud environment, A means for analyzing the accumulated learner data and identifying individual learning styles and tendencies, A means for generating a learning curriculum optimized for learners based on the analysis results, A means of presenting learning materials and tasks to learners according to a generated curriculum, A means of automatically creating drafts for the output produced by learners, A means to monitor learners' progress in real time and provide feedback on areas for improvement, A means of responding to learners' questions using a virtual teacher, A means of visualizing and presenting the learner's progress, A means of interacting with learners at home and dynamically adjusting the learning difficulty level, A means of adjusting learning content based on learners' reaction speed and accuracy, A system that includes this.

2. The system according to claim 1, further comprising means for identifying areas of weakness for learners and prioritizing the provision of learning content to overcome those weaknesses.

3. The system according to claim 1, further comprising means for providing learners with specialized educational content in accordance with a generated curriculum and for supporting the acquisition of practical skills.

Images