system

Abstract

We provide the system. [Solution] A processing device that receives learner learning data, analyzes that data, and evaluates learning progress and comprehension level, A curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the aforementioned processing device, A device that provides the generated curriculum to a medium used by learners, A response device that analyzes the questions entered by learners using natural language processing, generates appropriate answers, and presents them. It features a recording device that pre-saves learning content in the media, and has an asynchronous mode that allows it to operate even in areas with unstable communication environments. A method that incorporates home-based assistive devices that allow learners to experience education intuitively through physical contact and explain content using visual and physical representations, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 conventional learning systems, it has been difficult to provide equally high-quality educational opportunities to all learners due to regional and economic constraints. Also, in an environment with unstable Internet connection, online learning is easily interrupted, and as a result, there has been a problem that the learning opportunity is significantly impaired. Furthermore, it is difficult to provide customized education according to the understanding level and progress of individual learners, and there is a tendency to conduct uniform education. Thus, the lack of a flexible and universal learning support system specialized for the needs of individual learners is an issue.

Means for Solving the Problems

[0005] This invention includes an analysis means that receives learner learning data, analyzes that data, and evaluates learning progress and comprehension. It also includes a curriculum generation means that generates an individually optimized curriculum based on the evaluation, and provides the generated curriculum to the learner's terminal, thereby providing a real-time and efficient personalized educational experience. Furthermore, a question-answering means using natural language processing responds immediately to learner questions and provides multilingual support. In addition, by incorporating an offline mode, learning can be continued using pre-saved learning content even in areas without a network environment. In this way, a system is built that corrects educational disparities and provides equal educational opportunities to all learners.

[0006] A "learner" refers to someone who acquires knowledge and skills through the use of an educational system.

[0007] "Learning data" refers to all information generated by learners through educational activities, such as learning progress, comprehension, grades, and response trends.

[0008] "Analysis means" refers to a method or device that evaluates the learner's progress and level of understanding based on collected learning data and derives results.

[0009] "Curriculum generation means" refers to a method or system for constructing an educational curriculum optimized for each individual learner based on evaluations obtained through analysis means.

[0010] "Means of delivery" refers to methods or devices that directly present the generated curriculum to the learner's device.

[0011] A "question answering tool" refers to a method or function that receives questions from learners, generates appropriate answers using natural language processing, and responds to the learners.

[0012] "Offline mode" refers to a state in which certain system functions are available even when the internet connection is lost, and is characterized by the use of content stored on the device.

[0013] "Storage method" refers to a method or mechanism for accumulating learning content on a device and making it available regardless of whether or not there is a network connection. [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 Example 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.

Embodiments for Carrying Out the Invention

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

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

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

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

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

[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 that provides learners with an individualized educational experience. This system collects learner learning data and generates an appropriate learning curriculum based on that data. Furthermore, it implements an offline mode to ensure that education can continue even in areas with unstable internet connections.

[0036] The server receives learning data sent from learners via their devices. This data includes information about the learner's progress, past response history, and level of understanding. The received data is processed by an analysis system to evaluate the learner's learning status. Based on the evaluation results, the server generates a curriculum tailored to each individual learner. This curriculum aims to strengthen the learner's weaknesses and deepen their existing knowledge.

[0037] The terminal is responsible for presenting the curriculum received from the server to the learner. The terminal also allows learning to continue without relying on a network connection by using pre-downloaded learning content even in offline mode. Therefore, the terminal stores the necessary learning data locally in advance.

[0038] The learner, as the user, progresses through the learning process according to the curriculum presented via their device. If any questions or uncertainties arise during the learning process, the user can input questions in natural language. The server receives these questions and immediately generates answers using a question-answering mechanism. The generated answers are sent back to the user's device, and the user can refer to them to deepen their understanding.

[0039] As a concrete example, suppose User C is learning about "photosynthesis" in a science unit. The server incorporates relevant simulations and interactive teaching materials into the curriculum based on data related to "the relationship between light wavelengths and colors," which User C previously found difficult. User C can access these materials using their device and virtually check the experimental results. This allows User C to effectively acquire knowledge.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] Users log into the system and input information about their educational needs, such as learning topics and subjects they struggle with. Once they begin learning, progress information and answer data related to the learning content are saved on their device.

[0043] Step 2:

[0044] The terminal collects data obtained from the user and prepares it for transmission to the server. This data is sent to the server when the network connection is stable.

[0045] Step 3:

[0046] The server receives learning data sent from the terminal and uses analysis tools to analyze the user's learning progress and understanding. Here, statistical methods and machine learning techniques are used to identify areas of weakness.

[0047] Step 4:

[0048] Based on the analysis results, the server uses a curriculum generation mechanism to create a learning curriculum optimized for each individual user. This process generates a curriculum that reflects the user's areas of difficulty and interests.

[0049] Step 5:

[0050] The server sends the generated curriculum to the terminal, which then presents the curriculum to the user. The presented curriculum may include interactive learning materials and practice exercises.

[0051] Step 6:

[0052] Questions that arise during the user's learning process are entered into the device and sent to the server. Users can ask questions using natural language.

[0053] Step 7:

[0054] The server analyzes the received question using natural language processing and generates an appropriate answer using a question-answering mechanism. This answer is multilingual and translated into the user's selected language.

[0055] Step 8:

[0056] The generated answers are sent from the server to the terminal, which immediately presents them to the user. This allows the user to resolve any questions that arose during the learning process.

[0057] Step 9:

[0058] As the user progresses through their learning and completes a set course or reaches a certain level of progress, the device sends the latest progress data back to the server, which then generates a new curriculum. By repeating this cycle, the system provides users with continuous, personalized learning opportunities.

[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] In today's educational environment, there is a demand for providing personalized learning plans tailored to each individual student. However, accurately assessing students' progress and understanding, and then providing individualized learning materials based on that assessment, is difficult with traditional systems. To solve this problem, it is necessary to utilize the latest technologies to provide learning experiences that are appropriate for each student.

[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 evaluation means for receiving learner's educational data and analyzing the data to evaluate the progress and level of understanding of the education; plan generation means for generating an individualized educational plan for each learner based on the evaluation obtained by the evaluation means; provision means for providing the generated educational plan to the device used by the learner; and storage means for implementing an offline mode and pre-saving educational content to the device. This enables an individually optimized educational experience for learners, regardless of network conditions.

[0064] "Educational data" refers to information about learners' progress, past response history, and level of understanding. This information is analyzed to help generate personalized educational plans.

[0065] "Evaluation means" refers to technical functions that analyze received educational data to evaluate learners' educational progress and level of understanding.

[0066] "Plan generation means" refers to a function for generating an optimized educational plan for each learner based on educational data.

[0067] "Means of provision" refers to the function that provides the educational plan generated by the server to the device used by the learner, enabling the learner to proceed with their studies accordingly.

[0068] "Storage means" refers to a technical function for saving educational content to a device in advance so that learning can continue even in situations where the network connection is unstable.

[0069] A "question answering system" refers to a function that receives questions from learners in natural language, generates appropriate answers, and presents them.

[0070] A "generative artificial intelligence model" refers to a machine learning model or artificial intelligence technology used to generate appropriate answers to questions from learners.

[0071] "Optimization means" refers to technical functions that incorporate interactive educational materials and simulations into the structure of educational plans based on previous learning results and learners' weaknesses.

[0072] This invention is a system that provides learners with optimized educational plans. The system consists of a server, terminals, and users.

[0073] The server primarily plays a central role in receiving and analyzing learner education data. It uses software libraries such as Python and Scikit-learn to assess learners' progress and understanding. Machine learning models are utilized in data analysis to identify learners' strengths and areas for improvement.

[0074] The terminal displays the learning plan provided by the server to the learner. The terminal also has the ability to save necessary educational data to local storage in advance so that learners can access educational content even in an offline environment. A web browser and JavaScript® are used for saving and displaying the data.

[0075] The user, as the learner, can progress through the learning process according to the educational plan provided via the device. If they encounter a difficult point during learning, they can input a question in natural language. For example, they might input a prompt such as, "Please explain the roles of light wavelength and color in photosynthesis."

[0076] The server uses a generative AI model to generate appropriate responses to such prompts. The generated responses are immediately sent back to the terminal, allowing the user to review them and deepen their understanding. This system enables learners to enjoy a learning experience optimized according to their individual progress and level of understanding.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server receives educational data sent from the learner's device. The input is expected to be in JSON format, containing information about the learner's progress, past response history, and level of understanding. The server then runs a Python script to analyze this data and save it to a database. This process efficiently manages the learner's educational history.

[0080] Step 2:

[0081] The server uses a machine learning model to analyze the received educational data. The input is the stored educational data, which is used to evaluate the learner's progress and strengths and weaknesses. The output is the evaluation result, which includes the educational strengths and weaknesses identified for each learner. Specifically, it uses libraries such as Scikit-learn to process the data with a particular algorithm and generate evaluation criteria.

[0082] Step 3:

[0083] The server generates an optimal learning plan for the learner based on the analyzed evaluation results. The input is the evaluation results, and the output is provided as a curriculum tailored to the learner. A generative AI model is used to dynamically construct learning content and generate it in HTML format. This creates a personalized learning plan that focuses on what the learner needs.

[0084] Step 4:

[0085] The terminal receives the educational plan sent from the server and displays it to the user. The input is the educational plan from the server, and the output is the educational content displayed on the user's screen. The terminal temporarily stores the necessary content in local storage and dynamically displays it on the web browser using JavaScript. This allows the user to continue learning regardless of network availability.

[0086] Step 5:

[0087] Users input questions that arise during the learning process into the terminal. They can input natural language questions as prompts, such as "Explain the roles of light wavelength and color in photosynthesis." The input is this prompt, and the output is the answer returned by the server.

[0088] Step 6:

[0089] The server analyzes questions received from the user and generates appropriate answers using a generative AI model. The input is the user's prompt, and the output is the answer in natural language. The generated answer is immediately sent back to the terminal, and the user can use that information as a reference for learning.

[0090] (Application Example 1)

[0091] 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."

[0092] In today's educational environment, providing customized learning experiences tailored to each individual learner is crucial. However, traditional education systems struggle to deliver individually optimized curricula in real time, and consistent educational support may be unavailable depending on location and communication environment. Furthermore, home learning support, in particular, lacks physical and interactive elements, making it difficult to maintain learners' interest. An effective system is needed to address these challenges and support learners in actively engaging with their studies.

[0093] 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.

[0094] In this invention, the server includes a processing device that receives learner learning data and analyzes the data to evaluate learning progress and comprehension; a course generation device that generates a customized curriculum for each learner based on the evaluation obtained by the processing device; and a provisioning device that provides the generated curriculum to a medium used by the learner. This makes it possible to provide optimized educational content for each individual learner and to continue learning consistently regardless of location or communication environment. Furthermore, by using a response device to resolve learners' questions and providing physical educational experiences through home-use assistive devices, it is possible to increase learners' interest and improve the effectiveness of learning.

[0095] A "learner" is an individual who seeks to acquire knowledge and skills through the use of an educational system.

[0096] "Learning data" refers to information about the learner's progress, level of understanding, past learning history, and answer history.

[0097] A "processing device" is a device that analyzes received learning data and has the function of evaluating the learner's learning progress and level of understanding.

[0098] A "curriculum" refers to learning content and plans that are customized based on the evaluation results of learners.

[0099] A "curriculum generation device" is a device that generates individualized educational curricula based on the evaluation results of each learner.

[0100] A "distribution device" is a medium that plays the role of presenting the generated curriculum to learners.

[0101] A "response device" is a device that analyzes questions entered by learners using natural language processing, generates appropriate answers, and presents them.

[0102] "Home-use assistive devices" are devices that provide an intuitive educational experience through physical contact with the learner and explain learning content using visual and physical representations.

[0103] "Asynchronous mode" refers to a state in which the system operates based on data that has been previously stored locally, regardless of network conditions.

[0104] "Cameras and sensors" are devices that detect learners' movements, analyze that data, and support interactive educational activities.

[0105] To implement this invention, a system program is needed to provide learners with an individualized educational experience. This system functions through the combination of multiple elements.

[0106] The server receives learning data transmitted through the learner's medium, which includes information about the learner's progress, past response history, and level of understanding. This data is analyzed by the processing unit, which evaluates the learner's learning status. Based on this, the processing unit generates an optimal curriculum for the learner. The generated curriculum is then presented to the learner's medium by the providing device.

[0107] The medium not only displays the generated curriculum to learners but also includes a recording device that allows learning to continue even in offline environments and can operate in asynchronous mode. Even in areas with unstable communication environments, it is possible to utilize educational content previously stored on the medium.

[0108] Furthermore, the response device analyzes natural language questions entered by learners into the medium, instantly generates appropriate answers, and sends them back to the medium, thereby deepening the learner's understanding. Also included are home-use assistive devices that physically interact with learners and intuitively present educational content through visual and physical representations.

[0109] This system incorporates cameras and sensors to capture learners' movements and support real-time, interactive educational activities. Furthermore, the use of generative AI models ensures that the curriculum and response content are always up-to-date.

[0110] For example, if a learner asks, "Tell me about photosynthesis," the home-use assistive device visually reproduces the process of photosynthesis using a plant model, and the response device provides relevant information. This allows learners to deepen their knowledge through hands-on experience.

[0111] Example prompt: "Tell me about an application where you can ask a robot questions about photosynthesis, and it will explain them in detail using real-time visuals."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server receives learner data sent from the terminal. This data includes information about the learner's progress, past response history, and level of understanding. The received data is stored in a database.

[0115] Step 2:

[0116] The server analyzes the received learning data using a processing unit. Specifically, it uses data analysis algorithms to assess the learner's progress and level of understanding. The analysis results are output as evaluation data that shows the learner's level of understanding and characteristics.

[0117] Step 3:

[0118] The server utilizes a generation AI model based on evaluation data to generate a curriculum tailored to each learner. The curriculum generation process constructs a curriculum that takes into account each learner's strengths and weaknesses. This generated curriculum is then used in the next step.

[0119] Step 4:

[0120] The terminal presents the curriculum, received from the server via a distribution device, to the learner. If the learner accesses the curriculum in a local environment, offline learning is possible by using content pre-stored on the terminal.

[0121] Step 5:

[0122] The user (learner) can ask natural language questions entered into their device. The input data is sent to a response device and automatically analyzed through natural language processing. An appropriate answer generated based on the analysis results is output and displayed on the user's device.

[0123] Step 6:

[0124] Home-use assistive devices physically interact with learners and monitor their movements using sensors and cameras. They support real-time, interactive learning and provide visual explanations as needed. This process allows learners to understand educational content more intuitively.

[0125] 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.

[0126] This invention relates to a system that provides learners with an individualized educational experience, incorporating an emotion engine to recognize the learner's emotional state and dynamically adjusting the learning curriculum and educational content based on that state. This system monitors the learner's emotions in real time through the emotion engine and measures changes in stress and motivation.

[0127] The server receives learner learning data and comprehensively analyzes it, not only evaluating learning progress and comprehension through analysis tools, but also including emotional data provided by the emotion engine. This allows the curriculum generation tool to generate a customized curriculum based on the learner's emotional state. For example, if the emotion engine detects stress in the learner, the server can suggest relaxing learning content or a slower-paced curriculum to help them cope with that stress.

[0128] The device is responsible for providing learners with curriculum and learning content transmitted from the server, while simultaneously collecting emotional data. During the learning process, users engage with interactive content and adjust their learning experience in response to questions suggested by the device.

[0129] As a concrete example, suppose user D begins to feel stressed while trying to solve a difficult math problem. The emotion engine detects changes in user D's facial expressions and tone of voice through the camera and voice input, recognizing signs of stress. The server receives this information and supports user D's motivation to learn by including relaxing visual content and meditative music in the newly generated curriculum. As a result, user D can continue learning while reducing stress.

[0130] In this way, the integration of the emotion engine and the learning management system creates a flexible and responsive learning environment that responds to the individual emotional state of each learner.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] When a user begins learning, the device collects emotional data through its camera and microphone along with the learning data, and transmits this data to the server in real time.

[0134] Step 2:

[0135] The server processes the received learning data and sentiment data through an analysis device. In addition to evaluating learning progress and comprehension, the analysis device performs a sentiment evaluation using an emotion engine.

[0136] Step 3:

[0137] The emotion engine analyzes the user's emotional state and detects changes in stress and motivation. Based on these results, it assesses the degree to which stress reduction is needed.

[0138] Step 4:

[0139] Based on the analysis results, the server generates a curriculum tailored to the user's emotional state using a curriculum generation system. For example, if the user is experiencing high stress, the curriculum will incorporate slower-paced lessons and content designed to promote relaxation.

[0140] Step 5:

[0141] The server sends the generated curriculum to the terminal, which then presents it to the user. The terminal provides interactive feedback as needed.

[0142] Step 6:

[0143] As users progress through the learning process according to the provided curriculum, if questions arise, they can enter additional questions or requests via their device to receive support tailored to their emotional state.

[0144] Step 7:

[0145] The server receives questions from users and generates appropriate answers using question-answering mechanisms. Sentimental data is taken into consideration, and answers including mental support are generated as needed.

[0146] Step 8:

[0147] The answers are sent to the device, which then presents them to the user. Based on these answers, the user can deepen their understanding and revise their learning.

[0148] Step 9:

[0149] After a learning session ends, the device sends the latest learning data and emotional change history to the server. The server receives this data and uses it to optimize future curricula and emotional support.

[0150] (Example 2)

[0151] 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".

[0152] In today's educational environment, it is difficult for learners to receive an educational experience optimized based on their individual emotional state and learning progress. However, a uniform curriculum for each learner can lead to decreased learning efficiency and a decline in motivation. Therefore, there is a need to develop a system that can provide individualized curricula that take into account the learner's emotions and progress.

[0153] 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.

[0154] In this invention, the server includes means for receiving learner learning data and emotional data, analyzing the data to evaluate learning progress, comprehension, and emotional state; means for generating a customized curriculum for each learner that takes into account stress reduction and improved motivation to learn, based on the evaluation obtained by the analysis means; and means for providing the generated curriculum to the terminal used by the learner and simultaneously collecting emotional data in real time. This makes it possible to provide a dynamic and adaptive learning environment that is tailored to the individual circumstances of each learner.

[0155] "Learning data" refers to information about the learning activities that learners engage in on a daily basis, including indicators that show progress and level of understanding.

[0156] "Emotional data" refers to information that reflects the learner's mental state, and is derived from data such as facial expressions, voice, and behavioral patterns.

[0157] "Analysis means" refers to a technical method that processes collected learning data and sentiment data to evaluate the learner's progress, understanding, and emotional state.

[0158] A "curriculum generation method" is a technical method that uses evaluation results obtained through analysis to create a learning plan optimized for each learner.

[0159] "Delivery means" refers to the technical infrastructure for transmitting the generated curriculum and related learning content to the learner's device, enabling the learner to access it appropriately.

[0160] "Natural language processing" is a technology that analyzes learner input in a way that a machine can understand and generates an appropriate response.

[0161] "Offline mode" refers to a system configuration that allows learning content and functions to be provided even in situations with an unstable network connection, and where data is pre-stored on the device.

[0162] "Storage means" refers to technical components for pre-storing necessary learning materials and data within a device.

[0163] This invention is an educational system designed to personalize learners, combining an emotional engine with learning management. The program has the function of providing an adaptive curriculum based on collected data.

[0164] The server receives learning data and emotional data sent from learners. Emotional data is collected using facial recognition software and voice analysis tools that utilize the device's camera and microphone. The server analyzes this data and uses AI algorithms to evaluate learning progress, comprehension, and emotional state.

[0165] Based on this information, the server uses a generative AI model to create a customized curriculum that takes stress reduction and learning motivation into consideration. For example, if a user faces a difficult task and feels stressed, the server can provide relaxing content or a slower learning schedule.

[0166] The terminal presents the provided curriculum to the learner and collects learner feedback and new emotional data. This two-way data exchange allows the server to readjust the curriculum in real time and create an optimal learning environment tailored to the learner's situation.

[0167] For example, when a user is working on an advanced math problem, if the system detects the user's stress level through camera and voice input, it will recommend a new learning path accordingly. An example of the prompt in this case would be: "This system detects the user's stress level and generates a curriculum that suggests relaxing learning content. How does this system monitor the learner's emotional state and provide a personalized curriculum?"

[0168] In this way, a learning management system incorporating an emotion engine enables a flexible educational experience tailored to the learner's needs.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The device uses a camera and microphone to monitor the learner's learning progress and emotional state. Specifically, the device analyzes the user's facial expressions using facial recognition software and records the tone and speed of their voice using a speech recognition tool. This collects learning data and emotional data, which are then sent to a server as input and output.

[0172] Step 2:

[0173] The server analyzes the received learning data and emotional data. Specifically, it inputs the collected data into an AI algorithm to evaluate learning progress, comprehension, and emotional state. This process evaluates the learner's stress level and motivation level, and generates analysis results, which serve as both input and output.

[0174] Step 3:

[0175] The server uses a generative AI model to create a customized curriculum based on the analysis results. Specifically, this model configures appropriate learning content and resources based on each learner's evaluation and generates a new curriculum. The goal is to output a learning plan optimized for each learner.

[0176] Step 4:

[0177] The server sends the generated curriculum to the terminal. The terminal then begins displaying the received content to the user. Specifically, the terminal displays the provided curriculum on its screen and plays visual and auditory learning content. This provides the user with the information they need to progress in their learning.

[0178] Step 5:

[0179] Users progress through their learning based on the provided curriculum. As users progress, the device continuously collects data in real time by providing new questions and feedback. Specifically, when users provide feedback through interactive content, the data is updated based on the inquiry. This feedback is sent to the server and input as adjustments for the next curriculum.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0182] In recent years, there has been a growing demand for individualized education, making it crucial to provide curricula tailored to the individual needs and emotional states of each learner. However, conventional educational management systems have struggled to recognize learners' emotional states in real time and dynamically adjust learning content accordingly. This has resulted in challenges in reducing learner motivation and stress, and in providing an effective learning environment.

[0183] 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.

[0184] In this invention, the server includes an evaluation device that receives learner learning data and analyzes the data to evaluate learning progress and comprehension; a curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the evaluation device; a distribution device that provides the generated curriculum to the terminal used by the learner; an emotion analysis device that recognizes the learner's emotional state in real time; and a curriculum adjustment device that has the function of adjusting the learning content and pace to reduce stress based on the data from the emotion analysis device. This makes it possible to provide a flexible and adaptive learning experience that is tailored to the learner's individualized emotional state.

[0185] An "evaluation device" is a device that receives learner's learning data, analyzes that data, and evaluates their learning progress and level of understanding.

[0186] A "curriculum generation device" is a device that generates a customized curriculum for each learner based on evaluations obtained by an evaluation device.

[0187] A "distribution device" is a device that provides the generated curriculum to the terminals used by learners.

[0188] An "emotion analysis device" is a device that recognizes a learner's emotional state in real time.

[0189] A "curriculum adjustment device" is a device that adjusts learning content and pace to reduce stress based on data from an emotion analysis device.

[0190] The system for implementing this invention has a configuration that incorporates an evaluation device, a curriculum generation device, a distribution device, an emotion analysis device, and a curriculum adjustment device.

[0191] The server first receives learning data from learners using an evaluation device and performs analysis. This analysis evaluates the learners' learning progress and level of understanding. Next, based on the evaluation results, a curriculum generation device creates an individualized curriculum for each learner. Once generated, this curriculum is provided to the learner's terminal by a distribution device.

[0192] Furthermore, the terminal is equipped with an emotion analysis device that uses a camera and microphone to monitor changes in the learner's facial expressions and voice in real time. The emotion analysis device uses this data to determine the learner's emotional state. For example, if a learner is feeling stressed, the curriculum adjustment device can receive this data and issue instructions to adjust the learning content and pace.

[0193] As a concrete example, the system's program is written using Python. The camera module uses the OpenCV library to perform real-time facial expression analysis. In addition, Python's NLTK library is used for natural language processing to generate responses to learners' questions. When stress is detected, AWS Lambda is used to process instructions for curriculum adjustment in the cloud and notify the terminal of the results.

[0194] Consider a scenario where a user is using the system, for example, a primary school student tackling a complex math problem. If the emotion analysis device detects that the user is feeling confused, the curriculum adjustment device recommends relaxation content best suited to that state. In this situation, it is possible to send a prompt message to the generative AI model such as, "Please select relaxation content suitable for a student who is having trouble concentrating on the math problem. The student is confused and needs a short break," thereby providing appropriate educational content.

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server receives learning data from learners. The input data concerns the subjects the learners are studying and their progress. By analyzing this data, the server evaluates the learners' progress and understanding. Specifically, it performs statistical processing on the data and calculates a score for each item.

[0198] Step 2:

[0199] The server uses an evaluation device to assess the learner's level of understanding based on the analysis results, and then uses a curriculum generation device to create an individualized curriculum. The output is a new curriculum proposal, which determines the learning content best suited to the user's current learning level. Specifically, it uses an AI algorithm to propose personalized educational content.

[0200] Step 3:

[0201] The server transmits the curriculum to user terminals via a distribution device. The input is the generated curriculum draft, and the output is the learning content displayed on the user terminal. In this step, data is transmitted over the network to ensure that the educational content is delivered to learners on time.

[0202] Step 4:

[0203] The device uses an emotion analysis system to monitor the learner's emotional state in real time. Input is facial and audio data acquired from a camera and microphone, and output is the recognized emotional state of the learner. The system uses the OpenCV library to perform facial recognition and identify individual emotions.

[0204] Step 5:

[0205] The server receives emotional data from the emotion analysis device and dynamically adjusts the learning content and pace using the curriculum adjustment device. The input is emotional data, and the output is the adjusted educational curriculum. Specifically, if an indicator of stress is high, the curriculum is modified to reduce the learner's burden, such as by adding relaxation content.

[0206] Step 6:

[0207] When a user engages with content, a generative AI model is used to generate prompts and provide appropriate learning support. The input is information about the learning content and emotional state, and the output is a prompt generated based on that information. For example, it might generate a prompt such as, "Based on your current level of understanding, please suggest the next problem to solve," and then take specific actions to support learning.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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".

[0224] This invention is a system that provides learners with an individualized educational experience. This system collects learner learning data and generates an appropriate learning curriculum based on that data. Furthermore, it implements an offline mode to ensure that education can continue even in areas with unstable internet connections.

[0225] The server receives learning data sent from learners via their devices. This data includes information about the learner's progress, past response history, and level of understanding. The received data is processed by an analysis system to evaluate the learner's learning status. Based on the evaluation results, the server generates a curriculum tailored to each individual learner. This curriculum aims to strengthen the learner's weaknesses and deepen their existing knowledge.

[0226] The terminal is responsible for presenting the curriculum received from the server to the learner. The terminal also allows learning to continue without relying on a network connection by using pre-downloaded learning content even in offline mode. Therefore, the terminal stores the necessary learning data locally in advance.

[0227] The learner, as the user, progresses through the learning process according to the curriculum presented via their device. If any questions or uncertainties arise during the learning process, the user can input questions in natural language. The server receives these questions and immediately generates answers using a question-answering mechanism. The generated answers are sent back to the user's device, and the user can refer to them to deepen their understanding.

[0228] As a concrete example, suppose User C is learning about "photosynthesis" in a science unit. The server incorporates relevant simulations and interactive teaching materials into the curriculum based on data related to "the relationship between light wavelengths and colors," which User C previously found difficult. User C can access these materials using their device and virtually check the experimental results. This allows User C to effectively acquire knowledge.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] Users log into the system and input information about their educational needs, such as learning topics and subjects they struggle with. Once they begin learning, progress information and answer data related to the learning content are saved on their device.

[0232] Step 2:

[0233] The terminal collects data obtained from the user and prepares it for transmission to the server. This data is sent to the server when the network connection is stable.

[0234] Step 3:

[0235] The server receives learning data sent from the terminal and uses analysis tools to analyze the user's learning progress and understanding. Here, statistical methods and machine learning techniques are used to identify areas of weakness.

[0236] Step 4:

[0237] Based on the analysis results, the server uses a curriculum generation mechanism to create a learning curriculum optimized for each individual user. This process generates a curriculum that reflects the user's areas of difficulty and interests.

[0238] Step 5:

[0239] The server sends the generated curriculum to the terminal, which then presents the curriculum to the user. The presented curriculum may include interactive learning materials and practice exercises.

[0240] Step 6:

[0241] Questions that arise during the user's learning process are entered into the device and sent to the server. Users can ask questions using natural language.

[0242] Step 7:

[0243] The server analyzes the received question using natural language processing and generates an appropriate answer using a question-answering mechanism. This answer is multilingual and translated into the user's selected language.

[0244] Step 8:

[0245] The generated answers are sent from the server to the terminal, which immediately presents them to the user. This allows the user to resolve any questions that arose during the learning process.

[0246] Step 9:

[0247] As the user progresses through their learning and completes a set course or reaches a certain level of progress, the device sends the latest progress data back to the server, which then generates a new curriculum. By repeating this cycle, the system provides users with continuous, personalized learning opportunities.

[0248] (Example 1)

[0249] 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."

[0250] In today's educational environment, there is a demand for providing personalized learning plans tailored to each individual student. However, accurately assessing students' progress and understanding, and then providing individualized learning materials based on that assessment, is difficult with traditional systems. To solve this problem, it is necessary to utilize the latest technologies to provide learning experiences that are appropriate for each student.

[0251] 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.

[0252] In this invention, the server includes evaluation means for receiving learner's educational data and analyzing the data to evaluate the progress and level of understanding of the education; plan generation means for generating an individualized educational plan for each learner based on the evaluation obtained by the evaluation means; provision means for providing the generated educational plan to the device used by the learner; and storage means for implementing an offline mode and pre-saving educational content to the device. This enables an individually optimized educational experience for learners, regardless of network conditions.

[0253] "Educational data" refers to information about learners' progress, past response history, and level of understanding. This information is analyzed to help generate personalized educational plans.

[0254] "Evaluation means" refers to technical functions that analyze received educational data to evaluate learners' educational progress and level of understanding.

[0255] "Plan generation means" refers to a function for generating an optimized educational plan for each learner based on educational data.

[0256] "Means of provision" refers to the function that provides the educational plan generated by the server to the device used by the learner, enabling the learner to proceed with their studies accordingly.

[0257] "Storage means" refers to a technical function for saving educational content to a device in advance so that learning can continue even in situations where the network connection is unstable.

[0258] A "question answering system" refers to a function that receives questions from learners in natural language, generates appropriate answers, and presents them.

[0259] A "generative artificial intelligence model" refers to a machine learning model or artificial intelligence technology used to generate appropriate answers to questions from learners.

[0260] "Optimization means" refers to technical functions that incorporate interactive educational materials and simulations into the structure of educational plans based on previous learning results and learners' weaknesses.

[0261] This invention is a system that provides learners with optimized educational plans. The system consists of a server, terminals, and users.

[0262] The server primarily plays a central role in receiving and analyzing learner education data. It uses software libraries such as Python and Scikit-learn to assess learners' progress and understanding. Machine learning models are utilized in data analysis to identify learners' strengths and areas for improvement.

[0263] The device displays the learning plan provided by the server to the learner. The device also has the ability to pre-save necessary educational data to local storage so that learners can access the educational content even in offline environments. A web browser and JavaScript are used for saving and displaying the data.

[0264] The user, as the learner, can progress through the learning process according to the educational plan provided via the device. If they encounter a difficult point during learning, they can input a question in natural language. For example, they might input a prompt such as, "Please explain the roles of light wavelength and color in photosynthesis."

[0265] The server uses a generative AI model to generate appropriate responses to such prompts. The generated responses are immediately sent back to the terminal, allowing the user to review them and deepen their understanding. This system enables learners to enjoy a learning experience optimized according to their individual progress and level of understanding.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The server receives educational data sent from the learner's device. The input is expected to be in JSON format, containing information about the learner's progress, past response history, and level of understanding. The server then runs a Python script to analyze this data and save it to a database. This process efficiently manages the learner's educational history.

[0269] Step 2:

[0270] The server uses a machine learning model to analyze the received educational data. The input is the stored educational data, which is used to evaluate the learner's progress and strengths and weaknesses. The output is the evaluation result, which includes the educational strengths and weaknesses identified for each learner. Specifically, it uses libraries such as Scikit-learn to process the data with a particular algorithm and generate evaluation criteria.

[0271] Step 3:

[0272] The server generates an optimal learning plan for the learner based on the analyzed evaluation results. The input is the evaluation results, and the output is provided as a curriculum tailored to the learner. A generative AI model is used to dynamically construct learning content and generate it in HTML format. This creates a personalized learning plan that focuses on what the learner needs.

[0273] Step 4:

[0274] The terminal receives the educational plan sent from the server and displays it to the user. The input is the educational plan from the server, and the output is the educational content displayed on the user's screen. The terminal temporarily stores the necessary content in local storage and dynamically displays it on the web browser using JavaScript. This allows the user to continue learning regardless of network availability.

[0275] Step 5:

[0276] Users input questions that arise during the learning process into the terminal. They can input natural language questions as prompts, such as "Explain the roles of light wavelength and color in photosynthesis." The input is this prompt, and the output is the answer returned by the server.

[0277] Step 6:

[0278] The server analyzes questions received from the user and generates appropriate answers using a generative AI model. The input is the user's prompt, and the output is the answer in natural language. The generated answer is immediately sent back to the terminal, and the user can use that information as a reference for learning.

[0279] (Application Example 1)

[0280] 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."

[0281] In a modern educational environment, it is important to provide a customized educational experience tailored to each learner. However, in conventional educational systems, it is difficult to provide an individually optimized educational curriculum in real time, and furthermore, consistent educational support cannot be received depending on the region and communication environment. In addition, especially in learning support at home, there are no physical and interactive elements, making it difficult to maintain the interest of learners. There is a need for an effective system that solves these problems and supports learners in learning actively.

[0282] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0283] In this invention, the server includes a processing apparatus that receives learning data of a learner, analyzes the data, and evaluates the learning progress and comprehension level, a course generation apparatus that generates a customized educational course for each learner based on the evaluation obtained by the processing apparatus, and a providing apparatus that provides the generated educational course to a medium used by the learner. Thereby, it becomes possible to provide educational content optimized for each individual learner and to continuously learn consistently regardless of the region without depending on the communication environment. Furthermore, by eliminating the learner's questions with a response apparatus and providing a physical educational experience through home support equipment, it becomes possible to increase the learner's interest and improve the learning effect.

[0284] A "learner" is an individual who attempts to acquire knowledge and skills using an educational system.

[0285] "Learning data" refers to information regarding the progress, comprehension level, past learning history, and answer history of a learner.

[0286] A "processing apparatus" is an apparatus having a function for analyzing received learning data and evaluating the learning progress and comprehension level of a learner.

[0287] A "curriculum" refers to learning content and plans that are customized based on the evaluation results of learners.

[0288] A "curriculum generation device" is a device that generates individualized educational curricula based on the evaluation results of each learner.

[0289] A "distribution device" is a medium that plays the role of presenting the generated curriculum to learners.

[0290] A "response device" is a device that analyzes questions entered by learners using natural language processing, generates appropriate answers, and presents them.

[0291] "Home-use assistive devices" are devices that provide an intuitive educational experience through physical contact with the learner and explain learning content using visual and physical representations.

[0292] "Asynchronous mode" refers to a state in which the system operates based on data that has been previously stored locally, regardless of network conditions.

[0293] "Cameras and sensors" are devices that detect learners' movements, analyze that data, and support interactive educational activities.

[0294] To implement this invention, a system program is needed to provide learners with an individualized educational experience. This system functions through the combination of multiple elements.

[0295] The server receives learning data transmitted through the learner's medium, which includes information about the learner's progress, past response history, and level of understanding. This data is analyzed by the processing unit, which evaluates the learner's learning status. Based on this, the processing unit generates an optimal curriculum for the learner. The generated curriculum is then presented to the learner's medium by the providing device.

[0296] The medium not only displays the generated curriculum to learners but also includes a recording device that allows learning to continue even in offline environments and can operate in asynchronous mode. Even in areas with unstable communication environments, it is possible to utilize educational content previously stored on the medium.

[0297] Furthermore, the response device analyzes natural language questions entered by learners into the medium, instantly generates appropriate answers, and sends them back to the medium, thereby deepening the learner's understanding. Also included are home-use assistive devices that physically interact with learners and intuitively present educational content through visual and physical representations.

[0298] This system incorporates cameras and sensors to capture learners' movements and support real-time, interactive educational activities. Furthermore, the use of generative AI models ensures that the curriculum and response content are always up-to-date.

[0299] For example, if a learner asks, "Tell me about photosynthesis," the home-use assistive device visually reproduces the process of photosynthesis using a plant model, and the response device provides relevant information. This allows learners to deepen their knowledge through hands-on experience.

[0300] Example prompt: "Tell me about an application where you can ask a robot questions about photosynthesis, and it will explain them in detail using real-time visuals."

[0301] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0302] Step 1:

[0303] The server receives learner data sent from the terminal. This data includes information about the learner's progress, past response history, and level of understanding. The received data is stored in a database.

[0304] Step 2:

[0305] The server analyzes the received learning data using a processing device. Specifically, it evaluates the progress of learners and analyzes their understanding using data analysis algorithms. The analysis results are output as evaluation data indicating the understanding and characteristics of the learners.

[0306] Step 3:

[0307] The server utilizes the generated AI model based on the evaluation data to generate an educational curriculum suitable for the learners. In the educational curriculum generation process, a curriculum considering the weaknesses and strengths of each learner is constructed. This output educational curriculum is used in the next step.

[0308] Step 4:

[0309] The terminal presents the educational curriculum received from the server via the providing device to the learners. When the learners access the educational curriculum in a local environment, offline learning is possible by using the content pre - stored in the terminal.

[0310] Step 5:

[0311] The learner, who is the user, can input natural - language questions into the terminal. The input data is sent to the response device and automatically analyzed through natural - language processing. An appropriate answer generated based on the analysis results is output and presented to the user's terminal.

[0312] Step 6:

[0313] The home support device physically interacts with the learner and monitors the learner's actions using sensors and cameras. It supports real - time interactive learning and provides visual explanations if necessary. Through this process, the learner can more intuitively understand the educational content.

[0314] 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.

[0315] This invention relates to a system that provides learners with an individualized educational experience, incorporating an emotion engine to recognize the learner's emotional state and dynamically adjusting the learning curriculum and educational content based on that state. This system monitors the learner's emotions in real time through the emotion engine and measures changes in stress and motivation.

[0316] The server receives learner learning data and comprehensively analyzes it, not only evaluating learning progress and comprehension through analysis tools, but also including emotional data provided by the emotion engine. This allows the curriculum generation tool to generate a customized curriculum based on the learner's emotional state. For example, if the emotion engine detects stress in the learner, the server can suggest relaxing learning content or a slower-paced curriculum to help them cope with that stress.

[0317] The device is responsible for providing learners with curriculum and learning content transmitted from the server, while simultaneously collecting emotional data. During the learning process, users engage with interactive content and adjust their learning experience in response to questions suggested by the device.

[0318] As a concrete example, suppose user D begins to feel stressed while trying to solve a difficult math problem. The emotion engine detects changes in user D's facial expressions and tone of voice through the camera and voice input, recognizing signs of stress. The server receives this information and supports user D's motivation to learn by including relaxing visual content and meditative music in the newly generated curriculum. As a result, user D can continue learning while reducing stress.

[0319] In this way, the integration of the emotion engine and the learning management system creates a flexible and responsive learning environment that responds to the individual emotional state of each learner.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] When a user begins learning, the device collects emotional data through its camera and microphone along with the learning data, and transmits this data to the server in real time.

[0323] Step 2:

[0324] The server processes the received learning data and sentiment data through an analysis device. In addition to evaluating learning progress and comprehension, the analysis device performs a sentiment evaluation using an emotion engine.

[0325] Step 3:

[0326] The emotion engine analyzes the user's emotional state and detects changes in stress and motivation. Based on these results, it assesses the degree to which stress reduction is needed.

[0327] Step 4:

[0328] Based on the analysis results, the server generates a curriculum tailored to the user's emotional state using a curriculum generation system. For example, if the user is experiencing high stress, the curriculum will incorporate slower-paced lessons and content designed to promote relaxation.

[0329] Step 5:

[0330] The server sends the generated curriculum to the terminal, which then presents it to the user. The terminal provides interactive feedback as needed.

[0331] Step 6:

[0332] As users progress through the learning process according to the provided curriculum, if questions arise, they can enter additional questions or requests via their device to receive support tailored to their emotional state.

[0333] Step 7:

[0334] The server receives questions from users and generates appropriate answers using question-answering mechanisms. Sentimental data is taken into consideration, and answers including mental support are generated as needed.

[0335] Step 8:

[0336] The answers are sent to the device, which then presents them to the user. Based on these answers, the user can deepen their understanding and revise their learning.

[0337] Step 9:

[0338] After a learning session ends, the device sends the latest learning data and emotional change history to the server. The server receives this data and uses it to optimize future curricula and emotional support.

[0339] (Example 2)

[0340] 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".

[0341] In today's educational environment, it is difficult for learners to receive an educational experience optimized based on their individual emotional state and learning progress. However, a uniform curriculum for each learner can lead to decreased learning efficiency and a decline in motivation. Therefore, there is a need to develop a system that can provide individualized curricula that take into account the learner's emotions and progress.

[0342] 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.

[0343] In this invention, the server includes means for receiving learner learning data and emotional data, analyzing the data to evaluate learning progress, comprehension, and emotional state; means for generating a customized curriculum for each learner that takes into account stress reduction and improved motivation to learn, based on the evaluation obtained by the analysis means; and means for providing the generated curriculum to the terminal used by the learner and simultaneously collecting emotional data in real time. This makes it possible to provide a dynamic and adaptive learning environment that is tailored to the individual circumstances of each learner.

[0344] "Learning data" refers to information about the learning activities that learners engage in on a daily basis, including indicators that show progress and level of understanding.

[0345] "Emotional data" refers to information that reflects the learner's mental state, and is derived from data such as facial expressions, voice, and behavioral patterns.

[0346] "Analysis means" refers to a technical method that processes collected learning data and sentiment data to evaluate the learner's progress, understanding, and emotional state.

[0347] A "curriculum generation method" is a technical method that uses evaluation results obtained through analysis to create a learning plan optimized for each learner.

[0348] "Delivery means" refers to the technical infrastructure for transmitting the generated curriculum and related learning content to the learner's device, enabling the learner to access it appropriately.

[0349] "Natural language processing" is a technology that analyzes learner input in a way that a machine can understand and generates an appropriate response.

[0350] "Offline mode" refers to a system configuration that allows learning content and functions to be provided even in situations with an unstable network connection, and where data is pre-stored on the device.

[0351] "Storage means" refers to technical components for pre-storing necessary learning materials and data within a device.

[0352] This invention is an educational system designed to personalize learners, combining an emotional engine with learning management. The program has the function of providing an adaptive curriculum based on collected data.

[0353] The server receives learning data and emotional data sent from learners. Emotional data is collected using facial recognition software and voice analysis tools that utilize the device's camera and microphone. The server analyzes this data and uses AI algorithms to evaluate learning progress, comprehension, and emotional state.

[0354] Based on this information, the server uses a generative AI model to create a customized curriculum that takes stress reduction and learning motivation into consideration. For example, if a user faces a difficult task and feels stressed, the server can provide relaxing content or a slower learning schedule.

[0355] The terminal presents the provided curriculum to the learner and collects learner feedback and new emotional data. This two-way data exchange allows the server to readjust the curriculum in real time and create an optimal learning environment tailored to the learner's situation.

[0356] For example, when a user is working on an advanced math problem, if the system detects the user's stress level through camera and voice input, it will recommend a new learning path accordingly. An example of the prompt in this case would be: "This system detects the user's stress level and generates a curriculum that suggests relaxing learning content. How does this system monitor the learner's emotional state and provide a personalized curriculum?"

[0357] In this way, a learning management system incorporating an emotion engine enables a flexible educational experience tailored to the learner's needs.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The device uses a camera and microphone to monitor the learner's learning progress and emotional state. Specifically, the device analyzes the user's facial expressions using facial recognition software and records the tone and speed of their voice using a speech recognition tool. This collects learning data and emotional data, which are then sent to a server as input and output.

[0361] Step 2:

[0362] The server analyzes the received learning data and emotional data. Specifically, it inputs the collected data into an AI algorithm to evaluate learning progress, comprehension, and emotional state. This process evaluates the learner's stress level and motivation level, and generates analysis results, which serve as both input and output.

[0363] Step 3:

[0364] The server uses a generative AI model to create a customized curriculum based on the analysis results. Specifically, this model configures appropriate learning content and resources based on each learner's evaluation and generates a new curriculum. The goal is to output a learning plan optimized for each learner.

[0365] Step 4:

[0366] The server sends the generated curriculum to the terminal. The terminal then begins displaying the received content to the user. Specifically, the terminal displays the provided curriculum on its screen and plays visual and auditory learning content. This provides the user with the information they need to progress in their learning.

[0367] Step 5:

[0368] Users progress through their learning based on the provided curriculum. As users progress, the device continuously collects data in real time by providing new questions and feedback. Specifically, when users provide feedback through interactive content, the data is updated based on the inquiry. This feedback is sent to the server and input as adjustments for the next curriculum.

[0369] (Application Example 2)

[0370] 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."

[0371] In recent years, there has been a growing demand for individualized education, making it crucial to provide curricula tailored to the individual needs and emotional states of each learner. However, conventional educational management systems have struggled to recognize learners' emotional states in real time and dynamically adjust learning content accordingly. This has resulted in challenges in reducing learner motivation and stress, and in providing an effective learning environment.

[0372] 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.

[0373] In this invention, the server includes an evaluation device that receives learner learning data and analyzes the data to evaluate learning progress and comprehension; a curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the evaluation device; a distribution device that provides the generated curriculum to the terminal used by the learner; an emotion analysis device that recognizes the learner's emotional state in real time; and a curriculum adjustment device that has the function of adjusting the learning content and pace to reduce stress based on the data from the emotion analysis device. This makes it possible to provide a flexible and adaptive learning experience that is tailored to the learner's individualized emotional state.

[0374] An "evaluation device" is a device that receives learner's learning data, analyzes that data, and evaluates their learning progress and level of understanding.

[0375] A "curriculum generation device" is a device that generates a customized curriculum for each learner based on evaluations obtained by an evaluation device.

[0376] A "distribution device" is a device that provides the generated curriculum to the terminals used by learners.

[0377] An "emotion analysis device" is a device that recognizes a learner's emotional state in real time.

[0378] A "curriculum adjustment device" is a device that adjusts learning content and pace to reduce stress based on data from an emotion analysis device.

[0379] The system for implementing this invention has a configuration that incorporates an evaluation device, a curriculum generation device, a distribution device, an emotion analysis device, and a curriculum adjustment device.

[0380] The server first receives learning data from learners using an evaluation device and performs analysis. This analysis evaluates the learners' learning progress and level of understanding. Next, based on the evaluation results, a curriculum generation device creates an individualized curriculum for each learner. Once generated, this curriculum is provided to the learner's terminal by a distribution device.

[0381] Furthermore, the terminal is equipped with an emotion analysis device that uses a camera and microphone to monitor changes in the learner's facial expressions and voice in real time. The emotion analysis device uses this data to determine the learner's emotional state. For example, if a learner is feeling stressed, the curriculum adjustment device can receive this data and issue instructions to adjust the learning content and pace.

[0382] As a concrete example, the system's program is written using Python. The camera module uses the OpenCV library to perform real-time facial expression analysis. In addition, Python's NLTK library is used for natural language processing to generate responses to learners' questions. When stress is detected, AWS Lambda is used to process instructions for curriculum adjustment in the cloud and notify the terminal of the results.

[0383] Consider a scenario where a user is using the system, for example, a primary school student tackling a complex math problem. If the emotion analysis device detects that the user is feeling confused, the curriculum adjustment device recommends relaxation content best suited to that state. In this situation, it is possible to send a prompt message to the generative AI model such as, "Please select relaxation content suitable for a student who is having trouble concentrating on the math problem. The student is confused and needs a short break," thereby providing appropriate educational content.

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server receives learning data from learners. The input data concerns the subjects the learners are studying and their progress. By analyzing this data, the server evaluates the learners' progress and understanding. Specifically, it performs statistical processing on the data and calculates a score for each item.

[0387] Step 2:

[0388] The server uses an evaluation device to assess the learner's level of understanding based on the analysis results, and then uses a curriculum generation device to create an individualized curriculum. The output is a new curriculum proposal, which determines the learning content best suited to the user's current learning level. Specifically, it uses an AI algorithm to propose personalized educational content.

[0389] Step 3:

[0390] The server transmits the curriculum to user terminals via a distribution device. The input is the generated curriculum draft, and the output is the learning content displayed on the user terminal. In this step, data is transmitted over the network to ensure that the educational content is delivered to learners on time.

[0391] Step 4:

[0392] The device uses an emotion analysis system to monitor the learner's emotional state in real time. Input is facial and audio data acquired from a camera and microphone, and output is the recognized emotional state of the learner. The system uses the OpenCV library to perform facial recognition and identify individual emotions.

[0393] Step 5:

[0394] The server receives emotional data from the emotion analysis device and dynamically adjusts the learning content and pace using the curriculum adjustment device. The input is emotional data, and the output is the adjusted educational curriculum. Specifically, if an indicator of stress is high, the curriculum is modified to reduce the learner's burden, such as by adding relaxation content.

[0395] Step 6:

[0396] When a user engages with content, a generative AI model is used to generate prompts and provide appropriate learning support. The input is information about the learning content and emotional state, and the output is a prompt generated based on that information. For example, it might generate a prompt such as, "Based on your current level of understanding, please suggest the next problem to solve," and then take specific actions to support learning.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] [Third Embodiment]

[0401] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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".

[0413] This invention is a system that provides learners with an individualized educational experience. This system collects learner learning data and generates an appropriate learning curriculum based on that data. Furthermore, it implements an offline mode to ensure that education can continue even in areas with unstable internet connections.

[0414] The server receives learning data sent from learners via their devices. This data includes information about the learner's progress, past response history, and level of understanding. The received data is processed by an analysis system to evaluate the learner's learning status. Based on the evaluation results, the server generates a curriculum tailored to each individual learner. This curriculum aims to strengthen the learner's weaknesses and deepen their existing knowledge.

[0415] The terminal is responsible for presenting the curriculum received from the server to the learner. The terminal also allows learning to continue without relying on a network connection by using pre-downloaded learning content even in offline mode. Therefore, the terminal stores the necessary learning data locally in advance.

[0416] The learner, as the user, progresses through the learning process according to the curriculum presented via their device. If any questions or uncertainties arise during the learning process, the user can input questions in natural language. The server receives these questions and immediately generates answers using a question-answering mechanism. The generated answers are sent back to the user's device, and the user can refer to them to deepen their understanding.

[0417] As a concrete example, suppose User C is learning about "photosynthesis" in a science unit. The server incorporates relevant simulations and interactive teaching materials into the curriculum based on data related to "the relationship between light wavelengths and colors," which User C previously found difficult. User C can access these materials using their device and virtually check the experimental results. This allows User C to effectively acquire knowledge.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] Users log into the system and input information about their educational needs, such as learning topics and subjects they struggle with. Once they begin learning, progress information and answer data related to the learning content are saved on their device.

[0421] Step 2:

[0422] The terminal collects data obtained from the user and prepares it for transmission to the server. This data is sent to the server when the network connection is stable.

[0423] Step 3:

[0424] The server receives learning data sent from the terminal and uses analysis tools to analyze the user's learning progress and understanding. Here, statistical methods and machine learning techniques are used to identify areas of weakness.

[0425] Step 4:

[0426] Based on the analysis results, the server uses a curriculum generation mechanism to create a learning curriculum optimized for each individual user. This process generates a curriculum that reflects the user's areas of difficulty and interests.

[0427] Step 5:

[0428] The server sends the generated curriculum to the terminal, which then presents the curriculum to the user. The presented curriculum may include interactive learning materials and practice exercises.

[0429] Step 6:

[0430] Questions that arise during the user's learning process are entered into the device and sent to the server. Users can ask questions using natural language.

[0431] Step 7:

[0432] The server analyzes the received question using natural language processing and generates an appropriate answer using a question-answering mechanism. This answer is multilingual and translated into the user's selected language.

[0433] Step 8:

[0434] The generated answers are sent from the server to the terminal, which immediately presents them to the user. This allows the user to resolve any questions that arose during the learning process.

[0435] Step 9:

[0436] As the user progresses through their learning and completes a set course or reaches a certain level of progress, the device sends the latest progress data back to the server, which then generates a new curriculum. By repeating this cycle, the system provides users with continuous, personalized learning opportunities.

[0437] (Example 1)

[0438] 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."

[0439] In today's educational environment, there is a demand for providing personalized learning plans tailored to each individual student. However, accurately assessing students' progress and understanding, and then providing individualized learning materials based on that assessment, is difficult with traditional systems. To solve this problem, it is necessary to utilize the latest technologies to provide learning experiences that are appropriate for each student.

[0440] 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.

[0441] In this invention, the server includes evaluation means for receiving learner's educational data and analyzing the data to evaluate the progress and level of understanding of the education; plan generation means for generating an individualized educational plan for each learner based on the evaluation obtained by the evaluation means; provision means for providing the generated educational plan to the device used by the learner; and storage means for implementing an offline mode and pre-saving educational content to the device. This enables an individually optimized educational experience for learners, regardless of network conditions.

[0442] "Educational data" refers to information about learners' progress, past response history, and level of understanding. This information is analyzed to help generate personalized educational plans.

[0443] "Evaluation means" refers to technical functions that analyze received educational data to evaluate learners' educational progress and level of understanding.

[0444] "Plan generation means" refers to a function for generating an optimized educational plan for each learner based on educational data.

[0445] "Means of provision" refers to the function that provides the educational plan generated by the server to the device used by the learner, enabling the learner to proceed with their studies accordingly.

[0446] "Storage means" refers to a technical function for saving educational content to a device in advance so that learning can continue even in situations where the network connection is unstable.

[0447] A "question answering system" refers to a function that receives questions from learners in natural language, generates appropriate answers, and presents them.

[0448] A "generative artificial intelligence model" refers to a machine learning model or artificial intelligence technology used to generate appropriate answers to questions from learners.

[0449] "Optimization means" refers to technical functions that incorporate interactive educational materials and simulations into the structure of educational plans based on previous learning results and learners' weaknesses.

[0450] This invention is a system that provides learners with optimized educational plans. The system consists of a server, terminals, and users.

[0451] The server primarily plays a central role in receiving and analyzing learner education data. It uses software libraries such as Python and Scikit-learn to assess learners' progress and understanding. Machine learning models are utilized in data analysis to identify learners' strengths and areas for improvement.

[0452] The device displays the learning plan provided by the server to the learner. The device also has the ability to pre-save necessary educational data to local storage so that learners can access the educational content even in offline environments. A web browser and JavaScript are used for saving and displaying the data.

[0453] The user, as the learner, can progress through the learning process according to the educational plan provided via the device. If they encounter a difficult point during learning, they can input a question in natural language. For example, they might input a prompt such as, "Please explain the roles of light wavelength and color in photosynthesis."

[0454] The server uses a generative AI model to generate appropriate responses to such prompts. The generated responses are immediately sent back to the terminal, allowing the user to review them and deepen their understanding. This system enables learners to enjoy a learning experience optimized according to their individual progress and level of understanding.

[0455] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0456] Step 1:

[0457] The server receives educational data sent from the learner's device. The input is expected to be in JSON format, containing information about the learner's progress, past response history, and level of understanding. The server then runs a Python script to analyze this data and save it to a database. This process efficiently manages the learner's educational history.

[0458] Step 2:

[0459] The server uses a machine learning model to analyze the received educational data. The input is the stored educational data, which is used to evaluate the learner's progress and strengths and weaknesses. The output is the evaluation result, which includes the educational strengths and weaknesses identified for each learner. Specifically, it uses libraries such as Scikit-learn to process the data with a particular algorithm and generate evaluation criteria.

[0460] Step 3:

[0461] The server generates an optimal learning plan for the learner based on the analyzed evaluation results. The input is the evaluation results, and the output is provided as a curriculum tailored to the learner. A generative AI model is used to dynamically construct learning content and generate it in HTML format. This creates a personalized learning plan that focuses on what the learner needs.

[0462] Step 4:

[0463] The terminal receives the educational plan sent from the server and displays it to the user. The input is the educational plan from the server, and the output is the educational content displayed on the user's screen. The terminal temporarily stores the necessary content in local storage and dynamically displays it on the web browser using JavaScript. This allows the user to continue learning regardless of network availability.

[0464] Step 5:

[0465] Users input questions that arise during the learning process into the terminal. They can input natural language questions as prompts, such as "Explain the roles of light wavelength and color in photosynthesis." The input is this prompt, and the output is the answer returned by the server.

[0466] Step 6:

[0467] The server analyzes questions received from the user and generates appropriate answers using a generative AI model. The input is the user's prompt, and the output is the answer in natural language. The generated answer is immediately sent back to the terminal, and the user can use that information as a reference for learning.

[0468] (Application Example 1)

[0469] 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."

[0470] In today's educational environment, providing customized learning experiences tailored to each individual learner is crucial. However, traditional education systems struggle to deliver individually optimized curricula in real time, and consistent educational support may be unavailable depending on location and communication environment. Furthermore, home learning support, in particular, lacks physical and interactive elements, making it difficult to maintain learners' interest. An effective system is needed to address these challenges and support learners in actively engaging with their studies.

[0471] 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.

[0472] In this invention, the server includes a processing device that receives learner learning data and analyzes the data to evaluate learning progress and comprehension; a course generation device that generates a customized curriculum for each learner based on the evaluation obtained by the processing device; and a provisioning device that provides the generated curriculum to a medium used by the learner. This makes it possible to provide optimized educational content for each individual learner and to continue learning consistently regardless of location or communication environment. Furthermore, by using a response device to resolve learners' questions and providing physical educational experiences through home-use assistive devices, it is possible to increase learners' interest and improve the effectiveness of learning.

[0473] A "learner" is an individual who seeks to acquire knowledge and skills through the use of an educational system.

[0474] "Learning data" refers to information about the learner's progress, level of understanding, past learning history, and answer history.

[0475] A "processing device" is a device that analyzes received learning data and has the function of evaluating the learner's learning progress and level of understanding.

[0476] A "curriculum" refers to learning content and plans that are customized based on the evaluation results of learners.

[0477] A "curriculum generation device" is a device that generates individualized educational curricula based on the evaluation results of each learner.

[0478] A "distribution device" is a medium that plays the role of presenting the generated curriculum to learners.

[0479] A "response device" is a device that analyzes questions entered by learners using natural language processing, generates appropriate answers, and presents them.

[0480] "Home-use assistive devices" are devices that provide an intuitive educational experience through physical contact with the learner and explain learning content using visual and physical representations.

[0481] "Asynchronous mode" refers to a state in which the system operates based on data that has been previously stored locally, regardless of network conditions.

[0482] "Cameras and sensors" are devices that detect learners' movements, analyze that data, and support interactive educational activities.

[0483] To implement this invention, a system program is needed to provide learners with an individualized educational experience. This system functions through the combination of multiple elements.

[0484] The server receives learning data transmitted through the learner's medium, which includes information about the learner's progress, past response history, and level of understanding. This data is analyzed by the processing unit, which evaluates the learner's learning status. Based on this, the processing unit generates an optimal curriculum for the learner. The generated curriculum is then presented to the learner's medium by the providing device.

[0485] The medium not only displays the generated curriculum to learners but also includes a recording device that allows learning to continue even in offline environments and can operate in asynchronous mode. Even in areas with unstable communication environments, it is possible to utilize educational content previously stored on the medium.

[0486] Furthermore, the response device analyzes natural language questions entered by learners into the medium, instantly generates appropriate answers, and sends them back to the medium, thereby deepening the learner's understanding. Also included are home-use assistive devices that physically interact with learners and intuitively present educational content through visual and physical representations.

[0487] This system incorporates cameras and sensors to capture learners' movements and support real-time, interactive educational activities. Furthermore, the use of generative AI models ensures that the curriculum and response content are always up-to-date.

[0488] For example, if a learner asks, "Tell me about photosynthesis," the home-use assistive device visually reproduces the process of photosynthesis using a plant model, and the response device provides relevant information. This allows learners to deepen their knowledge through hands-on experience.

[0489] Example prompt: "Tell me about an application where you can ask a robot questions about photosynthesis, and it will explain them in detail using real-time visuals."

[0490] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0491] Step 1:

[0492] The server receives learner data sent from the terminal. This data includes information about the learner's progress, past response history, and level of understanding. The received data is stored in a database.

[0493] Step 2:

[0494] The server analyzes the received learning data using a processing unit. Specifically, it uses data analysis algorithms to assess the learner's progress and level of understanding. The analysis results are output as evaluation data that shows the learner's level of understanding and characteristics.

[0495] Step 3:

[0496] The server utilizes a generation AI model based on evaluation data to generate a curriculum tailored to each learner. The curriculum generation process constructs a curriculum that takes into account each learner's strengths and weaknesses. This generated curriculum is then used in the next step.

[0497] Step 4:

[0498] The terminal presents the curriculum, received from the server via a distribution device, to the learner. If the learner accesses the curriculum in a local environment, offline learning is possible by using content pre-stored on the terminal.

[0499] Step 5:

[0500] The user (learner) can ask natural language questions entered into their device. The input data is sent to a response device and automatically analyzed through natural language processing. An appropriate answer generated based on the analysis results is output and displayed on the user's device.

[0501] Step 6:

[0502] Home-use assistive devices physically interact with learners and monitor their movements using sensors and cameras. They support real-time, interactive learning and provide visual explanations as needed. This process allows learners to understand educational content more intuitively.

[0503] 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.

[0504] This invention relates to a system that provides learners with an individualized educational experience, incorporating an emotion engine to recognize the learner's emotional state and dynamically adjusting the learning curriculum and educational content based on that state. This system monitors the learner's emotions in real time through the emotion engine and measures changes in stress and motivation.

[0505] The server receives learner learning data and comprehensively analyzes it, not only evaluating learning progress and comprehension through analysis tools, but also including emotional data provided by the emotion engine. This allows the curriculum generation tool to generate a customized curriculum based on the learner's emotional state. For example, if the emotion engine detects stress in the learner, the server can suggest relaxing learning content or a slower-paced curriculum to help them cope with that stress.

[0506] The device is responsible for providing learners with curriculum and learning content transmitted from the server, while simultaneously collecting emotional data. During the learning process, users engage with interactive content and adjust their learning experience in response to questions suggested by the device.

[0507] As a concrete example, suppose user D begins to feel stressed while trying to solve a difficult math problem. The emotion engine detects changes in user D's facial expressions and tone of voice through the camera and voice input, recognizing signs of stress. The server receives this information and supports user D's motivation to learn by including relaxing visual content and meditative music in the newly generated curriculum. As a result, user D can continue learning while reducing stress.

[0508] In this way, the integration of the emotion engine and the learning management system creates a flexible and responsive learning environment that responds to the individual emotional state of each learner.

[0509] The following describes the processing flow.

[0510] Step 1:

[0511] When a user begins learning, the device collects emotional data through its camera and microphone along with the learning data, and transmits this data to the server in real time.

[0512] Step 2:

[0513] The server processes the received learning data and sentiment data through an analysis device. In addition to evaluating learning progress and comprehension, the analysis device performs a sentiment evaluation using an emotion engine.

[0514] Step 3:

[0515] The emotion engine analyzes the user's emotional state and detects changes in stress and motivation. Based on these results, it assesses the degree to which stress reduction is needed.

[0516] Step 4:

[0517] Based on the analysis results, the server generates a curriculum tailored to the user's emotional state using a curriculum generation system. For example, if the user is experiencing high stress, the curriculum will incorporate slower-paced lessons and content designed to promote relaxation.

[0518] Step 5:

[0519] The server sends the generated curriculum to the terminal, which then presents it to the user. The terminal provides interactive feedback as needed.

[0520] Step 6:

[0521] As users progress through the learning process according to the provided curriculum, if questions arise, they can enter additional questions or requests via their device to receive support tailored to their emotional state.

[0522] Step 7:

[0523] The server receives questions from users and generates appropriate answers using question-answering mechanisms. Sentimental data is taken into consideration, and answers including mental support are generated as needed.

[0524] Step 8:

[0525] The answers are sent to the device, which then presents them to the user. Based on these answers, the user can deepen their understanding and revise their learning.

[0526] Step 9:

[0527] After a learning session ends, the device sends the latest learning data and emotional change history to the server. The server receives this data and uses it to optimize future curricula and emotional support.

[0528] (Example 2)

[0529] 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."

[0530] In today's educational environment, it is difficult for learners to receive an educational experience optimized based on their individual emotional state and learning progress. However, a uniform curriculum for each learner can lead to decreased learning efficiency and a decline in motivation. Therefore, there is a need to develop a system that can provide individualized curricula that take into account the learner's emotions and progress.

[0531] 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.

[0532] In this invention, the server includes means for receiving learner learning data and emotional data, analyzing the data to evaluate learning progress, comprehension, and emotional state; means for generating a customized curriculum for each learner that takes into account stress reduction and improved motivation to learn, based on the evaluation obtained by the analysis means; and means for providing the generated curriculum to the terminal used by the learner and simultaneously collecting emotional data in real time. This makes it possible to provide a dynamic and adaptive learning environment that is tailored to the individual circumstances of each learner.

[0533] "Learning data" refers to information about the learning activities that learners engage in on a daily basis, including indicators that show progress and level of understanding.

[0534] "Emotional data" refers to information that reflects the learner's mental state, and is derived from data such as facial expressions, voice, and behavioral patterns.

[0535] "Analysis means" refers to a technical method that processes collected learning data and sentiment data to evaluate the learner's progress, understanding, and emotional state.

[0536] A "curriculum generation method" is a technical method that uses evaluation results obtained through analysis to create a learning plan optimized for each learner.

[0537] "Delivery means" refers to the technical infrastructure for transmitting the generated curriculum and related learning content to the learner's device, enabling the learner to access it appropriately.

[0538] "Natural language processing" is a technology that analyzes learner input in a way that a machine can understand and generates an appropriate response.

[0539] "Offline mode" refers to a system configuration that allows learning content and functions to be provided even in situations with an unstable network connection, and where data is pre-stored on the device.

[0540] "Storage means" refers to technical components for pre-storing necessary learning materials and data within a device.

[0541] This invention is an educational system designed to personalize learners, combining an emotional engine with learning management. The program has the function of providing an adaptive curriculum based on collected data.

[0542] The server receives learning data and emotional data sent from learners. Emotional data is collected using facial recognition software and voice analysis tools that utilize the device's camera and microphone. The server analyzes this data and uses AI algorithms to evaluate learning progress, comprehension, and emotional state.

[0543] Based on this information, the server uses a generative AI model to create a customized curriculum that takes stress reduction and learning motivation into consideration. For example, if a user faces a difficult task and feels stressed, the server can provide relaxing content or a slower learning schedule.

[0544] The terminal presents the provided curriculum to the learner and collects learner feedback and new emotional data. This two-way data exchange allows the server to readjust the curriculum in real time and create an optimal learning environment tailored to the learner's situation.

[0545] For example, when a user is working on an advanced math problem, if the system detects the user's stress level through camera and voice input, it will recommend a new learning path accordingly. An example of the prompt in this case would be: "This system detects the user's stress level and generates a curriculum that suggests relaxing learning content. How does this system monitor the learner's emotional state and provide a personalized curriculum?"

[0546] In this way, a learning management system incorporating an emotion engine enables a flexible educational experience tailored to the learner's needs.

[0547] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0548] Step 1:

[0549] The device uses a camera and microphone to monitor the learner's learning progress and emotional state. Specifically, the device analyzes the user's facial expressions using facial recognition software and records the tone and speed of their voice using a speech recognition tool. This collects learning data and emotional data, which are then sent to a server as input and output.

[0550] Step 2:

[0551] The server analyzes the received learning data and emotional data. Specifically, it inputs the collected data into an AI algorithm to evaluate learning progress, comprehension, and emotional state. This process evaluates the learner's stress level and motivation level, and generates analysis results, which serve as both input and output.

[0552] Step 3:

[0553] The server uses a generative AI model to create a customized curriculum based on the analysis results. Specifically, this model configures appropriate learning content and resources based on each learner's evaluation and generates a new curriculum. The goal is to output a learning plan optimized for each learner.

[0554] Step 4:

[0555] The server sends the generated curriculum to the terminal. The terminal then begins displaying the received content to the user. Specifically, the terminal displays the provided curriculum on its screen and plays visual and auditory learning content. This provides the user with the information they need to progress in their learning.

[0556] Step 5:

[0557] Users progress through their learning based on the provided curriculum. As users progress, the device continuously collects data in real time by providing new questions and feedback. Specifically, when users provide feedback through interactive content, the data is updated based on the inquiry. This feedback is sent to the server and input as adjustments for the next curriculum.

[0558] (Application Example 2)

[0559] 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."

[0560] In recent years, there has been a growing demand for individualized education, making it crucial to provide curricula tailored to the individual needs and emotional states of each learner. However, conventional educational management systems have struggled to recognize learners' emotional states in real time and dynamically adjust learning content accordingly. This has resulted in challenges in reducing learner motivation and stress, and in providing an effective learning environment.

[0561] 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.

[0562] In this invention, the server includes an evaluation device that receives learner learning data and analyzes the data to evaluate learning progress and comprehension; a curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the evaluation device; a distribution device that provides the generated curriculum to the terminal used by the learner; an emotion analysis device that recognizes the learner's emotional state in real time; and a curriculum adjustment device that has the function of adjusting the learning content and pace to reduce stress based on the data from the emotion analysis device. This makes it possible to provide a flexible and adaptive learning experience that is tailored to the learner's individualized emotional state.

[0563] An "evaluation device" is a device that receives learner's learning data, analyzes that data, and evaluates their learning progress and level of understanding.

[0564] A "curriculum generation device" is a device that generates a customized curriculum for each learner based on evaluations obtained by an evaluation device.

[0565] A "distribution device" is a device that provides the generated curriculum to the terminals used by learners.

[0566] An "emotion analysis device" is a device that recognizes a learner's emotional state in real time.

[0567] A "curriculum adjustment device" is a device that adjusts learning content and pace to reduce stress based on data from an emotion analysis device.

[0568] The system for implementing this invention has a configuration that incorporates an evaluation device, a curriculum generation device, a distribution device, an emotion analysis device, and a curriculum adjustment device.

[0569] The server first receives learning data from learners using an evaluation device and performs analysis. This analysis evaluates the learners' learning progress and level of understanding. Next, based on the evaluation results, a curriculum generation device creates an individualized curriculum for each learner. Once generated, this curriculum is provided to the learner's terminal by a distribution device.

[0570] Furthermore, the terminal is equipped with an emotion analysis device that uses a camera and microphone to monitor changes in the learner's facial expressions and voice in real time. The emotion analysis device uses this data to determine the learner's emotional state. For example, if a learner is feeling stressed, the curriculum adjustment device can receive this data and issue instructions to adjust the learning content and pace.

[0571] As a concrete example, the system's program is written using Python. The camera module uses the OpenCV library to perform real-time facial expression analysis. In addition, Python's NLTK library is used for natural language processing to generate responses to learners' questions. When stress is detected, AWS Lambda is used to process instructions for curriculum adjustment in the cloud and notify the terminal of the results.

[0572] Consider a scenario where a user is using the system, for example, a primary school student tackling a complex math problem. If the emotion analysis device detects that the user is feeling confused, the curriculum adjustment device recommends relaxation content best suited to that state. In this situation, it is possible to send a prompt message to the generative AI model such as, "Please select relaxation content suitable for a student who is having trouble concentrating on the math problem. The student is confused and needs a short break," thereby providing appropriate educational content.

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The server receives learning data from learners. The input data concerns the subjects the learners are studying and their progress. By analyzing this data, the server evaluates the learners' progress and understanding. Specifically, it performs statistical processing on the data and calculates a score for each item.

[0576] Step 2:

[0577] The server uses an evaluation device to assess the learner's level of understanding based on the analysis results, and then uses a curriculum generation device to create an individualized curriculum. The output is a new curriculum proposal, which determines the learning content best suited to the user's current learning level. Specifically, it uses an AI algorithm to propose personalized educational content.

[0578] Step 3:

[0579] The server transmits the curriculum to user terminals via a distribution device. The input is the generated curriculum draft, and the output is the learning content displayed on the user terminal. In this step, data is transmitted over the network to ensure that the educational content is delivered to learners on time.

[0580] Step 4:

[0581] The device uses an emotion analysis system to monitor the learner's emotional state in real time. Input is facial and audio data acquired from a camera and microphone, and output is the recognized emotional state of the learner. The system uses the OpenCV library to perform facial recognition and identify individual emotions.

[0582] Step 5:

[0583] The server receives emotional data from the emotion analysis device and dynamically adjusts the learning content and pace using the curriculum adjustment device. The input is emotional data, and the output is the adjusted educational curriculum. Specifically, if an indicator of stress is high, the curriculum is modified to reduce the learner's burden, such as by adding relaxation content.

[0584] Step 6:

[0585] When a user engages with content, a generative AI model is used to generate prompts and provide appropriate learning support. The input is information about the learning content and emotional state, and the output is a prompt generated based on that information. For example, it might generate a prompt such as, "Based on your current level of understanding, please suggest the next problem to solve," and then take specific actions to support learning.

[0586] 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.

[0587] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0588] 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.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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".

[0603] This invention is a system that provides learners with an individualized educational experience. This system collects learner learning data and generates an appropriate learning curriculum based on that data. Furthermore, it implements an offline mode to ensure that education can continue even in areas with unstable internet connections.

[0604] The server receives learning data sent from learners via their devices. This data includes information about the learner's progress, past response history, and level of understanding. The received data is processed by an analysis system to evaluate the learner's learning status. Based on the evaluation results, the server generates a curriculum tailored to each individual learner. This curriculum aims to strengthen the learner's weaknesses and deepen their existing knowledge.

[0605] The terminal is responsible for presenting the curriculum received from the server to the learner. The terminal also allows learning to continue without relying on a network connection by using pre-downloaded learning content even in offline mode. Therefore, the terminal stores the necessary learning data locally in advance.

[0606] The learner, as the user, progresses through the learning process according to the curriculum presented via their device. If any questions or uncertainties arise during the learning process, the user can input questions in natural language. The server receives these questions and immediately generates answers using a question-answering mechanism. The generated answers are sent back to the user's device, and the user can refer to them to deepen their understanding.

[0607] As a concrete example, suppose User C is learning about "photosynthesis" in a science unit. The server incorporates relevant simulations and interactive teaching materials into the curriculum based on data related to "the relationship between light wavelengths and colors," which User C previously found difficult. User C can access these materials using their device and virtually check the experimental results. This allows User C to effectively acquire knowledge.

[0608] The following describes the processing flow.

[0609] Step 1:

[0610] Users log into the system and input information about their educational needs, such as learning topics and subjects they struggle with. Once they begin learning, progress information and answer data related to the learning content are saved on their device.

[0611] Step 2:

[0612] The terminal collects data obtained from the user and prepares it for transmission to the server. This data is sent to the server when the network connection is stable.

[0613] Step 3:

[0614] The server receives learning data sent from the terminal and uses analysis tools to analyze the user's learning progress and understanding. Here, statistical methods and machine learning techniques are used to identify areas of weakness.

[0615] Step 4:

[0616] Based on the analysis results, the server uses a curriculum generation mechanism to create a learning curriculum optimized for each individual user. This process generates a curriculum that reflects the user's areas of difficulty and interests.

[0617] Step 5:

[0618] The server sends the generated curriculum to the terminal, which then presents the curriculum to the user. The presented curriculum may include interactive learning materials and practice exercises.

[0619] Step 6:

[0620] Questions that arise during the user's learning process are entered into the device and sent to the server. Users can ask questions using natural language.

[0621] Step 7:

[0622] The server analyzes the received question using natural language processing and generates an appropriate answer using a question-answering mechanism. This answer is multilingual and translated into the user's selected language.

[0623] Step 8:

[0624] The generated answers are sent from the server to the terminal, which immediately presents them to the user. This allows the user to resolve any questions that arose during the learning process.

[0625] Step 9:

[0626] As the user progresses through their learning and completes a set course or reaches a certain level of progress, the device sends the latest progress data back to the server, which then generates a new curriculum. By repeating this cycle, the system provides users with continuous, personalized learning opportunities.

[0627] (Example 1)

[0628] 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".

[0629] In today's educational environment, there is a demand for providing personalized learning plans tailored to each individual student. However, accurately assessing students' progress and understanding, and then providing individualized learning materials based on that assessment, is difficult with traditional systems. To solve this problem, it is necessary to utilize the latest technologies to provide learning experiences that are appropriate for each student.

[0630] 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.

[0631] In this invention, the server includes evaluation means for receiving learner's educational data and analyzing the data to evaluate the progress and level of understanding of the education; plan generation means for generating an individualized educational plan for each learner based on the evaluation obtained by the evaluation means; provision means for providing the generated educational plan to the device used by the learner; and storage means for implementing an offline mode and pre-saving educational content to the device. This enables an individually optimized educational experience for learners, regardless of network conditions.

[0632] "Educational data" refers to information about learners' progress, past response history, and level of understanding. This information is analyzed to help generate personalized educational plans.

[0633] "Evaluation means" refers to technical functions that analyze received educational data to evaluate learners' educational progress and level of understanding.

[0634] "Plan generation means" refers to a function for generating an optimized educational plan for each learner based on educational data.

[0635] "Means of provision" refers to the function that provides the educational plan generated by the server to the device used by the learner, enabling the learner to proceed with their studies accordingly.

[0636] "Storage means" refers to a technical function for saving educational content to a device in advance so that learning can continue even in situations where the network connection is unstable.

[0637] A "question answering system" refers to a function that receives questions from learners in natural language, generates appropriate answers, and presents them.

[0638] A "generative artificial intelligence model" refers to a machine learning model or artificial intelligence technology used to generate appropriate answers to questions from learners.

[0639] "Optimization means" refers to technical functions that incorporate interactive educational materials and simulations into the structure of educational plans based on previous learning results and learners' weaknesses.

[0640] This invention is a system that provides learners with optimized educational plans. The system consists of a server, terminals, and users.

[0641] The server primarily plays a central role in receiving and analyzing learner education data. It uses software libraries such as Python and Scikit-learn to assess learners' progress and understanding. Machine learning models are utilized in data analysis to identify learners' strengths and areas for improvement.

[0642] The device displays the learning plan provided by the server to the learner. The device also has the ability to pre-save necessary educational data to local storage so that learners can access the educational content even in offline environments. A web browser and JavaScript are used for saving and displaying the data.

[0643] The user, as the learner, can progress through the learning process according to the educational plan provided via the device. If they encounter a difficult point during learning, they can input a question in natural language. For example, they might input a prompt such as, "Please explain the roles of light wavelength and color in photosynthesis."

[0644] The server uses a generative AI model to generate appropriate responses to such prompts. The generated responses are immediately sent back to the terminal, allowing the user to review them and deepen their understanding. This system enables learners to enjoy a learning experience optimized according to their individual progress and level of understanding.

[0645] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0646] Step 1:

[0647] The server receives educational data sent from the learner's device. The input is expected to be in JSON format, containing information about the learner's progress, past response history, and level of understanding. The server then runs a Python script to analyze this data and save it to a database. This process efficiently manages the learner's educational history.

[0648] Step 2:

[0649] The server uses a machine learning model to analyze the received educational data. The input is the stored educational data, which is used to evaluate the learner's progress and strengths and weaknesses. The output is the evaluation result, which includes the educational strengths and weaknesses identified for each learner. Specifically, it uses libraries such as Scikit-learn to process the data with a particular algorithm and generate evaluation criteria.

[0650] Step 3:

[0651] The server generates an optimal learning plan for the learner based on the analyzed evaluation results. The input is the evaluation results, and the output is provided as a curriculum tailored to the learner. A generative AI model is used to dynamically construct learning content and generate it in HTML format. This creates a personalized learning plan that focuses on what the learner needs.

[0652] Step 4:

[0653] The terminal receives the educational plan sent from the server and displays it to the user. The input is the educational plan from the server, and the output is the educational content displayed on the user's screen. The terminal temporarily stores the necessary content in local storage and dynamically displays it on the web browser using JavaScript. This allows the user to continue learning regardless of network availability.

[0654] Step 5:

[0655] Users input questions that arise during the learning process into the terminal. They can input natural language questions as prompts, such as "Explain the roles of light wavelength and color in photosynthesis." The input is this prompt, and the output is the answer returned by the server.

[0656] Step 6:

[0657] The server analyzes questions received from the user and generates appropriate answers using a generative AI model. The input is the user's prompt, and the output is the answer in natural language. The generated answer is immediately sent back to the terminal, and the user can use that information as a reference for learning.

[0658] (Application Example 1)

[0659] 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".

[0660] In today's educational environment, providing customized learning experiences tailored to each individual learner is crucial. However, traditional education systems struggle to deliver individually optimized curricula in real time, and consistent educational support may be unavailable depending on location and communication environment. Furthermore, home learning support, in particular, lacks physical and interactive elements, making it difficult to maintain learners' interest. An effective system is needed to address these challenges and support learners in actively engaging with their studies.

[0661] 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.

[0662] In this invention, the server includes a processing device that receives learner learning data and analyzes the data to evaluate learning progress and comprehension; a course generation device that generates a customized curriculum for each learner based on the evaluation obtained by the processing device; and a provisioning device that provides the generated curriculum to a medium used by the learner. This makes it possible to provide optimized educational content for each individual learner and to continue learning consistently regardless of location or communication environment. Furthermore, by using a response device to resolve learners' questions and providing physical educational experiences through home-use assistive devices, it is possible to increase learners' interest and improve the effectiveness of learning.

[0663] A "learner" is an individual who seeks to acquire knowledge and skills through the use of an educational system.

[0664] "Learning data" refers to information about the learner's progress, level of understanding, past learning history, and answer history.

[0665] A "processing device" is a device that analyzes received learning data and has the function of evaluating the learner's learning progress and level of understanding.

[0666] A "curriculum" refers to learning content and plans that are customized based on the evaluation results of learners.

[0667] A "curriculum generation device" is a device that generates individualized educational curricula based on the evaluation results of each learner.

[0668] A "distribution device" is a medium that plays the role of presenting the generated curriculum to learners.

[0669] A "response device" is a device that analyzes questions entered by learners using natural language processing, generates appropriate answers, and presents them.

[0670] "Home-use assistive devices" are devices that provide an intuitive educational experience through physical contact with the learner and explain learning content using visual and physical representations.

[0671] "Asynchronous mode" refers to a state in which the system operates based on data that has been previously stored locally, regardless of network conditions.

[0672] "Cameras and sensors" are devices that detect learners' movements, analyze that data, and support interactive educational activities.

[0673] To implement this invention, a system program is needed to provide learners with an individualized educational experience. This system functions through the combination of multiple elements.

[0674] The server receives learning data transmitted through the learner's medium, which includes information about the learner's progress, past response history, and level of understanding. This data is analyzed by the processing unit, which evaluates the learner's learning status. Based on this, the processing unit generates an optimal curriculum for the learner. The generated curriculum is then presented to the learner's medium by the providing device.

[0675] The medium not only displays the generated curriculum to learners but also includes a recording device that allows learning to continue even in offline environments and can operate in asynchronous mode. Even in areas with unstable communication environments, it is possible to utilize educational content previously stored on the medium.

[0676] Furthermore, the response device analyzes natural language questions entered by learners into the medium, instantly generates appropriate answers, and sends them back to the medium, thereby deepening the learner's understanding. Also included are home-use assistive devices that physically interact with learners and intuitively present educational content through visual and physical representations.

[0677] This system incorporates cameras and sensors to capture learners' movements and support real-time, interactive educational activities. Furthermore, the use of generative AI models ensures that the curriculum and response content are always up-to-date.

[0678] For example, if a learner asks, "Tell me about photosynthesis," the home-use assistive device visually reproduces the process of photosynthesis using a plant model, and the response device provides relevant information. This allows learners to deepen their knowledge through hands-on experience.

[0679] Example prompt: "Tell me about an application where you can ask a robot questions about photosynthesis, and it will explain them in detail using real-time visuals."

[0680] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0681] Step 1:

[0682] The server receives learner data sent from the terminal. This data includes information about the learner's progress, past response history, and level of understanding. The received data is stored in a database.

[0683] Step 2:

[0684] The server analyzes the received learning data using a processing unit. Specifically, it uses data analysis algorithms to assess the learner's progress and level of understanding. The analysis results are output as evaluation data that shows the learner's level of understanding and characteristics.

[0685] Step 3:

[0686] The server utilizes a generation AI model based on evaluation data to generate a curriculum tailored to each learner. The curriculum generation process constructs a curriculum that takes into account each learner's strengths and weaknesses. This generated curriculum is then used in the next step.

[0687] Step 4:

[0688] The terminal presents the curriculum, received from the server via a distribution device, to the learner. If the learner accesses the curriculum in a local environment, offline learning is possible by using content pre-stored on the terminal.

[0689] Step 5:

[0690] The user (learner) can ask natural language questions entered into their device. The input data is sent to a response device and automatically analyzed through natural language processing. An appropriate answer generated based on the analysis results is output and displayed on the user's device.

[0691] Step 6:

[0692] Home-use assistive devices physically interact with learners and monitor their movements using sensors and cameras. They support real-time, interactive learning and provide visual explanations as needed. This process allows learners to understand educational content more intuitively.

[0693] 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.

[0694] This invention relates to a system that provides learners with an individualized educational experience, incorporating an emotion engine to recognize the learner's emotional state and dynamically adjusting the learning curriculum and educational content based on that state. This system monitors the learner's emotions in real time through the emotion engine and measures changes in stress and motivation.

[0695] The server receives learner learning data and comprehensively analyzes it, not only evaluating learning progress and comprehension through analysis tools, but also including emotional data provided by the emotion engine. This allows the curriculum generation tool to generate a customized curriculum based on the learner's emotional state. For example, if the emotion engine detects stress in the learner, the server can suggest relaxing learning content or a slower-paced curriculum to help them cope with that stress.

[0696] The device is responsible for providing learners with curriculum and learning content transmitted from the server, while simultaneously collecting emotional data. During the learning process, users engage with interactive content and adjust their learning experience in response to questions suggested by the device.

[0697] As a concrete example, suppose user D begins to feel stressed while trying to solve a difficult math problem. The emotion engine detects changes in user D's facial expressions and tone of voice through the camera and voice input, recognizing signs of stress. The server receives this information and supports user D's motivation to learn by including relaxing visual content and meditative music in the newly generated curriculum. As a result, user D can continue learning while reducing stress.

[0698] In this way, the integration of the emotion engine and the learning management system creates a flexible and responsive learning environment that responds to the individual emotional state of each learner.

[0699] The following describes the processing flow.

[0700] Step 1:

[0701] When a user begins learning, the device collects emotional data through its camera and microphone along with the learning data, and transmits this data to the server in real time.

[0702] Step 2:

[0703] The server processes the received learning data and sentiment data through an analysis device. In addition to evaluating learning progress and comprehension, the analysis device performs a sentiment evaluation using an emotion engine.

[0704] Step 3:

[0705] The emotion engine analyzes the user's emotional state and detects changes in stress and motivation. Based on these results, it assesses the degree to which stress reduction is needed.

[0706] Step 4:

[0707] Based on the analysis results, the server generates a curriculum tailored to the user's emotional state using a curriculum generation system. For example, if the user is experiencing high stress, the curriculum will incorporate slower-paced lessons and content designed to promote relaxation.

[0708] Step 5:

[0709] The server sends the generated curriculum to the terminal, which then presents it to the user. The terminal provides interactive feedback as needed.

[0710] Step 6:

[0711] As users progress through the learning process according to the provided curriculum, if questions arise, they can enter additional questions or requests via their device to receive support tailored to their emotional state.

[0712] Step 7:

[0713] The server receives questions from users and generates appropriate answers using question-answering mechanisms. Sentimental data is taken into consideration, and answers including mental support are generated as needed.

[0714] Step 8:

[0715] The answers are sent to the device, which then presents them to the user. Based on these answers, the user can deepen their understanding and revise their learning.

[0716] Step 9:

[0717] After a learning session ends, the device sends the latest learning data and emotional change history to the server. The server receives this data and uses it to optimize future curricula and emotional support.

[0718] (Example 2)

[0719] 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".

[0720] In today's educational environment, it is difficult for learners to receive an educational experience optimized based on their individual emotional state and learning progress. However, a uniform curriculum for each learner can lead to decreased learning efficiency and a decline in motivation. Therefore, there is a need to develop a system that can provide individualized curricula that take into account the learner's emotions and progress.

[0721] 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.

[0722] In this invention, the server includes means for receiving learner learning data and emotional data, analyzing the data to evaluate learning progress, comprehension, and emotional state; means for generating a customized curriculum for each learner that takes into account stress reduction and improved motivation to learn, based on the evaluation obtained by the analysis means; and means for providing the generated curriculum to the terminal used by the learner and simultaneously collecting emotional data in real time. This makes it possible to provide a dynamic and adaptive learning environment that is tailored to the individual circumstances of each learner.

[0723] "Learning data" refers to information about the learning activities that learners engage in on a daily basis, including indicators that show progress and level of understanding.

[0724] "Emotional data" refers to information that reflects the learner's mental state, and is derived from data such as facial expressions, voice, and behavioral patterns.

[0725] "Analysis means" refers to a technical method that processes collected learning data and sentiment data to evaluate the learner's progress, understanding, and emotional state.

[0726] A "curriculum generation method" is a technical method that uses evaluation results obtained through analysis to create a learning plan optimized for each learner.

[0727] "Delivery means" refers to the technical infrastructure for transmitting the generated curriculum and related learning content to the learner's device, enabling the learner to access it appropriately.

[0728] "Natural language processing" is a technology that analyzes learner input in a way that a machine can understand and generates an appropriate response.

[0729] "Offline mode" refers to a system configuration that allows learning content and functions to be provided even in situations with an unstable network connection, and where data is pre-stored on the device.

[0730] "Storage means" refers to technical components for pre-storing necessary learning materials and data within a device.

[0731] This invention is an educational system designed to personalize learners, combining an emotional engine with learning management. The program has the function of providing an adaptive curriculum based on collected data.

[0732] The server receives learning data and emotional data sent from learners. Emotional data is collected using facial recognition software and voice analysis tools that utilize the device's camera and microphone. The server analyzes this data and uses AI algorithms to evaluate learning progress, comprehension, and emotional state.

[0733] Based on this information, the server uses a generative AI model to create a customized curriculum that takes stress reduction and learning motivation into consideration. For example, if a user faces a difficult task and feels stressed, the server can provide relaxing content or a slower learning schedule.

[0734] The terminal presents the provided curriculum to the learner and collects learner feedback and new emotional data. This two-way data exchange allows the server to readjust the curriculum in real time and create an optimal learning environment tailored to the learner's situation.

[0735] For example, when a user is working on an advanced math problem, if the system detects the user's stress level through camera and voice input, it will recommend a new learning path accordingly. An example of the prompt in this case would be: "This system detects the user's stress level and generates a curriculum that suggests relaxing learning content. How does this system monitor the learner's emotional state and provide a personalized curriculum?"

[0736] In this way, a learning management system incorporating an emotion engine enables a flexible educational experience tailored to the learner's needs.

[0737] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0738] Step 1:

[0739] The device uses a camera and microphone to monitor the learner's learning progress and emotional state. Specifically, the device analyzes the user's facial expressions using facial recognition software and records the tone and speed of their voice using a speech recognition tool. This collects learning data and emotional data, which are then sent to a server as input and output.

[0740] Step 2:

[0741] The server analyzes the received learning data and emotional data. Specifically, it inputs the collected data into an AI algorithm to evaluate learning progress, comprehension, and emotional state. This process evaluates the learner's stress level and motivation level, and generates analysis results, which serve as both input and output.

[0742] Step 3:

[0743] The server uses a generative AI model to create a customized curriculum based on the analysis results. Specifically, this model configures appropriate learning content and resources based on each learner's evaluation and generates a new curriculum. The goal is to output a learning plan optimized for each learner.

[0744] Step 4:

[0745] The server sends the generated curriculum to the terminal. The terminal then begins displaying the received content to the user. Specifically, the terminal displays the provided curriculum on its screen and plays visual and auditory learning content. This provides the user with the information they need to progress in their learning.

[0746] Step 5:

[0747] Users progress through their learning based on the provided curriculum. As users progress, the device continuously collects data in real time by providing new questions and feedback. Specifically, when users provide feedback through interactive content, the data is updated based on the inquiry. This feedback is sent to the server and input as adjustments for the next curriculum.

[0748] (Application Example 2)

[0749] 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".

[0750] In recent years, there has been a growing demand for individualized education, making it crucial to provide curricula tailored to the individual needs and emotional states of each learner. However, conventional educational management systems have struggled to recognize learners' emotional states in real time and dynamically adjust learning content accordingly. This has resulted in challenges in reducing learner motivation and stress, and in providing an effective learning environment.

[0751] 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.

[0752] In this invention, the server includes an evaluation device that receives learner learning data and analyzes the data to evaluate learning progress and comprehension; a curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the evaluation device; a distribution device that provides the generated curriculum to the terminal used by the learner; an emotion analysis device that recognizes the learner's emotional state in real time; and a curriculum adjustment device that has the function of adjusting the learning content and pace to reduce stress based on the data from the emotion analysis device. This makes it possible to provide a flexible and adaptive learning experience that is tailored to the learner's individualized emotional state.

[0753] An "evaluation device" is a device that receives learner's learning data, analyzes that data, and evaluates their learning progress and level of understanding.

[0754] A "curriculum generation device" is a device that generates a customized curriculum for each learner based on evaluations obtained by an evaluation device.

[0755] A "distribution device" is a device that provides the generated curriculum to the terminals used by learners.

[0756] An "emotion analysis device" is a device that recognizes a learner's emotional state in real time.

[0757] A "curriculum adjustment device" is a device that adjusts learning content and pace to reduce stress based on data from an emotion analysis device.

[0758] The system for implementing this invention has a configuration that incorporates an evaluation device, a curriculum generation device, a distribution device, an emotion analysis device, and a curriculum adjustment device.

[0759] The server first receives learning data from learners using an evaluation device and performs analysis. This analysis evaluates the learners' learning progress and level of understanding. Next, based on the evaluation results, a curriculum generation device creates an individualized curriculum for each learner. Once generated, this curriculum is provided to the learner's terminal by a distribution device.

[0760] Furthermore, the terminal is equipped with an emotion analysis device that uses a camera and microphone to monitor changes in the learner's facial expressions and voice in real time. The emotion analysis device uses this data to determine the learner's emotional state. For example, if a learner is feeling stressed, the curriculum adjustment device can receive this data and issue instructions to adjust the learning content and pace.

[0761] As a concrete example, the system's program is written using Python. The camera module uses the OpenCV library to perform real-time facial expression analysis. In addition, Python's NLTK library is used for natural language processing to generate responses to learners' questions. When stress is detected, AWS Lambda is used to process instructions for curriculum adjustment in the cloud and notify the terminal of the results.

[0762] Consider a scenario where a user is using the system, for example, a primary school student tackling a complex math problem. If the emotion analysis device detects that the user is feeling confused, the curriculum adjustment device recommends relaxation content best suited to that state. In this situation, it is possible to send a prompt message to the generative AI model such as, "Please select relaxation content suitable for a student who is having trouble concentrating on the math problem. The student is confused and needs a short break," thereby providing appropriate educational content.

[0763] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0764] Step 1:

[0765] The server receives learning data from learners. The input data concerns the subjects the learners are studying and their progress. By analyzing this data, the server evaluates the learners' progress and understanding. Specifically, it performs statistical processing on the data and calculates a score for each item.

[0766] Step 2:

[0767] The server uses an evaluation device to assess the learner's level of understanding based on the analysis results, and then uses a curriculum generation device to create an individualized curriculum. The output is a new curriculum proposal, which determines the learning content best suited to the user's current learning level. Specifically, it uses an AI algorithm to propose personalized educational content.

[0768] Step 3:

[0769] The server transmits the curriculum to user terminals via a distribution device. The input is the generated curriculum draft, and the output is the learning content displayed on the user terminal. In this step, data is transmitted over the network to ensure that the educational content is delivered to learners on time.

[0770] Step 4:

[0771] The device uses an emotion analysis system to monitor the learner's emotional state in real time. Input is facial and audio data acquired from a camera and microphone, and output is the recognized emotional state of the learner. The system uses the OpenCV library to perform facial recognition and identify individual emotions.

[0772] Step 5:

[0773] The server receives emotional data from the emotion analysis device and dynamically adjusts the learning content and pace using the curriculum adjustment device. The input is emotional data, and the output is the adjusted educational curriculum. Specifically, if an indicator of stress is high, the curriculum is modified to reduce the learner's burden, such as by adding relaxation content.

[0774] Step 6:

[0775] When a user engages with content, a generative AI model is used to generate prompts and provide appropriate learning support. The input is information about the learning content and emotional state, and the output is a prompt generated based on that information. For example, it might generate a prompt such as, "Based on your current level of understanding, please suggest the next problem to solve," and then take specific actions to support learning.

[0776] 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.

[0777] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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."

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] The following is further disclosed regarding the embodiments described above.

[0798] (Claim 1)

[0799] An analysis means that receives learner learning data, analyzes that data to evaluate learning progress and comprehension,

[0800] A curriculum generation means that generates a customized curriculum for each learner based on the evaluation obtained by the analysis means,

[0801] A means of providing the generated curriculum to the learner's device,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, comprising a question-answering means that analyzes a question entered by a learner using natural language processing and generates and presents an appropriate answer.

[0805] (Claim 3)

[0806] The system according to claim 1, which has an offline mode that can operate even in areas with unstable network environments, and includes a storage means for saving learning content in advance on the terminal.

[0807] "Example 1"

[0808] (Claim 1)

[0809] An evaluation method that receives learner's educational data, analyzes that data to evaluate the progress and level of understanding of the education,

[0810] A plan generation means that generates an individualized educational plan for each learner based on the evaluation obtained by the evaluation means,

[0811] A means of providing the generated educational plan to the device used by the learner,

[0812] An offline mode is implemented, along with a storage method for pre-saving educational content to the device.

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, comprising a question answering means for analyzing a question input by a learner using natural language processing, generating and presenting an appropriate answer, and a means for using a generative artificial intelligence model.

[0816] (Claim 3)

[0817] The system according to claim 1, comprising an optimization means for incorporating interactive educational materials and simulations based on previous learning results and learners' weaknesses when structuring an educational plan.

[0818] "Application Example 1"

[0819] (Claim 1)

[0820] A processing device that receives learner learning data, analyzes that data, and evaluates learning progress and comprehension level,

[0821] A curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the aforementioned processing device,

[0822] A device that provides the generated curriculum to a medium used by learners,

[0823] A response device that analyzes the questions entered by learners using natural language processing, generates appropriate answers, and presents them.

[0824] It features a recording device that pre-saves learning content in the media, and has an asynchronous mode that allows it to operate even in areas with unstable communication environments.

[0825] A method that incorporates home-based assistive devices that allow learners to experience education intuitively through physical contact and explain content using visual and physical representations,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, which uses a camera and sensors to analyze the movements of learners and supports interactive educational activities.

[0829] (Claim 3)

[0830] The system according to claim 1, which collects offline learning progress and later synchronizes it online.

[0831] "Example 2 of combining an emotion engine"

[0832] (Claim 1)

[0833] An analytical means that receives learner learning data and emotional data, analyzes that data to evaluate learning progress, comprehension, and emotional state,

[0834] A curriculum generation means that generates a customized curriculum for each learner that takes into account stress reduction and improved motivation to learn, based on the evaluation obtained by the analysis means,

[0835] A means of providing the generated curriculum to the learner's device and simultaneously collecting emotional data in real time,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, comprising a question-answering means that analyzes questions and feedback entered by learners using natural language processing and provides appropriate answers and content adjustments.

[0839] (Claim 3)

[0840] The system according to claim 1, which includes an offline mode that can operate even in environments with unstable network communication, and includes a storage means for pre-storing learning materials on the terminal.

[0841] "Application example 2 when combining with an emotional engine"

[0842] (Claim 1)

[0843] An evaluation device that receives learner learning data, analyzes that data to evaluate learning progress and comprehension,

[0844] A curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the aforementioned evaluation device,

[0845] A distribution device that provides the generated curriculum to the learner's device,

[0846] An emotion analysis device that recognizes the learner's emotional state in real time,

[0847] A curriculum adjustment device that has the function of adjusting learning content and pace to reduce stress based on data from an emotion analysis device,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, comprising a response generation device that analyzes a question entered by a learner using natural language processing and generates and presents an appropriate answer.

[0851] (Claim 3)

[0852] The system according to claim 1, which has an offline mode that can operate even in areas with unstable network environments, and is equipped with a storage device that pre-stores learning content on the terminal. [Explanation of Symbols]

[0853] 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 processing device that receives learner learning data, analyzes that data, and evaluates learning progress and comprehension level, A curriculum generation device that generates a customized curriculum for each learner based on the evaluation obtained by the aforementioned processing device, A device that provides the generated curriculum to a medium used by learners, A response device that analyzes the questions entered by learners using natural language processing, generates appropriate answers, and presents them. It features a recording device that pre-saves learning content in the media, and has an asynchronous mode that allows it to operate even in areas with unstable communication environments. A method that incorporates home-based assistive devices that allow learners to experience education intuitively through physical contact and explain content using visual and physical representations, A system that includes this.

2. The system according to claim 1, which uses a camera and sensors to analyze the movements of learners and supports interactive educational activities.

3. The system according to claim 1, which collects offline learning progress and later synchronizes it online.

Images