System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting learning data of a student; means for analyzing the collected learning data and classifying a learning style of the student; means for generating an optimal learning plan for each student based on the classified learning style; and means for presenting the optimal learning plan to the student.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method 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 a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Many students find it difficult to find a study method that suits them within a uniform teaching style, making it difficult to progress efficiently. There is also a need for a means to provide effective learning methods without relying on private tutors or individual instruction. Conventional systems cannot adjust learning plans to suit each student in real time, which means that students are unable to maximize their learning effectiveness. [Means for solving the problem]

[0005] The AI ​​tutor system of the present invention includes a means for collecting student learning data, a means for analyzing the collected learning data and classifying the student's learning style, a means for generating an optimal learning plan for each student based on the classified learning style, and a means for presenting the optimal learning plan to the student. It also includes a means for real-time monitoring of the collected learning data and for instantly adjusting the learning plan based on the student's level of concentration and response. The learning plan is individually optimized based on the student's past academic performance data and learning progress, providing each student with an optimal learning method. This overcomes the drawbacks of a uniform teaching style and significantly improves student learning efficiency.

[0006] "Student learning data" refers to information collected when learners engage in learning activities, and specifically includes response times, accuracy rates, eye movements, facial expressions, and tone of voice.

[0007] "Means of collection" is a general term for equipment and software used to acquire and record student learning data, including cameras, microphones, keyboard input, etc.

[0008] "Means of analysis" refers to the algorithms and software used to analyze the collected data and identify students' learning styles, levels of concentration, and emotional states.

[0009] "Learning style" refers to the method or pattern in which an individual student can learn most effectively, and includes classifications such as "visual," "auditory," "abstract thinking," and "concrete thinking."

[0010] An "optimal learning plan" is a set of learning content and schedules that are deemed most effective for each individual student, created based on analyzed learning style and performance data.

[0011] "Presentation means" refers to devices or software for communicating and displaying the generated learning plan to students, and specifically includes displays, applications with notification functions, etc.

[0012] "Real-time monitoring" is the process of instantly observing and recording students' activities and reactions during learning, using cameras and microphones to continuously track students' gaze, facial expressions, and tone of voice.

[0013] "Concentration" is an indicator of how much attention and energy a student is putting into their studies, and is assessed based on factors such as fixed gaze, changes in facial expression, and fluctuations in voice tone.

[0014] "Adjusting the learning plan" is the process of changing the proposed learning plan as needed in response to changes in the student's real-time responses and concentration levels.

[0015] "Academic data" refers to the stored numerical data and records of a student's past learning achievements, including test results, evaluation scores, progress, etc. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0030] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This AI tutor system provides learners (users) with individually optimized learning plans and is designed to improve students' learning efficiency. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[0038] Data Collection Phase

[0039] When a user logs in to a device and begins learning, the device prepares to record their learning activities. Specifically, the device uses the built-in camera and microphone to collect information such as the user's eye movements, facial expressions, and voice tone. This data is sent to the server in real time, and the server stores it in a database.

[0040] Data analysis phase

[0041] The server uses a specific algorithm to analyze the collected learning data. The data analysis algorithm identifies the user's learning style (e.g., "visual," "auditory," "abstract thinking," "concrete thinking," etc.) and evaluates their concentration level and emotional state. Based on these results, the server classifies the user's learning style.

[0042] Optimization Phase

[0043] The server generates an individually optimized learning plan based on the analyzed learning style. This includes learning content and schedules that differ for each user. For example, a user who prefers concrete thinking can be provided with learning materials that include many concrete problems. The generated learning plan is sent to the terminal and presented to the user.

[0044] Execution Phase

[0045] The user follows the presented study plan. While studying, the device continuously monitors the user's eye movements, facial expressions, tone of voice, and other factors in real time. Based on this, the device evaluates the user's level of concentration and immediately adjusts the study plan as necessary. For example, if the user's level of concentration decreases, the device will recommend that the user take a break or present a new problem.

[0046] Specific examples

[0047] As a specific example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math study materials on his device, the device records his eye movements, facial expressions, tone of voice, and other data. This data is sent to the server in real time. The server analyzes the collected data and determines that Student A prefers concrete thinking. Based on this result, the server generates an optimal study plan for Student A. Specifically, it provides many study materials containing many actual math problems, and presents them with gradually increasing difficulty levels. This study plan is then displayed to Student A via his device.

[0048] If Student A's concentration level drops as he or she studies, the device will detect this change in real time and provide immediate feedback, such as inserting an easy question or informing the student to take a short break. This maximizes Student A's learning efficiency and improves their learning outcomes.

[0049] Through the above process, this AI tutor system provides each student with the optimal learning method, thereby overcoming the drawbacks of a uniform learning style and significantly improving students' learning efficiency.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The user logs in to the device and begins learning.

[0053] Step 2:

[0054] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, and voice tone in real time.

[0055] Step 3:

[0056] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[0057] Step 4:

[0058] The device transmits the collected data to the server in real time.

[0059] Step 5:

[0060] The server stores the received data in a database.

[0061] Step 6:

[0062] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style.

[0063] Step 7:

[0064] The server generates a personalized learning plan based on the user's learning style, for example, recommending learning materials with many concrete problems to a user who prefers concrete thinking.

[0065] Step 8:

[0066] The server transmits the generated study plan to the terminal.

[0067] Step 9:

[0068] The device presents the user with the optimal learning plan and displays it on the screen.

[0069] Step 10:

[0070] The user proceeds with the learning activities based on the presented learning plan.

[0071] Step 11:

[0072] During the learning process, the device continues to monitor the user's eye movements, facial expressions, and voice tone in real time.

[0073] Step 12:

[0074] The device assesses the user's level of concentration and response and adjusts the learning plan as needed, for example presenting new tasks or suggesting a break if concentration levels drop.

[0075] Step 13:

[0076] After the learning session is over, the device sends any new data it has collected to the server.

[0077] Step 14:

[0078] The server stores the new data in a database and updates the analysis algorithm to improve the accuracy of the next learning plan.

[0079] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] With conventional learning systems, it was difficult to grasp the learning style and concentration level of each learner in real time and dynamically adjust the learning plan based on that. As a result, learners were unable to obtain an optimal learning environment, and learning efficiency could not be sufficiently improved.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for collecting learner learning data, means for analyzing the collected learning data and classifying the learner's learning style, and means for generating an optimal learning plan for each learner based on the classified learning style. This makes it possible to monitor the learner's eye movements, facial expressions, and tone of voice in real time. Furthermore, by analyzing the collected data in real time and dynamically adjusting the learning plan, it is possible to provide the learner with an optimal learning experience.

[0085] A "learner" is a person who engages in learning activities to acquire specific knowledge or skills.

[0086] "Learning data" refers to information such as learning content, learning progress, eye movements, facial expressions, and vocal tone that is generated when a learner engages in learning activities.

[0087] "Means for collection" refers to a method or device for acquiring learner learning data using hardware such as a camera or microphone.

[0088] "Means for analyzing" refers to a method or device that processes collected learning data using computer algorithms to evaluate learning style and concentration.

[0089] A "study plan" refers to a plan that compiles optimal learning content and schedules based on a learner's learning style and concentration level.

[0090] "Means for generating" refers to a method or device for creating an optimal learning plan for a learner based on the analysis results.

[0091] "Presenting means" refers to a method or device for displaying the generated lesson plan to a learner.

[0092] "Means of real-time monitoring" refers to a method or device that checks the eye movements, facial expressions, tone of voice, etc. of learners in real time while they are studying, and collects that data.

[0093] "Dynamic adjustment means" refers to a method or device that instantly and adaptively modifies learning plans and content based on data collected in real time.

[0094] This invention is an AI tutor system that provides learners with individually optimized learning plans. The main components of the system are a server, a terminal, and a user.

[0095] Data Collection Phase

[0096] When a user logs in to a device and begins studying, the device begins recording their study activities. Specifically, the device's built-in camera and microphone are used to collect the user's eye movements, facial expressions, and tone of voice. This data is sent in real time to a server, which then stores it in a database. For example, the camera can track the user's eye movements while the microphone monitors changes in the tone of their voice, allowing the system to measure the user's interest and concentration.

[0097] Data analysis phase

[0098] The server uses specific algorithms to analyze the collected learning data. For example, it uses image processing algorithms to analyze the user's facial expressions and voice recognition algorithms to analyze the user's tone of voice. This analysis identifies the user's learning style (visual, auditory, abstract thinking, concrete thinking, etc.) and evaluates their concentration level and emotional state. For example, if a user responds more to visual information, they will be classified as "visual."

[0099] Optimization Phase

[0100] The server generates an individually optimized learning plan based on the analyzed learning style. This plan includes learning content and schedules that differ for each user. For example, for a user who prefers concrete thinking, learning materials containing many concrete problems are provided. The generated learning plan is sent to the terminal and presented to the user.

[0101] Execution Phase

[0102] The user follows the presented study plan as they study, and the device continues to monitor them as they do so. The device collects eye movements, facial expressions, tone of voice, and other data in real time, and evaluates the user's level of concentration based on this information. If the user's level of concentration decreases, the device immediately provides feedback, recommending a break or presenting a new problem. For example, if the user's eye movements are frequent, it will determine that the user is distracted and suggest a break.

[0103] Specific examples

[0104] As a concrete example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math materials on his device, the device records his eye movements and facial expressions with a camera and his tone of voice with a microphone. This data is sent to the server in real time, and the server analyzes it. If the analysis determines that Student A prefers concrete thinking, the server generates a study plan that includes many concrete problems and sends it to the device. The device presents this plan to Student A and continues to monitor his concentration level in real time while he studies. If his concentration level drops, the device immediately suggests a break or presents new problems.

[0105] Prompts for generative AI models

[0106] Below are the prompts for generating a lesson plan using this system:

[0107] Prompt: Student A struggles with math and has a concrete learning style. To help him study effectively, generate a study plan that is optimized for him. This plan should include specific problems that increase in difficulty, starting with concepts he's new to. It should also include actions to take if he loses focus (such as inserting easier problems or recommending breaks).

[0108] In this way, this AI tutoring system can maximize learners' learning efficiency by providing an individually optimized learning experience.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] The user logs in to the device and begins learning. The device receives the user's login information and is ready to proceed to the next step. The input is the user's ID and password, and the output is a signal to start the learning session.

[0112] Step 2:

[0113] The device activates its built-in camera and microphone to collect the user's eye movements, facial expressions, and voice tone. The input is biometric information from the user's learning activity, and the output is learning data such as eye movements and voice tone. The device begins collecting this data in real time.

[0114] Step 3:

[0115] The device sends the collected learning data to the server in real time. The server stores the received data in a database. The input is the learning data sent from the device, and the output is the data stored in the database. The stored information is stored with a timestamp.

[0116] Step 4:

[0117] The server retrieves the stored training data and begins analysis using a specific algorithm. The input is the stored training data, and the output is the data analysis results. Specifically, the image analysis algorithm analyzes the user's facial expression, and the voice analysis algorithm analyzes the voice tone.

[0118] Step 5:

[0119] The server identifies the user's learning style based on the analysis results. The input is the data analysis results, and the output is the identified learning style category (visual, auditory, abstract thinking, concrete thinking, etc.). In this process, a score is assigned to each learning style.

[0120] Step 6:

[0121] The server then evaluates the user's concentration and emotional state. The input is the detailed results of the analysis algorithm, and the output is an assessment of the user's concentration and emotional state. For example, it can determine whether the user is distracted from camera footage and infer stress levels from the tone of the user's voice.

[0122] Step 7:

[0123] The server generates an individually optimized learning plan based on the analysis results. The input is the assessment results of concentration level and learning style, and the output is an individualized learning plan. For example, for visual users, learning materials with many illustrations are selected.

[0124] Step 8:

[0125] The server sends the generated learning plan to the terminal and presents it to the user. The input is the personalized learning plan, and the output is the learning plan displayed on the terminal. The terminal displays a notification to prompt the user to confirm the plan.

[0126] Step 9:

[0127] The user performs learning activities according to the presented learning plan. The input is the displayed learning plan, and the output is the learning completion status and progress data. As the user progresses with their learning, the device continues to collect data such as eye movements, facial expressions, and voice tone.

[0128] Step 10:

[0129] The device evaluates the user's level of concentration based on real-time data and instantly adjusts the learning plan as needed. The input is the latest learning data collected in real time, and the output is an updated learning plan and feedback. For example, if the user's level of concentration decreases, the device will immediately respond by recommending a break or presenting a new problem.

[0130] (Application example 1)

[0131] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] Conventional online learning systems have difficulty fully understanding each student's learning style, concentration level, and emotional state. Furthermore, they are unable to provide each student with a personalized learning plan in real time, potentially reducing their learning efficiency. Furthermore, they lack a way to instantly adjust learning plans based on students' concentration levels and responses, making it difficult to provide effective learning support.

[0133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0134] In this invention, the server includes means for collecting the learner's gaze, facial expression, and tone of voice using a built-in camera and microphone; means for analyzing the collected gaze, facial expression, and tone of voice to evaluate the learner's concentration and emotional state; means for analyzing the collected learning data using a specific algorithm and classifying the user's learning style; means for generating an individually optimized learning plan based on the classified learning style; and means for transmitting the generated learning plan to a terminal and presenting it to the user. This makes it possible to grasp the user's learning style, concentration, and emotional state in real time and provide an optimal learning plan based on that. It also makes it possible to instantly adjust the learning plan based on the user's concentration and response, maximizing learning efficiency.

[0135] "Learning data" refers to data generated when a user learns, and includes eye movements, facial expressions, voice tones, operation history, and the like.

[0136] "Learning style" is a pattern that indicates how a user can learn most effectively, and includes classifications such as visual, auditory, concrete thinking, and abstract thinking.

[0137] A "study plan" is a plan that indicates optimal study content and schedule for a user, and includes learning materials and instruction content customized based on the user's learning style and concentration level.

[0138] The "gaze" is information indicating the point at which the user is looking, and is the movement of the viewpoint acquired using the built-in camera.

[0139] "Facial expression" is information that indicates the state of the user's face, and indicates emotions and concentration.

[0140] "Voice tone" refers to the tone of the voice uttered by the user, and serves as an indicator of emotions and concentration level.

[0141] "Level of concentration" is an index that evaluates how focused a user is on their studies, and is evaluated based on data such as gaze, facial expression, and tone of voice.

[0142] A "prompt sentence" is an instruction sentence input into a generative AI model, and is text used to obtain appropriate generated results according to the purpose.

[0143] The present invention is a system constructed to provide learners (users) with individually optimized study plans. A specific embodiment of this system will be described in detail below.

[0144] Overall system configuration

[0145] The main components of the system are the server, the terminal, and the user. The server is responsible for analyzing data and generating learning plans, the terminal is responsible for collecting data and presenting learning plans, and the user is the entity that carries out the learning.

[0146] Data Collection Phase

[0147] When a user logs in to a device and begins learning, the built-in camera and microphone are activated to collect data related to the learning activity. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. This data is sent to the server in real time.

[0148] Data analysis phase

[0149] The server uses specific algorithms to analyze the transmitted data, such as gaze, facial expression, and voice tone. The analysis results are used to evaluate the user's learning style and concentration level, and the user's learning style is then classified based on the evaluation results. Computer vision technology is used to analyze gaze and facial expression, and natural language processing (NLP) technology is used to analyze voice tone.

[0150] Optimization Phase

[0151] Based on the classified learning style, the server generates an individually optimized learning plan. For example, it provides learning materials containing many practical problems to a user who prefers concrete thinking, and creates a plan containing many diagrams and video materials for a user who finds visual instructions effective. The generated learning plan is sent to the terminal and presented to the user.

[0152] Execution Phase

[0153] The user carries out learning activities according to the presented learning plan. While studying, the device uses a camera and microphone to continuously monitor the user's gaze, facial expressions, and tone of voice in real time. If the user's level of concentration decreases, the device detects the change and sends feedback to the server. The server immediately adjusts the learning plan based on this feedback, and the device presents a new plan to the user.

[0154] Specific examples

[0155] For example, let's imagine that Student A, who is not good at math, uses this system. When Student A begins studying using math teaching materials on his / her device, the camera captures Student A's eye movements and facial expressions, and the microphone collects his / her voice tone. This data is sent to the server, which analyzes the results and determines that Student A prefers concrete thinking. Based on this evaluation, the server generates teaching materials that are optimal for Student A, including many concrete problems, and presents them to him / her via his / her device.

[0156] Prompt Sentence Examples

[0157] An example of a prompt to be input to the AI ​​model is as follows:

[0158] Collect video data of elementary school students learning math and perform emotion recognition. Next, analyze the tone from the audio data to obtain the average audio amplitude. Provide an optimized learning plan based on the obtained emotion data and audio tone.

[0159] Video data: {video_frame}

[0160] Audio data: {audio_data}

[0161] Emotion recognition result: {emotion}

[0162] Average audio amplitude: {avg_audio_amplitude}

[0163] The above steps realize a system that can provide a learning experience optimized for each user and improve learning efficiency.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. These data are sent to the server in real time. The input data are eye movements, facial expressions, and voice tones, and the output is the collected data.

[0167] Step 2:

[0168] The server analyzes the received data. Gaze and facial expression data are processed by computer vision algorithms to identify the user's emotional state using emotion recognition models. Voice tone data is analyzed using natural language processing (NLP) techniques to extract features for assessing attention and emotional state. The input data are gaze, facial expression, and voice tone, and the output is the analyzed emotional state and attention level.

[0169] Step 3:

[0170] Based on the analysis results, the server classifies the user's learning style, for example, into categories such as visual, auditory, concrete thinking, abstract thinking, etc. The input data are the emotional state and concentration level of the analysis results, and the output is the classification result of the user's learning style.

[0171] Step 4:

[0172] The server generates an individually optimized learning plan based on the classified learning style. For example, it creates a plan with more diagrams and video materials for visual users, and a plan with more practical problems for users who prefer concrete thinking. It uses a generative AI model to create prompts and input data to suggest learning plans. The input data is the learning style classification result, and the output is an individually optimized learning plan.

[0173] Step 5:

[0174] The generated study plan is sent to the terminal, which then presents it to the user. The user then studies according to this plan. The input data is the individually optimized study plan, and the output is the study plan presented to the user.

[0175] Step 6:

[0176] While the user is engaged in learning activities, the device monitors their eye movements, facial expressions, and voice tone in real time using a built-in camera and microphone. If their concentration level drops, the device feeds that information back to the server. The input data are real-time eye movements, facial expressions, and voice tone, and the output is feedback to the server.

[0177] Step 7:

[0178] The server receives the feedback and immediately adjusts the learning plan as needed. For example, if the level of concentration drops, the server decides on an action such as inserting new material or questions or recommending a short break. The input data is the concentration assessment as feedback, and the output is an adjusted learning plan.

[0179] Step 8:

[0180] The adjusted learning plan is sent back to the terminal, and the terminal presents the new learning plan to the user. The input data is the adjusted learning plan, and the output is the new learning plan presented to the user.

[0181] This ensures that the user's learning activities are always optimized and learning efficiency is maximized.

[0182] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0183] This invention is an AI tutor system designed to significantly improve students' learning efficiency, and by combining it with an emotion engine, it provides even more effective learning support. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[0184] Data Collection Phase

[0185] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone to record the user's eye movements, facial expressions, voice tone, and even emotional state in real time. This data is then sent to the server in real time, where it is stored in a database.

[0186] Introducing the Emotion Engine

[0187] The server is equipped with an emotion engine that analyzes the received data and recognizes the user's emotions. The emotion engine classifies the user's emotional state based on changes in facial expressions and voice. Emotional data reveals the state in which the user is studying and is useful for providing effective learning support.

[0188] Data analysis phase

[0189] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, response data, and emotional state to identify the user's learning style, and also integrates emotional data generated by the emotion engine to assess the user's concentration and stress levels.

[0190] Optimization Phase

[0191] The server generates an individually optimized learning plan based on the analyzed learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials containing many concrete problems will be recommended. The generated learning plan is sent to the terminal and presented to the user.

[0192] Execution Phase

[0193] The user follows the presented study plan and carries out study activities. While studying, the device continuously monitors the user's eye movements, facial expressions, voice tone, and emotional data in real time. Based on this, the device evaluates the user's concentration level and emotional state and adjusts the study plan as necessary. For example, if the device determines that the user is under stress, it will immediately suggest taking a break or present a less difficult task.

[0194] Specific examples

[0195] As a specific example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying using history materials on his device, the device records his eye movements, facial expressions, tone of voice, and emotional state. This data is sent to the server in real time, and the server analyzes it to identify Student B's learning style and emotional state.

[0196] It is determined that Student B is able to concentrate when he places importance on specific examples and finds the material enjoyable emotionally. Based on this result, the server generates learning materials that incorporate specific historical episodes that are enjoyable, and sends them to the device as a learning plan. Student B then proceeds with his studies based on this plan.

[0197] While studying, the device monitors Student B's gaze, facial expressions, and emotional state in real time, and if it determines that Student B's concentration is declining or that he or she is under stress, it will present a new task or suggest a break. This process maximizes Student B's learning efficiency and improves learning outcomes.

[0198] As described above, the AI ​​tutor system that combines the emotion engine of the present invention improves learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[0199] The processing flow will be explained below.

[0200] Step 1:

[0201] The user logs in to the device and begins learning.

[0202] Step 2:

[0203] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, vocal tone, and emotional state in real time.

[0204] Step 3:

[0205] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[0206] Step 4:

[0207] The device transmits the collected data to the server in real time.

[0208] Step 5:

[0209] The server stores the received data in a database.

[0210] Step 6:

[0211] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style, and an emotion engine to identify the user's emotional state (e.g., stressed, relaxed, focused, etc.).

[0212] Step 7:

[0213] The server generates a personalized learning plan based on the user's learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials with many concrete problems will be recommended.

[0214] Step 8:

[0215] The server transmits the generated study plan to the terminal.

[0216] Step 9:

[0217] The device presents the user with the optimal learning plan and displays it on the screen.

[0218] Step 10:

[0219] The user proceeds with the learning activities based on the presented learning plan.

[0220] Step 11:

[0221] During the learning process, the device continues to monitor the user's eye movements, facial expressions, voice tone, and emotional data in real time.

[0222] Step 12:

[0223] The device assesses the user's concentration and emotional state and adjusts the study plan as needed. For example, if it detects a decline in concentration and stress, it will suggest a new task or a break.

[0224] Step 13:

[0225] After the learning session is over, the device sends any new data it has collected to the server.

[0226] Step 14:

[0227] The server stores the new data in a database and updates the analysis algorithm and emotion engine to improve the accuracy of the next learning plan.

[0228] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[0229] Example 2

[0230] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0231] Conventional learning support systems primarily collect and analyze students' learning data, but do not provide learning plans that reflect students' emotional states or make real-time adjustments. This makes it difficult to provide optimal learning support that takes into account students' concentration levels and stress levels, limiting improvements in learning efficiency.

[0232] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0233] In this invention, the server includes means for collecting learning data of students, means for analyzing the collected learning data to classify the learning style and emotional state of the students, and means for generating an optimal learning plan for each student based on the classified learning style and emotional state. This makes it possible to provide appropriate feedback and adjust the learning plan in real time based on the learning data and emotional data of the students.

[0234] "Learning data" refers to information such as all actions, inputs, answers, and progress of students during the learning process.

[0235] "Emotional state" refers to the psychological and emotional state of a student as analyzed from facial expressions, tone of voice, behavioral patterns, etc.

[0236] "Learning styles" refer to the methods or patterns in which students learn most effectively, and include categories such as visual, auditory, and tactile learning.

[0237] A "learning plan" is a plan that outlines the optimal way to proceed with materials and tasks based on a student's individual learning style and emotional state.

[0238] "Real-time monitoring" refers to the process of instantly collecting and analyzing student data during learning, and providing feedback and adjustments on the spot.

[0239] "Concentration" refers to the degree to which a student pays attention to their studies, and is assessed by factors such as eye movements and the degree to which attention is divided.

[0240] "Response" refers to all responses that the system can detect, such as a student's behavior, facial expressions, and tone of voice while learning.

[0241] "Academic performance data" refers to historical data such as a student's past learning outcomes, test scores, and evaluation results.

[0242] "Learning growth" refers to an evaluation indicator that shows how much a student has understood the learning content and improved their skills over a certain period of time.

[0243] "Individual optimization" refers to the process of customizing the most effective learning plans and materials based on each student's characteristics and situation.

[0244] The following describes an embodiment of the invention of an "AI tutor system combined with an emotion engine."

[0245] MODE FOR CARRYING OUT THE INVENTION

[0246] The present invention is an AI tutor system that generates an optimal learning plan based on a student's learning data and emotional data, and provides learning support tailored to each student. A specific example of this system is described below.

[0247] Hardware and software used

[0248] The main components of the system include servers, terminals, and users. The roles and technologies used by each component are described below.

[0249] Server: Analyzes data and generates learning plans. Specifically, PostgreSQL and MongoDB are used for database management, Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used for emotion analysis, and Python's pandas and scikit-learn are used for data analysis.

[0250] Device: Collects students' gaze, facial expressions, and voice data and sends it to the server in real time. It also plays a role in presenting an optimized learning plan. The device must have a camera and microphone.

[0251] Users: Students who carry out learning activities. Their data is recorded and analyzed by the system.

[0252] Program processing

[0253] 1. User login and learning begins

[0254] Users log in to their devices with their own accounts. After logging in, learning materials and assignments are presented, and the user is ready to begin learning.

[0255] 2. Data Collection

[0256] The device activates its built-in camera and microphone to record the user's eye movements, facial expressions, and voice tone in real time, and this data is immediately sent to the server.

[0257] 3. Data storage

[0258] The server stores the received data in a database, using database technologies such as PostgreSQL or MongoDB.

[0259] 4. Emotion analysis

[0260] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. It uses services such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer to classify emotions from facial expressions and vocal tones.

[0261] 5. Data analysis and learning style identification

[0262] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and emotional data to identify the user's learning style, using Python's pandas and scikit-learn.

[0263] 6. Generate a learning plan

[0264] The server generates an optimal learning plan for each user based on the analysis results and emotional data, resulting in customized learning materials and assignments for each user.

[0265] 7. Study plan presentation and real-time monitoring

[0266] The generated study plan is sent to the device and presented to the user. During the study, the device continuously monitors the user's gaze, facial expressions, and tone of voice, and adjusts the study plan in real time as needed.

[0267] Specific examples

[0268] As a concrete example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying history materials on his device, the device records his eye movements, facial expressions, and voice tone, and sends them to the server in real time. The server analyzes the data and identifies Student B's learning style and emotional state. It can be seen that Student B places importance on specific examples and is able to concentrate when he finds them emotionally enjoyable. Based on these results, the server generates learning materials that incorporate specific, enjoyable historical episodes and sends them to the device as a study plan.

[0269] While studying, the device monitors B's gaze, facial expressions, and emotional state in real time, and if it determines that B's concentration is declining or that he is under stress, it will present a new assignment or suggest a break. This maximizes the student's learning efficiency and improves learning outcomes.

[0270] Example prompts for generative AI models

[0271] Example prompt 1: "Analyze the user's learning style and emotional state to generate an optimal study plan."

[0272] Example prompt 2: "Assess user engagement using eye movement, facial expression, and emotional data and adjust learning plans accordingly."

[0273] As described above, the AI ​​tutor system that combines the emotion engine of the present invention can improve learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1: User logs in and begins learning

[0276] The user logs in to the learning device using their account information. The user inputs the account information and the device outputs a message indicating whether the login was successful or not. If the login is successful, the learning materials and assignments are displayed on the device, and the user is ready to begin learning.

[0277] Step 2: Data collection

[0278] The device activates the built-in camera and microphone to record the user's gaze movements, facial expressions, and voice tone in real time. The input is the user's gaze data, facial expression data, and voice data, and data processing involves capturing each data and applying an initial filter. The output is a formatted version of this data. This data is sent to the server in real time.

[0279] Step 3: Send and save data to the server

[0280] The device sends the collected gaze data, facial expression data, and voice data to the server in real time. The input is formatted gaze data, facial expression data, and voice data, which the server receives and stores in a database such as PostgreSQL or MongoDB. The output is the data stored in the database.

[0281] Step 4: Sentiment Analysis

[0282] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. The inputs are gaze data, facial expression data, and voice data, and analysis tools such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used to process the data. The output is data that indicates the user's emotional state.

[0283] Step 5: Analyze data and identify learning styles

[0284] The server uses a data analysis algorithm to integrate gaze, facial expression, voice tone, and emotional data. The inputs are gaze, facial expression, voice, and emotional state data, and Python's pandas and scikit-learn are used for data processing. The output is data that identifies the user's learning style.

[0285] Step 6: Generate a personalized learning plan

[0286] The server generates an optimal learning plan for the user based on the analysis results and emotional data. The input is learning style data and emotional state data, and an optimization algorithm is applied to calculate the data. The output is a customized learning plan, which includes specific learning materials and assignments.

[0287] Step 7: Send and present your study plan to your device

[0288] The generated study plan is sent from the server to the terminal. The input is the generated study plan, which the terminal receives and presents to the user. The output is the plan displayed on the user's screen. The user proceeds with their study based on this plan.

[0289] Step 8: Real-time monitoring and concentration assessment

[0290] The device continuously monitors the user's eye movements, facial expressions, and vocal tone in real time during training. The inputs are gaze data, facial expression data, and vocal data, which are sent to the server. The server reanalyzes these data and evaluates the user's concentration and emotional state. The output is updated concentration and emotional state data in real time.

[0291] Step 9: Adjust your study plan

[0292] The server evaluates the user's state based on the data received in real time and instantly adjusts the study plan. The input is updated concentration data and emotional state data, and a dynamic adjustment algorithm is used to calculate the data. The output is a new, adjusted study plan. If necessary, the device will present new tasks or suggest a break.

[0293] The above is the flow of processing in the system program and the specific operations at each step.

[0294] (Application example 2)

[0295] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0296] Conventional learning support systems have the problem that they do not sufficiently consider students' real-time emotional state or concentration level when generating learning plans or using data analysis methods to improve students' learning efficiency. Furthermore, they are unable to quickly adjust learning plans under specific circumstances, limiting their effectiveness in the learning process. The present invention aims to solve these problems and propose a system that provides optimal learning support for each student.

[0297] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the student's eye movements, facial expressions, and voice tone in real time using a camera and microphone built into the smart device, means for transmitting the collected data to the server and analyzing the student's emotional state using an emotion engine, means for instantly adjusting the study plan based on the student's real-time concentration and stress level during study, and means for generating specific prompt sentences for the student using a generative AI model to improve study efficiency. This enables individually optimized study support that takes into account the student's emotional state and concentration level.

[0298] A "smart device" is an electronic device that has a built-in camera and microphone and can collect real-time data and exchange information with a server via an internet connection.

[0299] A "camera" is an optical device used to capture images and videos, and is a device used to record eye movements and changes in facial expressions.

[0300] A "microphone" is a device for collecting sound and is used to record voice tones and speech.

[0301] A "server" is a computer system that stores and processes data, and receives and analyzes data sent from terminals.

[0302] An "emotion engine" is software that includes an algorithm that analyzes a user's emotional state from collected data such as eye movements, facial expressions, and tone of voice, and classifies emotions.

[0303] "Concentration" is an index that indicates how much a user is concentrating on a learning activity, and is an element that is evaluated by the emotion engine.

[0304] "Stress level" is an index that indicates the degree of stress a user feels while studying, and is an element that is evaluated through the emotion engine.

[0305] "Generative AI model" means an artificial intelligence algorithm that generates optimal prompts and learning plans based on collected data.

[0306] A "prompt" is a sentence created by a generative AI model that provides specific instructions or suggestions to the user.

[0307] This invention realizes a system for improving students' learning efficiency. The main components of the system are a server, a smart device, and a user.

[0308] First, the user logs in to their smart device and begins learning. During this process, the smart device's built-in camera and microphone are used to record the user's eye movements, facial expressions, and tone of voice in real time. This data is then immediately sent to the server.

[0309] The server analyzes the received data using an emotion engine, which analyzes the user's emotional state based on eye movements, facial expressions, and tone of voice, and evaluates their concentration and stress levels in real time. This process allows the server to understand the emotional state of the students.

[0310] The server then uses the analyzed data to classify the student's learning style and generate an individually optimized study plan. The study plan is adjusted in real time, taking into account the user's emotional state and concentration level. For example, if the user is feeling stressed, the server can present them with a less difficult task or suggest a break.

[0311] The generative AI model generates appropriate prompts based on user data, providing students with specific instructions and suggestions to improve their learning efficiency. Below is an example of a prompt:

[0312] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[0313] The hardware used to realize this system is a smart device with a built-in camera and microphone. The software is a server that implements OpenCV (an image processing library), Requests (an HTTP library), and an emotion engine. The entire process, from data collection to analysis and feedback, works together to maximize learning efficiency.

[0314] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0315] Step 1:

[0316] A user logs in to a smart device and starts learning. At this time, the user gives permission to use the smart device's camera and microphone. The input is the login information and smart device's access permission, and the output is the system login status.

[0317] Step 2:

[0318] The device activates a camera and microphone to record the user's gaze, facial expressions, and voice tone in real time. This data is converted into a digital format and prepared for further analysis. The input is the user's gaze, facial expressions, and voice tone, and the output is gaze data, facial expression data, and voice data in digital data format.

[0319] Step 3:

[0320] The device transmits the collected data to the server in real time. This process includes data compression and encryption to ensure data security. The input is gaze data, facial expression data, and voice data in digital format, and the output is the completed transmission status to the server.

[0321] Step 4:

[0322] The server analyzes the received data using an emotion engine. The emotion engine evaluates the user's emotional state from eye movements, facial expressions, and vocal tone, and calculates the user's concentration and stress levels in real time. The input is the data sent to the server, and the output is the user's emotional state, concentration, and stress levels.

[0323] Step 5:

[0324] The server uses the analyzed data to classify the user's learning style and generate an individually optimized learning plan, taking into account past learning history and grade data. The input is the user's emotional state, concentration level, stress level, and past learning data, and the output is an individually optimized learning plan.

[0325] Step 6:

[0326] The server sends the generated lesson plan to the terminal and presents it to the user. The terminal receives it and displays it to the user in visual and auditory form. The input is the generated lesson plan, and the output is the display form to the user.

[0327] Step 7:

[0328] As the user continues learning, the device monitors the user's eye movements, facial expressions, and tone of voice in real time and sends this data to the server. The input is the user's real-time data, and the output is continuous data transmission to the server.

[0329] Step 8:

[0330] The server continuously analyzes the user's real-time data and instantly adjusts the study plan based on their concentration and stress level. For example, if the user feels stressed, it generates a prompt suggesting a break. The input is the user data sent in real time, and the output is the adjusted study plan and prompt.

[0331] Example prompt sentence:

[0332] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[0333] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0334] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0335] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0336] [Second embodiment]

[0337] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0338] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0339] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0340] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0341] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0342] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0343] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0344] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0345] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0346] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0347] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0348] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0349] This AI tutor system provides learners (users) with individually optimized learning plans and is designed to improve students' learning efficiency. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[0350] Data Collection Phase

[0351] When a user logs in to a device and begins learning, the device prepares to record their learning activities. Specifically, the device uses the built-in camera and microphone to collect information such as the user's eye movements, facial expressions, and voice tone. This data is sent to the server in real time, and the server stores it in a database.

[0352] Data analysis phase

[0353] The server uses a specific algorithm to analyze the collected learning data. The data analysis algorithm identifies the user's learning style (e.g., "visual," "auditory," "abstract thinking," "concrete thinking," etc.) and evaluates their concentration level and emotional state. Based on these results, the server classifies the user's learning style.

[0354] Optimization Phase

[0355] The server generates an individually optimized learning plan based on the analyzed learning style. This includes learning content and schedules that differ for each user. For example, a user who prefers concrete thinking can be provided with learning materials that include many concrete problems. The generated learning plan is sent to the terminal and presented to the user.

[0356] Execution Phase

[0357] The user follows the presented study plan. While studying, the device continuously monitors the user's eye movements, facial expressions, tone of voice, and other factors in real time. Based on this, the device evaluates the user's level of concentration and immediately adjusts the study plan as necessary. For example, if the user's level of concentration decreases, the device will recommend that the user take a break or present a new problem.

[0358] Specific examples

[0359] As a specific example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math study materials on his device, the device records his eye movements, facial expressions, tone of voice, and other data. This data is sent to the server in real time. The server analyzes the collected data and determines that Student A prefers concrete thinking. Based on this result, the server generates an optimal study plan for Student A. Specifically, it provides many study materials containing many actual math problems, and presents them with gradually increasing difficulty levels. This study plan is then displayed to Student A via his device.

[0360] If Student A's concentration level drops as he or she studies, the device will detect this change in real time and provide immediate feedback, such as inserting an easy question or informing the student to take a short break. This maximizes Student A's learning efficiency and improves their learning outcomes.

[0361] Through the above process, this AI tutor system provides each student with the optimal learning method, thereby overcoming the drawbacks of a uniform learning style and significantly improving students' learning efficiency.

[0362] The processing flow will be explained below.

[0363] Step 1:

[0364] The user logs in to the device and begins learning.

[0365] Step 2:

[0366] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, and voice tone in real time.

[0367] Step 3:

[0368] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[0369] Step 4:

[0370] The device transmits the collected data to the server in real time.

[0371] Step 5:

[0372] The server stores the received data in a database.

[0373] Step 6:

[0374] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style.

[0375] Step 7:

[0376] The server generates a personalized learning plan based on the user's learning style, for example, recommending learning materials with many concrete problems to a user who prefers concrete thinking.

[0377] Step 8:

[0378] The server transmits the generated study plan to the terminal.

[0379] Step 9:

[0380] The device presents the user with the optimal learning plan and displays it on the screen.

[0381] Step 10:

[0382] The user proceeds with the learning activities based on the presented learning plan.

[0383] Step 11:

[0384] During the learning process, the device continues to monitor the user's eye movements, facial expressions, and voice tone in real time.

[0385] Step 12:

[0386] The device assesses the user's level of concentration and response and adjusts the learning plan as needed, for example presenting new tasks or suggesting a break if concentration levels drop.

[0387] Step 13:

[0388] After the learning session is over, the device sends any new data it has collected to the server.

[0389] Step 14:

[0390] The server stores the new data in a database and updates the analysis algorithm to improve the accuracy of the next learning plan.

[0391] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[0392] Example 1

[0393] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0394] With conventional learning systems, it was difficult to grasp the learning style and concentration level of each learner in real time and dynamically adjust the learning plan based on that. As a result, learners were unable to obtain an optimal learning environment, and learning efficiency could not be sufficiently improved.

[0395] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0396] In this invention, the server includes means for collecting learner learning data, means for analyzing the collected learning data and classifying the learner's learning style, and means for generating an optimal learning plan for each learner based on the classified learning style. This makes it possible to monitor the learner's eye movements, facial expressions, and tone of voice in real time. Furthermore, by analyzing the collected data in real time and dynamically adjusting the learning plan, it is possible to provide the learner with an optimal learning experience.

[0397] A "learner" is a person who engages in learning activities to acquire specific knowledge or skills.

[0398] "Learning data" refers to information such as learning content, learning progress, eye movements, facial expressions, and vocal tone that is generated when a learner engages in learning activities.

[0399] "Means for collection" refers to a method or device for acquiring learner learning data using hardware such as a camera or microphone.

[0400] "Means for analyzing" refers to a method or device that processes collected learning data using computer algorithms to evaluate learning style and concentration.

[0401] A "study plan" refers to a plan that compiles optimal learning content and schedules based on a learner's learning style and concentration level.

[0402] "Means for generating" refers to a method or device for creating an optimal learning plan for a learner based on the analysis results.

[0403] "Presenting means" refers to a method or device for displaying the generated lesson plan to a learner.

[0404] "Means of real-time monitoring" refers to a method or device that checks the eye movements, facial expressions, tone of voice, etc. of learners in real time while they are studying, and collects that data.

[0405] "Dynamic adjustment means" refers to a method or device that instantly and adaptively modifies learning plans and content based on data collected in real time.

[0406] This invention is an AI tutor system that provides learners with individually optimized learning plans. The main components of the system are a server, a terminal, and a user.

[0407] Data Collection Phase

[0408] When a user logs in to a device and begins studying, the device begins recording their study activities. Specifically, the device's built-in camera and microphone are used to collect the user's eye movements, facial expressions, and tone of voice. This data is sent in real time to a server, which then stores it in a database. For example, the camera can track the user's eye movements while the microphone monitors changes in the tone of their voice, allowing the system to measure the user's interest and concentration.

[0409] Data analysis phase

[0410] The server uses specific algorithms to analyze the collected learning data. For example, it uses image processing algorithms to analyze the user's facial expressions and voice recognition algorithms to analyze the user's tone of voice. This analysis identifies the user's learning style (visual, auditory, abstract thinking, concrete thinking, etc.) and evaluates their concentration level and emotional state. For example, if a user responds more to visual information, they will be classified as "visual."

[0411] Optimization Phase

[0412] The server generates an individually optimized learning plan based on the analyzed learning style. This plan includes learning content and schedules that differ for each user. For example, for a user who prefers concrete thinking, learning materials containing many concrete problems are provided. The generated learning plan is sent to the terminal and presented to the user.

[0413] Execution Phase

[0414] The user follows the presented study plan as they study, and the device continues to monitor them as they do so. The device collects eye movements, facial expressions, tone of voice, and other data in real time, and evaluates the user's level of concentration based on this information. If the user's level of concentration decreases, the device immediately provides feedback, recommending a break or presenting a new problem. For example, if the user's eye movements are frequent, it will determine that the user is distracted and suggest a break.

[0415] Specific examples

[0416] As a concrete example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math materials on his device, the device records his eye movements and facial expressions with a camera and his tone of voice with a microphone. This data is sent to the server in real time, and the server analyzes it. If the analysis determines that Student A prefers concrete thinking, the server generates a study plan that includes many concrete problems and sends it to the device. The device presents this plan to Student A and continues to monitor his concentration level in real time while he studies. If his concentration level drops, the device immediately suggests a break or presents new problems.

[0417] Prompts for generative AI models

[0418] Below are the prompts for generating a lesson plan using this system:

[0419] Prompt: Student A struggles with math and has a concrete learning style. To help him study effectively, generate a study plan that is optimized for him. This plan should include specific problems that increase in difficulty, starting with concepts he's new to. It should also include actions to take if he loses focus (such as inserting easier problems or recommending breaks).

[0420] In this way, this AI tutoring system can maximize learners' learning efficiency by providing an individually optimized learning experience.

[0421] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0422] Step 1:

[0423] The user logs in to the device and begins learning. The device receives the user's login information and is ready to proceed to the next step. The input is the user's ID and password, and the output is a signal to start the learning session.

[0424] Step 2:

[0425] The device activates its built-in camera and microphone to collect the user's eye movements, facial expressions, and voice tone. The input is biometric information from the user's learning activity, and the output is learning data such as eye movements and voice tone. The device begins collecting this data in real time.

[0426] Step 3:

[0427] The device sends the collected learning data to the server in real time. The server stores the received data in a database. The input is the learning data sent from the device, and the output is the data stored in the database. The stored information is stored with a timestamp.

[0428] Step 4:

[0429] The server retrieves the stored training data and begins analysis using a specific algorithm. The input is the stored training data, and the output is the data analysis results. Specifically, the image analysis algorithm analyzes the user's facial expression, and the voice analysis algorithm analyzes the voice tone.

[0430] Step 5:

[0431] The server identifies the user's learning style based on the analysis results. The input is the data analysis results, and the output is the identified learning style category (visual, auditory, abstract thinking, concrete thinking, etc.). In this process, a score is assigned to each learning style.

[0432] Step 6:

[0433] The server then evaluates the user's concentration and emotional state. The input is the detailed results of the analysis algorithm, and the output is an assessment of the user's concentration and emotional state. For example, it can determine whether the user is distracted from camera footage and infer stress levels from the tone of the user's voice.

[0434] Step 7:

[0435] The server generates an individually optimized learning plan based on the analysis results. The input is the assessment results of concentration level and learning style, and the output is an individualized learning plan. For example, for visual users, learning materials with many illustrations are selected.

[0436] Step 8:

[0437] The server sends the generated learning plan to the terminal and presents it to the user. The input is the personalized learning plan, and the output is the learning plan displayed on the terminal. The terminal displays a notification to prompt the user to confirm the plan.

[0438] Step 9:

[0439] The user performs learning activities according to the presented learning plan. The input is the displayed learning plan, and the output is the learning completion status and progress data. As the user progresses with their learning, the device continues to collect data such as eye movements, facial expressions, and voice tone.

[0440] Step 10:

[0441] The device evaluates the user's level of concentration based on real-time data and instantly adjusts the learning plan as needed. The input is the latest learning data collected in real time, and the output is an updated learning plan and feedback. For example, if the user's level of concentration decreases, the device will immediately respond by recommending a break or presenting a new problem.

[0442] (Application example 1)

[0443] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0444] Conventional online learning systems have difficulty fully understanding each student's learning style, concentration level, and emotional state. Furthermore, they are unable to provide each student with a personalized learning plan in real time, potentially reducing their learning efficiency. Furthermore, they lack a way to instantly adjust learning plans based on students' concentration levels and responses, making it difficult to provide effective learning support.

[0445] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0446] In this invention, the server includes means for collecting the learner's gaze, facial expression, and tone of voice using a built-in camera and microphone; means for analyzing the collected gaze, facial expression, and tone of voice to evaluate the learner's concentration and emotional state; means for analyzing the collected learning data using a specific algorithm and classifying the user's learning style; means for generating an individually optimized learning plan based on the classified learning style; and means for transmitting the generated learning plan to a terminal and presenting it to the user. This makes it possible to grasp the user's learning style, concentration, and emotional state in real time and provide an optimal learning plan based on that. It also makes it possible to instantly adjust the learning plan based on the user's concentration and response, maximizing learning efficiency.

[0447] "Learning data" refers to data generated when a user learns, and includes eye movements, facial expressions, voice tones, operation history, and the like.

[0448] "Learning style" is a pattern that indicates how a user can learn most effectively, and includes classifications such as visual, auditory, concrete thinking, and abstract thinking.

[0449] A "study plan" is a plan that indicates optimal study content and schedule for a user, and includes learning materials and instruction content customized based on the user's learning style and concentration level.

[0450] The "gaze" is information indicating the point at which the user is looking, and is the movement of the viewpoint acquired using the built-in camera.

[0451] "Facial expression" is information that indicates the state of the user's face, and indicates emotions and concentration.

[0452] "Voice tone" refers to the tone of the voice uttered by the user, and serves as an indicator of emotions and concentration level.

[0453] "Level of concentration" is an index that evaluates how focused a user is on their studies, and is evaluated based on data such as gaze, facial expression, and tone of voice.

[0454] A "prompt sentence" is an instruction sentence input into a generative AI model, and is text used to obtain appropriate generated results according to the purpose.

[0455] The present invention is a system constructed to provide learners (users) with individually optimized study plans. A specific embodiment of this system will be described in detail below.

[0456] Overall system configuration

[0457] The main components of the system are the server, the terminal, and the user. The server is responsible for analyzing data and generating learning plans, the terminal is responsible for collecting data and presenting learning plans, and the user is the entity that carries out the learning.

[0458] Data Collection Phase

[0459] When a user logs in to a device and begins learning, the built-in camera and microphone are activated to collect data related to the learning activity. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. This data is sent to the server in real time.

[0460] Data analysis phase

[0461] The server uses specific algorithms to analyze the transmitted data, such as gaze, facial expression, and voice tone. The analysis results are used to evaluate the user's learning style and concentration level, and the user's learning style is then classified based on the evaluation results. Computer vision technology is used to analyze gaze and facial expression, and natural language processing (NLP) technology is used to analyze voice tone.

[0462] Optimization Phase

[0463] Based on the classified learning style, the server generates an individually optimized learning plan. For example, it provides learning materials containing many practical problems to a user who prefers concrete thinking, and creates a plan containing many diagrams and video materials for a user who finds visual instructions effective. The generated learning plan is sent to the terminal and presented to the user.

[0464] Execution Phase

[0465] The user carries out learning activities according to the presented learning plan. While studying, the device uses a camera and microphone to continuously monitor the user's gaze, facial expressions, and tone of voice in real time. If the user's level of concentration decreases, the device detects the change and sends feedback to the server. The server immediately adjusts the learning plan based on this feedback, and the device presents a new plan to the user.

[0466] Specific examples

[0467] For example, let's imagine that Student A, who is not good at math, uses this system. When Student A begins studying using math teaching materials on his / her device, the camera captures Student A's eye movements and facial expressions, and the microphone collects his / her voice tone. This data is sent to the server, which analyzes the results and determines that Student A prefers concrete thinking. Based on this evaluation, the server generates teaching materials that are optimal for Student A, including many concrete problems, and presents them to him / her via his / her device.

[0468] Prompt Sentence Examples

[0469] An example of a prompt to be input to the AI ​​model is as follows:

[0470] Collect video data of elementary school students learning math and perform emotion recognition. Next, analyze the tone from the audio data to obtain the average audio amplitude. Provide an optimized learning plan based on the obtained emotion data and audio tone.

[0471] Video data: {video_frame}

[0472] Audio data: {audio_data}

[0473] Emotion recognition result: {emotion}

[0474] Average audio amplitude: {avg_audio_amplitude}

[0475] The above steps realize a system that can provide a learning experience optimized for each user and improve learning efficiency.

[0476] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0477] Step 1:

[0478] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. These data are sent to the server in real time. The input data are eye movements, facial expressions, and voice tones, and the output is the collected data.

[0479] Step 2:

[0480] The server analyzes the received data. Gaze and facial expression data are processed by computer vision algorithms to identify the user's emotional state using emotion recognition models. Voice tone data is analyzed using natural language processing (NLP) techniques to extract features for assessing attention and emotional state. The input data are gaze, facial expression, and voice tone, and the output is the analyzed emotional state and attention level.

[0481] Step 3:

[0482] Based on the analysis results, the server classifies the user's learning style, for example, into categories such as visual, auditory, concrete thinking, abstract thinking, etc. The input data are the emotional state and concentration level of the analysis results, and the output is the classification result of the user's learning style.

[0483] Step 4:

[0484] The server generates an individually optimized learning plan based on the classified learning style. For example, it creates a plan with more diagrams and video materials for visual users, and a plan with more practical problems for users who prefer concrete thinking. It uses a generative AI model to create prompts and input data to suggest learning plans. The input data is the learning style classification result, and the output is an individually optimized learning plan.

[0485] Step 5:

[0486] The generated study plan is sent to the terminal, which then presents it to the user. The user then studies according to this plan. The input data is the individually optimized study plan, and the output is the study plan presented to the user.

[0487] Step 6:

[0488] While the user is engaged in learning activities, the device monitors their eye movements, facial expressions, and voice tone in real time using a built-in camera and microphone. If their concentration level drops, the device feeds that information back to the server. The input data are real-time eye movements, facial expressions, and voice tone, and the output is feedback to the server.

[0489] Step 7:

[0490] The server receives the feedback and immediately adjusts the learning plan as needed. For example, if the level of concentration drops, the server decides on an action such as inserting new material or questions or recommending a short break. The input data is the concentration assessment as feedback, and the output is an adjusted learning plan.

[0491] Step 8:

[0492] The adjusted learning plan is sent back to the terminal, and the terminal presents the new learning plan to the user. The input data is the adjusted learning plan, and the output is the new learning plan presented to the user.

[0493] This ensures that the user's learning activities are always optimized and learning efficiency is maximized.

[0494] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0495] This invention is an AI tutor system designed to significantly improve students' learning efficiency, and by combining it with an emotion engine, it provides even more effective learning support. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[0496] Data Collection Phase

[0497] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone to record the user's eye movements, facial expressions, voice tone, and even emotional state in real time. This data is then sent to the server in real time, where it is stored in a database.

[0498] Introducing the Emotion Engine

[0499] The server is equipped with an emotion engine that analyzes the received data and recognizes the user's emotions. The emotion engine classifies the user's emotional state based on changes in facial expressions and voice. Emotional data reveals the state in which the user is studying and is useful for providing effective learning support.

[0500] Data analysis phase

[0501] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, response data, and emotional state to identify the user's learning style, and also integrates emotional data generated by the emotion engine to assess the user's concentration and stress levels.

[0502] Optimization Phase

[0503] The server generates an individually optimized learning plan based on the analyzed learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials containing many concrete problems will be recommended. The generated learning plan is sent to the terminal and presented to the user.

[0504] Execution Phase

[0505] The user follows the presented study plan and carries out study activities. While studying, the device continuously monitors the user's eye movements, facial expressions, voice tone, and emotional data in real time. Based on this, the device evaluates the user's concentration level and emotional state and adjusts the study plan as necessary. For example, if the device determines that the user is under stress, it will immediately suggest taking a break or present a less difficult task.

[0506] Specific examples

[0507] As a specific example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying using history materials on his device, the device records his eye movements, facial expressions, tone of voice, and emotional state. This data is sent to the server in real time, and the server analyzes it to identify Student B's learning style and emotional state.

[0508] It is determined that Student B is able to concentrate when he places importance on specific examples and finds the material enjoyable emotionally. Based on this result, the server generates learning materials that incorporate specific historical episodes that are enjoyable, and sends them to the device as a learning plan. Student B then proceeds with his studies based on this plan.

[0509] While studying, the device monitors Student B's gaze, facial expressions, and emotional state in real time, and if it determines that Student B's concentration is declining or that he or she is under stress, it will present a new task or suggest a break. This process maximizes Student B's learning efficiency and improves learning outcomes.

[0510] As described above, the AI ​​tutor system that combines the emotion engine of the present invention improves learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[0511] The processing flow will be explained below.

[0512] Step 1:

[0513] The user logs in to the device and begins learning.

[0514] Step 2:

[0515] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, vocal tone, and emotional state in real time.

[0516] Step 3:

[0517] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[0518] Step 4:

[0519] The device transmits the collected data to the server in real time.

[0520] Step 5:

[0521] The server stores the received data in a database.

[0522] Step 6:

[0523] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style, and an emotion engine to identify the user's emotional state (e.g., stressed, relaxed, focused, etc.).

[0524] Step 7:

[0525] The server generates a personalized learning plan based on the user's learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials with many concrete problems will be recommended.

[0526] Step 8:

[0527] The server transmits the generated study plan to the terminal.

[0528] Step 9:

[0529] The device presents the user with the optimal learning plan and displays it on the screen.

[0530] Step 10:

[0531] The user proceeds with the learning activities based on the presented learning plan.

[0532] Step 11:

[0533] During the learning process, the device continues to monitor the user's eye movements, facial expressions, voice tone, and emotional data in real time.

[0534] Step 12:

[0535] The device assesses the user's concentration and emotional state and adjusts the study plan as needed. For example, if it detects a decline in concentration and stress, it will suggest a new task or a break.

[0536] Step 13:

[0537] After the learning session is over, the device sends any new data it has collected to the server.

[0538] Step 14:

[0539] The server stores the new data in a database and updates the analysis algorithm and emotion engine to improve the accuracy of the next learning plan.

[0540] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[0541] Example 2

[0542] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0543] Conventional learning support systems primarily collect and analyze students' learning data, but do not provide learning plans that reflect students' emotional states or make real-time adjustments. This makes it difficult to provide optimal learning support that takes into account students' concentration levels and stress levels, limiting improvements in learning efficiency.

[0544] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0545] In this invention, the server includes means for collecting learning data of students, means for analyzing the collected learning data to classify the learning style and emotional state of the students, and means for generating an optimal learning plan for each student based on the classified learning style and emotional state. This makes it possible to provide appropriate feedback and adjust the learning plan in real time based on the learning data and emotional data of the students.

[0546] "Learning data" refers to information such as all actions, inputs, answers, and progress of students during the learning process.

[0547] "Emotional state" refers to the psychological and emotional state of a student as analyzed from facial expressions, tone of voice, behavioral patterns, etc.

[0548] "Learning styles" refer to the methods or patterns in which students learn most effectively, and include categories such as visual, auditory, and tactile learning.

[0549] A "learning plan" is a plan that outlines the optimal way to proceed with materials and tasks based on a student's individual learning style and emotional state.

[0550] "Real-time monitoring" refers to the process of instantly collecting and analyzing student data during learning, and providing feedback and adjustments on the spot.

[0551] "Concentration" refers to the degree to which a student pays attention to their studies, and is assessed by factors such as eye movements and the degree to which attention is divided.

[0552] "Response" refers to all responses that the system can detect, such as a student's behavior, facial expressions, and tone of voice while learning.

[0553] "Academic performance data" refers to historical data such as a student's past learning outcomes, test scores, and evaluation results.

[0554] "Learning growth" refers to an evaluation indicator that shows how much a student has understood the learning content and improved their skills over a certain period of time.

[0555] "Individual optimization" refers to the process of customizing the most effective learning plans and materials based on each student's characteristics and situation.

[0556] The following describes an embodiment of the invention of an "AI tutor system combined with an emotion engine."

[0557] MODE FOR CARRYING OUT THE INVENTION

[0558] The present invention is an AI tutor system that generates an optimal learning plan based on a student's learning data and emotional data, and provides learning support tailored to each student. A specific example of this system is described below.

[0559] Hardware and software used

[0560] The main components of the system include servers, terminals, and users. The roles and technologies used by each component are described below.

[0561] Server: Analyzes data and generates learning plans. Specifically, PostgreSQL and MongoDB are used for database management, Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used for emotion analysis, and Python's pandas and scikit-learn are used for data analysis.

[0562] Device: Collects students' gaze, facial expressions, and voice data and sends it to the server in real time. It also plays a role in presenting an optimized learning plan. The device must have a camera and microphone.

[0563] Users: Students who carry out learning activities. Their data is recorded and analyzed by the system.

[0564] Program processing

[0565] 1. User login and learning begins

[0566] Users log in to their devices with their own accounts. After logging in, learning materials and assignments are presented, and the user is ready to begin learning.

[0567] 2. Data Collection

[0568] The device activates its built-in camera and microphone to record the user's eye movements, facial expressions, and voice tone in real time, and this data is immediately sent to the server.

[0569] 3. Data storage

[0570] The server stores the received data in a database, using database technologies such as PostgreSQL or MongoDB.

[0571] 4. Emotion analysis

[0572] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. It uses services such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer to classify emotions from facial expressions and vocal tones.

[0573] 5. Data analysis and learning style identification

[0574] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and emotional data to identify the user's learning style, using Python's pandas and scikit-learn.

[0575] 6. Generate a learning plan

[0576] The server generates an optimal learning plan for each user based on the analysis results and emotional data, resulting in customized learning materials and assignments for each user.

[0577] 7. Study plan presentation and real-time monitoring

[0578] The generated study plan is sent to the device and presented to the user. During the study, the device continuously monitors the user's gaze, facial expressions, and tone of voice, and adjusts the study plan in real time as needed.

[0579] Specific examples

[0580] As a concrete example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying history materials on his device, the device records his eye movements, facial expressions, and voice tone, and sends them to the server in real time. The server analyzes the data and identifies Student B's learning style and emotional state. It can be seen that Student B places importance on specific examples and is able to concentrate when he finds them emotionally enjoyable. Based on these results, the server generates learning materials that incorporate specific, enjoyable historical episodes and sends them to the device as a study plan.

[0581] While studying, the device monitors B's gaze, facial expressions, and emotional state in real time, and if it determines that B's concentration is declining or that he is under stress, it will present a new assignment or suggest a break. This maximizes the student's learning efficiency and improves learning outcomes.

[0582] Example prompts for generative AI models

[0583] Example prompt 1: "Analyze the user's learning style and emotional state to generate an optimal study plan."

[0584] Example prompt 2: "Assess user engagement using eye movement, facial expression, and emotional data and adjust learning plans accordingly."

[0585] As described above, the AI ​​tutor system that combines the emotion engine of the present invention can improve learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[0586] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0587] Step 1: User logs in and begins learning

[0588] The user logs in to the learning device using their account information. The user inputs the account information and the device outputs a message indicating whether the login was successful or not. If the login is successful, the learning materials and assignments are displayed on the device, and the user is ready to begin learning.

[0589] Step 2: Data collection

[0590] The device activates the built-in camera and microphone to record the user's gaze movements, facial expressions, and voice tone in real time. The input is the user's gaze data, facial expression data, and voice data, and data processing involves capturing each data and applying an initial filter. The output is a formatted version of this data. This data is sent to the server in real time.

[0591] Step 3: Send and save data to the server

[0592] The device sends the collected gaze data, facial expression data, and voice data to the server in real time. The input is formatted gaze data, facial expression data, and voice data, which the server receives and stores in a database such as PostgreSQL or MongoDB. The output is the data stored in the database.

[0593] Step 4: Sentiment Analysis

[0594] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. The inputs are gaze data, facial expression data, and voice data, and analysis tools such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used to process the data. The output is data that indicates the user's emotional state.

[0595] Step 5: Analyze data and identify learning styles

[0596] The server uses a data analysis algorithm to integrate gaze, facial expression, voice tone, and emotional data. The inputs are gaze, facial expression, voice, and emotional state data, and Python's pandas and scikit-learn are used for data processing. The output is data that identifies the user's learning style.

[0597] Step 6: Generate a personalized learning plan

[0598] The server generates an optimal learning plan for the user based on the analysis results and emotional data. The input is learning style data and emotional state data, and an optimization algorithm is applied to calculate the data. The output is a customized learning plan, which includes specific learning materials and assignments.

[0599] Step 7: Send and present your study plan to your device

[0600] The generated study plan is sent from the server to the terminal. The input is the generated study plan, which the terminal receives and presents to the user. The output is the plan displayed on the user's screen. The user proceeds with their study based on this plan.

[0601] Step 8: Real-time monitoring and concentration assessment

[0602] The device continuously monitors the user's eye movements, facial expressions, and vocal tone in real time during training. The inputs are gaze data, facial expression data, and vocal data, which are sent to the server. The server reanalyzes these data and evaluates the user's concentration and emotional state. The output is updated concentration and emotional state data in real time.

[0603] Step 9: Adjust your study plan

[0604] The server evaluates the user's state based on the data received in real time and instantly adjusts the study plan. The input is updated concentration data and emotional state data, and a dynamic adjustment algorithm is used to calculate the data. The output is a new, adjusted study plan. If necessary, the device will present new tasks or suggest a break.

[0605] The above is the flow of processing in the system program and the specific operations at each step.

[0606] (Application example 2)

[0607] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0608] Conventional learning support systems have the problem that they do not sufficiently consider students' real-time emotional state or concentration level when generating learning plans or using data analysis methods to improve students' learning efficiency. Furthermore, they are unable to quickly adjust learning plans under specific circumstances, limiting their effectiveness in the learning process. The present invention aims to solve these problems and propose a system that provides optimal learning support for each student.

[0609] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the student's eye movements, facial expressions, and voice tone in real time using a camera and microphone built into the smart device, means for transmitting the collected data to the server and analyzing the student's emotional state using an emotion engine, means for instantly adjusting the study plan based on the student's real-time concentration and stress level during study, and means for generating specific prompt sentences for the student using a generative AI model to improve study efficiency. This enables individually optimized study support that takes into account the student's emotional state and concentration level.

[0610] A "smart device" is an electronic device that has a built-in camera and microphone and can collect real-time data and exchange information with a server via an internet connection.

[0611] A "camera" is an optical device used to capture images and videos, and is a device used to record eye movements and changes in facial expressions.

[0612] A "microphone" is a device for collecting sound and is used to record voice tones and speech.

[0613] A "server" is a computer system that stores and processes data, and receives and analyzes data sent from terminals.

[0614] An "emotion engine" is software that includes an algorithm that analyzes a user's emotional state from collected data such as eye movements, facial expressions, and tone of voice, and classifies emotions.

[0615] "Concentration" is an index that indicates how much a user is concentrating on a learning activity, and is an element that is evaluated by the emotion engine.

[0616] "Stress level" is an index that indicates the degree of stress a user feels while studying, and is an element that is evaluated through the emotion engine.

[0617] "Generative AI model" means an artificial intelligence algorithm that generates optimal prompts and learning plans based on collected data.

[0618] A "prompt" is a sentence created by a generative AI model that provides specific instructions or suggestions to the user.

[0619] This invention realizes a system for improving students' learning efficiency. The main components of the system are a server, a smart device, and a user.

[0620] First, the user logs in to their smart device and begins learning. During this process, the smart device's built-in camera and microphone are used to record the user's eye movements, facial expressions, and tone of voice in real time. This data is then immediately sent to the server.

[0621] The server analyzes the received data using an emotion engine, which analyzes the user's emotional state based on eye movements, facial expressions, and tone of voice, and evaluates their concentration and stress levels in real time. This process allows the server to understand the emotional state of the students.

[0622] The server then uses the analyzed data to classify the student's learning style and generate an individually optimized study plan. The study plan is adjusted in real time, taking into account the user's emotional state and concentration level. For example, if the user is feeling stressed, the server can present them with a less difficult task or suggest a break.

[0623] The generative AI model generates appropriate prompts based on user data, providing students with specific instructions and suggestions to improve their learning efficiency. Below is an example of a prompt:

[0624] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[0625] The hardware used to realize this system is a smart device with a built-in camera and microphone. The software is a server that implements OpenCV (an image processing library), Requests (an HTTP library), and an emotion engine. The entire process, from data collection to analysis and feedback, works together to maximize learning efficiency.

[0626] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0627] Step 1:

[0628] A user logs in to a smart device and starts learning. At this time, the user gives permission to use the smart device's camera and microphone. The input is the login information and smart device's access permission, and the output is the system login status.

[0629] Step 2:

[0630] The device activates a camera and microphone to record the user's gaze, facial expressions, and voice tone in real time. This data is converted into a digital format and prepared for further analysis. The input is the user's gaze, facial expressions, and voice tone, and the output is gaze data, facial expression data, and voice data in digital data format.

[0631] Step 3:

[0632] The device transmits the collected data to the server in real time. This process includes data compression and encryption to ensure data security. The input is gaze data, facial expression data, and voice data in digital format, and the output is the completed transmission status to the server.

[0633] Step 4:

[0634] The server analyzes the received data using an emotion engine. The emotion engine evaluates the user's emotional state from eye movements, facial expressions, and vocal tone, and calculates the user's concentration and stress levels in real time. The input is the data sent to the server, and the output is the user's emotional state, concentration, and stress levels.

[0635] Step 5:

[0636] The server uses the analyzed data to classify the user's learning style and generate an individually optimized learning plan, taking into account past learning history and grade data. The input is the user's emotional state, concentration level, stress level, and past learning data, and the output is an individually optimized learning plan.

[0637] Step 6:

[0638] The server sends the generated lesson plan to the terminal and presents it to the user. The terminal receives it and displays it to the user in visual and auditory form. The input is the generated lesson plan, and the output is the display form to the user.

[0639] Step 7:

[0640] As the user continues learning, the device monitors the user's eye movements, facial expressions, and tone of voice in real time and sends this data to the server. The input is the user's real-time data, and the output is continuous data transmission to the server.

[0641] Step 8:

[0642] The server continuously analyzes the user's real-time data and instantly adjusts the study plan based on their concentration and stress level. For example, if the user feels stressed, it generates a prompt suggesting a break. The input is the user data sent in real time, and the output is the adjusted study plan and prompt.

[0643] Example prompt sentence:

[0644] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[0645] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0646] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0647] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0648] [Third embodiment]

[0649] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0650] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0651] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0652] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0653] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0654] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0655] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0656] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0657] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0658] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0659] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0660] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0661] This AI tutor system provides learners (users) with individually optimized learning plans and is designed to improve students' learning efficiency. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[0662] Data Collection Phase

[0663] When a user logs in to a device and begins learning, the device prepares to record their learning activities. Specifically, the device uses the built-in camera and microphone to collect information such as the user's eye movements, facial expressions, and voice tone. This data is sent to the server in real time, and the server stores it in a database.

[0664] Data analysis phase

[0665] The server uses a specific algorithm to analyze the collected learning data. The data analysis algorithm identifies the user's learning style (e.g., "visual," "auditory," "abstract thinking," "concrete thinking," etc.) and evaluates their concentration level and emotional state. Based on these results, the server classifies the user's learning style.

[0666] Optimization Phase

[0667] The server generates an individually optimized learning plan based on the analyzed learning style. This includes learning content and schedules that differ for each user. For example, a user who prefers concrete thinking can be provided with learning materials that include many concrete problems. The generated learning plan is sent to the terminal and presented to the user.

[0668] Execution Phase

[0669] The user follows the presented study plan. While studying, the device continuously monitors the user's eye movements, facial expressions, tone of voice, and other factors in real time. Based on this, the device evaluates the user's level of concentration and immediately adjusts the study plan as necessary. For example, if the user's level of concentration decreases, the device will recommend that the user take a break or present a new problem.

[0670] Specific examples

[0671] As a specific example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math study materials on his device, the device records his eye movements, facial expressions, tone of voice, and other data. This data is sent to the server in real time. The server analyzes the collected data and determines that Student A prefers concrete thinking. Based on this result, the server generates an optimal study plan for Student A. Specifically, it provides many study materials containing many actual math problems, and presents them with gradually increasing difficulty levels. This study plan is then displayed to Student A via his device.

[0672] If Student A's concentration level drops as he or she studies, the device will detect this change in real time and provide immediate feedback, such as inserting an easy question or informing the student to take a short break. This maximizes Student A's learning efficiency and improves their learning outcomes.

[0673] Through the above process, this AI tutor system provides each student with the optimal learning method, thereby overcoming the drawbacks of a uniform learning style and significantly improving students' learning efficiency.

[0674] The processing flow will be explained below.

[0675] Step 1:

[0676] The user logs in to the device and begins learning.

[0677] Step 2:

[0678] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, and voice tone in real time.

[0679] Step 3:

[0680] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[0681] Step 4:

[0682] The device transmits the collected data to the server in real time.

[0683] Step 5:

[0684] The server stores the received data in a database.

[0685] Step 6:

[0686] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style.

[0687] Step 7:

[0688] The server generates a personalized learning plan based on the user's learning style, for example, recommending learning materials with many concrete problems to a user who prefers concrete thinking.

[0689] Step 8:

[0690] The server transmits the generated study plan to the terminal.

[0691] Step 9:

[0692] The device presents the user with the optimal learning plan and displays it on the screen.

[0693] Step 10:

[0694] The user proceeds with the learning activities based on the presented learning plan.

[0695] Step 11:

[0696] During the learning process, the device continues to monitor the user's eye movements, facial expressions, and voice tone in real time.

[0697] Step 12:

[0698] The device assesses the user's level of concentration and response and adjusts the learning plan as needed, for example presenting new tasks or suggesting a break if concentration levels drop.

[0699] Step 13:

[0700] After the learning session is over, the device sends any new data it has collected to the server.

[0701] Step 14:

[0702] The server stores the new data in a database and updates the analysis algorithm to improve the accuracy of the next learning plan.

[0703] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[0704] Example 1

[0705] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0706] With conventional learning systems, it was difficult to grasp the learning style and concentration level of each learner in real time and dynamically adjust the learning plan based on that. As a result, learners were unable to obtain an optimal learning environment, and learning efficiency could not be sufficiently improved.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0708] In this invention, the server includes means for collecting learner learning data, means for analyzing the collected learning data and classifying the learner's learning style, and means for generating an optimal learning plan for each learner based on the classified learning style. This makes it possible to monitor the learner's eye movements, facial expressions, and tone of voice in real time. Furthermore, by analyzing the collected data in real time and dynamically adjusting the learning plan, it is possible to provide the learner with an optimal learning experience.

[0709] A "learner" is a person who engages in learning activities to acquire specific knowledge or skills.

[0710] "Learning data" refers to information such as learning content, learning progress, eye movements, facial expressions, and vocal tone that is generated when a learner engages in learning activities.

[0711] "Means for collection" refers to a method or device for acquiring learner learning data using hardware such as a camera or microphone.

[0712] "Means for analyzing" refers to a method or device that processes collected learning data using computer algorithms to evaluate learning style and concentration.

[0713] A "study plan" refers to a plan that compiles optimal learning content and schedules based on a learner's learning style and concentration level.

[0714] "Means for generating" refers to a method or device for creating an optimal learning plan for a learner based on the analysis results.

[0715] "Presenting means" refers to a method or device for displaying the generated lesson plan to a learner.

[0716] "Means of real-time monitoring" refers to a method or device that checks the eye movements, facial expressions, tone of voice, etc. of learners in real time while they are studying, and collects that data.

[0717] "Dynamic adjustment means" refers to a method or device that instantly and adaptively modifies learning plans and content based on data collected in real time.

[0718] This invention is an AI tutor system that provides learners with individually optimized learning plans. The main components of the system are a server, a terminal, and a user.

[0719] Data Collection Phase

[0720] When a user logs in to a device and begins studying, the device begins recording their study activities. Specifically, the device's built-in camera and microphone are used to collect the user's eye movements, facial expressions, and tone of voice. This data is sent in real time to a server, which then stores it in a database. For example, the camera can track the user's eye movements while the microphone monitors changes in the tone of their voice, allowing the system to measure the user's interest and concentration.

[0721] Data analysis phase

[0722] The server uses specific algorithms to analyze the collected learning data. For example, it uses image processing algorithms to analyze the user's facial expressions and voice recognition algorithms to analyze the user's tone of voice. This analysis identifies the user's learning style (visual, auditory, abstract thinking, concrete thinking, etc.) and evaluates their concentration level and emotional state. For example, if a user responds more to visual information, they will be classified as "visual."

[0723] Optimization Phase

[0724] The server generates an individually optimized learning plan based on the analyzed learning style. This plan includes learning content and schedules that differ for each user. For example, for a user who prefers concrete thinking, learning materials containing many concrete problems are provided. The generated learning plan is sent to the terminal and presented to the user.

[0725] Execution Phase

[0726] The user follows the presented study plan as they study, and the device continues to monitor them as they do so. The device collects eye movements, facial expressions, tone of voice, and other data in real time, and evaluates the user's level of concentration based on this information. If the user's level of concentration decreases, the device immediately provides feedback, recommending a break or presenting a new problem. For example, if the user's eye movements are frequent, it will determine that the user is distracted and suggest a break.

[0727] Specific examples

[0728] As a concrete example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math materials on his device, the device records his eye movements and facial expressions with a camera and his tone of voice with a microphone. This data is sent to the server in real time, and the server analyzes it. If the analysis determines that Student A prefers concrete thinking, the server generates a study plan that includes many concrete problems and sends it to the device. The device presents this plan to Student A and continues to monitor his concentration level in real time while he studies. If his concentration level drops, the device immediately suggests a break or presents new problems.

[0729] Prompts for generative AI models

[0730] Below are the prompts for generating a lesson plan using this system:

[0731] Prompt: Student A struggles with math and has a concrete learning style. To help him study effectively, generate a study plan that is optimized for him. This plan should include specific problems that increase in difficulty, starting with concepts he's new to. It should also include actions to take if he loses focus (such as inserting easier problems or recommending breaks).

[0732] In this way, this AI tutoring system can maximize learners' learning efficiency by providing an individually optimized learning experience.

[0733] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0734] Step 1:

[0735] The user logs in to the device and begins learning. The device receives the user's login information and is ready to proceed to the next step. The input is the user's ID and password, and the output is a signal to start the learning session.

[0736] Step 2:

[0737] The device activates its built-in camera and microphone to collect the user's eye movements, facial expressions, and voice tone. The input is biometric information from the user's learning activity, and the output is learning data such as eye movements and voice tone. The device begins collecting this data in real time.

[0738] Step 3:

[0739] The device sends the collected learning data to the server in real time. The server stores the received data in a database. The input is the learning data sent from the device, and the output is the data stored in the database. The stored information is stored with a timestamp.

[0740] Step 4:

[0741] The server retrieves the stored training data and begins analysis using a specific algorithm. The input is the stored training data, and the output is the data analysis results. Specifically, the image analysis algorithm analyzes the user's facial expression, and the voice analysis algorithm analyzes the voice tone.

[0742] Step 5:

[0743] The server identifies the user's learning style based on the analysis results. The input is the data analysis results, and the output is the identified learning style category (visual, auditory, abstract thinking, concrete thinking, etc.). In this process, a score is assigned to each learning style.

[0744] Step 6:

[0745] The server then evaluates the user's concentration and emotional state. The input is the detailed results of the analysis algorithm, and the output is an assessment of the user's concentration and emotional state. For example, it can determine whether the user is distracted from camera footage and infer stress levels from the tone of the user's voice.

[0746] Step 7:

[0747] The server generates an individually optimized learning plan based on the analysis results. The input is the assessment results of concentration level and learning style, and the output is an individualized learning plan. For example, for visual users, learning materials with many illustrations are selected.

[0748] Step 8:

[0749] The server sends the generated learning plan to the terminal and presents it to the user. The input is the personalized learning plan, and the output is the learning plan displayed on the terminal. The terminal displays a notification to prompt the user to confirm the plan.

[0750] Step 9:

[0751] The user performs learning activities according to the presented learning plan. The input is the displayed learning plan, and the output is the learning completion status and progress data. As the user progresses with their learning, the device continues to collect data such as eye movements, facial expressions, and voice tone.

[0752] Step 10:

[0753] The device evaluates the user's level of concentration based on real-time data and instantly adjusts the learning plan as needed. The input is the latest learning data collected in real time, and the output is an updated learning plan and feedback. For example, if the user's level of concentration decreases, the device will immediately respond by recommending a break or presenting a new problem.

[0754] (Application example 1)

[0755] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0756] Conventional online learning systems have difficulty fully understanding each student's learning style, concentration level, and emotional state. Furthermore, they are unable to provide each student with a personalized learning plan in real time, potentially reducing their learning efficiency. Furthermore, they lack a way to instantly adjust learning plans based on students' concentration levels and responses, making it difficult to provide effective learning support.

[0757] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0758] In this invention, the server includes means for collecting the learner's gaze, facial expression, and tone of voice using a built-in camera and microphone; means for analyzing the collected gaze, facial expression, and tone of voice to evaluate the learner's concentration and emotional state; means for analyzing the collected learning data using a specific algorithm and classifying the user's learning style; means for generating an individually optimized learning plan based on the classified learning style; and means for transmitting the generated learning plan to a terminal and presenting it to the user. This makes it possible to grasp the user's learning style, concentration, and emotional state in real time and provide an optimal learning plan based on that. It also makes it possible to instantly adjust the learning plan based on the user's concentration and response, maximizing learning efficiency.

[0759] "Learning data" refers to data generated when a user learns, and includes eye movements, facial expressions, voice tones, operation history, and the like.

[0760] "Learning style" is a pattern that indicates how a user can learn most effectively, and includes classifications such as visual, auditory, concrete thinking, and abstract thinking.

[0761] A "study plan" is a plan that indicates optimal study content and schedule for a user, and includes learning materials and instruction content customized based on the user's learning style and concentration level.

[0762] The "gaze" is information indicating the point at which the user is looking, and is the movement of the viewpoint acquired using the built-in camera.

[0763] "Facial expression" is information that indicates the state of the user's face, and indicates emotions and concentration.

[0764] "Voice tone" refers to the tone of the voice uttered by the user, and serves as an indicator of emotions and concentration level.

[0765] "Level of concentration" is an index that evaluates how focused a user is on their studies, and is evaluated based on data such as gaze, facial expression, and tone of voice.

[0766] A "prompt sentence" is an instruction sentence input into a generative AI model, and is text used to obtain appropriate generated results according to the purpose.

[0767] The present invention is a system constructed to provide learners (users) with individually optimized study plans. A specific embodiment of this system will be described in detail below.

[0768] Overall system configuration

[0769] The main components of the system are the server, the terminal, and the user. The server is responsible for analyzing data and generating learning plans, the terminal is responsible for collecting data and presenting learning plans, and the user is the entity that carries out the learning.

[0770] Data Collection Phase

[0771] When a user logs in to a device and begins learning, the built-in camera and microphone are activated to collect data related to the learning activity. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. This data is sent to the server in real time.

[0772] Data analysis phase

[0773] The server uses specific algorithms to analyze the transmitted data, such as gaze, facial expression, and voice tone. The analysis results are used to evaluate the user's learning style and concentration level, and the user's learning style is then classified based on the evaluation results. Computer vision technology is used to analyze gaze and facial expression, and natural language processing (NLP) technology is used to analyze voice tone.

[0774] Optimization Phase

[0775] Based on the classified learning style, the server generates an individually optimized learning plan. For example, it provides learning materials containing many practical problems to a user who prefers concrete thinking, and creates a plan containing many diagrams and video materials for a user who finds visual instructions effective. The generated learning plan is sent to the terminal and presented to the user.

[0776] Execution Phase

[0777] The user carries out learning activities according to the presented learning plan. While studying, the device uses a camera and microphone to continuously monitor the user's gaze, facial expressions, and tone of voice in real time. If the user's level of concentration decreases, the device detects the change and sends feedback to the server. The server immediately adjusts the learning plan based on this feedback, and the device presents a new plan to the user.

[0778] Specific examples

[0779] For example, let's imagine that Student A, who is not good at math, uses this system. When Student A begins studying using math teaching materials on his / her device, the camera captures Student A's eye movements and facial expressions, and the microphone collects his / her voice tone. This data is sent to the server, which analyzes the results and determines that Student A prefers concrete thinking. Based on this evaluation, the server generates teaching materials that are optimal for Student A, including many concrete problems, and presents them to him / her via his / her device.

[0780] Prompt Sentence Examples

[0781] An example of a prompt to be input to the AI ​​model is as follows:

[0782] Collect video data of elementary school students learning math and perform emotion recognition. Next, analyze the tone from the audio data to obtain the average audio amplitude. Provide an optimized learning plan based on the obtained emotion data and audio tone.

[0783] Video data: {video_frame}

[0784] Audio data: {audio_data}

[0785] Emotion recognition result: {emotion}

[0786] Average audio amplitude: {avg_audio_amplitude}

[0787] The above steps realize a system that can provide a learning experience optimized for each user and improve learning efficiency.

[0788] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0789] Step 1:

[0790] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. These data are sent to the server in real time. The input data are eye movements, facial expressions, and voice tones, and the output is the collected data.

[0791] Step 2:

[0792] The server analyzes the received data. Gaze and facial expression data are processed by computer vision algorithms to identify the user's emotional state using emotion recognition models. Voice tone data is analyzed using natural language processing (NLP) techniques to extract features for assessing attention and emotional state. The input data are gaze, facial expression, and voice tone, and the output is the analyzed emotional state and attention level.

[0793] Step 3:

[0794] Based on the analysis results, the server classifies the user's learning style, for example, into categories such as visual, auditory, concrete thinking, abstract thinking, etc. The input data are the emotional state and concentration level of the analysis results, and the output is the classification result of the user's learning style.

[0795] Step 4:

[0796] The server generates an individually optimized learning plan based on the classified learning style. For example, it creates a plan with more diagrams and video materials for visual users, and a plan with more practical problems for users who prefer concrete thinking. It uses a generative AI model to create prompts and input data to suggest learning plans. The input data is the learning style classification result, and the output is an individually optimized learning plan.

[0797] Step 5:

[0798] The generated study plan is sent to the terminal, which then presents it to the user. The user then studies according to this plan. The input data is the individually optimized study plan, and the output is the study plan presented to the user.

[0799] Step 6:

[0800] While the user is engaged in learning activities, the device monitors their eye movements, facial expressions, and voice tone in real time using a built-in camera and microphone. If their concentration level drops, the device feeds that information back to the server. The input data are real-time eye movements, facial expressions, and voice tone, and the output is feedback to the server.

[0801] Step 7:

[0802] The server receives the feedback and immediately adjusts the learning plan as needed. For example, if the level of concentration drops, the server decides on an action such as inserting new material or questions or recommending a short break. The input data is the concentration assessment as feedback, and the output is an adjusted learning plan.

[0803] Step 8:

[0804] The adjusted learning plan is sent back to the terminal, and the terminal presents the new learning plan to the user. The input data is the adjusted learning plan, and the output is the new learning plan presented to the user.

[0805] This ensures that the user's learning activities are always optimized and learning efficiency is maximized.

[0806] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0807] This invention is an AI tutor system designed to significantly improve students' learning efficiency, and by combining it with an emotion engine, it provides even more effective learning support. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[0808] Data Collection Phase

[0809] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone to record the user's eye movements, facial expressions, voice tone, and even emotional state in real time. This data is then sent to the server in real time, where it is stored in a database.

[0810] Introducing the Emotion Engine

[0811] The server is equipped with an emotion engine that analyzes the received data and recognizes the user's emotions. The emotion engine classifies the user's emotional state based on changes in facial expressions and voice. Emotional data reveals the state in which the user is studying and is useful for providing effective learning support.

[0812] Data analysis phase

[0813] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, response data, and emotional state to identify the user's learning style, and also integrates emotional data generated by the emotion engine to assess the user's concentration and stress levels.

[0814] Optimization Phase

[0815] The server generates an individually optimized learning plan based on the analyzed learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials containing many concrete problems will be recommended. The generated learning plan is sent to the terminal and presented to the user.

[0816] Execution Phase

[0817] The user follows the presented study plan and carries out study activities. While studying, the device continuously monitors the user's eye movements, facial expressions, voice tone, and emotional data in real time. Based on this, the device evaluates the user's concentration level and emotional state and adjusts the study plan as necessary. For example, if the device determines that the user is under stress, it will immediately suggest taking a break or present a less difficult task.

[0818] Specific examples

[0819] As a specific example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying using history materials on his device, the device records his eye movements, facial expressions, tone of voice, and emotional state. This data is sent to the server in real time, and the server analyzes it to identify Student B's learning style and emotional state.

[0820] It is determined that Student B is able to concentrate when he places importance on specific examples and finds the material enjoyable emotionally. Based on this result, the server generates learning materials that incorporate specific historical episodes that are enjoyable, and sends them to the device as a learning plan. Student B then proceeds with his studies based on this plan.

[0821] While studying, the device monitors Student B's gaze, facial expressions, and emotional state in real time, and if it determines that Student B's concentration is declining or that he or she is under stress, it will present a new task or suggest a break. This process maximizes Student B's learning efficiency and improves learning outcomes.

[0822] As described above, the AI ​​tutor system that combines the emotion engine of the present invention improves learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[0823] The processing flow will be explained below.

[0824] Step 1:

[0825] The user logs in to the device and begins learning.

[0826] Step 2:

[0827] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, vocal tone, and emotional state in real time.

[0828] Step 3:

[0829] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[0830] Step 4:

[0831] The device transmits the collected data to the server in real time.

[0832] Step 5:

[0833] The server stores the received data in a database.

[0834] Step 6:

[0835] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style, and an emotion engine to identify the user's emotional state (e.g., stressed, relaxed, focused, etc.).

[0836] Step 7:

[0837] The server generates a personalized learning plan based on the user's learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials with many concrete problems will be recommended.

[0838] Step 8:

[0839] The server transmits the generated study plan to the terminal.

[0840] Step 9:

[0841] The device presents the user with the optimal learning plan and displays it on the screen.

[0842] Step 10:

[0843] The user proceeds with the learning activities based on the presented learning plan.

[0844] Step 11:

[0845] During the learning process, the device continues to monitor the user's eye movements, facial expressions, voice tone, and emotional data in real time.

[0846] Step 12:

[0847] The device assesses the user's concentration and emotional state and adjusts the study plan as needed. For example, if it detects a decline in concentration and stress, it will suggest a new task or a break.

[0848] Step 13:

[0849] After the learning session is over, the device sends any new data it has collected to the server.

[0850] Step 14:

[0851] The server stores the new data in a database and updates the analysis algorithm and emotion engine to improve the accuracy of the next learning plan.

[0852] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[0853] Example 2

[0854] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0855] Conventional learning support systems primarily collect and analyze students' learning data, but do not provide learning plans that reflect students' emotional states or make real-time adjustments. This makes it difficult to provide optimal learning support that takes into account students' concentration levels and stress levels, limiting improvements in learning efficiency.

[0856] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0857] In this invention, the server includes means for collecting learning data of students, means for analyzing the collected learning data to classify the learning style and emotional state of the students, and means for generating an optimal learning plan for each student based on the classified learning style and emotional state. This makes it possible to provide appropriate feedback and adjust the learning plan in real time based on the learning data and emotional data of the students.

[0858] "Learning data" refers to information such as all actions, inputs, answers, and progress of students during the learning process.

[0859] "Emotional state" refers to the psychological and emotional state of a student as analyzed from facial expressions, tone of voice, behavioral patterns, etc.

[0860] "Learning styles" refer to the methods or patterns in which students learn most effectively, and include categories such as visual, auditory, and tactile learning.

[0861] A "learning plan" is a plan that outlines the optimal way to proceed with materials and tasks based on a student's individual learning style and emotional state.

[0862] "Real-time monitoring" refers to the process of instantly collecting and analyzing student data during learning, and providing feedback and adjustments on the spot.

[0863] "Concentration" refers to the degree to which a student pays attention to their studies, and is assessed by factors such as eye movements and the degree to which attention is divided.

[0864] "Response" refers to all responses that the system can detect, such as a student's behavior, facial expressions, and tone of voice while learning.

[0865] "Academic performance data" refers to historical data such as a student's past learning outcomes, test scores, and evaluation results.

[0866] "Learning growth" refers to an evaluation indicator that shows how much a student has understood the learning content and improved their skills over a certain period of time.

[0867] "Individual optimization" refers to the process of customizing the most effective learning plans and materials based on each student's characteristics and situation.

[0868] The following describes an embodiment of the invention of an "AI tutor system combined with an emotion engine."

[0869] MODE FOR CARRYING OUT THE INVENTION

[0870] The present invention is an AI tutor system that generates an optimal learning plan based on a student's learning data and emotional data, and provides learning support tailored to each student. A specific example of this system is described below.

[0871] Hardware and software used

[0872] The main components of the system include servers, terminals, and users. The roles and technologies used by each component are described below.

[0873] Server: Analyzes data and generates learning plans. Specifically, PostgreSQL and MongoDB are used for database management, Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used for emotion analysis, and Python's pandas and scikit-learn are used for data analysis.

[0874] Device: Collects students' gaze, facial expressions, and voice data and sends it to the server in real time. It also plays a role in presenting an optimized learning plan. The device must have a camera and microphone.

[0875] Users: Students who carry out learning activities. Their data is recorded and analyzed by the system.

[0876] Program processing

[0877] 1. User login and learning begins

[0878] Users log in to their devices with their own accounts. After logging in, learning materials and assignments are presented, and the user is ready to begin learning.

[0879] 2. Data Collection

[0880] The device activates its built-in camera and microphone to record the user's eye movements, facial expressions, and voice tone in real time, and this data is immediately sent to the server.

[0881] 3. Data storage

[0882] The server stores the received data in a database, using database technologies such as PostgreSQL or MongoDB.

[0883] 4. Emotion analysis

[0884] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. It uses services such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer to classify emotions from facial expressions and vocal tones.

[0885] 5. Data analysis and learning style identification

[0886] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and emotional data to identify the user's learning style, using Python's pandas and scikit-learn.

[0887] 6. Generate a learning plan

[0888] The server generates an optimal learning plan for each user based on the analysis results and emotional data, resulting in customized learning materials and assignments for each user.

[0889] 7. Study plan presentation and real-time monitoring

[0890] The generated study plan is sent to the device and presented to the user. During the study, the device continuously monitors the user's gaze, facial expressions, and tone of voice, and adjusts the study plan in real time as needed.

[0891] Specific examples

[0892] As a concrete example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying history materials on his device, the device records his eye movements, facial expressions, and voice tone, and sends them to the server in real time. The server analyzes the data and identifies Student B's learning style and emotional state. It can be seen that Student B places importance on specific examples and is able to concentrate when he finds them emotionally enjoyable. Based on these results, the server generates learning materials that incorporate specific, enjoyable historical episodes and sends them to the device as a study plan.

[0893] While studying, the device monitors B's gaze, facial expressions, and emotional state in real time, and if it determines that B's concentration is declining or that he is under stress, it will present a new assignment or suggest a break. This maximizes the student's learning efficiency and improves learning outcomes.

[0894] Example prompts for generative AI models

[0895] Example prompt 1: "Analyze the user's learning style and emotional state to generate an optimal study plan."

[0896] Example prompt 2: "Assess user engagement using eye movement, facial expression, and emotional data and adjust learning plans accordingly."

[0897] As described above, the AI ​​tutor system that combines the emotion engine of the present invention can improve learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[0898] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0899] Step 1: User logs in and begins learning

[0900] The user logs in to the learning device using their account information. The user inputs the account information and the device outputs a message indicating whether the login was successful or not. If the login is successful, the learning materials and assignments are displayed on the device, and the user is ready to begin learning.

[0901] Step 2: Data collection

[0902] The device activates the built-in camera and microphone to record the user's gaze movements, facial expressions, and voice tone in real time. The input is the user's gaze data, facial expression data, and voice data, and data processing involves capturing each data and applying an initial filter. The output is a formatted version of this data. This data is sent to the server in real time.

[0903] Step 3: Send and save data to the server

[0904] The device sends the collected gaze data, facial expression data, and voice data to the server in real time. The input is formatted gaze data, facial expression data, and voice data, which the server receives and stores in a database such as PostgreSQL or MongoDB. The output is the data stored in the database.

[0905] Step 4: Sentiment Analysis

[0906] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. The inputs are gaze data, facial expression data, and voice data, and analysis tools such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used to process the data. The output is data that indicates the user's emotional state.

[0907] Step 5: Analyze data and identify learning styles

[0908] The server uses a data analysis algorithm to integrate gaze, facial expression, voice tone, and emotional data. The inputs are gaze, facial expression, voice, and emotional state data, and Python's pandas and scikit-learn are used for data processing. The output is data that identifies the user's learning style.

[0909] Step 6: Generate a personalized learning plan

[0910] The server generates an optimal learning plan for the user based on the analysis results and emotional data. The input is learning style data and emotional state data, and an optimization algorithm is applied to calculate the data. The output is a customized learning plan, which includes specific learning materials and assignments.

[0911] Step 7: Send and present your study plan to your device

[0912] The generated study plan is sent from the server to the terminal. The input is the generated study plan, which the terminal receives and presents to the user. The output is the plan displayed on the user's screen. The user proceeds with their study based on this plan.

[0913] Step 8: Real-time monitoring and concentration assessment

[0914] The device continuously monitors the user's eye movements, facial expressions, and vocal tone in real time during training. The inputs are gaze data, facial expression data, and vocal data, which are sent to the server. The server reanalyzes these data and evaluates the user's concentration and emotional state. The output is updated concentration and emotional state data in real time.

[0915] Step 9: Adjust your study plan

[0916] The server evaluates the user's state based on the data received in real time and instantly adjusts the study plan. The input is updated concentration data and emotional state data, and a dynamic adjustment algorithm is used to calculate the data. The output is a new, adjusted study plan. If necessary, the device will present new tasks or suggest a break.

[0917] The above is the flow of processing in the system program and the specific operations at each step.

[0918] (Application example 2)

[0919] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0920] Conventional learning support systems have the problem that they do not sufficiently consider students' real-time emotional state or concentration level when generating learning plans or using data analysis methods to improve students' learning efficiency. Furthermore, they are unable to quickly adjust learning plans under specific circumstances, limiting their effectiveness in the learning process. The present invention aims to solve these problems and propose a system that provides optimal learning support for each student.

[0921] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the student's eye movements, facial expressions, and voice tone in real time using a camera and microphone built into the smart device, means for transmitting the collected data to the server and analyzing the student's emotional state using an emotion engine, means for instantly adjusting the study plan based on the student's real-time concentration and stress level during study, and means for generating specific prompt sentences for the student using a generative AI model to improve study efficiency. This enables individually optimized study support that takes into account the student's emotional state and concentration level.

[0922] A "smart device" is an electronic device that has a built-in camera and microphone and can collect real-time data and exchange information with a server via an internet connection.

[0923] A "camera" is an optical device used to capture images and videos, and is a device used to record eye movements and changes in facial expressions.

[0924] A "microphone" is a device for collecting sound and is used to record voice tones and speech.

[0925] A "server" is a computer system that stores and processes data, and receives and analyzes data sent from terminals.

[0926] An "emotion engine" is software that includes an algorithm that analyzes a user's emotional state from collected data such as eye movements, facial expressions, and tone of voice, and classifies emotions.

[0927] "Concentration" is an index that indicates how much a user is concentrating on a learning activity, and is an element that is evaluated by the emotion engine.

[0928] "Stress level" is an index that indicates the degree of stress a user feels while studying, and is an element that is evaluated through the emotion engine.

[0929] "Generative AI model" means an artificial intelligence algorithm that generates optimal prompts and learning plans based on collected data.

[0930] A "prompt" is a sentence created by a generative AI model that provides specific instructions or suggestions to the user.

[0931] This invention realizes a system for improving students' learning efficiency. The main components of the system are a server, a smart device, and a user.

[0932] First, the user logs in to their smart device and begins learning. During this process, the smart device's built-in camera and microphone are used to record the user's eye movements, facial expressions, and tone of voice in real time. This data is then immediately sent to the server.

[0933] The server analyzes the received data using an emotion engine, which analyzes the user's emotional state based on eye movements, facial expressions, and tone of voice, and evaluates their concentration and stress levels in real time. This process allows the server to understand the emotional state of the students.

[0934] The server then uses the analyzed data to classify the student's learning style and generate an individually optimized study plan. The study plan is adjusted in real time, taking into account the user's emotional state and concentration level. For example, if the user is feeling stressed, the server can present them with a less difficult task or suggest a break.

[0935] The generative AI model generates appropriate prompts based on user data, providing students with specific instructions and suggestions to improve their learning efficiency. Below is an example of a prompt:

[0936] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[0937] The hardware used to realize this system is a smart device with a built-in camera and microphone. The software is a server that implements OpenCV (an image processing library), Requests (an HTTP library), and an emotion engine. The entire process, from data collection to analysis and feedback, works together to maximize learning efficiency.

[0938] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0939] Step 1:

[0940] A user logs in to a smart device and starts learning. At this time, the user gives permission to use the smart device's camera and microphone. The input is the login information and smart device's access permission, and the output is the system login status.

[0941] Step 2:

[0942] The device activates a camera and microphone to record the user's gaze, facial expressions, and voice tone in real time. This data is converted into a digital format and prepared for further analysis. The input is the user's gaze, facial expressions, and voice tone, and the output is gaze data, facial expression data, and voice data in digital data format.

[0943] Step 3:

[0944] The device transmits the collected data to the server in real time. This process includes data compression and encryption to ensure data security. The input is gaze data, facial expression data, and voice data in digital format, and the output is the completed transmission status to the server.

[0945] Step 4:

[0946] The server analyzes the received data using an emotion engine. The emotion engine evaluates the user's emotional state from eye movements, facial expressions, and vocal tone, and calculates the user's concentration and stress levels in real time. The input is the data sent to the server, and the output is the user's emotional state, concentration, and stress levels.

[0947] Step 5:

[0948] The server uses the analyzed data to classify the user's learning style and generate an individually optimized learning plan, taking into account past learning history and grade data. The input is the user's emotional state, concentration level, stress level, and past learning data, and the output is an individually optimized learning plan.

[0949] Step 6:

[0950] The server sends the generated lesson plan to the terminal and presents it to the user. The terminal receives it and displays it to the user in visual and auditory form. The input is the generated lesson plan, and the output is the display form to the user.

[0951] Step 7:

[0952] As the user continues learning, the device monitors the user's eye movements, facial expressions, and tone of voice in real time and sends this data to the server. The input is the user's real-time data, and the output is continuous data transmission to the server.

[0953] Step 8:

[0954] The server continuously analyzes the user's real-time data and instantly adjusts the study plan based on their concentration and stress level. For example, if the user feels stressed, it generates a prompt suggesting a break. The input is the user data sent in real time, and the output is the adjusted study plan and prompt.

[0955] Example prompt sentence:

[0956] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[0957] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0958] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0959] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0960] [Fourth embodiment]

[0961] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0962] 7, a 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.

[0963] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0964] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0965] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0966] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0967] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0968] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0969] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0970] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0971] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0972] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0973] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0974] This AI tutor system provides learners (users) with individually optimized learning plans and is designed to improve students' learning efficiency. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[0975] Data Collection Phase

[0976] When a user logs in to a device and begins learning, the device prepares to record their learning activities. Specifically, the device uses the built-in camera and microphone to collect information such as the user's eye movements, facial expressions, and voice tone. This data is sent to the server in real time, and the server stores it in a database.

[0977] Data analysis phase

[0978] The server uses a specific algorithm to analyze the collected learning data. The data analysis algorithm identifies the user's learning style (e.g., "visual," "auditory," "abstract thinking," "concrete thinking," etc.) and evaluates their concentration level and emotional state. Based on these results, the server classifies the user's learning style.

[0979] Optimization Phase

[0980] The server generates an individually optimized learning plan based on the analyzed learning style. This includes learning content and schedules that differ for each user. For example, a user who prefers concrete thinking can be provided with learning materials that include many concrete problems. The generated learning plan is sent to the terminal and presented to the user.

[0981] Execution Phase

[0982] The user follows the presented study plan. While studying, the device continuously monitors the user's eye movements, facial expressions, tone of voice, and other factors in real time. Based on this, the device evaluates the user's level of concentration and immediately adjusts the study plan as necessary. For example, if the user's level of concentration decreases, the device will recommend that the user take a break or present a new problem.

[0983] Specific examples

[0984] As a specific example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math study materials on his device, the device records his eye movements, facial expressions, tone of voice, and other data. This data is sent to the server in real time. The server analyzes the collected data and determines that Student A prefers concrete thinking. Based on this result, the server generates an optimal study plan for Student A. Specifically, it provides many study materials containing many actual math problems, and presents them with gradually increasing difficulty levels. This study plan is then displayed to Student A via his device.

[0985] If Student A's concentration level drops as he or she studies, the device will detect this change in real time and provide immediate feedback, such as inserting an easy question or informing the student to take a short break. This maximizes Student A's learning efficiency and improves their learning outcomes.

[0986] Through the above process, this AI tutor system provides each student with the optimal learning method, thereby overcoming the drawbacks of a uniform learning style and significantly improving students' learning efficiency.

[0987] The processing flow will be explained below.

[0988] Step 1:

[0989] The user logs in to the device and begins learning.

[0990] Step 2:

[0991] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, and voice tone in real time.

[0992] Step 3:

[0993] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[0994] Step 4:

[0995] The device transmits the collected data to the server in real time.

[0996] Step 5:

[0997] The server stores the received data in a database.

[0998] Step 6:

[0999] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style.

[1000] Step 7:

[1001] The server generates a personalized learning plan based on the user's learning style, for example, recommending learning materials with many concrete problems to a user who prefers concrete thinking.

[1002] Step 8:

[1003] The server transmits the generated study plan to the terminal.

[1004] Step 9:

[1005] The device presents the user with the optimal learning plan and displays it on the screen.

[1006] Step 10:

[1007] The user proceeds with the learning activities based on the presented learning plan.

[1008] Step 11:

[1009] During the learning process, the device continues to monitor the user's eye movements, facial expressions, and voice tone in real time.

[1010] Step 12:

[1011] The device assesses the user's level of concentration and response and adjusts the learning plan as needed, for example presenting new tasks or suggesting a break if concentration levels drop.

[1012] Step 13:

[1013] After the learning session is over, the device sends any new data it has collected to the server.

[1014] Step 14:

[1015] The server stores the new data in a database and updates the analysis algorithm to improve the accuracy of the next learning plan.

[1016] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[1017] Example 1

[1018] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1019] With conventional learning systems, it was difficult to grasp the learning style and concentration level of each learner in real time and dynamically adjust the learning plan based on that. As a result, learners were unable to obtain an optimal learning environment, and learning efficiency could not be sufficiently improved.

[1020] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1021] In this invention, the server includes means for collecting learner learning data, means for analyzing the collected learning data and classifying the learner's learning style, and means for generating an optimal learning plan for each learner based on the classified learning style. This makes it possible to monitor the learner's eye movements, facial expressions, and tone of voice in real time. Furthermore, by analyzing the collected data in real time and dynamically adjusting the learning plan, it is possible to provide the learner with an optimal learning experience.

[1022] A "learner" is a person who engages in learning activities to acquire specific knowledge or skills.

[1023] "Learning data" refers to information such as learning content, learning progress, eye movements, facial expressions, and vocal tone that is generated when a learner engages in learning activities.

[1024] "Means for collection" refers to a method or device for acquiring learner learning data using hardware such as a camera or microphone.

[1025] "Means for analyzing" refers to a method or device that processes collected learning data using computer algorithms to evaluate learning style and concentration.

[1026] A "study plan" refers to a plan that compiles optimal learning content and schedules based on a learner's learning style and concentration level.

[1027] "Means for generating" refers to a method or device for creating an optimal learning plan for a learner based on the analysis results.

[1028] "Presenting means" refers to a method or device for displaying the generated lesson plan to a learner.

[1029] "Means of real-time monitoring" refers to a method or device that checks the eye movements, facial expressions, tone of voice, etc. of learners in real time while they are studying, and collects that data.

[1030] "Dynamic adjustment means" refers to a method or device that instantly and adaptively modifies learning plans and content based on data collected in real time.

[1031] This invention is an AI tutor system that provides learners with individually optimized learning plans. The main components of the system are a server, a terminal, and a user.

[1032] Data Collection Phase

[1033] When a user logs in to a device and begins studying, the device begins recording their study activities. Specifically, the device's built-in camera and microphone are used to collect the user's eye movements, facial expressions, and tone of voice. This data is sent in real time to a server, which then stores it in a database. For example, the camera can track the user's eye movements while the microphone monitors changes in the tone of their voice, allowing the system to measure the user's interest and concentration.

[1034] Data analysis phase

[1035] The server uses specific algorithms to analyze the collected learning data. For example, it uses image processing algorithms to analyze the user's facial expressions and voice recognition algorithms to analyze the user's tone of voice. This analysis identifies the user's learning style (visual, auditory, abstract thinking, concrete thinking, etc.) and evaluates their concentration level and emotional state. For example, if a user responds more to visual information, they will be classified as "visual."

[1036] Optimization Phase

[1037] The server generates an individually optimized learning plan based on the analyzed learning style. This plan includes learning content and schedules that differ for each user. For example, for a user who prefers concrete thinking, learning materials containing many concrete problems are provided. The generated learning plan is sent to the terminal and presented to the user.

[1038] Execution Phase

[1039] The user follows the presented study plan as they study, and the device continues to monitor them as they do so. The device collects eye movements, facial expressions, tone of voice, and other data in real time, and evaluates the user's level of concentration based on this information. If the user's level of concentration decreases, the device immediately provides feedback, recommending a break or presenting a new problem. For example, if the user's eye movements are frequent, it will determine that the user is distracted and suggest a break.

[1040] Specific examples

[1041] As a concrete example, let's consider the case where Student A, who is not good at math, uses this system. When Student A begins studying using math materials on his device, the device records his eye movements and facial expressions with a camera and his tone of voice with a microphone. This data is sent to the server in real time, and the server analyzes it. If the analysis determines that Student A prefers concrete thinking, the server generates a study plan that includes many concrete problems and sends it to the device. The device presents this plan to Student A and continues to monitor his concentration level in real time while he studies. If his concentration level drops, the device immediately suggests a break or presents new problems.

[1042] Prompts for generative AI models

[1043] Below are the prompts for generating a lesson plan using this system:

[1044] Prompt: Student A struggles with math and has a concrete learning style. To help him study effectively, generate a study plan that is optimized for him. This plan should include specific problems that increase in difficulty, starting with concepts he's new to. It should also include actions to take if he loses focus (such as inserting easier problems or recommending breaks).

[1045] In this way, this AI tutoring system can maximize learners' learning efficiency by providing an individually optimized learning experience.

[1046] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1047] Step 1:

[1048] The user logs in to the device and begins learning. The device receives the user's login information and is ready to proceed to the next step. The input is the user's ID and password, and the output is a signal to start the learning session.

[1049] Step 2:

[1050] The device activates its built-in camera and microphone to collect the user's eye movements, facial expressions, and voice tone. The input is biometric information from the user's learning activity, and the output is learning data such as eye movements and voice tone. The device begins collecting this data in real time.

[1051] Step 3:

[1052] The device sends the collected learning data to the server in real time. The server stores the received data in a database. The input is the learning data sent from the device, and the output is the data stored in the database. The stored information is stored with a timestamp.

[1053] Step 4:

[1054] The server retrieves the stored training data and begins analysis using a specific algorithm. The input is the stored training data, and the output is the data analysis results. Specifically, the image analysis algorithm analyzes the user's facial expression, and the voice analysis algorithm analyzes the voice tone.

[1055] Step 5:

[1056] The server identifies the user's learning style based on the analysis results. The input is the data analysis results, and the output is the identified learning style category (visual, auditory, abstract thinking, concrete thinking, etc.). In this process, a score is assigned to each learning style.

[1057] Step 6:

[1058] The server then evaluates the user's concentration and emotional state. The input is the detailed results of the analysis algorithm, and the output is an assessment of the user's concentration and emotional state. For example, it can determine whether the user is distracted from camera footage and infer stress levels from the tone of the user's voice.

[1059] Step 7:

[1060] The server generates an individually optimized learning plan based on the analysis results. The input is the assessment results of concentration level and learning style, and the output is an individualized learning plan. For example, for visual users, learning materials with many illustrations are selected.

[1061] Step 8:

[1062] The server sends the generated learning plan to the terminal and presents it to the user. The input is the personalized learning plan, and the output is the learning plan displayed on the terminal. The terminal displays a notification to prompt the user to confirm the plan.

[1063] Step 9:

[1064] The user performs learning activities according to the presented learning plan. The input is the displayed learning plan, and the output is the learning completion status and progress data. As the user progresses with their learning, the device continues to collect data such as eye movements, facial expressions, and voice tone.

[1065] Step 10:

[1066] The device evaluates the user's level of concentration based on real-time data and instantly adjusts the learning plan as needed. The input is the latest learning data collected in real time, and the output is an updated learning plan and feedback. For example, if the user's level of concentration decreases, the device will immediately respond by recommending a break or presenting a new problem.

[1067] (Application example 1)

[1068] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1069] Conventional online learning systems have difficulty fully understanding each student's learning style, concentration level, and emotional state. Furthermore, they are unable to provide each student with a personalized learning plan in real time, potentially reducing their learning efficiency. Furthermore, they lack a way to instantly adjust learning plans based on students' concentration levels and responses, making it difficult to provide effective learning support.

[1070] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1071] In this invention, the server includes means for collecting the learner's gaze, facial expression, and tone of voice using a built-in camera and microphone; means for analyzing the collected gaze, facial expression, and tone of voice to evaluate the learner's concentration and emotional state; means for analyzing the collected learning data using a specific algorithm and classifying the user's learning style; means for generating an individually optimized learning plan based on the classified learning style; and means for transmitting the generated learning plan to a terminal and presenting it to the user. This makes it possible to grasp the user's learning style, concentration, and emotional state in real time and provide an optimal learning plan based on that. It also makes it possible to instantly adjust the learning plan based on the user's concentration and response, maximizing learning efficiency.

[1072] "Learning data" refers to data generated when a user learns, and includes eye movements, facial expressions, voice tones, operation history, and the like.

[1073] "Learning style" is a pattern that indicates how a user can learn most effectively, and includes classifications such as visual, auditory, concrete thinking, and abstract thinking.

[1074] A "study plan" is a plan that indicates optimal study content and schedule for a user, and includes learning materials and instruction content customized based on the user's learning style and concentration level.

[1075] The "gaze" is information indicating the point at which the user is looking, and is the movement of the viewpoint acquired using the built-in camera.

[1076] "Facial expression" is information that indicates the state of the user's face, and indicates emotions and concentration.

[1077] "Voice tone" refers to the tone of the voice uttered by the user, and serves as an indicator of emotions and concentration level.

[1078] "Level of concentration" is an index that evaluates how focused a user is on their studies, and is evaluated based on data such as gaze, facial expression, and tone of voice.

[1079] A "prompt sentence" is an instruction sentence input into a generative AI model, and is text used to obtain appropriate generated results according to the purpose.

[1080] The present invention is a system constructed to provide learners (users) with individually optimized study plans. A specific embodiment of this system will be described in detail below.

[1081] Overall system configuration

[1082] The main components of the system are the server, the terminal, and the user. The server is responsible for analyzing data and generating learning plans, the terminal is responsible for collecting data and presenting learning plans, and the user is the entity that carries out the learning.

[1083] Data Collection Phase

[1084] When a user logs in to a device and begins learning, the built-in camera and microphone are activated to collect data related to the learning activity. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. This data is sent to the server in real time.

[1085] Data analysis phase

[1086] The server uses specific algorithms to analyze the transmitted data, such as gaze, facial expression, and voice tone. The analysis results are used to evaluate the user's learning style and concentration level, and the user's learning style is then classified based on the evaluation results. Computer vision technology is used to analyze gaze and facial expression, and natural language processing (NLP) technology is used to analyze voice tone.

[1087] Optimization Phase

[1088] Based on the classified learning style, the server generates an individually optimized learning plan. For example, it provides learning materials containing many practical problems to a user who prefers concrete thinking, and creates a plan containing many diagrams and video materials for a user who finds visual instructions effective. The generated learning plan is sent to the terminal and presented to the user.

[1089] Execution Phase

[1090] The user carries out learning activities according to the presented learning plan. While studying, the device uses a camera and microphone to continuously monitor the user's gaze, facial expressions, and tone of voice in real time. If the user's level of concentration decreases, the device detects the change and sends feedback to the server. The server immediately adjusts the learning plan based on this feedback, and the device presents a new plan to the user.

[1091] Specific examples

[1092] For example, let's imagine that Student A, who is not good at math, uses this system. When Student A begins studying using math teaching materials on his / her device, the camera captures Student A's eye movements and facial expressions, and the microphone collects his / her voice tone. This data is sent to the server, which analyzes the results and determines that Student A prefers concrete thinking. Based on this evaluation, the server generates teaching materials that are optimal for Student A, including many concrete problems, and presents them to him / her via his / her device.

[1093] Prompt Sentence Examples

[1094] An example of a prompt to be input to the AI ​​model is as follows:

[1095] Collect video data of elementary school students learning math and perform emotion recognition. Next, analyze the tone from the audio data to obtain the average audio amplitude. Provide an optimized learning plan based on the obtained emotion data and audio tone.

[1096] Video data: {video_frame}

[1097] Audio data: {audio_data}

[1098] Emotion recognition result: {emotion}

[1099] Average audio amplitude: {avg_audio_amplitude}

[1100] The above steps realize a system that can provide a learning experience optimized for each user and improve learning efficiency.

[1101] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1102] Step 1:

[1103] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone. The camera captures the user's eye movements and facial expressions, and the microphone collects voice tones. These data are sent to the server in real time. The input data are eye movements, facial expressions, and voice tones, and the output is the collected data.

[1104] Step 2:

[1105] The server analyzes the received data. Gaze and facial expression data are processed by computer vision algorithms to identify the user's emotional state using emotion recognition models. Voice tone data is analyzed using natural language processing (NLP) techniques to extract features for assessing attention and emotional state. The input data are gaze, facial expression, and voice tone, and the output is the analyzed emotional state and attention level.

[1106] Step 3:

[1107] Based on the analysis results, the server classifies the user's learning style, for example, into categories such as visual, auditory, concrete thinking, abstract thinking, etc. The input data are the emotional state and concentration level of the analysis results, and the output is the classification result of the user's learning style.

[1108] Step 4:

[1109] The server generates an individually optimized learning plan based on the classified learning style. For example, it creates a plan with more diagrams and video materials for visual users, and a plan with more practical problems for users who prefer concrete thinking. It uses a generative AI model to create prompts and input data to suggest learning plans. The input data is the learning style classification result, and the output is an individually optimized learning plan.

[1110] Step 5:

[1111] The generated study plan is sent to the terminal, which then presents it to the user. The user then studies according to this plan. The input data is the individually optimized study plan, and the output is the study plan presented to the user.

[1112] Step 6:

[1113] While the user is engaged in learning activities, the device monitors their eye movements, facial expressions, and voice tone in real time using a built-in camera and microphone. If their concentration level drops, the device feeds that information back to the server. The input data are real-time eye movements, facial expressions, and voice tone, and the output is feedback to the server.

[1114] Step 7:

[1115] The server receives the feedback and immediately adjusts the learning plan as needed. For example, if the level of concentration drops, the server decides on an action such as inserting new material or questions or recommending a short break. The input data is the concentration assessment as feedback, and the output is an adjusted learning plan.

[1116] Step 8:

[1117] The adjusted learning plan is sent back to the terminal, and the terminal presents the new learning plan to the user. The input data is the adjusted learning plan, and the output is the new learning plan presented to the user.

[1118] This ensures that the user's learning activities are always optimized and learning efficiency is maximized.

[1119] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1120] This invention is an AI tutor system designed to significantly improve students' learning efficiency, and by combining it with an emotion engine, it provides even more effective learning support. A specific example is described below. The main components of the system are a server, a terminal, and a user.

[1121] Data Collection Phase

[1122] When a user logs in to a device and starts learning, the device activates its built-in camera and microphone to record the user's eye movements, facial expressions, voice tone, and even emotional state in real time. This data is then sent to the server in real time, where it is stored in a database.

[1123] Introducing the Emotion Engine

[1124] The server is equipped with an emotion engine that analyzes the received data and recognizes the user's emotions. The emotion engine classifies the user's emotional state based on changes in facial expressions and voice. Emotional data reveals the state in which the user is studying and is useful for providing effective learning support.

[1125] Data analysis phase

[1126] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, response data, and emotional state to identify the user's learning style, and also integrates emotional data generated by the emotion engine to assess the user's concentration and stress levels.

[1127] Optimization Phase

[1128] The server generates an individually optimized learning plan based on the analyzed learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials containing many concrete problems will be recommended. The generated learning plan is sent to the terminal and presented to the user.

[1129] Execution Phase

[1130] The user follows the presented study plan and carries out study activities. While studying, the device continuously monitors the user's eye movements, facial expressions, voice tone, and emotional data in real time. Based on this, the device evaluates the user's concentration level and emotional state and adjusts the study plan as necessary. For example, if the device determines that the user is under stress, it will immediately suggest taking a break or present a less difficult task.

[1131] Specific examples

[1132] As a specific example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying using history materials on his device, the device records his eye movements, facial expressions, tone of voice, and emotional state. This data is sent to the server in real time, and the server analyzes it to identify Student B's learning style and emotional state.

[1133] It is determined that Student B is able to concentrate when he places importance on specific examples and finds the material enjoyable emotionally. Based on this result, the server generates learning materials that incorporate specific historical episodes that are enjoyable, and sends them to the device as a learning plan. Student B then proceeds with his studies based on this plan.

[1134] While studying, the device monitors Student B's gaze, facial expressions, and emotional state in real time, and if it determines that Student B's concentration is declining or that he or she is under stress, it will present a new task or suggest a break. This process maximizes Student B's learning efficiency and improves learning outcomes.

[1135] As described above, the AI ​​tutor system that combines the emotion engine of the present invention improves learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] The user logs in to the device and begins learning.

[1139] Step 2:

[1140] The device activates its built-in camera and microphone and prepares to record the user's eye movements, facial expressions, vocal tone, and emotional state in real time.

[1141] Step 3:

[1142] The device acquires data that the user inputs while studying (e.g., response time, accuracy rate, etc.) and collects this data in real time.

[1143] Step 4:

[1144] The device transmits the collected data to the server in real time.

[1145] Step 5:

[1146] The server stores the received data in a database.

[1147] Step 6:

[1148] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and response data to identify the user's learning style, and an emotion engine to identify the user's emotional state (e.g., stressed, relaxed, focused, etc.).

[1149] Step 7:

[1150] The server generates a personalized learning plan based on the user's learning style and emotional data. For example, if a user prefers concrete thinking and is in a relaxed emotional state, learning materials with many concrete problems will be recommended.

[1151] Step 8:

[1152] The server transmits the generated study plan to the terminal.

[1153] Step 9:

[1154] The device presents the user with the optimal learning plan and displays it on the screen.

[1155] Step 10:

[1156] The user proceeds with the learning activities based on the presented learning plan.

[1157] Step 11:

[1158] During the learning process, the device continues to monitor the user's eye movements, facial expressions, voice tone, and emotional data in real time.

[1159] Step 12:

[1160] The device assesses the user's concentration and emotional state and adjusts the study plan as needed. For example, if it detects a decline in concentration and stress, it will suggest a new task or a break.

[1161] Step 13:

[1162] After the learning session is over, the device sends any new data it has collected to the server.

[1163] Step 14:

[1164] The server stores the new data in a database and updates the analysis algorithm and emotion engine to improve the accuracy of the next learning plan.

[1165] Through the above processing steps, the AI ​​tutor system can provide each student with the most suitable learning method and improve learning efficiency.

[1166] Example 2

[1167] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1168] Conventional learning support systems primarily collect and analyze students' learning data, but do not provide learning plans that reflect students' emotional states or make real-time adjustments. This makes it difficult to provide optimal learning support that takes into account students' concentration levels and stress levels, limiting improvements in learning efficiency.

[1169] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1170] In this invention, the server includes means for collecting learning data of students, means for analyzing the collected learning data to classify the learning style and emotional state of the students, and means for generating an optimal learning plan for each student based on the classified learning style and emotional state. This makes it possible to provide appropriate feedback and adjust the learning plan in real time based on the learning data and emotional data of the students.

[1171] "Learning data" refers to information such as all actions, inputs, answers, and progress of students during the learning process.

[1172] "Emotional state" refers to the psychological and emotional state of a student as analyzed from facial expressions, tone of voice, behavioral patterns, etc.

[1173] "Learning styles" refer to the methods or patterns in which students learn most effectively, and include categories such as visual, auditory, and tactile learning.

[1174] A "learning plan" is a plan that outlines the optimal way to proceed with materials and tasks based on a student's individual learning style and emotional state.

[1175] "Real-time monitoring" refers to the process of instantly collecting and analyzing student data during learning, and providing feedback and adjustments on the spot.

[1176] "Concentration" refers to the degree to which a student pays attention to their studies, and is assessed by factors such as eye movements and the degree to which attention is divided.

[1177] "Response" refers to all responses that the system can detect, such as a student's behavior, facial expressions, and tone of voice while learning.

[1178] "Academic performance data" refers to historical data such as a student's past learning outcomes, test scores, and evaluation results.

[1179] "Learning growth" refers to an evaluation indicator that shows how much a student has understood the learning content and improved their skills over a certain period of time.

[1180] "Individual optimization" refers to the process of customizing the most effective learning plans and materials based on each student's characteristics and situation.

[1181] The following describes an embodiment of the invention of an "AI tutor system combined with an emotion engine."

[1182] MODE FOR CARRYING OUT THE INVENTION

[1183] The present invention is an AI tutor system that generates an optimal learning plan based on a student's learning data and emotional data, and provides learning support tailored to each student. A specific example of this system is described below.

[1184] Hardware and software used

[1185] The main components of the system include servers, terminals, and users. The roles and technologies used by each component are described below.

[1186] Server: Analyzes data and generates learning plans. Specifically, PostgreSQL and MongoDB are used for database management, Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used for emotion analysis, and Python's pandas and scikit-learn are used for data analysis.

[1187] Device: Collects students' gaze, facial expressions, and voice data and sends it to the server in real time. It also plays a role in presenting an optimized learning plan. The device must have a camera and microphone.

[1188] Users: Students who carry out learning activities. Their data is recorded and analyzed by the system.

[1189] Program processing

[1190] 1. User login and learning begins

[1191] Users log in to their devices with their own accounts. After logging in, learning materials and assignments are presented, and the user is ready to begin learning.

[1192] 2. Data Collection

[1193] The device activates its built-in camera and microphone to record the user's eye movements, facial expressions, and voice tone in real time, and this data is immediately sent to the server.

[1194] 3. Data storage

[1195] The server stores the received data in a database, using database technologies such as PostgreSQL or MongoDB.

[1196] 4. Emotion analysis

[1197] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. It uses services such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer to classify emotions from facial expressions and vocal tones.

[1198] 5. Data analysis and learning style identification

[1199] The server uses data analysis algorithms to analyze eye movements, facial expressions, voice tone, and emotional data to identify the user's learning style, using Python's pandas and scikit-learn.

[1200] 6. Generate a learning plan

[1201] The server generates an optimal learning plan for each user based on the analysis results and emotional data, resulting in customized learning materials and assignments for each user.

[1202] 7. Study plan presentation and real-time monitoring

[1203] The generated study plan is sent to the device and presented to the user. During the study, the device continuously monitors the user's gaze, facial expressions, and tone of voice, and adjusts the study plan in real time as needed.

[1204] Specific examples

[1205] As a concrete example, let's consider the case where Student B, who is not good at history, uses this system. When Student B begins studying history materials on his device, the device records his eye movements, facial expressions, and voice tone, and sends them to the server in real time. The server analyzes the data and identifies Student B's learning style and emotional state. It can be seen that Student B places importance on specific examples and is able to concentrate when he finds them emotionally enjoyable. Based on these results, the server generates learning materials that incorporate specific, enjoyable historical episodes and sends them to the device as a study plan.

[1206] While studying, the device monitors B's gaze, facial expressions, and emotional state in real time, and if it determines that B's concentration is declining or that he is under stress, it will present a new assignment or suggest a break. This maximizes the student's learning efficiency and improves learning outcomes.

[1207] Example prompts for generative AI models

[1208] Example prompt 1: "Analyze the user's learning style and emotional state to generate an optimal study plan."

[1209] Example prompt 2: "Assess user engagement using eye movement, facial expression, and emotional data and adjust learning plans accordingly."

[1210] As described above, the AI ​​tutor system that combines the emotion engine of the present invention can improve learning efficiency by adapting to the learning style and emotional state of each student and providing the optimal learning method.

[1211] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1212] Step 1: User logs in and begins learning

[1213] The user logs in to the learning device using their account information. The user inputs the account information and the device outputs a message indicating whether the login was successful or not. If the login is successful, the learning materials and assignments are displayed on the device, and the user is ready to begin learning.

[1214] Step 2: Data collection

[1215] The device activates the built-in camera and microphone to record the user's gaze movements, facial expressions, and voice tone in real time. The input is the user's gaze data, facial expression data, and voice data, and data processing involves capturing each data and applying an initial filter. The output is a formatted version of this data. This data is sent to the server in real time.

[1216] Step 3: Send and save data to the server

[1217] The device sends the collected gaze data, facial expression data, and voice data to the server in real time. The input is formatted gaze data, facial expression data, and voice data, which the server receives and stores in a database such as PostgreSQL or MongoDB. The output is the data stored in the database.

[1218] Step 4: Sentiment Analysis

[1219] The emotion engine installed on the server analyzes the received data and recognizes the user's emotions. The inputs are gaze data, facial expression data, and voice data, and analysis tools such as Microsoft Azure's Face API and IBM Watson's Tone Analyzer are used to process the data. The output is data that indicates the user's emotional state.

[1220] Step 5: Analyze data and identify learning styles

[1221] The server uses a data analysis algorithm to integrate gaze, facial expression, voice tone, and emotional data. The inputs are gaze, facial expression, voice, and emotional state data, and Python's pandas and scikit-learn are used for data processing. The output is data that identifies the user's learning style.

[1222] Step 6: Generate a personalized learning plan

[1223] The server generates an optimal learning plan for the user based on the analysis results and emotional data. The input is learning style data and emotional state data, and an optimization algorithm is applied to calculate the data. The output is a customized learning plan, which includes specific learning materials and assignments.

[1224] Step 7: Send and present your study plan to your device

[1225] The generated study plan is sent from the server to the terminal. The input is the generated study plan, which the terminal receives and presents to the user. The output is the plan displayed on the user's screen. The user proceeds with their study based on this plan.

[1226] Step 8: Real-time monitoring and concentration assessment

[1227] The device continuously monitors the user's eye movements, facial expressions, and vocal tone in real time during training. The inputs are gaze data, facial expression data, and vocal data, which are sent to the server. The server reanalyzes these data and evaluates the user's concentration and emotional state. The output is updated concentration and emotional state data in real time.

[1228] Step 9: Adjust your study plan

[1229] The server evaluates the user's state based on the data received in real time and instantly adjusts the study plan. The input is updated concentration data and emotional state data, and a dynamic adjustment algorithm is used to calculate the data. The output is a new, adjusted study plan. If necessary, the device will present new tasks or suggest a break.

[1230] The above is the flow of processing in the system program and the specific operations at each step.

[1231] (Application example 2)

[1232] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1233] Conventional learning support systems have the problem that they do not sufficiently consider students' real-time emotional state or concentration level when generating learning plans or using data analysis methods to improve students' learning efficiency. Furthermore, they are unable to quickly adjust learning plans under specific circumstances, limiting their effectiveness in the learning process. The present invention aims to solve these problems and propose a system that provides optimal learning support for each student.

[1234] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording the student's eye movements, facial expressions, and voice tone in real time using a camera and microphone built into the smart device, means for transmitting the collected data to the server and analyzing the student's emotional state using an emotion engine, means for instantly adjusting the study plan based on the student's real-time concentration and stress level during study, and means for generating specific prompt sentences for the student using a generative AI model to improve study efficiency. This enables individually optimized study support that takes into account the student's emotional state and concentration level.

[1235] A "smart device" is an electronic device that has a built-in camera and microphone and can collect real-time data and exchange information with a server via an internet connection.

[1236] A "camera" is an optical device used to capture images and videos, and is a device used to record eye movements and changes in facial expressions.

[1237] A "microphone" is a device for collecting sound and is used to record voice tones and speech.

[1238] A "server" is a computer system that stores and processes data, and receives and analyzes data sent from terminals.

[1239] An "emotion engine" is software that includes an algorithm that analyzes a user's emotional state from collected data such as eye movements, facial expressions, and tone of voice, and classifies emotions.

[1240] "Concentration" is an index that indicates how much a user is concentrating on a learning activity, and is an element that is evaluated by the emotion engine.

[1241] "Stress level" is an index that indicates the degree of stress a user feels while studying, and is an element that is evaluated through the emotion engine.

[1242] "Generative AI model" means an artificial intelligence algorithm that generates optimal prompts and learning plans based on collected data.

[1243] A "prompt" is a sentence created by a generative AI model that provides specific instructions or suggestions to the user.

[1244] This invention realizes a system for improving students' learning efficiency. The main components of the system are a server, a smart device, and a user.

[1245] First, the user logs in to their smart device and begins learning. During this process, the smart device's built-in camera and microphone are used to record the user's eye movements, facial expressions, and tone of voice in real time. This data is then immediately sent to the server.

[1246] The server analyzes the received data using an emotion engine, which analyzes the user's emotional state based on eye movements, facial expressions, and tone of voice, and evaluates their concentration and stress levels in real time. This process allows the server to understand the emotional state of the students.

[1247] The server then uses the analyzed data to classify the student's learning style and generate an individually optimized study plan. The study plan is adjusted in real time, taking into account the user's emotional state and concentration level. For example, if the user is feeling stressed, the server can present them with a less difficult task or suggest a break.

[1248] The generative AI model generates appropriate prompts based on user data, providing students with specific instructions and suggestions to improve their learning efficiency. Below is an example of a prompt:

[1249] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[1250] The hardware used to realize this system is a smart device with a built-in camera and microphone. The software is a server that implements OpenCV (an image processing library), Requests (an HTTP library), and an emotion engine. The entire process, from data collection to analysis and feedback, works together to maximize learning efficiency.

[1251] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1252] Step 1:

[1253] A user logs in to a smart device and starts learning. At this time, the user gives permission to use the smart device's camera and microphone. The input is the login information and smart device's access permission, and the output is the system login status.

[1254] Step 2:

[1255] The device activates a camera and microphone to record the user's gaze, facial expressions, and voice tone in real time. This data is converted into a digital format and prepared for further analysis. The input is the user's gaze, facial expressions, and voice tone, and the output is gaze data, facial expression data, and voice data in digital data format.

[1256] Step 3:

[1257] The device transmits the collected data to the server in real time. This process includes data compression and encryption to ensure data security. The input is gaze data, facial expression data, and voice data in digital format, and the output is the completed transmission status to the server.

[1258] Step 4:

[1259] The server analyzes the received data using an emotion engine. The emotion engine evaluates the user's emotional state from eye movements, facial expressions, and vocal tone, and calculates the user's concentration and stress levels in real time. The input is the data sent to the server, and the output is the user's emotional state, concentration, and stress levels.

[1260] Step 5:

[1261] The server uses the analyzed data to classify the user's learning style and generate an individually optimized learning plan, taking into account past learning history and grade data. The input is the user's emotional state, concentration level, stress level, and past learning data, and the output is an individually optimized learning plan.

[1262] Step 6:

[1263] The server sends the generated lesson plan to the terminal and presents it to the user. The terminal receives it and displays it to the user in visual and auditory form. The input is the generated lesson plan, and the output is the display form to the user.

[1264] Step 7:

[1265] As the user continues learning, the device monitors the user's eye movements, facial expressions, and tone of voice in real time and sends this data to the server. The input is the user's real-time data, and the output is continuous data transmission to the server.

[1266] Step 8:

[1267] The server continuously analyzes the user's real-time data and instantly adjusts the study plan based on their concentration and stress level. For example, if the user feels stressed, it generates a prompt suggesting a break. The input is the user data sent in real time, and the output is the adjusted study plan and prompt.

[1268] Example prompt sentence:

[1269] "Your current concentration level is declining. We recommend taking a 5-minute break. Try some deep breathing and gentle stretching to refresh yourself before returning to your next task."

[1270] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1271] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1272] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1273] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1274] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1275] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1276] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1277] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1278] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1279] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1280] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1281] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1282] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1283] 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.

[1284] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1285] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1286] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1287] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1288] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1289] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1290] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1291] The following is further disclosed regarding the above embodiment.

[1292] (Claim 1)

[1293] a means of collecting student learning data;

[1294] A means of analyzing the collected learning data to classify students' learning styles;

[1295] A means for generating an optimal learning plan for each student based on the classified learning style;

[1296] A means to present optimal learning plans to students,

[1297] A system including:

[1298] (Claim 2)

[1299] Real-time monitoring of collected student learning data and the means to instantly adjust learning plans based on student engagement and response;

[1300] 10. The system of claim 1, further comprising:

[1301] (Claim 3)

[1302] In generating a learning plan, a means for individually optimizing the plan based on past student performance data and learning progress;

[1303] 10. The system of claim 1, further comprising:

[1304] "Example 1"

[1305] (Claim 1)

[1306] A means for collecting learner learning data;

[1307] A means for analyzing the collected learning data to classify the learner's learning style;

[1308] A means for generating an optimal learning plan for each individual learner based on the classified learning style;

[1309] A means of presenting the optimal learning plan to learners,

[1310] A means of monitoring learners' eye movements, facial expressions, and vocal tone in real time;

[1311] A means to analyze data collected in real time and dynamically adjust learning plans;

[1312] A system including:

[1313] (Claim 2)

[1314] Real-time monitoring of collected learner learning data and a means to instantly adjust learning plans based on learner engagement and response;

[1315] 10. The system of claim 1, further comprising:

[1316] (Claim 3)

[1317] In generating a learning plan, a means for individually optimizing the plan based on the learner's past performance data and learning progress;

[1318] 10. The system of claim 1, further comprising:

[1319] "Application Example 1"

[1320] (Claim 1)

[1321] a means of collecting student learning data;

[1322] A means of analyzing the collected learning data to classify students' learning styles;

[1323] A means for generating an optimal learning plan for each student based on the classified learning style;

[1324] A means to present optimal learning plans to students,

[1325] A means for collecting the learner's gaze, facial expression, and tone of voice using a built-in camera and microphone;

[1326] A means of analyzing collected gaze, facial expressions, and tone of voice to assess the learner's concentration and emotional state;

[1327] A system including:

[1328] (Claim 2)

[1329] Real-time monitoring of collected student learning data and the means to instantly adjust learning plans based on student engagement and response;

[1330] A means for generating prompt sentences based on the analysis results and promoting the optimization of learning plans;

[1331] 10. The system of claim 1, further comprising:

[1332] (Claim 3)

[1333] In generating a learning plan, a means for individually optimizing the plan based on past student performance data and learning progress;

[1334] A means of reflecting the results of assessments of concentration and emotional state collected in real time;

[1335] 10. The system of claim 1, further comprising:

[1336] "Example 2: Combining Emotion Engines"

[1337] (Claim 1)

[1338] a means of collecting student learning data;

[1339] a means of analyzing the collected learning data to classify students' learning styles and emotional states;

[1340] A means for generating an optimal learning plan for each student based on the classified learning style and emotional state;

[1341] A means to present optimal learning plans to students,

[1342] A system including:

[1343] (Claim 2)

[1344] Real-time monitoring of collected student learning and emotional data and means for instantly adjusting learning plans based on students' attention, reactions, and emotional states;

[1345] 10. The system of claim 1, further comprising:

[1346] (Claim 3)

[1347] A means for individually optimizing a learning plan based on past student performance data, learning progress, and emotional data when generating the plan;

[1348] 10. The system of claim 1, further comprising:

[1349] "Application example 2 when combining emotion engines"

[1350] (Claim 1)

[1351] a means of collecting student learning data;

[1352] A means of analyzing the collected learning data to classify students' learning styles;

[1353] A means for generating an optimal learning plan for each student based on the classified learning style;

[1354] A means to present optimal learning plans to students,

[1355] A means of recording students' eye movements, facial expressions, and voice tones in real time using the camera and microphone built into smart devices;

[1356] a means for transmitting the collected data to a server and analyzing the emotional state of the students by an emotion engine;

[1357] A means to instantly adjust learning plans based on real-time student focus and stress levels during learning;

[1358] A means of using generative AI models to generate specific prompts for students to improve learning efficiency; and

[1359] A system including:

[1360] (Claim 2)

[1361] Real-time monitoring of collected student learning data and the means to instantly adjust learning plans based on student engagement and response;

[1362] A means of understanding students' emotional states through real-time eye tracking, facial expression analysis, and voice analysis using smart devices;

[1363] 10. The system of claim 1, further comprising:

[1364] (Claim 3)

[1365] In generating a learning plan, a means for individually optimizing the plan based on past student performance data and learning progress;

[1366] a means of adjusting learning plans while taking into account students' emotional states using an emotion engine;

[1367] 10. The system of claim 1, further comprising: [Explanation of symbols]

[1368] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting student learning data; A means of analyzing the collected learning data to classify students' learning styles; A means for generating an optimal learning plan for each student based on the classified learning style; A means to present optimal learning plans to students, A system including:

2. Real-time monitoring of collected student learning data and the means to instantly adjust learning plans based on student engagement and response; The system of claim 1 further comprising:

3. In generating a learning plan, a means for individually optimizing the plan based on past student performance data and learning progress; The system of claim 1 further comprising:

Images