system

Abstract

We provide the system. [Solution] A means for receiving user attribute data and learning objective data, A means of collecting user learning activity data in real time, A means of analyzing the user's level of understanding based on the received data, A means of generating a learning plan based on the user's level of understanding, A means of providing the generated learning plan to the user, A means of receiving questions from users, generating and providing relevant explanations, 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 the 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 that responds 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 educational platforms, it has been difficult to provide a learning plan suitable for the progress and understanding of each student, resulting in a problem of reduced learning efficiency. In addition, since there are limited means to immediately resolve specific doubts that students have during learning, it is difficult to improve students' understanding. Due to these problems, there is an issue that students cannot enjoy an individually optimized learning experience.

Means for Solving the Problems

[0005] This invention provides means for receiving user attribute data and learning objective data, and for collecting user learning activity data in real time, thereby generating a learning plan tailored to each individual user. Furthermore, it analyzes the user's level of understanding and dynamically updates the learning plan based on the analysis results, providing appropriate learning content according to the user's progress. In addition, by incorporating an on-demand tutor function that accepts user questions and provides relevant explanations generated by AI, it is possible to resolve students' doubts immediately and appropriately. In this way, the aim is to individually optimize the student's learning experience and achieve efficient learning.

[0006] A "user" refers to an individual or institution that uses the system for learning.

[0007] "Attribute data" refers to data that includes basic information such as the user's age, grade level, and learning goals.

[0008] "Learning objective data" refers to information about the specific learning goals and objectives that the user wants to achieve.

[0009] "Learning activity data" refers to data that records a user's actions during learning, such as learning time, answer results, and content viewing history.

[0010] "Comprehension level" refers to an indicator that shows how well a user understands a particular learning content or subject.

[0011] A "learning plan" refers to a collection of individually optimized learning content generated based on the user's level of understanding.

[0012] The "on-demand tutor function" refers to a feature that accepts questions from users and uses AI to generate appropriate explanations and materials in response.

[0013] "AI" refers to artificial intelligence, a program that analyzes data and makes decisions. [Brief explanation of the drawing]

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

MODE FOR CARRYING OUT THE INVENTION

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

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

[0017] In the following embodiments, a labeled 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 labeled 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 labeled 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 an educational platform that provides personalized learning plans utilizing generative AI, aiming to maximize user learning efficiency. The system collects user attribute data and learning goal data, and monitors user learning activity data in real time. This enables the provision of learning plans optimized for each individual user.

[0036] Specifically, the server receives attribute data and learning objective data initially provided by the user. This data includes basic information such as the user's age, grade level, specific learning objectives, and known level. Based on this data, the server generates an initial learning plan and presents it to the user via the device.

[0037] As the user progresses through the learning process, the device continuously collects activity data and sends it to the server. This data includes information such as what content the user views, how much time they spend on it, and how accurately they answer each question. The server receives this data and uses AI algorithms to analyze the user's understanding in real time. Based on this analysis, the server dynamically updates the user's learning plan and recommends new content and practice problems.

[0038] Furthermore, if users encounter questions during their learning process, they can utilize the on-demand tutoring function via their device. When a user sends a question to the server, AI analyzes the question and generates and provides relevant explanations and supplementary materials. This allows users to access information to deepen their understanding at any time.

[0039] To give a concrete example, suppose a middle school student is learning the mathematical algebra. Initially, the server provides basic algebra exercises, taking into account the user's grade level and the field they are studying. As the user progresses, if they achieve a high success rate, the server adds more difficult problems according to their progress. Conversely, if they make many mistakes on a particular concept, the server suggests video explanations or additional practice exercises to deepen their understanding of that area. If the user asks about the quadratic formula, the server uses AI to generate and immediately provide an explanation of the derivation process. In this way, the system provides an effective learning experience optimized for the user.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server receives attribute data and learning objective data entered by the user. This allows it to obtain basic information such as the user's grade level, field of study, and learning objectives.

[0043] Step 2:

[0044] The server generates an initial learning plan based on the received attribute data and goals. During this process, it selects the most suitable learning materials for the user from its existing database of educational content.

[0045] Step 3:

[0046] The terminal displays the learning plan sent from the server to the user and provides an interface for starting the learning process.

[0047] Step 4:

[0048] As the user progresses through the learning process, the device collects data on the user's learning activities. This data includes the time spent learning, the results of problems solved, and the content viewed.

[0049] Step 5:

[0050] The device sequentially transmits the collected learning activity data to the server. This data transmission occurs in real time and periodically.

[0051] Step 6:

[0052] The server analyzes the received learning activity data using an AI algorithm to evaluate the user's level of understanding. Analysis items include the accuracy rate, response speed, and whether or not repeated learning was performed.

[0053] Step 7:

[0054] The server updates the user's learning plan based on the analysis results. Specific updates include adjusting the difficulty level, providing additional practice problems, and recommending new content.

[0055] Step 8:

[0056] The device presents the user with a new learning plan and encourages continued learning. Notification features can also alert the user to begin the next step.

[0057] Step 9:

[0058] If a user has a question during their learning process, they can use the on-demand tutoring function via their device to send their question to the server. The question is in text format, entered by the user.

[0059] Step 10:

[0060] The server analyzes user questions and uses AI to generate relevant explanations and supplementary materials. The generated explanations are intended to deepen the user's understanding.

[0061] Step 11:

[0062] The server sends the generated explanations and materials back to the terminal, where they are displayed to the user. The user can then use this information to resolve any questions and continue learning.

[0063] Step 12:

[0064] The device collects user feedback and sends that data to the server. The feedback concerns the usefulness of the content and learning satisfaction.

[0065] Step 13:

[0066] The server aims to use feedback data to generate the next learning plan, thereby providing an even more customized learning experience.

[0067] (Example 1)

[0068] 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."

[0069] Traditional education systems have struggled to provide personalized learning experiences and maximize user learning efficiency. In particular, there is a growing need to improve the quality of learning by providing dynamic learning plans and immediate feedback tailored to the user's progress.

[0070] 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.

[0071] In this invention, the server includes means for receiving user attribute information and learning objective information, means for collecting user learning behavior data in a timely manner, and means for analyzing the user's understanding state based on the received information. This enables the provision of a learning plan optimized for each individual user and efficient management of learning progress.

[0072] "User attribute information" refers to basic personal information such as the user's age, grade level, and experience level.

[0073] "Learning objective information" refers to information that indicates the specific learning goals that the user is trying to achieve.

[0074] "User learning behavior data" refers to data that shows what activities a user performed during learning, including content viewed, response time, and accuracy rate.

[0075] "Analyzing comprehension" refers to evaluating the user's level of understanding of knowledge and skills based on collected user learning behavior data.

[0076] "Dynamically generating learning plans" refers to creating optimized learning content and schedules for each user in real time, based on analysis results.

[0077] "Receiving questions, generating and presenting explanations" refers to processing user inquiries on a server, generating relevant detailed information and explanations, and providing them to the user.

[0078] This invention is an educational platform that provides personalized learning plans utilizing a generative AI model, aiming to maximize user learning efficiency. The server receives attribute information and learning objective information provided by the user. This information includes basic information such as age, grade level, specific learning objectives, and known level. The server utilizes this received information and generates an initial learning plan using a generative AI model.

[0079] Once a user begins learning, the device collects real-time data on their learning behavior. This includes details such as what content the user views, how much time they spend on it, and how accurately they answer questions. The device sends this data to a server, which uses an AI algorithm to analyze the user's understanding. Based on the analysis, the server reuses the generative AI model to dynamically update the learning plan according to the user's level of understanding. This then presents new learning content and practice problems.

[0080] Furthermore, if a user encounters a question during their learning process, they can send it to the server on demand via their device. The server can then use a generative AI model to analyze the question, generate relevant explanations, and present them, providing the user with the information they need.

[0081] For example, if a middle school student is learning algebra, the server will present basic algebra problems, taking into account their grade level and the subject they are currently studying. As the learning progresses, the plan will be adjusted based on the user's answers. For instance, if there is a question about the quadratic formula, the server will generate and provide information that explains its derivation and application in detail.

[0082] An example of a prompt in this system would be, "Based on the user's learning progress data, please generate the next recommended math problem." This prompt allows the generating AI model to dynamically create a corresponding learning plan.

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

[0084] Step 1:

[0085] The server receives attribute information and learning objective information from the user. As input, it receives basic information such as age, grade level, and learning objectives entered by the user on their device. Based on this data, it performs initial analysis and updates a database to understand the user's characteristics.

[0086] Step 2:

[0087] The server uses the generated AI model as a prompt based on the received attribute information to generate an initial learning plan. In this process, the prompt "Generate the optimal initial learning plan for the newly registered user" is used, and the AI ​​outputs a plan. The result is sent to the terminal and presented to the user.

[0088] Step 3:

[0089] Once a user begins learning, the device continuously collects data on their learning behavior. This data includes inputs such as the user's viewing history of learning content, response time, and accuracy rate. The device then organizes this data and sends it to the server.

[0090] Step 4:

[0091] The server analyzes the collected learning behavior data. Using an AI algorithm, it evaluates the user's understanding in real time. Based on the analysis results, it inputs the prompt message "Generate the next learning task based on the user's understanding" into the generating AI model and outputs a new learning plan.

[0092] Step 5:

[0093] The server sends the newly generated learning plan to the terminal and presents it to the user. This allows the user to work on continuously updated and optimal challenges.

[0094] Step 6:

[0095] If a user encounters a question during the learning process, they send it to the server via their device. The server receives the user's specific question as input. In response, the server uses a generative AI model to generate an explanation for the question.

[0096] Step 7:

[0097] The server sends the generated explanations back to the terminal, providing them to the user. This allows the user to quickly resolve their questions and continue learning.

[0098] (Application Example 1)

[0099] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0100] Traditional learning platforms suffer from a lack of real-time optimization to meet individual user learning needs and from a failure to provide a learning experience linked to the real-world physical environment. This limitation prevents users from making the most of the information resources available to them during their learning process.

[0101] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0102] In this invention, the server includes means for receiving user attribute data and learning objective data, means for collecting user learning activity data in real time, and means for analyzing the user's level of understanding based on the received data. This enables the provision of a learning plan optimized for the user and the visual presentation of educational resources linked to the real-world physical environment.

[0103] "User attribute data" refers to data that contains basic information about the user, such as age, grade level, and learning goals.

[0104] "Learning objective data" refers to information about the specific learning goals and objectives that the user wants to achieve.

[0105] "Learning activity data" refers to data that shows a user's activity history, including what content they viewed, how much time they spent on it, and how accurately they answered each question.

[0106] "Means of analyzing comprehension" refers to methods and technologies for evaluating a user's knowledge level and comprehension based on their learning activity data.

[0107] "Means for generating learning plans" refers to methods and devices that suggest optimal learning content and methods according to the user's level of understanding and learning goals.

[0108] "Means of providing the generated learning plan to the user" refers to the methods and technologies for deploying the generated learning plan in a format that the user can use.

[0109] The "On-Demand Tutor Function" refers to a feature that automatically generates and provides necessary explanations and information in response to user questions.

[0110] "Means of visually presenting information within a physical environment" refers to methods and devices for visually displaying user-related information in real-world space.

[0111] "Means of presenting educational resources based on location data" refers to methods and technologies for presenting optimal learning materials and information based on the user's current location.

[0112] The system for realizing this invention mainly consists of a server, a user terminal, and devices such as smart glasses. The server receives attribute data and learning objective data provided by the user and generates an initial learning plan. This learning plan is presented visually through the user's smart glasses, and the user's progress and learning activity data are collected in real time.

[0113] The server uses generated AI to analyze the user's understanding based on this activity data. This analysis is used to dynamically update the user's learning plan, recommending new content and practice exercises as needed. Furthermore, appropriate educational resources are visually presented based on the user's physical location data. For example, when a user moves to a specific learning area within a physical store, relevant learning materials and information are displayed on the smart glasses' screen.

[0114] Furthermore, an on-demand tutoring function is included to support users with questions that arise during their learning. Questions from users are sent to the server, where a generating AI analyzes them and instantly generates relevant explanations and supplementary materials.

[0115] As a concrete example, consider a scenario where a middle school student visits a physical store's learning space to study geometry. When this user searches for "recommended learning materials on triangle congruence conditions" using smart glasses, the system identifies the most relevant books and learning materials for that location and visually guides them on the display. Furthermore, when the user asks a question about "triangle congruence conditions," the generative AI model instantly generates an explanation of the derivation process.

[0116] An example of a prompt message would be: "Based on the user's attribute data, generate a list of learning materials best suited to the current learning objectives and provide detailed descriptions of them."

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server receives attribute data and learning objective data from the user's terminal. This includes the user's age, grade level, and learning objectives as input, and the server generates an initial learning plan based on this data. At this stage, it references similar past cases from the database to select a base learning pattern.

[0120] Step 2:

[0121] The user puts on smart glasses and enters a physical store. The device collects the user's location data and surrounding environmental information, and sends it to a server. As the user moves to a specific area within the store, the content displayed on the smart glasses dynamically changes. During this process, the glasses collect environmental data in real time using cameras and sensors.

[0122] Step 3:

[0123] Based on the received location data and user attribute information, the server uses a generative AI model to identify the most suitable learning resources for the user and sends visual instructions to the glasses. This process involves extracting learning materials that match the user's learning progress and objectives from a digital database, and then organizing and providing information about them.

[0124] Step 4:

[0125] If a user has a question during the learning process, they input the question through smart glasses. This question is sent from the device to a server for analysis. The AI ​​model analyzes the input question and generates relevant materials and explanations.

[0126] Step 5:

[0127] The server uses a generative AI model to generate appropriate explanations and supplementary information in response to user questions, and immediately sends them to the smart glasses. The output information includes video links and detailed explanations to enhance the user's understanding.

[0128] Step 6:

[0129] The device collects learning activity data, such as the learning materials used and the time spent studying, and continuously transmits it to the server. The server analyzes this data and evaluates the user's level of understanding. Based on this evaluation, the learning plan for the next step is dynamically updated, and the optimal route to achieving the goal is presented.

[0130] 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.

[0131] This invention provides a system that combines an emotion engine with an educational platform using generative AI to offer users more personalized learning support. This system collects user attribute data and learning goal data, and monitors user learning activity data and emotional data in real time. This allows for the creation and provision of an optimal learning plan that takes into account the user's level of understanding and emotional state.

[0132] Specifically, the server receives attribute data and learning objective data as basic information obtained from the user. Based on this information, an initial learning plan is generated on the server and presented to the user via the terminal. As the user progresses through the learning process, the terminal sends learning activity data and emotion data detected using the emotion engine to the server.

[0133] This emotional data includes the user's stress levels, level of interest, and level of concentration during learning, allowing for a detailed analysis of the user's state of mind. The server uses AI algorithms to comprehensively analyze this data and evaluate the user's current level of understanding and emotional state. Based on the evaluation results, the server dynamically adjusts the learning plan. For example, if it is determined that the user has lost interest in learning, the plan can be made more interactive or its difficulty level adjusted.

[0134] Furthermore, if a user has a question, it is sent from the device to the server, and the AI ​​generates a relevant explanation and responds. Here, responses based on the user's emotions are also taken into consideration, so for example, if the user is feeling stressed, content that promotes relaxation may be incorporated.

[0135] As a concrete example, let's consider a case where an elementary school student is learning programming for the first time. In the initial setup, a plan is provided to learn basic programming concepts based on the user's learning goals. If the emotion engine detects a decrease in the user's concentration during learning, the server adopts a strategy of changing the learning content into a game format to regain attention. Also, if the user asks a question such as "Why does this happen?", in addition to a simple answer, information on related topics that will pique the user's interest is also provided. In this way, the present invention allows users to enjoy a more effective and engaging learning experience.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The server receives attribute data and learning objective data entered by the user. This includes information such as age, grade level, and learning goals.

[0139] Step 2:

[0140] The server generates an initial learning plan. This plan selects specific learning content and materials based on the user data received.

[0141] Step 3:

[0142] The device presents the user with an initial learning plan sent from the server. The user can then begin learning.

[0143] Step 4:

[0144] As the user progresses through the learning process, the device collects data on the user's learning activities. This includes learning time, content progress, and the results of answering questions.

[0145] Step 5:

[0146] The emotion engine acquires user emotional data through facial recognition and voice tone analysis. This data includes information such as stress levels, interest levels, and concentration levels.

[0147] Step 6:

[0148] The device sends collected learning activity data and emotional data to the server. This transmission occurs in real time, and the data is continuously updated.

[0149] Step 7:

[0150] The server uses AI algorithms to analyze this data and evaluate the user's level of understanding and emotional state. This allows for the measurement of learning effectiveness and user motivation.

[0151] Step 8:

[0152] The server adapts the learning plan based on the evaluation results. Specifically, if the user's concentration wavers, adjustments are made, such as incorporating game elements or suggesting breaks.

[0153] Step 9:

[0154] The device presents the user with a new learning plan and notifies them of the changes, allowing the user to proceed to the next learning step.

[0155] Step 10:

[0156] When a user has a question, they can send it to the server via their device. The question entered here is in text format.

[0157] Step 11:

[0158] The server uses AI to analyze user questions and generates and provides relevant explanations and learning materials to the user. In doing so, the server also considers the user's emotional state to select the most appropriate response.

[0159] Step 12:

[0160] The server collects user feedback data and uses it to generate the next learning plan. Based on the feedback, improvements are made to provide a more effective learning experience.

[0161] (Example 2)

[0162] 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".

[0163] Traditional educational platforms struggle to fully understand each user's individual learning state and emotions, and to provide personalized learning support accordingly. In particular, they cannot dynamically adjust learning plans in response to changes in user interests or improvements in comprehension, resulting in limited learning effectiveness.

[0164] 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.

[0165] In this invention, the server includes means for receiving basic user information and goal information, means for collecting user learning activity information and emotional information in real time, and means for analyzing the user's level of understanding and state based on the received information. This makes it possible to dynamically adjust the learning plan according to the user's individual emotional state and learning progress, and to provide optimal learning support.

[0166] "Basic information" refers to information that indicates the user's personal characteristics, including age, grade level, areas of expertise, and areas of weakness.

[0167] "Goal information" refers to information about the learning goals that the user wishes to achieve, and includes specific learning outcomes and progress targets.

[0168] "Learning activity information" refers to data related to the learning activities undertaken by the user, including the time spent learning, the number of completed assignments, and their progress.

[0169] "Emotional information" refers to information related to the user's emotional state, including data measuring the user's stress level, level of interest, and level of concentration.

[0170] "Comprehension level" is an evaluation metric that indicates how well a user understands the learning material, and is estimated from the user's accuracy rate and speed of response.

[0171] "State" refers to the mental and emotional state of a user during learning, and is a concept that includes levels of interest and stress based on emotional information.

[0172] "Dynamic adjustment" means modifying the learning plan in real time according to the user's level of understanding and status, and updating the content as needed to optimize learning support.

[0173] A "learning plan" is a plan that outlines the learning content and activities that a user should accomplish within a certain period of time, and includes specific learning topics and a sequence of content.

[0174] This invention is an educational system that provides personalized learning support to users using generative AI technology and emotion analysis technology. The server receives attribute information and learning goal information from the user and creates an initial learning plan based on this information. The terminal collects activity information and emotional information in real time during the user's learning activities. This emotional information is measured from the user's facial expressions, voice, operation speed, etc., and is data that indicates the user's stress level, interest level, and concentration level.

[0175] The server analyzes received learning activity and emotional information using a generative AI model to evaluate the user's understanding and emotional state. Based on this evaluation, the server dynamically adjusts the learning plan. This ensures that the learning content remains engaging for the user, maximizing learning effectiveness. Furthermore, if the user has questions, they can submit them through their device. The server then generates explanations using the generative AI in response to these questions, providing answers tailored to the user's emotional state.

[0176] As a concrete example, consider a scenario where an elementary school student is learning programming for the first time. The server receives the user's goal information and generates a learning plan to teach the basics of programming as an initial setup. However, if the server determines through the terminal that the user's concentration is waning, it can change the learning plan to be more interactive and gamified to re-engage the user.

[0177] An example of a prompt message might be, "Explain basic programming concepts in a fun way to an elementary school student who is learning programming for the first time." This system allows users to achieve effective learning tailored to their individual needs.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The server receives basic information and learning objectives from the user. Input consists of personal information provided by the user via their device, such as age, grade level, and learning objectives. The server stores this information in a database and uses it as foundational data to generate an initial learning plan. Output is the foundational information for the initial learning plan.

[0181] Step 2:

[0182] The server generates an initial training plan based on the information received using a generative AI model. The input consists of basic information and training objectives. The generative AI model processes this data to generate a first training plan tailored to the user's individual needs. The output is the initial training plan presented to the user. This plan is provided to the user via the terminal.

[0183] Step 3:

[0184] The device collects learning activity information and emotional information in real time while the user is learning. Inputs include the user's actions, facial expressions, and voice during learning. The device uses sensors and microphones to collect learning time, answer status, and emotional data based on facial expression analysis. Outputs are sent to the server as learning activity information and emotional information.

[0185] Step 4:

[0186] The server analyzes the received learning activity and emotional information to evaluate the user's current level of understanding and emotional state. The input consists of collected learning activity and emotional information. Using an AI algorithm, the server comprehensively analyzes this data to determine the user's interests and level of understanding. The output is the evaluation result, which dynamically adjusts the user's learning plan.

[0187] Step 5:

[0188] The server dynamically adjusts the learning plan using a generated AI model based on the evaluation results. For example, if it determines that the user's concentration is waning, it might lower the difficulty level or increase the amount of interactive content. The input is the evaluation results, and the output is the adjusted learning plan. This new plan is then provided to the user again through the device.

[0189] Step 6:

[0190] If a user has a question during the learning process, they send the question to the server via their device. The input is the user's question. The server uses generative AI to generate a detailed and appropriate explanation for the question and sends it back to the user. The output is explanatory information tailored to the user's emotional state, which may include elements that promote relaxation.

[0191] (Application Example 2)

[0192] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0193] Conventional online learning platforms often provide a uniform learning experience without considering the user's emotional state, which has led to decreased learning efficiency and motivation. Furthermore, simply providing plans based on comprehension levels makes it difficult to flexibly respond to the user's current emotions and interests. This invention aims to solve these problems and provide a more personalized learning experience.

[0194] 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.

[0195] In this invention, the server includes means for receiving user attribute information and purpose information, means for collecting user activity information in real time, means for evaluating the learner's understanding based on the received information, means for generating a plan based on the learner's understanding, means for providing the generated plan to the user, means for receiving inquiries from the user and generating and providing relevant explanations, and means for analyzing the user's emotional state and providing recommendation information accordingly. This makes it possible to provide a dynamic and flexible learning plan that simultaneously considers the user's level of understanding and emotional state.

[0196] "User attribute information" refers to personal characteristics and background information about users, including data such as age, gender, occupation, and learning experience.

[0197] "Purpose information" refers to information that indicates the learning goals or objectives that the user wishes to achieve, or their current areas of interest.

[0198] "Activity information" refers to data on various actions taken by users on the platform, including content viewed, questions answered, and access frequency.

[0199] "Participant comprehension level" refers to information indicating how well users understand the material they have learned, and is evaluated based on factors such as grades and the accuracy of answers.

[0200] "Means for generating plans" refer to methods and functions for creating efficient and effective learning plans based on the user's understanding and attribute information.

[0201] "User inquiries" refer to questions and requests that users send to the system when they have questions while learning.

[0202] "Means for generating and providing relevant explanations" refers to methods and functions for generating appropriate and easy-to-understand explanations in response to user inquiries and informing users of the results.

[0203] "User emotional state" refers to information that captures the mental and emotional state exhibited by users during learning, and includes, for example, excitement, concentration, and boredom.

[0204] "Means of providing recommendation information" refers to methods or functions for suggesting appropriate products, services, or learning content that are tailored to the user's emotional state.

[0205] This invention is implemented by a system consisting of three elements: a server, a terminal, and a user.

[0206] The server generates an initial learning plan using attribute and objective information obtained from the user. This plan is then provided to the user via the terminal. The server analyzes the received user activity and sentiment information in real time, continuously evaluating the user's understanding and emotional state. This allows the server to dynamically adjust the learning plan as needed, providing an optimal learning environment.

[0207] The device monitors the user's learning activity and sends activity information and emotional state data acquired through an emotion recognition library to the server. This process utilizes a system equipped with a generative AI model to analyze complex datasets, including the user's emotional data.

[0208] If a user has questions during the learning process, they can submit them through their device. The server uses a generative AI model to generate appropriate explanations for these inquiries, taking into account the user's emotional state when providing answers.

[0209] As a concrete example, imagine a scenario where an elementary school student is learning programming for the first time in a virtual store. If the user shows signs of boredom during the learning process, the system will automatically adjust the plan to present more interactive learning materials to capture their attention. Also, if the user asks a question about programming, such as "Why does this result occur?", the AI ​​will provide an easy-to-understand explanation on the spot, along with information on related topics to further increase their interest.

[0210] Examples of prompts for a generative AI model:

[0211] "Please provide information that clearly explains the programming learning materials displayed by the user, based on other reference materials and the experiences of other learners."

[0212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0213] Step 1:

[0214] The server receives attribute and purpose information from the user. The received data is stored in a database and used as input when generating an initial learning plan. Based on this information, suitable educational content and starting guidelines are formulated.

[0215] Step 2:

[0216] The device collects user activity information in real time and sends it to the server. This activity information includes the user's progress and behavior logs, which are used to track learning progress. The device also uses its camera and input devices to collect additional data necessary for evaluating emotional states.

[0217] Step 3:

[0218] The server uses received activity information and sentiment data to simultaneously evaluate the user's understanding and emotional state. A generative AI model is used to process the input data, analyzing the user's level of understanding and emotional tendencies. The optimized evaluation results are then output.

[0219] Step 4:

[0220] The server dynamically adjusts the learning plan based on the evaluation results and provides the updated plan to the device. This adjustment includes selecting learning materials tailored to the user's interests and understanding, and changing the difficulty level. This process ensures that users can always continue learning in an optimal state.

[0221] Step 5:

[0222] When a user enters a question during the learning process, the device sends the inquiry to the server. The server uses a generative AI model to generate an appropriate explanation for the question and sends it to the device. The generated explanation takes the user's emotional state into consideration and is presented in an easy-to-understand and relaxed format.

[0223] Step 6:

[0224] The server analyzes the user's emotional state and provides corresponding recommendations to the device. For example, if interest is waning, new interactive content will be recommended. This helps maintain the user's learning motivation.

[0225] 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.

[0226] 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 those described above. 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 shown 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.

[0227] 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.

[0228] [Second Embodiment]

[0229] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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".

[0241] This invention is an educational platform that provides personalized learning plans utilizing generative AI, aiming to maximize user learning efficiency. The system collects user attribute data and learning goal data, and monitors user learning activity data in real time. This enables the provision of learning plans optimized for each individual user.

[0242] Specifically, the server receives attribute data and learning objective data initially provided by the user. This data includes basic information such as the user's age, grade level, specific learning objectives, and known level. Based on this data, the server generates an initial learning plan and presents it to the user via the device.

[0243] As the user progresses through the learning process, the device continuously collects activity data and sends it to the server. This data includes information such as what content the user views, how much time they spend on it, and how accurately they answer each question. The server receives this data and uses AI algorithms to analyze the user's understanding in real time. Based on this analysis, the server dynamically updates the user's learning plan and recommends new content and practice problems.

[0244] Furthermore, if users encounter questions during their learning process, they can utilize the on-demand tutoring function via their device. When a user sends a question to the server, AI analyzes the question and generates and provides relevant explanations and supplementary materials. This allows users to access information to deepen their understanding at any time.

[0245] To give a concrete example, suppose a middle school student is learning the mathematical algebra. Initially, the server provides basic algebra exercises, taking into account the user's grade level and the field they are studying. As the user progresses, if they achieve a high success rate, the server adds more difficult problems according to their progress. Conversely, if they make many mistakes on a particular concept, the server suggests video explanations or additional practice exercises to deepen their understanding of that area. If the user asks about the quadratic formula, the server uses AI to generate and immediately provide an explanation of the derivation process. In this way, the system provides an effective learning experience optimized for the user.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The server receives attribute data and learning objective data entered by the user. This allows it to obtain basic information such as the user's grade level, field of study, and learning objectives.

[0249] Step 2:

[0250] The server generates an initial learning plan based on the received attribute data and goals. During this process, it selects the most suitable learning materials for the user from its existing database of educational content.

[0251] Step 3:

[0252] The terminal displays the learning plan sent from the server to the user and provides an interface for starting the learning process.

[0253] Step 4:

[0254] As the user progresses through the learning process, the device collects data on the user's learning activities. This data includes the time spent learning, the results of problems solved, and the content viewed.

[0255] Step 5:

[0256] The device sequentially transmits the collected learning activity data to the server. This data transmission occurs in real time and periodically.

[0257] Step 6:

[0258] The server analyzes the received learning activity data using an AI algorithm to evaluate the user's level of understanding. Analysis items include the accuracy rate, response speed, and whether or not repeated learning was performed.

[0259] Step 7:

[0260] The server updates the user's learning plan based on the analysis results. Specific updates include adjusting the difficulty level, providing additional practice problems, and recommending new content.

[0261] Step 8:

[0262] The device presents the user with a new learning plan and encourages continued learning. Notification features can also alert the user to begin the next step.

[0263] Step 9:

[0264] If a user has a question during their learning process, they can use the on-demand tutoring function via their device to send their question to the server. The question is in text format, entered by the user.

[0265] Step 10:

[0266] The server analyzes user questions and uses AI to generate relevant explanations and supplementary materials. The generated explanations are intended to deepen the user's understanding.

[0267] Step 11:

[0268] The server sends the generated explanations and materials back to the terminal, where they are displayed to the user. The user can then use this information to resolve any questions and continue learning.

[0269] Step 12:

[0270] The device collects user feedback and sends that data to the server. The feedback concerns the usefulness of the content and learning satisfaction.

[0271] Step 13:

[0272] The server aims to use feedback data to generate the next learning plan, thereby providing an even more customized learning experience.

[0273] (Example 1)

[0274] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] Traditional education systems have struggled to provide personalized learning experiences and maximize user learning efficiency. In particular, there is a growing need to improve the quality of learning by providing dynamic learning plans and immediate feedback tailored to the user's progress.

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

[0277] In this invention, the server includes means for receiving user attribute information and learning objective information, means for collecting user learning behavior data in a timely manner, and means for analyzing the user's understanding state based on the received information. This enables the provision of a learning plan optimized for each individual user and efficient management of learning progress.

[0278] "User attribute information" refers to basic personal information such as the user's age, grade level, and experience level.

[0279] "Learning objective information" refers to information that indicates the specific learning goals that the user is trying to achieve.

[0280] "User learning behavior data" refers to data that shows what activities a user performed during learning, including content viewed, response time, and accuracy rate.

[0281] "Analyzing comprehension" refers to evaluating the user's level of understanding of knowledge and skills based on collected user learning behavior data.

[0282] "Dynamically generating learning plans" refers to creating optimized learning content and schedules for each user in real time, based on analysis results.

[0283] "Receiving questions, generating, and presenting explanations" refers to the server processing inquiries from users and generating and providing users with relevant detailed information and explanations.

[0284] This invention is an educational platform that provides an individualized learning plan leveraging a generative AI model, aiming to maximize the learning efficiency of users. The server receives attribute information and learning goal information provided by users. This information includes basic information such as age, grade, specific learning goals, and known levels. The server utilizes the received information and uses a generative AI model to generate an initial learning plan.

[0285] When the user starts learning, the terminal collects the user's learning behavior data in real time. This includes details such as which content the user views, how much time is spent, and how accurately the user answers questions. The terminal transmits this data to the server, and the server analyzes the user's understanding state using an AI algorithm. Based on the analysis results, the server once again utilizes the generative AI model to dynamically update the learning plan according to the user's degree of understanding. As a result, new learning content and practice questions are presented.

[0286] Furthermore, when the user has doubts during learning, questions can be sent to the server on demand through the terminal. The server can use the generative AI model to analyze the question content and generate and present relevant explanations to provide the information needed by the user.

[0287] Taking a specific example, when a junior high school student user is learning algebra, the server presents basic algebra problems considering the grade and the ongoing learning field. As learning progresses, the plan is adjusted based on the user's answers. For example, if there are questions about the "quadratic formula", information explaining its derivation and usage in detail is generated and provided.

[0288] An example of a prompt in this system would be, "Based on the user's learning progress data, please generate the next recommended math problem." This prompt allows the generating AI model to dynamically create a corresponding learning plan.

[0289] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0290] Step 1:

[0291] The server receives attribute information and learning objective information from the user. As input, it receives basic information such as age, grade level, and learning objectives entered by the user on their device. Based on this data, it performs initial analysis and updates a database to understand the user's characteristics.

[0292] Step 2:

[0293] The server uses the generated AI model as a prompt based on the received attribute information to generate an initial learning plan. In this process, the prompt "Generate the optimal initial learning plan for the newly registered user" is used, and the AI ​​outputs a plan. The result is sent to the terminal and presented to the user.

[0294] Step 3:

[0295] Once a user begins learning, the device continuously collects data on their learning behavior. This data includes inputs such as the user's viewing history of learning content, response time, and accuracy rate. The device then organizes this data and sends it to the server.

[0296] Step 4:

[0297] The server analyzes the collected learning behavior data. Using an AI algorithm, it evaluates the user's understanding in real time. Based on the analysis results, it inputs the prompt message "Generate the next learning task based on the user's understanding" into the generating AI model and outputs a new learning plan.

[0298] Step 5:

[0299] The server sends the newly generated learning plan to the terminal and presents it to the user. This allows the user to work on continuously updated and optimal challenges.

[0300] Step 6:

[0301] If a user encounters a question during the learning process, they send it to the server via their device. The server receives the user's specific question as input. In response, the server uses a generative AI model to generate an explanation for the question.

[0302] Step 7:

[0303] The server sends the generated explanations back to the terminal, providing them to the user. This allows the user to quickly resolve their questions and continue learning.

[0304] (Application Example 1)

[0305] 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."

[0306] Traditional learning platforms suffer from a lack of real-time optimization to meet individual user learning needs and from a failure to provide a learning experience linked to the real-world physical environment. This limitation prevents users from making the most of the information resources available to them during their learning process.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0308] In this invention, the server includes means for receiving user attribute data and learning target data, means for collecting user learning activity data in real time, and means for analyzing the user's degree of understanding based on the received data. As a result, it becomes possible to provide a learning plan optimized for each user and visually present educational resources linked to the physical environment in the real world.

[0309] "User attribute data" refers to data indicating basic information about the user, such as age, grade, and learning goals.

[0310] "Learning target data" refers to information regarding specific learning purposes or goals that the user wishes to achieve.

[0311] "Learning activity data" refers to data indicating an activity history that includes what content the user has browsed, how much time has been spent, or how accurately the user has answered which questions.

[0312] "Means for analyzing the degree of understanding" refers to methods or technologies for evaluating the user's knowledge level and degree of understanding based on the user's learning activity data.

[0313] "Means for generating a learning plan" refers to methods or devices for proposing optimal learning content and methods according to the user's degree of understanding and learning goals.

[0314] "Means for providing the generated learning plan to the user" refers to methods or technologies for deploying the generated learning plan in a form that can be used by the user.

[0315] "On-demand tutor function" refers to a function that automatically generates and provides explanations and information necessary for the user's questions.

[0316] "Means of visually presenting information within a physical environment" refers to methods and devices for visually displaying user-related information in real-world space.

[0317] "Means of presenting educational resources based on location data" refers to methods and technologies for presenting optimal learning materials and information based on the user's current location.

[0318] The system for realizing this invention mainly consists of a server, a user terminal, and devices such as smart glasses. The server receives attribute data and learning objective data provided by the user and generates an initial learning plan. This learning plan is presented visually through the user's smart glasses, and the user's progress and learning activity data are collected in real time.

[0319] The server uses generated AI to analyze the user's understanding based on this activity data. This analysis is used to dynamically update the user's learning plan, recommending new content and practice exercises as needed. Furthermore, appropriate educational resources are visually presented based on the user's physical location data. For example, when a user moves to a specific learning area within a physical store, relevant learning materials and information are displayed on the smart glasses' screen.

[0320] Furthermore, an on-demand tutoring function is included to support users with questions that arise during their learning. Questions from users are sent to the server, where a generating AI analyzes them and instantly generates relevant explanations and supplementary materials.

[0321] As a concrete example, consider a scenario where a middle school student visits a physical store's learning space to study geometry. When this user searches for "recommended learning materials on triangle congruence conditions" using smart glasses, the system identifies the most relevant books and learning materials for that location and visually guides them on the display. Furthermore, when the user asks a question about "triangle congruence conditions," the generative AI model instantly generates an explanation of the derivation process.

[0322] An example of a prompt message would be: "Based on the user's attribute data, generate a list of learning materials best suited to the current learning objectives and provide detailed descriptions of them."

[0323] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0324] Step 1:

[0325] The server receives attribute data and learning objective data from the user's terminal. This includes the user's age, grade level, and learning objectives as input, and the server generates an initial learning plan based on this data. At this stage, it references similar past cases from the database to select a base learning pattern.

[0326] Step 2:

[0327] The user puts on smart glasses and enters a physical store. The device collects the user's location data and surrounding environmental information, and sends it to a server. As the user moves to a specific area within the store, the content displayed on the smart glasses dynamically changes. During this process, the glasses collect environmental data in real time using cameras and sensors.

[0328] Step 3:

[0329] Based on the received location data and user attribute information, the server uses a generative AI model to identify the most suitable learning resources for the user and sends visual instructions to the glasses. This process involves extracting learning materials that match the user's learning progress and objectives from a digital database, and then organizing and providing information about them.

[0330] Step 4:

[0331] If a user has a question during the learning process, they input the question through smart glasses. This question is sent from the device to a server for analysis. The AI ​​model analyzes the input question and generates relevant materials and explanations.

[0332] Step 5:

[0333] The server uses a generative AI model to generate appropriate explanations and supplementary information in response to user questions, and immediately sends them to the smart glasses. The output information includes video links and detailed explanations to enhance the user's understanding.

[0334] Step 6:

[0335] The device collects learning activity data, such as the learning materials used and the time spent studying, and continuously transmits it to the server. The server analyzes this data and evaluates the user's level of understanding. Based on this evaluation, the learning plan for the next step is dynamically updated, and the optimal route to achieving the goal is presented.

[0336] 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.

[0337] This invention provides a system that combines an emotion engine with an educational platform using generative AI to offer users more personalized learning support. This system collects user attribute data and learning goal data, and monitors user learning activity data and emotional data in real time. This allows for the creation and provision of an optimal learning plan that takes into account the user's level of understanding and emotional state.

[0338] Specifically, the server receives attribute data and learning objective data as basic information obtained from the user. Based on this information, an initial learning plan is generated on the server and presented to the user via the terminal. As the user progresses through the learning process, the terminal sends learning activity data and emotion data detected using the emotion engine to the server.

[0339] This emotional data includes the user's stress levels, level of interest, and level of concentration during learning, allowing for a detailed analysis of the user's state of mind. The server uses AI algorithms to comprehensively analyze this data and evaluate the user's current level of understanding and emotional state. Based on the evaluation results, the server dynamically adjusts the learning plan. For example, if it is determined that the user has lost interest in learning, the plan can be made more interactive or its difficulty level adjusted.

[0340] Furthermore, if a user has a question, it is sent from the device to the server, and the AI ​​generates a relevant explanation and responds. Here, responses based on the user's emotions are also taken into consideration, so for example, if the user is feeling stressed, content that promotes relaxation may be incorporated.

[0341] As a concrete example, let's consider a case where an elementary school student is learning programming for the first time. In the initial setup, a plan is provided to learn basic programming concepts based on the user's learning goals. If the emotion engine detects a decrease in the user's concentration during learning, the server adopts a strategy of changing the learning content into a game format to regain attention. Also, if the user asks a question such as "Why does this happen?", in addition to a simple answer, information on related topics that will pique the user's interest is also provided. In this way, the present invention allows users to enjoy a more effective and engaging learning experience.

[0342] The following describes the processing flow.

[0343] Step 1:

[0344] The server receives attribute data and learning objective data entered by the user. This includes information such as age, grade level, and learning goals.

[0345] Step 2:

[0346] The server generates an initial learning plan. This plan selects specific learning content and materials based on the user data received.

[0347] Step 3:

[0348] The device presents the user with an initial learning plan sent from the server. The user can then begin learning.

[0349] Step 4:

[0350] As the user progresses through the learning process, the device collects data on the user's learning activities. This includes learning time, content progress, and the results of answering questions.

[0351] Step 5:

[0352] The emotion engine acquires user emotional data through facial recognition and voice tone analysis. This data includes information such as stress levels, interest levels, and concentration levels.

[0353] Step 6:

[0354] The device sends collected learning activity data and emotional data to the server. This transmission occurs in real time, and the data is continuously updated.

[0355] Step 7:

[0356] The server uses AI algorithms to analyze this data and evaluate the user's level of understanding and emotional state. This allows for the measurement of learning effectiveness and user motivation.

[0357] Step 8:

[0358] The server adapts the learning plan based on the evaluation results. Specifically, if the user's concentration wavers, adjustments are made, such as incorporating game elements or suggesting breaks.

[0359] Step 9:

[0360] The device presents the user with a new learning plan and notifies them of the changes, allowing the user to proceed to the next learning step.

[0361] Step 10:

[0362] When a user has a question, they can send it to the server via their device. The question entered here is in text format.

[0363] Step 11:

[0364] The server uses AI to analyze user questions and generates and provides relevant explanations and learning materials to the user. In doing so, the server also considers the user's emotional state to select the most appropriate response.

[0365] Step 12:

[0366] The server collects user feedback data and uses it to generate the next learning plan. Based on the feedback, improvements are made to provide a more effective learning experience.

[0367] (Example 2)

[0368] 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".

[0369] Traditional educational platforms struggle to fully understand each user's individual learning state and emotions, and to provide personalized learning support accordingly. In particular, they cannot dynamically adjust learning plans in response to changes in user interests or improvements in comprehension, resulting in limited learning effectiveness.

[0370] 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.

[0371] In this invention, the server includes means for receiving basic user information and goal information, means for collecting user learning activity information and emotional information in real time, and means for analyzing the user's level of understanding and state based on the received information. This makes it possible to dynamically adjust the learning plan according to the user's individual emotional state and learning progress, and to provide optimal learning support.

[0372] "Basic information" refers to information that indicates the user's personal characteristics, including age, grade level, areas of expertise, and areas of weakness.

[0373] "Goal information" refers to information about the learning goals that the user wishes to achieve, and includes specific learning outcomes and progress targets.

[0374] "Learning activity information" refers to data related to the learning activities undertaken by the user, including the time spent learning, the number of completed assignments, and their progress.

[0375] "Emotional information" refers to information related to the user's emotional state, including data measuring the user's stress level, level of interest, and level of concentration.

[0376] "Comprehension level" is an evaluation metric that indicates how well a user understands the learning material, and is estimated from the user's accuracy rate and speed of response.

[0377] "State" refers to the mental and emotional state of a user during learning, and is a concept that includes levels of interest and stress based on emotional information.

[0378] "Dynamic adjustment" means modifying the learning plan in real time according to the user's level of understanding and status, and updating the content as needed to optimize learning support.

[0379] A "learning plan" is a plan that outlines the learning content and activities that a user should accomplish within a certain period of time, and includes specific learning topics and a sequence of content.

[0380] This invention is an educational system that provides personalized learning support to users using generative AI technology and emotion analysis technology. The server receives attribute information and learning goal information from the user and creates an initial learning plan based on this information. The terminal collects activity information and emotional information in real time during the user's learning activities. This emotional information is measured from the user's facial expressions, voice, operation speed, etc., and is data that indicates the user's stress level, interest level, and concentration level.

[0381] The server analyzes received learning activity and emotional information using a generative AI model to evaluate the user's understanding and emotional state. Based on this evaluation, the server dynamically adjusts the learning plan. This ensures that the learning content remains engaging for the user, maximizing learning effectiveness. Furthermore, if the user has questions, they can submit them through their device. The server then generates explanations using the generative AI in response to these questions, providing answers tailored to the user's emotional state.

[0382] As a concrete example, consider a scenario where an elementary school student is learning programming for the first time. The server receives the user's goal information and generates a learning plan to teach the basics of programming as an initial setup. However, if the server determines through the terminal that the user's concentration is waning, it can change the learning plan to be more interactive and gamified to re-engage the user.

[0383] An example of a prompt message might be, "Explain basic programming concepts in a fun way to an elementary school student who is learning programming for the first time." This system allows users to achieve effective learning tailored to their individual needs.

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The server receives basic information and learning objectives from the user. Input consists of personal information provided by the user via their device, such as age, grade level, and learning objectives. The server stores this information in a database and uses it as foundational data to generate an initial learning plan. Output is the foundational information for the initial learning plan.

[0387] Step 2:

[0388] The server generates an initial training plan based on the information received using a generative AI model. The input consists of basic information and training objectives. The generative AI model processes this data to generate a first training plan tailored to the user's individual needs. The output is the initial training plan presented to the user. This plan is provided to the user via the terminal.

[0389] Step 3:

[0390] The device collects learning activity information and emotional information in real time while the user is learning. Inputs include the user's actions, facial expressions, and voice during learning. The device uses sensors and microphones to collect learning time, answer status, and emotional data based on facial expression analysis. Outputs are sent to the server as learning activity information and emotional information.

[0391] Step 4:

[0392] The server analyzes the received learning activity and emotional information to evaluate the user's current level of understanding and emotional state. The input consists of collected learning activity and emotional information. Using an AI algorithm, the server comprehensively analyzes this data to determine the user's interests and level of understanding. The output is the evaluation result, which dynamically adjusts the user's learning plan.

[0393] Step 5:

[0394] The server dynamically adjusts the learning plan using a generated AI model based on the evaluation results. For example, if it determines that the user's concentration is waning, it might lower the difficulty level or increase the amount of interactive content. The input is the evaluation results, and the output is the adjusted learning plan. This new plan is then provided to the user again through the device.

[0395] Step 6:

[0396] If a user has a question during the learning process, they send the question to the server via their device. The input is the user's question. The server uses generative AI to generate a detailed and appropriate explanation for the question and sends it back to the user. The output is explanatory information tailored to the user's emotional state, which may include elements that promote relaxation.

[0397] (Application Example 2)

[0398] 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."

[0399] Conventional online learning platforms often provide a uniform learning experience without considering the user's emotional state, which has led to decreased learning efficiency and motivation. Furthermore, simply providing plans based on comprehension levels makes it difficult to flexibly respond to the user's current emotions and interests. This invention aims to solve these problems and provide a more personalized learning experience.

[0400] 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.

[0401] In this invention, the server includes means for receiving user attribute information and purpose information, means for collecting user activity information in real time, means for evaluating the learner's understanding based on the received information, means for generating a plan based on the learner's understanding, means for providing the generated plan to the user, means for receiving inquiries from the user and generating and providing relevant explanations, and means for analyzing the user's emotional state and providing recommendation information accordingly. This makes it possible to provide a dynamic and flexible learning plan that simultaneously considers the user's level of understanding and emotional state.

[0402] "User attribute information" refers to personal characteristics and background information about users, including data such as age, gender, occupation, and learning experience.

[0403] "Purpose information" refers to information that indicates the learning goals or objectives that the user wishes to achieve, or their current areas of interest.

[0404] "Activity information" refers to data on various actions taken by users on the platform, including content viewed, questions answered, and access frequency.

[0405] "Participant comprehension level" refers to information indicating how well users understand the material they have learned, and is evaluated based on factors such as grades and the accuracy of answers.

[0406] "Means for generating plans" refer to methods and functions for creating efficient and effective learning plans based on the user's understanding and attribute information.

[0407] "User inquiries" refer to questions and requests that users send to the system when they have questions while learning.

[0408] "Means for generating and providing relevant explanations" refers to methods and functions for generating appropriate and easy-to-understand explanations in response to user inquiries and informing users of the results.

[0409] "User emotional state" refers to information that captures the mental and emotional state exhibited by users during learning, and includes, for example, excitement, concentration, and boredom.

[0410] "Means of providing recommendation information" refers to methods or functions for suggesting appropriate products, services, or learning content that are tailored to the user's emotional state.

[0411] This invention is implemented by a system consisting of three elements: a server, a terminal, and a user.

[0412] The server generates an initial learning plan using attribute and objective information obtained from the user. This plan is then provided to the user via the terminal. The server analyzes the received user activity and sentiment information in real time, continuously evaluating the user's understanding and emotional state. This allows the server to dynamically adjust the learning plan as needed, providing an optimal learning environment.

[0413] The device monitors the user's learning activity and sends activity information and emotional state data acquired through an emotion recognition library to the server. This process utilizes a system equipped with a generative AI model to analyze complex datasets, including the user's emotional data.

[0414] If a user has questions during the learning process, they can submit them through their device. The server uses a generative AI model to generate appropriate explanations for these inquiries, taking into account the user's emotional state when providing answers.

[0415] As a concrete example, imagine a scenario where an elementary school student is learning programming for the first time in a virtual store. If the user shows signs of boredom during the learning process, the system will automatically adjust the plan to present more interactive learning materials to capture their attention. Also, if the user asks a question about programming, such as "Why does this result occur?", the AI ​​will provide an easy-to-understand explanation on the spot, along with information on related topics to further increase their interest.

[0416] Examples of prompts for a generative AI model:

[0417] "Please provide information that clearly explains the programming learning materials displayed by the user, based on other reference materials and the experiences of other learners."

[0418] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0419] Step 1:

[0420] The server receives attribute and purpose information from the user. The received data is stored in a database and used as input when generating an initial learning plan. Based on this information, suitable educational content and starting guidelines are formulated.

[0421] Step 2:

[0422] The device collects user activity information in real time and sends it to the server. This activity information includes the user's progress and behavior logs, which are used to track learning progress. The device also uses its camera and input devices to collect additional data necessary for evaluating emotional states.

[0423] Step 3:

[0424] The server uses received activity information and sentiment data to simultaneously evaluate the user's understanding and emotional state. A generative AI model is used to process the input data, analyzing the user's level of understanding and emotional tendencies. The optimized evaluation results are then output.

[0425] Step 4:

[0426] The server dynamically adjusts the learning plan based on the evaluation results and provides the updated plan to the device. This adjustment includes selecting learning materials tailored to the user's interests and understanding, and changing the difficulty level. This process ensures that users can always continue learning in an optimal state.

[0427] Step 5:

[0428] When a user enters a question during the learning process, the device sends the inquiry to the server. The server uses a generative AI model to generate an appropriate explanation for the question and sends it to the device. The generated explanation takes the user's emotional state into consideration and is presented in an easy-to-understand and relaxed format.

[0429] Step 6:

[0430] The server analyzes the user's emotional state and provides corresponding recommendations to the device. For example, if interest is waning, new interactive content will be recommended. This helps maintain the user's learning motivation.

[0431] 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.

[0432] 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 those described above. 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 shown 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.

[0433] 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.

[0434] [Third Embodiment]

[0435] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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".

[0447] This invention is an educational platform that provides personalized learning plans utilizing generative AI, aiming to maximize user learning efficiency. The system collects user attribute data and learning goal data, and monitors user learning activity data in real time. This enables the provision of learning plans optimized for each individual user.

[0448] Specifically, the server receives attribute data and learning objective data initially provided by the user. This data includes basic information such as the user's age, grade level, specific learning objectives, and known level. Based on this data, the server generates an initial learning plan and presents it to the user via the device.

[0449] As the user progresses through the learning process, the device continuously collects activity data and sends it to the server. This data includes information such as what content the user views, how much time they spend on it, and how accurately they answer each question. The server receives this data and uses AI algorithms to analyze the user's understanding in real time. Based on this analysis, the server dynamically updates the user's learning plan and recommends new content and practice problems.

[0450] Furthermore, if users encounter questions during their learning process, they can utilize the on-demand tutoring function via their device. When a user sends a question to the server, AI analyzes the question and generates and provides relevant explanations and supplementary materials. This allows users to access information to deepen their understanding at any time.

[0451] To give a concrete example, suppose a middle school student is learning the mathematical algebra. Initially, the server provides basic algebra exercises, taking into account the user's grade level and the field they are studying. As the user progresses, if they achieve a high success rate, the server adds more difficult problems according to their progress. Conversely, if they make many mistakes on a particular concept, the server suggests video explanations or additional practice exercises to deepen their understanding of that area. If the user asks about the quadratic formula, the server uses AI to generate and immediately provide an explanation of the derivation process. In this way, the system provides an effective learning experience optimized for the user.

[0452] The following describes the processing flow.

[0453] Step 1:

[0454] The server receives attribute data and learning objective data entered by the user. This allows it to obtain basic information such as the user's grade level, field of study, and learning objectives.

[0455] Step 2:

[0456] The server generates an initial learning plan based on the received attribute data and goals. During this process, it selects the most suitable learning materials for the user from its existing database of educational content.

[0457] Step 3:

[0458] The terminal displays the learning plan sent from the server to the user and provides an interface for starting the learning process.

[0459] Step 4:

[0460] As the user progresses through the learning process, the device collects data on the user's learning activities. This data includes the time spent learning, the results of problems solved, and the content viewed.

[0461] Step 5:

[0462] The device sequentially transmits the collected learning activity data to the server. This data transmission occurs in real time and periodically.

[0463] Step 6:

[0464] The server analyzes the received learning activity data using an AI algorithm to evaluate the user's level of understanding. Analysis items include the accuracy rate, response speed, and whether or not repeated learning was performed.

[0465] Step 7:

[0466] The server updates the user's learning plan based on the analysis results. Specific updates include adjusting the difficulty level, providing additional practice problems, and recommending new content.

[0467] Step 8:

[0468] The device presents the user with a new learning plan and encourages continued learning. Notification features can also alert the user to begin the next step.

[0469] Step 9:

[0470] If a user has a question during their learning process, they can use the on-demand tutoring function via their device to send their question to the server. The question is in text format, entered by the user.

[0471] Step 10:

[0472] The server analyzes user questions and uses AI to generate relevant explanations and supplementary materials. The generated explanations are intended to deepen the user's understanding.

[0473] Step 11:

[0474] The server sends the generated explanations and materials back to the terminal, where they are displayed to the user. The user can then use this information to resolve any questions and continue learning.

[0475] Step 12:

[0476] The device collects user feedback and sends that data to the server. The feedback concerns the usefulness of the content and learning satisfaction.

[0477] Step 13:

[0478] The server aims to use feedback data to generate the next learning plan, thereby providing an even more customized learning experience.

[0479] (Example 1)

[0480] 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."

[0481] Traditional education systems have struggled to provide personalized learning experiences and maximize user learning efficiency. In particular, there is a growing need to improve the quality of learning by providing dynamic learning plans and immediate feedback tailored to the user's progress.

[0482] 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.

[0483] In this invention, the server includes means for receiving user attribute information and learning objective information, means for collecting user learning behavior data in a timely manner, and means for analyzing the user's understanding state based on the received information. This enables the provision of a learning plan optimized for each individual user and efficient management of learning progress.

[0484] "User attribute information" refers to basic personal information such as the user's age, grade level, and experience level.

[0485] "Learning objective information" refers to information that indicates the specific learning goals that the user is trying to achieve.

[0486] "User learning behavior data" refers to data that shows what activities a user performed during learning, including content viewed, response time, and accuracy rate.

[0487] "Analyzing comprehension" refers to evaluating the user's level of understanding of knowledge and skills based on collected user learning behavior data.

[0488] "Dynamically generating learning plans" refers to creating optimized learning content and schedules for each user in real time, based on analysis results.

[0489] "Receiving questions, generating and presenting explanations" refers to processing user inquiries on a server, generating relevant detailed information and explanations, and providing them to the user.

[0490] This invention is an educational platform that provides personalized learning plans utilizing a generative AI model, aiming to maximize user learning efficiency. The server receives attribute information and learning objective information provided by the user. This information includes basic information such as age, grade level, specific learning objectives, and known level. The server utilizes this received information and generates an initial learning plan using a generative AI model.

[0491] Once a user begins learning, the device collects real-time data on their learning behavior. This includes details such as what content the user views, how much time they spend on it, and how accurately they answer questions. The device sends this data to a server, which uses an AI algorithm to analyze the user's understanding. Based on the analysis, the server reuses the generative AI model to dynamically update the learning plan according to the user's level of understanding. This then presents new learning content and practice problems.

[0492] Furthermore, if a user encounters a question during their learning process, they can send it to the server on demand via their device. The server can then use a generative AI model to analyze the question, generate relevant explanations, and present them, providing the user with the information they need.

[0493] For example, if a middle school student is learning algebra, the server will present basic algebra problems, taking into account their grade level and the subject they are currently studying. As the learning progresses, the plan will be adjusted based on the user's answers. For instance, if there is a question about the quadratic formula, the server will generate and provide information that explains its derivation and application in detail.

[0494] An example of a prompt in this system would be, "Based on the user's learning progress data, please generate the next recommended math problem." This prompt allows the generating AI model to dynamically create a corresponding learning plan.

[0495] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0496] Step 1:

[0497] The server receives attribute information and learning objective information from the user. As input, it receives basic information such as age, grade level, and learning objectives entered by the user on their device. Based on this data, it performs initial analysis and updates a database to understand the user's characteristics.

[0498] Step 2:

[0499] The server uses the generated AI model as a prompt based on the received attribute information to generate an initial learning plan. In this process, the prompt "Generate the optimal initial learning plan for the newly registered user" is used, and the AI ​​outputs a plan. The result is sent to the terminal and presented to the user.

[0500] Step 3:

[0501] Once a user begins learning, the device continuously collects data on their learning behavior. This data includes inputs such as the user's viewing history of learning content, response time, and accuracy rate. The device then organizes this data and sends it to the server.

[0502] Step 4:

[0503] The server analyzes the collected learning behavior data. Using an AI algorithm, it evaluates the user's understanding in real time. Based on the analysis results, it inputs the prompt message "Generate the next learning task based on the user's understanding" into the generating AI model and outputs a new learning plan.

[0504] Step 5:

[0505] The server sends the newly generated learning plan to the terminal and presents it to the user. This allows the user to work on continuously updated and optimal challenges.

[0506] Step 6:

[0507] If a user encounters a question during the learning process, they send it to the server via their device. The server receives the user's specific question as input. In response, the server uses a generative AI model to generate an explanation for the question.

[0508] Step 7:

[0509] The server sends the generated explanations back to the terminal, providing them to the user. This allows the user to quickly resolve their questions and continue learning.

[0510] (Application Example 1)

[0511] 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."

[0512] Traditional learning platforms suffer from a lack of real-time optimization to meet individual user learning needs and from a failure to provide a learning experience linked to the real-world physical environment. This limitation prevents users from making the most of the information resources available to them during their learning process.

[0513] 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.

[0514] In this invention, the server includes means for receiving user attribute data and learning objective data, means for collecting user learning activity data in real time, and means for analyzing the user's level of understanding based on the received data. This enables the provision of a learning plan optimized for the user and the visual presentation of educational resources linked to the real-world physical environment.

[0515] "User attribute data" refers to data that contains basic information about the user, such as age, grade level, and learning goals.

[0516] "Learning objective data" refers to information about the specific learning goals and objectives that the user wants to achieve.

[0517] "Learning activity data" refers to data that shows a user's activity history, including what content they viewed, how much time they spent on it, and how accurately they answered each question.

[0518] "Means of analyzing comprehension" refers to methods and technologies for evaluating a user's knowledge level and comprehension based on their learning activity data.

[0519] "Means for generating learning plans" refers to methods and devices that suggest optimal learning content and methods according to the user's level of understanding and learning goals.

[0520] "Means of providing the generated learning plan to the user" refers to the methods and technologies for deploying the generated learning plan in a format that the user can use.

[0521] The "On-Demand Tutor Function" refers to a feature that automatically generates and provides necessary explanations and information in response to user questions.

[0522] "Means of visually presenting information within a physical environment" refers to methods and devices for visually displaying user-related information in real-world space.

[0523] "Means of presenting educational resources based on location data" refers to methods and technologies for presenting optimal learning materials and information based on the user's current location.

[0524] The system for realizing this invention mainly consists of a server, a user terminal, and devices such as smart glasses. The server receives attribute data and learning objective data provided by the user and generates an initial learning plan. This learning plan is presented visually through the user's smart glasses, and the user's progress and learning activity data are collected in real time.

[0525] The server uses generated AI to analyze the user's understanding based on this activity data. This analysis is used to dynamically update the user's learning plan, recommending new content and practice exercises as needed. Furthermore, appropriate educational resources are visually presented based on the user's physical location data. For example, when a user moves to a specific learning area within a physical store, relevant learning materials and information are displayed on the smart glasses' screen.

[0526] Furthermore, an on-demand tutoring function is included to support users with questions that arise during their learning. Questions from users are sent to the server, where a generating AI analyzes them and instantly generates relevant explanations and supplementary materials.

[0527] As a concrete example, consider a scenario where a middle school student visits a physical store's learning space to study geometry. When this user searches for "recommended learning materials on triangle congruence conditions" using smart glasses, the system identifies the most relevant books and learning materials for that location and visually guides them on the display. Furthermore, when the user asks a question about "triangle congruence conditions," the generative AI model instantly generates an explanation of the derivation process.

[0528] An example of a prompt message would be: "Based on the user's attribute data, generate a list of learning materials best suited to the current learning objectives and provide detailed descriptions of them."

[0529] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0530] Step 1:

[0531] The server receives attribute data and learning objective data from the user's terminal. This includes the user's age, grade level, and learning objectives as input, and the server generates an initial learning plan based on this data. At this stage, it references similar past cases from the database to select a base learning pattern.

[0532] Step 2:

[0533] The user puts on smart glasses and enters a physical store. The device collects the user's location data and surrounding environmental information, and sends it to a server. As the user moves to a specific area within the store, the content displayed on the smart glasses dynamically changes. During this process, the glasses collect environmental data in real time using cameras and sensors.

[0534] Step 3:

[0535] Based on the received location data and user attribute information, the server uses a generative AI model to identify the most suitable learning resources for the user and sends visual instructions to the glasses. This process involves extracting learning materials that match the user's learning progress and objectives from a digital database, and then organizing and providing information about them.

[0536] Step 4:

[0537] If a user has a question during the learning process, they input the question through smart glasses. This question is sent from the device to a server for analysis. The AI ​​model analyzes the input question and generates relevant materials and explanations.

[0538] Step 5:

[0539] The server uses a generative AI model to generate appropriate explanations and supplementary information in response to user questions, and immediately sends them to the smart glasses. The output information includes video links and detailed explanations to enhance the user's understanding.

[0540] Step 6:

[0541] The device collects learning activity data, such as the learning materials used and the time spent studying, and continuously transmits it to the server. The server analyzes this data and evaluates the user's level of understanding. Based on this evaluation, the learning plan for the next step is dynamically updated, and the optimal route to achieving the goal is presented.

[0542] 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.

[0543] This invention provides a system that combines an emotion engine with an educational platform using generative AI to offer users more personalized learning support. This system collects user attribute data and learning goal data, and monitors user learning activity data and emotional data in real time. This allows for the creation and provision of an optimal learning plan that takes into account the user's level of understanding and emotional state.

[0544] Specifically, the server receives attribute data and learning objective data as basic information obtained from the user. Based on this information, an initial learning plan is generated on the server and presented to the user via the terminal. As the user progresses through the learning process, the terminal sends learning activity data and emotion data detected using the emotion engine to the server.

[0545] This emotional data includes the user's stress levels, level of interest, and level of concentration during learning, allowing for a detailed analysis of the user's state of mind. The server uses AI algorithms to comprehensively analyze this data and evaluate the user's current level of understanding and emotional state. Based on the evaluation results, the server dynamically adjusts the learning plan. For example, if it is determined that the user has lost interest in learning, the plan can be made more interactive or its difficulty level adjusted.

[0546] Furthermore, if a user has a question, it is sent from the device to the server, and the AI ​​generates a relevant explanation and responds. Here, responses based on the user's emotions are also taken into consideration, so for example, if the user is feeling stressed, content that promotes relaxation may be incorporated.

[0547] As a concrete example, let's consider a case where an elementary school student is learning programming for the first time. In the initial setup, a plan is provided to learn basic programming concepts based on the user's learning goals. If the emotion engine detects a decrease in the user's concentration during learning, the server adopts a strategy of changing the learning content into a game format to regain attention. Also, if the user asks a question such as "Why does this happen?", in addition to a simple answer, information on related topics that will pique the user's interest is also provided. In this way, the present invention allows users to enjoy a more effective and engaging learning experience.

[0548] The following describes the processing flow.

[0549] Step 1:

[0550] The server receives attribute data and learning objective data entered by the user. This includes information such as age, grade level, and learning goals.

[0551] Step 2:

[0552] The server generates an initial learning plan. This plan selects specific learning content and materials based on the user data received.

[0553] Step 3:

[0554] The device presents the user with an initial learning plan sent from the server. The user can then begin learning.

[0555] Step 4:

[0556] As the user progresses through the learning process, the device collects data on the user's learning activities. This includes learning time, content progress, and the results of answering questions.

[0557] Step 5:

[0558] The emotion engine acquires user emotional data through facial recognition and voice tone analysis. This data includes information such as stress levels, interest levels, and concentration levels.

[0559] Step 6:

[0560] The device sends collected learning activity data and emotional data to the server. This transmission occurs in real time, and the data is continuously updated.

[0561] Step 7:

[0562] The server uses AI algorithms to analyze this data and evaluate the user's level of understanding and emotional state. This allows for the measurement of learning effectiveness and user motivation.

[0563] Step 8:

[0564] The server adapts the learning plan based on the evaluation results. Specifically, if the user's concentration wavers, adjustments are made, such as incorporating game elements or suggesting breaks.

[0565] Step 9:

[0566] The device presents the user with a new learning plan and notifies them of the changes, allowing the user to proceed to the next learning step.

[0567] Step 10:

[0568] When a user has a question, they can send it to the server via their device. The question entered here is in text format.

[0569] Step 11:

[0570] The server uses AI to analyze user questions and generates and provides relevant explanations and learning materials to the user. In doing so, the server also considers the user's emotional state to select the most appropriate response.

[0571] Step 12:

[0572] The server collects user feedback data and uses it to generate the next learning plan. Based on the feedback, improvements are made to provide a more effective learning experience.

[0573] (Example 2)

[0574] 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."

[0575] Traditional educational platforms struggle to fully understand each user's individual learning state and emotions, and to provide personalized learning support accordingly. In particular, they cannot dynamically adjust learning plans in response to changes in user interests or improvements in comprehension, resulting in limited learning effectiveness.

[0576] 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.

[0577] In this invention, the server includes means for receiving basic user information and goal information, means for collecting user learning activity information and emotional information in real time, and means for analyzing the user's level of understanding and state based on the received information. This makes it possible to dynamically adjust the learning plan according to the user's individual emotional state and learning progress, and to provide optimal learning support.

[0578] "Basic information" refers to information that indicates the user's personal characteristics, including age, grade level, areas of expertise, and areas of weakness.

[0579] "Goal information" refers to information about the learning goals that the user wishes to achieve, and includes specific learning outcomes and progress targets.

[0580] "Learning activity information" refers to data related to the learning activities undertaken by the user, including the time spent learning, the number of completed assignments, and their progress.

[0581] "Emotional information" refers to information related to the user's emotional state, including data measuring the user's stress level, level of interest, and level of concentration.

[0582] "Comprehension level" is an evaluation metric that indicates how well a user understands the learning material, and is estimated from the user's accuracy rate and speed of response.

[0583] "State" refers to the mental and emotional state of a user during learning, and is a concept that includes levels of interest and stress based on emotional information.

[0584] "Dynamic adjustment" means modifying the learning plan in real time according to the user's level of understanding and status, and updating the content as needed to optimize learning support.

[0585] A "learning plan" is a plan that outlines the learning content and activities that a user should accomplish within a certain period of time, and includes specific learning topics and a sequence of content.

[0586] This invention is an educational system that provides personalized learning support to users using generative AI technology and emotion analysis technology. The server receives attribute information and learning goal information from the user and creates an initial learning plan based on this information. The terminal collects activity information and emotional information in real time during the user's learning activities. This emotional information is measured from the user's facial expressions, voice, operation speed, etc., and is data that indicates the user's stress level, interest level, and concentration level.

[0587] The server analyzes received learning activity and emotional information using a generative AI model to evaluate the user's understanding and emotional state. Based on this evaluation, the server dynamically adjusts the learning plan. This ensures that the learning content remains engaging for the user, maximizing learning effectiveness. Furthermore, if the user has questions, they can submit them through their device. The server then generates explanations using the generative AI in response to these questions, providing answers tailored to the user's emotional state.

[0588] As a concrete example, consider a scenario where an elementary school student is learning programming for the first time. The server receives the user's goal information and generates a learning plan to teach the basics of programming as an initial setup. However, if the server determines through the terminal that the user's concentration is waning, it can change the learning plan to be more interactive and gamified to re-engage the user.

[0589] An example of a prompt message might be, "Explain basic programming concepts in a fun way to an elementary school student who is learning programming for the first time." This system allows users to achieve effective learning tailored to their individual needs.

[0590] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0591] Step 1:

[0592] The server receives basic information and learning objectives from the user. Input consists of personal information provided by the user via their device, such as age, grade level, and learning objectives. The server stores this information in a database and uses it as foundational data to generate an initial learning plan. Output is the foundational information for the initial learning plan.

[0593] Step 2:

[0594] The server generates an initial training plan based on the information received using a generative AI model. The input consists of basic information and training objectives. The generative AI model processes this data to generate a first training plan tailored to the user's individual needs. The output is the initial training plan presented to the user. This plan is provided to the user via the terminal.

[0595] Step 3:

[0596] The device collects learning activity information and emotional information in real time while the user is learning. Inputs include the user's actions, facial expressions, and voice during learning. The device uses sensors and microphones to collect learning time, answer status, and emotional data based on facial expression analysis. Outputs are sent to the server as learning activity information and emotional information.

[0597] Step 4:

[0598] The server analyzes the received learning activity and emotional information to evaluate the user's current level of understanding and emotional state. The input consists of collected learning activity and emotional information. Using an AI algorithm, the server comprehensively analyzes this data to determine the user's interests and level of understanding. The output is the evaluation result, which dynamically adjusts the user's learning plan.

[0599] Step 5:

[0600] The server dynamically adjusts the learning plan using a generated AI model based on the evaluation results. For example, if it determines that the user's concentration is waning, it might lower the difficulty level or increase the amount of interactive content. The input is the evaluation results, and the output is the adjusted learning plan. This new plan is then provided to the user again through the device.

[0601] Step 6:

[0602] If a user has a question during the learning process, they send the question to the server via their device. The input is the user's question. The server uses generative AI to generate a detailed and appropriate explanation for the question and sends it back to the user. The output is explanatory information tailored to the user's emotional state, which may include elements that promote relaxation.

[0603] (Application Example 2)

[0604] 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."

[0605] Conventional online learning platforms often provide a uniform learning experience without considering the user's emotional state, which has led to decreased learning efficiency and motivation. Furthermore, simply providing plans based on comprehension levels makes it difficult to flexibly respond to the user's current emotions and interests. This invention aims to solve these problems and provide a more personalized learning experience.

[0606] 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.

[0607] In this invention, the server includes means for receiving user attribute information and purpose information, means for collecting user activity information in real time, means for evaluating the learner's understanding based on the received information, means for generating a plan based on the learner's understanding, means for providing the generated plan to the user, means for receiving inquiries from the user and generating and providing relevant explanations, and means for analyzing the user's emotional state and providing recommendation information accordingly. This makes it possible to provide a dynamic and flexible learning plan that simultaneously considers the user's level of understanding and emotional state.

[0608] "User attribute information" refers to personal characteristics and background information about users, including data such as age, gender, occupation, and learning experience.

[0609] "Purpose information" refers to information that indicates the learning goals or objectives that the user wishes to achieve, or their current areas of interest.

[0610] "Activity information" refers to data on various actions taken by users on the platform, including content viewed, questions answered, and access frequency.

[0611] "Participant comprehension level" refers to information indicating how well users understand the material they have learned, and is evaluated based on factors such as grades and the accuracy of answers.

[0612] "Means for generating plans" refer to methods and functions for creating efficient and effective learning plans based on the user's understanding and attribute information.

[0613] "User inquiries" refer to questions and requests that users send to the system when they have questions while learning.

[0614] "Means for generating and providing relevant explanations" refers to methods and functions for generating appropriate and easy-to-understand explanations in response to user inquiries and informing users of the results.

[0615] "User emotional state" refers to information that captures the mental and emotional state exhibited by users during learning, and includes, for example, excitement, concentration, and boredom.

[0616] "Means of providing recommendation information" refers to methods or functions for suggesting appropriate products, services, or learning content that are tailored to the user's emotional state.

[0617] This invention is implemented by a system consisting of three elements: a server, a terminal, and a user.

[0618] The server generates an initial learning plan using attribute and objective information obtained from the user. This plan is then provided to the user via the terminal. The server analyzes the received user activity and sentiment information in real time, continuously evaluating the user's understanding and emotional state. This allows the server to dynamically adjust the learning plan as needed, providing an optimal learning environment.

[0619] The device monitors the user's learning activity and sends activity information and emotional state data acquired through an emotion recognition library to the server. This process utilizes a system equipped with a generative AI model to analyze complex datasets, including the user's emotional data.

[0620] If a user has questions during the learning process, they can submit them through their device. The server uses a generative AI model to generate appropriate explanations for these inquiries, taking into account the user's emotional state when providing answers.

[0621] As a concrete example, imagine a scenario where an elementary school student is learning programming for the first time in a virtual store. If the user shows signs of boredom during the learning process, the system will automatically adjust the plan to present more interactive learning materials to capture their attention. Also, if the user asks a question about programming, such as "Why does this result occur?", the AI ​​will provide an easy-to-understand explanation on the spot, along with information on related topics to further increase their interest.

[0622] Examples of prompts for a generative AI model:

[0623] "Please provide information that clearly explains the programming learning materials displayed by the user, based on other reference materials and the experiences of other learners."

[0624] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0625] Step 1:

[0626] The server receives attribute and purpose information from the user. The received data is stored in a database and used as input when generating an initial learning plan. Based on this information, suitable educational content and starting guidelines are formulated.

[0627] Step 2:

[0628] The device collects user activity information in real time and sends it to the server. This activity information includes the user's progress and behavior logs, which are used to track learning progress. The device also uses its camera and input devices to collect additional data necessary for evaluating emotional states.

[0629] Step 3:

[0630] The server uses received activity information and sentiment data to simultaneously evaluate the user's understanding and emotional state. A generative AI model is used to process the input data, analyzing the user's level of understanding and emotional tendencies. The optimized evaluation results are then output.

[0631] Step 4:

[0632] The server dynamically adjusts the learning plan based on the evaluation results and provides the updated plan to the device. This adjustment includes selecting learning materials tailored to the user's interests and understanding, and changing the difficulty level. This process ensures that users can always continue learning in an optimal state.

[0633] Step 5:

[0634] When a user enters a question during the learning process, the device sends the inquiry to the server. The server uses a generative AI model to generate an appropriate explanation for the question and sends it to the device. The generated explanation takes the user's emotional state into consideration and is presented in an easy-to-understand and relaxed format.

[0635] Step 6:

[0636] The server analyzes the user's emotional state and provides corresponding recommendations to the device. For example, if interest is waning, new interactive content will be recommended. This helps maintain the user's learning motivation.

[0637] 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.

[0638] 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 those described above. 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 shown 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.

[0639] 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.

[0640] [Fourth Embodiment]

[0641] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0642] 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.

[0643] 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).

[0644] 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.

[0645] 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.

[0646] 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).

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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".

[0654] This invention is an educational platform that provides personalized learning plans utilizing generative AI, aiming to maximize user learning efficiency. The system collects user attribute data and learning goal data, and monitors user learning activity data in real time. This enables the provision of learning plans optimized for each individual user.

[0655] Specifically, the server receives attribute data and learning objective data initially provided by the user. This data includes basic information such as the user's age, grade level, specific learning objectives, and known level. Based on this data, the server generates an initial learning plan and presents it to the user via the device.

[0656] As the user progresses through the learning process, the device continuously collects activity data and sends it to the server. This data includes information such as what content the user views, how much time they spend on it, and how accurately they answer each question. The server receives this data and uses AI algorithms to analyze the user's understanding in real time. Based on this analysis, the server dynamically updates the user's learning plan and recommends new content and practice problems.

[0657] Furthermore, if users encounter questions during their learning process, they can utilize the on-demand tutoring function via their device. When a user sends a question to the server, AI analyzes the question and generates and provides relevant explanations and supplementary materials. This allows users to access information to deepen their understanding at any time.

[0658] To give a concrete example, suppose a middle school student is learning the mathematical algebra. Initially, the server provides basic algebra exercises, taking into account the user's grade level and the field they are studying. As the user progresses, if they achieve a high success rate, the server adds more difficult problems according to their progress. Conversely, if they make many mistakes on a particular concept, the server suggests video explanations or additional practice exercises to deepen their understanding of that area. If the user asks about the quadratic formula, the server uses AI to generate and immediately provide an explanation of the derivation process. In this way, the system provides an effective learning experience optimized for the user.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] The server receives attribute data and learning objective data entered by the user. This allows it to obtain basic information such as the user's grade level, field of study, and learning objectives.

[0662] Step 2:

[0663] The server generates an initial learning plan based on the received attribute data and goals. During this process, it selects the most suitable learning materials for the user from its existing database of educational content.

[0664] Step 3:

[0665] The terminal displays the learning plan sent from the server to the user and provides an interface for starting the learning process.

[0666] Step 4:

[0667] As the user progresses through the learning process, the device collects data on the user's learning activities. This data includes the time spent learning, the results of problems solved, and the content viewed.

[0668] Step 5:

[0669] The device sequentially transmits the collected learning activity data to the server. This data transmission occurs in real time and periodically.

[0670] Step 6:

[0671] The server analyzes the received learning activity data using an AI algorithm to evaluate the user's level of understanding. Analysis items include the accuracy rate, response speed, and whether or not repeated learning was performed.

[0672] Step 7:

[0673] The server updates the user's learning plan based on the analysis results. Specific updates include adjusting the difficulty level, providing additional practice problems, and recommending new content.

[0674] Step 8:

[0675] The device presents the user with a new learning plan and encourages continued learning. Notification features can also alert the user to begin the next step.

[0676] Step 9:

[0677] If a user has a question during their learning process, they can use the on-demand tutoring function via their device to send their question to the server. The question is in text format, entered by the user.

[0678] Step 10:

[0679] The server analyzes user questions and uses AI to generate relevant explanations and supplementary materials. The generated explanations are intended to deepen the user's understanding.

[0680] Step 11:

[0681] The server sends the generated explanations and materials back to the terminal, where they are displayed to the user. The user can then use this information to resolve any questions and continue learning.

[0682] Step 12:

[0683] The device collects user feedback and sends that data to the server. The feedback concerns the usefulness of the content and learning satisfaction.

[0684] Step 13:

[0685] The server aims to use feedback data to generate the next learning plan, thereby providing an even more customized learning experience.

[0686] (Example 1)

[0687] 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".

[0688] Traditional education systems have struggled to provide personalized learning experiences and maximize user learning efficiency. In particular, there is a growing need to improve the quality of learning by providing dynamic learning plans and immediate feedback tailored to the user's progress.

[0689] 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.

[0690] In this invention, the server includes means for receiving user attribute information and learning objective information, means for collecting user learning behavior data in a timely manner, and means for analyzing the user's understanding state based on the received information. This enables the provision of a learning plan optimized for each individual user and efficient management of learning progress.

[0691] "User attribute information" refers to basic personal information such as the user's age, grade level, and experience level.

[0692] "Learning objective information" refers to information that indicates the specific learning goals that the user is trying to achieve.

[0693] "User learning behavior data" refers to data that shows what activities a user performed during learning, including content viewed, response time, and accuracy rate.

[0694] "Analyzing comprehension" refers to evaluating the user's level of understanding of knowledge and skills based on collected user learning behavior data.

[0695] "Dynamically generating learning plans" refers to creating optimized learning content and schedules for each user in real time, based on analysis results.

[0696] "Receiving questions, generating and presenting explanations" refers to processing user inquiries on a server, generating relevant detailed information and explanations, and providing them to the user.

[0697] This invention is an educational platform that provides personalized learning plans utilizing a generative AI model, aiming to maximize user learning efficiency. The server receives attribute information and learning objective information provided by the user. This information includes basic information such as age, grade level, specific learning objectives, and known level. The server utilizes this received information and generates an initial learning plan using a generative AI model.

[0698] Once a user begins learning, the device collects real-time data on their learning behavior. This includes details such as what content the user views, how much time they spend on it, and how accurately they answer questions. The device sends this data to a server, which uses an AI algorithm to analyze the user's understanding. Based on the analysis, the server reuses the generative AI model to dynamically update the learning plan according to the user's level of understanding. This then presents new learning content and practice problems.

[0699] Furthermore, if a user encounters a question during their learning process, they can send it to the server on demand via their device. The server can then use a generative AI model to analyze the question, generate relevant explanations, and present them, providing the user with the information they need.

[0700] For example, if a middle school student is learning algebra, the server will present basic algebra problems, taking into account their grade level and the subject they are currently studying. As the learning progresses, the plan will be adjusted based on the user's answers. For instance, if there is a question about the quadratic formula, the server will generate and provide information that explains its derivation and application in detail.

[0701] An example of a prompt in this system would be, "Based on the user's learning progress data, please generate the next recommended math problem." This prompt allows the generating AI model to dynamically create a corresponding learning plan.

[0702] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0703] Step 1:

[0704] The server receives attribute information and learning objective information from the user. As input, it receives basic information such as age, grade level, and learning objectives entered by the user on their device. Based on this data, it performs initial analysis and updates a database to understand the user's characteristics.

[0705] Step 2:

[0706] The server uses the generated AI model as a prompt based on the received attribute information to generate an initial learning plan. In this process, the prompt "Generate the optimal initial learning plan for the newly registered user" is used, and the AI ​​outputs a plan. The result is sent to the terminal and presented to the user.

[0707] Step 3:

[0708] Once a user begins learning, the device continuously collects data on their learning behavior. This data includes inputs such as the user's viewing history of learning content, response time, and accuracy rate. The device then organizes this data and sends it to the server.

[0709] Step 4:

[0710] The server analyzes the collected learning behavior data. Using an AI algorithm, it evaluates the user's understanding in real time. Based on the analysis results, it inputs the prompt message "Generate the next learning task based on the user's understanding" into the generating AI model and outputs a new learning plan.

[0711] Step 5:

[0712] The server sends the newly generated learning plan to the terminal and presents it to the user. This allows the user to work on continuously updated and optimal challenges.

[0713] Step 6:

[0714] If a user encounters a question during the learning process, they send it to the server via their device. The server receives the user's specific question as input. In response, the server uses a generative AI model to generate an explanation for the question.

[0715] Step 7:

[0716] The server sends the generated explanations back to the terminal, providing them to the user. This allows the user to quickly resolve their questions and continue learning.

[0717] (Application Example 1)

[0718] 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".

[0719] Traditional learning platforms suffer from a lack of real-time optimization to meet individual user learning needs and from a failure to provide a learning experience linked to the real-world physical environment. This limitation prevents users from making the most of the information resources available to them during their learning process.

[0720] 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.

[0721] In this invention, the server includes means for receiving user attribute data and learning objective data, means for collecting user learning activity data in real time, and means for analyzing the user's level of understanding based on the received data. This enables the provision of a learning plan optimized for the user and the visual presentation of educational resources linked to the real-world physical environment.

[0722] "User attribute data" refers to data that contains basic information about the user, such as age, grade level, and learning goals.

[0723] "Learning objective data" refers to information about the specific learning goals and objectives that the user wants to achieve.

[0724] "Learning activity data" refers to data that shows a user's activity history, including what content they viewed, how much time they spent on it, and how accurately they answered each question.

[0725] "Means of analyzing comprehension" refers to methods and technologies for evaluating a user's knowledge level and comprehension based on their learning activity data.

[0726] "Means for generating learning plans" refers to methods and devices that suggest optimal learning content and methods according to the user's level of understanding and learning goals.

[0727] "Means of providing the generated learning plan to the user" refers to the methods and technologies for deploying the generated learning plan in a format that the user can use.

[0728] The "On-Demand Tutor Function" refers to a feature that automatically generates and provides necessary explanations and information in response to user questions.

[0729] "Means of visually presenting information within a physical environment" refers to methods and devices for visually displaying user-related information in real-world space.

[0730] "Means of presenting educational resources based on location data" refers to methods and technologies for presenting optimal learning materials and information based on the user's current location.

[0731] The system for realizing this invention mainly consists of a server, a user terminal, and devices such as smart glasses. The server receives attribute data and learning objective data provided by the user and generates an initial learning plan. This learning plan is presented visually through the user's smart glasses, and the user's progress and learning activity data are collected in real time.

[0732] The server uses generated AI to analyze the user's understanding based on this activity data. This analysis is used to dynamically update the user's learning plan, recommending new content and practice exercises as needed. Furthermore, appropriate educational resources are visually presented based on the user's physical location data. For example, when a user moves to a specific learning area within a physical store, relevant learning materials and information are displayed on the smart glasses' screen.

[0733] Furthermore, an on-demand tutoring function is included to support users with questions that arise during their learning. Questions from users are sent to the server, where a generating AI analyzes them and instantly generates relevant explanations and supplementary materials.

[0734] As a concrete example, consider a scenario where a middle school student visits a physical store's learning space to study geometry. When this user searches for "recommended learning materials on triangle congruence conditions" using smart glasses, the system identifies the most relevant books and learning materials for that location and visually guides them on the display. Furthermore, when the user asks a question about "triangle congruence conditions," the generative AI model instantly generates an explanation of the derivation process.

[0735] An example of a prompt message would be: "Based on the user's attribute data, generate a list of learning materials best suited to the current learning objectives and provide detailed descriptions of them."

[0736] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0737] Step 1:

[0738] The server receives attribute data and learning objective data from the user's terminal. This includes the user's age, grade level, and learning objectives as input, and the server generates an initial learning plan based on this data. At this stage, it references similar past cases from the database to select a base learning pattern.

[0739] Step 2:

[0740] The user puts on smart glasses and enters a physical store. The device collects the user's location data and surrounding environmental information, and sends it to a server. As the user moves to a specific area within the store, the content displayed on the smart glasses dynamically changes. During this process, the glasses collect environmental data in real time using cameras and sensors.

[0741] Step 3:

[0742] Based on the received location data and user attribute information, the server uses a generative AI model to identify the most suitable learning resources for the user and sends visual instructions to the glasses. This process involves extracting learning materials that match the user's learning progress and objectives from a digital database, and then organizing and providing information about them.

[0743] Step 4:

[0744] If a user has a question during the learning process, they input the question through smart glasses. This question is sent from the device to a server for analysis. The AI ​​model analyzes the input question and generates relevant materials and explanations.

[0745] Step 5:

[0746] The server uses a generative AI model to generate appropriate explanations and supplementary information in response to user questions, and immediately sends them to the smart glasses. The output information includes video links and detailed explanations to enhance the user's understanding.

[0747] Step 6:

[0748] The device collects learning activity data, such as the learning materials used and the time spent studying, and continuously transmits it to the server. The server analyzes this data and evaluates the user's level of understanding. Based on this evaluation, the learning plan for the next step is dynamically updated, and the optimal route to achieving the goal is presented.

[0749] 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.

[0750] This invention provides a system that combines an emotion engine with an educational platform using generative AI to offer users more personalized learning support. This system collects user attribute data and learning goal data, and monitors user learning activity data and emotional data in real time. This allows for the creation and provision of an optimal learning plan that takes into account the user's level of understanding and emotional state.

[0751] Specifically, the server receives attribute data and learning objective data as basic information obtained from the user. Based on this information, an initial learning plan is generated on the server and presented to the user via the terminal. As the user progresses through the learning process, the terminal sends learning activity data and emotion data detected using the emotion engine to the server.

[0752] This emotional data includes the user's stress levels, level of interest, and level of concentration during learning, allowing for a detailed analysis of the user's state of mind. The server uses AI algorithms to comprehensively analyze this data and evaluate the user's current level of understanding and emotional state. Based on the evaluation results, the server dynamically adjusts the learning plan. For example, if it is determined that the user has lost interest in learning, the plan can be made more interactive or its difficulty level adjusted.

[0753] Furthermore, if a user has a question, it is sent from the device to the server, and the AI ​​generates a relevant explanation and responds. Here, responses based on the user's emotions are also taken into consideration, so for example, if the user is feeling stressed, content that promotes relaxation may be incorporated.

[0754] As a concrete example, let's consider a case where an elementary school student is learning programming for the first time. In the initial setup, a plan is provided to learn basic programming concepts based on the user's learning goals. If the emotion engine detects a decrease in the user's concentration during learning, the server adopts a strategy of changing the learning content into a game format to regain attention. Also, if the user asks a question such as "Why does this happen?", in addition to a simple answer, information on related topics that will pique the user's interest is also provided. In this way, the present invention allows users to enjoy a more effective and engaging learning experience.

[0755] The following describes the processing flow.

[0756] Step 1:

[0757] The server receives attribute data and learning objective data entered by the user. This includes information such as age, grade level, and learning goals.

[0758] Step 2:

[0759] The server generates an initial learning plan. This plan selects specific learning content and materials based on the user data received.

[0760] Step 3:

[0761] The device presents the user with an initial learning plan sent from the server. The user can then begin learning.

[0762] Step 4:

[0763] As the user progresses through the learning process, the device collects data on the user's learning activities. This includes learning time, content progress, and the results of answering questions.

[0764] Step 5:

[0765] The emotion engine acquires user emotional data through facial recognition and voice tone analysis. This data includes information such as stress levels, interest levels, and concentration levels.

[0766] Step 6:

[0767] The device sends collected learning activity data and emotional data to the server. This transmission occurs in real time, and the data is continuously updated.

[0768] Step 7:

[0769] The server uses AI algorithms to analyze this data and evaluate the user's level of understanding and emotional state. This allows for the measurement of learning effectiveness and user motivation.

[0770] Step 8:

[0771] The server adapts the learning plan based on the evaluation results. Specifically, if the user's concentration wavers, adjustments are made, such as incorporating game elements or suggesting breaks.

[0772] Step 9:

[0773] The device presents the user with a new learning plan and notifies them of the changes, allowing the user to proceed to the next learning step.

[0774] Step 10:

[0775] When a user has a question, they can send it to the server via their device. The question entered here is in text format.

[0776] Step 11:

[0777] The server uses AI to analyze user questions and generates and provides relevant explanations and learning materials to the user. In doing so, the server also considers the user's emotional state to select the most appropriate response.

[0778] Step 12:

[0779] The server collects user feedback data and uses it to generate the next learning plan. Based on the feedback, improvements are made to provide a more effective learning experience.

[0780] (Example 2)

[0781] 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".

[0782] Traditional educational platforms struggle to fully understand each user's individual learning state and emotions, and to provide personalized learning support accordingly. In particular, they cannot dynamically adjust learning plans in response to changes in user interests or improvements in comprehension, resulting in limited learning effectiveness.

[0783] 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.

[0784] In this invention, the server includes means for receiving basic user information and goal information, means for collecting user learning activity information and emotional information in real time, and means for analyzing the user's level of understanding and state based on the received information. This makes it possible to dynamically adjust the learning plan according to the user's individual emotional state and learning progress, and to provide optimal learning support.

[0785] "Basic information" refers to information that indicates the user's personal characteristics, including age, grade level, areas of expertise, and areas of weakness.

[0786] "Goal information" refers to information about the learning goals that the user wishes to achieve, and includes specific learning outcomes and progress targets.

[0787] "Learning activity information" refers to data related to the learning activities undertaken by the user, including the time spent learning, the number of completed assignments, and their progress.

[0788] "Emotional information" refers to information related to the user's emotional state, including data measuring the user's stress level, level of interest, and level of concentration.

[0789] "Comprehension level" is an evaluation metric that indicates how well a user understands the learning material, and is estimated from the user's accuracy rate and speed of response.

[0790] "State" refers to the mental and emotional state of a user during learning, and is a concept that includes levels of interest and stress based on emotional information.

[0791] "Dynamic adjustment" means modifying the learning plan in real time according to the user's level of understanding and status, and updating the content as needed to optimize learning support.

[0792] A "learning plan" is a plan that outlines the learning content and activities that a user should accomplish within a certain period of time, and includes specific learning topics and a sequence of content.

[0793] This invention is an educational system that provides personalized learning support to users using generative AI technology and emotion analysis technology. The server receives attribute information and learning goal information from the user and creates an initial learning plan based on this information. The terminal collects activity information and emotional information in real time during the user's learning activities. This emotional information is measured from the user's facial expressions, voice, operation speed, etc., and is data that indicates the user's stress level, interest level, and concentration level.

[0794] The server analyzes received learning activity and emotional information using a generative AI model to evaluate the user's understanding and emotional state. Based on this evaluation, the server dynamically adjusts the learning plan. This ensures that the learning content remains engaging for the user, maximizing learning effectiveness. Furthermore, if the user has questions, they can submit them through their device. The server then generates explanations using the generative AI in response to these questions, providing answers tailored to the user's emotional state.

[0795] As a concrete example, consider a scenario where an elementary school student is learning programming for the first time. The server receives the user's goal information and generates a learning plan to teach the basics of programming as an initial setup. However, if the server determines through the terminal that the user's concentration is waning, it can change the learning plan to be more interactive and gamified to re-engage the user.

[0796] An example of a prompt message might be, "Explain basic programming concepts in a fun way to an elementary school student who is learning programming for the first time." This system allows users to achieve effective learning tailored to their individual needs.

[0797] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0798] Step 1:

[0799] The server receives basic information and learning objectives from the user. Input consists of personal information provided by the user via their device, such as age, grade level, and learning objectives. The server stores this information in a database and uses it as foundational data to generate an initial learning plan. Output is the foundational information for the initial learning plan.

[0800] Step 2:

[0801] The server generates an initial training plan based on the information received using a generative AI model. The input consists of basic information and training objectives. The generative AI model processes this data to generate a first training plan tailored to the user's individual needs. The output is the initial training plan presented to the user. This plan is provided to the user via the terminal.

[0802] Step 3:

[0803] The device collects learning activity information and emotional information in real time while the user is learning. Inputs include the user's actions, facial expressions, and voice during learning. The device uses sensors and microphones to collect learning time, answer status, and emotional data based on facial expression analysis. Outputs are sent to the server as learning activity information and emotional information.

[0804] Step 4:

[0805] The server analyzes the received learning activity and emotional information to evaluate the user's current level of understanding and emotional state. The input consists of collected learning activity and emotional information. Using an AI algorithm, the server comprehensively analyzes this data to determine the user's interests and level of understanding. The output is the evaluation result, which dynamically adjusts the user's learning plan.

[0806] Step 5:

[0807] The server dynamically adjusts the learning plan using a generated AI model based on the evaluation results. For example, if it determines that the user's concentration is waning, it might lower the difficulty level or increase the amount of interactive content. The input is the evaluation results, and the output is the adjusted learning plan. This new plan is then provided to the user again through the device.

[0808] Step 6:

[0809] If a user has a question during the learning process, they send the question to the server via their device. The input is the user's question. The server uses generative AI to generate a detailed and appropriate explanation for the question and sends it back to the user. The output is explanatory information tailored to the user's emotional state, which may include elements that promote relaxation.

[0810] (Application Example 2)

[0811] 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".

[0812] Conventional online learning platforms often provide a uniform learning experience without considering the user's emotional state, which has led to decreased learning efficiency and motivation. Furthermore, simply providing plans based on comprehension levels makes it difficult to flexibly respond to the user's current emotions and interests. This invention aims to solve these problems and provide a more personalized learning experience.

[0813] 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.

[0814] In this invention, the server includes means for receiving user attribute information and purpose information, means for collecting user activity information in real time, means for evaluating the learner's understanding based on the received information, means for generating a plan based on the learner's understanding, means for providing the generated plan to the user, means for receiving inquiries from the user and generating and providing relevant explanations, and means for analyzing the user's emotional state and providing recommendation information accordingly. This makes it possible to provide a dynamic and flexible learning plan that simultaneously considers the user's level of understanding and emotional state.

[0815] "User attribute information" refers to personal characteristics and background information about users, including data such as age, gender, occupation, and learning experience.

[0816] "Purpose information" refers to information that indicates the learning goals or objectives that the user wishes to achieve, or their current areas of interest.

[0817] "Activity information" refers to data on various actions taken by users on the platform, including content viewed, questions answered, and access frequency.

[0818] "Participant comprehension level" refers to information indicating how well users understand the material they have learned, and is evaluated based on factors such as grades and the accuracy of answers.

[0819] "Means for generating plans" refer to methods and functions for creating efficient and effective learning plans based on the user's understanding and attribute information.

[0820] "User inquiries" refer to questions and requests that users send to the system when they have questions while learning.

[0821] "Means for generating and providing relevant explanations" refers to methods and functions for generating appropriate and easy-to-understand explanations in response to user inquiries and informing users of the results.

[0822] "User emotional state" refers to information that captures the mental and emotional state exhibited by users during learning, and includes, for example, excitement, concentration, and boredom.

[0823] "Means of providing recommendation information" refers to methods or functions for suggesting appropriate products, services, or learning content that are tailored to the user's emotional state.

[0824] This invention is implemented by a system consisting of three elements: a server, a terminal, and a user.

[0825] The server generates an initial learning plan using attribute and objective information obtained from the user. This plan is then provided to the user via the terminal. The server analyzes the received user activity and sentiment information in real time, continuously evaluating the user's understanding and emotional state. This allows the server to dynamically adjust the learning plan as needed, providing an optimal learning environment.

[0826] The device monitors the user's learning activity and sends activity information and emotional state data acquired through an emotion recognition library to the server. This process utilizes a system equipped with a generative AI model to analyze complex datasets, including the user's emotional data.

[0827] If a user has questions during the learning process, they can submit them through their device. The server uses a generative AI model to generate appropriate explanations for these inquiries, taking into account the user's emotional state when providing answers.

[0828] As a concrete example, imagine a scenario where an elementary school student is learning programming for the first time in a virtual store. If the user shows signs of boredom during the learning process, the system will automatically adjust the plan to present more interactive learning materials to capture their attention. Also, if the user asks a question about programming, such as "Why does this result occur?", the AI ​​will provide an easy-to-understand explanation on the spot, along with information on related topics to further increase their interest.

[0829] Examples of prompts for a generative AI model:

[0830] "Please provide information that clearly explains the programming learning materials displayed by the user, based on other reference materials and the experiences of other learners."

[0831] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0832] Step 1:

[0833] The server receives attribute and purpose information from the user. The received data is stored in a database and used as input when generating an initial learning plan. Based on this information, suitable educational content and starting guidelines are formulated.

[0834] Step 2:

[0835] The device collects user activity information in real time and sends it to the server. This activity information includes the user's progress and behavior logs, which are used to track learning progress. The device also uses its camera and input devices to collect additional data necessary for evaluating emotional states.

[0836] Step 3:

[0837] The server uses received activity information and sentiment data to simultaneously evaluate the user's understanding and emotional state. A generative AI model is used to process the input data, analyzing the user's level of understanding and emotional tendencies. The optimized evaluation results are then output.

[0838] Step 4:

[0839] The server dynamically adjusts the learning plan based on the evaluation results and provides the updated plan to the device. This adjustment includes selecting learning materials tailored to the user's interests and understanding, and changing the difficulty level. This process ensures that users can always continue learning in an optimal state.

[0840] Step 5:

[0841] When a user enters a question during the learning process, the device sends the inquiry to the server. The server uses a generative AI model to generate an appropriate explanation for the question and sends it to the device. The generated explanation takes the user's emotional state into consideration and is presented in an easy-to-understand and relaxed format.

[0842] Step 6:

[0843] The server analyzes the user's emotional state and provides corresponding recommendations to the device. For example, if interest is waning, new interactive content will be recommended. This helps maintain the user's learning motivation.

[0844] 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.

[0845] 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 those described above. 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 shown 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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."

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] The following is further disclosed regarding the embodiments described above.

[0866] (Claim 1)

[0867] A means for receiving user attribute data and learning objective data,

[0868] A means of collecting user learning activity data in real time,

[0869] A means of analyzing the user's level of understanding based on the received data,

[0870] A means of generating a learning plan based on the user's level of understanding,

[0871] A means of providing the generated learning plan to the user,

[0872] A means of receiving questions from users, generating and providing relevant explanations,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, which collects user feedback data and uses it to improve learning plans.

[0876] (Claim 3)

[0877] The system according to claim 1, in the stage of comprehension analysis, using the user's response time and correct response rate as evaluation criteria.

[0878] "Example 1"

[0879] (Claim 1)

[0880] Means for receiving user attribute information and learning objective information,

[0881] A means of collecting user learning behavior data in a time-synchronized manner,

[0882] A means of analyzing the user's understanding based on the received information,

[0883] A means for dynamically generating a learning plan based on the user's understanding,

[0884] A means of presenting the generated learning plan to the user,

[0885] A means of receiving questions from users, generating and presenting relevant explanations,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, which collects user feedback data and uses it to improve learning plans.

[0889] (Claim 3)

[0890] The system according to claim 1, in the stage of understanding state analysis, using the time required for the user to answer and the accuracy rate as evaluation criteria.

[0891] "Application Example 1"

[0892] (Claim 1)

[0893] A means for receiving user attribute data and learning objective data,

[0894] A means of collecting user learning activity data in real time,

[0895] A means of analyzing the user's level of understanding based on the received data,

[0896] A means of generating a learning plan based on the user's level of understanding,

[0897] A means of providing the generated learning plan to the user,

[0898] A means of receiving questions from users, generating and providing relevant explanations,

[0899] A means of visually presenting information based on the user's learning theme within a real-world physical environment,

[0900] A means of presenting appropriate educational resources based on the user's location data and attribute data,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, which collects user feedback data and uses it to improve learning plans.

[0904] (Claim 3)

[0905] The system according to claim 1, in the stage of comprehension analysis, using the user's response time and correct response rate as evaluation criteria.

[0906] "Example 2 of combining an emotion engine"

[0907] (Claim 1)

[0908] A means of receiving the user's basic information and target information,

[0909] A means of collecting user learning activity information and emotional information in real time,

[0910] A means of analyzing the user's level of understanding and state based on the received information,

[0911] A means for dynamically adjusting the learning plan based on the user's level of understanding and emotional state using generative AI technology,

[0912] A means of providing the generated learning plan to the user,

[0913] A means of receiving inquiries from users and generating and providing explanations that respond to the user's emotions,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, which analyzes emotional information related to a user's learning activities and uses it to improve the learning plan.

[0917] (Claim 3)

[0918] The system according to claim 1, in which the user's level of interest and concentration are used as evaluation criteria during the comprehension analysis stage.

[0919] "Application example 2 when combining with an emotional engine"

[0920] (Claim 1)

[0921] Means for receiving user attribute information and purpose information,

[0922] A means of collecting user activity information in real time,

[0923] A means of evaluating the level of understanding of participants based on the information received,

[0924] A means of generating a plan based on the participants' level of understanding,

[0925] Means for providing the generated plan to the user,

[0926] A means of receiving inquiries from users, generating and providing relevant explanations,

[0927] A means of analyzing the emotional state of users and providing recommendation information accordingly,

[0928] A system that includes this.

[0929] (Claim 2)

[0930] The system according to claim 1, which collects user sentiment information and uses it to adapt the plan.

[0931] (Claim 3)

[0932] The system according to claim 1, wherein the user's response time and accuracy rate are used as evaluation criteria during the analysis stage. [Explanation of Symbols]

[0933] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving user attribute data and learning objective data, A means of collecting user learning activity data in real time, A means of analyzing the user's level of understanding based on the received data, A means of generating a learning plan based on the user's level of understanding, A means of providing the generated learning plan to the user, A means of receiving questions from users, generating and providing relevant explanations, A system that includes this.

2. The system according to claim 1, which collects user feedback data and uses it to improve learning plans.

3. The system according to claim 1, in the stage of comprehension analysis, using the user's response time and correct response rate as evaluation criteria.

Images