System

Abstract

A system is provided.SOLUTION: This system includes a means for providing learning data by a user, a means for collecting and storing the learning data of the user by a server, a means for analyzing the collected data and specifying the weak point of the user by the server, a means for generating a learning material based on the specified weak point by a generation controller, and a means for distributing the generated learning material to the user by a terminal.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] Traditional online learning platforms and teaching materials are uniform and do not adapt to the specific needs of individual learners. This prevents them from providing learning materials optimized for each individual learner, hindering efficient learning. Furthermore, learning materials that effectively address specific weaknesses of learners are often not provided, resulting in insufficient improvement in academic ability. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: a means for a user to provide learning data; a means for a server to collect and store the user's learning data; a means for the server to analyze the collected data and identify the user's weaknesses; a generation control device to generate learning materials based on the identified weaknesses; and a terminal to distribute the generated learning materials to the user. This makes it possible to provide learning materials that meet individual learning needs, thereby realizing an efficient learning environment. Furthermore, the generation control device optimizes the learning materials based on the user's level of understanding and interests, enabling even more effective learning.

[0006] A "user" is an individual or group who uses the system to learn.

[0007] "Learning data" refers to information provided by the user, such as test results, learning history, answer time, and accuracy rate.

[0008] A "server" is a central management device that collects, stores, and analyzes learning data.

[0009] The "generation control device" is a device that generates and optimizes learning materials based on the analysis results.

[0010] "Learning materials" are educational content created to address the user's weaknesses, and may take the form of text, video, exercises, etc.

[0011] A "terminal" is a device (such as a PC, tablet, or smartphone) that a user uses to access learning materials.

[0012] The "means for distributing the generated learning materials" refers to the methods and procedures for providing the learning materials to the user using the terminal.

[0013] A "weakness" is a particular topic or subject in which the user has insufficient understanding as indicated by an analysis of the learning data.

[0014] "Database" means an information management system for storing collected learning data and generated learning materials.

[0015] "Notification" refers to the act of conveying information to a user via a device, including reminders and information about the delivery of new learning materials. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

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

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0037] The present invention relates to a system for providing learning materials optimized for each individual learner, and is configured as follows.

[0038] Program processing

[0039] Overall flow

[0040] Users' usual learning activities and tests are collected and analyzed on the server to identify specific weaknesses. The generation control device generates and optimizes learning materials based on the weaknesses. The final generated learning materials are delivered to the user via their device.

[0041] Data collection

[0042] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online math test, the results (correct answer rate, answer time, etc.) are automatically sent from the device to the server.

[0043] Data storage and analysis

[0044] The server receives the collected learning data and stores it in a database. The stored data is analyzed using machine learning algorithms, etc. Through the analysis, for example, "linear equations" may be identified as the user's weakness.

[0045] Teaching material generation

[0046] Based on the analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated learning materials are optimized to suit the user's level of understanding and learning style. For example, learning materials are created that include everything from basic explanations of linear equations to applied problems.

[0047] Teaching material distribution

[0048] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[0049] Specific examples

[0050] For a math test

[0051] 1. Data collection: User A takes an online math test and the results (60% correct answer rate) are sent from the device to the server.

[0052] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User A is identified as having a weakness in the "linear equation."

[0053] 3. Teaching material generation: The generation control device generates teaching materials related to linear equations. For example, it includes "basic explanations, videos of calculation procedures, and applied problems."

[0054] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[0055] For an English quiz

[0056] 1. Data collection: User B takes a short English quiz and the results (40% correct answers on grammar questions) are sent from the device to the server.

[0057] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User B is identified as having a weakness in "grammar."

[0058] 3. Teaching material generation: The generation control device generates grammar teaching materials, such as "basic grammar rules and related exercises."

[0059] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[0060] In this way, the system collects and analyzes users' learning data, generates, optimizes, and delivers learning materials that address specific weaknesses, thereby providing an efficient and effective learning environment.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] A user takes an online test.

[0064] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[0065] Step 2:

[0066] The device sends the learning data to the server.

[0067] Immediately after the user completes the test, the device sends the answer data to the server, including the user ID, test type, answer data for each question, and the answer time.

[0068] Step 3:

[0069] The server stores the learning data.

[0070] The server stores the received learning data in a database, which also stores each user's past learning data, making it easy to compare it with new data.

[0071] Step 4:

[0072] The server analyzes the training data.

[0073] The server then uses the stored data to begin analyzing the user. It uses machine learning algorithms to identify the user's weaknesses. Specifically, it creates a list of questions the user answered incorrectly the most or took the most time to answer, and identifies weaknesses related to those topics.

[0074] Step 5:

[0075] A generation control device generates a draft of the teaching material.

[0076] Based on the identified weaknesses, a generative control system uses generative AI to draft learning materials, including basic explanations, examples, and practice questions.

[0077] Step 6:

[0078] The generation control device optimizes the teaching materials.

[0079] Based on the generated draft, the generation control device optimizes the learning materials to suit the user's learning style and level of understanding, specifically adjusting the content according to the user's preferred learning format (text, video, interactive questions, etc.).

[0080] Step 7:

[0081] The server stores the optimized teaching materials in a database.

[0082] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[0083] Step 8:

[0084] The server sends a notification of the distribution of the teaching material to the terminal.

[0085] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[0086] Step 9:

[0087] Users receive notifications and access the learning materials.

[0088] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[0089] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning.

[0090] Example 1

[0091] 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."

[0092] Conventional learning systems have difficulty addressing the individual weaknesses and needs of learners. As a result, learners are forced to use uniform learning materials, which can lead to inefficient learning. Furthermore, existing systems have difficulty providing appropriate reminders and feedback based on learners' progress and level of understanding, which can lead to reduced learning effectiveness.

[0093] 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.

[0094] In this invention, the server includes a learning data collection means, a storage means, and an analysis means, which enables efficient collection, storage, and analysis of user learning data.

[0095] "User" refers to a learner who uses the system to carry out learning activities.

[0096] "Learning Data" refers to results and progress information generated when a user completes a learning activity or test.

[0097] "Server" refers to a computer system that collects, stores, and analyzes learning data and distributes generated learning materials.

[0098] A "generation controller" is a device or process for generating learning materials based on a user's weaknesses.

[0099] A "terminal" is a computer or mobile device that a user uses to perform learning activities.

[0100] A "machine learning algorithm" is a data analysis method used to analyze collected data and identify users' learning patterns and weaknesses.

[0101] A "generative AI model" is an artificial intelligence system that automatically generates learning materials based on specific prompts.

[0102] "Notification function" refers to a function on the terminal that notifies the user that generated learning materials are available.

[0103] "Reminder" is a function that notifies users of their learning progress and what they need to study.

[0104] MODE FOR CARRYING OUT THE INVENTION

[0105] The present invention is a learning support system designed to optimize a user's learning activities. Specific embodiments of the system are described below.

[0106] Hardware and Software Configuration

[0107] Collecting and storing learning data

[0108] Users use learning devices (e.g., personal computers, tablets, smartphones, etc.) to carry out learning activities and take tests. The devices collect learning data (e.g., correct answer rate, answer time, etc.) generated as a result of these activities and send it to a server via the Internet. The server stores this learning data using a database system such as MySQL (registered trademark) or PostgreSQL.

[0109] Data analysis

[0110] The server analyzes the saved learning data using Python libraries (e.g., scikit-learn or TENSORFLOW®). This allows the server to apply machine learning algorithms to identify the user's weaknesses. For example, if a user takes an online math test and gets 60% correct answers, the server will recognize through analysis that "linear equations" is a weak point.

[0111] Teaching material generation

[0112] The server uses a generative controller to generate learning materials based on the identified weaknesses. The generative controller creates learning materials using a generative AI model such as OpenAI's GPT-4. An example of a generation prompt is "Please generate learning materials for beginners about linear equations."

[0113] Teaching material distribution and notifications

[0114] The server delivers the generated learning materials to the user's device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials and begin learning.

[0115] Specific examples

[0116] For a math test

[0117] For example, when User A takes an online math test, the results (e.g., a 60% accuracy rate) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User A's weakness lies in "linear equations." The generation control device then uses a generative AI model such as GPT-4 to generate learning materials related to linear equations. These learning materials include basic explanations, videos showing calculation procedures, and applied problems. The generated learning materials are distributed from the server to User A's device, and notifications are sent via Firebase Cloud Messaging. User A then uses the learning materials distributed via the device to continue their studies.

[0118] For an English quiz

[0119] Furthermore, when User B takes an English quiz, the results (for example, a 40% accuracy rate on grammar questions) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User B's weakness lies in "grammar." The generation control device then uses a generative AI model such as GPT-4 to generate grammar-related learning materials. These learning materials include basic grammar rules and related practice questions. The generated learning materials are distributed from the server to User B's device, and User B is notified via a notification function. User B uses the distributed learning materials to study.

[0120] This invention provides an efficient and effective learning environment by collecting, storing, and analyzing user learning data, and generating and delivering learning materials based on identified weaknesses.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1: Data collection

[0123] The user uses the device to carry out learning activities and tests. For example, they take an online math test. The test results (number of correct answers, answering time, etc.) are generated. The device processes these results and sends them to the server as learning data.

[0124] Input: User test results (number of correct answers, answer time, etc.)

[0125] Data processing: Formatting test results as training data

[0126] Output: Learning data is sent to the server. Specific operation: The device automatically compiles the test results and calls an API that sends them to the server.

[0127] Step 2: Save data

[0128] The server stores the learning data received from the device in a database, using a database management system such as MySQL or PostgreSQL.

[0129] Input: Training data sent from the device

[0130] Data processing: Converting training data into a format that can be stored in a database

[0131] Output: The training data is saved in the database. Specific operation: The server adds the received data to the corresponding table in the database.

[0132] Step 3: Data analysis

[0133] The server analyzes the saved learning data and identifies the user's weaknesses using machine learning libraries such as Python's scikit-learn and TensorFlow. For example, if the user's accuracy rate for "linear equations" is low, this will be identified as the user's weakness.

[0134] Input: Training data stored in a database

[0135] Data processing: Applying machine learning algorithms to identify user weaknesses

[0136] Output: The result of identifying the user's weaknesses is obtained. Specific operation: The server reads the learning data from the database and applies the machine learning algorithm to identify the user's weaknesses.

[0137] Step 4: Creating teaching materials

[0138] The server uses a generative controller to generate learning materials based on the identified weaknesses. This generation process uses a generative AI model, such as OpenAI's GPT-4. Example prompt: "Generate learning materials for beginners on linear equations."

[0139] Input: User weakness identification results, prompt text

[0140] Data processing: Using generative AI models to generate learning materials

[0141] Output: Generated learning materials. Specific operation: The generation control device inputs a prompt sentence into the generation AI model and obtains the generated learning materials.

[0142] Step 5: Distribution of teaching materials

[0143] The server delivers the generated learning materials to the device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials through the device and begin learning.

[0144] Input: Generated learning materials

[0145] Data processing: Converting educational materials into a delivery format

[0146] Output: The teaching materials are delivered to the terminal and the user is notified. Specific operation: The server sends the generated teaching materials to the terminal and notifies the user through the notification function.

[0147] (Application example 1)

[0148] 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."

[0149] To improve the efficiency and accuracy of robot operations in factories, it is necessary to provide individually optimized training programs for each robot. However, currently, it is difficult to effectively analyze robot operation data and quickly generate appropriate training programs. Furthermore, there is a lack of a system for delivering appropriate training programs to robots in a timely manner and improving their operational performance. This poses the issue of reduced efficiency across the production line and increased risk of breakdowns.

[0150] 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.

[0151] In this invention, the server includes a means for collecting and storing robot operation data, a means for analyzing the collected data and identifying the robot's weaknesses, a generation control device for generating a training program based on the identified weaknesses, and a terminal for distributing the generated training program to the robot. This makes it possible to quickly provide a training program optimized for each robot in order to effectively improve the efficiency and accuracy of the robot's operation.

[0152] "User" refers to an individual or organization that uses the system and provides learning data.

[0153] A "server" is an electronic computing device that stores and analyzes data collected from users and robots.

[0154] "Learning data" refers to data generated by users through learning activities and tests.

[0155] A "generation control device" is a device that generates learning materials and training programs based on the results of analysis by the server.

[0156] A "terminal" is a device through which a user or robot receives learning materials and training programs.

[0157] "Operational data" refers to performance data such as the speed, accuracy, and work height of a factory robot.

[0158] "Weaknesses" are challenges or shortcomings that the user or robot must overcome as a result of data analysis.

[0159] A "training program" is training content created to improve the robot's movement performance.

[0160] "Reminders" are information about learning and training progress that the server notifies the user and robot.

[0161] The system that realizes this invention collects and analyzes user learning data and factory robot operation data, and based on that, generates and distributes optimal teaching materials and training programs. A specific implementation method is shown below.

[0162] Data collection

[0163] When users take online tests or study activities, learning data (e.g., accuracy rate, answer time, etc.) is generated and sent to a server via their devices. Similarly, operational data (speed, accuracy, work height, etc.) of factory robots is collected in real time via sensors and sent to a server. The hardware used includes network-connected PCs and tablets, as well as sensors (e.g., LiDAR, cameras) mounted on factory robots.

[0164] Data storage and analysis

[0165] The server stores the received learning data and operation data in a database. The stored data is analyzed using machine learning algorithms. Specifically, the data is analyzed using scalable cloud storage (e.g., Amazon S3) and a data analysis platform (e.g., Apache Spark). As a result of the analysis, weaknesses in the user's learning and problems with the factory robot's operation are identified. For example, it may be identified that the user has a weakness in "linear equations" or that the robot's speed performance is low.

[0166] Creation of educational materials and training programs

[0167] Based on the analysis results, a generation control device on the server generates optimal learning materials and training programs. Specifically, learning materials and training programs are generated using Python and provided to users and robots. For example, learning materials on linear equations are generated to include video explanations and application problems. Also, a training program to improve the robot's speed is generated.

[0168] Delivery of educational materials and training programs

[0169] The generated learning materials and training programs are distributed from the server to the user's device or robot. The user or robot receives the materials and programs and carries out the learning or training. Notification services (e.g., Firebase) and reminder functions are used to manage notifications and learning progress.

[0170] Specific examples

[0171] For example, if User A takes an online math test and gets 60% correct, the data is sent to the server and analyzed. As a result, linear equations are identified as a weak point. The generation control device generates optimal teaching materials for linear equations (basic explanations, videos showing calculation procedures, and applied problems) and delivers them to User A's device.

[0172] Furthermore, if the operational data of a factory robot is analyzed and it is determined that the speed performance is low, the production control device will generate a training program to improve the speed and distribute it to the robot.

[0173] Examples of prompt statements

[0174] "Collect operational data (speed, accuracy, work height) of factory robots and analyze their weaknesses through clustering. Based on the analysis results, create a training program to compensate for specific weaknesses and distribute it to the robot."

[0175] In this way, the system can quickly and effectively provide educational materials and training programs optimized for each user and robot.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] Users generate learning data through online tests and learning activities. This data includes, for example, the percentage of correct answers and the time it takes to answer. The device transmits this data to the server in real time. The input is the learning data generated by the user, and the output is the learning data transmitted to the server.

[0179] Step 2:

[0180] The server receives the training data sent from the device and stores it in a database. Specifically, it stores the data using an SQL server or NoSQL database. The input is the training data sent from the device, and the output is the stored training data.

[0181] Step 3:

[0182] The server analyzes the stored training data using a machine learning algorithm. The specific operation here is to normalize the data and apply a specific algorithm (e.g., clustering) to identify the user's weaknesses. The input is the stored training data, and the output is the analysis result (the user's weaknesses).

[0183] Step 4:

[0184] The generation control device in the server generates learning materials based on the analysis results. Specifically, it uses Python to generate learning materials from templates and customizes the content according to the user's level of understanding and interests. The input is the analysis results, and the output is the generated learning materials.

[0185] Step 5:

[0186] The server delivers the generated learning materials to the device. Specifically, it uses a cloud notification service (e.g., Firebase) to notify the user that new learning materials are available. The input is the generated learning materials, and the output is the learning materials delivered to the user's device and the notification.

[0187] Step 6:

[0188] The terminal notifies the user that new learning materials are available, and the user accesses the delivered materials to study. Specific operations include displaying the materials through a user interface and managing how the user progresses with their learning activities. The input is the delivered learning materials, and the output is the user's learning activity data.

[0189] Step 7:

[0190] For factory robots, the robot's operational data (speed, accuracy, work height, etc.) is collected through sensors and sent to a server. The input is the robot's operational data, and the output is the operational data sent to the server.

[0191] Step 8:

[0192] The server receives the robot's motion data and stores it in the database in the same way as the training data. The input is the robot's motion data, and the output is the stored motion data.

[0193] Step 9:

[0194] The server analyzes the stored robot's motion data and identifies the robot's weaknesses. The input is the stored motion data, and the output is the analysis result (the robot's motion weaknesses).

[0195] Step 10:

[0196] The generation control device generates a training program for the robot based on the analysis results. Specifically, it automatically generates training content for specific weaknesses and puts it into program format. The input is the analysis results, and the output is the generated training program.

[0197] Step 11:

[0198] The server distributes the generated training program to the robot. The input is the generated training program, and the output is the training program distributed to the robot.

[0199] Step 12:

[0200] The robot automatically begins training based on the received training program to improve its performance. Specifically, it modifies its movements according to the training program to improve its performance. The input is the delivered training program, and the output is the robot's improved performance.

[0201] 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.

[0202] The present invention relates to a system for providing learning materials optimized for each individual learner, and also has a function for recognizing the user's emotions and optimizing the learning materials. Specific embodiments of the system are described below.

[0203] Program processing

[0204] Overall flow

[0205] Users provide learning data through online tests and learning activities. Based on that data, the server analyzes specific weaknesses, and the generation control device generates and optimizes learning materials. An emotion engine is also incorporated to optimize learning materials based on the user's emotions. Finally, the generated learning materials are delivered to the user via their device.

[0206] Data collection

[0207] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online English test, emotional data is collected using the device's camera and microphone along with the results (correct answer rate, answer time, etc.). This data is sent from the device to a server.

[0208] Data storage and analysis

[0209] The server stores the collected learning data and emotional data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expressions, tone of voice, and text-based emotional expressions). The stored data is analyzed by an analysis module on the server. Based on the analysis results, topics and subjects that are the user's weaknesses are identified.

[0210] Teaching material generation and optimization

[0211] Based on the server's analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated materials include custom content tailored to the user's level of understanding and learning style. Furthermore, emotional data collected by the emotion engine is also used. For example, optimizations are made, such as providing a format that is easy for the user to understand (videos, interactive questions, etc.) or adjusting the difficulty level if the user is suspected to be stressed.

[0212] Teaching material distribution

[0213] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[0214] Specific examples

[0215] Mathematics testing and emotional data collection

[0216] 1. Data collection: User A takes an online math test, and the results (50% correct answer rate) and emotional data (facial expression data captured by a camera) are sent from the device to the server. The emotional data suggests that User A may be frustrated during the test.

[0217] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User A has a weakness in "linear equations" and that he was frustrated during the test.

[0218] 3. Teaching material generation and optimization: The generation control device generates teaching materials related to linear equations. For example, it may include "basic explanations, videos showing calculation procedures, and applied problems." The difficulty level of the teaching materials is adjusted based on the emotion data, and they are provided in a format that is easy for User A to understand.

[0219] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[0220] English quiz and emotional data collection

[0221] 1. Data collection: User B takes a short English quiz, and the results (40% correct answer rate for grammar questions) and emotional data (tone of voice recorded by a microphone) are sent from the device to the server. The emotional data suggests that User B is relaxed and engaged in studying.

[0222] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User B has weaknesses in "grammar" and is able to study in a relaxed state.

[0223] 3. Learning material generation and optimization: The generation control device generates grammar learning materials, including basic grammar rules and related exercises. Based on emotional data, the content is provided in a way that makes it easy to learn in a relaxed state.

[0224] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[0225] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a more personalized learning experience and create an efficient and effective learning environment.

[0226] The processing flow will be explained below.

[0227] Step 1:

[0228] A user takes an online test.

[0229] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[0230] Step 2:

[0231] The device collects emotional data.

[0232] During the online test, the device collects emotional data such as the user's facial expressions and tone of voice. For example, the camera recognizes the user's facial expressions and the microphone analyzes the tone of voice.

[0233] Step 3:

[0234] The device sends the learning data and emotion data to the server.

[0235] Immediately after the user completes the test, the device sends the answer data and collected emotion data to the server, including the user ID, test type, answer data, answer time, and emotion data.

[0236] Step 4:

[0237] The server stores the training data and emotion data.

[0238] The server stores the received training data and emotion data in a database, which also stores each user's past training data and emotion data, making it easy to compare with new data.

[0239] Step 5:

[0240] The server analyzes the training data and emotion data.

[0241] The server then begins analysis using the stored learning data and emotional data. Using machine learning algorithms, it identifies the user's weaknesses and evaluates their emotional state. For example, it can list questions on which the user got the most answers wrong or took the longest time, identify weaknesses related to those topics, and evaluate the user's emotional state during the test.

[0242] Step 6:

[0243] A generation control device generates a draft of the teaching material.

[0244] Based on the identified weaknesses, the generation control device uses generative AI to create draft learning materials, including basic explanations, examples, and practice questions.

[0245] Step 7:

[0246] The generation control device optimizes the teaching materials based on the emotion data.

[0247] Based on the generated draft, the generation control device optimizes the learning materials based on the user's learning style, level of comprehension, and emotional data. For example, if the user feels stressed during a test, the difficulty level of the learning materials will be adjusted.

[0248] Step 8:

[0249] The server stores the optimized teaching materials in a database.

[0250] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[0251] Step 9:

[0252] The server sends a notification of the distribution of the teaching material to the terminal.

[0253] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[0254] Step 10:

[0255] Users receive notifications and access the learning materials.

[0256] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[0257] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning. The introduction of an emotion engine provides an optimal learning environment according to the user's emotional state.

[0258] Example 2

[0259] 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."

[0260] Conventional learning systems have difficulty providing learning materials that take into account each learner's level of understanding and emotional state. This has led to issues such as reduced learning efficiency and frequent instances of learner stress. It has also been difficult to reflect the user's progress in real time and provide new learning materials at the optimal timing.

[0261] 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: a means for the user to provide learning data and emotional data; a means for the server to collect and store the user's learning data and emotional data; a means for the server to analyze the collected learning data and emotional data and identify the user's weaknesses; a means for the generation control device to generate and optimize learning materials based on the identified weaknesses and emotional data; and a means for the terminal to deliver the generated learning materials to the user. This makes it possible to provide customized and effective learning materials that take into account the level of understanding and emotional state of each individual learner.

[0262] "User" refers to an individual who uses the learning system.

[0263] "Learning Data" refers to information such as grades and response times provided by users through online tests and learning activities.

[0264] "Emotional data" refers to information collected from a user's facial expressions, tone of voice, and emotions expressed in text.

[0265] "Server" refers to a computer system that collects, stores, and analyzes learning data and emotional data, and issues instructions for generating teaching materials as needed.

[0266] The "generation control device" refers to a device that generates learning materials based on the analysis results of the server.

[0267] "Learning Materials" refers to educational content provided based on a user's weaknesses and learning progress.

[0268] "Terminal" refers to a device (e.g., a smartphone or PC) through which a user accesses learning materials and performs learning activities.

[0269] "Data collection means" refers to the technical means for collecting user learning data and emotion data.

[0270] "Data storage means" refers to the technical means for storing collected training data and emotion data in a database.

[0271] "Data analysis means" refers to the technical means for analyzing the collected data and identifying the user's learning weaknesses and emotional state.

[0272] "Optimization Measures" refers to technological measures for adjusting and optimizing learning materials based on user weaknesses and emotional data.

[0273] "Learning material delivery means" refers to the technical means for delivering the generated and optimized learning materials to the user's terminal.

[0274] "Progress data" refers to information that indicates the user's learning progress and results.

[0275] This invention relates to a system that provides learning materials optimized for each individual learner, and also has a function of recognizing the user's emotions and optimizing the learning materials. Specific embodiments of this system are described below.

[0276] Hardware and Software Configuration

[0277] This system uses the following main hardware and software:

[0278] Hardware

[0279] Server: Collects, stores, and analyzes training data and emotion data. A server with a high-performance CPU and sufficient memory is required.

[0280] Terminal: The device used by the user, such as a smartphone or computer. It is desirable that it has a built-in camera and microphone.

[0281] software

[0282] Database Management System: MySQL is used to store the collected data.

[0283] Data Analysis Module: Performs data analysis using Python and the pandas library.

[0284] Emotion Engine: Includes facial expression recognition and speech analysis algorithms powered by TensorFlow.

[0285] Generative control device: Generates learning materials using OpenAI's GPT model.

[0286] REST API: Used as a communication protocol to deliver educational materials to devices.

[0287] Example

[0288] Data collection

[0289] When a user takes an online test, the device acquires the test results (correct answer rate, answer time, etc.). At the same time, the device's camera and microphone are used to collect emotional data such as the user's facial expression and tone of voice. This data is sent to the server in real time.

[0290] Data storage and analysis

[0291] The server stores the submitted data in a MySQL database. The stored data includes the user ID, test results, answer data for each question, answer time, and emotional data such as facial expressions and tone of voice. The server's data analysis module then analyzes this data to identify the user's weaknesses and emotional state. For example, the data analysis module uses Python and the pandas library to process the data and identify the user's weaknesses in certain topics.

[0292] Teaching material generation and optimization

[0293] The server sends the analysis results in JSON format to the generation controller, which uses OpenAI's GPT model to generate customized learning materials based on the user's weaknesses. The emotion engine then takes the user's emotional data into account to optimize the format and difficulty of the materials. For example, if the user feels stressed during a test, a short relaxation video can be added.

[0294] Teaching material distribution

[0295] The generated learning materials are delivered from the server to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available, and the user can access the delivered materials and begin learning.

[0296] Specific examples

[0297] For example, suppose that User A takes an online math test and gets a 50% success rate and 30 minutes to complete it. Emotional data is collected from facial expressions showing signs of stress during the test. The server analyzes this data and identifies that User A has a weakness in "linear equations." At the same time, taking into account User A's feelings of stress, the generation control device generates learning materials for linear equations, including basic instructional videos, practice problems, and short videos for relaxation. These learning materials are then distributed to User A's device via the server.

[0298] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a personalized and effective learning experience.

[0299] Prompt Sentence Examples

[0300] "Generate learning materials for the following grammar rule: subject-verb agreement" "Create an instructional video for the following math problem: how to solve a linear equation"

[0301] The above is an embodiment of the present invention.

[0302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0303] Step 1: Data collection

[0304] A user takes an online test. For example, when a user takes an online English test, the device collects the test results (80% correct answer rate, 15 minutes to answer). The device also uses a camera and microphone to collect emotional data such as facial expression data (smiling expression) and tone of voice (calm voice). This data is sent to a server using the HTTPS protocol. The input is the test result and emotional data, and the output is the data sent to the server.

[0305] Step 2: Save data

[0306] The server stores the received learning data and emotion data in a database. Specifically, the MySQL database stores user IDs, test results, answer data for each question, answer time, facial expression data, tone of voice, etc. The input is the data sent to the server, and the output is the data stored in the database.

[0307] Step 3: Data analysis

[0308] The server performs data analysis using Python scripts and the pandas library. The analysis module analyzes the test results and emotion data to identify the user's weaknesses (e.g., grammar problems). At the same time, the user's emotions (e.g., they were relaxed during the test) are identified. The input is the data stored in the database, and the output is the analyzed results of the user's weaknesses and emotional state.

[0309] Step 4: Creating educational materials using a generation control device

[0310] The server sends the analysis results in JSON format to the generation control device. The generation control device uses OpenAI's GPT model to generate learning materials that address the user's weaknesses (e.g., grammar). The generated learning materials include basic grammar rules, related example sentences, and practice questions. Based on emotional data, easy-to-understand videos are also added to help users relax and learn. The input is the analysis results, and the output is the generated learning materials.

[0311] Step 5: Distribution of teaching materials

[0312] The server sends the generated learning materials to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning. The input is the generated learning materials, and the output is the learning materials delivered to the device.

[0313] Step 6: Monitoring your learning progress

[0314] The user progresses with their studies using the delivered learning materials. The device collects learning progress data (e.g., learning completion rate, answer time, correct answer rate) and sends it to the server. The server stores this progress data in a database in real time and reanalyzes it using an analysis module. This accumulates the data necessary for generating the next learning material. The input is the learning progress data, and the output is the progress data sent to the server.

[0315] Through these steps, the system can effectively utilize the learning data and emotional data of each individual user to provide optimized learning materials.

[0316] (Application example 2)

[0317] 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."

[0318] Conventional learning systems provide learning materials based solely on the user's learning data, making it difficult to provide an optimal learning experience that takes into account the user's emotional state. Furthermore, because learning materials are not generated or optimized based on emotional aspects such as stress or decreased motivation, it is difficult to maximize individual learning outcomes. Furthermore, there are limitations to the means of providing appropriate reminders to users in real time.

[0319] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0320] In this invention, the server includes a means for users to provide learning data and emotional data, a means for collecting and storing the learning data and emotional data of users, and a means for analyzing the collected data and identifying the weaknesses and emotional state of the users, thereby enabling the generation and optimization of optimal learning materials that take into account not only the learning situation but also the emotional state of the users.

[0321] "Means by which a user provides learning data and emotional data" refers to means including devices and software for collecting information about a user's learning activities and emotional state.

[0322] "Means for the server to collect and store user learning data and emotional data" refers to a system that has the function of receiving learning data and emotional data sent by users and storing them in a database or storage.

[0323] "Means for the server to analyze the collected data and identify the user's weaknesses and emotional state" refers to analytical technology that analyzes the collected learning data and emotional data to identify the areas where the user has difficulty understanding and their mental state.

[0324] "Means for the generation control device to generate and optimize learning materials based on identified weaknesses and emotional state" refers to a device and method that automatically generates optimal learning materials based on the analysis of a user's weaknesses and emotional state, and adjusts them to meet the user's needs.

[0325] "Means for the terminal to deliver the generated learning materials to the user" refers to the communication means or software that transmits the generated learning materials to the user's device and makes them available.

[0326] The present invention is a system that collects and analyzes user learning data and emotional data, and provides optimized learning materials based on the collected data. To realize this system, the following hardware and software are required:

[0327] Hardware and Software Configuration

[0328] 1. User Device

[0329] Camera: Used to collect the user's facial expression data.

[0330] Microphone: Used to collect the user's tone of voice.

[0331] 2. Server

[0332] Database: A storage system for storing user learning data and emotion data.

[0333] Analysis module: Software for analyzing training data and sentiment data, specifically using machine learning libraries such as Scikit-Learn and TensorFlow.

[0334] Generation control device: Software that generates learning materials based on an algorithm and optimizes them according to the user's emotions.

[0335] 3. Communication Network

[0336] Internet: A communications infrastructure for sending and receiving data between user devices and servers.

[0337] System processing overview

[0338] Data collection

[0339] Users provide learning data and emotional data through online tests and learning activities. Specifically, the system collects the user's facial expressions and voice using the camera and microphone on the user's device. This data is sent to the server in real time.

[0340] Data analysis and storage

[0341] The server stores the collected learning data and emotional data in a database. Based on the stored data, the analysis module analyzes the user's learning weaknesses and emotional state. This analysis uses machine learning algorithms and natural language processing techniques.

[0342] Teaching material generation and optimization

[0343] Based on the analysis results, the generation control device generates optimal learning materials according to the user's learning and emotional state. The generated learning materials are provided in a format that is easy for the user to understand (e.g., videos, interactive questions), and the difficulty level is adjusted according to the emotional data.

[0344] Teaching material distribution

[0345] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available and allows the user to access the materials and progress with their studies.

[0346] Specific examples

[0347] For example, if a user takes a math test and facial expression data collected by a camera indicates that the user is stressed, subsequent study materials will be provided in a more understandable format. Similarly, if a user takes an English quiz in a relaxed state, study materials including basic grammar rules and practice questions will be generated.

[0348] Prompt Sentence Examples

[0349] "Please provide Python code that analyzes emotions based on facial expression data when a user takes a math test and generates optimal learning materials."

[0350] This system makes it possible to provide optimal learning materials that take into account the user's learning data and emotional state, resulting in a more effective learning experience.

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Step 1:

[0353] Users use their devices to take online tests and study activities. For example, when taking a math test, the device's camera and microphone are automatically activated to collect facial expression data and tone of voice. This allows learning data (test results) and emotional data (facial expressions and voice) to be collected simultaneously.

[0354] Input: User's learning data (test results), emotion data (facial expression data, voice data)

[0355] Output: Collected raw data (training data, emotion data)

[0356] Step 2:

[0357] The device transmits the collected learning data and emotion data to the server in real time, and the data is transferred to the server via a communication network.

[0358] Input: Collected raw data (training data, emotion data)

[0359] Output: Data sent to the server

[0360] Step 3:

[0361] The server stores the received data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expression data, voice data). Database management software (e.g., MySQL) is used.

[0362] Input: Data sent to the server

[0363] Output: Data stored in the database

[0364] Step 4:

[0365] The server's analysis module retrieves the learning data and emotion data from the database and performs analysis using machine learning algorithms (e.g., Scikit-Learn and TensorFlow) to identify the user's weaknesses (e.g., lack of understanding of linear equations) and emotional state (e.g., stress).

[0366] Input: Data stored in the database

[0367] Output: Analysis results (user weaknesses, emotional state)

[0368] Step 5:

[0369] The generation control device generates learning materials based on the analysis results. The learning materials are designed to address the user's weaknesses, and include, for example, basic explanations of linear equations, videos showing calculation procedures, and applied problems. The difficulty and format of the learning materials are also adjusted based on the user's emotional state.

[0370] Input: Analysis results (user weaknesses, emotional state)

[0371] Output: Generated learning materials

[0372] Step 6:

[0373] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available. The user receives the notification and can access the new learning materials through the device.

[0374] Input: Generated learning materials

[0375] Output: Learning materials delivered to the user's device

[0376] 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.

[0377] 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.

[0378] 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.

[0379] [Second embodiment]

[0380] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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."

[0392] The present invention relates to a system for providing learning materials optimized for each individual learner, and is configured as follows.

[0393] Program processing

[0394] Overall flow

[0395] Users' usual learning activities and tests are collected and analyzed on the server to identify specific weaknesses. The generation control device generates and optimizes learning materials based on the weaknesses. The final generated learning materials are delivered to the user via their device.

[0396] Data collection

[0397] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online math test, the results (correct answer rate, answer time, etc.) are automatically sent from the device to the server.

[0398] Data storage and analysis

[0399] The server receives the collected learning data and stores it in a database. The stored data is analyzed using machine learning algorithms, etc. Through the analysis, for example, "linear equations" may be identified as the user's weakness.

[0400] Teaching material generation

[0401] Based on the analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated learning materials are optimized to suit the user's level of understanding and learning style. For example, learning materials are created that include everything from basic explanations of linear equations to applied problems.

[0402] Teaching material distribution

[0403] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[0404] Specific examples

[0405] For a math test

[0406] 1. Data collection: User A takes an online math test and the results (60% correct answer rate) are sent from the device to the server.

[0407] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User A is identified as having a weakness in the "linear equation."

[0408] 3. Teaching material generation: The generation control device generates teaching materials related to linear equations. For example, it includes "basic explanations, videos of calculation procedures, and applied problems."

[0409] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[0410] For an English quiz

[0411] 1. Data collection: User B takes a short English quiz and the results (40% correct answers on grammar questions) are sent from the device to the server.

[0412] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User B is identified as having a weakness in "grammar."

[0413] 3. Teaching material generation: The generation control device generates grammar teaching materials, such as "basic grammar rules and related exercises."

[0414] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[0415] In this way, the system collects and analyzes users' learning data, generates, optimizes, and delivers learning materials that address specific weaknesses, thereby providing an efficient and effective learning environment.

[0416] The processing flow will be explained below.

[0417] Step 1:

[0418] A user takes an online test.

[0419] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[0420] Step 2:

[0421] The device sends the learning data to the server.

[0422] Immediately after the user completes the test, the device sends the answer data to the server, including the user ID, test type, answer data for each question, and the answer time.

[0423] Step 3:

[0424] The server stores the learning data.

[0425] The server stores the received learning data in a database, which also stores each user's past learning data, making it easy to compare it with new data.

[0426] Step 4:

[0427] The server analyzes the training data.

[0428] The server then uses the stored data to begin analyzing the user. It uses machine learning algorithms to identify the user's weaknesses. Specifically, it creates a list of questions the user answered incorrectly the most or took the most time to answer, and identifies weaknesses related to those topics.

[0429] Step 5:

[0430] A generation control device generates a draft of the teaching material.

[0431] Based on the identified weaknesses, a generative control system uses generative AI to draft learning materials, including basic explanations, examples, and practice questions.

[0432] Step 6:

[0433] The generation control device optimizes the teaching materials.

[0434] Based on the generated draft, the generation control device optimizes the learning materials to suit the user's learning style and level of understanding, specifically adjusting the content according to the user's preferred learning format (text, video, interactive questions, etc.).

[0435] Step 7:

[0436] The server stores the optimized teaching materials in a database.

[0437] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[0438] Step 8:

[0439] The server sends a notification of the distribution of the teaching material to the terminal.

[0440] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[0441] Step 9:

[0442] Users receive notifications and access the learning materials.

[0443] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[0444] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning.

[0445] Example 1

[0446] 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."

[0447] Conventional learning systems have difficulty addressing the individual weaknesses and needs of learners. As a result, learners are forced to use uniform learning materials, which can lead to inefficient learning. Furthermore, existing systems have difficulty providing appropriate reminders and feedback based on learners' progress and level of understanding, which can lead to reduced learning effectiveness.

[0448] 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.

[0449] In this invention, the server includes a learning data collection means, a storage means, and an analysis means, which enables efficient collection, storage, and analysis of user learning data.

[0450] "User" refers to a learner who uses the system to carry out learning activities.

[0451] "Learning Data" refers to results and progress information generated when a user completes a learning activity or test.

[0452] "Server" refers to a computer system that collects, stores, and analyzes learning data and distributes generated learning materials.

[0453] A "generation controller" is a device or process for generating learning materials based on a user's weaknesses.

[0454] A "terminal" is a computer or mobile device that a user uses to perform learning activities.

[0455] A "machine learning algorithm" is a data analysis method used to analyze collected data and identify users' learning patterns and weaknesses.

[0456] A "generative AI model" is an artificial intelligence system that automatically generates learning materials based on specific prompts.

[0457] "Notification function" refers to a function on the terminal that notifies the user that generated learning materials are available.

[0458] "Reminder" is a function that notifies users of their learning progress and what they need to study.

[0459] MODE FOR CARRYING OUT THE INVENTION

[0460] The present invention is a learning support system designed to optimize a user's learning activities. Specific embodiments of the system are described below.

[0461] Hardware and Software Configuration

[0462] Collecting and storing learning data

[0463] Users use learning devices (e.g., personal computers, tablets, smartphones, etc.) to carry out learning activities and take tests. The devices collect learning data (e.g., correct answer rate, answer time, etc.) generated as a result of these activities and send it to a server via the Internet. The server stores this learning data using a database system such as MySQL or PostgreSQL.

[0464] Data analysis

[0465] The server analyzes the stored learning data using Python libraries (e.g., scikit-learn and TensorFlow). This allows the server to apply machine learning algorithms to identify the user's weaknesses. For example, if a user takes an online math test and gets 60% correct, the server will recognize through analysis that "linear equations" is a weak point.

[0466] Teaching material generation

[0467] The server uses a generative controller to generate learning materials based on the identified weaknesses. This generative controller creates learning materials using a generative AI model such as OpenAI's GPT-4. An example of a generation prompt is the input text, "Generate learning materials for beginners on linear equations."

[0468] Teaching material distribution and notifications

[0469] The server delivers the generated learning materials to the user's device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials and begin learning.

[0470] Specific examples

[0471] For a math test

[0472] For example, when User A takes an online math test, the results (e.g., a 60% accuracy rate) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User A's weakness lies in "linear equations." The generation control device then uses a generative AI model such as GPT-4 to generate learning materials related to linear equations. These learning materials include basic explanations, videos showing calculation procedures, and applied problems. The generated learning materials are distributed from the server to User A's device, and notifications are sent via Firebase Cloud Messaging. User A then uses the learning materials distributed via the device to continue their studies.

[0473] For an English quiz

[0474] Furthermore, when User B takes an English quiz, the results (for example, a 40% accuracy rate on grammar questions) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User B's weakness lies in "grammar." The generation control device then uses a generative AI model such as GPT-4 to generate grammar-related learning materials. These learning materials include basic grammar rules and related practice questions. The generated learning materials are distributed from the server to User B's device, and User B is notified via a notification function. User B uses the distributed learning materials to study.

[0475] This invention provides an efficient and effective learning environment by collecting, storing, and analyzing user learning data, and generating and delivering learning materials based on identified weaknesses.

[0476] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0477] Step 1: Data collection

[0478] The user uses the device to carry out learning activities and tests. For example, they take an online math test. The test results (number of correct answers, answering time, etc.) are generated. The device processes these results and sends them to the server as learning data.

[0479] Input: User test results (number of correct answers, answer time, etc.)

[0480] Data processing: Formatting test results as training data

[0481] Output: Learning data is sent to the server. Specific operation: The device automatically compiles the test results and calls an API that sends them to the server.

[0482] Step 2: Save data

[0483] The server stores the learning data received from the device in a database, using a database management system such as MySQL or PostgreSQL.

[0484] Input: Training data sent from the device

[0485] Data processing: Converting training data into a format that can be stored in a database

[0486] Output: The training data is saved in the database. Specific operation: The server adds the received data to the corresponding table in the database.

[0487] Step 3: Data analysis

[0488] The server analyzes the saved learning data and identifies the user's weaknesses using machine learning libraries such as Python's scikit-learn and TensorFlow. For example, if the user's accuracy rate for "linear equations" is low, this will be identified as the user's weakness.

[0489] Input: Training data stored in a database

[0490] Data processing: Applying machine learning algorithms to identify user weaknesses

[0491] Output: The result of identifying the user's weaknesses is obtained. Specific operation: The server reads the learning data from the database and applies the machine learning algorithm to identify the user's weaknesses.

[0492] Step 4: Creating teaching materials

[0493] The server uses a generative controller to generate learning materials based on the identified weaknesses. This generation process uses a generative AI model, such as OpenAI's GPT-4. Example prompt: "Generate learning materials for beginners on linear equations."

[0494] Input: User weakness identification results, prompt text

[0495] Data processing: Using generative AI models to generate learning materials

[0496] Output: Generated learning materials. Specific operation: The generation control device inputs a prompt sentence into the generation AI model and obtains the generated learning materials.

[0497] Step 5: Distribution of teaching materials

[0498] The server delivers the generated learning materials to the device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials through the device and begin learning.

[0499] Input: Generated learning materials

[0500] Data processing: Converting educational materials into a delivery format

[0501] Output: The teaching materials are delivered to the terminal and the user is notified. Specific operation: The server sends the generated teaching materials to the terminal and notifies the user through the notification function.

[0502] (Application example 1)

[0503] 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."

[0504] To improve the efficiency and accuracy of robot operations in factories, it is necessary to provide individually optimized training programs for each robot. However, currently, it is difficult to effectively analyze robot operation data and quickly generate appropriate training programs. Furthermore, there is a lack of a system for delivering appropriate training programs to robots in a timely manner and improving their operational performance. This poses the issue of reduced efficiency across the production line and increased risk of breakdowns.

[0505] 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.

[0506] In this invention, the server includes a means for collecting and storing robot operation data, a means for analyzing the collected data and identifying the robot's weaknesses, a generation control device for generating a training program based on the identified weaknesses, and a terminal for distributing the generated training program to the robot. This makes it possible to quickly provide a training program optimized for each robot in order to effectively improve the efficiency and accuracy of the robot's operation.

[0507] "User" refers to an individual or organization that uses the system and provides learning data.

[0508] A "server" is an electronic computing device that stores and analyzes data collected from users and robots.

[0509] "Learning data" refers to data generated by users through learning activities and tests.

[0510] A "generation control device" is a device that generates learning materials and training programs based on the results of analysis by the server.

[0511] A "terminal" is a device through which a user or robot receives learning materials and training programs.

[0512] "Operational data" refers to performance data such as the speed, accuracy, and work height of a factory robot.

[0513] "Weaknesses" are challenges or shortcomings that the user or robot must overcome as a result of data analysis.

[0514] A "training program" is training content created to improve the robot's movement performance.

[0515] "Reminders" are information about learning and training progress that the server notifies the user and robot.

[0516] The system that realizes this invention collects and analyzes user learning data and factory robot operation data, and based on that, generates and distributes optimal teaching materials and training programs. A specific implementation method is shown below.

[0517] Data collection

[0518] When users take online tests or study activities, learning data (e.g., accuracy rate, answer time, etc.) is generated and sent to a server via their devices. Similarly, operational data (speed, accuracy, work height, etc.) of factory robots is collected in real time via sensors and sent to a server. The hardware used includes network-connected PCs and tablets, as well as sensors (e.g., LiDAR, cameras) mounted on factory robots.

[0519] Data storage and analysis

[0520] The server stores the received learning data and operation data in a database. The stored data is analyzed using machine learning algorithms. Specifically, the data is analyzed using scalable cloud storage (e.g., Amazon S3) and a data analysis platform (e.g., Apache Spark). As a result of the analysis, weaknesses in the user's learning and problems with the factory robot's operation are identified. For example, it may be identified that the user has a weakness in "linear equations" or that the robot's speed performance is low.

[0521] Creation of educational materials and training programs

[0522] Based on the analysis results, a generation control device on the server generates optimal learning materials and training programs. Specifically, learning materials and training programs are generated using Python and provided to users and robots. For example, learning materials on linear equations are generated to include video explanations and application problems. Also, a training program to improve the robot's speed is generated.

[0523] Delivery of educational materials and training programs

[0524] The generated learning materials and training programs are distributed from the server to the user's device or robot. The user or robot receives the materials and programs and carries out the learning or training. Notification services (e.g., Firebase) and reminder functions are used to manage notifications and learning progress.

[0525] Specific examples

[0526] For example, if User A takes an online math test and gets 60% correct, the data is sent to the server and analyzed. As a result, linear equations are identified as a weak point. The generation control device generates optimal teaching materials for linear equations (basic explanations, videos showing calculation procedures, and applied problems) and delivers them to User A's device.

[0527] Furthermore, if the operational data of a factory robot is analyzed and it is determined that the speed performance is low, the production control device will generate a training program to improve the speed and distribute it to the robot.

[0528] Examples of prompt statements

[0529] "Collect operational data (speed, accuracy, work height) of factory robots and analyze their weaknesses through clustering. Based on the analysis results, create a training program to compensate for specific weaknesses and distribute it to the robot."

[0530] In this way, the system can quickly and effectively provide educational materials and training programs optimized for each user and robot.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] Users generate learning data through online tests and learning activities. This data includes, for example, the percentage of correct answers and the time it takes to answer. The device transmits this data to the server in real time. The input is the learning data generated by the user, and the output is the learning data transmitted to the server.

[0534] Step 2:

[0535] The server receives the training data sent from the device and stores it in a database. Specifically, it stores the data using an SQL server or NoSQL database. The input is the training data sent from the device, and the output is the stored training data.

[0536] Step 3:

[0537] The server analyzes the stored training data using a machine learning algorithm. The specific operation here is to normalize the data and apply a specific algorithm (e.g., clustering) to identify the user's weaknesses. The input is the stored training data, and the output is the analysis result (the user's weaknesses).

[0538] Step 4:

[0539] The generation control device in the server generates learning materials based on the analysis results. Specifically, it uses Python to generate learning materials from templates and customizes the content according to the user's level of understanding and interests. The input is the analysis results, and the output is the generated learning materials.

[0540] Step 5:

[0541] The server delivers the generated learning materials to the device. Specifically, it uses a cloud notification service (e.g., Firebase) to notify the user that new learning materials are available. The input is the generated learning materials, and the output is the learning materials delivered to the user's device and the notification.

[0542] Step 6:

[0543] The terminal notifies the user that new learning materials are available, and the user accesses the delivered materials to study. Specific operations include displaying the materials through a user interface and managing how the user progresses with their learning activities. The input is the delivered learning materials, and the output is the user's learning activity data.

[0544] Step 7:

[0545] For factory robots, the robot's operational data (speed, accuracy, work height, etc.) is collected through sensors and sent to a server. The input is the robot's operational data, and the output is the operational data sent to the server.

[0546] Step 8:

[0547] The server receives the robot's motion data and stores it in the database in the same way as the training data. The input is the robot's motion data, and the output is the stored motion data.

[0548] Step 9:

[0549] The server analyzes the stored robot's motion data and identifies the robot's weaknesses. The input is the stored motion data, and the output is the analysis result (the robot's motion weaknesses).

[0550] Step 10:

[0551] The generation control device generates a training program for the robot based on the analysis results. Specifically, it automatically generates training content for specific weaknesses and puts it into program format. The input is the analysis results, and the output is the generated training program.

[0552] Step 11:

[0553] The server distributes the generated training program to the robot. The input is the generated training program, and the output is the training program distributed to the robot.

[0554] Step 12:

[0555] The robot automatically begins training based on the received training program to improve its performance. Specifically, it modifies its movements according to the training program to improve its performance. The input is the delivered training program, and the output is the robot's improved performance.

[0556] 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.

[0557] The present invention relates to a system for providing learning materials optimized for each individual learner, and also has a function for recognizing the user's emotions and optimizing the learning materials. Specific embodiments of the system are described below.

[0558] Program processing

[0559] Overall flow

[0560] Users provide learning data through online tests and learning activities. Based on that data, the server analyzes specific weaknesses, and the generation control device generates and optimizes learning materials. An emotion engine is also incorporated to optimize learning materials based on the user's emotions. Finally, the generated learning materials are delivered to the user via their device.

[0561] Data collection

[0562] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online English test, emotional data is collected using the device's camera and microphone along with the results (correct answer rate, answer time, etc.). This data is sent from the device to a server.

[0563] Data storage and analysis

[0564] The server stores the collected learning data and emotional data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expressions, tone of voice, and text-based emotional expressions). The stored data is analyzed by an analysis module on the server. Based on the analysis results, topics and subjects that are the user's weaknesses are identified.

[0565] Teaching material generation and optimization

[0566] Based on the server's analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated materials include custom content tailored to the user's level of understanding and learning style. Furthermore, emotional data collected by the emotion engine is also used. For example, optimizations are made, such as providing a format that is easy for the user to understand (videos, interactive questions, etc.) or adjusting the difficulty level if the user is suspected to be stressed.

[0567] Teaching material distribution

[0568] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[0569] Specific examples

[0570] Mathematics testing and emotional data collection

[0571] 1. Data collection: User A takes an online math test, and the results (50% correct answer rate) and emotional data (facial expression data captured by a camera) are sent from the device to the server. The emotional data suggests that User A may be frustrated during the test.

[0572] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User A has a weakness in "linear equations" and that he was frustrated during the test.

[0573] 3. Teaching material generation and optimization: The generation control device generates teaching materials related to linear equations. For example, it may include "basic explanations, videos showing calculation procedures, and applied problems." The difficulty level of the teaching materials is adjusted based on the emotion data, and they are provided in a format that is easy for User A to understand.

[0574] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[0575] English quiz and emotional data collection

[0576] 1. Data collection: User B takes a short English quiz, and the results (40% correct answer rate for grammar questions) and emotional data (tone of voice recorded by a microphone) are sent from the device to the server. The emotional data suggests that User B is relaxed and engaged in studying.

[0577] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User B has weaknesses in "grammar" and is able to study in a relaxed state.

[0578] 3. Learning material generation and optimization: The generation control device generates grammar learning materials, including basic grammar rules and related exercises. Based on emotional data, the content is provided in a way that makes it easy to learn in a relaxed state.

[0579] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[0580] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a more personalized learning experience and create an efficient and effective learning environment.

[0581] The processing flow will be explained below.

[0582] Step 1:

[0583] A user takes an online test.

[0584] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[0585] Step 2:

[0586] The device collects emotional data.

[0587] During the online test, the device collects emotional data such as the user's facial expressions and tone of voice. For example, the camera recognizes the user's facial expressions and the microphone analyzes the tone of voice.

[0588] Step 3:

[0589] The device sends the learning data and emotion data to the server.

[0590] Immediately after the user completes the test, the device sends the answer data and collected emotion data to the server, including the user ID, test type, answer data, answer time, and emotion data.

[0591] Step 4:

[0592] The server stores the training data and emotion data.

[0593] The server stores the received training data and emotion data in a database, which also stores each user's past training data and emotion data, making it easy to compare with new data.

[0594] Step 5:

[0595] The server analyzes the training data and emotion data.

[0596] The server then begins analysis using the stored learning data and emotional data. Using machine learning algorithms, it identifies the user's weaknesses and evaluates their emotional state. For example, it can list questions on which the user got the most answers wrong or took the longest time, identify weaknesses related to those topics, and evaluate the user's emotional state during the test.

[0597] Step 6:

[0598] A generation control device generates a draft of the teaching material.

[0599] Based on the identified weaknesses, the generation control device uses generative AI to create draft learning materials, including basic explanations, examples, and practice questions.

[0600] Step 7:

[0601] The generation control device optimizes the teaching materials based on the emotion data.

[0602] Based on the generated draft, the generation control device optimizes the learning materials based on the user's learning style, level of comprehension, and emotional data. For example, if the user feels stressed during a test, the difficulty level of the learning materials will be adjusted.

[0603] Step 8:

[0604] The server stores the optimized teaching materials in a database.

[0605] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[0606] Step 9:

[0607] The server sends a notification of the distribution of the teaching material to the terminal.

[0608] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[0609] Step 10:

[0610] Users receive notifications and access the learning materials.

[0611] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[0612] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning. The introduction of an emotion engine provides an optimal learning environment according to the user's emotional state.

[0613] Example 2

[0614] 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."

[0615] Conventional learning systems have difficulty providing learning materials that take into account each learner's level of understanding and emotional state. This has led to issues such as reduced learning efficiency and frequent instances of learner stress. It has also been difficult to reflect the user's progress in real time and provide new learning materials at the optimal timing.

[0616] 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: a means for the user to provide learning data and emotional data; a means for the server to collect and store the user's learning data and emotional data; a means for the server to analyze the collected learning data and emotional data and identify the user's weaknesses; a means for the generation control device to generate and optimize learning materials based on the identified weaknesses and emotional data; and a means for the terminal to deliver the generated learning materials to the user. This makes it possible to provide customized and effective learning materials that take into account the level of understanding and emotional state of each individual learner.

[0617] "User" refers to an individual who uses the learning system.

[0618] "Learning Data" refers to information such as grades and response times provided by users through online tests and learning activities.

[0619] "Emotional data" refers to information collected from a user's facial expressions, tone of voice, and emotions expressed in text.

[0620] "Server" refers to a computer system that collects, stores, and analyzes learning data and emotional data, and issues instructions for generating teaching materials as needed.

[0621] The "generation control device" refers to a device that generates learning materials based on the analysis results of the server.

[0622] "Learning Materials" refers to educational content provided based on a user's weaknesses and learning progress.

[0623] "Terminal" refers to a device (e.g., a smartphone or PC) through which a user accesses learning materials and performs learning activities.

[0624] "Data collection means" refers to the technical means for collecting user learning data and emotion data.

[0625] "Data storage means" refers to the technical means for storing collected training data and emotion data in a database.

[0626] "Data analysis means" refers to the technical means for analyzing the collected data and identifying the user's learning weaknesses and emotional state.

[0627] "Optimization Measures" refers to technological measures for adjusting and optimizing learning materials based on user weaknesses and emotional data.

[0628] "Learning material delivery means" refers to the technical means for delivering the generated and optimized learning materials to the user's terminal.

[0629] "Progress data" refers to information that indicates the user's learning progress and results.

[0630] This invention relates to a system that provides learning materials optimized for each individual learner, and also has a function of recognizing the user's emotions and optimizing the learning materials. Specific embodiments of this system are described below.

[0631] Hardware and Software Configuration

[0632] This system uses the following main hardware and software:

[0633] Hardware

[0634] Server: Collects, stores, and analyzes training data and emotion data. A server with a high-performance CPU and sufficient memory is required.

[0635] Terminal: The device used by the user, such as a smartphone or computer. It is desirable that it has a built-in camera and microphone.

[0636] software

[0637] Database Management System: MySQL is used to store the collected data.

[0638] Data Analysis Module: Performs data analysis using Python and the pandas library.

[0639] Emotion Engine: Includes facial expression recognition and speech analysis algorithms powered by TensorFlow.

[0640] Generative control device: Generates learning materials using OpenAI's GPT model.

[0641] REST API: Used as a communication protocol to deliver educational materials to devices.

[0642] Example

[0643] Data collection

[0644] When a user takes an online test, the device acquires the test results (correct answer rate, answer time, etc.). At the same time, the device's camera and microphone are used to collect emotional data such as the user's facial expression and tone of voice. This data is sent to the server in real time.

[0645] Data storage and analysis

[0646] The server stores the submitted data in a MySQL database. The stored data includes the user ID, test results, answer data for each question, answer time, and emotional data such as facial expressions and tone of voice. The server's data analysis module then analyzes this data to identify the user's weaknesses and emotional state. For example, the data analysis module uses Python and the pandas library to process the data and identify the user's weaknesses in certain topics.

[0647] Teaching material generation and optimization

[0648] The server sends the analysis results in JSON format to the generation controller, which uses OpenAI's GPT model to generate customized learning materials based on the user's weaknesses. The emotion engine then takes the user's emotional data into account to optimize the format and difficulty of the materials. For example, if the user feels stressed during a test, a short relaxation video can be added.

[0649] Teaching material distribution

[0650] The generated learning materials are delivered from the server to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available, and the user can access the delivered materials and begin learning.

[0651] Specific examples

[0652] For example, suppose that User A takes an online math test and gets a 50% success rate and 30 minutes to complete it. Emotional data is collected from facial expressions showing signs of stress during the test. The server analyzes this data and identifies that User A has a weakness in "linear equations." At the same time, taking into account User A's feelings of stress, the generation control device generates learning materials for linear equations, including basic instructional videos, practice problems, and short videos for relaxation. These learning materials are then distributed to User A's device via the server.

[0653] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a personalized and effective learning experience.

[0654] Prompt Sentence Examples

[0655] "Generate learning materials for the following grammar rule: subject-verb agreement" "Create an instructional video for the following math problem: how to solve a linear equation"

[0656] The above is an embodiment of the present invention.

[0657] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0658] Step 1: Data collection

[0659] A user takes an online test. For example, when a user takes an online English test, the device collects the test results (80% correct answer rate, 15 minutes to answer). The device also uses a camera and microphone to collect emotional data such as facial expression data (smiling expression) and tone of voice (calm voice). This data is sent to a server using the HTTPS protocol. The input is the test result and emotional data, and the output is the data sent to the server.

[0660] Step 2: Save data

[0661] The server stores the received learning data and emotion data in a database. Specifically, the MySQL database stores user IDs, test results, answer data for each question, answer time, facial expression data, tone of voice, etc. The input is the data sent to the server, and the output is the data stored in the database.

[0662] Step 3: Data analysis

[0663] The server performs data analysis using Python scripts and the pandas library. The analysis module analyzes the test results and emotion data to identify the user's weaknesses (e.g., grammar problems). At the same time, the user's emotions (e.g., they were relaxed during the test) are identified. The input is the data stored in the database, and the output is the analyzed results of the user's weaknesses and emotional state.

[0664] Step 4: Creating educational materials using a generation control device

[0665] The server sends the analysis results in JSON format to the generation control device. The generation control device uses OpenAI's GPT model to generate learning materials that address the user's weaknesses (e.g., grammar). The generated learning materials include basic grammar rules, related example sentences, and practice questions. Based on emotional data, easy-to-understand videos are also added to help users relax and learn. The input is the analysis results, and the output is the generated learning materials.

[0666] Step 5: Distribution of teaching materials

[0667] The server sends the generated learning materials to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning. The input is the generated learning materials, and the output is the learning materials delivered to the device.

[0668] Step 6: Monitoring your learning progress

[0669] The user progresses with their studies using the delivered learning materials. The device collects learning progress data (e.g., learning completion rate, answer time, correct answer rate) and sends it to the server. The server stores this progress data in a database in real time and reanalyzes it using an analysis module. This accumulates the data necessary for generating the next learning material. The input is the learning progress data, and the output is the progress data sent to the server.

[0670] Through these steps, the system can effectively utilize the learning data and emotional data of each individual user to provide optimized learning materials.

[0671] (Application example 2)

[0672] 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."

[0673] Conventional learning systems provide learning materials based solely on the user's learning data, making it difficult to provide an optimal learning experience that takes into account the user's emotional state. Furthermore, because learning materials are not generated or optimized based on emotional aspects such as stress or decreased motivation, it is difficult to maximize individual learning outcomes. Furthermore, there are limitations to the means of providing appropriate reminders to users in real time.

[0674] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0675] In this invention, the server includes a means for users to provide learning data and emotional data, a means for collecting and storing the learning data and emotional data of users, and a means for analyzing the collected data and identifying the weaknesses and emotional state of the users, thereby enabling the generation and optimization of optimal learning materials that take into account not only the learning situation but also the emotional state of the users.

[0676] "Means by which a user provides learning data and emotional data" refers to means including devices and software for collecting information about a user's learning activities and emotional state.

[0677] "Means for the server to collect and store user learning data and emotional data" refers to a system that has the function of receiving learning data and emotional data sent by users and storing them in a database or storage.

[0678] "Means for the server to analyze the collected data and identify the user's weaknesses and emotional state" refers to analytical technology that analyzes the collected learning data and emotional data to identify the areas where the user has difficulty understanding and their mental state.

[0679] "Means for the generation control device to generate and optimize learning materials based on identified weaknesses and emotional state" refers to a device and method that automatically generates optimal learning materials based on the analysis of a user's weaknesses and emotional state, and adjusts them to meet the user's needs.

[0680] "Means for the terminal to deliver the generated learning materials to the user" refers to the communication means or software that transmits the generated learning materials to the user's device and makes them available.

[0681] The present invention is a system that collects and analyzes user learning data and emotional data, and provides optimized learning materials based on the collected data. To realize this system, the following hardware and software are required:

[0682] Hardware and Software Configuration

[0683] 1. User Device

[0684] Camera: Used to collect the user's facial expression data.

[0685] Microphone: Used to collect the user's tone of voice.

[0686] 2. Server

[0687] Database: A storage system for storing user learning data and emotion data.

[0688] Analysis module: Software for analyzing training data and sentiment data, specifically using machine learning libraries such as Scikit-Learn and TensorFlow.

[0689] Generation control device: Software that generates learning materials based on an algorithm and optimizes them according to the user's emotions.

[0690] 3. Communication Network

[0691] Internet: A communications infrastructure for sending and receiving data between user devices and servers.

[0692] System processing overview

[0693] Data collection

[0694] Users provide learning data and emotional data through online tests and learning activities. Specifically, the system collects the user's facial expressions and voice using the camera and microphone on the user's device. This data is sent to the server in real time.

[0695] Data analysis and storage

[0696] The server stores the collected learning data and emotional data in a database. Based on the stored data, the analysis module analyzes the user's learning weaknesses and emotional state. This analysis uses machine learning algorithms and natural language processing techniques.

[0697] Teaching material generation and optimization

[0698] Based on the analysis results, the generation control device generates optimal learning materials according to the user's learning and emotional state. The generated learning materials are provided in a format that is easy for the user to understand (e.g., videos, interactive questions), and the difficulty level is adjusted according to the emotional data.

[0699] Teaching material distribution

[0700] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available and allows the user to access the materials and progress with their studies.

[0701] Specific examples

[0702] For example, if a user takes a math test and facial expression data collected by a camera indicates that the user is stressed, subsequent study materials will be provided in a more understandable format. Similarly, if a user takes an English quiz in a relaxed state, study materials including basic grammar rules and practice questions will be generated.

[0703] Prompt Sentence Examples

[0704] "Please provide Python code that analyzes emotions based on facial expression data when a user takes a math test and generates optimal learning materials."

[0705] This system makes it possible to provide optimal learning materials that take into account the user's learning data and emotional state, resulting in a more effective learning experience.

[0706] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0707] Step 1:

[0708] Users use their devices to take online tests and study activities. For example, when taking a math test, the device's camera and microphone are automatically activated to collect facial expression data and tone of voice. This allows learning data (test results) and emotional data (facial expressions and voice) to be collected simultaneously.

[0709] Input: User's learning data (test results), emotion data (facial expression data, voice data)

[0710] Output: Collected raw data (training data, emotion data)

[0711] Step 2:

[0712] The device transmits the collected learning data and emotion data to the server in real time, and the data is transferred to the server via a communication network.

[0713] Input: Collected raw data (training data, emotion data)

[0714] Output: Data sent to the server

[0715] Step 3:

[0716] The server stores the received data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expression data, voice data). Database management software (e.g., MySQL) is used.

[0717] Input: Data sent to the server

[0718] Output: Data stored in the database

[0719] Step 4:

[0720] The server's analysis module retrieves the learning data and emotion data from the database and performs analysis using machine learning algorithms (e.g., Scikit-Learn and TensorFlow) to identify the user's weaknesses (e.g., lack of understanding of linear equations) and emotional state (e.g., stress).

[0721] Input: Data stored in the database

[0722] Output: Analysis results (user weaknesses, emotional state)

[0723] Step 5:

[0724] The generation control device generates learning materials based on the analysis results. The learning materials are designed to address the user's weaknesses, and include, for example, basic explanations of linear equations, videos showing calculation procedures, and applied problems. The difficulty and format of the learning materials are also adjusted based on the user's emotional state.

[0725] Input: Analysis results (user weaknesses, emotional state)

[0726] Output: Generated learning materials

[0727] Step 6:

[0728] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available. The user receives the notification and can access the new learning materials through the device.

[0729] Input: Generated learning materials

[0730] Output: Learning materials delivered to the user's device

[0731] 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.

[0732] 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.

[0733] 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.

[0734] [Third embodiment]

[0735] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0736] 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.

[0737] 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).

[0738] 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.

[0739] 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.

[0740] 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).

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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."

[0747] The present invention relates to a system for providing learning materials optimized for each individual learner, and is configured as follows.

[0748] Program processing

[0749] Overall flow

[0750] Users' usual learning activities and tests are collected and analyzed on the server to identify specific weaknesses. The generation control device generates and optimizes learning materials based on the weaknesses. The final generated learning materials are delivered to the user via their device.

[0751] Data collection

[0752] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online math test, the results (correct answer rate, answer time, etc.) are automatically sent from the device to the server.

[0753] Data storage and analysis

[0754] The server receives the collected learning data and stores it in a database. The stored data is analyzed using machine learning algorithms, etc. Through the analysis, for example, "linear equations" may be identified as the user's weakness.

[0755] Teaching material generation

[0756] Based on the analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated learning materials are optimized to suit the user's level of understanding and learning style. For example, learning materials are created that include everything from basic explanations of linear equations to applied problems.

[0757] Teaching material distribution

[0758] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[0759] Specific examples

[0760] For a math test

[0761] 1. Data collection: User A takes an online math test and the results (60% correct answer rate) are sent from the device to the server.

[0762] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User A is identified as having a weakness in the "linear equation."

[0763] 3. Teaching material generation: The generation control device generates teaching materials related to linear equations. For example, it includes "basic explanations, videos of calculation procedures, and applied problems."

[0764] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[0765] For an English quiz

[0766] 1. Data collection: User B takes a short English quiz and the results (40% correct answers on grammar questions) are sent from the device to the server.

[0767] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User B is identified as having a weakness in "grammar."

[0768] 3. Teaching material generation: The generation control device generates grammar teaching materials, such as "basic grammar rules and related exercises."

[0769] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[0770] In this way, the system collects and analyzes users' learning data, generates, optimizes, and delivers learning materials that address specific weaknesses, thereby providing an efficient and effective learning environment.

[0771] The processing flow will be explained below.

[0772] Step 1:

[0773] A user takes an online test.

[0774] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[0775] Step 2:

[0776] The device sends the learning data to the server.

[0777] Immediately after the user completes the test, the device sends the answer data to the server, including the user ID, test type, answer data for each question, and the answer time.

[0778] Step 3:

[0779] The server stores the learning data.

[0780] The server stores the received learning data in a database, which also stores each user's past learning data, making it easy to compare it with new data.

[0781] Step 4:

[0782] The server analyzes the training data.

[0783] The server then uses the stored data to begin analyzing the user. It uses machine learning algorithms to identify the user's weaknesses. Specifically, it creates a list of questions the user answered incorrectly the most or took the most time to answer, and identifies weaknesses related to those topics.

[0784] Step 5:

[0785] A generation control device generates a draft of the teaching material.

[0786] Based on the identified weaknesses, a generative control system uses generative AI to draft learning materials, including basic explanations, examples, and practice questions.

[0787] Step 6:

[0788] The generation control device optimizes the teaching materials.

[0789] Based on the generated draft, the generation control device optimizes the learning materials to suit the user's learning style and level of understanding, specifically adjusting the content according to the user's preferred learning format (text, video, interactive questions, etc.).

[0790] Step 7:

[0791] The server stores the optimized teaching materials in a database.

[0792] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[0793] Step 8:

[0794] The server sends a notification of the distribution of the teaching material to the terminal.

[0795] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[0796] Step 9:

[0797] Users receive notifications and access the learning materials.

[0798] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[0799] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning.

[0800] Example 1

[0801] 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."

[0802] Conventional learning systems have difficulty addressing the individual weaknesses and needs of learners. As a result, learners are forced to use uniform learning materials, which can lead to inefficient learning. Furthermore, existing systems have difficulty providing appropriate reminders and feedback based on learners' progress and level of understanding, which can lead to reduced learning effectiveness.

[0803] 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.

[0804] In this invention, the server includes a learning data collection means, a storage means, and an analysis means, which enables efficient collection, storage, and analysis of user learning data.

[0805] "User" refers to a learner who uses the system to carry out learning activities.

[0806] "Learning Data" refers to results and progress information generated when a user completes a learning activity or test.

[0807] "Server" refers to a computer system that collects, stores, and analyzes learning data and distributes generated learning materials.

[0808] A "generation controller" is a device or process for generating learning materials based on a user's weaknesses.

[0809] A "terminal" is a computer or mobile device that a user uses to perform learning activities.

[0810] A "machine learning algorithm" is a data analysis method used to analyze collected data and identify users' learning patterns and weaknesses.

[0811] A "generative AI model" is an artificial intelligence system that automatically generates learning materials based on specific prompts.

[0812] "Notification function" refers to a function on the terminal that notifies the user that generated learning materials are available.

[0813] "Reminder" is a function that notifies users of their learning progress and what they need to study.

[0814] MODE FOR CARRYING OUT THE INVENTION

[0815] The present invention is a learning support system designed to optimize a user's learning activities. Specific embodiments of the system are described below.

[0816] Hardware and Software Configuration

[0817] Collecting and storing learning data

[0818] Users use learning devices (e.g., personal computers, tablets, smartphones, etc.) to carry out learning activities and take tests. The devices collect learning data (e.g., correct answer rate, answer time, etc.) generated as a result of these activities and send it to a server via the Internet. The server stores this learning data using a database system such as MySQL or PostgreSQL.

[0819] Data analysis

[0820] The server analyzes the stored learning data using Python libraries (e.g., scikit-learn and TensorFlow). This allows the server to apply machine learning algorithms to identify the user's weaknesses. For example, if a user takes an online math test and gets 60% correct, the server will recognize through analysis that "linear equations" is a weak point.

[0821] Teaching material generation

[0822] The server uses a generative controller to generate learning materials based on the identified weaknesses. This generative controller creates learning materials using a generative AI model such as OpenAI's GPT-4. An example of a generation prompt is the input text, "Generate learning materials for beginners on linear equations."

[0823] Teaching material distribution and notifications

[0824] The server delivers the generated learning materials to the user's device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials and begin learning.

[0825] Specific examples

[0826] For a math test

[0827] For example, when User A takes an online math test, the results (e.g., a 60% accuracy rate) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User A's weakness lies in "linear equations." The generation control device then uses a generative AI model such as GPT-4 to generate learning materials related to linear equations. These learning materials include basic explanations, videos showing calculation procedures, and applied problems. The generated learning materials are distributed from the server to User A's device, and notifications are sent via Firebase Cloud Messaging. User A then uses the learning materials distributed via the device to continue their studies.

[0828] For an English quiz

[0829] Furthermore, when User B takes an English quiz, the results (for example, a 40% accuracy rate on grammar questions) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User B's weakness lies in "grammar." The generation control device then uses a generative AI model such as GPT-4 to generate grammar-related learning materials. These learning materials include basic grammar rules and related practice questions. The generated learning materials are distributed from the server to User B's device, and User B is notified via a notification function. User B uses the distributed learning materials to study.

[0830] This invention provides an efficient and effective learning environment by collecting, storing, and analyzing user learning data, and generating and delivering learning materials based on identified weaknesses.

[0831] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0832] Step 1: Data collection

[0833] The user uses the device to carry out learning activities and tests. For example, they take an online math test. The test results (number of correct answers, answering time, etc.) are generated. The device processes these results and sends them to the server as learning data.

[0834] Input: User test results (number of correct answers, answer time, etc.)

[0835] Data processing: Formatting test results as training data

[0836] Output: Learning data is sent to the server. Specific operation: The device automatically compiles the test results and calls an API that sends them to the server.

[0837] Step 2: Save data

[0838] The server stores the learning data received from the device in a database, using a database management system such as MySQL or PostgreSQL.

[0839] Input: Training data sent from the device

[0840] Data processing: Converting training data into a format that can be stored in a database

[0841] Output: The training data is saved in the database. Specific operation: The server adds the received data to the corresponding table in the database.

[0842] Step 3: Data analysis

[0843] The server analyzes the saved learning data and identifies the user's weaknesses using machine learning libraries such as Python's scikit-learn and TensorFlow. For example, if the user's accuracy rate for "linear equations" is low, this will be identified as the user's weakness.

[0844] Input: Training data stored in a database

[0845] Data processing: Applying machine learning algorithms to identify user weaknesses

[0846] Output: The result of identifying the user's weaknesses is obtained. Specific operation: The server reads the learning data from the database and applies the machine learning algorithm to identify the user's weaknesses.

[0847] Step 4: Creating teaching materials

[0848] The server uses a generative controller to generate learning materials based on the identified weaknesses. This generation process uses a generative AI model, such as OpenAI's GPT-4. Example prompt: "Generate learning materials for beginners on linear equations."

[0849] Input: User weakness identification results, prompt text

[0850] Data processing: Using generative AI models to generate learning materials

[0851] Output: Generated learning materials. Specific operation: The generation control device inputs a prompt sentence into the generation AI model and obtains the generated learning materials.

[0852] Step 5: Distribution of teaching materials

[0853] The server delivers the generated learning materials to the device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials through the device and begin learning.

[0854] Input: Generated learning materials

[0855] Data processing: Converting educational materials into a delivery format

[0856] Output: The teaching materials are delivered to the terminal and the user is notified. Specific operation: The server sends the generated teaching materials to the terminal and notifies the user through the notification function.

[0857] (Application example 1)

[0858] 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."

[0859] To improve the efficiency and accuracy of robot operations in factories, it is necessary to provide individually optimized training programs for each robot. However, currently, it is difficult to effectively analyze robot operation data and quickly generate appropriate training programs. Furthermore, there is a lack of a system for delivering appropriate training programs to robots in a timely manner and improving their operational performance. This poses the issue of reduced efficiency across the production line and increased risk of breakdowns.

[0860] 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.

[0861] In this invention, the server includes a means for collecting and storing robot operation data, a means for analyzing the collected data and identifying the robot's weaknesses, a generation control device for generating a training program based on the identified weaknesses, and a terminal for distributing the generated training program to the robot. This makes it possible to quickly provide a training program optimized for each robot in order to effectively improve the efficiency and accuracy of the robot's operation.

[0862] "User" refers to an individual or organization that uses the system and provides learning data.

[0863] A "server" is an electronic computing device that stores and analyzes data collected from users and robots.

[0864] "Learning data" refers to data generated by users through learning activities and tests.

[0865] A "generation control device" is a device that generates learning materials and training programs based on the results of analysis by the server.

[0866] A "terminal" is a device through which a user or robot receives learning materials and training programs.

[0867] "Operational data" refers to performance data such as the speed, accuracy, and work height of a factory robot.

[0868] "Weaknesses" are challenges or shortcomings that the user or robot must overcome as a result of data analysis.

[0869] A "training program" is training content created to improve the robot's movement performance.

[0870] "Reminders" are information about learning and training progress that the server notifies the user and robot.

[0871] The system that realizes this invention collects and analyzes user learning data and factory robot operation data, and based on that, generates and distributes optimal teaching materials and training programs. A specific implementation method is shown below.

[0872] Data collection

[0873] When users take online tests or study activities, learning data (e.g., accuracy rate, answer time, etc.) is generated and sent to a server via their devices. Similarly, operational data (speed, accuracy, work height, etc.) of factory robots is collected in real time via sensors and sent to a server. The hardware used includes network-connected PCs and tablets, as well as sensors (e.g., LiDAR, cameras) mounted on factory robots.

[0874] Data storage and analysis

[0875] The server stores the received learning data and operation data in a database. The stored data is analyzed using machine learning algorithms. Specifically, the data is analyzed using scalable cloud storage (e.g., Amazon S3) and a data analysis platform (e.g., Apache Spark). As a result of the analysis, weaknesses in the user's learning and problems with the factory robot's operation are identified. For example, it may be identified that the user has a weakness in "linear equations" or that the robot's speed performance is low.

[0876] Creation of educational materials and training programs

[0877] Based on the analysis results, a generation control device on the server generates optimal learning materials and training programs. Specifically, learning materials and training programs are generated using Python and provided to users and robots. For example, learning materials on linear equations are generated to include video explanations and application problems. Also, a training program to improve the robot's speed is generated.

[0878] Delivery of educational materials and training programs

[0879] The generated learning materials and training programs are distributed from the server to the user's device or robot. The user or robot receives the materials and programs and carries out the learning or training. Notification services (e.g., Firebase) and reminder functions are used to manage notifications and learning progress.

[0880] Specific examples

[0881] For example, if User A takes an online math test and gets 60% correct, the data is sent to the server and analyzed. As a result, linear equations are identified as a weak point. The generation control device generates optimal teaching materials for linear equations (basic explanations, videos showing calculation procedures, and applied problems) and delivers them to User A's device.

[0882] Furthermore, if the operational data of a factory robot is analyzed and it is determined that the speed performance is low, the production control device will generate a training program to improve the speed and distribute it to the robot.

[0883] Examples of prompt statements

[0884] "Collect operational data (speed, accuracy, work height) of factory robots and analyze their weaknesses through clustering. Based on the analysis results, create a training program to compensate for specific weaknesses and distribute it to the robot."

[0885] In this way, the system can quickly and effectively provide educational materials and training programs optimized for each user and robot.

[0886] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0887] Step 1:

[0888] Users generate learning data through online tests and learning activities. This data includes, for example, the percentage of correct answers and the time it takes to answer. The device transmits this data to the server in real time. The input is the learning data generated by the user, and the output is the learning data transmitted to the server.

[0889] Step 2:

[0890] The server receives the training data sent from the device and stores it in a database. Specifically, it stores the data using an SQL server or NoSQL database. The input is the training data sent from the device, and the output is the stored training data.

[0891] Step 3:

[0892] The server analyzes the stored training data using a machine learning algorithm. The specific operation here is to normalize the data and apply a specific algorithm (e.g., clustering) to identify the user's weaknesses. The input is the stored training data, and the output is the analysis result (the user's weaknesses).

[0893] Step 4:

[0894] The generation control device in the server generates learning materials based on the analysis results. Specifically, it uses Python to generate learning materials from templates and customizes the content according to the user's level of understanding and interests. The input is the analysis results, and the output is the generated learning materials.

[0895] Step 5:

[0896] The server delivers the generated learning materials to the device. Specifically, it uses a cloud notification service (e.g., Firebase) to notify the user that new learning materials are available. The input is the generated learning materials, and the output is the learning materials delivered to the user's device and the notification.

[0897] Step 6:

[0898] The terminal notifies the user that new learning materials are available, and the user accesses the delivered materials to study. Specific operations include displaying the materials through a user interface and managing how the user progresses with their learning activities. The input is the delivered learning materials, and the output is the user's learning activity data.

[0899] Step 7:

[0900] For factory robots, the robot's operational data (speed, accuracy, work height, etc.) is collected through sensors and sent to a server. The input is the robot's operational data, and the output is the operational data sent to the server.

[0901] Step 8:

[0902] The server receives the robot's motion data and stores it in the database in the same way as the training data. The input is the robot's motion data, and the output is the stored motion data.

[0903] Step 9:

[0904] The server analyzes the stored robot's motion data and identifies the robot's weaknesses. The input is the stored motion data, and the output is the analysis result (the robot's motion weaknesses).

[0905] Step 10:

[0906] The generation control device generates a training program for the robot based on the analysis results. Specifically, it automatically generates training content for specific weaknesses and puts it into program format. The input is the analysis results, and the output is the generated training program.

[0907] Step 11:

[0908] The server distributes the generated training program to the robot. The input is the generated training program, and the output is the training program distributed to the robot.

[0909] Step 12:

[0910] The robot automatically begins training based on the received training program to improve its performance. Specifically, it modifies its movements according to the training program to improve its performance. The input is the delivered training program, and the output is the robot's improved performance.

[0911] 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.

[0912] The present invention relates to a system for providing learning materials optimized for each individual learner, and also has a function for recognizing the user's emotions and optimizing the learning materials. Specific embodiments of the system are described below.

[0913] Program processing

[0914] Overall flow

[0915] Users provide learning data through online tests and learning activities. Based on that data, the server analyzes specific weaknesses, and the generation control device generates and optimizes learning materials. An emotion engine is also incorporated to optimize learning materials based on the user's emotions. Finally, the generated learning materials are delivered to the user via their device.

[0916] Data collection

[0917] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online English test, emotional data is collected using the device's camera and microphone along with the results (correct answer rate, answer time, etc.). This data is sent from the device to a server.

[0918] Data storage and analysis

[0919] The server stores the collected learning data and emotional data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expressions, tone of voice, and text-based emotional expressions). The stored data is analyzed by an analysis module on the server. Based on the analysis results, topics and subjects that are the user's weaknesses are identified.

[0920] Teaching material generation and optimization

[0921] Based on the server's analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated materials include custom content tailored to the user's level of understanding and learning style. Furthermore, emotional data collected by the emotion engine is also used. For example, optimizations are made, such as providing a format that is easy for the user to understand (videos, interactive questions, etc.) or adjusting the difficulty level if the user is suspected to be stressed.

[0922] Teaching material distribution

[0923] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[0924] Specific examples

[0925] Mathematics testing and emotional data collection

[0926] 1. Data collection: User A takes an online math test, and the results (50% correct answer rate) and emotional data (facial expression data captured by a camera) are sent from the device to the server. The emotional data suggests that User A may be frustrated during the test.

[0927] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User A has a weakness in "linear equations" and that he was frustrated during the test.

[0928] 3. Teaching material generation and optimization: The generation control device generates teaching materials related to linear equations. For example, it may include "basic explanations, videos showing calculation procedures, and applied problems." The difficulty level of the teaching materials is adjusted based on the emotion data, and they are provided in a format that is easy for User A to understand.

[0929] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[0930] English quiz and emotional data collection

[0931] 1. Data collection: User B takes a short English quiz, and the results (40% correct answer rate for grammar questions) and emotional data (tone of voice recorded by a microphone) are sent from the device to the server. The emotional data suggests that User B is relaxed and engaged in studying.

[0932] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User B has weaknesses in "grammar" and is able to study in a relaxed state.

[0933] 3. Learning material generation and optimization: The generation control device generates grammar learning materials, including basic grammar rules and related exercises. Based on emotional data, the content is provided in a way that makes it easy to learn in a relaxed state.

[0934] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[0935] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a more personalized learning experience and create an efficient and effective learning environment.

[0936] The processing flow will be explained below.

[0937] Step 1:

[0938] A user takes an online test.

[0939] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[0940] Step 2:

[0941] The device collects emotional data.

[0942] During the online test, the device collects emotional data such as the user's facial expressions and tone of voice. For example, the camera recognizes the user's facial expressions and the microphone analyzes the tone of voice.

[0943] Step 3:

[0944] The device sends the learning data and emotion data to the server.

[0945] Immediately after the user completes the test, the device sends the answer data and collected emotion data to the server, including the user ID, test type, answer data, answer time, and emotion data.

[0946] Step 4:

[0947] The server stores the training data and emotion data.

[0948] The server stores the received training data and emotion data in a database, which also stores each user's past training data and emotion data, making it easy to compare with new data.

[0949] Step 5:

[0950] The server analyzes the training data and emotion data.

[0951] The server then begins analysis using the stored learning data and emotional data. Using machine learning algorithms, it identifies the user's weaknesses and evaluates their emotional state. For example, it can list questions on which the user got the most answers wrong or took the longest time, identify weaknesses related to those topics, and evaluate the user's emotional state during the test.

[0952] Step 6:

[0953] A generation control device generates a draft of the teaching material.

[0954] Based on the identified weaknesses, the generation control device uses generative AI to create draft learning materials, including basic explanations, examples, and practice questions.

[0955] Step 7:

[0956] The generation control device optimizes the teaching materials based on the emotion data.

[0957] Based on the generated draft, the generation control device optimizes the learning materials based on the user's learning style, level of comprehension, and emotional data. For example, if the user feels stressed during a test, the difficulty level of the learning materials will be adjusted.

[0958] Step 8:

[0959] The server stores the optimized teaching materials in a database.

[0960] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[0961] Step 9:

[0962] The server sends a notification of the distribution of the teaching material to the terminal.

[0963] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[0964] Step 10:

[0965] Users receive notifications and access the learning materials.

[0966] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[0967] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning. The introduction of an emotion engine provides an optimal learning environment according to the user's emotional state.

[0968] Example 2

[0969] 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."

[0970] Conventional learning systems have difficulty providing learning materials that take into account each learner's level of understanding and emotional state. This has led to issues such as reduced learning efficiency and frequent instances of learner stress. It has also been difficult to reflect the user's progress in real time and provide new learning materials at the optimal timing.

[0971] 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: a means for the user to provide learning data and emotional data; a means for the server to collect and store the user's learning data and emotional data; a means for the server to analyze the collected learning data and emotional data and identify the user's weaknesses; a means for the generation control device to generate and optimize learning materials based on the identified weaknesses and emotional data; and a means for the terminal to deliver the generated learning materials to the user. This makes it possible to provide customized and effective learning materials that take into account the level of understanding and emotional state of each individual learner.

[0972] "User" refers to an individual who uses the learning system.

[0973] "Learning Data" refers to information such as grades and response times provided by users through online tests and learning activities.

[0974] "Emotional data" refers to information collected from a user's facial expressions, tone of voice, and emotions expressed in text.

[0975] "Server" refers to a computer system that collects, stores, and analyzes learning data and emotional data, and issues instructions for generating teaching materials as needed.

[0976] The "generation control device" refers to a device that generates learning materials based on the analysis results of the server.

[0977] "Learning Materials" refers to educational content provided based on a user's weaknesses and learning progress.

[0978] "Terminal" refers to a device (e.g., a smartphone or PC) through which a user accesses learning materials and performs learning activities.

[0979] "Data collection means" refers to the technical means for collecting user learning data and emotion data.

[0980] "Data storage means" refers to the technical means for storing collected training data and emotion data in a database.

[0981] "Data analysis means" refers to the technical means for analyzing the collected data and identifying the user's learning weaknesses and emotional state.

[0982] "Optimization Measures" refers to technological measures for adjusting and optimizing learning materials based on user weaknesses and emotional data.

[0983] "Learning material delivery means" refers to the technical means for delivering the generated and optimized learning materials to the user's terminal.

[0984] "Progress data" refers to information that indicates the user's learning progress and results.

[0985] This invention relates to a system that provides learning materials optimized for each individual learner, and also has a function of recognizing the user's emotions and optimizing the learning materials. Specific embodiments of this system are described below.

[0986] Hardware and Software Configuration

[0987] This system uses the following main hardware and software:

[0988] Hardware

[0989] Server: Collects, stores, and analyzes training data and emotion data. A server with a high-performance CPU and sufficient memory is required.

[0990] Terminal: The device used by the user, such as a smartphone or computer. It is desirable that it has a built-in camera and microphone.

[0991] software

[0992] Database Management System: MySQL is used to store the collected data.

[0993] Data Analysis Module: Performs data analysis using Python and the pandas library.

[0994] Emotion Engine: Includes facial expression recognition and speech analysis algorithms powered by TensorFlow.

[0995] Generative control device: Generates learning materials using OpenAI's GPT model.

[0996] REST API: Used as a communication protocol to deliver educational materials to devices.

[0997] Example

[0998] Data collection

[0999] When a user takes an online test, the device acquires the test results (correct answer rate, answer time, etc.). At the same time, the device's camera and microphone are used to collect emotional data such as the user's facial expression and tone of voice. This data is sent to the server in real time.

[1000] Data storage and analysis

[1001] The server stores the submitted data in a MySQL database. The stored data includes the user ID, test results, answer data for each question, answer time, and emotional data such as facial expressions and tone of voice. The server's data analysis module then analyzes this data to identify the user's weaknesses and emotional state. For example, the data analysis module uses Python and the pandas library to process the data and identify the user's weaknesses in certain topics.

[1002] Teaching material generation and optimization

[1003] The server sends the analysis results in JSON format to the generation controller, which uses OpenAI's GPT model to generate customized learning materials based on the user's weaknesses. The emotion engine then takes the user's emotional data into account to optimize the format and difficulty of the materials. For example, if the user feels stressed during a test, a short relaxation video can be added.

[1004] Teaching material distribution

[1005] The generated learning materials are delivered from the server to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available, and the user can access the delivered materials and begin learning.

[1006] Specific examples

[1007] For example, suppose that User A takes an online math test and gets a 50% success rate and 30 minutes to complete it. Emotional data is collected from facial expressions showing signs of stress during the test. The server analyzes this data and identifies that User A has a weakness in "linear equations." At the same time, taking into account User A's feelings of stress, the generation control device generates learning materials for linear equations, including basic instructional videos, practice problems, and short videos for relaxation. These learning materials are then distributed to User A's device via the server.

[1008] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a personalized and effective learning experience.

[1009] Prompt Sentence Examples

[1010] "Generate learning materials for the following grammar rule: subject-verb agreement" "Create an instructional video for the following math problem: how to solve a linear equation"

[1011] The above is an embodiment of the present invention.

[1012] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1013] Step 1: Data collection

[1014] A user takes an online test. For example, when a user takes an online English test, the device collects the test results (80% correct answer rate, 15 minutes to answer). The device also uses a camera and microphone to collect emotional data such as facial expression data (smiling expression) and tone of voice (calm voice). This data is sent to a server using the HTTPS protocol. The input is the test result and emotional data, and the output is the data sent to the server.

[1015] Step 2: Save data

[1016] The server stores the received learning data and emotion data in a database. Specifically, the MySQL database stores user IDs, test results, answer data for each question, answer time, facial expression data, tone of voice, etc. The input is the data sent to the server, and the output is the data stored in the database.

[1017] Step 3: Data analysis

[1018] The server performs data analysis using Python scripts and the pandas library. The analysis module analyzes the test results and emotion data to identify the user's weaknesses (e.g., grammar problems). At the same time, the user's emotions (e.g., they were relaxed during the test) are identified. The input is the data stored in the database, and the output is the analyzed results of the user's weaknesses and emotional state.

[1019] Step 4: Creating educational materials using a generation control device

[1020] The server sends the analysis results in JSON format to the generation control device. The generation control device uses OpenAI's GPT model to generate learning materials that address the user's weaknesses (e.g., grammar). The generated learning materials include basic grammar rules, related example sentences, and practice questions. Based on emotional data, easy-to-understand videos are also added to help users relax and learn. The input is the analysis results, and the output is the generated learning materials.

[1021] Step 5: Distribution of teaching materials

[1022] The server sends the generated learning materials to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning. The input is the generated learning materials, and the output is the learning materials delivered to the device.

[1023] Step 6: Monitoring your learning progress

[1024] The user progresses with their studies using the delivered learning materials. The device collects learning progress data (e.g., learning completion rate, answer time, correct answer rate) and sends it to the server. The server stores this progress data in a database in real time and reanalyzes it using an analysis module. This accumulates the data necessary for generating the next learning material. The input is the learning progress data, and the output is the progress data sent to the server.

[1025] Through these steps, the system can effectively utilize the learning data and emotional data of each individual user to provide optimized learning materials.

[1026] (Application example 2)

[1027] 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."

[1028] Conventional learning systems provide learning materials based solely on the user's learning data, making it difficult to provide an optimal learning experience that takes into account the user's emotional state. Furthermore, because learning materials are not generated or optimized based on emotional aspects such as stress or decreased motivation, it is difficult to maximize individual learning outcomes. Furthermore, there are limitations to the means of providing appropriate reminders to users in real time.

[1029] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1030] In this invention, the server includes a means for users to provide learning data and emotional data, a means for collecting and storing the learning data and emotional data of users, and a means for analyzing the collected data and identifying the weaknesses and emotional state of the users, thereby enabling the generation and optimization of optimal learning materials that take into account not only the learning situation but also the emotional state of the users.

[1031] "Means by which a user provides learning data and emotional data" refers to means including devices and software for collecting information about a user's learning activities and emotional state.

[1032] "Means for the server to collect and store user learning data and emotional data" refers to a system that has the function of receiving learning data and emotional data sent by users and storing them in a database or storage.

[1033] "Means for the server to analyze the collected data and identify the user's weaknesses and emotional state" refers to analytical technology that analyzes the collected learning data and emotional data to identify the areas where the user has difficulty understanding and their mental state.

[1034] "Means for the generation control device to generate and optimize learning materials based on identified weaknesses and emotional state" refers to a device and method that automatically generates optimal learning materials based on the analysis of a user's weaknesses and emotional state, and adjusts them to meet the user's needs.

[1035] "Means for the terminal to deliver the generated learning materials to the user" refers to the communication means or software that transmits the generated learning materials to the user's device and makes them available.

[1036] The present invention is a system that collects and analyzes user learning data and emotional data, and provides optimized learning materials based on the collected data. To realize this system, the following hardware and software are required:

[1037] Hardware and Software Configuration

[1038] 1. User Device

[1039] Camera: Used to collect the user's facial expression data.

[1040] Microphone: Used to collect the user's tone of voice.

[1041] 2. Server

[1042] Database: A storage system for storing user learning data and emotion data.

[1043] Analysis module: Software for analyzing training data and sentiment data, specifically using machine learning libraries such as Scikit-Learn and TensorFlow.

[1044] Generation control device: Software that generates learning materials based on an algorithm and optimizes them according to the user's emotions.

[1045] 3. Communication Network

[1046] Internet: A communications infrastructure for sending and receiving data between user devices and servers.

[1047] System processing overview

[1048] Data collection

[1049] Users provide learning data and emotional data through online tests and learning activities. Specifically, the system collects the user's facial expressions and voice using the camera and microphone on the user's device. This data is sent to the server in real time.

[1050] Data analysis and storage

[1051] The server stores the collected learning data and emotional data in a database. Based on the stored data, the analysis module analyzes the user's learning weaknesses and emotional state. This analysis uses machine learning algorithms and natural language processing techniques.

[1052] Teaching material generation and optimization

[1053] Based on the analysis results, the generation control device generates optimal learning materials according to the user's learning and emotional state. The generated learning materials are provided in a format that is easy for the user to understand (e.g., videos, interactive questions), and the difficulty level is adjusted according to the emotional data.

[1054] Teaching material distribution

[1055] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available and allows the user to access the materials and progress with their studies.

[1056] Specific examples

[1057] For example, if a user takes a math test and facial expression data collected by a camera indicates that the user is stressed, subsequent study materials will be provided in a more understandable format. Similarly, if a user takes an English quiz in a relaxed state, study materials including basic grammar rules and practice questions will be generated.

[1058] Prompt Sentence Examples

[1059] "Please provide Python code that analyzes emotions based on facial expression data when a user takes a math test and generates optimal learning materials."

[1060] This system makes it possible to provide optimal learning materials that take into account the user's learning data and emotional state, resulting in a more effective learning experience.

[1061] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1062] Step 1:

[1063] Users use their devices to take online tests and study activities. For example, when taking a math test, the device's camera and microphone are automatically activated to collect facial expression data and tone of voice. This allows learning data (test results) and emotional data (facial expressions and voice) to be collected simultaneously.

[1064] Input: User's learning data (test results), emotion data (facial expression data, voice data)

[1065] Output: Collected raw data (training data, emotion data)

[1066] Step 2:

[1067] The device transmits the collected learning data and emotion data to the server in real time, and the data is transferred to the server via a communication network.

[1068] Input: Collected raw data (training data, emotion data)

[1069] Output: Data sent to the server

[1070] Step 3:

[1071] The server stores the received data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expression data, voice data). Database management software (e.g., MySQL) is used.

[1072] Input: Data sent to the server

[1073] Output: Data stored in the database

[1074] Step 4:

[1075] The server's analysis module retrieves the learning data and emotion data from the database and performs analysis using machine learning algorithms (e.g., Scikit-Learn and TensorFlow) to identify the user's weaknesses (e.g., lack of understanding of linear equations) and emotional state (e.g., stress).

[1076] Input: Data stored in the database

[1077] Output: Analysis results (user weaknesses, emotional state)

[1078] Step 5:

[1079] The generation control device generates learning materials based on the analysis results. The learning materials are designed to address the user's weaknesses, and include, for example, basic explanations of linear equations, videos showing calculation procedures, and applied problems. The difficulty and format of the learning materials are also adjusted based on the user's emotional state.

[1080] Input: Analysis results (user weaknesses, emotional state)

[1081] Output: Generated learning materials

[1082] Step 6:

[1083] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available. The user receives the notification and can access the new learning materials through the device.

[1084] Input: Generated learning materials

[1085] Output: Learning materials delivered to the user's device

[1086] 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.

[1087] 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.

[1088] 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.

[1089] [Fourth embodiment]

[1090] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1091] 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.

[1092] 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).

[1093] 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.

[1094] 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.

[1095] 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).

[1096] 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.

[1097] 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.

[1098] 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.

[1099] 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.

[1100] 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.

[1101] 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.

[1102] 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."

[1103] The present invention relates to a system for providing learning materials optimized for each individual learner, and is configured as follows.

[1104] Program processing

[1105] Overall flow

[1106] Users' usual learning activities and tests are collected and analyzed on the server to identify specific weaknesses. The generation control device generates and optimizes learning materials based on the weaknesses. The final generated learning materials are delivered to the user via their device.

[1107] Data collection

[1108] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online math test, the results (correct answer rate, answer time, etc.) are automatically sent from the device to the server.

[1109] Data storage and analysis

[1110] The server receives the collected learning data and stores it in a database. The stored data is analyzed using machine learning algorithms, etc. Through the analysis, for example, "linear equations" may be identified as the user's weakness.

[1111] Teaching material generation

[1112] Based on the analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated learning materials are optimized to suit the user's level of understanding and learning style. For example, learning materials are created that include everything from basic explanations of linear equations to applied problems.

[1113] Teaching material distribution

[1114] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[1115] Specific examples

[1116] For a math test

[1117] 1. Data collection: User A takes an online math test and the results (60% correct answer rate) are sent from the device to the server.

[1118] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User A is identified as having a weakness in the "linear equation."

[1119] 3. Teaching material generation: The generation control device generates teaching materials related to linear equations. For example, it includes "basic explanations, videos of calculation procedures, and applied problems."

[1120] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[1121] For an English quiz

[1122] 1. Data collection: User B takes a short English quiz and the results (40% correct answers on grammar questions) are sent from the device to the server.

[1123] 2. Data storage and analysis: The server stores and analyzes the transmitted data. As a result, User B is identified as having a weakness in "grammar."

[1124] 3. Teaching material generation: The generation control device generates grammar teaching materials, such as "basic grammar rules and related exercises."

[1125] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[1126] In this way, the system collects and analyzes users' learning data, generates, optimizes, and delivers learning materials that address specific weaknesses, thereby providing an efficient and effective learning environment.

[1127] The processing flow will be explained below.

[1128] Step 1:

[1129] A user takes an online test.

[1130] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[1131] Step 2:

[1132] The device sends the learning data to the server.

[1133] Immediately after the user completes the test, the device sends the answer data to the server, including the user ID, test type, answer data for each question, and the answer time.

[1134] Step 3:

[1135] The server stores the learning data.

[1136] The server stores the received learning data in a database, which also stores each user's past learning data, making it easy to compare it with new data.

[1137] Step 4:

[1138] The server analyzes the training data.

[1139] The server then uses the stored data to begin analyzing the user. It uses machine learning algorithms to identify the user's weaknesses. Specifically, it creates a list of questions the user answered incorrectly the most or took the most time to answer, and identifies weaknesses related to those topics.

[1140] Step 5:

[1141] A generation control device generates a draft of the teaching material.

[1142] Based on the identified weaknesses, a generative control system uses generative AI to draft learning materials, including basic explanations, examples, and practice questions.

[1143] Step 6:

[1144] The generation control device optimizes the teaching materials.

[1145] Based on the generated draft, the generation control device optimizes the learning materials to suit the user's learning style and level of understanding, specifically adjusting the content according to the user's preferred learning format (text, video, interactive questions, etc.).

[1146] Step 7:

[1147] The server stores the optimized teaching materials in a database.

[1148] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[1149] Step 8:

[1150] The server sends a notification of the distribution of the teaching material to the terminal.

[1151] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[1152] Step 9:

[1153] Users receive notifications and access the learning materials.

[1154] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[1155] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning.

[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 robot 414 will be referred to as a "terminal."

[1158] Conventional learning systems have difficulty addressing the individual weaknesses and needs of learners. As a result, learners are forced to use uniform learning materials, which can lead to inefficient learning. Furthermore, existing systems have difficulty providing appropriate reminders and feedback based on learners' progress and level of understanding, which can lead to reduced learning effectiveness.

[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 learning data collection means, a storage means, and an analysis means, which enables efficient collection, storage, and analysis of user learning data.

[1161] "User" refers to a learner who uses the system to carry out learning activities.

[1162] "Learning Data" refers to results and progress information generated when a user completes a learning activity or test.

[1163] "Server" refers to a computer system that collects, stores, and analyzes learning data and distributes generated learning materials.

[1164] A "generation controller" is a device or process for generating learning materials based on a user's weaknesses.

[1165] A "terminal" is a computer or mobile device that a user uses to perform learning activities.

[1166] A "machine learning algorithm" is a data analysis method used to analyze collected data and identify users' learning patterns and weaknesses.

[1167] A "generative AI model" is an artificial intelligence system that automatically generates learning materials based on specific prompts.

[1168] "Notification function" refers to a function on the terminal that notifies the user that generated learning materials are available.

[1169] "Reminder" is a function that notifies users of their learning progress and what they need to study.

[1170] MODE FOR CARRYING OUT THE INVENTION

[1171] The present invention is a learning support system designed to optimize a user's learning activities. Specific embodiments of the system are described below.

[1172] Hardware and Software Configuration

[1173] Collecting and storing learning data

[1174] Users use learning devices (e.g., personal computers, tablets, smartphones, etc.) to carry out learning activities and take tests. The devices collect learning data (e.g., correct answer rate, answer time, etc.) generated as a result of these activities and send it to a server via the Internet. The server stores this learning data using a database system such as MySQL or PostgreSQL.

[1175] Data analysis

[1176] The server analyzes the stored learning data using Python libraries (e.g., scikit-learn and TensorFlow). This allows the server to apply machine learning algorithms to identify the user's weaknesses. For example, if a user takes an online math test and gets 60% correct, the server will recognize through analysis that "linear equations" is a weak point.

[1177] Teaching material generation

[1178] The server uses a generative controller to generate learning materials based on the identified weaknesses. This generative controller creates learning materials using a generative AI model such as OpenAI's GPT-4. An example of a generation prompt is the input text, "Generate learning materials for beginners on linear equations."

[1179] Teaching material distribution and notifications

[1180] The server delivers the generated learning materials to the user's device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials and begin learning.

[1181] Specific examples

[1182] For a math test

[1183] For example, when User A takes an online math test, the results (e.g., a 60% accuracy rate) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User A's weakness lies in "linear equations." The generation control device then uses a generative AI model such as GPT-4 to generate learning materials related to linear equations. These learning materials include basic explanations, videos showing calculation procedures, and applied problems. The generated learning materials are distributed from the server to User A's device, and notifications are sent via Firebase Cloud Messaging. User A then uses the learning materials distributed via the device to continue their studies.

[1184] For an English quiz

[1185] Furthermore, when User B takes an English quiz, the results (for example, a 40% accuracy rate on grammar questions) are sent from the device to the server. The server saves and analyzes this data. As a result, it is determined that User B's weakness lies in "grammar." The generation control device then uses a generative AI model such as GPT-4 to generate grammar-related learning materials. These learning materials include basic grammar rules and related practice questions. The generated learning materials are distributed from the server to User B's device, and User B is notified via a notification function. User B uses the distributed learning materials to study.

[1186] This invention provides an efficient and effective learning environment by collecting, storing, and analyzing user learning data, and generating and delivering learning materials based on identified weaknesses.

[1187] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1188] Step 1: Data collection

[1189] The user uses the device to carry out learning activities and tests. For example, they take an online math test. The test results (number of correct answers, answering time, etc.) are generated. The device processes these results and sends them to the server as learning data.

[1190] Input: User test results (number of correct answers, answer time, etc.)

[1191] Data processing: Formatting test results as training data

[1192] Output: Learning data is sent to the server. Specific operation: The device automatically compiles the test results and calls an API that sends them to the server.

[1193] Step 2: Save data

[1194] The server stores the learning data received from the device in a database, using a database management system such as MySQL or PostgreSQL.

[1195] Input: Training data sent from the device

[1196] Data processing: Converting training data into a format that can be stored in a database

[1197] Output: The training data is saved in the database. Specific operation: The server adds the received data to the corresponding table in the database.

[1198] Step 3: Data analysis

[1199] The server analyzes the saved learning data and identifies the user's weaknesses using machine learning libraries such as Python's scikit-learn and TensorFlow. For example, if the user's accuracy rate for "linear equations" is low, this will be identified as the user's weakness.

[1200] Input: Training data stored in a database

[1201] Data processing: Applying machine learning algorithms to identify user weaknesses

[1202] Output: The result of identifying the user's weaknesses is obtained. Specific operation: The server reads the learning data from the database and applies the machine learning algorithm to identify the user's weaknesses.

[1203] Step 4: Creating teaching materials

[1204] The server uses a generative controller to generate learning materials based on the identified weaknesses. This generation process uses a generative AI model, such as OpenAI's GPT-4. Example prompt: "Generate learning materials for beginners on linear equations."

[1205] Input: User weakness identification results, prompt text

[1206] Data processing: Using generative AI models to generate learning materials

[1207] Output: Generated learning materials. Specific operation: The generation control device inputs a prompt sentence into the generation AI model and obtains the generated learning materials.

[1208] Step 5: Distribution of teaching materials

[1209] The server delivers the generated learning materials to the device, which then uses a push notification feature such as Firebase Cloud Messaging to notify the user that new learning materials are available. The user can then access the delivered learning materials through the device and begin learning.

[1210] Input: Generated learning materials

[1211] Data processing: Converting educational materials into a delivery format

[1212] Output: The teaching materials are delivered to the terminal and the user is notified. Specific operation: The server sends the generated teaching materials to the terminal and notifies the user through the notification function.

[1213] (Application example 1)

[1214] 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."

[1215] To improve the efficiency and accuracy of robot operations in factories, it is necessary to provide individually optimized training programs for each robot. However, currently, it is difficult to effectively analyze robot operation data and quickly generate appropriate training programs. Furthermore, there is a lack of a system for delivering appropriate training programs to robots in a timely manner and improving their operational performance. This poses the issue of reduced efficiency across the production line and increased risk of breakdowns.

[1216] 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.

[1217] In this invention, the server includes a means for collecting and storing robot operation data, a means for analyzing the collected data and identifying the robot's weaknesses, a generation control device for generating a training program based on the identified weaknesses, and a terminal for distributing the generated training program to the robot. This makes it possible to quickly provide a training program optimized for each robot in order to effectively improve the efficiency and accuracy of the robot's operation.

[1218] "User" refers to an individual or organization that uses the system and provides learning data.

[1219] A "server" is an electronic computing device that stores and analyzes data collected from users and robots.

[1220] "Learning data" refers to data generated by users through learning activities and tests.

[1221] A "generation control device" is a device that generates learning materials and training programs based on the results of analysis by the server.

[1222] A "terminal" is a device through which a user or robot receives learning materials and training programs.

[1223] "Operational data" refers to performance data such as the speed, accuracy, and work height of a factory robot.

[1224] "Weaknesses" are challenges or shortcomings that the user or robot must overcome as a result of data analysis.

[1225] A "training program" is training content created to improve the robot's movement performance.

[1226] "Reminders" are information about learning and training progress that the server notifies the user and robot.

[1227] The system that realizes this invention collects and analyzes user learning data and factory robot operation data, and based on that, generates and distributes optimal teaching materials and training programs. A specific implementation method is shown below.

[1228] Data collection

[1229] When users take online tests or study activities, learning data (e.g., accuracy rate, answer time, etc.) is generated and sent to a server via their devices. Similarly, operational data (speed, accuracy, work height, etc.) of factory robots is collected in real time via sensors and sent to a server. The hardware used includes network-connected PCs and tablets, as well as sensors (e.g., LiDAR, cameras) mounted on factory robots.

[1230] Data storage and analysis

[1231] The server stores the received learning data and operation data in a database. The stored data is analyzed using machine learning algorithms. Specifically, the data is analyzed using scalable cloud storage (e.g., Amazon S3) and a data analysis platform (e.g., Apache Spark). As a result of the analysis, weaknesses in the user's learning and problems with the factory robot's operation are identified. For example, it may be identified that the user has a weakness in "linear equations" or that the robot's speed performance is low.

[1232] Creation of educational materials and training programs

[1233] Based on the analysis results, a generation control device on the server generates optimal learning materials and training programs. Specifically, learning materials and training programs are generated using Python and provided to users and robots. For example, learning materials on linear equations are generated to include video explanations and application problems. Also, a training program to improve the robot's speed is generated.

[1234] Delivery of educational materials and training programs

[1235] The generated learning materials and training programs are distributed from the server to the user's device or robot. The user or robot receives the materials and programs and carries out the learning or training. Notification services (e.g., Firebase) and reminder functions are used to manage notifications and learning progress.

[1236] Specific examples

[1237] For example, if User A takes an online math test and gets 60% correct, the data is sent to the server and analyzed. As a result, linear equations are identified as a weak point. The generation control device generates optimal teaching materials for linear equations (basic explanations, videos showing calculation procedures, and applied problems) and delivers them to User A's device.

[1238] Furthermore, if the operational data of a factory robot is analyzed and it is determined that the speed performance is low, the production control device will generate a training program to improve the speed and distribute it to the robot.

[1239] Examples of prompt statements

[1240] "Collect operational data (speed, accuracy, work height) of factory robots and analyze their weaknesses through clustering. Based on the analysis results, create a training program to compensate for specific weaknesses and distribute it to the robot."

[1241] In this way, the system can quickly and effectively provide educational materials and training programs optimized for each user and robot.

[1242] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1243] Step 1:

[1244] Users generate learning data through online tests and learning activities. This data includes, for example, the percentage of correct answers and the time it takes to answer. The device transmits this data to the server in real time. The input is the learning data generated by the user, and the output is the learning data transmitted to the server.

[1245] Step 2:

[1246] The server receives the training data sent from the device and stores it in a database. Specifically, it stores the data using an SQL server or NoSQL database. The input is the training data sent from the device, and the output is the stored training data.

[1247] Step 3:

[1248] The server analyzes the stored training data using a machine learning algorithm. The specific operation here is to normalize the data and apply a specific algorithm (e.g., clustering) to identify the user's weaknesses. The input is the stored training data, and the output is the analysis result (the user's weaknesses).

[1249] Step 4:

[1250] The generation control device in the server generates learning materials based on the analysis results. Specifically, it uses Python to generate learning materials from templates and customizes the content according to the user's level of understanding and interests. The input is the analysis results, and the output is the generated learning materials.

[1251] Step 5:

[1252] The server delivers the generated learning materials to the device. Specifically, it uses a cloud notification service (e.g., Firebase) to notify the user that new learning materials are available. The input is the generated learning materials, and the output is the learning materials delivered to the user's device and the notification.

[1253] Step 6:

[1254] The terminal notifies the user that new learning materials are available, and the user accesses the delivered materials to study. Specific operations include displaying the materials through a user interface and managing how the user progresses with their learning activities. The input is the delivered learning materials, and the output is the user's learning activity data.

[1255] Step 7:

[1256] For factory robots, the robot's operational data (speed, accuracy, work height, etc.) is collected through sensors and sent to a server. The input is the robot's operational data, and the output is the operational data sent to the server.

[1257] Step 8:

[1258] The server receives the robot's motion data and stores it in the database in the same way as the training data. The input is the robot's motion data, and the output is the stored motion data.

[1259] Step 9:

[1260] The server analyzes the stored robot's motion data and identifies the robot's weaknesses. The input is the stored motion data, and the output is the analysis result (the robot's motion weaknesses).

[1261] Step 10:

[1262] The generation control device generates a training program for the robot based on the analysis results. Specifically, it automatically generates training content for specific weaknesses and puts it into program format. The input is the analysis results, and the output is the generated training program.

[1263] Step 11:

[1264] The server distributes the generated training program to the robot. The input is the generated training program, and the output is the training program distributed to the robot.

[1265] Step 12:

[1266] The robot automatically begins training based on the received training program to improve its performance. Specifically, it modifies its movements according to the training program to improve its performance. The input is the delivered training program, and the output is the robot's improved performance.

[1267] 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.

[1268] The present invention relates to a system for providing learning materials optimized for each individual learner, and also has a function for recognizing the user's emotions and optimizing the learning materials. Specific embodiments of the system are described below.

[1269] Program processing

[1270] Overall flow

[1271] Users provide learning data through online tests and learning activities. Based on that data, the server analyzes specific weaknesses, and the generation control device generates and optimizes learning materials. An emotion engine is also incorporated to optimize learning materials based on the user's emotions. Finally, the generated learning materials are delivered to the user via their device.

[1272] Data collection

[1273] Users generate learning data through online tests and daily learning activities. For example, when a user takes an online English test, emotional data is collected using the device's camera and microphone along with the results (correct answer rate, answer time, etc.). This data is sent from the device to a server.

[1274] Data storage and analysis

[1275] The server stores the collected learning data and emotional data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expressions, tone of voice, and text-based emotional expressions). The stored data is analyzed by an analysis module on the server. Based on the analysis results, topics and subjects that are the user's weaknesses are identified.

[1276] Teaching material generation and optimization

[1277] Based on the server's analysis results, the generation control device generates learning materials to reinforce the identified weaknesses. The generated materials include custom content tailored to the user's level of understanding and learning style. Furthermore, emotional data collected by the emotion engine is also used. For example, optimizations are made, such as providing a format that is easy for the user to understand (videos, interactive questions, etc.) or adjusting the difficulty level if the user is suspected to be stressed.

[1278] Teaching material distribution

[1279] The generated learning materials are delivered from the server to the user's device. The device notifies the user that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning.

[1280] Specific examples

[1281] Mathematics testing and emotional data collection

[1282] 1. Data collection: User A takes an online math test, and the results (50% correct answer rate) and emotional data (facial expression data captured by a camera) are sent from the device to the server. The emotional data suggests that User A may be frustrated during the test.

[1283] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User A has a weakness in "linear equations" and that he was frustrated during the test.

[1284] 3. Teaching material generation and optimization: The generation control device generates teaching materials related to linear equations. For example, it may include "basic explanations, videos showing calculation procedures, and applied problems." The difficulty level of the teaching materials is adjusted based on the emotion data, and they are provided in a format that is easy for User A to understand.

[1285] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User A's device. The device notifies User A that new learning materials are available, and User A begins learning using the delivered materials.

[1286] English quiz and emotional data collection

[1287] 1. Data collection: User B takes a short English quiz, and the results (40% correct answer rate for grammar questions) and emotional data (tone of voice recorded by a microphone) are sent from the device to the server. The emotional data suggests that User B is relaxed and engaged in studying.

[1288] 2. Data storage and analysis: The server stores and analyzes the training data and emotion data. As a result of the analysis, it is determined that User B has weaknesses in "grammar" and is able to study in a relaxed state.

[1289] 3. Learning material generation and optimization: The generation control device generates grammar learning materials, including basic grammar rules and related exercises. Based on emotional data, the content is provided in a way that makes it easy to learn in a relaxed state.

[1290] 4. Delivery of learning materials: The generated learning materials are delivered from the server to User B's device. The device notifies User B that new learning materials are available, and User B begins learning using the delivered materials.

[1291] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a more personalized learning experience and create an efficient and effective learning environment.

[1292] The processing flow will be explained below.

[1293] Step 1:

[1294] A user takes an online test.

[1295] Users log in to an online test for a specific subject through the learning platform and answer questions. Once the test is completed, the user's answer data (correct / incorrect answers for each question, answer time, etc.) is generated and stored on the device.

[1296] Step 2:

[1297] The device collects emotional data.

[1298] During the online test, the device collects emotional data such as the user's facial expressions and tone of voice. For example, the camera recognizes the user's facial expressions and the microphone analyzes the tone of voice.

[1299] Step 3:

[1300] The device sends the learning data and emotion data to the server.

[1301] Immediately after the user completes the test, the device sends the answer data and collected emotion data to the server, including the user ID, test type, answer data, answer time, and emotion data.

[1302] Step 4:

[1303] The server stores the training data and emotion data.

[1304] The server stores the received training data and emotion data in a database, which also stores each user's past training data and emotion data, making it easy to compare with new data.

[1305] Step 5:

[1306] The server analyzes the training data and emotion data.

[1307] The server then begins analysis using the stored learning data and emotional data. Using machine learning algorithms, it identifies the user's weaknesses and evaluates their emotional state. For example, it can list questions on which the user got the most answers wrong or took the longest time, identify weaknesses related to those topics, and evaluate the user's emotional state during the test.

[1308] Step 6:

[1309] A generation control device generates a draft of the teaching material.

[1310] Based on the identified weaknesses, the generation control device uses generative AI to create draft learning materials, including basic explanations, examples, and practice questions.

[1311] Step 7:

[1312] The generation control device optimizes the teaching materials based on the emotion data.

[1313] Based on the generated draft, the generation control device optimizes the learning materials based on the user's learning style, level of comprehension, and emotional data. For example, if the user feels stressed during a test, the difficulty level of the learning materials will be adjusted.

[1314] Step 8:

[1315] The server stores the optimized teaching materials in a database.

[1316] The optimized learning materials are then stored in a database by the server, ready to be distributed to users.

[1317] Step 9:

[1318] The server sends a notification of the distribution of the teaching material to the terminal.

[1319] After the server confirms that the learning materials have been generated and saved, it sends a notification to the user's device indicating that new learning materials are available.

[1320] Step 10:

[1321] Users receive notifications and access the learning materials.

[1322] The device displays a notification to the user that new learning materials are available. The user confirms the notification, accesses the delivered learning materials through the device, and begins learning.

[1323] Through these specific processing steps, the system can provide a customized learning experience for each user and support efficient learning. The introduction of an emotion engine provides an optimal learning environment according to the user's emotional state.

[1324] Example 2

[1325] 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."

[1326] Conventional learning systems have difficulty providing learning materials that take into account each learner's level of understanding and emotional state. This has led to issues such as reduced learning efficiency and frequent instances of learner stress. It has also been difficult to reflect the user's progress in real time and provide new learning materials at the optimal timing.

[1327] 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: a means for the user to provide learning data and emotional data; a means for the server to collect and store the user's learning data and emotional data; a means for the server to analyze the collected learning data and emotional data and identify the user's weaknesses; a means for the generation control device to generate and optimize learning materials based on the identified weaknesses and emotional data; and a means for the terminal to deliver the generated learning materials to the user. This makes it possible to provide customized and effective learning materials that take into account the level of understanding and emotional state of each individual learner.

[1328] "User" refers to an individual who uses the learning system.

[1329] "Learning Data" refers to information such as grades and response times provided by users through online tests and learning activities.

[1330] "Emotional data" refers to information collected from a user's facial expressions, tone of voice, and emotions expressed in text.

[1331] "Server" refers to a computer system that collects, stores, and analyzes learning data and emotional data, and issues instructions for generating teaching materials as needed.

[1332] The "generation control device" refers to a device that generates learning materials based on the analysis results of the server.

[1333] "Learning Materials" refers to educational content provided based on a user's weaknesses and learning progress.

[1334] "Terminal" refers to a device (e.g., a smartphone or PC) through which a user accesses learning materials and performs learning activities.

[1335] "Data collection means" refers to the technical means for collecting user learning data and emotion data.

[1336] "Data storage means" refers to the technical means for storing collected training data and emotion data in a database.

[1337] "Data analysis means" refers to the technical means for analyzing the collected data and identifying the user's learning weaknesses and emotional state.

[1338] "Optimization Measures" refers to technological measures for adjusting and optimizing learning materials based on user weaknesses and emotional data.

[1339] "Learning material delivery means" refers to the technical means for delivering the generated and optimized learning materials to the user's terminal.

[1340] "Progress data" refers to information that indicates the user's learning progress and results.

[1341] This invention relates to a system that provides learning materials optimized for each individual learner, and also has a function of recognizing the user's emotions and optimizing the learning materials. Specific embodiments of this system are described below.

[1342] Hardware and Software Configuration

[1343] This system uses the following main hardware and software:

[1344] Hardware

[1345] Server: Collects, stores, and analyzes training data and emotion data. A server with a high-performance CPU and sufficient memory is required.

[1346] Terminal: The device used by the user, such as a smartphone or computer. It is desirable that it has a built-in camera and microphone.

[1347] software

[1348] Database Management System: MySQL is used to store the collected data.

[1349] Data Analysis Module: Performs data analysis using Python and the pandas library.

[1350] Emotion Engine: Includes facial expression recognition and speech analysis algorithms powered by TensorFlow.

[1351] Generative control device: Generates learning materials using OpenAI's GPT model.

[1352] REST API: Used as a communication protocol to deliver educational materials to devices.

[1353] Example

[1354] Data collection

[1355] When a user takes an online test, the device acquires the test results (correct answer rate, answer time, etc.). At the same time, the device's camera and microphone are used to collect emotional data such as the user's facial expression and tone of voice. This data is sent to the server in real time.

[1356] Data storage and analysis

[1357] The server stores the submitted data in a MySQL database. The stored data includes the user ID, test results, answer data for each question, answer time, and emotional data such as facial expressions and tone of voice. The server's data analysis module then analyzes this data to identify the user's weaknesses and emotional state. For example, the data analysis module uses Python and the pandas library to process the data and identify the user's weaknesses in certain topics.

[1358] Teaching material generation and optimization

[1359] The server sends the analysis results in JSON format to the generation controller, which uses OpenAI's GPT model to generate customized learning materials based on the user's weaknesses. The emotion engine then takes the user's emotional data into account to optimize the format and difficulty of the materials. For example, if the user feels stressed during a test, a short relaxation video can be added.

[1360] Teaching material distribution

[1361] The generated learning materials are delivered from the server to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available, and the user can access the delivered materials and begin learning.

[1362] Specific examples

[1363] For example, suppose that User A takes an online math test and gets a 50% success rate and 30 minutes to complete it. Emotional data is collected from facial expressions showing signs of stress during the test. The server analyzes this data and identifies that User A has a weakness in "linear equations." At the same time, taking into account User A's feelings of stress, the generation control device generates learning materials for linear equations, including basic instructional videos, practice problems, and short videos for relaxation. These learning materials are then distributed to User A's device via the server.

[1364] In this way, the system collects, analyzes, and optimizes users' learning and emotional data to provide a personalized and effective learning experience.

[1365] Prompt Sentence Examples

[1366] "Generate learning materials for the following grammar rule: subject-verb agreement" "Create an instructional video for the following math problem: how to solve a linear equation"

[1367] The above is an embodiment of the present invention.

[1368] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1369] Step 1: Data collection

[1370] A user takes an online test. For example, when a user takes an online English test, the device collects the test results (80% correct answer rate, 15 minutes to answer). The device also uses a camera and microphone to collect emotional data such as facial expression data (smiling expression) and tone of voice (calm voice). This data is sent to a server using the HTTPS protocol. The input is the test result and emotional data, and the output is the data sent to the server.

[1371] Step 2: Save data

[1372] The server stores the received learning data and emotion data in a database. Specifically, the MySQL database stores user IDs, test results, answer data for each question, answer time, facial expression data, tone of voice, etc. The input is the data sent to the server, and the output is the data stored in the database.

[1373] Step 3: Data analysis

[1374] The server performs data analysis using Python scripts and the pandas library. The analysis module analyzes the test results and emotion data to identify the user's weaknesses (e.g., grammar problems). At the same time, the user's emotions (e.g., they were relaxed during the test) are identified. The input is the data stored in the database, and the output is the analyzed results of the user's weaknesses and emotional state.

[1375] Step 4: Creating educational materials using a generation control device

[1376] The server sends the analysis results in JSON format to the generation control device. The generation control device uses OpenAI's GPT model to generate learning materials that address the user's weaknesses (e.g., grammar). The generated learning materials include basic grammar rules, related example sentences, and practice questions. Based on emotional data, easy-to-understand videos are also added to help users relax and learn. The input is the analysis results, and the output is the generated learning materials.

[1377] Step 5: Distribution of teaching materials

[1378] The server sends the generated learning materials to the user's device via a REST API. The device notifies the user via a push notification that new learning materials are available. The user accesses the delivered learning materials through the device and begins learning. The input is the generated learning materials, and the output is the learning materials delivered to the device.

[1379] Step 6: Monitoring your learning progress

[1380] The user progresses with their studies using the delivered learning materials. The device collects learning progress data (e.g., learning completion rate, answer time, correct answer rate) and sends it to the server. The server stores this progress data in a database in real time and reanalyzes it using an analysis module. This accumulates the data necessary for generating the next learning material. The input is the learning progress data, and the output is the progress data sent to the server.

[1381] Through these steps, the system can effectively utilize the learning data and emotional data of each individual user to provide optimized learning materials.

[1382] (Application example 2)

[1383] 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."

[1384] Conventional learning systems provide learning materials based solely on the user's learning data, making it difficult to provide an optimal learning experience that takes into account the user's emotional state. Furthermore, because learning materials are not generated or optimized based on emotional aspects such as stress or decreased motivation, it is difficult to maximize individual learning outcomes. Furthermore, there are limitations to the means of providing appropriate reminders to users in real time.

[1385] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1386] In this invention, the server includes a means for users to provide learning data and emotional data, a means for collecting and storing the learning data and emotional data of users, and a means for analyzing the collected data and identifying the weaknesses and emotional state of the users, thereby enabling the generation and optimization of optimal learning materials that take into account not only the learning situation but also the emotional state of the users.

[1387] "Means by which a user provides learning data and emotional data" refers to means including devices and software for collecting information about a user's learning activities and emotional state.

[1388] "Means for the server to collect and store user learning data and emotional data" refers to a system that has the function of receiving learning data and emotional data sent by users and storing them in a database or storage.

[1389] "Means for the server to analyze the collected data and identify the user's weaknesses and emotional state" refers to analytical technology that analyzes the collected learning data and emotional data to identify the areas where the user has difficulty understanding and their mental state.

[1390] "Means for the generation control device to generate and optimize learning materials based on identified weaknesses and emotional state" refers to a device and method that automatically generates optimal learning materials based on the analysis of a user's weaknesses and emotional state, and adjusts them to meet the user's needs.

[1391] "Means for the terminal to deliver the generated learning materials to the user" refers to the communication means or software that transmits the generated learning materials to the user's device and makes them available.

[1392] The present invention is a system that collects and analyzes user learning data and emotional data, and provides optimized learning materials based on the collected data. To realize this system, the following hardware and software are required:

[1393] Hardware and Software Configuration

[1394] 1. User Device

[1395] Camera: Used to collect the user's facial expression data.

[1396] Microphone: Used to collect the user's tone of voice.

[1397] 2. Server

[1398] Database: A storage system for storing user learning data and emotion data.

[1399] Analysis module: Software for analyzing training data and sentiment data, specifically using machine learning libraries such as Scikit-Learn and TensorFlow.

[1400] Generation control device: Software that generates learning materials based on an algorithm and optimizes them according to the user's emotions.

[1401] 3. Communication Network

[1402] Internet: A communications infrastructure for sending and receiving data between user devices and servers.

[1403] System processing overview

[1404] Data collection

[1405] Users provide learning data and emotional data through online tests and learning activities. Specifically, the system collects the user's facial expressions and voice using the camera and microphone on the user's device. This data is sent to the server in real time.

[1406] Data analysis and storage

[1407] The server stores the collected learning data and emotional data in a database. Based on the stored data, the analysis module analyzes the user's learning weaknesses and emotional state. This analysis uses machine learning algorithms and natural language processing techniques.

[1408] Teaching material generation and optimization

[1409] Based on the analysis results, the generation control device generates optimal learning materials according to the user's learning and emotional state. The generated learning materials are provided in a format that is easy for the user to understand (e.g., videos, interactive questions), and the difficulty level is adjusted according to the emotional data.

[1410] Teaching material distribution

[1411] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available and allows the user to access the materials and progress with their studies.

[1412] Specific examples

[1413] For example, if a user takes a math test and facial expression data collected by a camera indicates that the user is stressed, subsequent study materials will be provided in a more understandable format. Similarly, if a user takes an English quiz in a relaxed state, study materials including basic grammar rules and practice questions will be generated.

[1414] Prompt Sentence Examples

[1415] "Please provide Python code that analyzes emotions based on facial expression data when a user takes a math test and generates optimal learning materials."

[1416] This system makes it possible to provide optimal learning materials that take into account the user's learning data and emotional state, resulting in a more effective learning experience.

[1417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1418] Step 1:

[1419] Users use their devices to take online tests and study activities. For example, when taking a math test, the device's camera and microphone are automatically activated to collect facial expression data and tone of voice. This allows learning data (test results) and emotional data (facial expressions and voice) to be collected simultaneously.

[1420] Input: User's learning data (test results), emotion data (facial expression data, voice data)

[1421] Output: Collected raw data (training data, emotion data)

[1422] Step 2:

[1423] The device transmits the collected learning data and emotion data to the server in real time, and the data is transferred to the server via a communication network.

[1424] Input: Collected raw data (training data, emotion data)

[1425] Output: Data sent to the server

[1426] Step 3:

[1427] The server stores the received data in a database. The data includes the user ID, test results, answer data for each question, answer time, and emotional data (facial expression data, voice data). Database management software (e.g., MySQL) is used.

[1428] Input: Data sent to the server

[1429] Output: Data stored in the database

[1430] Step 4:

[1431] The server's analysis module retrieves the learning data and emotion data from the database and performs analysis using machine learning algorithms (e.g., Scikit-Learn and TensorFlow) to identify the user's weaknesses (e.g., lack of understanding of linear equations) and emotional state (e.g., stress).

[1432] Input: Data stored in the database

[1433] Output: Analysis results (user weaknesses, emotional state)

[1434] Step 5:

[1435] The generation control device generates learning materials based on the analysis results. The learning materials are designed to address the user's weaknesses, and include, for example, basic explanations of linear equations, videos showing calculation procedures, and applied problems. The difficulty and format of the learning materials are also adjusted based on the user's emotional state.

[1436] Input: Analysis results (user weaknesses, emotional state)

[1437] Output: Generated learning materials

[1438] Step 6:

[1439] The generated learning materials are delivered from the server to the user's device, which notifies the user that new learning materials are available. The user receives the notification and can access the new learning materials through the device.

[1440] Input: Generated learning materials

[1441] Output: Learning materials delivered to the user's device

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1447] 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.

[1448] 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).

[1449] 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.

[1450] 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."

[1451] 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.

[1452] 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).

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] The following is further disclosed regarding the above embodiment.

[1464] (Claim 1)

[1465] A means for users to provide training data;

[1466] A means for the server to collect and store user learning data;

[1467] a means for the server to analyze the collected data and identify weaknesses of the user;

[1468] a generation control device for generating learning materials based on the identified weaknesses;

[1469] A means for distributing the generated learning materials to the user by the terminal;

[1470] A system including:

[1471] (Claim 2)

[1472] 2. The system of claim 1, wherein the generation control device optimizes the learning materials based on the user's level of understanding and interests.

[1473] (Claim 3)

[1474] 2. The system according to claim 1, wherein the server manages learning progress data and notifies the user of appropriate reminders.

[1475] "Example 1"

[1476] (Claim 1)

[1477] A means for users to provide training data;

[1478] A means for the server to collect and store user learning data;

[1479] a means for the server to analyze the collected data and identify weaknesses of the user;

[1480] a generation control device for generating learning materials based on the identified weaknesses;

[1481] A means for distributing the generated learning materials to the user by the terminal;

[1482] A means for using machine learning algorithms and generative AI models in the process of collecting, storing, and analyzing learning data and generating teaching materials;

[1483] means for executing a notification function on the terminal to notify the user of the generated educational material and allow the user to access the educational material;

[1484] A system including:

[1485] (Claim 2)

[1486] 2. The system of claim 1, wherein the generation control device optimizes the learning materials based on the user's level of understanding and learning style.

[1487] (Claim 3)

[1488] 2. The system according to claim 1, wherein the server manages learning progress data and notifies the user of appropriate reminders.

[1489] "Application Example 1"

[1490] (Claim 1)

[1491] A means for users to provide training data;

[1492] A means for the server to collect and store user learning data;

[1493] a means for the server to analyze the collected data and identify weaknesses of the user;

[1494] a generation control device for generating learning materials based on the identified weaknesses;

[1495] A means for distributing the generated learning materials to the user by the terminal;

[1496] means for collecting and analyzing robot motion data;

[1497] a means for generating a training program based on the identified weaknesses of the robot;

[1498] A means for the terminal to distribute the generated training program to the robot;

[1499] A system including:

[1500] (Claim 2)

[1501] 2. The system of claim 1, wherein the generation control device optimizes the learning materials based on the user's level of understanding and interests.

[1502] (Claim 3)

[1503] 10. The system of claim 1, wherein the production control device optimizes the training program based on the robot's motion performance.

[1504] (Claim 4)

[1505] 2. The system according to claim 1, wherein the server manages learning progress data and notifies the user of appropriate reminders.

[1506] (Claim 5)

[1507] 2. The system according to claim 1, wherein the server manages the robot's operational performance data and notifies the robot of appropriate reminders.

[1508] "Example 2: Combining Emotion Engines"

[1509] (Claim 1)

[1510] a means for a user to provide training data and emotion data;

[1511] A means for the server to collect and store user learning data and emotion data;

[1512] A means for the server to analyze the collected learning data and emotion data and identify the weaknesses of the user;

[1513] means for the generation control device to generate and optimize learning materials based on the identified weaknesses and emotion data;

[1514] A means for distributing the generated learning materials to the user by the terminal;

[1515] A system including:

[1516] (Claim 2)

[1517] 2. The system according to claim 1, wherein the generation control device adjusts the format and difficulty of the learning materials based on the user's emotional data.

[1518] (Claim 3)

[1519] 10. The system of claim 1, wherein the server manages the user's learning progress data and notifies the user of the availability of new learning materials as appropriate.

[1520] "Application example 2 when combining emotion engines"

[1521] (Claim 1)

[1522] a means for a user to provide training data and emotion data;

[1523] A means for the server to collect and store user learning data and emotion data;

[1524] means for the server to analyze the collected data and identify the user's weaknesses and emotional state;

[1525] means for a generation control device to generate and optimize learning materials based on the identified weaknesses and emotional states;

[1526] A means for distributing the generated learning materials to the user by the terminal;

[1527] A system including:

[1528] (Claim 2)

[1529] 10. The system of claim 1, wherein the production control device optimizes the learning material based on the user's comprehension, interests, and emotional state.

[1530] (Claim 3)

[1531] 2. The system according to claim 1, wherein the server manages learning progress data and emotional state data and notifies the user of appropriate reminders. [Explanation of symbols]

[1532] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to provide training data; A means for the server to collect and store user learning data; a means for the server to analyze the collected data and identify weaknesses of the user; a generation control device for generating learning materials based on the identified weaknesses; A means for distributing the generated learning materials to the user by the terminal; A system including:

2. 10. The system of claim 1, wherein the production control device optimizes the learning materials based on the user's level of understanding and interests.

3. 2. The system according to claim 1, wherein the server manages the learning progress data and notifies the user of appropriate reminders.

Images