System

Abstract

A system is provided.SOLUTION: A system comprising: means for optimizing generated learning content based on individual learning progress and comprehension; means for delivering the learning content to a terminal for display; means for displaying the learning content; means for collecting learning outcomes from the terminal; means for analyzing the learning outcomes and generating new learning content; means for collecting health data and optimizing a learning plan; means for providing learning content based on the health data; and means for providing a dashboard that visually displays learning progress and comprehension for a teacher.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] In conventional education systems, it was difficult to individually optimize learning according to each student's learning progress and level of understanding, and they often provided uniform educational content, which led to issues with differences in students' levels of understanding. Furthermore, the burden on teachers was heavy, making it difficult to provide detailed instruction to many students. Furthermore, there was a lack of learning plans that took into account students' health and lifestyles, making it difficult to maximize learning effectiveness. [Means for solving the problem]

[0005] This invention optimizes the generated learning content based on each student's learning progress and level of understanding and delivers it to the device. It also has a means for displaying the learning content, collects learning outcomes, and generates new learning content based on those outcomes. It also includes a means for collecting health data and optimizing learning plans. Furthermore, by providing learning content based on the student's physical condition and lifestyle, and visually displaying learning progress and level of understanding on a teacher dashboard, it realizes a system that provides optimal education for each student while reducing the burden on teachers.

[0006] "Learning content" refers to the learning materials, video lessons, practice questions, etc. that students use to study.

[0007] "Individual optimization" refers to adjusting the learning content according to each student's learning progress and level of understanding.

[0008] "Terminal" refers to a device used by a student to display learning content.

[0009] A "generative AI model" refers to a machine learning model that learns how cram school teachers conduct their lessons and generates video lesson content that reflects that.

[0010] "Learning outcomes" refers to the results of students' work on learning tasks, and includes data such as the percentage of correct answers and the time it took to complete them.

[0011] "Health data" refers to information about a student's physical condition and daily rhythm, including heart rate, sleep time, and activity level.

[0012] A "dashboard" is an interface that allows teachers to visually check students' learning progress, level of understanding, areas of weakness, etc.

[0013] "Optimize" refers to adjusting conditions or parameters to make them more effective and efficient in order to achieve a particular purpose. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

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

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their terminals. Below, we will show a specific embodiment of the entire system and explain the program processing in natural language.

[0036] Server Processing

[0037] 1. Data Collection and Analysis

[0038] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[0039] The collected data is analyzed to evaluate students' learning progress, level of understanding, areas of weakness, current physical condition, etc.

[0040] 2. Generating learning content

[0041] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model learns the teacher's speech patterns and explanation methods, and reproduces the lesson style that attracts students' attention.

[0042] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0043] 3. Optimize your study plan

[0044] The server uses health data to optimize a student's study schedule, for example by concentrating study time in the morning after a student has had enough sleep.

[0045] 4. Content Delivery

[0046] The server delivers the generated learning content and optimized learning plans to students' devices.

[0047] 5. Providing a dashboard

[0048] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[0049] Handling terminals (student devices)

[0050] 1. Receiving and viewing learning content

[0051] Students' devices receive video lesson content and practice questions delivered from the server.

[0052] The received content is presented in an appropriate format to engage students in their learning.

[0053] 2. Submit your learning outcomes

[0054] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0055] 3. Health Data Collection

[0056] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[0057] User (homeroom teacher) processing

[0058] 1. Check the dashboard

[0059] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[0060] Use the dashboard to plan appropriate instruction and advice for students.

[0061] Specific examples

[0062] Server example

[0063] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[0064] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[0065] Specific examples of terminals (student devices)

[0066] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[0067] Student A's device completes the practice questions and sends the results data to the server.

[0068] Example of a user (homeroom teacher)

[0069] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[0070] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[0071] In this way, the present invention is a system that provides learning content optimized for each student, reduces the burden on teachers, and realizes effective learning.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] Data collection: The server retrieves students' past learning data (e.g., test results, submitted assignments, and learning history) from the database. It also receives students' health data (e.g., heart rate, sleep duration, and activity level) from the wearable device.

[0075] Step 2:

[0076] Data analysis: The server analyzes the acquired data, evaluates each student's level of understanding, and identifies weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm.

[0077] Step 3:

[0078] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[0079] Step 4:

[0080] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[0081] Step 5:

[0082] Optimizing learning plans: The server takes into account students' health data and generates the most efficient learning schedule. For example, it will reduce the learning load for students who are not getting enough sleep.

[0083] Step 6:

[0084] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0085] Step 7:

[0086] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[0087] Step 8:

[0088] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[0089] Step 9:

[0090] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[0091] Step 10:

[0092] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[0093] Step 11:

[0094] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, visually displaying each student's learning progress, level of understanding, areas of weakness, etc.

[0095] Step 12:

[0096] Checking the dashboard: The user (homeroom teacher) checks the dashboard to understand the student's learning status, considers necessary measures, and plans additional instruction and support.

[0097] Step 13:

[0098] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[0099] By repeating the above steps, it is possible to provide individually optimized and continuous learning support.

[0100] Example 1

[0101] 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."

[0102] Conventional learning systems have difficulty optimizing learning content that comprehensively reflects individual data such as each student's learning progress, level of understanding, and physical condition, and as a result, have not been able to provide sufficient, effective learning support. Furthermore, it places a heavy burden on teachers to grasp students' learning progress and level of understanding and provide individual support. Therefore, there was a need for a system that provides learning support optimized for each student's learning needs and reduces the burden on teachers.

[0103] 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.

[0104] In this invention, the server includes a means for collecting, analyzing, and evaluating students' learning data and health data, a means for generating learning content based on the students' learning progress and level of understanding using a generative AI model, and a means for delivering the generated learning content and optimized learning plans to the students' devices, thereby enabling the provision of learning content optimized based on the students' individual learning progress, level of understanding, and physical condition.

[0105] "Student learning data" refers to information related to a student's learning activities, such as test results, submitted assignments, and learning history.

[0106] "Health data" refers to information about a student's physical condition, such as heart rate, sleep duration, and activity level.

[0107] A "generative AI model" is an artificial intelligence model that generates learning content according to a student's learning progress and level of understanding.

[0108] "Learning content" refers to educational materials such as generated video lessons and exercises.

[0109] A "device" is a device used by a student to view learning content and perform learning activities.

[0110] "Learning outcome data" refers to data such as the percentage of correct answers and the time it took to answer a question obtained after a student has completed a learning task.

[0111] A "wearable device" is a device worn by students that measures and records health data such as heart rate and activity levels.

[0112] The "dashboard" is an interface that allows homeroom teachers to visually check students' learning progress, level of understanding, and health status.

[0113] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[0114] This invention is a system that provides learning content optimized for each student based on their learning progress, level of understanding, and physical condition. The system consists of three main components: a server, a terminal (student device), and a user (homeroom teacher).

[0115] Server Features

[0116] The server has the following functions:

[0117] 1. Data Collection and Analysis

[0118] The server collects students' learning data (e.g., test results, submitted assignments, learning history, etc.) and health data (e.g., heart rate, sleep time, activity level, etc.).

[0119] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and current physical condition.

[0120] 2. Generating learning content

[0121] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model has learned the teacher's speech patterns and explanation methods.

[0122] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0123] 3. Optimize your study plan

[0124] The server uses health data to optimize a student's study plan, for example by concentrating study time in the morning after a student has had enough sleep.

[0125] 4. Content Delivery

[0126] The server delivers the generated learning content and optimized learning plans to students' devices.

[0127] 5. Providing a dashboard

[0128] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[0129] Device (student device) capabilities

[0130] Student devices have the following features:

[0131] 1. Receiving and viewing learning content

[0132] Students' devices receive video lesson content and practice questions delivered from the server.

[0133] The received content is presented in an appropriate format to engage students in their learning.

[0134] 2. Submit your learning outcomes

[0135] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0136] 3. Health Data Collection

[0137] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[0138] User (homeroom teacher) functions

[0139] The user (homeroom teacher) uses the following functions.

[0140] 1. Check the dashboard

[0141] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[0142] 2. Lesson planning

[0143] Use the dashboard to plan appropriate instruction and advice for students.

[0144] Specific examples

[0145] Server example

[0146] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[0147] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[0148] Specific examples of terminals (student devices)

[0149] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[0150] Student A's device completes the practice questions and sends the results data to the server.

[0151] Example of a user (homeroom teacher)

[0152] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[0153] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[0154] Prompt Sentence Examples

[0155] "Student A's test results show that he is not good at fraction calculations. Please create a video explaining fraction calculations for this student in a style similar to that of a cram school teacher."

[0156] "Based on Student B's health data from the previous day, he or she has had enough sleep. Please create a study plan for the next morning that will allow this student to concentrate well."

[0157] This invention is a system that provides learning content optimized for each student and realizes effective learning. This system can maximize the learning effect of students while reducing the burden on teachers.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1: Data collection

[0160] Specific behavior:

[0161] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[0162] input:

[0163] Data collected from student devices and wearable devices.

[0164] Data processing:

[0165] Information from various data sources is integrated and stored in a centralized database.

[0166] output:

[0167] Integrated training and health data sets.

[0168] Step 2: Data analysis

[0169] Specific behavior:

[0170] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and physical condition.

[0171] input:

[0172] Integrated learning and health data.

[0173] Data processing:

[0174] Machine learning algorithms are used to analyze each student's level of understanding and progress.

[0175] Generate visual representations such as graphs and heat maps based on numerical data.

[0176] output:

[0177] Reports on each student's learning progress, level of understanding, weak areas, and physical condition evaluation.

[0178] Step 3: Generate learning content

[0179] Specific behavior:

[0180] The server uses a generative AI model to generate video lesson content and practice questions that correspond to the student's level of understanding and progress.

[0181] input:

[0182] Report on learning progress and comprehension, weak areas, and physical condition evaluation.

[0183] Data processing:

[0184] Generate prompt sentences and input them into a generative AI model.

[0185] A generative AI model generates lesson content based on these prompts.

[0186] output:

[0187] Personalized video lesson content and practice questions.

[0188] Step 4: Optimize your study plan

[0189] Specific behavior:

[0190] The server adjusts and optimizes students' learning plans based on health data.

[0191] input:

[0192] Health data, generated learning content.

[0193] Data processing:

[0194] Analyze health data and calculate the optimal study time and study load.

[0195] Adjust your study plan and generate a new timetable.

[0196] output:

[0197] Optimized study plans.

[0198] Step 5: Deliver your content

[0199] Specific behavior:

[0200] The server delivers the generated learning content and optimized learning plans to students' devices.

[0201] input:

[0202] Learning content, optimized study plans.

[0203] Data processing:

[0204] Converting content and lesson plans into a format that can be received by student devices.

[0205] output:

[0206] Learning content and plans sent to student devices.

[0207] Step 6: Collect learning outcomes

[0208] Specific behavior:

[0209] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0210] input:

[0211] Learning outcome data sent from student devices.

[0212] Data processing:

[0213] Analyzes incoming data and updates student progress reports.

[0214] output:

[0215] Updated learning outcomes data repository.

[0216] Step 7: Refresh the dashboard

[0217] Specific behavior:

[0218] The server updates and provides a dashboard that visually displays learning data for the homeroom teacher.

[0219] input:

[0220] Updated learning outcomes data.

[0221] Data processing:

[0222] Converting the training data into a graphical format for display on a dashboard.

[0223] output:

[0224] Latest dashboard display for homeroom teachers.

[0225] Step 8: Lesson Planning

[0226] Specific behavior:

[0227] The user (homeroom teacher) uses the dashboard to plan appropriate instruction and advice for students.

[0228] input:

[0229] Training data displayed on the dashboard.

[0230] Data processing:

[0231] Identify the necessary instructional content based on learning data.

[0232] output:

[0233] A customized lesson plan for each student.

[0234] (Application example 1)

[0235] 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."

[0236] Conventional learning support systems have had problems in that they are difficult to fully respond to each student's learning progress and level of understanding, and are unable to provide individualized support that takes into account the student's physical condition and lifestyle. It is also difficult for teachers to grasp students' learning outcomes in real time, making effective instruction difficult. Another issue is that it is difficult for the generated learning content to sustain students' interest. The goal of this system is to solve these problems and provide a learning experience that is optimized for each student.

[0237] 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.

[0238] In this invention, the server includes: means for optimizing the generated learning content based on each student's individual learning progress and level of comprehension; means for distributing the learning content to a device that displays the learning content; means for displaying the learning content; means for collecting learning outcomes from the device; means for analyzing the learning outcomes and generating new learning content; means for collecting health data and optimizing learning plans; means for providing learning content based on the health data; means for providing a dashboard that visually displays learning progress and level of comprehension for teachers; means for being installed on a smartphone as a learning support application; means for acquiring health data from a wearable device and transmitting it to the server; and means for generating video lesson content based on prompts using a generative AI model and providing it according to each student's level of comprehension. This enables the provision of optimized learning content that takes into account each student's learning progress, level of comprehension, and health data. Furthermore, teachers can grasp each student's learning status in real time through the dashboard and provide effective instruction. Furthermore, video lesson content generated based on prompts is more likely to attract students' interest and promote their motivation to learn.

[0239] "Learning content" refers to educational data such as learning materials and exercises that are optimized based on a student's learning progress and level of understanding.

[0240] A "terminal" is an information processing device that displays learning content and is used by students for learning, such as a smartphone or tablet.

[0241] "Learning outcomes" refers to the results data when students complete learning tasks or practice problems, including the percentage of correct answers and the time it takes to complete them.

[0242] "Health data" refers to data that represents a student's physical condition, including their heart rate, sleep time, and activity level.

[0243] "Optimization" means adjusting learning content and plans to be most effective based on each student's learning progress and health condition.

[0244] A "dashboard" is an information display interface that allows teachers to visually check students' learning progress, level of understanding, and physical condition.

[0245] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate learning content and video lessons based on prompt sentences.

[0246] A "prompt sentence" is an instruction sentence that a generative AI model uses to generate learning content, and contains information about the specific content and structure.

[0247] A "wearable device" is a device worn by students to constantly measure and collect health data such as heart rate and activity levels.

[0248] The "server" is a computer system that collects and analyzes learning data and health data and manages the generated learning content.

[0249] A "smartphone" is an information terminal on which learning support applications can be installed and used.

[0250] This invention is a system that provides optimized learning content taking into consideration the learning progress, level of understanding, and health condition of each student. A system that realizes this application example will be described in detail below.

[0251] Server Processing

[0252] The server processes and calculates data using the following hardware and software:

[0253] Hardware: High-performance computer system (e.g., AWS EC2 instance)

[0254] Software: Generative AI models, database management systems (e.g., MySQL®), data analysis tools (e.g., Python libraries)

[0255] Data collection and analysis

[0256] The server first collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). Health data is acquired using wearable devices (e.g., Fitbit, Apple Watch) and sent to the server. The collected data is stored in a database and analyzed using a Python library.

[0257] Generating learning content

[0258] Based on the analyzed learning data, a generative AI model is used to generate video lesson content and practice problems. Lesson content that will attract students' interest is generated based on a prompt. An example of this prompt would be, "Generate video lesson content on 'Calculating Fractions' from Student A's learning data. Please include the following content: 1. An explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations."

[0259] Optimize your study plan

[0260] The server optimizes learning plans based on the student's health data. For example, if the student has had enough sleep the night before, it will adjust the schedule to focus on studying the following morning, ensuring effective learning.

[0261] Content Delivery

[0262] The generated learning content and optimized learning plans are delivered to students' devices (smartphones) in real time via the Internet.

[0263] Providing a dashboard

[0264] The server provides teachers with a dashboard that visually displays students' learning progress, level of understanding, and physical condition, allowing them to grasp students' learning status in real time and provide appropriate guidance.

[0265] Handling terminals (student devices)

[0266] Receive and view learning content

[0267] The student's device receives the video lesson content and exercises delivered from the server. The received content is displayed in an appropriate format through the learning support application, and the student uses the content to study.

[0268] Submitting learning outcomes

[0269] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is automatically sent to the server, allowing the server to continuously monitor the student's learning progress and level of understanding.

[0270] User (homeroom teacher) processing

[0271] Check the dashboard

[0272] Homeroom teachers can use the dashboard provided by the server to visually check students' learning progress, level of understanding, and physical condition, which allows them to plan and implement appropriate guidance and advice.

[0273] Collaboration between servers, devices, and users

[0274] This system provides an individually optimized learning experience by comprehensively managing and optimizing each student's learning progress, level of understanding, and health status. Its unique feature is its ability to provide highly personalized learning content in real time by using a generative AI model. This is expected to improve students' learning efficiency and enhance teachers' teaching effectiveness.

[0275] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0276] Step 1:

[0277] The server collects students' learning data and health data. Learning data includes test results, submitted assignments, and learning history, while health data includes heart rate, sleep time, and activity level. Input data is obtained from students' wearable devices and the learning progress system. These data are stored in a database for the next analysis step.

[0278] Step 2:

[0279] The server analyzes the collected learning data and health data. The learning data and health data collected in step 1 are used as input data. Python libraries are used to analyze and evaluate the data, extracting and evaluating the student's learning progress, level of understanding, areas of weakness, physical condition, etc. The analysis results are used to generate learning content in the next step.

[0280] Step 3:

[0281] The server uses a generative AI model to generate video lesson content and practice problems based on the analysis data. A prompt sentence is entered based on the generated learning data, and the generative AI model generates optimized lesson content. An example of a specific prompt sentence is, "Please generate video lesson content on 'fraction calculations' from Student A's learning data. Please include the following content: 1. Explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations." The generated content is stored in a database and prepared for the next distribution step.

[0282] Step 4:

[0283] The server distributes the generated learning content and optimized learning plans to the student's device (smartphone). The content and learning plans generated in step 3 are used as input data. Distribution is performed in real time via the Internet, and the content arrives at the student's device.

[0284] Step 5:

[0285] The device receives the distributed learning content and displays it in an appropriate format. It receives the learning content and study plan distributed from the server as input data. Students watch video lessons and work on practice problems. The device displays the content through a learning support application to support students' learning.

[0286] Step 6:

[0287] The terminal transmits the student's learning results to the server. As input data, it collects performance data (correct answer rate, answer time, etc.) for the learning tasks the student has completed. The terminal transmits this performance data to the server via the Internet, and the server stores it in a database.

[0288] Step 7:

[0289] The server provides teachers with a dashboard that visually displays learning progress, comprehension, and physical condition. The learning outcome data collected in Step 6 and past learning data are used as input data. The dashboard is designed to enable teachers to grasp students' learning status in real time. Teachers can use the dashboard to plan and implement appropriate instruction and advice.

[0290] Step 8:

[0291] The user uses the dashboard provided by the server to visually check the student's learning progress, level of understanding, and physical condition. The dashboard display data from the server is used as input data. Based on this, the user (teacher) can provide feedback to the student and create individual teaching plans to provide effective learning support.

[0292] Through the above steps, the system of the present invention comprehensively manages the learning progress, level of understanding, and health condition of each student, thereby realizing effective learning support.

[0293] 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.

[0294] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and delivers it to their device. The purpose is to maximize learning effectiveness by recognizing the user's emotions during learning and dynamically adjusting the learning content in real time. Below, we will show a specific embodiment of the entire system and explain the program's processing in natural language.

[0295] Server Processing

[0296] 1. Data Collection and Analysis

[0297] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[0298] The collected data is analyzed to assess students' learning progress, level of understanding, areas of weakness, current physical condition, emotional state, etc.

[0299] 2. Generating learning content

[0300] The server uses a generative AI model to generate video lesson content that mimics the way a cram school teacher conducts a lesson. This AI model adopts a lesson format that is likely to attract students' attention.

[0301] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0302] 3. Optimize your study plan

[0303] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[0304] 4. Content Delivery

[0305] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0306] 5. Providing a dashboard

[0307] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[0308] Handling terminals (student devices)

[0309] 1. Receiving and viewing learning content

[0310] Students' devices receive video lesson content and practice questions delivered from the server.

[0311] The received content is presented in an appropriate format to engage students in their learning.

[0312] 2. Monitoring emotions during learning

[0313] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[0314] 3. Submit your learning outcomes

[0315] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0316] User (homeroom teacher) processing

[0317] 1. Check the dashboard

[0318] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[0319] Use the dashboard to plan appropriate instruction and advice for students.

[0320] Specific examples

[0321] Server example

[0322] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[0323] The server analyzes Student A's health and emotional data, determines that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his study plan to reduce his learning load.

[0324] Specific examples of terminals (student devices)

[0325] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[0326] The device monitors Student A's facial expressions while he is studying using a camera, and if the emotion engine determines that he is feeling stressed, it sends the data to the server in real time.

[0327] Student A completes the practice questions and sends the results data to the server.

[0328] Example of a user (homeroom teacher)

[0329] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations" and is feeling stressed while studying.

[0330] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding. The teacher will also explore the reasons why the student felt stressed and provide appropriate feedback.

[0331] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[0332] The processing flow will be explained below.

[0333] Step 1:

[0334] Data collection: The server retrieves students' learning data (test results, submitted assignments, learning history, etc.) from the database. It also receives students' health data (heart rate, sleep time, activity level, etc.) from the wearable device. Furthermore, the emotion engine collects students' emotional data (facial expressions, tone of voice, etc.) via the device's camera and microphone.

[0335] Step 2:

[0336] Data analysis: The server analyzes the acquired data to evaluate each student's level of understanding, learning progress, and weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm. It also analyzes emotional data in real time to determine the student's current emotional state (joy, excitement, anxiety, stress, etc.).

[0337] Step 3:

[0338] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[0339] Step 4:

[0340] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[0341] Step 5:

[0342] Optimization of study plans: The server generates optimal study plans based on health and emotional data. For example, if fatigue or stress levels are high, the server will adjust the study plan by reducing the study load and adding relaxing content.

[0343] Step 6:

[0344] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0345] Step 7:

[0346] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[0347] Step 8:

[0348] Emotion monitoring during learning: The device uses a camera and microphone to analyze students' facial expressions and tone of voice with an emotion engine, and sends emotional data to the server in real time. If the emotion exceeds a certain threshold, a notification is sent.

[0349] Step 9:

[0350] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[0351] Step 10:

[0352] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[0353] Step 11:

[0354] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[0355] Step 12:

[0356] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, which visually displays each student's learning progress, level of understanding, weak areas, physical condition, and emotional state.

[0357] Step 13:

[0358] Checking the dashboard: The user (teacher) checks the dashboard to understand the student's learning situation and emotional state, consider necessary measures, and plan additional instruction and support.

[0359] Step 14:

[0360] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[0361] By repeating these steps, we will create a system that supports individually optimized learning for students and maximizes learning effectiveness by utilizing real-time feedback from the emotion engine.

[0362] Example 2

[0363] 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."

[0364] Conventional learning management systems have difficulty providing optimal learning content that takes into account each learner's progress and level of understanding, and are unable to reflect the learner's emotional state in real time, resulting in problems such as reduced learning efficiency and decreased learner motivation.

[0365] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for optimizing the generated learning content based on each learner's individual learning progress and level of comprehension, means for distributing the learning content to a terminal that displays the learning content, means for displaying the learning content, means for collecting learning outcomes from the terminal, means for analyzing the learning outcomes and generating new learning content, means for collecting health data and optimizing a learning plan, means for providing learning content based on the health data, means for analyzing emotional data collected in real time and dynamically adjusting the learning content, and means for providing a dashboard that visually displays the learning progress and level of comprehension for teachers. This enables the provision of learning content optimized for each learner and a dynamic learning experience that reflects emotional states in real time.

[0366] "Generated learning content" refers to educational materials and exercises generated using digital tools and artificial intelligence.

[0367] "Individual learning progress" refers to the current learning progress of each learner, and indicates the extent to which they have understood and acquired the material.

[0368] "Comprehension" is an indicator that measures how accurately a learner understands a specific learning content.

[0369] "Devices" refer to digital devices used by learners, such as computers, tablets, and smartphones.

[0370] "Learning outcomes" refers to the grades and performance data that learners obtain as a result of completing assignments and tests.

[0371] "Health data" refers to data that indicates a learner's physical condition, such as heart rate, sleep time, and activity level.

[0372] "Emotional data" refers to data that indicates the emotional state of a learner, as obtained from facial expressions, tone of voice, etc.

[0373] A "dashboard" is a user interface that visually displays learning progress, comprehension, emotional state, etc.

[0374] A "generative AI model" is a model for creating new content using artificial intelligence.

[0375] A "prompt" is a sentence of instructions or questions that is input into a generative AI model.

[0376] "Dynamic adjustment" means changing content and settings as needed in response to changing real-time conditions.

[0377] These definitions clarify the meaning of key terms contained in the following claims.

[0378] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their devices. A specific embodiment of this entire system is shown below.

[0379] Server Processing

[0380] The server uses the following hardware and software:

[0381] Hardware: A server machine equipped with a high-performance processor

[0382] Software: Database management systems (e.g., MySQL), generative AI models (e.g., GPT-4®), emotion engines (e.g., Emotion API), data analysis libraries (e.g., scikit-learn)

[0383] 1. Data Collection and Analysis

[0384] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[0385] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, weak areas, current physical condition, emotional state, etc. The analysis is carried out using machine learning models and statistical methods.

[0386] 2. Generating learning content

[0387] The server uses a generative AI model (e.g., GPT-4) to generate video lesson content that mimics the teacher's teaching style. This AI model adopts a lesson format that is likely to attract students' attention.

[0388] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0389] An example prompt is, "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[0390] 3. Optimize your study plan

[0391] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[0392] 4. Content Delivery

[0393] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0394] 5. Providing a dashboard

[0395] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[0396] Handling terminals (student devices)

[0397] The terminal uses the following hardware and software:

[0398] Hardware: Learners' computers, tablets, smartphones, etc.

[0399] Software: Video playback software, emotion analysis software (e.g., OpenCV)

[0400] 1. Receiving and viewing learning content

[0401] The terminal receives video lesson content and practice questions delivered from the server.

[0402] The device displays the received content in the appropriate format, allowing students to engage in their studies.

[0403] 2. Monitoring emotions during learning

[0404] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[0405] 3. Submit your learning outcomes

[0406] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0407] User (homeroom teacher) processing

[0408] 1. Check the dashboard

[0409] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[0410] Use the dashboard to plan appropriate instruction and advice for students.

[0411] As a specific example, the server identifies Student A's weak areas in "fraction calculations" based on his past learning data and current learning progress, and generates video lesson content specialized for that area. It also analyzes Student A's health and emotional data, confirms that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his learning plan to reduce his learning load.

[0412] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[0413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0414] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[0415] Server Processing

[0416] Step 1: Data collection and analysis preparation

[0417] Input: Student learning data, health data, and emotion data

[0418] What happens: The server initializes the database and API connections.

[0419] Output: Database connection object, API connection object

[0420] Step 2: Collect training data

[0421] Input: Student ID

[0422] What it does: The server sends an SQL query to retrieve the learning data corresponding to the student ID from the database.

[0423] Output: Student learning dataset (test results, assignment submissions, learning history, etc.)

[0424] Example: "SELECT FROM training_data WHERE student_id = 'A123'"

[0425] Step 3: Collect health data

[0426] Input: API request

[0427] How it works: The server retrieves health data from the wearable device via an API request.

[0428] Output: Student health dataset (heart rate, sleep time, activity level, etc.)

[0429] Example: "GET / api / healthdata?student_id=A123"

[0430] Step 4: Collecting sentiment data

[0431] Input: Real-time data from the device

[0432] How it works: The server receives student emotion data using WebSocket or HTTP POST requests.

[0433] Output: Student emotion dataset (happiness, interest, anxiety, etc.)

[0434] Step 5: Analyze the data

[0435] Input: Training dataset, Health dataset, Emotion dataset

[0436] How it works: The server analyzes the data using machine learning models (e.g., scikit-learn) to assess the student's learning progress, comprehension, weak areas, physical condition, and emotional state.

[0437] Output: Analysis results (learning progress, level of understanding, weak areas, etc.)

[0438] Step 6: Prepare to generate learning content

[0439] Input: Analysis results

[0440] What it does: The server initializes a generative AI model (e.g., GPT-4) and generates a prompt.

[0441] Output: prompt statement

[0442] Example: "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[0443] Step 7: Generate learning content

[0444] Input: prompt statement

[0445] Operation: The server inputs prompt sentences into the generative AI model and generates video lesson content.

[0446] Output: Video lesson content

[0447] Step 8: Optimize your study plan

[0448] Input: Health data, emotion data

[0449] How it works: The server generates the most efficient learning schedule based on health and emotional data.

[0450] Output: Optimized learning plan

[0451] Example: Reducing study load and adjusting sleep schedule

[0452] Step 9: Deliver your content

[0453] Input: Video lesson content, optimized learning plans

[0454] How it works: The server sends this data to the student's device.

[0455] Output: Data delivered to student devices

[0456] Step 10: Update the dashboard

[0457] Input: Analysis results, emotion data

[0458] What it does: The server then displays this data in a dashboard for teachers.

[0459] Output: Updated dashboard

[0460] Handling terminals (student devices)

[0461] Step 1: Receiving content

[0462] Input: Data delivered from the server

[0463] Operation: The device receives the video lesson content and exercises from the server.

[0464] Output: Received learning content, exercises

[0465] Step 2: Viewing content

[0466] Input: Received learning content

[0467] What happens: The device displays the received content in the appropriate format, and the student engages with their learning.

[0468] Output: Displayed learning content

[0469] Step 3: Monitoring sentiment data

[0470] Input: Real-time facial and voice data from camera and microphone

[0471] How it works: The device uses a camera and microphone to analyze students' facial expressions and tone of voice using an emotion engine.

[0472] Output: Parsed emotion data

[0473] Step 4: Sending emotion data

[0474] Input: Parsed emotion data

[0475] How it works: The device sends emotion data to the server in real time.

[0476] Output: Emotion data sent to the server

[0477] Step 5: Record and submit your learning outcomes

[0478] Input: Study task performance data (correct answer rate, answer time, etc.)

[0479] How it works: When a student completes a learning task, the performance data is recorded and sent to the server.

[0480] Output: Learning outcome data sent to the server

[0481] User (homeroom teacher) processing

[0482] Step 1: Check the dashboard

[0483] Input: Updated dashboard

[0484] How it works: The teacher accesses the dashboard from a web browser and checks the data.

[0485] Output: Confirmed learning progress, comprehension, and emotional state

[0486] Step 2: Plan your lesson

[0487] Input: Dashboard data

[0488] How it works: The teacher uses the dashboard analysis results to plan instruction and feedback for the students.

[0489] Output: Planned lesson content

[0490] Through these specific processing steps, the present invention is a system that provides an optimized learning environment for each learner and realizes effective education.

[0491] (Application example 2)

[0492] 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."

[0493] Conventional in-car entertainment systems rely on static content delivery and are unable to respond quickly to changes in passengers' emotional state or preferences. This makes it difficult to improve passenger satisfaction and relaxation, and provides a comfortable riding experience.

[0494] 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 optimizing the generated personalized content based on individual conditions and preferences, means for delivering the content to a display device in the vehicle that displays the content, means for displaying the content, means for collecting behavioral data from the display device, means for analyzing the behavioral data and generating new content, means for collecting emotional data and optimizing the content to be provided, means for providing content based on the emotional data, and means for providing a dashboard that visually displays the conditions and emotional states in the vehicle. This enables dynamic content delivery that quickly responds to the emotional conditions and preferences of passengers.

[0495] "Generated personalized content" refers to entertainment and information that is optimized based on a passenger's individual circumstances and preferences.

[0496] "Individual conditions" refers to the different circumstances of each passenger, such as their physical condition, emotional state, and current environment.

[0497] "Preferences" refer to genres or types of content that a passenger is particularly interested in, such as music, movies, news, etc.

[0498] An "in-vehicle display device" is a device installed inside a vehicle for displaying or playing content, such as a screen, monitor, or speaker.

[0499] "Behavioral data" refers to data such as passenger operation history, viewing history, and physical reactions collected from display devices and sensors inside the vehicle.

[0500] "Emotional data" refers to data on passengers' emotional states that is determined from their facial expressions, tone of voice, heart rate, etc., collected using sensors such as cameras and microphones.

[0501] A "dashboard" is an interface that visually displays passenger status, emotional state, system operation status, etc.

[0502] This invention provides a personalized infotainment system that enhances the entertainment experience for passengers in autonomous vehicles. The system delivers content optimized based on each passenger's individual conditions and preferences, ensuring a comfortable and satisfying riding experience.

[0503] System configuration

[0504] server

[0505] The server includes the following means:

[0506] 1. A means to optimize the generated personalized content based on individual conditions and preferences.

[0507] 2. Means for delivering said content to a display device within the vehicle.

[0508] 3. A means of collecting behavioral and emotional data and generating new content.

[0509] 4. Means for providing content based on said emotion data.

[0510] 5. A means of providing a dashboard that visually displays the passenger's condition and emotional state.

[0511] The server analyzes behavioral and emotional data collected using cameras and microphones, generates new content using generative AI models, and delivers optimized content based on passenger preferences and their current emotional state.

[0512] Terminal (display device inside the vehicle)

[0513] The terminal does the following:

[0514] 1. Receive and display or play content delivered from the server.

[0515] 2. Passengers' facial expressions and tone of voice are captured through cameras and microphones and analyzed using an emotion engine (e.g., Affectiva SDK).

[0516] 3. The analysis results are sent to the server in real time and dynamic content adjustments are made.

[0517] User (passenger)

[0518] The user does the following:

[0519] 1. View content provided through a display device in the vehicle.

[0520] 2. Providing emotional data such as facial expressions and tone of voice.

[0521] Hardware and software used

[0522] Camera: Used to monitor passengers' facial expressions.

[0523] Microphone: Used to analyze passengers' voice tones.

[0524] Emotion engine (e.g., Affectiva SDK): assesses the passenger's emotional state.

[0525] Generative AI models (e.g., OpenAI® GPT-4): Generate personalized content.

[0526] Data analysis server: Analyzes behavioral and emotional data to optimize content.

[0527] Specific examples

[0528] For example, if a passenger feels like relaxing on a rainy day, the system collects emotional data in real time and sends a prompt to the generative AI model, such as:

[0529] "A passenger wants to relax on a rainy day. Their tastes are classical music and jazz. Generate a music playlist that is perfect for this situation."

[0530] Based on this prompt, the generative AI model will generate an optimal music playlist, which the server will then distribute to the display devices inside the vehicle, allowing passengers to enjoy relaxing music and a comfortable riding experience.

[0531] As described above, this system provides content that is dynamically optimized according to the individual state and emotional state of each passenger, ensuring a comfortable riding experience.

[0532] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0533] Step 1:

[0534] The server uses a camera and microphone to capture the facial expressions and tone of voice of passengers in the vehicle. This data is analyzed by an emotion engine (e.g., Affectiva SDK) to evaluate the passenger's current emotional state. The input is camera video and audio data, and the output is the passenger's emotional state (e.g., relaxed, anxious, etc.). Specifically, the facial expression analysis module and audio analysis module process the data in real time to determine the emotional state.

[0535] Step 2:

[0536] The server collects passengers' past behavioral data (riding history, music and video play history) and analyzed emotional data, and sends it to the data analysis server. The input is data collected from the camera and microphone and past behavioral history, and the output is log information for data analysis. Specifically, the server retrieves passenger history data from the database and integrates it with emotional data.

[0537] Step 3:

[0538] The data analysis server sends prompts to the generative AI model based on the passenger's preferences and current emotional state. For example, it generates a prompt like, "A passenger on a rainy day feels like relaxing. Their hobbies are classical music and jazz. Please generate a music playlist that is best suited to this situation." The input is emotional data and passenger preference data, and the output is a prompt. Specifically, the prompt generation module receives the data and creates an appropriate prompt.

[0539] Step 4:

[0540] The generative AI model generates optimal personalized content based on the received prompt. The input is the prompt, and the output is personalized content (e.g., music playlist, video list). Specifically, the generative AI model performs natural language processing and creates content based on the prompt.

[0541] Step 5:

[0542] The server distributes the generated personalized content to the display device in the vehicle. The input is the content from the generative AI model, and the output is the content data to the display device. Specifically, the content distribution module receives the data and sends it to the specified device.

[0543] Step 6:

[0544] The terminal (display device inside the vehicle) displays or plays the distributed content. The input is content data from the server, and the output is the video or music that passengers watch. Specifically, the playback module receives the content data and displays or plays it on the screen or speaker.

[0545] Step 7:

[0546] The device again collects the passenger's emotional data through the camera and microphone and transmits it to the server in real time. The input is new camera video and audio data, and the output is updated emotional state data. Specifically, the emotion monitoring module continues to analyze the data and send it back to the server.

[0547] 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.

[0548] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0549] 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.

[0550] [Second embodiment]

[0551] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0552] 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.

[0553] 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).

[0554] 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.

[0555] 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.

[0556] 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).

[0557] 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. 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.

[0558] 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.

[0559] 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.

[0560] 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.

[0561] 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.

[0562] 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."

[0563] This invention is a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their terminals. Below, we will show a specific embodiment of the entire system and explain the program processing in natural language.

[0564] Server Processing

[0565] 1. Data Collection and Analysis

[0566] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[0567] The collected data is analyzed to evaluate students' learning progress, level of understanding, areas of weakness, current physical condition, etc.

[0568] 2. Generating learning content

[0569] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model learns the teacher's speech patterns and explanation methods, and reproduces the lesson style that attracts students' attention.

[0570] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0571] 3. Optimize your study plan

[0572] The server uses health data to optimize a student's study schedule, for example by concentrating study time in the morning after a student has had enough sleep.

[0573] 4. Content Delivery

[0574] The server delivers the generated learning content and optimized learning plans to students' devices.

[0575] 5. Providing a dashboard

[0576] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[0577] Handling terminals (student devices)

[0578] 1. Receiving and viewing learning content

[0579] Students' devices receive video lesson content and practice questions delivered from the server.

[0580] The received content is presented in an appropriate format to engage students in their learning.

[0581] 2. Submit your learning outcomes

[0582] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0583] 3. Health Data Collection

[0584] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[0585] User (homeroom teacher) processing

[0586] 1. Check the dashboard

[0587] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[0588] Use the dashboard to plan appropriate instruction and advice for students.

[0589] Specific examples

[0590] Server example

[0591] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[0592] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[0593] Specific examples of terminals (student devices)

[0594] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[0595] Student A's device completes the practice questions and sends the results data to the server.

[0596] Example of a user (homeroom teacher)

[0597] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[0598] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[0599] In this way, the present invention is a system that provides learning content optimized for each student, reduces the burden on teachers, and realizes effective learning.

[0600] The processing flow will be explained below.

[0601] Step 1:

[0602] Data collection: The server retrieves students' past learning data (e.g., test results, submitted assignments, and learning history) from the database. It also receives students' health data (e.g., heart rate, sleep duration, and activity level) from the wearable device.

[0603] Step 2:

[0604] Data analysis: The server analyzes the acquired data, evaluates each student's level of understanding, and identifies weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm.

[0605] Step 3:

[0606] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[0607] Step 4:

[0608] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[0609] Step 5:

[0610] Optimizing learning plans: The server takes into account students' health data and generates the most efficient learning schedule. For example, it will reduce the learning load for students who are not getting enough sleep.

[0611] Step 6:

[0612] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0613] Step 7:

[0614] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[0615] Step 8:

[0616] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[0617] Step 9:

[0618] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[0619] Step 10:

[0620] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[0621] Step 11:

[0622] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, visually displaying each student's learning progress, level of understanding, areas of weakness, etc.

[0623] Step 12:

[0624] Checking the dashboard: The user (homeroom teacher) checks the dashboard to understand the student's learning status, considers necessary measures, and plans additional instruction and support.

[0625] Step 13:

[0626] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[0627] By repeating the above steps, it is possible to provide individually optimized and continuous learning support.

[0628] Example 1

[0629] 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."

[0630] Conventional learning systems have difficulty optimizing learning content that comprehensively reflects individual data such as each student's learning progress, level of understanding, and physical condition, and as a result, have not been able to provide sufficient, effective learning support. Furthermore, it places a heavy burden on teachers to grasp students' learning progress and level of understanding and provide individual support. Therefore, there was a need for a system that provides learning support optimized for each student's learning needs and reduces the burden on teachers.

[0631] 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.

[0632] In this invention, the server includes a means for collecting, analyzing, and evaluating students' learning data and health data, a means for generating learning content based on the students' learning progress and level of understanding using a generative AI model, and a means for delivering the generated learning content and optimized learning plans to the students' devices, thereby enabling the provision of learning content optimized based on the students' individual learning progress, level of understanding, and physical condition.

[0633] "Student learning data" refers to information related to a student's learning activities, such as test results, submitted assignments, and learning history.

[0634] "Health data" refers to information about a student's physical condition, such as heart rate, sleep duration, and activity level.

[0635] A "generative AI model" is an artificial intelligence model that generates learning content according to a student's learning progress and level of understanding.

[0636] "Learning content" refers to educational materials such as generated video lessons and exercises.

[0637] A "device" is a device used by a student to view learning content and perform learning activities.

[0638] "Learning outcome data" refers to data such as the percentage of correct answers and the time it took to answer a question obtained after a student has completed a learning task.

[0639] A "wearable device" is a device worn by students that measures and records health data such as heart rate and activity levels.

[0640] The "dashboard" is an interface that allows homeroom teachers to visually check students' learning progress, level of understanding, and health status.

[0641] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[0642] This invention is a system that provides learning content optimized for each student based on their learning progress, level of understanding, and physical condition. The system consists of three main components: a server, a terminal (student device), and a user (homeroom teacher).

[0643] Server Features

[0644] The server has the following functions:

[0645] 1. Data Collection and Analysis

[0646] The server collects students' learning data (e.g., test results, submitted assignments, learning history, etc.) and health data (e.g., heart rate, sleep time, activity level, etc.).

[0647] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and current physical condition.

[0648] 2. Generating learning content

[0649] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model has learned the teacher's speech patterns and explanation methods.

[0650] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0651] 3. Optimize your study plan

[0652] The server uses health data to optimize a student's study plan, for example by concentrating study time in the morning after a student has had enough sleep.

[0653] 4. Content Delivery

[0654] The server delivers the generated learning content and optimized learning plans to students' devices.

[0655] 5. Providing a dashboard

[0656] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[0657] Device (student device) capabilities

[0658] Student devices have the following features:

[0659] 1. Receiving and viewing learning content

[0660] Students' devices receive video lesson content and practice questions delivered from the server.

[0661] The received content is presented in an appropriate format to engage students in their learning.

[0662] 2. Submit your learning outcomes

[0663] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0664] 3. Health Data Collection

[0665] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[0666] User (homeroom teacher) functions

[0667] The user (homeroom teacher) uses the following functions.

[0668] 1. Check the dashboard

[0669] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[0670] 2. Lesson planning

[0671] Use the dashboard to plan appropriate instruction and advice for students.

[0672] Specific examples

[0673] Server example

[0674] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[0675] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[0676] Specific examples of terminals (student devices)

[0677] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[0678] Student A's device completes the practice questions and sends the results data to the server.

[0679] Example of a user (homeroom teacher)

[0680] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[0681] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[0682] Prompt Sentence Examples

[0683] "Student A's test results show that he is not good at fraction calculations. Please create a video explaining fraction calculations for this student in a style similar to that of a cram school teacher."

[0684] "Based on Student B's health data from the previous day, he or she has had enough sleep. Please create a study plan for the next morning that will allow this student to concentrate well."

[0685] This invention is a system that provides learning content optimized for each student and realizes effective learning. This system can maximize the learning effect of students while reducing the burden on teachers.

[0686] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0687] Step 1: Data collection

[0688] Specific behavior:

[0689] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[0690] input:

[0691] Data collected from student devices and wearable devices.

[0692] Data processing:

[0693] Information from various data sources is integrated and stored in a centralized database.

[0694] output:

[0695] Integrated training and health data sets.

[0696] Step 2: Data analysis

[0697] Specific behavior:

[0698] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and physical condition.

[0699] input:

[0700] Integrated learning and health data.

[0701] Data processing:

[0702] Machine learning algorithms are used to analyze each student's level of understanding and progress.

[0703] Generate visual representations such as graphs and heat maps based on numerical data.

[0704] output:

[0705] Reports on each student's learning progress, level of understanding, weak areas, and physical condition evaluation.

[0706] Step 3: Generate learning content

[0707] Specific behavior:

[0708] The server uses a generative AI model to generate video lesson content and practice questions that correspond to the student's level of understanding and progress.

[0709] input:

[0710] Report on learning progress and comprehension, weak areas, and physical condition evaluation.

[0711] Data processing:

[0712] Generate prompt sentences and input them into a generative AI model.

[0713] A generative AI model generates lesson content based on these prompts.

[0714] output:

[0715] Personalized video lesson content and practice questions.

[0716] Step 4: Optimize your study plan

[0717] Specific behavior:

[0718] The server adjusts and optimizes students' learning plans based on health data.

[0719] input:

[0720] Health data, generated learning content.

[0721] Data processing:

[0722] Analyze health data and calculate the optimal study time and study load.

[0723] Adjust your study plan and generate a new timetable.

[0724] output:

[0725] Optimized study plans.

[0726] Step 5: Deliver your content

[0727] Specific behavior:

[0728] The server delivers the generated learning content and optimized learning plans to students' devices.

[0729] input:

[0730] Learning content, optimized study plans.

[0731] Data processing:

[0732] Converting content and lesson plans into a format that can be received by student devices.

[0733] output:

[0734] Learning content and plans sent to student devices.

[0735] Step 6: Collect learning outcomes

[0736] Specific behavior:

[0737] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0738] input:

[0739] Learning outcome data sent from student devices.

[0740] Data processing:

[0741] Analyzes incoming data and updates student progress reports.

[0742] output:

[0743] Updated learning outcomes data repository.

[0744] Step 7: Refresh the dashboard

[0745] Specific behavior:

[0746] The server updates and provides a dashboard that visually displays learning data for the homeroom teacher.

[0747] input:

[0748] Updated learning outcomes data.

[0749] Data processing:

[0750] Converting the training data into a graphical format for display on a dashboard.

[0751] output:

[0752] Latest dashboard display for homeroom teachers.

[0753] Step 8: Lesson Planning

[0754] Specific behavior:

[0755] The user (homeroom teacher) uses the dashboard to plan appropriate instruction and advice for students.

[0756] input:

[0757] Training data displayed on the dashboard.

[0758] Data processing:

[0759] Identify the necessary instructional content based on learning data.

[0760] output:

[0761] A customized lesson plan for each student.

[0762] (Application example 1)

[0763] 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."

[0764] Conventional learning support systems have had problems in that they are difficult to fully respond to each student's learning progress and level of understanding, and are unable to provide individualized support that takes into account the student's physical condition and lifestyle. It is also difficult for teachers to grasp students' learning outcomes in real time, making effective instruction difficult. Another issue is that it is difficult for the generated learning content to sustain students' interest. The goal of this system is to solve these problems and provide a learning experience that is optimized for each student.

[0765] 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.

[0766] In this invention, the server includes: means for optimizing the generated learning content based on each student's individual learning progress and level of comprehension; means for distributing the learning content to a device that displays the learning content; means for displaying the learning content; means for collecting learning outcomes from the device; means for analyzing the learning outcomes and generating new learning content; means for collecting health data and optimizing learning plans; means for providing learning content based on the health data; means for providing a dashboard that visually displays learning progress and level of comprehension for teachers; means for being installed on a smartphone as a learning support application; means for acquiring health data from a wearable device and transmitting it to the server; and means for generating video lesson content based on prompts using a generative AI model and providing it according to each student's level of comprehension. This enables the provision of optimized learning content that takes into account each student's learning progress, level of comprehension, and health data. Furthermore, teachers can grasp each student's learning status in real time through the dashboard and provide effective instruction. Furthermore, video lesson content generated based on prompts is more likely to attract students' interest and promote their motivation to learn.

[0767] "Learning content" refers to educational data such as learning materials and exercises that are optimized based on a student's learning progress and level of understanding.

[0768] A "terminal" is an information processing device that displays learning content and is used by students for learning, such as a smartphone or tablet.

[0769] "Learning outcomes" refers to the results data when students complete learning tasks or practice problems, including the percentage of correct answers and the time it takes to complete them.

[0770] "Health data" refers to data that represents a student's physical condition, including their heart rate, sleep time, and activity level.

[0771] "Optimization" means adjusting learning content and plans to be most effective based on each student's learning progress and health condition.

[0772] A "dashboard" is an information display interface that allows teachers to visually check students' learning progress, level of understanding, and physical condition.

[0773] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate learning content and video lessons based on prompt sentences.

[0774] A "prompt sentence" is an instruction sentence that a generative AI model uses to generate learning content, and contains information about the specific content and structure.

[0775] A "wearable device" is a device worn by students to constantly measure and collect health data such as heart rate and activity levels.

[0776] The "server" is a computer system that collects and analyzes learning data and health data and manages the generated learning content.

[0777] A "smartphone" is an information terminal on which learning support applications can be installed and used.

[0778] This invention is a system that provides optimized learning content taking into consideration the learning progress, level of understanding, and health condition of each student. A system that realizes this application example will be described in detail below.

[0779] Server Processing

[0780] The server processes and calculates data using the following hardware and software:

[0781] Hardware: High-performance computer systems (e.g., AWS EC2 instances)

[0782] Software: Generative AI models, database management systems (e.g., MySQL), data analysis tools (e.g., Python libraries)

[0783] Data collection and analysis

[0784] The server first collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). Health data is acquired using wearable devices (e.g., Fitbit, Apple Watch) and sent to the server. The collected data is stored in a database and analyzed using a Python library.

[0785] Generating learning content

[0786] Based on the analyzed learning data, a generative AI model is used to generate video lesson content and practice problems. Lesson content that will attract students' interest is generated based on a prompt. An example of this prompt would be, "Generate video lesson content on 'Calculating Fractions' from Student A's learning data. Please include the following content: 1. An explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations."

[0787] Optimize your study plan

[0788] The server optimizes learning plans based on the student's health data. For example, if the student has had enough sleep the night before, it will adjust the schedule to focus on studying the following morning, ensuring effective learning.

[0789] Content Delivery

[0790] The generated learning content and optimized learning plans are delivered to students' devices (smartphones) in real time via the Internet.

[0791] Providing a dashboard

[0792] The server provides teachers with a dashboard that visually displays students' learning progress, level of understanding, and physical condition, allowing them to grasp students' learning status in real time and provide appropriate guidance.

[0793] Handling terminals (student devices)

[0794] Receive and view learning content

[0795] The student's device receives the video lesson content and exercises delivered from the server. The received content is displayed in an appropriate format through the learning support application, and the student uses the content to study.

[0796] Submitting learning outcomes

[0797] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is automatically sent to the server, allowing the server to continuously monitor the student's learning progress and level of understanding.

[0798] User (homeroom teacher) processing

[0799] Check the dashboard

[0800] Homeroom teachers can use the dashboard provided by the server to visually check students' learning progress, level of understanding, and physical condition, which allows them to plan and implement appropriate guidance and advice.

[0801] Collaboration between servers, devices, and users

[0802] This system provides an individually optimized learning experience by comprehensively managing and optimizing each student's learning progress, level of understanding, and health status. Its unique feature is its ability to provide highly personalized learning content in real time by using a generative AI model. This is expected to improve students' learning efficiency and enhance teachers' teaching effectiveness.

[0803] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0804] Step 1:

[0805] The server collects students' learning data and health data. Learning data includes test results, submitted assignments, and learning history, while health data includes heart rate, sleep time, and activity level. Input data is obtained from students' wearable devices and the learning progress system. These data are stored in a database for the next analysis step.

[0806] Step 2:

[0807] The server analyzes the collected learning data and health data. The learning data and health data collected in step 1 are used as input data. Python libraries are used to analyze and evaluate the data, extracting and evaluating the student's learning progress, level of understanding, areas of weakness, physical condition, etc. The analysis results are used to generate learning content in the next step.

[0808] Step 3:

[0809] The server uses a generative AI model to generate video lesson content and practice problems based on the analysis data. A prompt sentence is entered based on the generated learning data, and the generative AI model generates optimized lesson content. An example of a specific prompt sentence is, "Please generate video lesson content on 'fraction calculations' from Student A's learning data. Please include the following content: 1. Explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations." The generated content is stored in a database and prepared for the next distribution step.

[0810] Step 4:

[0811] The server distributes the generated learning content and optimized learning plans to the student's device (smartphone). The content and learning plans generated in step 3 are used as input data. Distribution is performed in real time via the Internet, and the content arrives at the student's device.

[0812] Step 5:

[0813] The device receives the distributed learning content and displays it in an appropriate format. It receives the learning content and study plan distributed from the server as input data. Students watch video lessons and work on practice problems. The device displays the content through a learning support application to support students' learning.

[0814] Step 6:

[0815] The terminal transmits the student's learning results to the server. As input data, it collects performance data (correct answer rate, answer time, etc.) for the learning tasks the student has completed. The terminal transmits this performance data to the server via the Internet, and the server stores it in a database.

[0816] Step 7:

[0817] The server provides teachers with a dashboard that visually displays learning progress, comprehension, and physical condition. The learning outcome data collected in Step 6 and past learning data are used as input data. The dashboard is designed to enable teachers to grasp students' learning status in real time. Teachers can use the dashboard to plan and implement appropriate instruction and advice.

[0818] Step 8:

[0819] The user uses the dashboard provided by the server to visually check the student's learning progress, level of understanding, and physical condition. The dashboard display data from the server is used as input data. Based on this, the user (teacher) can provide feedback to the student and create individual teaching plans to provide effective learning support.

[0820] Through the above steps, the system of the present invention comprehensively manages the learning progress, level of understanding, and health condition of each student, thereby realizing effective learning support.

[0821] 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.

[0822] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and delivers it to their device. The purpose is to maximize learning effectiveness by recognizing the user's emotions during learning and dynamically adjusting the learning content in real time. Below, we will show a specific embodiment of the entire system and explain the program's processing in natural language.

[0823] Server Processing

[0824] 1. Data Collection and Analysis

[0825] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[0826] The collected data is analyzed to assess students' learning progress, level of understanding, areas of weakness, current physical condition, emotional state, etc.

[0827] 2. Generating learning content

[0828] The server uses a generative AI model to generate video lesson content that mimics the way a cram school teacher conducts a lesson. This AI model adopts a lesson format that is likely to attract students' attention.

[0829] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0830] 3. Optimize your study plan

[0831] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[0832] 4. Content Delivery

[0833] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0834] 5. Providing a dashboard

[0835] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[0836] Handling terminals (student devices)

[0837] 1. Receiving and viewing learning content

[0838] Students' devices receive video lesson content and practice questions delivered from the server.

[0839] The received content is presented in an appropriate format to engage students in their learning.

[0840] 2. Monitoring emotions during learning

[0841] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[0842] 3. Submit your learning outcomes

[0843] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0844] User (homeroom teacher) processing

[0845] 1. Check the dashboard

[0846] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[0847] Use the dashboard to plan appropriate instruction and advice for students.

[0848] Specific examples

[0849] Server example

[0850] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[0851] The server analyzes Student A's health and emotional data, determines that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his study plan to reduce his learning load.

[0852] Specific examples of terminals (student devices)

[0853] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[0854] The device monitors Student A's facial expressions while he is studying using a camera, and if the emotion engine determines that he is feeling stressed, it sends the data to the server in real time.

[0855] Student A completes the practice questions and sends the results data to the server.

[0856] Example of a user (homeroom teacher)

[0857] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations" and is feeling stressed while studying.

[0858] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding. The teacher will also explore the reasons why the student felt stressed and provide appropriate feedback.

[0859] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[0860] The processing flow will be explained below.

[0861] Step 1:

[0862] Data collection: The server retrieves students' learning data (test results, submitted assignments, learning history, etc.) from the database. It also receives students' health data (heart rate, sleep time, activity level, etc.) from the wearable device. Furthermore, the emotion engine collects students' emotional data (facial expressions, tone of voice, etc.) via the device's camera and microphone.

[0863] Step 2:

[0864] Data analysis: The server analyzes the acquired data to evaluate each student's level of understanding, learning progress, and weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm. It also analyzes emotional data in real time to determine the student's current emotional state (joy, excitement, anxiety, stress, etc.).

[0865] Step 3:

[0866] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[0867] Step 4:

[0868] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[0869] Step 5:

[0870] Optimization of study plans: The server generates optimal study plans based on health and emotional data. For example, if fatigue or stress levels are high, the server will adjust the study plan by reducing the study load and adding relaxing content.

[0871] Step 6:

[0872] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0873] Step 7:

[0874] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[0875] Step 8:

[0876] Emotion monitoring during learning: The device uses a camera and microphone to analyze students' facial expressions and tone of voice with an emotion engine, and sends emotional data to the server in real time. If the emotion exceeds a certain threshold, a notification is sent.

[0877] Step 9:

[0878] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[0879] Step 10:

[0880] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[0881] Step 11:

[0882] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[0883] Step 12:

[0884] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, which visually displays each student's learning progress, level of understanding, weak areas, physical condition, and emotional state.

[0885] Step 13:

[0886] Checking the dashboard: The user (teacher) checks the dashboard to understand the student's learning situation and emotional state, consider necessary measures, and plan additional instruction and support.

[0887] Step 14:

[0888] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[0889] By repeating these steps, we will create a system that supports individually optimized learning for students and maximizes learning effectiveness by utilizing real-time feedback from the emotion engine.

[0890] Example 2

[0891] 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."

[0892] Conventional learning management systems have difficulty providing optimal learning content that takes into account each learner's progress and level of understanding, and are unable to reflect the learner's emotional state in real time, resulting in problems such as reduced learning efficiency and decreased learner motivation.

[0893] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for optimizing the generated learning content based on each learner's individual learning progress and level of comprehension, means for distributing the learning content to a terminal that displays the learning content, means for displaying the learning content, means for collecting learning outcomes from the terminal, means for analyzing the learning outcomes and generating new learning content, means for collecting health data and optimizing a learning plan, means for providing learning content based on the health data, means for analyzing emotional data collected in real time and dynamically adjusting the learning content, and means for providing a dashboard that visually displays the learning progress and level of comprehension for teachers. This enables the provision of learning content optimized for each learner and a dynamic learning experience that reflects emotional states in real time.

[0894] "Generated learning content" refers to educational materials and exercises generated using digital tools and artificial intelligence.

[0895] "Individual learning progress" refers to the current learning progress of each learner, and indicates the extent to which they have understood and acquired the material.

[0896] "Comprehension" is an indicator that measures how accurately a learner understands a specific learning content.

[0897] "Devices" refer to digital devices used by learners, such as computers, tablets, and smartphones.

[0898] "Learning outcomes" refers to the grades and performance data that learners obtain as a result of completing assignments and tests.

[0899] "Health data" refers to data that indicates a learner's physical condition, such as heart rate, sleep time, and activity level.

[0900] "Emotional data" refers to data that indicates the emotional state of a learner, as obtained from facial expressions, tone of voice, etc.

[0901] A "dashboard" is a user interface that visually displays learning progress, comprehension, emotional state, etc.

[0902] A "generative AI model" is a model for creating new content using artificial intelligence.

[0903] A "prompt" is a sentence of instructions or questions that is input into a generative AI model.

[0904] "Dynamic adjustment" means changing content and settings as needed in response to changing real-time conditions.

[0905] These definitions clarify the meaning of key terms contained in the following claims.

[0906] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their devices. A specific embodiment of this entire system is shown below.

[0907] Server Processing

[0908] The server uses the following hardware and software:

[0909] Hardware: A server machine equipped with a high-performance processor

[0910] Software: Database management systems (e.g., MySQL), generative AI models (e.g., GPT-4), emotion engines (e.g., Emotion API), data analysis libraries (e.g., scikit-learn)

[0911] 1. Data Collection and Analysis

[0912] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[0913] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, weak areas, current physical condition, emotional state, etc. The analysis is carried out using machine learning models and statistical methods.

[0914] 2. Generating learning content

[0915] The server uses a generative AI model (e.g., GPT-4) to generate video lesson content that mimics the teacher's teaching style. This AI model adopts a lesson format that is likely to attract students' attention.

[0916] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[0917] An example prompt is, "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[0918] 3. Optimize your study plan

[0919] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[0920] 4. Content Delivery

[0921] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[0922] 5. Providing a dashboard

[0923] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[0924] Handling terminals (student devices)

[0925] The terminal uses the following hardware and software:

[0926] Hardware: Learners' computers, tablets, smartphones, etc.

[0927] Software: Video playback software, emotion analysis software (e.g., OpenCV)

[0928] 1. Receiving and viewing learning content

[0929] The terminal receives video lesson content and practice questions delivered from the server.

[0930] The device displays the received content in the appropriate format, allowing students to engage in their studies.

[0931] 2. Monitoring emotions during learning

[0932] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[0933] 3. Submit your learning outcomes

[0934] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[0935] User (homeroom teacher) processing

[0936] 1. Check the dashboard

[0937] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[0938] Use the dashboard to plan appropriate instruction and advice for students.

[0939] As a specific example, the server identifies Student A's weak areas in "fraction calculations" based on his past learning data and current learning progress, and generates video lesson content specialized for that area. It also analyzes Student A's health and emotional data, confirms that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his learning plan to reduce his learning load.

[0940] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[0941] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0942] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[0943] Server Processing

[0944] Step 1: Data collection and analysis preparation

[0945] Input: Student learning data, health data, and emotion data

[0946] What happens: The server initializes the database and API connections.

[0947] Output: Database connection object, API connection object

[0948] Step 2: Collect training data

[0949] Input: Student ID

[0950] What it does: The server sends an SQL query to retrieve the learning data corresponding to the student ID from the database.

[0951] Output: Student learning dataset (test results, assignment submissions, learning history, etc.)

[0952] Example: "SELECT FROM training_data WHERE student_id = 'A123'"

[0953] Step 3: Collect health data

[0954] Input: API request

[0955] How it works: The server retrieves health data from the wearable device via an API request.

[0956] Output: Student health dataset (heart rate, sleep time, activity level, etc.)

[0957] Example: "GET / api / healthdata?student_id=A123"

[0958] Step 4: Collecting sentiment data

[0959] Input: Real-time data from the device

[0960] How it works: The server receives student emotion data using WebSocket or HTTP POST requests.

[0961] Output: Student emotion dataset (happiness, interest, anxiety, etc.)

[0962] Step 5: Analyze the data

[0963] Input: Training dataset, Health dataset, Emotion dataset

[0964] How it works: The server analyzes the data using machine learning models (e.g., scikit-learn) to assess the student's learning progress, comprehension, weak areas, physical condition, and emotional state.

[0965] Output: Analysis results (learning progress, level of understanding, weak areas, etc.)

[0966] Step 6: Prepare to generate learning content

[0967] Input: Analysis results

[0968] What it does: The server initializes a generative AI model (e.g., GPT-4) and generates a prompt.

[0969] Output: prompt statement

[0970] Example: "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[0971] Step 7: Generate learning content

[0972] Input: prompt statement

[0973] Operation: The server inputs prompt sentences into the generative AI model and generates video lesson content.

[0974] Output: Video lesson content

[0975] Step 8: Optimize your study plan

[0976] Input: Health data, emotion data

[0977] How it works: The server generates the most efficient learning schedule based on health and emotional data.

[0978] Output: Optimized learning plan

[0979] Example: Reducing study load and adjusting sleep schedule

[0980] Step 9: Deliver your content

[0981] Input: Video lesson content, optimized learning plans

[0982] How it works: The server sends this data to the student's device.

[0983] Output: Data delivered to student devices

[0984] Step 10: Update the dashboard

[0985] Input: Analysis results, emotion data

[0986] What it does: The server then displays this data in a dashboard for teachers.

[0987] Output: Updated dashboard

[0988] Handling terminals (student devices)

[0989] Step 1: Receiving content

[0990] Input: Data delivered from the server

[0991] Operation: The device receives the video lesson content and exercises from the server.

[0992] Output: Received learning content, exercises

[0993] Step 2: Viewing content

[0994] Input: Received learning content

[0995] What happens: The device displays the received content in the appropriate format, and the student engages with their learning.

[0996] Output: Displayed learning content

[0997] Step 3: Monitoring sentiment data

[0998] Input: Real-time facial and voice data from camera and microphone

[0999] How it works: The device uses a camera and microphone to analyze students' facial expressions and tone of voice using an emotion engine.

[1000] Output: Parsed emotion data

[1001] Step 4: Sending emotion data

[1002] Input: Parsed emotion data

[1003] How it works: The device sends emotion data to the server in real time.

[1004] Output: Emotion data sent to the server

[1005] Step 5: Record and submit your learning outcomes

[1006] Input: Study task performance data (correct answer rate, answer time, etc.)

[1007] How it works: When a student completes a learning task, the performance data is recorded and sent to the server.

[1008] Output: Learning outcome data sent to the server

[1009] User (homeroom teacher) processing

[1010] Step 1: Check the dashboard

[1011] Input: Updated dashboard

[1012] How it works: The teacher accesses the dashboard from a web browser and checks the data.

[1013] Output: Confirmed learning progress, comprehension, and emotional state

[1014] Step 2: Plan your lesson

[1015] Input: Dashboard data

[1016] How it works: The teacher uses the dashboard analysis results to plan instruction and feedback for the students.

[1017] Output: Planned lesson content

[1018] Through these specific processing steps, the present invention is a system that provides an optimized learning environment for each learner and realizes effective education.

[1019] (Application example 2)

[1020] 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."

[1021] Conventional in-car entertainment systems rely on static content delivery and are unable to respond quickly to changes in passengers' emotional state or preferences. This makes it difficult to improve passenger satisfaction and relaxation, and provides a comfortable riding experience.

[1022] 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 optimizing the generated personalized content based on individual conditions and preferences, means for delivering the content to a display device in the vehicle that displays the content, means for displaying the content, means for collecting behavioral data from the display device, means for analyzing the behavioral data and generating new content, means for collecting emotional data and optimizing the content to be provided, means for providing content based on the emotional data, and means for providing a dashboard that visually displays the conditions and emotional states in the vehicle. This enables dynamic content delivery that quickly responds to the emotional conditions and preferences of passengers.

[1023] "Generated personalized content" refers to entertainment and information that is optimized based on a passenger's individual circumstances and preferences.

[1024] "Individual conditions" refers to the different circumstances of each passenger, such as their physical condition, emotional state, and current environment.

[1025] "Preferences" refer to genres or types of content that a passenger is particularly interested in, such as music, movies, news, etc.

[1026] An "in-vehicle display device" is a device installed inside a vehicle for displaying or playing content, such as a screen, monitor, or speaker.

[1027] "Behavioral data" refers to data such as passenger operation history, viewing history, and physical reactions collected from display devices and sensors inside the vehicle.

[1028] "Emotional data" refers to data on passengers' emotional states that is determined from their facial expressions, tone of voice, heart rate, etc., collected using sensors such as cameras and microphones.

[1029] A "dashboard" is an interface that visually displays passenger status, emotional state, system operation status, etc.

[1030] This invention provides a personalized infotainment system that enhances the entertainment experience for passengers in autonomous vehicles. The system delivers content optimized based on each passenger's individual conditions and preferences, ensuring a comfortable and satisfying riding experience.

[1031] System configuration

[1032] server

[1033] The server includes the following means:

[1034] 1. A means to optimize the generated personalized content based on individual conditions and preferences.

[1035] 2. Means for delivering said content to a display device within the vehicle.

[1036] 3. A means of collecting behavioral and emotional data and generating new content.

[1037] 4. Means for providing content based on said emotion data.

[1038] 5. A means of providing a dashboard that visually displays the passenger's condition and emotional state.

[1039] The server analyzes behavioral and emotional data collected using cameras and microphones, generates new content using generative AI models, and delivers optimized content based on passenger preferences and their current emotional state.

[1040] Terminal (display device inside the vehicle)

[1041] The terminal does the following:

[1042] 1. Receive and display or play content delivered from the server.

[1043] 2. Passengers' facial expressions and tone of voice are captured through cameras and microphones and analyzed using an emotion engine (e.g., Affectiva SDK).

[1044] 3. The analysis results are sent to the server in real time and dynamic content adjustments are made.

[1045] User (passenger)

[1046] The user does the following:

[1047] 1. View content provided through a display device in the vehicle.

[1048] 2. Providing emotional data such as facial expressions and tone of voice.

[1049] Hardware and software used

[1050] Camera: Used to monitor passengers' facial expressions.

[1051] Microphone: Used to analyze passengers' voice tones.

[1052] Emotion engine (e.g., Affectiva SDK): assesses the passenger's emotional state.

[1053] Generative AI models (e.g., OpenAI GPT-4): Generate personalized content.

[1054] Data analysis server: Analyzes behavioral and emotional data to optimize content.

[1055] Specific examples

[1056] For example, if a passenger feels like relaxing on a rainy day, the system collects emotional data in real time and sends a prompt to the generative AI model, such as:

[1057] "A passenger wants to relax on a rainy day. Their tastes are classical music and jazz. Generate a music playlist that is perfect for this situation."

[1058] Based on this prompt, the generative AI model will generate an optimal music playlist, which the server will then distribute to the display devices inside the vehicle, allowing passengers to enjoy relaxing music and a comfortable riding experience.

[1059] As described above, this system provides content that is dynamically optimized according to the individual state and emotional state of each passenger, ensuring a comfortable riding experience.

[1060] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1061] Step 1:

[1062] The server uses a camera and microphone to capture the facial expressions and tone of voice of passengers in the vehicle. This data is analyzed by an emotion engine (e.g., Affectiva SDK) to evaluate the passenger's current emotional state. The input is camera video and audio data, and the output is the passenger's emotional state (e.g., relaxed, anxious, etc.). Specifically, the facial expression analysis module and audio analysis module process the data in real time to determine the emotional state.

[1063] Step 2:

[1064] The server collects passengers' past behavioral data (riding history, music and video play history) and analyzed emotional data, and sends it to the data analysis server. The input is data collected from the camera and microphone and past behavioral history, and the output is log information for data analysis. Specifically, the server retrieves passenger history data from the database and integrates it with emotional data.

[1065] Step 3:

[1066] The data analysis server sends prompts to the generative AI model based on the passenger's preferences and current emotional state. For example, it generates a prompt like, "A passenger on a rainy day feels like relaxing. Their hobbies are classical music and jazz. Please generate a music playlist that is best suited to this situation." The input is emotional data and passenger preference data, and the output is a prompt. Specifically, the prompt generation module receives the data and creates an appropriate prompt.

[1067] Step 4:

[1068] The generative AI model generates optimal personalized content based on the received prompt. The input is the prompt, and the output is personalized content (e.g., music playlist, video list). Specifically, the generative AI model performs natural language processing and creates content based on the prompt.

[1069] Step 5:

[1070] The server distributes the generated personalized content to the display device in the vehicle. The input is the content from the generative AI model, and the output is the content data to the display device. Specifically, the content distribution module receives the data and sends it to the specified device.

[1071] Step 6:

[1072] The terminal (display device inside the vehicle) displays or plays the distributed content. The input is content data from the server, and the output is the video or music that passengers watch. Specifically, the playback module receives the content data and displays or plays it on the screen or speaker.

[1073] Step 7:

[1074] The device again collects the passenger's emotional data through the camera and microphone and transmits it to the server in real time. The input is new camera video and audio data, and the output is updated emotional state data. Specifically, the emotion monitoring module continues to analyze the data and send it back to the server.

[1075] 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.

[1076] 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.

[1077] 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.

[1078] [Third embodiment]

[1079] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1080] 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.

[1081] 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).

[1082] 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.

[1083] 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.

[1084] 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).

[1085] 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. 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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."

[1091] This invention is a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their terminals. Below, we will show a specific embodiment of the entire system and explain the program processing in natural language.

[1092] Server Processing

[1093] 1. Data Collection and Analysis

[1094] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[1095] The collected data is analyzed to evaluate students' learning progress, level of understanding, areas of weakness, current physical condition, etc.

[1096] 2. Generating learning content

[1097] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model learns the teacher's speech patterns and explanation methods, and reproduces the lesson style that attracts students' attention.

[1098] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1099] 3. Optimize your study plan

[1100] The server uses health data to optimize a student's study schedule, for example by concentrating study time in the morning after a student has had enough sleep.

[1101] 4. Content Delivery

[1102] The server delivers the generated learning content and optimized learning plans to students' devices.

[1103] 5. Providing a dashboard

[1104] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[1105] Handling terminals (student devices)

[1106] 1. Receiving and viewing learning content

[1107] Students' devices receive video lesson content and practice questions delivered from the server.

[1108] The received content is presented in an appropriate format to engage students in their learning.

[1109] 2. Submit your learning outcomes

[1110] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1111] 3. Health Data Collection

[1112] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[1113] User (homeroom teacher) processing

[1114] 1. Check the dashboard

[1115] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[1116] Use the dashboard to plan appropriate instruction and advice for students.

[1117] Specific examples

[1118] Server example

[1119] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[1120] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[1121] Specific examples of terminals (student devices)

[1122] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[1123] Student A's device completes the practice questions and sends the results data to the server.

[1124] Example of a user (homeroom teacher)

[1125] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[1126] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[1127] In this way, the present invention is a system that provides learning content optimized for each student, reduces the burden on teachers, and realizes effective learning.

[1128] The processing flow will be explained below.

[1129] Step 1:

[1130] Data collection: The server retrieves students' past learning data (e.g., test results, submitted assignments, and learning history) from the database. It also receives students' health data (e.g., heart rate, sleep duration, and activity level) from the wearable device.

[1131] Step 2:

[1132] Data analysis: The server analyzes the acquired data, evaluates each student's level of understanding, and identifies weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm.

[1133] Step 3:

[1134] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[1135] Step 4:

[1136] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[1137] Step 5:

[1138] Optimizing learning plans: The server takes into account students' health data and generates the most efficient learning schedule. For example, it will reduce the learning load for students who are not getting enough sleep.

[1139] Step 6:

[1140] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1141] Step 7:

[1142] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[1143] Step 8:

[1144] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[1145] Step 9:

[1146] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[1147] Step 10:

[1148] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[1149] Step 11:

[1150] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, visually displaying each student's learning progress, level of understanding, areas of weakness, etc.

[1151] Step 12:

[1152] Checking the dashboard: The user (homeroom teacher) checks the dashboard to understand the student's learning status, considers necessary measures, and plans additional instruction and support.

[1153] Step 13:

[1154] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[1155] By repeating the above steps, it is possible to provide individually optimized and continuous learning support.

[1156] Example 1

[1157] 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."

[1158] Conventional learning systems have difficulty optimizing learning content that comprehensively reflects individual data such as each student's learning progress, level of understanding, and physical condition, and as a result, have not been able to provide sufficient, effective learning support. Furthermore, it places a heavy burden on teachers to grasp students' learning progress and level of understanding and provide individual support. Therefore, there was a need for a system that provides learning support optimized for each student's learning needs and reduces the burden on teachers.

[1159] 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.

[1160] In this invention, the server includes a means for collecting, analyzing, and evaluating students' learning data and health data, a means for generating learning content based on the students' learning progress and level of understanding using a generative AI model, and a means for delivering the generated learning content and optimized learning plans to the students' devices, thereby enabling the provision of learning content optimized based on the students' individual learning progress, level of understanding, and physical condition.

[1161] "Student learning data" refers to information related to a student's learning activities, such as test results, submitted assignments, and learning history.

[1162] "Health data" refers to information about a student's physical condition, such as heart rate, sleep duration, and activity level.

[1163] A "generative AI model" is an artificial intelligence model that generates learning content according to a student's learning progress and level of understanding.

[1164] "Learning content" refers to educational materials such as generated video lessons and exercises.

[1165] A "device" is a device used by a student to view learning content and perform learning activities.

[1166] "Learning outcome data" refers to data such as the percentage of correct answers and the time it took to answer a question obtained after a student has completed a learning task.

[1167] A "wearable device" is a device worn by students that measures and records health data such as heart rate and activity levels.

[1168] The "dashboard" is an interface that allows homeroom teachers to visually check students' learning progress, level of understanding, and health status.

[1169] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[1170] This invention is a system that provides learning content optimized for each student based on their learning progress, level of understanding, and physical condition. The system consists of three main components: a server, a terminal (student device), and a user (homeroom teacher).

[1171] Server Features

[1172] The server has the following functions:

[1173] 1. Data Collection and Analysis

[1174] The server collects students' learning data (e.g., test results, submitted assignments, learning history, etc.) and health data (e.g., heart rate, sleep time, activity level, etc.).

[1175] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and current physical condition.

[1176] 2. Generating learning content

[1177] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model has learned the teacher's speech patterns and explanation methods.

[1178] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1179] 3. Optimize your study plan

[1180] The server uses health data to optimize a student's study plan, for example by concentrating study time in the morning after a student has had enough sleep.

[1181] 4. Content Delivery

[1182] The server delivers the generated learning content and optimized learning plans to students' devices.

[1183] 5. Providing a dashboard

[1184] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[1185] Device (student device) capabilities

[1186] Student devices have the following features:

[1187] 1. Receiving and viewing learning content

[1188] Students' devices receive video lesson content and practice questions delivered from the server.

[1189] The received content is presented in an appropriate format to engage students in their learning.

[1190] 2. Submit your learning outcomes

[1191] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1192] 3. Health Data Collection

[1193] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[1194] User (homeroom teacher) functions

[1195] The user (homeroom teacher) uses the following functions.

[1196] 1. Check the dashboard

[1197] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[1198] 2. Lesson planning

[1199] Use the dashboard to plan appropriate instruction and advice for students.

[1200] Specific examples

[1201] Server example

[1202] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[1203] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[1204] Specific examples of terminals (student devices)

[1205] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[1206] Student A's device completes the practice questions and sends the results data to the server.

[1207] Example of a user (homeroom teacher)

[1208] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[1209] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[1210] Prompt Sentence Examples

[1211] "Student A's test results show that he is not good at fraction calculations. Please create a video explaining fraction calculations for this student in a style similar to that of a cram school teacher."

[1212] "Based on Student B's health data from the previous day, he or she has had enough sleep. Please create a study plan for the next morning that will allow this student to concentrate well."

[1213] This invention is a system that provides learning content optimized for each student and realizes effective learning. This system can maximize the learning effect of students while reducing the burden on teachers.

[1214] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1215] Step 1: Data collection

[1216] Specific behavior:

[1217] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[1218] input:

[1219] Data collected from student devices and wearable devices.

[1220] Data processing:

[1221] Information from various data sources is integrated and stored in a centralized database.

[1222] output:

[1223] Integrated training and health data sets.

[1224] Step 2: Data analysis

[1225] Specific behavior:

[1226] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and physical condition.

[1227] input:

[1228] Integrated learning and health data.

[1229] Data processing:

[1230] Machine learning algorithms are used to analyze each student's level of understanding and progress.

[1231] Generate visual representations such as graphs and heat maps based on numerical data.

[1232] output:

[1233] Reports on each student's learning progress, level of understanding, weak areas, and physical condition evaluation.

[1234] Step 3: Generate learning content

[1235] Specific behavior:

[1236] The server uses a generative AI model to generate video lesson content and practice questions that correspond to the student's level of understanding and progress.

[1237] input:

[1238] Report on learning progress and comprehension, weak areas, and physical condition evaluation.

[1239] Data processing:

[1240] Generate prompt sentences and input them into a generative AI model.

[1241] A generative AI model generates lesson content based on these prompts.

[1242] output:

[1243] Personalized video lesson content and practice questions.

[1244] Step 4: Optimize your study plan

[1245] Specific behavior:

[1246] The server adjusts and optimizes students' learning plans based on health data.

[1247] input:

[1248] Health data, generated learning content.

[1249] Data processing:

[1250] Analyze health data and calculate the optimal study time and study load.

[1251] Adjust your study plan and generate a new timetable.

[1252] output:

[1253] Optimized study plans.

[1254] Step 5: Deliver your content

[1255] Specific behavior:

[1256] The server delivers the generated learning content and optimized learning plans to students' devices.

[1257] input:

[1258] Learning content, optimized study plans.

[1259] Data processing:

[1260] Converting content and lesson plans into a format that can be received by student devices.

[1261] output:

[1262] Learning content and plans sent to student devices.

[1263] Step 6: Collect learning outcomes

[1264] Specific behavior:

[1265] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1266] input:

[1267] Learning outcome data sent from student devices.

[1268] Data processing:

[1269] Analyzes incoming data and updates student progress reports.

[1270] output:

[1271] Updated learning outcomes data repository.

[1272] Step 7: Refresh the dashboard

[1273] Specific behavior:

[1274] The server updates and provides a dashboard that visually displays learning data for the homeroom teacher.

[1275] input:

[1276] Updated learning outcomes data.

[1277] Data processing:

[1278] Converting the training data into a graphical format for display on a dashboard.

[1279] output:

[1280] Latest dashboard display for homeroom teachers.

[1281] Step 8: Lesson Planning

[1282] Specific behavior:

[1283] The user (homeroom teacher) uses the dashboard to plan appropriate instruction and advice for students.

[1284] input:

[1285] Training data displayed on the dashboard.

[1286] Data processing:

[1287] Identify the necessary instructional content based on learning data.

[1288] output:

[1289] A customized lesson plan for each student.

[1290] (Application example 1)

[1291] 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."

[1292] Conventional learning support systems have had problems in that they are difficult to fully respond to each student's learning progress and level of understanding, and are unable to provide individualized support that takes into account the student's physical condition and lifestyle. It is also difficult for teachers to grasp students' learning outcomes in real time, making effective instruction difficult. Another issue is that it is difficult for the generated learning content to sustain students' interest. The goal of this system is to solve these problems and provide a learning experience that is optimized for each student.

[1293] 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.

[1294] In this invention, the server includes: means for optimizing the generated learning content based on each student's individual learning progress and level of comprehension; means for distributing the learning content to a device that displays the learning content; means for displaying the learning content; means for collecting learning outcomes from the device; means for analyzing the learning outcomes and generating new learning content; means for collecting health data and optimizing learning plans; means for providing learning content based on the health data; means for providing a dashboard that visually displays learning progress and level of comprehension for teachers; means for being installed on a smartphone as a learning support application; means for acquiring health data from a wearable device and transmitting it to the server; and means for generating video lesson content based on prompts using a generative AI model and providing it according to each student's level of comprehension. This enables the provision of optimized learning content that takes into account each student's learning progress, level of comprehension, and health data. Furthermore, teachers can grasp each student's learning status in real time through the dashboard and provide effective instruction. Furthermore, video lesson content generated based on prompts is more likely to attract students' interest and promote their motivation to learn.

[1295] "Learning content" refers to educational data such as learning materials and exercises that are optimized based on a student's learning progress and level of understanding.

[1296] A "terminal" is an information processing device that displays learning content and is used by students for learning, such as a smartphone or tablet.

[1297] "Learning outcomes" refers to the results data when students complete learning tasks or practice problems, including the percentage of correct answers and the time it takes to complete them.

[1298] "Health data" refers to data that represents a student's physical condition, including their heart rate, sleep time, and activity level.

[1299] "Optimization" means adjusting learning content and plans to be most effective based on each student's learning progress and health condition.

[1300] A "dashboard" is an information display interface that allows teachers to visually check students' learning progress, level of understanding, and physical condition.

[1301] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate learning content and video lessons based on prompt sentences.

[1302] A "prompt sentence" is an instruction sentence that a generative AI model uses to generate learning content, and contains information about the specific content and structure.

[1303] A "wearable device" is a device worn by students to constantly measure and collect health data such as heart rate and activity levels.

[1304] The "server" is a computer system that collects and analyzes learning data and health data and manages the generated learning content.

[1305] A "smartphone" is an information terminal on which learning support applications can be installed and used.

[1306] This invention is a system that provides optimized learning content taking into consideration the learning progress, level of understanding, and health condition of each student. A system that realizes this application example will be described in detail below.

[1307] Server Processing

[1308] The server processes and calculates data using the following hardware and software:

[1309] Hardware: High-performance computer systems (e.g., AWS EC2 instances)

[1310] Software: Generative AI models, database management systems (e.g., MySQL), data analysis tools (e.g., Python libraries)

[1311] Data collection and analysis

[1312] The server first collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). Health data is acquired using wearable devices (e.g., Fitbit, Apple Watch) and sent to the server. The collected data is stored in a database and analyzed using a Python library.

[1313] Generating learning content

[1314] Based on the analyzed learning data, a generative AI model is used to generate video lesson content and practice problems. Lesson content that will attract students' interest is generated based on a prompt. An example of this prompt would be, "Generate video lesson content on 'Calculating Fractions' from Student A's learning data. Please include the following content: 1. An explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations."

[1315] Optimize your study plan

[1316] The server optimizes learning plans based on the student's health data. For example, if the student has had enough sleep the night before, it will adjust the schedule to focus on studying the following morning, ensuring effective learning.

[1317] Content Delivery

[1318] The generated learning content and optimized learning plans are delivered to students' devices (smartphones) in real time via the Internet.

[1319] Providing a dashboard

[1320] The server provides teachers with a dashboard that visually displays students' learning progress, level of understanding, and physical condition, allowing them to grasp students' learning status in real time and provide appropriate guidance.

[1321] Handling terminals (student devices)

[1322] Receive and view learning content

[1323] The student's device receives the video lesson content and exercises delivered from the server. The received content is displayed in an appropriate format through the learning support application, and the student uses the content to study.

[1324] Submitting learning outcomes

[1325] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is automatically sent to the server, allowing the server to continuously monitor the student's learning progress and level of understanding.

[1326] User (homeroom teacher) processing

[1327] Check the dashboard

[1328] Homeroom teachers can use the dashboard provided by the server to visually check students' learning progress, level of understanding, and physical condition, which allows them to plan and implement appropriate guidance and advice.

[1329] Collaboration between servers, devices, and users

[1330] This system provides an individually optimized learning experience by comprehensively managing and optimizing each student's learning progress, level of understanding, and health status. Its unique feature is its ability to provide highly personalized learning content in real time by using a generative AI model. This is expected to improve students' learning efficiency and enhance teachers' teaching effectiveness.

[1331] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1332] Step 1:

[1333] The server collects students' learning data and health data. Learning data includes test results, submitted assignments, and learning history, while health data includes heart rate, sleep time, and activity level. Input data is obtained from students' wearable devices and the learning progress system. These data are stored in a database for the next analysis step.

[1334] Step 2:

[1335] The server analyzes the collected learning data and health data. The learning data and health data collected in step 1 are used as input data. Python libraries are used to analyze and evaluate the data, extracting and evaluating the student's learning progress, level of understanding, areas of weakness, physical condition, etc. The analysis results are used to generate learning content in the next step.

[1336] Step 3:

[1337] The server uses a generative AI model to generate video lesson content and practice problems based on the analysis data. A prompt sentence is entered based on the generated learning data, and the generative AI model generates optimized lesson content. An example of a specific prompt sentence is, "Please generate video lesson content on 'fraction calculations' from Student A's learning data. Please include the following content: 1. Explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations." The generated content is stored in a database and prepared for the next distribution step.

[1338] Step 4:

[1339] The server distributes the generated learning content and optimized learning plans to the student's device (smartphone). The content and learning plans generated in step 3 are used as input data. Distribution is performed in real time via the Internet, and the content arrives at the student's device.

[1340] Step 5:

[1341] The device receives the distributed learning content and displays it in an appropriate format. It receives the learning content and study plan distributed from the server as input data. Students watch video lessons and work on practice problems. The device displays the content through a learning support application to support students' learning.

[1342] Step 6:

[1343] The terminal transmits the student's learning results to the server. As input data, it collects performance data (correct answer rate, answer time, etc.) for the learning tasks the student has completed. The terminal transmits this performance data to the server via the Internet, and the server stores it in a database.

[1344] Step 7:

[1345] The server provides teachers with a dashboard that visually displays learning progress, comprehension, and physical condition. The learning outcome data collected in Step 6 and past learning data are used as input data. The dashboard is designed to enable teachers to grasp students' learning status in real time. Teachers can use the dashboard to plan and implement appropriate instruction and advice.

[1346] Step 8:

[1347] The user uses the dashboard provided by the server to visually check the student's learning progress, level of understanding, and physical condition. The dashboard display data from the server is used as input data. Based on this, the user (teacher) can provide feedback to the student and create individual teaching plans to provide effective learning support.

[1348] Through the above steps, the system of the present invention comprehensively manages the learning progress, level of understanding, and health condition of each student, thereby realizing effective learning support.

[1349] 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.

[1350] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and delivers it to their device. The purpose is to maximize learning effectiveness by recognizing the user's emotions during learning and dynamically adjusting the learning content in real time. Below, we will show a specific embodiment of the entire system and explain the program's processing in natural language.

[1351] Server Processing

[1352] 1. Data Collection and Analysis

[1353] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[1354] The collected data is analyzed to assess students' learning progress, level of understanding, areas of weakness, current physical condition, emotional state, etc.

[1355] 2. Generating learning content

[1356] The server uses a generative AI model to generate video lesson content that mimics the way a cram school teacher conducts a lesson. This AI model adopts a lesson format that is likely to attract students' attention.

[1357] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1358] 3. Optimize your study plan

[1359] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[1360] 4. Content Delivery

[1361] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1362] 5. Providing a dashboard

[1363] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[1364] Handling terminals (student devices)

[1365] 1. Receiving and viewing learning content

[1366] Students' devices receive video lesson content and practice questions delivered from the server.

[1367] The received content is presented in an appropriate format to engage students in their learning.

[1368] 2. Monitoring emotions during learning

[1369] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[1370] 3. Submit your learning outcomes

[1371] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1372] User (homeroom teacher) processing

[1373] 1. Check the dashboard

[1374] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[1375] Use the dashboard to plan appropriate instruction and advice for students.

[1376] Specific examples

[1377] Server example

[1378] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[1379] The server analyzes Student A's health and emotional data, determines that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his study plan to reduce his learning load.

[1380] Specific examples of terminals (student devices)

[1381] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[1382] The device monitors Student A's facial expressions while he is studying using a camera, and if the emotion engine determines that he is feeling stressed, it sends the data to the server in real time.

[1383] Student A completes the practice questions and sends the results data to the server.

[1384] Example of a user (homeroom teacher)

[1385] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations" and is feeling stressed while studying.

[1386] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding. The teacher will also explore the reasons why the student felt stressed and provide appropriate feedback.

[1387] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[1388] The processing flow will be explained below.

[1389] Step 1:

[1390] Data collection: The server retrieves students' learning data (test results, submitted assignments, learning history, etc.) from the database. It also receives students' health data (heart rate, sleep time, activity level, etc.) from the wearable device. Furthermore, the emotion engine collects students' emotional data (facial expressions, tone of voice, etc.) via the device's camera and microphone.

[1391] Step 2:

[1392] Data analysis: The server analyzes the acquired data to evaluate each student's level of understanding, learning progress, and weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm. It also analyzes emotional data in real time to determine the student's current emotional state (joy, excitement, anxiety, stress, etc.).

[1393] Step 3:

[1394] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[1395] Step 4:

[1396] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[1397] Step 5:

[1398] Optimization of study plans: The server generates optimal study plans based on health and emotional data. For example, if fatigue or stress levels are high, the server will adjust the study plan by reducing the study load and adding relaxing content.

[1399] Step 6:

[1400] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1401] Step 7:

[1402] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[1403] Step 8:

[1404] Emotion monitoring during learning: The device uses a camera and microphone to analyze students' facial expressions and tone of voice with an emotion engine, and sends emotional data to the server in real time. If the emotion exceeds a certain threshold, a notification is sent.

[1405] Step 9:

[1406] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[1407] Step 10:

[1408] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[1409] Step 11:

[1410] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[1411] Step 12:

[1412] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, which visually displays each student's learning progress, level of understanding, weak areas, physical condition, and emotional state.

[1413] Step 13:

[1414] Checking the dashboard: The user (teacher) checks the dashboard to understand the student's learning situation and emotional state, consider necessary measures, and plan additional instruction and support.

[1415] Step 14:

[1416] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[1417] By repeating these steps, we will create a system that supports individually optimized learning for students and maximizes learning effectiveness by utilizing real-time feedback from the emotion engine.

[1418] Example 2

[1419] 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."

[1420] Conventional learning management systems have difficulty providing optimal learning content that takes into account each learner's progress and level of understanding, and are unable to reflect the learner's emotional state in real time, resulting in problems such as reduced learning efficiency and decreased learner motivation.

[1421] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for optimizing the generated learning content based on each learner's individual learning progress and level of comprehension, means for distributing the learning content to a terminal that displays the learning content, means for displaying the learning content, means for collecting learning outcomes from the terminal, means for analyzing the learning outcomes and generating new learning content, means for collecting health data and optimizing a learning plan, means for providing learning content based on the health data, means for analyzing emotional data collected in real time and dynamically adjusting the learning content, and means for providing a dashboard that visually displays the learning progress and level of comprehension for teachers. This enables the provision of learning content optimized for each learner and a dynamic learning experience that reflects emotional states in real time.

[1422] "Generated learning content" refers to educational materials and exercises generated using digital tools and artificial intelligence.

[1423] "Individual learning progress" refers to the current learning progress of each learner, and indicates the extent to which they have understood and acquired the material.

[1424] "Comprehension" is an indicator that measures how accurately a learner understands a specific learning content.

[1425] "Devices" refer to digital devices used by learners, such as computers, tablets, and smartphones.

[1426] "Learning outcomes" refers to the grades and performance data that learners obtain as a result of completing assignments and tests.

[1427] "Health data" refers to data that indicates a learner's physical condition, such as heart rate, sleep time, and activity level.

[1428] "Emotional data" refers to data that indicates the emotional state of a learner, as obtained from facial expressions, tone of voice, etc.

[1429] A "dashboard" is a user interface that visually displays learning progress, comprehension, emotional state, etc.

[1430] A "generative AI model" is a model for creating new content using artificial intelligence.

[1431] A "prompt" is a sentence of instructions or questions that is input into a generative AI model.

[1432] "Dynamic adjustment" means changing content and settings as needed in response to changing real-time conditions.

[1433] These definitions clarify the meaning of key terms contained in the following claims.

[1434] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their devices. A specific embodiment of this entire system is shown below.

[1435] Server Processing

[1436] The server uses the following hardware and software:

[1437] Hardware: A server machine equipped with a high-performance processor

[1438] Software: Database management systems (e.g., MySQL), generative AI models (e.g., GPT-4), emotion engines (e.g., Emotion API), data analysis libraries (e.g., scikit-learn)

[1439] 1. Data Collection and Analysis

[1440] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[1441] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, weak areas, current physical condition, emotional state, etc. The analysis is carried out using machine learning models and statistical methods.

[1442] 2. Generating learning content

[1443] The server uses a generative AI model (e.g., GPT-4) to generate video lesson content that mimics the teacher's teaching style. This AI model adopts a lesson format that is likely to attract students' attention.

[1444] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1445] An example prompt is, "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[1446] 3. Optimize your study plan

[1447] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[1448] 4. Content Delivery

[1449] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1450] 5. Providing a dashboard

[1451] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[1452] Handling terminals (student devices)

[1453] The terminal uses the following hardware and software:

[1454] Hardware: Learners' computers, tablets, smartphones, etc.

[1455] Software: Video playback software, emotion analysis software (e.g., OpenCV)

[1456] 1. Receiving and viewing learning content

[1457] The terminal receives video lesson content and practice questions delivered from the server.

[1458] The device displays the received content in the appropriate format, allowing students to engage in their studies.

[1459] 2. Monitoring emotions during learning

[1460] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[1461] 3. Submit your learning outcomes

[1462] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1463] User (homeroom teacher) processing

[1464] 1. Check the dashboard

[1465] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[1466] Use the dashboard to plan appropriate instruction and advice for students.

[1467] As a specific example, the server identifies Student A's weak areas in "fraction calculations" based on his past learning data and current learning progress, and generates video lesson content specialized for that area. It also analyzes Student A's health and emotional data, confirms that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his learning plan to reduce his learning load.

[1468] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[1469] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1470] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[1471] Server Processing

[1472] Step 1: Data collection and analysis preparation

[1473] Input: Student learning data, health data, and emotion data

[1474] What happens: The server initializes the database and API connections.

[1475] Output: Database connection object, API connection object

[1476] Step 2: Collect training data

[1477] Input: Student ID

[1478] What it does: The server sends an SQL query to retrieve the learning data corresponding to the student ID from the database.

[1479] Output: Student learning dataset (test results, assignment submissions, learning history, etc.)

[1480] Example: "SELECT FROM training_data WHERE student_id = 'A123'"

[1481] Step 3: Collect health data

[1482] Input: API request

[1483] How it works: The server retrieves health data from the wearable device via an API request.

[1484] Output: Student health dataset (heart rate, sleep time, activity level, etc.)

[1485] Example: "GET / api / healthdata?student_id=A123"

[1486] Step 4: Collecting sentiment data

[1487] Input: Real-time data from the device

[1488] How it works: The server receives student emotion data using WebSocket or HTTP POST requests.

[1489] Output: Student emotion dataset (happiness, interest, anxiety, etc.)

[1490] Step 5: Analyze the data

[1491] Input: Training dataset, Health dataset, Emotion dataset

[1492] How it works: The server analyzes the data using machine learning models (e.g., scikit-learn) to assess the student's learning progress, comprehension, weak areas, physical condition, and emotional state.

[1493] Output: Analysis results (learning progress, level of understanding, weak areas, etc.)

[1494] Step 6: Prepare to generate learning content

[1495] Input: Analysis results

[1496] What it does: The server initializes a generative AI model (e.g., GPT-4) and generates a prompt.

[1497] Output: prompt statement

[1498] Example: "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[1499] Step 7: Generate learning content

[1500] Input: prompt statement

[1501] Operation: The server inputs prompt sentences into the generative AI model and generates video lesson content.

[1502] Output: Video lesson content

[1503] Step 8: Optimize your study plan

[1504] Input: Health data, emotion data

[1505] How it works: The server generates the most efficient learning schedule based on health and emotional data.

[1506] Output: Optimized learning plan

[1507] Example: Reducing study load and adjusting sleep schedule

[1508] Step 9: Deliver your content

[1509] Input: Video lesson content, optimized learning plans

[1510] How it works: The server sends this data to the student's device.

[1511] Output: Data delivered to student devices

[1512] Step 10: Update the dashboard

[1513] Input: Analysis results, emotion data

[1514] What it does: The server then displays this data in a dashboard for teachers.

[1515] Output: Updated dashboard

[1516] Handling terminals (student devices)

[1517] Step 1: Receiving content

[1518] Input: Data delivered from the server

[1519] Operation: The device receives the video lesson content and exercises from the server.

[1520] Output: Received learning content, exercises

[1521] Step 2: Viewing content

[1522] Input: Received learning content

[1523] What happens: The device displays the received content in the appropriate format, and the student engages with their learning.

[1524] Output: Displayed learning content

[1525] Step 3: Monitoring sentiment data

[1526] Input: Real-time facial and voice data from camera and microphone

[1527] How it works: The device uses a camera and microphone to analyze students' facial expressions and tone of voice using an emotion engine.

[1528] Output: Parsed emotion data

[1529] Step 4: Sending emotion data

[1530] Input: Parsed emotion data

[1531] How it works: The device sends emotion data to the server in real time.

[1532] Output: Emotion data sent to the server

[1533] Step 5: Record and submit your learning outcomes

[1534] Input: Study task performance data (correct answer rate, answer time, etc.)

[1535] How it works: When a student completes a learning task, the performance data is recorded and sent to the server.

[1536] Output: Learning outcome data sent to the server

[1537] User (homeroom teacher) processing

[1538] Step 1: Check the dashboard

[1539] Input: Updated dashboard

[1540] How it works: The teacher accesses the dashboard from a web browser and checks the data.

[1541] Output: Confirmed learning progress, comprehension, and emotional state

[1542] Step 2: Plan your lesson

[1543] Input: Dashboard data

[1544] How it works: The teacher uses the dashboard analysis results to plan instruction and feedback for the students.

[1545] Output: Planned lesson content

[1546] Through these specific processing steps, the present invention is a system that provides an optimized learning environment for each learner and realizes effective education.

[1547] (Application example 2)

[1548] 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."

[1549] Conventional in-car entertainment systems rely on static content delivery and are unable to respond quickly to changes in passengers' emotional state or preferences. This makes it difficult to improve passenger satisfaction and relaxation, and provides a comfortable riding experience.

[1550] 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 optimizing the generated personalized content based on individual conditions and preferences, means for delivering the content to a display device in the vehicle that displays the content, means for displaying the content, means for collecting behavioral data from the display device, means for analyzing the behavioral data and generating new content, means for collecting emotional data and optimizing the content to be provided, means for providing content based on the emotional data, and means for providing a dashboard that visually displays the conditions and emotional states in the vehicle. This enables dynamic content delivery that quickly responds to the emotional conditions and preferences of passengers.

[1551] "Generated personalized content" refers to entertainment and information that is optimized based on a passenger's individual circumstances and preferences.

[1552] "Individual conditions" refers to the different circumstances of each passenger, such as their physical condition, emotional state, and current environment.

[1553] "Preferences" refer to genres or types of content that a passenger is particularly interested in, such as music, movies, news, etc.

[1554] An "in-vehicle display device" is a device installed inside a vehicle for displaying or playing content, such as a screen, monitor, or speaker.

[1555] "Behavioral data" refers to data such as passenger operation history, viewing history, and physical reactions collected from display devices and sensors inside the vehicle.

[1556] "Emotional data" refers to data on passengers' emotional states that is determined from their facial expressions, tone of voice, heart rate, etc., collected using sensors such as cameras and microphones.

[1557] A "dashboard" is an interface that visually displays passenger status, emotional state, system operation status, etc.

[1558] This invention provides a personalized infotainment system that enhances the entertainment experience for passengers in autonomous vehicles. The system delivers content optimized based on each passenger's individual conditions and preferences, ensuring a comfortable and satisfying riding experience.

[1559] System configuration

[1560] server

[1561] The server includes the following means:

[1562] 1. A means to optimize the generated personalized content based on individual conditions and preferences.

[1563] 2. Means for delivering said content to a display device within the vehicle.

[1564] 3. A means of collecting behavioral and emotional data and generating new content.

[1565] 4. Means for providing content based on said emotion data.

[1566] 5. A means of providing a dashboard that visually displays the passenger's condition and emotional state.

[1567] The server analyzes behavioral and emotional data collected using cameras and microphones, generates new content using generative AI models, and delivers optimized content based on passenger preferences and their current emotional state.

[1568] Terminal (display device inside the vehicle)

[1569] The terminal does the following:

[1570] 1. Receive and display or play content delivered from the server.

[1571] 2. Passengers' facial expressions and tone of voice are captured through cameras and microphones and analyzed using an emotion engine (e.g., Affectiva SDK).

[1572] 3. The analysis results are sent to the server in real time and dynamic content adjustments are made.

[1573] User (passenger)

[1574] The user does the following:

[1575] 1. View content provided through a display device in the vehicle.

[1576] 2. Providing emotional data such as facial expressions and tone of voice.

[1577] Hardware and software used

[1578] Camera: Used to monitor passengers' facial expressions.

[1579] Microphone: Used to analyze passengers' voice tones.

[1580] Emotion engine (e.g., Affectiva SDK): assesses the passenger's emotional state.

[1581] Generative AI models (e.g., OpenAI GPT-4): Generate personalized content.

[1582] Data analysis server: Analyzes behavioral and emotional data to optimize content.

[1583] Specific examples

[1584] For example, if a passenger feels like relaxing on a rainy day, the system collects emotional data in real time and sends a prompt to the generative AI model, such as:

[1585] "A passenger wants to relax on a rainy day. Their tastes are classical music and jazz. Generate a music playlist that is perfect for this situation."

[1586] Based on this prompt, the generative AI model will generate an optimal music playlist, which the server will then distribute to the display devices inside the vehicle, allowing passengers to enjoy relaxing music and a comfortable riding experience.

[1587] As described above, this system provides content that is dynamically optimized according to the individual state and emotional state of each passenger, ensuring a comfortable riding experience.

[1588] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1589] Step 1:

[1590] The server uses a camera and microphone to capture the facial expressions and tone of voice of passengers in the vehicle. This data is analyzed by an emotion engine (e.g., Affectiva SDK) to evaluate the passenger's current emotional state. The input is camera video and audio data, and the output is the passenger's emotional state (e.g., relaxed, anxious, etc.). Specifically, the facial expression analysis module and audio analysis module process the data in real time to determine the emotional state.

[1591] Step 2:

[1592] The server collects passengers' past behavioral data (riding history, music and video play history) and analyzed emotional data, and sends it to the data analysis server. The input is data collected from the camera and microphone and past behavioral history, and the output is log information for data analysis. Specifically, the server retrieves passenger history data from the database and integrates it with emotional data.

[1593] Step 3:

[1594] The data analysis server sends prompts to the generative AI model based on the passenger's preferences and current emotional state. For example, it generates a prompt like, "A passenger on a rainy day feels like relaxing. Their hobbies are classical music and jazz. Please generate a music playlist that is best suited to this situation." The input is emotional data and passenger preference data, and the output is a prompt. Specifically, the prompt generation module receives the data and creates an appropriate prompt.

[1595] Step 4:

[1596] The generative AI model generates optimal personalized content based on the received prompt. The input is the prompt, and the output is personalized content (e.g., music playlist, video list). Specifically, the generative AI model performs natural language processing and creates content based on the prompt.

[1597] Step 5:

[1598] The server distributes the generated personalized content to the display device in the vehicle. The input is the content from the generative AI model, and the output is the content data to the display device. Specifically, the content distribution module receives the data and sends it to the specified device.

[1599] Step 6:

[1600] The terminal (display device inside the vehicle) displays or plays the distributed content. The input is content data from the server, and the output is the video or music that passengers watch. Specifically, the playback module receives the content data and displays or plays it on the screen or speaker.

[1601] Step 7:

[1602] The device again collects the passenger's emotional data through the camera and microphone and transmits it to the server in real time. The input is new camera video and audio data, and the output is updated emotional state data. Specifically, the emotion monitoring module continues to analyze the data and send it back to the server.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] [Fourth embodiment]

[1607] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1608] 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.

[1609] 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).

[1610] 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.

[1611] 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.

[1612] 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).

[1613] 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. 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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."

[1620] This invention is a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their terminals. Below, we will show a specific embodiment of the entire system and explain the program processing in natural language.

[1621] Server Processing

[1622] 1. Data Collection and Analysis

[1623] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[1624] The collected data is analyzed to evaluate students' learning progress, level of understanding, areas of weakness, current physical condition, etc.

[1625] 2. Generating learning content

[1626] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model learns the teacher's speech patterns and explanation methods, and reproduces the lesson style that attracts students' attention.

[1627] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1628] 3. Optimize your study plan

[1629] The server uses health data to optimize a student's study schedule, for example by concentrating study time in the morning after a student has had enough sleep.

[1630] 4. Content Delivery

[1631] The server delivers the generated learning content and optimized learning plans to students' devices.

[1632] 5. Providing a dashboard

[1633] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[1634] Handling terminals (student devices)

[1635] 1. Receiving and viewing learning content

[1636] Students' devices receive video lesson content and practice questions delivered from the server.

[1637] The received content is presented in an appropriate format to engage students in their learning.

[1638] 2. Submit your learning outcomes

[1639] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1640] 3. Health Data Collection

[1641] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[1642] User (homeroom teacher) processing

[1643] 1. Check the dashboard

[1644] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[1645] Use the dashboard to plan appropriate instruction and advice for students.

[1646] Specific examples

[1647] Server example

[1648] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[1649] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[1650] Specific examples of terminals (student devices)

[1651] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[1652] Student A's device completes the practice questions and sends the results data to the server.

[1653] Example of a user (homeroom teacher)

[1654] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[1655] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[1656] In this way, the present invention is a system that provides learning content optimized for each student, reduces the burden on teachers, and realizes effective learning.

[1657] The processing flow will be explained below.

[1658] Step 1:

[1659] Data collection: The server retrieves students' past learning data (e.g., test results, submitted assignments, and learning history) from the database. It also receives students' health data (e.g., heart rate, sleep duration, and activity level) from the wearable device.

[1660] Step 2:

[1661] Data analysis: The server analyzes the acquired data, evaluates each student's level of understanding, and identifies weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm.

[1662] Step 3:

[1663] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[1664] Step 4:

[1665] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[1666] Step 5:

[1667] Optimizing learning plans: The server takes into account students' health data and generates the most efficient learning schedule. For example, it will reduce the learning load for students who are not getting enough sleep.

[1668] Step 6:

[1669] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1670] Step 7:

[1671] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[1672] Step 8:

[1673] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[1674] Step 9:

[1675] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[1676] Step 10:

[1677] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[1678] Step 11:

[1679] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, visually displaying each student's learning progress, level of understanding, areas of weakness, etc.

[1680] Step 12:

[1681] Checking the dashboard: The user (homeroom teacher) checks the dashboard to understand the student's learning status, considers necessary measures, and plans additional instruction and support.

[1682] Step 13:

[1683] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[1684] By repeating the above steps, it is possible to provide individually optimized and continuous learning support.

[1685] Example 1

[1686] 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."

[1687] Conventional learning systems have difficulty optimizing learning content that comprehensively reflects individual data such as each student's learning progress, level of understanding, and physical condition, and as a result, have not been able to provide sufficient, effective learning support. Furthermore, it places a heavy burden on teachers to grasp students' learning progress and level of understanding and provide individual support. Therefore, there was a need for a system that provides learning support optimized for each student's learning needs and reduces the burden on teachers.

[1688] 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.

[1689] In this invention, the server includes a means for collecting, analyzing, and evaluating students' learning data and health data, a means for generating learning content based on the students' learning progress and level of understanding using a generative AI model, and a means for delivering the generated learning content and optimized learning plans to the students' devices, thereby enabling the provision of learning content optimized based on the students' individual learning progress, level of understanding, and physical condition.

[1690] "Student learning data" refers to information related to a student's learning activities, such as test results, submitted assignments, and learning history.

[1691] "Health data" refers to information about a student's physical condition, such as heart rate, sleep duration, and activity level.

[1692] A "generative AI model" is an artificial intelligence model that generates learning content according to a student's learning progress and level of understanding.

[1693] "Learning content" refers to educational materials such as generated video lessons and exercises.

[1694] A "device" is a device used by a student to view learning content and perform learning activities.

[1695] "Learning outcome data" refers to data such as the percentage of correct answers and the time it took to answer a question obtained after a student has completed a learning task.

[1696] A "wearable device" is a device worn by students that measures and records health data such as heart rate and activity levels.

[1697] The "dashboard" is an interface that allows homeroom teachers to visually check students' learning progress, level of understanding, and health status.

[1698] A "prompt sentence" is an input sentence that gives specific instructions to a generative AI model.

[1699] This invention is a system that provides learning content optimized for each student based on their learning progress, level of understanding, and physical condition. The system consists of three main components: a server, a terminal (student device), and a user (homeroom teacher).

[1700] Server Features

[1701] The server has the following functions:

[1702] 1. Data Collection and Analysis

[1703] The server collects students' learning data (e.g., test results, submitted assignments, learning history, etc.) and health data (e.g., heart rate, sleep time, activity level, etc.).

[1704] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and current physical condition.

[1705] 2. Generating learning content

[1706] The server uses a generative AI model to generate video lesson content that mimics the teacher's teaching style. This model has learned the teacher's speech patterns and explanation methods.

[1707] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1708] 3. Optimize your study plan

[1709] The server uses health data to optimize a student's study plan, for example by concentrating study time in the morning after a student has had enough sleep.

[1710] 4. Content Delivery

[1711] The server delivers the generated learning content and optimized learning plans to students' devices.

[1712] 5. Providing a dashboard

[1713] The server updates and provides a dashboard for homeroom teachers that visually displays learning data, including students' learning progress, level of understanding, areas of weakness, and physical condition.

[1714] Device (student device) capabilities

[1715] Student devices have the following features:

[1716] 1. Receiving and viewing learning content

[1717] Students' devices receive video lesson content and practice questions delivered from the server.

[1718] The received content is presented in an appropriate format to engage students in their learning.

[1719] 2. Submit your learning outcomes

[1720] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1721] 3. Health Data Collection

[1722] Students' wearable devices regularly measure and record health data such as heart rate, sleep time, and activity level, and send it to a server.

[1723] User (homeroom teacher) functions

[1724] The user (homeroom teacher) uses the following functions.

[1725] 1. Check the dashboard

[1726] Homeroom teachers can use the dashboard provided by the server to check students' learning progress, level of understanding, and physical condition.

[1727] 2. Lesson planning

[1728] Use the dashboard to plan appropriate instruction and advice for students.

[1729] Specific examples

[1730] Server example

[1731] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[1732] The server analyzes Student A's health data, confirms that he or she got enough sleep the previous night, and adjusts his or her study plan to focus on studying the next morning.

[1733] Specific examples of terminals (student devices)

[1734] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[1735] Student A's device completes the practice questions and sends the results data to the server.

[1736] Example of a user (homeroom teacher)

[1737] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations."

[1738] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding.

[1739] Prompt Sentence Examples

[1740] "Student A's test results show that he is not good at fraction calculations. Please create a video explaining fraction calculations for this student in a style similar to that of a cram school teacher."

[1741] "Based on Student B's health data from the previous day, he or she has had enough sleep. Please create a study plan for the next morning that will allow this student to concentrate well."

[1742] This invention is a system that provides learning content optimized for each student and realizes effective learning. This system can maximize the learning effect of students while reducing the burden on teachers.

[1743] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1744] Step 1: Data collection

[1745] Specific behavior:

[1746] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.).

[1747] input:

[1748] Data collected from student devices and wearable devices.

[1749] Data processing:

[1750] Information from various data sources is integrated and stored in a centralized database.

[1751] output:

[1752] Integrated training and health data sets.

[1753] Step 2: Data analysis

[1754] Specific behavior:

[1755] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, areas of weakness, and physical condition.

[1756] input:

[1757] Integrated learning and health data.

[1758] Data processing:

[1759] Machine learning algorithms are used to analyze each student's level of understanding and progress.

[1760] Generate visual representations such as graphs and heat maps based on numerical data.

[1761] output:

[1762] Reports on each student's learning progress, level of understanding, weak areas, and physical condition evaluation.

[1763] Step 3: Generate learning content

[1764] Specific behavior:

[1765] The server uses a generative AI model to generate video lesson content and practice questions that correspond to the student's level of understanding and progress.

[1766] input:

[1767] Report on learning progress and comprehension, weak areas, and physical condition evaluation.

[1768] Data processing:

[1769] Generate prompt sentences and input them into a generative AI model.

[1770] A generative AI model generates lesson content based on these prompts.

[1771] output:

[1772] Personalized video lesson content and practice questions.

[1773] Step 4: Optimize your study plan

[1774] Specific behavior:

[1775] The server adjusts and optimizes students' learning plans based on health data.

[1776] input:

[1777] Health data, generated learning content.

[1778] Data processing:

[1779] Analyze health data and calculate the optimal study time and study load.

[1780] Adjust your study plan and generate a new timetable.

[1781] output:

[1782] Optimized study plans.

[1783] Step 5: Deliver your content

[1784] Specific behavior:

[1785] The server delivers the generated learning content and optimized learning plans to students' devices.

[1786] input:

[1787] Learning content, optimized study plans.

[1788] Data processing:

[1789] Converting content and lesson plans into a format that can be received by student devices.

[1790] output:

[1791] Learning content and plans sent to student devices.

[1792] Step 6: Collect learning outcomes

[1793] Specific behavior:

[1794] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1795] input:

[1796] Learning outcome data sent from student devices.

[1797] Data processing:

[1798] Analyzes incoming data and updates student progress reports.

[1799] output:

[1800] Updated learning outcomes data repository.

[1801] Step 7: Refresh the dashboard

[1802] Specific behavior:

[1803] The server updates and provides a dashboard that visually displays learning data for the homeroom teacher.

[1804] input:

[1805] Updated learning outcomes data.

[1806] Data processing:

[1807] Converting the training data into a graphical format for display on a dashboard.

[1808] output:

[1809] Latest dashboard display for homeroom teachers.

[1810] Step 8: Lesson Planning

[1811] Specific behavior:

[1812] The user (homeroom teacher) uses the dashboard to plan appropriate instruction and advice for students.

[1813] input:

[1814] Training data displayed on the dashboard.

[1815] Data processing:

[1816] Identify the necessary instructional content based on learning data.

[1817] output:

[1818] A customized lesson plan for each student.

[1819] (Application example 1)

[1820] 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."

[1821] Conventional learning support systems have had problems in that they are difficult to fully respond to each student's learning progress and level of understanding, and are unable to provide individualized support that takes into account the student's physical condition and lifestyle. It is also difficult for teachers to grasp students' learning outcomes in real time, making effective instruction difficult. Another issue is that it is difficult for the generated learning content to sustain students' interest. The goal of this system is to solve these problems and provide a learning experience that is optimized for each student.

[1822] 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.

[1823] In this invention, the server includes: means for optimizing the generated learning content based on each student's individual learning progress and level of comprehension; means for distributing the learning content to a device that displays the learning content; means for displaying the learning content; means for collecting learning outcomes from the device; means for analyzing the learning outcomes and generating new learning content; means for collecting health data and optimizing learning plans; means for providing learning content based on the health data; means for providing a dashboard that visually displays learning progress and level of comprehension for teachers; means for being installed on a smartphone as a learning support application; means for acquiring health data from a wearable device and transmitting it to the server; and means for generating video lesson content based on prompts using a generative AI model and providing it according to each student's level of comprehension. This enables the provision of optimized learning content that takes into account each student's learning progress, level of comprehension, and health data. Furthermore, teachers can grasp each student's learning status in real time through the dashboard and provide effective instruction. Furthermore, video lesson content generated based on prompts is more likely to attract students' interest and promote their motivation to learn.

[1824] "Learning content" refers to educational data such as learning materials and exercises that are optimized based on a student's learning progress and level of understanding.

[1825] A "terminal" is an information processing device that displays learning content and is used by students for learning, such as a smartphone or tablet.

[1826] "Learning outcomes" refers to the results data when students complete learning tasks or practice problems, including the percentage of correct answers and the time it takes to complete them.

[1827] "Health data" refers to data that represents a student's physical condition, including their heart rate, sleep time, and activity level.

[1828] "Optimization" means adjusting learning content and plans to be most effective based on each student's learning progress and health condition.

[1829] A "dashboard" is an information display interface that allows teachers to visually check students' learning progress, level of understanding, and physical condition.

[1830] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate learning content and video lessons based on prompt sentences.

[1831] A "prompt sentence" is an instruction sentence that a generative AI model uses to generate learning content, and contains information about the specific content and structure.

[1832] A "wearable device" is a device worn by students to constantly measure and collect health data such as heart rate and activity levels.

[1833] The "server" is a computer system that collects and analyzes learning data and health data and manages the generated learning content.

[1834] A "smartphone" is an information terminal on which learning support applications can be installed and used.

[1835] This invention is a system that provides optimized learning content taking into consideration the learning progress, level of understanding, and health condition of each student. A system that realizes this application example will be described in detail below.

[1836] Server Processing

[1837] The server processes and calculates data using the following hardware and software:

[1838] Hardware: High-performance computer systems (e.g., AWS EC2 instances)

[1839] Software: Generative AI models, database management systems (e.g., MySQL), data analysis tools (e.g., Python libraries)

[1840] Data collection and analysis

[1841] The server first collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). Health data is acquired using wearable devices (e.g., Fitbit, Apple Watch) and sent to the server. The collected data is stored in a database and analyzed using a Python library.

[1842] Generating learning content

[1843] Based on the analyzed learning data, a generative AI model is used to generate video lesson content and practice problems. Lesson content that will attract students' interest is generated based on a prompt. An example of this prompt would be, "Generate video lesson content on 'Calculating Fractions' from Student A's learning data. Please include the following content: 1. An explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations."

[1844] Optimize your study plan

[1845] The server optimizes learning plans based on the student's health data. For example, if the student has had enough sleep the night before, it will adjust the schedule to focus on studying the following morning, ensuring effective learning.

[1846] Content Delivery

[1847] The generated learning content and optimized learning plans are delivered to students' devices (smartphones) in real time via the Internet.

[1848] Providing a dashboard

[1849] The server provides teachers with a dashboard that visually displays students' learning progress, level of understanding, and physical condition, allowing them to grasp students' learning status in real time and provide appropriate guidance.

[1850] Handling terminals (student devices)

[1851] Receive and view learning content

[1852] The student's device receives the video lesson content and exercises delivered from the server. The received content is displayed in an appropriate format through the learning support application, and the student uses the content to study.

[1853] Submitting learning outcomes

[1854] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is automatically sent to the server, allowing the server to continuously monitor the student's learning progress and level of understanding.

[1855] User (homeroom teacher) processing

[1856] Check the dashboard

[1857] Homeroom teachers can use the dashboard provided by the server to visually check students' learning progress, level of understanding, and physical condition, which allows them to plan and implement appropriate guidance and advice.

[1858] Collaboration between servers, devices, and users

[1859] This system provides an individually optimized learning experience by comprehensively managing and optimizing each student's learning progress, level of understanding, and health status. Its unique feature is its ability to provide highly personalized learning content in real time by using a generative AI model. This is expected to improve students' learning efficiency and enhance teachers' teaching effectiveness.

[1860] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1861] Step 1:

[1862] The server collects students' learning data and health data. Learning data includes test results, submitted assignments, and learning history, while health data includes heart rate, sleep time, and activity level. Input data is obtained from students' wearable devices and the learning progress system. These data are stored in a database for the next analysis step.

[1863] Step 2:

[1864] The server analyzes the collected learning data and health data. The learning data and health data collected in step 1 are used as input data. Python libraries are used to analyze and evaluate the data, extracting and evaluating the student's learning progress, level of understanding, areas of weakness, physical condition, etc. The analysis results are used to generate learning content in the next step.

[1865] Step 3:

[1866] The server uses a generative AI model to generate video lesson content and practice problems based on the analysis data. A prompt sentence is entered based on the generated learning data, and the generative AI model generates optimized lesson content. An example of a specific prompt sentence is, "Please generate video lesson content on 'fraction calculations' from Student A's learning data. Please include the following content: 1. Explanation of the basic concept of fractions, 2. Addition and subtraction of fractions, 3. Practice problems and their explanations." The generated content is stored in a database and prepared for the next distribution step.

[1867] Step 4:

[1868] The server distributes the generated learning content and optimized learning plans to the student's device (smartphone). The content and learning plans generated in step 3 are used as input data. Distribution is performed in real time via the Internet, and the content arrives at the student's device.

[1869] Step 5:

[1870] The device receives the distributed learning content and displays it in an appropriate format. It receives the learning content and study plan distributed from the server as input data. Students watch video lessons and work on practice problems. The device displays the content through a learning support application to support students' learning.

[1871] Step 6:

[1872] The terminal transmits the student's learning results to the server. As input data, it collects performance data (correct answer rate, answer time, etc.) for the learning tasks the student has completed. The terminal transmits this performance data to the server via the Internet, and the server stores it in a database.

[1873] Step 7:

[1874] The server provides teachers with a dashboard that visually displays learning progress, comprehension, and physical condition. The learning outcome data collected in Step 6 and past learning data are used as input data. The dashboard is designed to enable teachers to grasp students' learning status in real time. Teachers can use the dashboard to plan and implement appropriate instruction and advice.

[1875] Step 8:

[1876] The user uses the dashboard provided by the server to visually check the student's learning progress, level of understanding, and physical condition. The dashboard display data from the server is used as input data. Based on this, the user (teacher) can provide feedback to the student and create individual teaching plans to provide effective learning support.

[1877] Through the above steps, the system of the present invention comprehensively manages the learning progress, level of understanding, and health condition of each student, thereby realizing effective learning support.

[1878] 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.

[1879] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and delivers it to their device. The purpose is to maximize learning effectiveness by recognizing the user's emotions during learning and dynamically adjusting the learning content in real time. Below, we will show a specific embodiment of the entire system and explain the program's processing in natural language.

[1880] Server Processing

[1881] 1. Data Collection and Analysis

[1882] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[1883] The collected data is analyzed to assess students' learning progress, level of understanding, areas of weakness, current physical condition, emotional state, etc.

[1884] 2. Generating learning content

[1885] The server uses a generative AI model to generate video lesson content that mimics the way a cram school teacher conducts a lesson. This AI model adopts a lesson format that is likely to attract students' attention.

[1886] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1887] 3. Optimize your study plan

[1888] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[1889] 4. Content Delivery

[1890] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1891] 5. Providing a dashboard

[1892] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[1893] Handling terminals (student devices)

[1894] 1. Receiving and viewing learning content

[1895] Students' devices receive video lesson content and practice questions delivered from the server.

[1896] The received content is presented in an appropriate format to engage students in their learning.

[1897] 2. Monitoring emotions during learning

[1898] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[1899] 3. Submit your learning outcomes

[1900] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1901] User (homeroom teacher) processing

[1902] 1. Check the dashboard

[1903] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[1904] Use the dashboard to plan appropriate instruction and advice for students.

[1905] Specific examples

[1906] Server example

[1907] Based on Student A's past learning data and current learning progress, the server identifies Student A's weak areas in "fraction calculation" and generates video lesson content specialized for that area.

[1908] The server analyzes Student A's health and emotional data, determines that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his study plan to reduce his learning load.

[1909] Specific examples of terminals (student devices)

[1910] Student A's device receives the "video lesson on fraction calculation" provided by the server, and works on related practice problems while playing the video.

[1911] The device monitors Student A's facial expressions while he is studying using a camera, and if the emotion engine determines that he is feeling stressed, it sends the data to the server in real time.

[1912] Student A completes the practice questions and sends the results data to the server.

[1913] Example of a user (homeroom teacher)

[1914] The homeroom teacher checks the dashboard and finds out that Student A has difficulty with "fraction calculations" and is feeling stressed while studying.

[1915] The homeroom teacher will provide Student A with additional explanations of fraction calculations and plan a supplementary program to improve his understanding. The teacher will also explore the reasons why the student felt stressed and provide appropriate feedback.

[1916] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[1917] The processing flow will be explained below.

[1918] Step 1:

[1919] Data collection: The server retrieves students' learning data (test results, submitted assignments, learning history, etc.) from the database. It also receives students' health data (heart rate, sleep time, activity level, etc.) from the wearable device. Furthermore, the emotion engine collects students' emotional data (facial expressions, tone of voice, etc.) via the device's camera and microphone.

[1920] Step 2:

[1921] Data analysis: The server analyzes the acquired data to evaluate each student's level of understanding, learning progress, and weak areas. It also analyzes health data to understand the student's physical condition and daily rhythm. It also analyzes emotional data in real time to determine the student's current emotional state (joy, excitement, anxiety, stress, etc.).

[1922] Step 3:

[1923] Learning content generation: The server uses a generative AI model to generate video lesson content that mimics the teaching style of a cram school teacher. This AI model adopts a lesson format that is likely to attract students' attention.

[1924] Step 4:

[1925] Creation of learning scenarios and practice questions: Based on the analysis results, the server automatically generates learning scenarios and practice questions that correspond to each student's level of understanding and progress.

[1926] Step 5:

[1927] Optimization of study plans: The server generates optimal study plans based on health and emotional data. For example, if fatigue or stress levels are high, the server will adjust the study plan by reducing the study load and adding relaxing content.

[1928] Step 6:

[1929] Content distribution: The server distributes the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1930] Step 7:

[1931] Displaying content: The device plays the received video lesson and displays practice questions according to the learning scenario, allowing students to proceed with their studies.

[1932] Step 8:

[1933] Emotion monitoring during learning: The device uses a camera and microphone to analyze students' facial expressions and tone of voice with an emotion engine, and sends emotional data to the server in real time. If the emotion exceeds a certain threshold, a notification is sent.

[1934] Step 9:

[1935] Monitoring learning activities: The device records students' learning progress in real time and accumulates learning activity data.

[1936] Step 10:

[1937] Collection of learning results: The terminal collects performance data (correct answer rate, answer time, etc.) of the practice problems completed by the student and sends it to the server.

[1938] Step 11:

[1939] Analysis of outcome data: The server analyzes the received learning outcome data to identify changes in the student's understanding and new areas of weakness.

[1940] Step 12:

[1941] Dashboard update: Based on the analysis results, the server updates the dashboard for the homeroom teacher, which visually displays each student's learning progress, level of understanding, weak areas, physical condition, and emotional state.

[1942] Step 13:

[1943] Checking the dashboard: The user (teacher) checks the dashboard to understand the student's learning situation and emotional state, consider necessary measures, and plan additional instruction and support.

[1944] Step 14:

[1945] Adjustment of learning plan: Based on newly acquired data and teacher feedback, the server re-optimizes the student's learning plan and generates and delivers the next cycle of learning content.

[1946] By repeating these steps, we will create a system that supports individually optimized learning for students and maximizes learning effectiveness by utilizing real-time feedback from the emotion engine.

[1947] Example 2

[1948] 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."

[1949] Conventional learning management systems have difficulty providing optimal learning content that takes into account each learner's progress and level of understanding, and are unable to reflect the learner's emotional state in real time, resulting in problems such as reduced learning efficiency and decreased learner motivation.

[1950] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for optimizing the generated learning content based on each learner's individual learning progress and level of comprehension, means for distributing the learning content to a terminal that displays the learning content, means for displaying the learning content, means for collecting learning outcomes from the terminal, means for analyzing the learning outcomes and generating new learning content, means for collecting health data and optimizing a learning plan, means for providing learning content based on the health data, means for analyzing emotional data collected in real time and dynamically adjusting the learning content, and means for providing a dashboard that visually displays the learning progress and level of comprehension for teachers. This enables the provision of learning content optimized for each learner and a dynamic learning experience that reflects emotional states in real time.

[1951] "Generated learning content" refers to educational materials and exercises generated using digital tools and artificial intelligence.

[1952] "Individual learning progress" refers to the current learning progress of each learner, and indicates the extent to which they have understood and acquired the material.

[1953] "Comprehension" is an indicator that measures how accurately a learner understands a specific learning content.

[1954] "Devices" refer to digital devices used by learners, such as computers, tablets, and smartphones.

[1955] "Learning outcomes" refers to the grades and performance data that learners obtain as a result of completing assignments and tests.

[1956] "Health data" refers to data that indicates a learner's physical condition, such as heart rate, sleep time, and activity level.

[1957] "Emotional data" refers to data that indicates the emotional state of a learner, as obtained from facial expressions, tone of voice, etc.

[1958] A "dashboard" is a user interface that visually displays learning progress, comprehension, emotional state, etc.

[1959] A "generative AI model" is a model for creating new content using artificial intelligence.

[1960] A "prompt" is a sentence of instructions or questions that is input into a generative AI model.

[1961] "Dynamic adjustment" means changing content and settings as needed in response to changing real-time conditions.

[1962] These definitions clarify the meaning of key terms contained in the following claims.

[1963] This invention combines an emotion engine with a system that optimizes generated learning content based on each student's learning progress and level of understanding and distributes it to their devices. A specific embodiment of this entire system is shown below.

[1964] Server Processing

[1965] The server uses the following hardware and software:

[1966] Hardware: A server machine equipped with a high-performance processor

[1967] Software: Database management systems (e.g., MySQL), generative AI models (e.g., GPT-4), emotion engines (e.g., Emotion API), data analysis libraries (e.g., scikit-learn)

[1968] 1. Data Collection and Analysis

[1969] The server collects students' learning data (test results, submitted assignments, learning history, etc.) and health data (heart rate, sleep time, activity level, etc.). It also collects students' emotional data (joy, interest, anxiety, etc.) through an emotion engine.

[1970] The server analyzes the collected data and evaluates the student's learning progress, level of understanding, weak areas, current physical condition, emotional state, etc. The analysis is carried out using machine learning models and statistical methods.

[1971] 2. Generating learning content

[1972] The server uses a generative AI model (e.g., GPT-4) to generate video lesson content that mimics the teacher's teaching style. This AI model adopts a lesson format that is likely to attract students' attention.

[1973] Based on the analyzed learning data, learning scenarios and practice questions are automatically generated according to the student's level of understanding and progress.

[1974] An example prompt is, "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[1975] 3. Optimize your study plan

[1976] The server generates the most efficient study schedule based on health and emotional data. For example, if fatigue or stress levels are high, it will adjust the study load accordingly.

[1977] 4. Content Delivery

[1978] The server delivers the generated video lesson content, exercises, and optimized learning plans to students' devices.

[1979] 5. Providing a dashboard

[1980] The server updates and provides a dashboard for teachers to visually display learning and emotional data, including students' learning progress, level of understanding, areas of weakness, physical condition, and emotional state.

[1981] Handling terminals (student devices)

[1982] The terminal uses the following hardware and software:

[1983] Hardware: Learners' computers, tablets, smartphones, etc.

[1984] Software: Video playback software, emotion analysis software (e.g., OpenCV)

[1985] 1. Receiving and viewing learning content

[1986] The terminal receives video lesson content and practice questions delivered from the server.

[1987] The device displays the received content in the appropriate format, allowing students to engage in their studies.

[1988] 2. Monitoring emotions during learning

[1989] The device uses an emotion engine to analyze students' facial expressions and tone of voice via a camera and microphone, and transmits emotional data to a server in real time.

[1990] 3. Submit your learning outcomes

[1991] When a student completes a learning task, the performance data (correct answer rate, answer time, etc.) is sent to the server.

[1992] User (homeroom teacher) processing

[1993] 1. Check the dashboard

[1994] Homeroom teachers can use a dashboard provided by the server to check students' learning progress, level of understanding, and emotional state.

[1995] Use the dashboard to plan appropriate instruction and advice for students.

[1996] As a specific example, the server identifies Student A's weak areas in "fraction calculations" based on his past learning data and current learning progress, and generates video lesson content specialized for that area. It also analyzes Student A's health and emotional data, confirms that he did not get enough sleep the night before and is feeling stressed while studying, and adjusts his learning plan to reduce his learning load.

[1997] In this way, the present invention is a system that provides learning content optimized for each student and adjusts the student's learning experience in real time using an emotion engine, thereby reducing the burden on teachers and enabling effective learning.

[1998] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1999] The processing flow of the program of this system will be explained in detail below, divided into processing steps.

[2000] Server Processing

[2001] Step 1: Data collection and analysis preparation

[2002] Input: Student learning data, health data, and emotion data

[2003] What happens: The server initializes the database and API connections.

[2004] Output: Database connection object, API connection object

[2005] Step 2: Collect training data

[2006] Input: Student ID

[2007] What it does: The server sends an SQL query to retrieve the learning data corresponding to the student ID from the database.

[2008] Output: Student learning dataset (test results, assignment submissions, learning history, etc.)

[2009] Example: "SELECT FROM training_data WHERE student_id = 'A123'"

[2010] Step 3: Collect health data

[2011] Input: API request

[2012] How it works: The server retrieves health data from the wearable device via an API request.

[2013] Output: Student health dataset (heart rate, sleep time, activity level, etc.)

[2014] Example: "GET / api / healthdata?student_id=A123"

[2015] Step 4: Collecting sentiment data

[2016] Input: Real-time data from the device

[2017] How it works: The server receives student emotion data using WebSocket or HTTP POST requests.

[2018] Output: Student emotion dataset (happiness, interest, anxiety, etc.)

[2019] Step 5: Analyze the data

[2020] Input: Training dataset, Health dataset, Emotion dataset

[2021] How it works: The server analyzes the data using machine learning models (e.g., scikit-learn) to assess the student's learning progress, comprehension, weak areas, physical condition, and emotional state.

[2022] Output: Analysis results (learning progress, level of understanding, weak areas, etc.)

[2023] Step 6: Prepare to generate learning content

[2024] Input: Analysis results

[2025] What it does: The server initializes a generative AI model (e.g., GPT-4) and generates a prompt.

[2026] Output: prompt statement

[2027] Example: "Create an engaging video lesson on fraction calculations based on Student A's past learning data."

[2028] Step 7: Generate learning content

[2029] Input: prompt statement

[2030] Operation: The server inputs prompt sentences into the generative AI model and generates video lesson content.

[2031] Output: Video lesson content

[2032] Step 8: Optimize your study plan

[2033] Input: Health data, emotion data

[2034] How it works: The server generates the most efficient learning schedule based on health and emotional data.

[2035] Output: Optimized learning plan

[2036] Example: Reducing study load and adjusting sleep schedule

[2037] Step 9: Deliver your content

[2038] Input: Video lesson content, optimized learning plans

[2039] How it works: The server sends this data to the student's device.

[2040] Output: Data delivered to student devices

[2041] Step 10: Update the dashboard

[2042] Input: Analysis results, emotion data

[2043] What it does: The server then displays this data in a dashboard for teachers.

[2044] Output: Updated dashboard

[2045] Handling terminals (student devices)

[2046] Step 1: Receiving content

[2047] Input: Data delivered from the server

[2048] Operation: The device receives the video lesson content and exercises from the server.

[2049] Output: Received learning content, exercises

[2050] Step 2: Viewing content

[2051] Input: Received learning content

[2052] What happens: The device displays the received content in the appropriate format, and the student engages with their learning.

[2053] Output: Displayed learning content

[2054] Step 3: Monitoring sentiment data

[2055] Input: Real-time facial and voice data from camera and microphone

[2056] How it works: The device uses a camera and microphone to analyze students' facial expressions and tone of voice using an emotion engine.

[2057] Output: Parsed emotion data

[2058] Step 4: Sending emotion data

[2059] Input: Parsed emotion data

[2060] How it works: The device sends emotion data to the server in real time.

[2061] Output: Emotion data sent to the server

[2062] Step 5: Record and submit your learning outcomes

[2063] Input: Study task performance data (correct answer rate, answer time, etc.)

[2064] How it works: When a student completes a learning task, the performance data is recorded and sent to the server.

[2065] Output: Learning outcome data sent to the server

[2066] User (homeroom teacher) processing

[2067] Step 1: Check the dashboard

[2068] Input: Updated dashboard

[2069] How it works: The teacher accesses the dashboard from a web browser and checks the data.

[2070] Output: Confirmed learning progress, comprehension, and emotional state

[2071] Step 2: Plan your lesson

[2072] Input: Dashboard data

[2073] How it works: The teacher uses the dashboard analysis results to plan instruction and feedback for the students.

[2074] Output: Planned lesson content

[2075] Through these specific processing steps, the present invention is a system that provides an optimized learning environment for each learner and realizes effective education.

[2076] (Application example 2)

[2077] 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."

[2078] Conventional in-car entertainment systems rely on static content delivery and are unable to respond quickly to changes in passengers' emotional state or preferences. This makes it difficult to improve passenger satisfaction and relaxation, and provides a comfortable riding experience.

[2079] 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 optimizing the generated personalized content based on individual conditions and preferences, means for delivering the content to a display device in the vehicle that displays the content, means for displaying the content, means for collecting behavioral data from the display device, means for analyzing the behavioral data and generating new content, means for collecting emotional data and optimizing the content to be provided, means for providing content based on the emotional data, and means for providing a dashboard that visually displays the conditions and emotional states in the vehicle. This enables dynamic content delivery that quickly responds to the emotional conditions and preferences of passengers.

[2080] "Generated personalized content" refers to entertainment and information that is optimized based on a passenger's individual circumstances and preferences.

[2081] "Individual conditions" refers to the different circumstances of each passenger, such as their physical condition, emotional state, and current environment.

[2082] "Preferences" refer to genres or types of content that a passenger is particularly interested in, such as music, movies, news, etc.

[2083] An "in-vehicle display device" is a device installed inside a vehicle for displaying or playing content, such as a screen, monitor, or speaker.

[2084] "Behavioral data" refers to data such as passenger operation history, viewing history, and physical reactions collected from display devices and sensors inside the vehicle.

[2085] "Emotional data" refers to data on passengers' emotional states that is determined from their facial expressions, tone of voice, heart rate, etc., collected using sensors such as cameras and microphones.

[2086] A "dashboard" is an interface that visually displays passenger status, emotional state, system operation status, etc.

[2087] This invention provides a personalized infotainment system that enhances the entertainment experience for passengers in autonomous vehicles. The system delivers content optimized based on each passenger's individual conditions and preferences, ensuring a comfortable and satisfying riding experience.

[2088] System configuration

[2089] server

[2090] The server includes the following means:

[2091] 1. A means to optimize the generated personalized content based on individual conditions and preferences.

[2092] 2. Means for delivering said content to a display device within the vehicle.

[2093] 3. A means of collecting behavioral and emotional data and generating new content.

[2094] 4. Means for providing content based on said emotion data.

[2095] 5. A means of providing a dashboard that visually displays the passenger's condition and emotional state.

[2096] The server analyzes behavioral and emotional data collected using cameras and microphones, generates new content using generative AI models, and delivers optimized content based on passenger preferences and their current emotional state.

[2097] Terminal (display device inside the vehicle)

[2098] The terminal does the following:

[2099] 1. Receive and display or play content delivered from the server.

[2100] 2. Passengers' facial expressions and tone of voice are captured through cameras and microphones and analyzed using an emotion engine (e.g., Affectiva SDK).

[2101] 3. The analysis results are sent to the server in real time and dynamic content adjustments are made.

[2102] User (passenger)

[2103] The user does the following:

[2104] 1. View content provided through a display device in the vehicle.

[2105] 2. Providing emotional data such as facial expressions and tone of voice.

[2106] Hardware and software used

[2107] Camera: Used to monitor passengers' facial expressions.

[2108] Microphone: Used to analyze passengers' voice tones.

[2109] Emotion engine (e.g., Affectiva SDK): assesses the passenger's emotional state.

[2110] Generative AI models (e.g., OpenAI GPT-4): Generate personalized content.

[2111] Data analysis server: Analyzes behavioral and emotional data to optimize content.

[2112] Specific examples

[2113] For example, if a passenger feels like relaxing on a rainy day, the system collects emotional data in real time and sends a prompt to the generative AI model, such as:

[2114] "A passenger wants to relax on a rainy day. Their tastes are classical music and jazz. Generate a music playlist that is perfect for this situation."

[2115] Based on this prompt, the generative AI model will generate an optimal music playlist, which the server will then distribute to the display devices inside the vehicle, allowing passengers to enjoy relaxing music and a comfortable riding experience.

[2116] As described above, this system provides content that is dynamically optimized according to the individual state and emotional state of each passenger, ensuring a comfortable riding experience.

[2117] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2118] Step 1:

[2119] The server uses a camera and microphone to capture the facial expressions and tone of voice of passengers in the vehicle. This data is analyzed by an emotion engine (e.g., Affectiva SDK) to evaluate the passenger's current emotional state. The input is camera video and audio data, and the output is the passenger's emotional state (e.g., relaxed, anxious, etc.). Specifically, the facial expression analysis module and audio analysis module process the data in real time to determine the emotional state.

[2120] Step 2:

[2121] The server collects passengers' past behavioral data (riding history, music and video play history) and analyzed emotional data, and sends it to the data analysis server. The input is data collected from the camera and microphone and past behavioral history, and the output is log information for data analysis. Specifically, the server retrieves passenger history data from the database and integrates it with emotional data.

[2122] Step 3:

[2123] The data analysis server sends prompts to the generative AI model based on the passenger's preferences and current emotional state. For example, it generates a prompt like, "A passenger on a rainy day feels like relaxing. Their hobbies are classical music and jazz. Please generate a music playlist that is best suited to this situation." The input is emotional data and passenger preference data, and the output is a prompt. Specifically, the prompt generation module receives the data and creates an appropriate prompt.

[2124] Step 4:

[2125] The generative AI model generates optimal personalized content based on the received prompt. The input is the prompt, and the output is personalized content (e.g., music playlist, video list). Specifically, the generative AI model performs natural language processing and creates content based on the prompt.

[2126] Step 5:

[2127] The server distributes the generated personalized content to the display device in the vehicle. The input is the content from the generative AI model, and the output is the content data to the display device. Specifically, the content distribution module receives the data and sends it to the specified device.

[2128] Step 6:

[2129] The terminal (display device inside the vehicle) displays or plays the distributed content. The input is content data from the server, and the output is the video or music that passengers watch. Specifically, the playback module receives the content data and displays or plays it on the screen or speaker.

[2130] Step 7:

[2131] The device again collects the passenger's emotional data through the camera and microphone and transmits it to the server in real time. The input is new camera video and audio data, and the output is updated emotional state data. Specifically, the emotion monitoring module continues to analyze the data and send it back to the server.

[2132] 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.

[2133] 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.

[2134] 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.

[2135] 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.

[2136] FIG. 9 is a diagram illustrating 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 actions 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.

[2137] 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.

[2138] 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).

[2139] 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.

[2140] 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."

[2141] 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.

[2142] 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).

[2143] 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.

[2144] 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.

[2145] 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.

[2146] 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.

[2147] 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.

[2148] 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.

[2149] 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.

[2150] 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.

[2151] 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.

[2152] 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.

[2153] The following is further disclosed regarding the above embodiment.

[2154] (Claim 1)

[2155] A means for optimizing the generated learning content based on individual learning progress and comprehension;

[2156] means for distributing the learning content to a terminal that displays the learning content;

[2157] means for displaying the learning content;

[2158] means for collecting learning outcomes from the terminal;

[2159] A means for analyzing the learning outcomes and generating new learning content;

[2160] a means of collecting health data and optimizing learning plans;

[2161] means for providing learning content based on the health data;

[2162] A means to provide teachers with a dashboard that visually displays progress and understanding

[2163] A system including:

[2164] (Claim 2)

[2165] 2. The system according to claim 1, further comprising means for studying video lesson content that imitates the progress of a cram school teacher's lesson and providing the video lesson content as part of the learning content.

[2166] (Claim 3)

[2167] 10. The system according to claim 1, further comprising means for optimizing the generated learning content based on the physical c...

Claims

1. A means for optimizing the generated learning content based on individual learning progress and comprehension; means for distributing the learning content to a terminal that displays the learning content; means for displaying the learning content; means for collecting learning outcomes from the terminal; A means for analyzing the learning outcomes and generating new learning content; a means of collecting health data and optimizing learning plans; means for providing learning content based on the health data; A means to provide teachers with a dashboard that visually displays progress and understanding A system including:

2. The system according to claim 1, further comprising means for studying video lesson content that imitates the progress of a lesson by a cram school teacher, and providing the video lesson content as part of the learning content.

3. The system according to claim 1 , further comprising means for optimizing the generated learning content based on the physical condition and lifestyle of the student.

Images