system

Abstract

Provide a system. [Solution] A means for collecting children's learning data using generative AI; A means of analyzing the collected data in a comprehensive manner, A means to identify children's potential talents and areas of expertise based on the analysis results; A means to create a customized coaching plan based on the areas identified; A means to provide customized coaching plans; A system including:

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 education systems often find it difficult to efficiently identify individual children's talents and areas of strength, resulting in a one-size-fits-all educational approach for all children. This approach fails to fully tap into each child's potential talents, and as a result, can limit the child's own growth and development. The problem this invention aims to solve is to use generative AI to comprehensively analyze children's data and identify individual talents and areas of strength, thereby providing each child with the optimal educational approach and support. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting a child's learning data using generative AI, a means for comprehensively analyzing the collected data, a means for identifying the child's potential talents and areas of expertise based on the analysis results, a means for creating a customized coaching plan based on the identified areas, and a means for providing the customized coaching plan. This system enables accurate understanding of each child's characteristics and a personalized educational approach to maximize their talents. For example, a child's test results and extracurricular activity data can be analyzed using an AI model to identify areas of expertise and talents, and a customized learning plan can be provided based on these. This makes it possible to provide the most appropriate educational support for each child and maximize their development.

[0006] "Generative AI" is a type of artificial intelligence that uses algorithms to generate new information and patterns from input data.

[0007] "Learning data" is a collection of information that indicates a child's learning situation, including the child's learning activities, grades, extracurricular activities, etc.

[0008] "Composite analysis" refers to the act of combining multiple data sources and analytical methods to derive more comprehensive and accurate results.

[0009] "Potential talent" refers to talent that is not manifested in current abilities or performance, but which has the potential to be unleashed with appropriate support and training.

[0010] A "strength area" refers to an area in which a child has particularly outstanding abilities or interests compared to other areas.

[0011] "Coaching plan" means a plan that includes individualized learning activities and support methods based on a child's talents and areas of strength.

[0012] "Means of collection" refers to the methods and technologies used to collect children's learning data.

[0013] "Composite analytical methods" refer to methods of analyzing collected data using multiple algorithms and models to extract useful information.

[0014] "Means of identification" refers to techniques and methods for clearly identifying a child's talents and areas of expertise from the analysis results.

[0015] "Means of creation" refers to the techniques and methods used to design a customized coaching plan based on the information obtained.

[0016] "Means for providing" refers to the methods and techniques for communicating the created coaching plan to users and making it available in actual educational settings. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized coaching plans.

[0039] First, users (parents or educators) input various learning data about their children via a device. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data into the device using a dedicated application or web interface. This interface is designed to simplify data entry, allowing users to enter data easily.

[0040] The server then collects the data sent from the device and stores it in a database, ensuring that the collected data is securely stored and available for subsequent analysis.

[0041] The collected data is then analyzed on a server using generative AI. This analysis uses machine learning algorithms and data mining techniques to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores well in math tests, this could be used to determine whether they have a talent for math.

[0042] The server then uses the analysis results to identify the child's potential talents and areas of strength. The identified talents and areas of strength are organized in a report format and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0043] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a child who excels in math might get a plan incorporating math puzzles and advanced problem-solving activities, while a child interested in music might be offered a plan to study music theory or practice an instrument.

[0044] Finally, the customized coaching plan is sent from the server to the user's device. The user can access the plan through their device and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of strength, and as a result, it is expected that they will develop more effectively.

[0045] For example, consider the case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0046] This system allows for a personalized learning approach based on each child's talents and areas of strength, solving the challenges facing the existing education system.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0050] Step 2:

[0051] The terminal sends the entered data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0052] Step 3:

[0053] The server retrieves the training data stored in the database and performs a complex analysis using machine learning algorithms, using a combination of supervised and unsupervised learning techniques to extract patterns and trends from the data.

[0054] Step 4:

[0055] The server uses the analysis results to identify a child's potential talents and areas of expertise. This identification process takes into account multiple evaluation criteria (e.g., test scores and extracurricular activity performance) and makes a comprehensive judgment.

[0056] Step 5:

[0057] The server creates a customized coaching plan based on the identified talents and areas of strength, including specific learning activities and materials to use. For example, a child who shows talent in math will receive a plan that includes math puzzles and applied problems.

[0058] Step 6:

[0059] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0060] Step 7:

[0061] Users receive coaching plans via their device and incorporate them into their child's daily learning activities. They regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0062] For example, if Student A is interested in math and music, the user can input this data and the server can analyze it to determine that Student A has high grades in math and also has excellent musical performance skills. Based on this, the server can create a customized plan for Student A that includes math puzzles and music theory exercises and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0063] Example 1

[0064] 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."

[0065] In traditional education systems, it is difficult to identify a child's individual talents and areas of strength and provide a personalized learning plan based on them. It is also extremely time-consuming and laborious for parents and educators to manually collect and analyze children's learning data. This can result in children's potential talents being overlooked.

[0066] 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.

[0067] In this invention, the server includes a means for inputting a child's learning data via an input interface, a means for storing the input data in a database, a means for comprehensively analyzing the collected data using a generative AI model, a means for identifying the child's potential talents and areas of expertise based on the analysis results, a means for creating a customized educational plan based on the identified areas, and a means for providing the customized educational plan. This makes it possible to quickly and accurately identify each child's individual talents and areas of expertise and provide an individualized learning plan based on these.

[0068] An "input interface" is a screen, form, or other means by which a user inputs their child's learning data via a terminal.

[0069] A "database" is a system for safely and efficiently storing, managing, and searching collected learning data.

[0070] A "generative AI model" is a type of artificial intelligence that learns from large amounts of data and performs data analysis and predictions.

[0071] "Comprehensive analysis" means analyzing collected data from multiple angles and processing it to extract patterns and trends.

[0072] "Potential talent" is talent that is not clearly manifested at present but shows high ability or potential in a particular field.

[0073] A "strength area" is an area in which a child has a particular interest and excels.

[0074] An "educational plan" is a plan that combines the most appropriate learning content and activities based on a child's talents and areas of expertise.

[0075] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized educational plans. Specific embodiments of this system are described below.

[0076] Users first use their device to access a dedicated application or web interface. This interface is designed for easy data entry, allowing users to easily input their child's learning data. For example, test scores, extracurricular activity results, and daily behavior records are handled as input data. Software such as the "EduTrack app" or "EduTrack web portal" can be used.

[0077] The input learning data is sent by the device to the server. The sent data is encrypted to ensure security, and after receiving it, the server stores it in a database such as "Amazon RDS" or "MySQL (registered trademark)."

[0078] The server then performs a complex analysis of the collected data using a generative AI model. This analysis uses machine learning libraries such as Tensorflow® and PyTorch to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores high on math tests, the server can determine that the child is mathematically gifted.

[0079] Based on the analysis results, the server identifies the child's potential talents and areas of expertise. After this identification, the server compiles the results in the form of a report and provides it to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0080] The server then uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, a child who excels in math might have a plan that includes math puzzles and advanced problem-solving activities. The plan is designed to allow users to select the learning content and activities that are best suited to the target learner.

[0081] The customized educational plan is sent to the user's device, where the user can access it and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of expertise, and is expected to result in more effective development.

[0082] For example, consider a case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0083] Below are some examples of prompts to input to a generative AI model.

[0084] "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents."

[0085] This system allows for a personalized learning approach based on a child's talents and areas of strength, solving the problems inherent in traditional education systems.

[0086] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0087] Step 1:

[0088] Users use their devices to access a dedicated application or web interface. This interface is software such as the "EduTrack App" or "EduTrack Web Portal," and is designed to facilitate data entry. Inputs here include a child's test scores (e.g., math test result: 95 points) and extracurricular activity results (daily records: piano playing records). The output is the input learning data.

[0089] Step 2:

[0090] The training data entered by the user is sent to the server by the terminal. The entered data is encrypted to ensure security. The server stores this data in a database such as "Amazon RDS" or "MySQL." The input here is the encrypted training data, and the output is the training data stored in the database.

[0091] Step 3:

[0092] The server preprocesses the training data stored in the database. This preprocessing uses data processing libraries such as "Pandas" and "NumPy." Specifically, the received data is cleaned and normalized. For example, "Math test score: 95 points" is normalized by comparing it with other scores. The input here is the training data in the database, and the output is the preprocessed data.

[0093] Step 4:

[0094] The server analyzes the preprocessed data using a generative AI model. This analysis uses machine learning libraries such as TensorFlow and PyTorch. The server extracts a child's learning patterns and behavioral trends based on past data. For example, consistently high math test scores indicate strong mathematical intuition. The input here is the preprocessed data, and the output is the analysis results.

[0095] Step 5:

[0096] The server identifies the child's potential talents and areas of expertise based on the analysis results. The talents and areas of expertise identified through the analysis are organized in a report format. This report includes the child's current performance, a comparison with the Japanese average, recommended study methods, and so on. For example, it may state "Mathematical talent: High" or "Recommended study method: Solving math puzzles." The input here is the analysis results, and the output is specific information in the form of a report.

[0097] Step 6:

[0098] The server uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, for a child who excels in math, a plan incorporating math puzzles and advanced problem-solving activities is created. The AI ​​model receives a prompt such as, "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents." The input is specific information, and the output is a customized educational plan.

[0099] Step 7:

[0100] The server sends the generated customized educational plan to the device. The user accesses this plan via the device and incorporates it into their child's daily learning. For example, the educational plan provided by the server can be checked and implemented using the "EduTrack app." The input here is the customized educational plan, and the output is the progress of learning based on the plan.

[0101] Through these steps, the system collects and analyzes children's learning data and provides personalized learning plans to maximize their potential.

[0102] (Application example 1)

[0103] 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."

[0104] The current education system struggles to identify each child's potential talents and areas of expertise and provide them with personalized learning plans. It also lacks appropriate methods for providing engaging and effective learning experiences. It is particularly difficult to provide real-time feedback and an immersive learning environment. To address these issues, more advanced analytical techniques and interactive learning methods are needed.

[0105] 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.

[0106] In this invention, the server includes means for collecting learning data of a child using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, and means for providing a customized learning experience in a virtual reality space. This makes it possible to provide a customized plan that meets the individual learning needs of each child and to provide an interactive and immersive learning experience in a virtual reality space.

[0107] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to analyze data and output results or products based on specific goals.

[0108] A "virtual reality space" is a virtual 3D environment generated using computer technology in which users can have interactive experiences and activities.

[0109] "Learning data" refers to all information related to a child's learning, including test results, extracurricular activities, daily behavior, and other data.

[0110] "Potential talent" refers to the abilities and areas of expertise that a child may have but have not yet manifested.

[0111] "Strengths" refers to areas of learning or activity in which a child excels or has a strong interest compared to other areas.

[0112] A "customized coaching plan" refers to a learning plan or instructional methodology specifically designed for each child based on their individual talents and interests.

[0113] "Analysis" refers to the process of examining collected learning data in detail to find patterns and trends.

[0114] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized learning experiences using virtual reality spaces.

[0115] First, users (parents or educators) enter their child's learning data via smartphone. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data using a dedicated application. This application has the function of sending the data to a database such as Firebase Firestore.

[0116] The server then collects the data and stores it in a database. The collected data is analyzed using GPT-4 (registered trademark) and other machine learning algorithms (e.g., scikit-learn). The analysis involves extracting a child's learning patterns and behavioral trends. For example, high math grades and music performance records can be analyzed to identify a child's mathematical or musical talents.

[0117] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This information is organized in the form of a report and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0118] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a math-savvy child might have a plan that includes math puzzles and advanced problem-solving activities, while a musically-inclined child might have a plan that includes music theory lessons and instrument practice.

[0119] Furthermore, the customized coaching plan is implemented in a virtual reality space. Unity is used to create the virtual environment, which provides an immersive learning experience for children through a head-mounted display (e.g., Oculus Rift, PlayStation VR). Within this virtual environment, children can solve problems, conduct experiments, and play music.

[0120] For example, if a student is interested in science and art, the user enters that information into the application. The server analyzes this information and provides plans for science experiments and art projects in a virtual reality space. The student can learn in a virtual laboratory or art studio.

[0121] An example of a prompt is as follows:

[0122] Analyze student learning data and create lesson plans focused on science and art. Deliver virtual reality learning experiences that include science experiments and art projects.

[0123] The system provides an effective learning environment by offering customized plans tailored to each child's individual learning needs and by providing an interactive and immersive learning experience in a virtual reality space.

[0124] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0125] Step 1:

[0126] Users use a dedicated smartphone application to enter their child's learning data (test results, extracurricular activity results, daily behavior records, etc.).

[0127] Input: Test results, extracurricular activity results, daily activity records, etc.

[0128] Output: The collected training data is ready to be sent to the server.

[0129] Step 2:

[0130] The device sends the collected data to a database such as Firebase Firestore.

[0131] Input: Training data entered by the user.

[0132] Output: Training data stored securely in a database.

[0133] How it works: The smartphone application sends data to FIREBASE, where it is stored securely and quickly.

[0134] Step 3:

[0135] The server retrieves the collected data from the database and performs complex analysis of the data using generative AI (GPT-4) and machine learning algorithms (scikit-learn).

[0136] Input: Training data stored in a database.

[0137] Output: Analysis results that extract children's learning patterns and behavioral tendencies.

[0138] Specific operation: The server issues a query to the database and analyzes the data using analytical algorithms.

[0139] Step 4:

[0140] Based on the analysis results, the server identifies the child's potential talents and areas of expertise and organizes them in a report format.

[0141] Input: Analysis results.

[0142] Output: A report on your child's potential talents and areas of expertise.

[0143] Specific operation: The generative AI evaluates the analysis results and creates a report in a format that is easy for the user to understand.

[0144] Step 5:

[0145] Create a customized coaching plan based on the server's identified strengths and talents.

[0146] Input: Potential talent and strengths report.

[0147] Output: A customized coaching plan.

[0148] Specific operation: The server uses a guidance template to generate a plan tailored to individual learning needs.

[0149] Step 6:

[0150] The server implements the customized coaching plan in a virtual reality space and provides it using a head-mounted display.

[0151] Enter: a customized coaching plan.

[0152] Output: A learning experience in a virtual reality space.

[0153] Specific Action: Use Unity to build a virtual environment and reflect specific learning activities in a virtual reality space.

[0154] Step 7:

[0155] The user allows the child to experience virtual reality learning through a head-mounted display.

[0156] Input: Learning experiences in virtual reality spaces.

[0157] Output: Interactive learning activities that children can experience firsthand.

[0158] Specific actions: Children wear a head-mounted display and learn and experiment in a virtual environment.

[0159] 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.

[0160] This invention combines a system that uses generative AI to collect and analyze children's learning data, identifies potential talents and areas of strength, and provides personalized coaching plans with an emotion engine. This system enables a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0161] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0162] The server then collects the data sent from the device and securely stores it in a database. At the same time, the device acquires the user's facial expression, voice, and text data and analyzes them through an emotion engine. The emotion engine then uses this data to recognize the user's emotional state in real time and transmits the results to the server.

[0163] The server integrates the learning data and the emotional data obtained by the emotion engine, and performs a comprehensive analysis using generative AI. This analysis uses machine learning algorithms and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[0164] Next, the server uses the analysis results to identify the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress while performing that task, the server can reconsider coaching in that area.

[0165] The server then uses the results of these analyses to create a customized coaching plan. By incorporating emotional data, it can determine the most effective learning method for each child. For example, if a child performs well in low-stress situations, it can recommend a relaxing learning environment.

[0166] The server then sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user can regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0167] For example, if Student A is interested in math and music, the user can input this data into their device and the server will analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine will also determine that Student A has a high stress level. Based on this information, the server will create a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0168] This system enables personalized learning approaches based on a child's talents and areas of expertise, and also provides educational support that takes into account their emotional state, improving children's learning efficiency and helping them to continue learning with sustained high motivation.

[0169] The processing flow will be explained below.

[0170] Step 1:

[0171] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0172] Step 2:

[0173] The device sends the input learning data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0174] Step 3:

[0175] The device transmits the learning data and simultaneously acquires the user's facial expression, voice, and text data, which are collected in real time with the user's consent.

[0176] Step 4:

[0177] The device sends the collected facial, voice, and text data to the emotion engine, which analyzes the data and determines the user's emotional state. The determination results include emotions such as stress, excitement, and relaxation.

[0178] Step 5:

[0179] The emotion engine sends the determined emotional state to the server, which combines the learning data with the emotion data and stores it securely.

[0180] Step 6:

[0181] The server inputs the collected learning data and emotional data into the AI ​​generator, which then performs a comprehensive analysis using machine learning algorithms and data mining techniques to derive a comprehensive result that takes into account the child's learning patterns, behavioral tendencies, and emotional state.

[0182] Step 7:

[0183] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress when performing that task, the server can reconsider the coaching content in that area.

[0184] Step 8:

[0185] The server then creates a customized coaching plan based on the identified talents and areas of strength. The plan includes specific learning activities and materials to use, and incorporates emotional data to determine how a child will learn most effectively. For example, if a child performs better in a relaxed environment, the server will recommend learning methods that take advantage of that environment.

[0186] Step 9:

[0187] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0188] Step 10:

[0189] The user then integrates the coaching plan received from the device into their child's daily learning activities. The user periodically checks progress and enters additional data as needed, allowing the system to provide continuous, optimized support.

[0190] For example, if Student A is interested in math and music, the user can input this data into their device and the server can analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine can also determine that Student A has high stress levels. Based on this information, the server creates a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provides it to the user. The user can then implement this plan to maximize Student A's talents. This system enables personalized learning approaches based on a child's talents and areas of expertise, and can also provide educational support that takes their emotional state into account.

[0191] Example 2

[0192] 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."

[0193] Current education systems struggle to provide personalized educational approaches that fully consider each child's learning progress and emotional state. This can result in ineffectively drawing out a child's talents and areas of expertise, leading to a decline in learning efficiency and motivation. Furthermore, creating learning plans without considering a child's emotional state risks increasing stress and anxiety. Therefore, there is a need for a system that can comprehensively analyze learning data and emotional data to bring out a child's potential talents.

[0194] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generation AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means including an emotion engine for collecting and analyzing emotion data, and means for integrating and analyzing the emotion data and the learning data. This provides an individualized learning approach based on the child's talents and areas of expertise and enables educational support that takes into account the child's emotional state, thereby improving learning efficiency and maintaining sustainable motivation.

[0195] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data, particularly utilizing machine learning and natural language processing.

[0196] "Educational data" refers to various educational data such as a child's learning progress, test results, extracurricular activity results, and areas of interest.

[0197] "Composite analysis methods" are methods that integrate collected data and analyze it from multiple perspectives using machine learning algorithms and data mining techniques.

[0198] "Potential talent" refers to a child's abilities and characteristics that are not currently clearly manifested but have the potential to blossom with appropriate support.

[0199] "Strengths" refer to specific academic areas or activities in which a child excels more than others.

[0200] "Customized coaching plan" refers to an individualized educational support program created based on a specific individual's learning and emotional data.

[0201] "Emotional data" refers to data that indicates the psychological state of a user obtained from facial expressions, voice, and text.

[0202] "Emotion engine" refers to software or a system for analyzing collected emotional data and recognizing emotional states.

[0203] "Means for integrated analysis" refers to a method for processing training data and emotion data in a unified manner and conducting comprehensive analysis.

[0204] "Machine learning algorithms" refer to computational methods and models that learn patterns and rules from data and make predictions and classifications.

[0205] "Data mining technology" refers to an analytical method for extracting useful information and insights from large data sets.

[0206] This invention combines an emotion engine with a system that uses a generative AI model to collect and analyze children's learning data, identify potential talents and areas of expertise, and then provides customized coaching plans. This allows for a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0207] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, and the children's areas of interest. The device provides dedicated applications and web interfaces to make it easy for users to input data. For example, if Student A is interested in mathematics and music, that information is also entered.

[0208] The device then temporarily stores the learning data entered by the user and sends it to a server via the internet. At the same time, the device also collects facial expressions and voice data from the user via a camera and microphone. This data is then analyzed in real time by the emotion engine.

[0209] The server receives the training data and emotion data sent from the device and stores them in a secure database. The server uses, for example, an SQL database as the database. The server performs an initial analysis, checks the consistency of the data, and verifies whether any data is missing.

[0210] The emotion engine analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. For example, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and sends the analysis results to the server.

[0211] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (such as GPT-4 or BERT). This analysis uses machine learning algorithms (such as random forests or k-nearest neighbors) and data mining techniques (such as puppetry). Based on the analysis results, the server identifies a child's potential talents and areas of expertise. For example, it may be discovered that Student A has high grades in math, but experiences increased stress during tests.

[0212] The server then uses these analysis results to create a customized coaching plan, which could include things like math puzzles incorporating relaxation exercises or music practice strategies for calmer emotional situations. For example, the generative AI model might be prompted with the following prompt: "Generate a new coaching plan for Student A based on his or her latest emotional state and learning progress."

[0213] The server then sends the generated customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user periodically checks their child's learning progress and emotional state and inputs new data as needed. This allows the system to provide continuously optimized support.

[0214] This system provides an individualized learning approach and enables educational support that takes into account children's emotional state, thereby improving children's learning efficiency and maintaining sustained motivation.

[0215] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0216] Step 1:

[0217] Users enter their child's learning data using a dedicated application or web interface. This data includes daily learning progress, test results, extracurricular activity results, and areas of interest. For example, they enter information such as "Math test result: 90 points, Music lesson results: 50 minutes of piano practice." The entered data is temporarily stored on the device.

[0218] Step 2:

[0219] The device temporarily stores the learning data entered by the user and then sends it to a server via the Internet. Specifically, data such as learning progress and test results are packaged in packets in JSON format and sent to the server using a secure protocol (e.g., HTTPS). The input is the learning data, and the output is the data packet sent to the server.

[0220] Step 3:

[0221] The device also simultaneously collects the user's facial and voice data. It uses a camera and microphone to capture facial and voice data and sends it to the emotion engine for real-time analysis. Specifically, it sends video data to a facial recognition API and voice data to an emotion analysis API. The input is facial and voice data, and the output is a dataset of the analysis results.

[0222] Step 4:

[0223] The server receives the training data and emotion data sent from the device and stores them in a secure database (e.g., SQL database). Before storing the data in the database, the server first checks the integrity of the data and confirms that there is no missing data. The input is the data received from the device, and the output is a notification that storage to the database is complete.

[0224] Step 5:

[0225] The emotion engine in the server analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. Specifically, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and stores these analysis results in a database. The input is emotion data, and the output is analyzed emotion information.

[0226] Step 6:

[0227] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (e.g., GPT-4 or BERT). Specifically, it analyzes children's learning patterns and behavioral trends using machine learning algorithms (e.g., random forests and k-nearest neighbors) and data mining techniques. The input is the integrated learning data and emotion data, and the output is the analysis results.

[0228] Step 7:

[0229] The server creates a customized coaching plan based on the analysis results. For example, it may include math puzzles incorporating relaxation exercises or music practice methods in emotionally calm situations. Specifically, the generative AI model receives a prompt: "Generate a new coaching plan based on Student A's latest emotional state and learning progress." The input is the analysis results, and the output is a customized coaching plan.

[0230] Step 8:

[0231] The server sends the generated customized coaching plan to the terminal. The user can access this plan through the terminal and incorporate it into their daily learning activities. Specifically, the plan is displayed through an application or web interface, and the user can reflect it in their learning activities. The input is the customized coaching plan, and the output is information on how it is applied to the user's learning activities.

[0232] Step 9:

[0233] The user periodically checks their learning progress and emotional state and inputs new data as needed. This allows the system to always provide optimized support based on the latest data. The input is new learning data and emotional data, and the output is updated data sent to the server.

[0234] This system improves children's learning efficiency and enables them to continue learning with sustained high motivation.

[0235] (Application example 2)

[0236] 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."

[0237] Conventional learning support systems often only consider a child's learning progress and ignore their emotional state, resulting in suboptimal learning performance. This makes it difficult for parents and educators to create personalized educational plans for each child, making it difficult to provide effective learning support. Furthermore, the lack of real-time emotional state monitoring makes it difficult to quickly identify and address learning stressors.

[0238] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means for analyzing the child's emotional state using an emotion engine and for integrated processing of the learning data and the emotional data, means for a parent or educator to input learning data through a terminal and monitor the emotional state, and means for transmitting a customized coaching plan to the terminal based on the data analysis results and continuously optimizing it. This enables the provision of more effective and personalized educational support that takes into account not only the child's learning progress but also their emotional state.

[0239] "Generative AI" is a technology that uses artificial intelligence to generate new data and information from large amounts of data.

[0240] "Learning data" refers to various information related to learning activities, such as a child's learning progress, test results, extracurricular activity data, and emotional state data written in diary format.

[0241] "Complex analysis" means integrating collected learning data and emotional data and analyzing them using machine learning algorithms and facial recognition technology.

[0242] "Potential talent" refers to abilities or areas of expertise that are not yet apparent but have the potential to be demonstrated with the right environment and guidance.

[0243] "Strengths" refer to areas of study or activity in which a child can perform particularly well.

[0244] A "customized coaching plan" is a specific plan that identifies and implements the teaching methods and learning tasks that are best suited to each individual child.

[0245] An "emotion engine" refers to a system that uses facial recognition technology and voice analysis to analyze a user's emotional state in real time.

[0246] "Device" refers to an electronic device, such as a smartphone, tablet, or computer, used by a parent or educator to input learning data or monitor emotional states.

[0247] "Integrated processing" means processing multiple types of collected data in a unified manner and conducting comprehensive analysis.

[0248] "Monitoring" means collecting and analyzing data in real time or near real time and observing the results.

[0249] "Continuous optimization" means constantly improving systems and plans based on acquired data and analysis results.

[0250] This invention is a system that uses generative AI to collect and analyze children's learning data, combines it with an emotion engine, and provides personalized coaching plans. Specific methods for implementing the system are described below.

[0251] First, the user (parent or educator) must enter their child's learning data through a device, which can be a smartphone, tablet, or computer. This data includes daily learning progress, test results, extracurricular activity results, and emotional states recorded in diary format. This allows the user to centrally manage their child's learning activities and emotional states.

[0252] The device then uses a camera or microphone to collect facial and voice data from the child. This data is then analyzed by an emotion engine to recognize the child's emotional state in real time. The emotion engine uses machine learning libraries such as TensorFlow and Keras, and includes a combination of facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library).

[0253] The device transmits the collected learning and emotional data to a server, which securely stores this data in a database and performs a complex analysis using a generative AI model. This analysis uses machine learning algorithms and facial recognition technology, and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[0254] Based on the analysis, the server identifies potential talents and areas of strength for the child. For example, if a child shows high achievement in math or music but is experiencing stress, the server can adjust coaching in those areas.

[0255] Finally, the server creates a customized coaching plan and sends it to the device. The user can access the plan through the device and continuously support their learning activities. The user can also add new data from time to time, allowing the system to continuously optimize the plan.

[0256] As a concrete example, consider the case where Student A is interested in math and music. In this case, a parent or educator inputs this data into the device, and the server analyzes it. The analysis results show that Student A has high math grades and excellent musical performance skills, but the emotion engine identifies high stress levels. Based on this information, the server creates and provides a plan to the user that includes math puzzles with relaxation exercises and music practice methods that allow students to learn while having fun.

[0257] The server then uses this data to run a generative AI model based on the following example prompt: "These are the results of a math test. Please analyze the data, including my emotional state, to generate a low-stress, effective study plan."

[0258] Through the above process, the present invention is able to provide effective and personalized educational support that takes into account not only a child's learning progress but also their emotional state.

[0259] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0260] Step 1:

[0261] The user uses a device to input their child's learning data. This data includes daily learning progress, test results, extracurricular activity results, and emotional states described in diary format. The input data is designed to be easily entered through the device's interface. The output of the input data is saved as learning data for use in subsequent processing steps.

[0262] Step 2:

[0263] The device uses a camera or microphone to collect facial and voice data from the child. This data is acquired in real time and sent to the emotion engine. The emotion engine analyzes the collected image and voice data to recognize the child's emotional state. Specifically, it uses facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library). The input is facial and voice data, and the output is the analysis result of the child's emotional state.

[0264] Step 3:

[0265] The device sends the collected training data and emotion data to a server, which stores this data securely in a database. The input is the training data and emotion data, and the output is a database entry stored on the server.

[0266] Step 4:

[0267] The server uses a generative AI model to perform a complex analysis of the collected data. This analysis uses machine learning algorithms and facial recognition technology. Data mining technology is used to determine the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state. The input is the stored learning data and emotional data, and the output is the analysis results.

[0268] Step 5:

[0269] The server identifies the child's potential talents and areas of strength based on the analysis results. This process takes into account performance data in specific academic subjects and activities, as well as emotional state, to make a comprehensive assessment. The input is the analysis results, and the output is the identified talents and areas of strength.

[0270] Step 6:

[0271] The server creates a customized coaching plan based on the identified areas. For example, if the person is feeling stressed, it suggests learning methods that incorporate stress reduction techniques. Specific learning tasks and teaching methods are determined at this stage. The input is the identified talents and areas of strength, and the output is a customized coaching plan.

[0272] Step 7:

[0273] The server sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into the child's learning activities. The device can also monitor the progress of the implemented plan and add new data. The input is the customized coaching plan, and the output is the specific learning activities that the user will carry out.

[0274] Through the above steps, the present invention can provide personalized educational support that takes into consideration a child's learning progress and emotional state in an integrated manner.

[0275] 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.

[0276] 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.

[0277] 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.

[0278] [Second embodiment]

[0279] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0280] 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.

[0281] 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).

[0282] 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.

[0283] 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.

[0284] 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).

[0285] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0286] 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.

[0287] 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.

[0288] 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.

[0289] 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.

[0290] 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."

[0291] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized coaching plans.

[0292] First, users (parents or educators) input various learning data about their children via a device. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data into the device using a dedicated application or web interface. This interface is designed to simplify data entry, allowing users to enter data easily.

[0293] The server then collects the data sent from the device and stores it in a database, ensuring that the collected data is securely stored and available for subsequent analysis.

[0294] The collected data is then analyzed on a server using generative AI. This analysis uses machine learning algorithms and data mining techniques to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores well in math tests, this could be used to determine whether they have a talent for math.

[0295] The server then uses the analysis results to identify the child's potential talents and areas of strength. The identified talents and areas of strength are organized in a report format and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0296] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a child who excels in math might get a plan incorporating math puzzles and advanced problem-solving activities, while a child interested in music might be offered a plan to study music theory or practice an instrument.

[0297] Finally, the customized coaching plan is sent from the server to the user's device. The user can access the plan through their device and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of strength, and as a result, it is expected that they will develop more effectively.

[0298] For example, consider the case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0299] This system allows for a personalized learning approach based on each child's talents and areas of strength, solving the challenges facing the existing education system.

[0300] The processing flow will be explained below.

[0301] Step 1:

[0302] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0303] Step 2:

[0304] The terminal sends the entered data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0305] Step 3:

[0306] The server retrieves the training data stored in the database and performs a complex analysis using machine learning algorithms, using a combination of supervised and unsupervised learning techniques to extract patterns and trends from the data.

[0307] Step 4:

[0308] The server uses the analysis results to identify a child's potential talents and areas of expertise. This identification process takes into account multiple evaluation criteria (e.g., test scores and extracurricular activity performance) and makes a comprehensive judgment.

[0309] Step 5:

[0310] The server creates a customized coaching plan based on the identified talents and areas of strength, including specific learning activities and materials to use. For example, a child who shows talent in math will receive a plan that includes math puzzles and applied problems.

[0311] Step 6:

[0312] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0313] Step 7:

[0314] Users receive coaching plans via their device and incorporate them into their child's daily learning activities. They regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0315] For example, if Student A is interested in math and music, the user can input this data and the server can analyze it to determine that Student A has high grades in math and also has excellent musical performance skills. Based on this, the server can create a customized plan for Student A that includes math puzzles and music theory exercises and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0316] Example 1

[0317] 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."

[0318] In traditional education systems, it is difficult to identify a child's individual talents and areas of strength and provide a personalized learning plan based on them. It is also extremely time-consuming and laborious for parents and educators to manually collect and analyze children's learning data. This can result in children's potential talents being overlooked.

[0319] 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.

[0320] In this invention, the server includes a means for inputting a child's learning data via an input interface, a means for storing the input data in a database, a means for comprehensively analyzing the collected data using a generative AI model, a means for identifying the child's potential talents and areas of expertise based on the analysis results, a means for creating a customized educational plan based on the identified areas, and a means for providing the customized educational plan. This makes it possible to quickly and accurately identify each child's individual talents and areas of expertise and provide an individualized learning plan based on these.

[0321] An "input interface" is a screen, form, or other means by which a user inputs their child's learning data via a terminal.

[0322] A "database" is a system for safely and efficiently storing, managing, and searching collected learning data.

[0323] A "generative AI model" is a type of artificial intelligence that learns from large amounts of data and performs data analysis and predictions.

[0324] "Comprehensive analysis" means analyzing collected data from multiple angles and processing it to extract patterns and trends.

[0325] "Potential talent" is talent that is not clearly manifested at present but shows high ability or potential in a particular field.

[0326] A "strength area" is an area in which a child has a particular interest and excels.

[0327] An "educational plan" is a plan that combines the most appropriate learning content and activities based on a child's talents and areas of expertise.

[0328] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized educational plans. Specific embodiments of this system are described below.

[0329] Users first use their device to access a dedicated application or web interface. This interface is designed for easy data entry, allowing users to easily input their child's learning data. For example, test scores, extracurricular activity results, and daily behavior records are handled as input data. Software such as the "EduTrack app" or "EduTrack web portal" can be used.

[0330] The input learning data is sent by the device to the server, which encrypts the data to ensure its security. After receiving the data, the server stores it in a database such as Amazon RDS or MySQL.

[0331] The server then uses a generative AI model to analyze the collected data in a complex manner. This analysis uses machine learning libraries such as TensorFlow and PyTorch to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores well on math tests, the server can determine that the child is mathematically gifted.

[0332] Based on the analysis results, the server identifies the child's potential talents and areas of expertise. After this identification, the server compiles the results in the form of a report and provides it to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0333] The server then uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, a child who excels in math might have a plan that includes math puzzles and advanced problem-solving activities. The plan is designed to allow users to select the learning content and activities that are best suited to the target learner.

[0334] The customized educational plan is sent to the user's device, where the user can access it and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of expertise, and is expected to result in more effective development.

[0335] For example, consider a case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0336] Below are some examples of prompts to input to a generative AI model.

[0337] "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents."

[0338] This system allows for a personalized learning approach based on a child's talents and areas of strength, solving the problems inherent in traditional education systems.

[0339] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0340] Step 1:

[0341] Users use their devices to access a dedicated application or web interface. This interface is software such as the "EduTrack App" or "EduTrack Web Portal," and is designed to facilitate data entry. Inputs here include a child's test scores (e.g., math test result: 95 points) and extracurricular activity results (daily records: piano playing records). The output is the input learning data.

[0342] Step 2:

[0343] The training data entered by the user is sent to the server by the terminal. The entered data is encrypted to ensure security. The server stores this data in a database such as "Amazon RDS" or "MySQL." The input here is the encrypted training data, and the output is the training data stored in the database.

[0344] Step 3:

[0345] The server preprocesses the training data stored in the database. This preprocessing uses data processing libraries such as "Pandas" and "NumPy." Specifically, the received data is cleaned and normalized. For example, "Math test score: 95 points" is normalized by comparing it with other scores. The input here is the training data in the database, and the output is the preprocessed data.

[0346] Step 4:

[0347] The server analyzes the preprocessed data using a generative AI model. This analysis uses machine learning libraries such as TensorFlow and PyTorch. The server extracts a child's learning patterns and behavioral trends based on past data. For example, consistently high math test scores indicate strong mathematical intuition. The input here is the preprocessed data, and the output is the analysis results.

[0348] Step 5:

[0349] The server identifies the child's potential talents and areas of expertise based on the analysis results. The talents and areas of expertise identified through the analysis are organized in a report format. This report includes the child's current performance, a comparison with the Japanese average, recommended study methods, and so on. For example, it may state "Mathematical talent: High" or "Recommended study method: Solving math puzzles." The input here is the analysis results, and the output is specific information in the form of a report.

[0350] Step 6:

[0351] The server uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, for a child who excels in math, a plan incorporating math puzzles and advanced problem-solving activities is created. The AI ​​model receives a prompt such as, "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents." The input is specific information, and the output is a customized educational plan.

[0352] Step 7:

[0353] The server sends the generated customized educational plan to the device. The user accesses this plan via the device and incorporates it into their child's daily learning. For example, the educational plan provided by the server can be checked and implemented using the "EduTrack app." The input here is the customized educational plan, and the output is the progress of learning based on the plan.

[0354] Through these steps, the system collects and analyzes children's learning data and provides personalized learning plans to maximize their potential.

[0355] (Application example 1)

[0356] 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."

[0357] The current education system struggles to identify each child's potential talents and areas of expertise and provide them with personalized learning plans. It also lacks appropriate methods for providing engaging and effective learning experiences. It is particularly difficult to provide real-time feedback and an immersive learning environment. To address these issues, more advanced analytical techniques and interactive learning methods are needed.

[0358] 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.

[0359] In this invention, the server includes means for collecting learning data of a child using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, and means for providing a customized learning experience in a virtual reality space. This makes it possible to provide a customized plan that meets the individual learning needs of each child and to provide an interactive and immersive learning experience in a virtual reality space.

[0360] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to analyze data and output results or products based on specific goals.

[0361] A "virtual reality space" is a virtual 3D environment generated using computer technology in which users can have interactive experiences and activities.

[0362] "Learning data" refers to all information related to a child's learning, including test results, extracurricular activities, daily behavior, and other data.

[0363] "Potential talent" refers to the abilities and areas of expertise that a child may have but have not yet manifested.

[0364] "Strengths" refers to areas of learning or activity in which a child excels or has a strong interest compared to other areas.

[0365] A "customized coaching plan" refers to a learning plan or instructional methodology specifically designed for each child based on their individual talents and interests.

[0366] "Analysis" refers to the process of examining collected learning data in detail to find patterns and trends.

[0367] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized learning experiences using virtual reality spaces.

[0368] First, users (parents or educators) enter their child's learning data via smartphone. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data using a dedicated application. This application has the function of sending the data to a database such as Firebase Firestore.

[0369] The server then collects the data and stores it in a database. The collected data is analyzed using GPT-4 and other machine learning algorithms (e.g., scikit-learn). The analysis involves extracting a child's learning patterns and behavioral trends. For example, analyzing high math grades or music performance records can identify a child's mathematical or musical talents.

[0370] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This information is organized in the form of a report and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0371] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a math-savvy child might have a plan that includes math puzzles and advanced problem-solving activities, while a musically-inclined child might have a plan that includes music theory lessons and instrument practice.

[0372] Furthermore, the customized coaching plan is implemented in a virtual reality space. Unity is used to create the virtual environment, which provides an immersive learning experience for children through a head-mounted display (e.g., Oculus Rift, PlayStation VR). Within this virtual environment, children can solve problems, conduct experiments, and play music.

[0373] For example, if a student is interested in science and art, the user enters that information into the application. The server analyzes this information and provides plans for science experiments and art projects in a virtual reality space. The student can learn in a virtual laboratory or art studio.

[0374] An example of a prompt is as follows:

[0375] Analyze student learning data and create lesson plans focused on science and art. Deliver virtual reality learning experiences that include science experiments and art projects.

[0376] The system provides an effective learning environment by offering customized plans tailored to each child's individual learning needs and by providing an interactive and immersive learning experience in a virtual reality space.

[0377] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0378] Step 1:

[0379] Users use a dedicated smartphone application to enter their child's learning data (test results, extracurricular activity results, daily behavior records, etc.).

[0380] Input: Test results, extracurricular activity results, daily activity records, etc.

[0381] Output: The collected training data is ready to be sent to the server.

[0382] Step 2:

[0383] The device sends the collected data to a database such as Firebase Firestore.

[0384] Input: Training data entered by the user.

[0385] Output: Training data stored securely in a database.

[0386] How it works: The smartphone application sends data to FIREBASE, where it is stored securely and quickly.

[0387] Step 3:

[0388] The server retrieves the collected data from the database and performs complex analysis of the data using generative AI (GPT-4) and machine learning algorithms (scikit-learn).

[0389] Input: Training data stored in a database.

[0390] Output: Analysis results that extract children's learning patterns and behavioral tendencies.

[0391] Specific operation: The server issues a query to the database and analyzes the data using analytical algorithms.

[0392] Step 4:

[0393] Based on the analysis results, the server identifies the child's potential talents and areas of expertise and organizes them in a report format.

[0394] Input: Analysis results.

[0395] Output: A report on your child's potential talents and areas of expertise.

[0396] Specific operation: The generative AI evaluates the analysis results and creates a report in a format that is easy for the user to understand.

[0397] Step 5:

[0398] Create a customized coaching plan based on the server's identified strengths and talents.

[0399] Input: Potential talent and strengths report.

[0400] Output: A customized coaching plan.

[0401] Specific operation: The server uses a guidance template to generate a plan tailored to individual learning needs.

[0402] Step 6:

[0403] The server implements the customized coaching plan in a virtual reality space and provides it using a head-mounted display.

[0404] Enter: a customized coaching plan.

[0405] Output: A learning experience in a virtual reality space.

[0406] Specific Action: Use Unity to build a virtual environment and reflect specific learning activities in a virtual reality space.

[0407] Step 7:

[0408] The user allows the child to experience virtual reality learning through a head-mounted display.

[0409] Input: Learning experiences in virtual reality spaces.

[0410] Output: Interactive learning activities that children can experience firsthand.

[0411] Specific actions: Children wear a head-mounted display and learn and experiment in a virtual environment.

[0412] 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.

[0413] This invention combines a system that uses generative AI to collect and analyze children's learning data, identifies potential talents and areas of strength, and provides personalized coaching plans with an emotion engine. This system enables a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0414] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0415] The server then collects the data sent from the device and securely stores it in a database. At the same time, the device acquires the user's facial expression, voice, and text data and analyzes them through an emotion engine. The emotion engine then uses this data to recognize the user's emotional state in real time and transmits the results to the server.

[0416] The server integrates the learning data and the emotional data obtained by the emotion engine, and performs a comprehensive analysis using generative AI. This analysis uses machine learning algorithms and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[0417] Next, the server uses the analysis results to identify the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress while performing that task, the server can reconsider coaching in that area.

[0418] The server then uses the results of these analyses to create a customized coaching plan. By incorporating emotional data, it can determine the most effective learning method for each child. For example, if a child performs well in low-stress situations, it can recommend a relaxing learning environment.

[0419] The server then sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user can regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0420] For example, if Student A is interested in math and music, the user can input this data into their device and the server will analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine will also determine that Student A has a high stress level. Based on this information, the server will create a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0421] This system enables personalized learning approaches based on a child's talents and areas of expertise, and also provides educational support that takes into account their emotional state, improving children's learning efficiency and helping them to continue learning with sustained high motivation.

[0422] The processing flow will be explained below.

[0423] Step 1:

[0424] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0425] Step 2:

[0426] The device sends the input learning data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0427] Step 3:

[0428] The device transmits the learning data and simultaneously acquires the user's facial expression, voice, and text data, which are collected in real time with the user's consent.

[0429] Step 4:

[0430] The device sends the collected facial, voice, and text data to the emotion engine, which analyzes the data and determines the user's emotional state. The determination results include emotions such as stress, excitement, and relaxation.

[0431] Step 5:

[0432] The emotion engine sends the determined emotional state to the server, which combines the learning data with the emotion data and stores it securely.

[0433] Step 6:

[0434] The server inputs the collected learning data and emotional data into the AI ​​generator, which then performs a comprehensive analysis using machine learning algorithms and data mining techniques to derive a comprehensive result that takes into account the child's learning patterns, behavioral tendencies, and emotional state.

[0435] Step 7:

[0436] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress when performing that task, the server can reconsider the coaching content in that area.

[0437] Step 8:

[0438] The server then creates a customized coaching plan based on the identified talents and areas of strength. The plan includes specific learning activities and materials to use, and incorporates emotional data to determine how a child will learn most effectively. For example, if a child performs better in a relaxed environment, the server will recommend learning methods that take advantage of that environment.

[0439] Step 9:

[0440] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0441] Step 10:

[0442] The user then integrates the coaching plan received from the device into their child's daily learning activities. The user periodically checks progress and enters additional data as needed, allowing the system to provide continuous, optimized support.

[0443] For example, if Student A is interested in math and music, the user can input this data into their device and the server can analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine can also determine that Student A has high stress levels. Based on this information, the server creates a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provides it to the user. The user can then implement this plan to maximize Student A's talents. This system enables personalized learning approaches based on a child's talents and areas of expertise, and can also provide educational support that takes their emotional state into account.

[0444] Example 2

[0445] 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."

[0446] Current education systems struggle to provide personalized educational approaches that fully consider each child's learning progress and emotional state. This can result in ineffectively drawing out a child's talents and areas of expertise, leading to a decline in learning efficiency and motivation. Furthermore, creating learning plans without considering a child's emotional state risks increasing stress and anxiety. Therefore, there is a need for a system that can comprehensively analyze learning data and emotional data to bring out a child's potential talents.

[0447] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generation AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means including an emotion engine for collecting and analyzing emotion data, and means for integrating and analyzing the emotion data and the learning data. This provides an individualized learning approach based on the child's talents and areas of expertise and enables educational support that takes into account the child's emotional state, thereby improving learning efficiency and maintaining sustainable motivation.

[0448] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data, particularly utilizing machine learning and natural language processing.

[0449] "Educational data" refers to various educational data such as a child's learning progress, test results, extracurricular activity results, and areas of interest.

[0450] "Composite analysis methods" are methods that integrate collected data and analyze it from multiple perspectives using machine learning algorithms and data mining techniques.

[0451] "Potential talent" refers to a child's abilities and characteristics that are not currently clearly manifested but have the potential to blossom with appropriate support.

[0452] "Strengths" refer to specific academic areas or activities in which a child excels more than others.

[0453] "Customized coaching plan" refers to an individualized educational support program created based on a specific individual's learning and emotional data.

[0454] "Emotional data" refers to data that indicates the psychological state of a user obtained from facial expressions, voice, and text.

[0455] "Emotion engine" refers to software or a system for analyzing collected emotional data and recognizing emotional states.

[0456] "Means for integrated analysis" refers to a method for processing training data and emotion data in a unified manner and conducting comprehensive analysis.

[0457] "Machine learning algorithms" refer to computational methods and models that learn patterns and rules from data and make predictions and classifications.

[0458] "Data mining technology" refers to an analytical method for extracting useful information and insights from large data sets.

[0459] This invention combines an emotion engine with a system that uses a generative AI model to collect and analyze children's learning data, identify potential talents and areas of expertise, and then provides customized coaching plans. This allows for a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0460] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, and the children's areas of interest. The device provides dedicated applications and web interfaces to make it easy for users to input data. For example, if Student A is interested in mathematics and music, that information is also entered.

[0461] The device then temporarily stores the learning data entered by the user and sends it to a server via the internet. At the same time, the device also collects facial expressions and voice data from the user via a camera and microphone. This data is then analyzed in real time by the emotion engine.

[0462] The server receives the training data and emotion data sent from the device and stores them in a secure database. The server uses, for example, an SQL database as the database. The server performs an initial analysis, checks the consistency of the data, and verifies whether any data is missing.

[0463] The emotion engine analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. For example, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and sends the analysis results to the server.

[0464] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (such as GPT-4 or BERT). This analysis uses machine learning algorithms (such as random forests or k-nearest neighbors) and data mining techniques (such as puppetry). Based on the analysis results, the server identifies a child's potential talents and areas of expertise. For example, it may be discovered that Student A has high grades in math, but experiences increased stress during tests.

[0465] The server then uses these analysis results to create a customized coaching plan, which could include things like math puzzles incorporating relaxation exercises or music practice strategies for calmer emotional situations. For example, the generative AI model might be prompted with the following prompt: "Generate a new coaching plan for Student A based on his or her latest emotional state and learning progress."

[0466] The server then sends the generated customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user periodically checks their child's learning progress and emotional state and inputs new data as needed. This allows the system to provide continuously optimized support.

[0467] This system provides an individualized learning approach and enables educational support that takes into account children's emotional state, thereby improving children's learning efficiency and maintaining sustained motivation.

[0468] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0469] Step 1:

[0470] Users enter their child's learning data using a dedicated application or web interface. This data includes daily learning progress, test results, extracurricular activity results, and areas of interest. For example, they enter information such as "Math test result: 90 points, Music lesson results: 50 minutes of piano practice." The entered data is temporarily stored on the device.

[0471] Step 2:

[0472] The device temporarily stores the learning data entered by the user and then sends it to a server via the Internet. Specifically, data such as learning progress and test results are packaged in packets in JSON format and sent to the server using a secure protocol (e.g., HTTPS). The input is the learning data, and the output is the data packet sent to the server.

[0473] Step 3:

[0474] The device also simultaneously collects the user's facial and voice data. It uses a camera and microphone to capture facial and voice data and sends it to the emotion engine for real-time analysis. Specifically, it sends video data to a facial recognition API and voice data to an emotion analysis API. The input is facial and voice data, and the output is a dataset of the analysis results.

[0475] Step 4:

[0476] The server receives the training data and emotion data sent from the device and stores them in a secure database (e.g., SQL database). Before storing the data in the database, the server first checks the integrity of the data and confirms that there is no missing data. The input is the data received from the device, and the output is a notification that storage to the database is complete.

[0477] Step 5:

[0478] The emotion engine in the server analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. Specifically, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and stores these analysis results in a database. The input is emotion data, and the output is analyzed emotion information.

[0479] Step 6:

[0480] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (e.g., GPT-4 or BERT). Specifically, it analyzes children's learning patterns and behavioral trends using machine learning algorithms (e.g., random forests and k-nearest neighbors) and data mining techniques. The input is the integrated learning data and emotion data, and the output is the analysis results.

[0481] Step 7:

[0482] The server creates a customized coaching plan based on the analysis results. For example, it may include math puzzles incorporating relaxation exercises or music practice methods in emotionally calm situations. Specifically, the generative AI model receives a prompt: "Generate a new coaching plan based on Student A's latest emotional state and learning progress." The input is the analysis results, and the output is a customized coaching plan.

[0483] Step 8:

[0484] The server sends the generated customized coaching plan to the terminal. The user can access this plan through the terminal and incorporate it into their daily learning activities. Specifically, the plan is displayed through an application or web interface, and the user can reflect it in their learning activities. The input is the customized coaching plan, and the output is information on how it is applied to the user's learning activities.

[0485] Step 9:

[0486] The user periodically checks their learning progress and emotional state and inputs new data as needed. This allows the system to always provide optimized support based on the latest data. The input is new learning data and emotional data, and the output is updated data sent to the server.

[0487] This system improves children's learning efficiency and enables them to continue learning with sustained high motivation.

[0488] (Application example 2)

[0489] 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."

[0490] Conventional learning support systems often only consider a child's learning progress and ignore their emotional state, resulting in suboptimal learning performance. This makes it difficult for parents and educators to create personalized educational plans for each child, making it difficult to provide effective learning support. Furthermore, the lack of real-time emotional state monitoring makes it difficult to quickly identify and address learning stressors.

[0491] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means for analyzing the child's emotional state using an emotion engine and for integrated processing of the learning data and the emotional data, means for a parent or educator to input learning data through a terminal and monitor the emotional state, and means for transmitting a customized coaching plan to the terminal based on the data analysis results and continuously optimizing it. This enables the provision of more effective and personalized educational support that takes into account not only the child's learning progress but also their emotional state.

[0492] "Generative AI" is a technology that uses artificial intelligence to generate new data and information from large amounts of data.

[0493] "Learning data" refers to various information related to learning activities, such as a child's learning progress, test results, extracurricular activity data, and emotional state data written in diary format.

[0494] "Complex analysis" means integrating collected learning data and emotional data and analyzing them using machine learning algorithms and facial recognition technology.

[0495] "Potential talent" refers to abilities or areas of expertise that are not yet apparent but have the potential to be demonstrated with the right environment and guidance.

[0496] "Strengths" refer to areas of study or activity in which a child can perform particularly well.

[0497] A "customized coaching plan" is a specific plan that identifies and implements the teaching methods and learning tasks that are best suited to each individual child.

[0498] An "emotion engine" refers to a system that uses facial recognition technology and voice analysis to analyze a user's emotional state in real time.

[0499] "Device" refers to an electronic device, such as a smartphone, tablet, or computer, used by a parent or educator to input learning data or monitor emotional states.

[0500] "Integrated processing" means processing multiple types of collected data in a unified manner and conducting comprehensive analysis.

[0501] "Monitoring" means collecting and analyzing data in real time or near real time and observing the results.

[0502] "Continuous optimization" means constantly improving systems and plans based on acquired data and analysis results.

[0503] This invention is a system that uses generative AI to collect and analyze children's learning data, combines it with an emotion engine, and provides personalized coaching plans. Specific methods for implementing the system are described below.

[0504] First, the user (parent or educator) must enter their child's learning data through a device, which can be a smartphone, tablet, or computer. This data includes daily learning progress, test results, extracurricular activity results, and emotional states recorded in diary format. This allows the user to centrally manage their child's learning activities and emotional states.

[0505] The device then uses a camera or microphone to collect facial and voice data from the child. This data is then analyzed by an emotion engine to recognize the child's emotional state in real time. The emotion engine uses machine learning libraries such as TensorFlow and Keras, and includes a combination of facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library).

[0506] The device transmits the collected learning and emotional data to a server, which securely stores this data in a database and performs a complex analysis using a generative AI model. This analysis uses machine learning algorithms and facial recognition technology, and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[0507] Based on the analysis, the server identifies potential talents and areas of strength for the child. For example, if a child shows high achievement in math or music but is experiencing stress, the server can adjust coaching in those areas.

[0508] Finally, the server creates a customized coaching plan and sends it to the device. The user can access the plan through the device and continuously support their learning activities. The user can also add new data from time to time, allowing the system to continuously optimize the plan.

[0509] As a concrete example, consider the case where Student A is interested in math and music. In this case, a parent or educator inputs this data into the device, and the server analyzes it. The analysis results show that Student A has high math grades and excellent musical performance skills, but the emotion engine identifies high stress levels. Based on this information, the server creates and provides a plan to the user that includes math puzzles with relaxation exercises and music practice methods that allow students to learn while having fun.

[0510] The server then uses this data to run a generative AI model based on the following example prompt: "These are the results of a math test. Please analyze the data, including my emotional state, to generate a low-stress, effective study plan."

[0511] Through the above process, the present invention is able to provide effective and personalized educational support that takes into account not only a child's learning progress but also their emotional state.

[0512] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0513] Step 1:

[0514] The user uses a device to input their child's learning data. This data includes daily learning progress, test results, extracurricular activity results, and emotional states described in diary format. The input data is designed to be easily entered through the device's interface. The output of the input data is saved as learning data for use in subsequent processing steps.

[0515] Step 2:

[0516] The device uses a camera or microphone to collect facial and voice data from the child. This data is acquired in real time and sent to the emotion engine. The emotion engine analyzes the collected image and voice data to recognize the child's emotional state. Specifically, it uses facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library). The input is facial and voice data, and the output is the analysis result of the child's emotional state.

[0517] Step 3:

[0518] The device sends the collected training data and emotion data to a server, which stores this data securely in a database. The input is the training data and emotion data, and the output is a database entry stored on the server.

[0519] Step 4:

[0520] The server uses a generative AI model to perform a complex analysis of the collected data. This analysis uses machine learning algorithms and facial recognition technology. Data mining technology is used to determine the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state. The input is the stored learning data and emotional data, and the output is the analysis results.

[0521] Step 5:

[0522] The server identifies the child's potential talents and areas of strength based on the analysis results. This process takes into account performance data in specific academic subjects and activities, as well as emotional state, to make a comprehensive assessment. The input is the analysis results, and the output is the identified talents and areas of strength.

[0523] Step 6:

[0524] The server creates a customized coaching plan based on the identified areas. For example, if the person is feeling stressed, it suggests learning methods that incorporate stress reduction techniques. Specific learning tasks and teaching methods are determined at this stage. The input is the identified talents and areas of strength, and the output is a customized coaching plan.

[0525] Step 7:

[0526] The server sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into the child's learning activities. The device can also monitor the progress of the implemented plan and add new data. The input is the customized coaching plan, and the output is the specific learning activities that the user will carry out.

[0527] Through the above steps, the present invention can provide personalized educational support that takes into consideration a child's learning progress and emotional state in an integrated manner.

[0528] 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.

[0529] 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.

[0530] 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.

[0531] [Third embodiment]

[0532] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0533] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0534] 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).

[0535] 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.

[0536] 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.

[0537] 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).

[0538] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] 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.

[0543] 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."

[0544] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized coaching plans.

[0545] First, users (parents or educators) input various learning data about their children via a device. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data into the device using a dedicated application or web interface. This interface is designed to simplify data entry, allowing users to enter data easily.

[0546] The server then collects the data sent from the device and stores it in a database, ensuring that the collected data is securely stored and available for subsequent analysis.

[0547] The collected data is then analyzed on a server using generative AI. This analysis uses machine learning algorithms and data mining techniques to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores well in math tests, this could be used to determine whether they have a talent for math.

[0548] The server then uses the analysis results to identify the child's potential talents and areas of strength. The identified talents and areas of strength are organized in a report format and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0549] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a child who excels in math might get a plan incorporating math puzzles and advanced problem-solving activities, while a child interested in music might be offered a plan to study music theory or practice an instrument.

[0550] Finally, the customized coaching plan is sent from the server to the user's device. The user can access the plan through their device and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of strength, and as a result, it is expected that they will develop more effectively.

[0551] For example, consider the case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0552] This system allows for a personalized learning approach based on each child's talents and areas of strength, solving the challenges facing the existing education system.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0556] Step 2:

[0557] The terminal sends the entered data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0558] Step 3:

[0559] The server retrieves the training data stored in the database and performs a complex analysis using machine learning algorithms, using a combination of supervised and unsupervised learning techniques to extract patterns and trends from the data.

[0560] Step 4:

[0561] The server uses the analysis results to identify a child's potential talents and areas of expertise. This identification process takes into account multiple evaluation criteria (e.g., test scores and extracurricular activity performance) and makes a comprehensive judgment.

[0562] Step 5:

[0563] The server creates a customized coaching plan based on the identified talents and areas of strength, including specific learning activities and materials to use. For example, a child who shows talent in math will receive a plan that includes math puzzles and applied problems.

[0564] Step 6:

[0565] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0566] Step 7:

[0567] Users receive coaching plans via their device and incorporate them into their child's daily learning activities. They regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0568] For example, if Student A is interested in math and music, the user can input this data and the server can analyze it to determine that Student A has high grades in math and also has excellent musical performance skills. Based on this, the server can create a customized plan for Student A that includes math puzzles and music theory exercises and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0569] Example 1

[0570] 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."

[0571] In traditional education systems, it is difficult to identify a child's individual talents and areas of strength and provide a personalized learning plan based on them. It is also extremely time-consuming and laborious for parents and educators to manually collect and analyze children's learning data. This can result in children's potential talents being overlooked.

[0572] 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.

[0573] In this invention, the server includes a means for inputting a child's learning data via an input interface, a means for storing the input data in a database, a means for comprehensively analyzing the collected data using a generative AI model, a means for identifying the child's potential talents and areas of expertise based on the analysis results, a means for creating a customized educational plan based on the identified areas, and a means for providing the customized educational plan. This makes it possible to quickly and accurately identify each child's individual talents and areas of expertise and provide an individualized learning plan based on these.

[0574] An "input interface" is a screen, form, or other means by which a user inputs their child's learning data via a terminal.

[0575] A "database" is a system for safely and efficiently storing, managing, and searching collected learning data.

[0576] A "generative AI model" is a type of artificial intelligence that learns from large amounts of data and performs data analysis and predictions.

[0577] "Comprehensive analysis" means analyzing collected data from multiple angles and processing it to extract patterns and trends.

[0578] "Potential talent" is talent that is not clearly manifested at present but shows high ability or potential in a particular field.

[0579] A "strength area" is an area in which a child has a particular interest and excels.

[0580] An "educational plan" is a plan that combines the most appropriate learning content and activities based on a child's talents and areas of expertise.

[0581] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized educational plans. Specific embodiments of this system are described below.

[0582] Users first use their device to access a dedicated application or web interface. This interface is designed for easy data entry, allowing users to easily input their child's learning data. For example, test scores, extracurricular activity results, and daily behavior records are handled as input data. Software such as the "EduTrack app" or "EduTrack web portal" can be used.

[0583] The input learning data is sent by the device to the server, which encrypts the data to ensure its security. After receiving the data, the server stores it in a database such as Amazon RDS or MySQL.

[0584] The server then uses a generative AI model to analyze the collected data in a complex manner. This analysis uses machine learning libraries such as TensorFlow and PyTorch to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores well on math tests, the server can determine that the child is mathematically gifted.

[0585] Based on the analysis results, the server identifies the child's potential talents and areas of expertise. After this identification, the server compiles the results in the form of a report and provides it to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0586] The server then uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, a child who excels in math might have a plan that includes math puzzles and advanced problem-solving activities. The plan is designed to allow users to select the learning content and activities that are best suited to the target learner.

[0587] The customized educational plan is sent to the user's device, where the user can access it and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of expertise, and is expected to result in more effective development.

[0588] For example, consider a case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0589] Below are some examples of prompts to input to a generative AI model.

[0590] "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents."

[0591] This system allows for a personalized learning approach based on a child's talents and areas of strength, solving the problems inherent in traditional education systems.

[0592] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0593] Step 1:

[0594] Users use their devices to access a dedicated application or web interface. This interface is software such as the "EduTrack App" or "EduTrack Web Portal," and is designed to facilitate data entry. Inputs here include a child's test scores (e.g., math test result: 95 points) and extracurricular activity results (daily records: piano playing records). The output is the input learning data.

[0595] Step 2:

[0596] The training data entered by the user is sent to the server by the terminal. The entered data is encrypted to ensure security. The server stores this data in a database such as "Amazon RDS" or "MySQL." The input here is the encrypted training data, and the output is the training data stored in the database.

[0597] Step 3:

[0598] The server preprocesses the training data stored in the database. This preprocessing uses data processing libraries such as "Pandas" and "NumPy." Specifically, the received data is cleaned and normalized. For example, "Math test score: 95 points" is normalized by comparing it with other scores. The input here is the training data in the database, and the output is the preprocessed data.

[0599] Step 4:

[0600] The server analyzes the preprocessed data using a generative AI model. This analysis uses machine learning libraries such as TensorFlow and PyTorch. The server extracts a child's learning patterns and behavioral trends based on past data. For example, consistently high math test scores indicate strong mathematical intuition. The input here is the preprocessed data, and the output is the analysis results.

[0601] Step 5:

[0602] The server identifies the child's potential talents and areas of expertise based on the analysis results. The talents and areas of expertise identified through the analysis are organized in a report format. This report includes the child's current performance, a comparison with the Japanese average, recommended study methods, and so on. For example, it may state "Mathematical talent: High" or "Recommended study method: Solving math puzzles." The input here is the analysis results, and the output is specific information in the form of a report.

[0603] Step 6:

[0604] The server uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, for a child who excels in math, a plan incorporating math puzzles and advanced problem-solving activities is created. The AI ​​model receives a prompt such as, "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents." The input is specific information, and the output is a customized educational plan.

[0605] Step 7:

[0606] The server sends the generated customized educational plan to the device. The user accesses this plan via the device and incorporates it into their child's daily learning. For example, the educational plan provided by the server can be checked and implemented using the "EduTrack app." The input here is the customized educational plan, and the output is the progress of learning based on the plan.

[0607] Through these steps, the system collects and analyzes children's learning data and provides personalized learning plans to maximize their potential.

[0608] (Application example 1)

[0609] 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."

[0610] The current education system struggles to identify each child's potential talents and areas of expertise and provide them with personalized learning plans. It also lacks appropriate methods for providing engaging and effective learning experiences. It is particularly difficult to provide real-time feedback and an immersive learning environment. To address these issues, more advanced analytical techniques and interactive learning methods are needed.

[0611] 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.

[0612] In this invention, the server includes means for collecting learning data of a child using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, and means for providing a customized learning experience in a virtual reality space. This makes it possible to provide a customized plan that meets the individual learning needs of each child and to provide an interactive and immersive learning experience in a virtual reality space.

[0613] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to analyze data and output results or products based on specific goals.

[0614] A "virtual reality space" is a virtual 3D environment generated using computer technology in which users can have interactive experiences and activities.

[0615] "Learning data" refers to all information related to a child's learning, including test results, extracurricular activities, daily behavior, and other data.

[0616] "Potential talent" refers to the abilities and areas of expertise that a child may have but have not yet manifested.

[0617] "Strengths" refers to areas of learning or activity in which a child excels or has a strong interest compared to other areas.

[0618] A "customized coaching plan" refers to a learning plan or instructional methodology specifically designed for each child based on their individual talents and interests.

[0619] "Analysis" refers to the process of examining collected learning data in detail to find patterns and trends.

[0620] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized learning experiences using virtual reality spaces.

[0621] First, users (parents or educators) enter their child's learning data via smartphone. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data using a dedicated application. This application has the function of sending the data to a database such as Firebase Firestore.

[0622] The server then collects the data and stores it in a database. The collected data is analyzed using GPT-4 and other machine learning algorithms (e.g., scikit-learn). The analysis involves extracting a child's learning patterns and behavioral trends. For example, analyzing high math grades or music performance records can identify a child's mathematical or musical talents.

[0623] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This information is organized in the form of a report and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0624] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a math-savvy child might have a plan that includes math puzzles and advanced problem-solving activities, while a musically-inclined child might have a plan that includes music theory lessons and instrument practice.

[0625] Furthermore, the customized coaching plan is implemented in a virtual reality space. Unity is used to create the virtual environment, which provides an immersive learning experience for children through a head-mounted display (e.g., Oculus Rift, PlayStation VR). Within this virtual environment, children can solve problems, conduct experiments, and play music.

[0626] For example, if a student is interested in science and art, the user enters that information into the application. The server analyzes this information and provides plans for science experiments and art projects in a virtual reality space. The student can learn in a virtual laboratory or art studio.

[0627] An example of a prompt is as follows:

[0628] Analyze student learning data and create lesson plans focused on science and art. Deliver virtual reality learning experiences that include science experiments and art projects.

[0629] The system provides an effective learning environment by offering customized plans tailored to each child's individual learning needs and by providing an interactive and immersive learning experience in a virtual reality space.

[0630] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0631] Step 1:

[0632] Users use a dedicated smartphone application to enter their child's learning data (test results, extracurricular activity results, daily behavior records, etc.).

[0633] Input: Test results, extracurricular activity results, daily activity records, etc.

[0634] Output: The collected training data is ready to be sent to the server.

[0635] Step 2:

[0636] The device sends the collected data to a database such as Firebase Firestore.

[0637] Input: Training data entered by the user.

[0638] Output: Training data stored securely in a database.

[0639] How it works: The smartphone application sends data to FIREBASE, where it is stored securely and quickly.

[0640] Step 3:

[0641] The server retrieves the collected data from the database and performs complex analysis of the data using generative AI (GPT-4) and machine learning algorithms (scikit-learn).

[0642] Input: Training data stored in a database.

[0643] Output: Analysis results that extract children's learning patterns and behavioral tendencies.

[0644] Specific operation: The server issues a query to the database and analyzes the data using analytical algorithms.

[0645] Step 4:

[0646] Based on the analysis results, the server identifies the child's potential talents and areas of expertise and organizes them in a report format.

[0647] Input: Analysis results.

[0648] Output: A report on your child's potential talents and areas of expertise.

[0649] Specific operation: The generative AI evaluates the analysis results and creates a report in a format that is easy for the user to understand.

[0650] Step 5:

[0651] Create a customized coaching plan based on the server's identified strengths and talents.

[0652] Input: Potential talent and strengths report.

[0653] Output: A customized coaching plan.

[0654] Specific operation: The server uses a guidance template to generate a plan tailored to individual learning needs.

[0655] Step 6:

[0656] The server implements the customized coaching plan in a virtual reality space and provides it using a head-mounted display.

[0657] Enter: a customized coaching plan.

[0658] Output: A learning experience in a virtual reality space.

[0659] Specific Action: Use Unity to build a virtual environment and reflect specific learning activities in a virtual reality space.

[0660] Step 7:

[0661] The user allows the child to experience virtual reality learning through a head-mounted display.

[0662] Input: Learning experiences in virtual reality spaces.

[0663] Output: Interactive learning activities that children can experience firsthand.

[0664] Specific actions: Children wear a head-mounted display and learn and experiment in a virtual environment.

[0665] 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.

[0666] This invention combines a system that uses generative AI to collect and analyze children's learning data, identifies potential talents and areas of strength, and provides personalized coaching plans with an emotion engine. This system enables a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0667] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0668] The server then collects the data sent from the device and securely stores it in a database. At the same time, the device acquires the user's facial expression, voice, and text data and analyzes them through an emotion engine. The emotion engine then uses this data to recognize the user's emotional state in real time and transmits the results to the server.

[0669] The server integrates the learning data and the emotional data obtained by the emotion engine, and performs a comprehensive analysis using generative AI. This analysis uses machine learning algorithms and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[0670] Next, the server uses the analysis results to identify the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress while performing that task, the server can reconsider coaching in that area.

[0671] The server then uses the results of these analyses to create a customized coaching plan. By incorporating emotional data, it can determine the most effective learning method for each child. For example, if a child performs well in low-stress situations, it can recommend a relaxing learning environment.

[0672] The server then sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user can regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0673] For example, if Student A is interested in math and music, the user can input this data into their device and the server will analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine will also determine that Student A has a high stress level. Based on this information, the server will create a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0674] This system enables personalized learning approaches based on a child's talents and areas of expertise, and also provides educational support that takes into account their emotional state, improving children's learning efficiency and helping them to continue learning with sustained high motivation.

[0675] The processing flow will be explained below.

[0676] Step 1:

[0677] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0678] Step 2:

[0679] The device sends the input learning data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0680] Step 3:

[0681] The device transmits the learning data and simultaneously acquires the user's facial expression, voice, and text data, which are collected in real time with the user's consent.

[0682] Step 4:

[0683] The device sends the collected facial, voice, and text data to the emotion engine, which analyzes the data and determines the user's emotional state. The determination results include emotions such as stress, excitement, and relaxation.

[0684] Step 5:

[0685] The emotion engine sends the determined emotional state to the server, which combines the learning data with the emotion data and stores it securely.

[0686] Step 6:

[0687] The server inputs the collected learning data and emotional data into the AI ​​generator, which then performs a comprehensive analysis using machine learning algorithms and data mining techniques to derive a comprehensive result that takes into account the child's learning patterns, behavioral tendencies, and emotional state.

[0688] Step 7:

[0689] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress when performing that task, the server can reconsider the coaching content in that area.

[0690] Step 8:

[0691] The server then creates a customized coaching plan based on the identified talents and areas of strength. The plan includes specific learning activities and materials to use, and incorporates emotional data to determine how a child will learn most effectively. For example, if a child performs better in a relaxed environment, the server will recommend learning methods that take advantage of that environment.

[0692] Step 9:

[0693] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0694] Step 10:

[0695] The user then integrates the coaching plan received from the device into their child's daily learning activities. The user periodically checks progress and enters additional data as needed, allowing the system to provide continuous, optimized support.

[0696] For example, if Student A is interested in math and music, the user can input this data into their device and the server can analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine can also determine that Student A has high stress levels. Based on this information, the server creates a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provides it to the user. The user can then implement this plan to maximize Student A's talents. This system enables personalized learning approaches based on a child's talents and areas of expertise, and can also provide educational support that takes their emotional state into account.

[0697] Example 2

[0698] 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."

[0699] Current education systems struggle to provide personalized educational approaches that fully consider each child's learning progress and emotional state. This can result in ineffectively drawing out a child's talents and areas of expertise, leading to a decline in learning efficiency and motivation. Furthermore, creating learning plans without considering a child's emotional state risks increasing stress and anxiety. Therefore, there is a need for a system that can comprehensively analyze learning data and emotional data to bring out a child's potential talents.

[0700] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generation AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means including an emotion engine for collecting and analyzing emotion data, and means for integrating and analyzing the emotion data and the learning data. This provides an individualized learning approach based on the child's talents and areas of expertise and enables educational support that takes into account the child's emotional state, thereby improving learning efficiency and maintaining sustainable motivation.

[0701] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data, particularly utilizing machine learning and natural language processing.

[0702] "Educational data" refers to various educational data such as a child's learning progress, test results, extracurricular activity results, and areas of interest.

[0703] "Composite analysis methods" are methods that integrate collected data and analyze it from multiple perspectives using machine learning algorithms and data mining techniques.

[0704] "Potential talent" refers to a child's abilities and characteristics that are not currently clearly manifested but have the potential to blossom with appropriate support.

[0705] "Strengths" refer to specific academic areas or activities in which a child excels more than others.

[0706] "Customized coaching plan" refers to an individualized educational support program created based on a specific individual's learning and emotional data.

[0707] "Emotional data" refers to data that indicates the psychological state of a user obtained from facial expressions, voice, and text.

[0708] "Emotion engine" refers to software or a system for analyzing collected emotional data and recognizing emotional states.

[0709] "Means for integrated analysis" refers to a method for processing training data and emotion data in a unified manner and conducting comprehensive analysis.

[0710] "Machine learning algorithms" refer to computational methods and models that learn patterns and rules from data and make predictions and classifications.

[0711] "Data mining technology" refers to an analytical method for extracting useful information and insights from large data sets.

[0712] This invention combines an emotion engine with a system that uses a generative AI model to collect and analyze children's learning data, identify potential talents and areas of expertise, and then provides customized coaching plans. This allows for a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0713] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, and the children's areas of interest. The device provides dedicated applications and web interfaces to make it easy for users to input data. For example, if Student A is interested in mathematics and music, that information is also entered.

[0714] The device then temporarily stores the learning data entered by the user and sends it to a server via the internet. At the same time, the device also collects facial expressions and voice data from the user via a camera and microphone. This data is then analyzed in real time by the emotion engine.

[0715] The server receives the training data and emotion data sent from the device and stores them in a secure database. The server uses, for example, an SQL database as the database. The server performs an initial analysis, checks the consistency of the data, and verifies whether any data is missing.

[0716] The emotion engine analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. For example, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and sends the analysis results to the server.

[0717] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (such as GPT-4 or BERT). This analysis uses machine learning algorithms (such as random forests or k-nearest neighbors) and data mining techniques (such as puppetry). Based on the analysis results, the server identifies a child's potential talents and areas of expertise. For example, it may be discovered that Student A has high grades in math, but experiences increased stress during tests.

[0718] The server then uses these analysis results to create a customized coaching plan, which could include things like math puzzles incorporating relaxation exercises or music practice strategies for calmer emotional situations. For example, the generative AI model might be prompted with the following prompt: "Generate a new coaching plan for Student A based on his or her latest emotional state and learning progress."

[0719] The server then sends the generated customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user periodically checks their child's learning progress and emotional state and inputs new data as needed. This allows the system to provide continuously optimized support.

[0720] This system provides an individualized learning approach and enables educational support that takes into account children's emotional state, thereby improving children's learning efficiency and maintaining sustained motivation.

[0721] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0722] Step 1:

[0723] Users enter their child's learning data using a dedicated application or web interface. This data includes daily learning progress, test results, extracurricular activity results, and areas of interest. For example, they enter information such as "Math test result: 90 points, Music lesson results: 50 minutes of piano practice." The entered data is temporarily stored on the device.

[0724] Step 2:

[0725] The device temporarily stores the learning data entered by the user and then sends it to a server via the Internet. Specifically, data such as learning progress and test results are packaged in packets in JSON format and sent to the server using a secure protocol (e.g., HTTPS). The input is the learning data, and the output is the data packet sent to the server.

[0726] Step 3:

[0727] The device also simultaneously collects the user's facial and voice data. It uses a camera and microphone to capture facial and voice data and sends it to the emotion engine for real-time analysis. Specifically, it sends video data to a facial recognition API and voice data to an emotion analysis API. The input is facial and voice data, and the output is a dataset of the analysis results.

[0728] Step 4:

[0729] The server receives the training data and emotion data sent from the device and stores them in a secure database (e.g., SQL database). Before storing the data in the database, the server first checks the integrity of the data and confirms that there is no missing data. The input is the data received from the device, and the output is a notification that storage to the database is complete.

[0730] Step 5:

[0731] The emotion engine in the server analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. Specifically, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and stores these analysis results in a database. The input is emotion data, and the output is analyzed emotion information.

[0732] Step 6:

[0733] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (e.g., GPT-4 or BERT). Specifically, it analyzes children's learning patterns and behavioral trends using machine learning algorithms (e.g., random forests and k-nearest neighbors) and data mining techniques. The input is the integrated learning data and emotion data, and the output is the analysis results.

[0734] Step 7:

[0735] The server creates a customized coaching plan based on the analysis results. For example, it may include math puzzles incorporating relaxation exercises or music practice methods in emotionally calm situations. Specifically, the generative AI model receives a prompt: "Generate a new coaching plan based on Student A's latest emotional state and learning progress." The input is the analysis results, and the output is a customized coaching plan.

[0736] Step 8:

[0737] The server sends the generated customized coaching plan to the terminal. The user can access this plan through the terminal and incorporate it into their daily learning activities. Specifically, the plan is displayed through an application or web interface, and the user can reflect it in their learning activities. The input is the customized coaching plan, and the output is information on how it is applied to the user's learning activities.

[0738] Step 9:

[0739] The user periodically checks their learning progress and emotional state and inputs new data as needed. This allows the system to always provide optimized support based on the latest data. The input is new learning data and emotional data, and the output is updated data sent to the server.

[0740] This system improves children's learning efficiency and enables them to continue learning with sustained high motivation.

[0741] (Application example 2)

[0742] 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."

[0743] Conventional learning support systems often only consider a child's learning progress and ignore their emotional state, resulting in suboptimal learning performance. This makes it difficult for parents and educators to create personalized educational plans for each child, making it difficult to provide effective learning support. Furthermore, the lack of real-time emotional state monitoring makes it difficult to quickly identify and address learning stressors.

[0744] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means for analyzing the child's emotional state using an emotion engine and for integrated processing of the learning data and the emotional data, means for a parent or educator to input learning data through a terminal and monitor the emotional state, and means for transmitting a customized coaching plan to the terminal based on the data analysis results and continuously optimizing it. This enables the provision of more effective and personalized educational support that takes into account not only the child's learning progress but also their emotional state.

[0745] "Generative AI" is a technology that uses artificial intelligence to generate new data and information from large amounts of data.

[0746] "Learning data" refers to various information related to learning activities, such as a child's learning progress, test results, extracurricular activity data, and emotional state data written in diary format.

[0747] "Complex analysis" means integrating collected learning data and emotional data and analyzing them using machine learning algorithms and facial recognition technology.

[0748] "Potential talent" refers to abilities or areas of expertise that are not yet apparent but have the potential to be demonstrated with the right environment and guidance.

[0749] "Strengths" refer to areas of study or activity in which a child can perform particularly well.

[0750] A "customized coaching plan" is a specific plan that identifies and implements the teaching methods and learning tasks that are best suited to each individual child.

[0751] An "emotion engine" refers to a system that uses facial recognition technology and voice analysis to analyze a user's emotional state in real time.

[0752] "Device" refers to an electronic device, such as a smartphone, tablet, or computer, used by a parent or educator to input learning data or monitor emotional states.

[0753] "Integrated processing" means processing multiple types of collected data in a unified manner and conducting comprehensive analysis.

[0754] "Monitoring" means collecting and analyzing data in real time or near real time and observing the results.

[0755] "Continuous optimization" means constantly improving systems and plans based on acquired data and analysis results.

[0756] This invention is a system that uses generative AI to collect and analyze children's learning data, combines it with an emotion engine, and provides personalized coaching plans. Specific methods for implementing the system are described below.

[0757] First, the user (parent or educator) must enter their child's learning data through a device, which can be a smartphone, tablet, or computer. This data includes daily learning progress, test results, extracurricular activity results, and emotional states recorded in diary format. This allows the user to centrally manage their child's learning activities and emotional states.

[0758] The device then uses a camera or microphone to collect facial and voice data from the child. This data is then analyzed by an emotion engine to recognize the child's emotional state in real time. The emotion engine uses machine learning libraries such as TensorFlow and Keras, and includes a combination of facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library).

[0759] The device transmits the collected learning and emotional data to a server, which securely stores this data in a database and performs a complex analysis using a generative AI model. This analysis uses machine learning algorithms and facial recognition technology, and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[0760] Based on the analysis, the server identifies potential talents and areas of strength for the child. For example, if a child shows high achievement in math or music but is experiencing stress, the server can adjust coaching in those areas.

[0761] Finally, the server creates a customized coaching plan and sends it to the device. The user can access the plan through the device and continuously support their learning activities. The user can also add new data from time to time, allowing the system to continuously optimize the plan.

[0762] As a concrete example, consider the case where Student A is interested in math and music. In this case, a parent or educator inputs this data into the device, and the server analyzes it. The analysis results show that Student A has high math grades and excellent musical performance skills, but the emotion engine identifies high stress levels. Based on this information, the server creates and provides a plan to the user that includes math puzzles with relaxation exercises and music practice methods that allow students to learn while having fun.

[0763] The server then uses this data to run a generative AI model based on the following example prompt: "These are the results of a math test. Please analyze the data, including my emotional state, to generate a low-stress, effective study plan."

[0764] Through the above process, the present invention is able to provide effective and personalized educational support that takes into account not only a child's learning progress but also their emotional state.

[0765] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0766] Step 1:

[0767] The user uses a device to input their child's learning data. This data includes daily learning progress, test results, extracurricular activity results, and emotional states described in diary format. The input data is designed to be easily entered through the device's interface. The output of the input data is saved as learning data for use in subsequent processing steps.

[0768] Step 2:

[0769] The device uses a camera or microphone to collect facial and voice data from the child. This data is acquired in real time and sent to the emotion engine. The emotion engine analyzes the collected image and voice data to recognize the child's emotional state. Specifically, it uses facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library). The input is facial and voice data, and the output is the analysis result of the child's emotional state.

[0770] Step 3:

[0771] The device sends the collected training data and emotion data to a server, which stores this data securely in a database. The input is the training data and emotion data, and the output is a database entry stored on the server.

[0772] Step 4:

[0773] The server uses a generative AI model to perform a complex analysis of the collected data. This analysis uses machine learning algorithms and facial recognition technology. Data mining technology is used to determine the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state. The input is the stored learning data and emotional data, and the output is the analysis results.

[0774] Step 5:

[0775] The server identifies the child's potential talents and areas of strength based on the analysis results. This process takes into account performance data in specific academic subjects and activities, as well as emotional state, to make a comprehensive assessment. The input is the analysis results, and the output is the identified talents and areas of strength.

[0776] Step 6:

[0777] The server creates a customized coaching plan based on the identified areas. For example, if the person is feeling stressed, it suggests learning methods that incorporate stress reduction techniques. Specific learning tasks and teaching methods are determined at this stage. The input is the identified talents and areas of strength, and the output is a customized coaching plan.

[0778] Step 7:

[0779] The server sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into the child's learning activities. The device can also monitor the progress of the implemented plan and add new data. The input is the customized coaching plan, and the output is the specific learning activities that the user will carry out.

[0780] Through the above steps, the present invention can provide personalized educational support that takes into consideration a child's learning progress and emotional state in an integrated manner.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] [Fourth embodiment]

[0785] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0786] 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.

[0787] 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).

[0788] 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.

[0789] 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.

[0790] 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).

[0791] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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."

[0798] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized coaching plans.

[0799] First, users (parents or educators) input various learning data about their children via a device. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data into the device using a dedicated application or web interface. This interface is designed to simplify data entry, allowing users to enter data easily.

[0800] The server then collects the data sent from the device and stores it in a database, ensuring that the collected data is securely stored and available for subsequent analysis.

[0801] The collected data is then analyzed on a server using generative AI. This analysis uses machine learning algorithms and data mining techniques to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores well in math tests, this could be used to determine whether they have a talent for math.

[0802] The server then uses the analysis results to identify the child's potential talents and areas of strength. The identified talents and areas of strength are organized in a report format and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0803] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a child who excels in math might get a plan incorporating math puzzles and advanced problem-solving activities, while a child interested in music might be offered a plan to study music theory or practice an instrument.

[0804] Finally, the customized coaching plan is sent from the server to the user's device. The user can access the plan through their device and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of strength, and as a result, it is expected that they will develop more effectively.

[0805] For example, consider the case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0806] This system allows for a personalized learning approach based on each child's talents and areas of strength, solving the challenges facing the existing education system.

[0807] The processing flow will be explained below.

[0808] Step 1:

[0809] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0810] Step 2:

[0811] The terminal sends the entered data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0812] Step 3:

[0813] The server retrieves the training data stored in the database and performs a complex analysis using machine learning algorithms, using a combination of supervised and unsupervised learning techniques to extract patterns and trends from the data.

[0814] Step 4:

[0815] The server uses the analysis results to identify a child's potential talents and areas of expertise. This identification process takes into account multiple evaluation criteria (e.g., test scores and extracurricular activity performance) and makes a comprehensive judgment.

[0816] Step 5:

[0817] The server creates a customized coaching plan based on the identified talents and areas of strength, including specific learning activities and materials to use. For example, a child who shows talent in math will receive a plan that includes math puzzles and applied problems.

[0818] Step 6:

[0819] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0820] Step 7:

[0821] Users receive coaching plans via their device and incorporate them into their child's daily learning activities. They regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0822] For example, if Student A is interested in math and music, the user can input this data and the server can analyze it to determine that Student A has high grades in math and also has excellent musical performance skills. Based on this, the server can create a customized plan for Student A that includes math puzzles and music theory exercises and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0823] Example 1

[0824] 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."

[0825] In traditional education systems, it is difficult to identify a child's individual talents and areas of strength and provide a personalized learning plan based on them. It is also extremely time-consuming and laborious for parents and educators to manually collect and analyze children's learning data. This can result in children's potential talents being overlooked.

[0826] 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.

[0827] In this invention, the server includes a means for inputting a child's learning data via an input interface, a means for storing the input data in a database, a means for comprehensively analyzing the collected data using a generative AI model, a means for identifying the child's potential talents and areas of expertise based on the analysis results, a means for creating a customized educational plan based on the identified areas, and a means for providing the customized educational plan. This makes it possible to quickly and accurately identify each child's individual talents and areas of expertise and provide an individualized learning plan based on these.

[0828] An "input interface" is a screen, form, or other means by which a user inputs their child's learning data via a terminal.

[0829] A "database" is a system for safely and efficiently storing, managing, and searching collected learning data.

[0830] A "generative AI model" is a type of artificial intelligence that learns from large amounts of data and performs data analysis and predictions.

[0831] "Comprehensive analysis" means analyzing collected data from multiple angles and processing it to extract patterns and trends.

[0832] "Potential talent" is talent that is not clearly manifested at present but shows high ability or potential in a particular field.

[0833] A "strength area" is an area in which a child has a particular interest and excels.

[0834] An "educational plan" is a plan that combines the most appropriate learning content and activities based on a child's talents and areas of expertise.

[0835] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized educational plans. Specific embodiments of this system are described below.

[0836] Users first use their device to access a dedicated application or web interface. This interface is designed for easy data entry, allowing users to easily input their child's learning data. For example, test scores, extracurricular activity results, and daily behavior records are handled as input data. Software such as the "EduTrack app" or "EduTrack web portal" can be used.

[0837] The input learning data is sent by the device to the server, which encrypts the data to ensure its security. After receiving the data, the server stores it in a database such as Amazon RDS or MySQL.

[0838] The server then uses a generative AI model to analyze the collected data in a complex manner. This analysis uses machine learning libraries such as TensorFlow and PyTorch to extract a child's learning patterns and behavioral trends. For example, if a child consistently scores well on math tests, the server can determine that the child is mathematically gifted.

[0839] Based on the analysis results, the server identifies the child's potential talents and areas of expertise. After this identification, the server compiles the results in the form of a report and provides it to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0840] The server then uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, a child who excels in math might have a plan that includes math puzzles and advanced problem-solving activities. The plan is designed to allow users to select the learning content and activities that are best suited to the target learner.

[0841] The customized educational plan is sent to the user's device, where the user can access it and incorporate it into their child's daily learning. This allows children to receive learning tailored to their talents and areas of expertise, and is expected to result in more effective development.

[0842] For example, consider a case where Student A is interested in mathematics and music. In this case, the user inputs Student A's mathematics test scores and music performance records into the system. The server collects this data and analyzes it with generative AI to identify Student A's mathematical intuition and musical talent. Based on this information, the server creates a customized plan that combines mathematics workbooks and music theory materials and provides it to the user. By implementing this plan with Student A, the user can maximize his talents.

[0843] Below are some examples of prompts to input to a generative AI model.

[0844] "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents."

[0845] This system allows for a personalized learning approach based on a child's talents and areas of strength, solving the problems inherent in traditional education systems.

[0846] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0847] Step 1:

[0848] Users use their devices to access a dedicated application or web interface. This interface is software such as the "EduTrack App" or "EduTrack Web Portal," and is designed to facilitate data entry. Inputs here include a child's test scores (e.g., math test result: 95 points) and extracurricular activity results (daily records: piano playing records). The output is the input learning data.

[0849] Step 2:

[0850] The training data entered by the user is sent to the server by the terminal. The entered data is encrypted to ensure security. The server stores this data in a database such as "Amazon RDS" or "MySQL." The input here is the encrypted training data, and the output is the training data stored in the database.

[0851] Step 3:

[0852] The server preprocesses the training data stored in the database. This preprocessing uses data processing libraries such as "Pandas" and "NumPy." Specifically, the received data is cleaned and normalized. For example, "Math test score: 95 points" is normalized by comparing it with other scores. The input here is the training data in the database, and the output is the preprocessed data.

[0853] Step 4:

[0854] The server analyzes the preprocessed data using a generative AI model. This analysis uses machine learning libraries such as TensorFlow and PyTorch. The server extracts a child's learning patterns and behavioral trends based on past data. For example, consistently high math test scores indicate strong mathematical intuition. The input here is the preprocessed data, and the output is the analysis results.

[0855] Step 5:

[0856] The server identifies the child's potential talents and areas of expertise based on the analysis results. The talents and areas of expertise identified through the analysis are organized in a report format. This report includes the child's current performance, a comparison with the Japanese average, recommended study methods, and so on. For example, it may state "Mathematical talent: High" or "Recommended study method: Solving math puzzles." The input here is the analysis results, and the output is specific information in the form of a report.

[0857] Step 6:

[0858] The server uses a generative AI model to create a customized educational plan based on the identified talents and areas of expertise. For example, for a child who excels in math, a plan incorporating math puzzles and advanced problem-solving activities is created. The AI ​​model receives a prompt such as, "Student A's math test scores average 90 points. He also has an excellent piano performance record. Please suggest a customized plan based on his mathematical and musical talents." The input is specific information, and the output is a customized educational plan.

[0859] Step 7:

[0860] The server sends the generated customized educational plan to the device. The user accesses this plan via the device and incorporates it into their child's daily learning. For example, the educational plan provided by the server can be checked and implemented using the "EduTrack app." The input here is the customized educational plan, and the output is the progress of learning based on the plan.

[0861] Through these steps, the system collects and analyzes children's learning data and provides personalized learning plans to maximize their potential.

[0862] (Application example 1)

[0863] 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."

[0864] The current education system struggles to identify each child's potential talents and areas of expertise and provide them with personalized learning plans. It also lacks appropriate methods for providing engaging and effective learning experiences. It is particularly difficult to provide real-time feedback and an immersive learning environment. To address these issues, more advanced analytical techniques and interactive learning methods are needed.

[0865] 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.

[0866] In this invention, the server includes means for collecting learning data of a child using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, and means for providing a customized learning experience in a virtual reality space. This makes it possible to provide a customized plan that meets the individual learning needs of each child and to provide an interactive and immersive learning experience in a virtual reality space.

[0867] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to analyze data and output results or products based on specific goals.

[0868] A "virtual reality space" is a virtual 3D environment generated using computer technology in which users can have interactive experiences and activities.

[0869] "Learning data" refers to all information related to a child's learning, including test results, extracurricular activities, daily behavior, and other data.

[0870] "Potential talent" refers to the abilities and areas of expertise that a child may have but have not yet manifested.

[0871] "Strengths" refers to areas of learning or activity in which a child excels or has a strong interest compared to other areas.

[0872] A "customized coaching plan" refers to a learning plan or instructional methodology specifically designed for each child based on their individual talents and interests.

[0873] "Analysis" refers to the process of examining collected learning data in detail to find patterns and trends.

[0874] This invention relates to a system that uses generative AI to collect and analyze children's learning data, identify potential talents and areas of expertise, and provide personalized learning experiences using virtual reality spaces.

[0875] First, users (parents or educators) enter their child's learning data via smartphone. This data includes test results, extracurricular activity results, and daily behavior records. Users enter this data using a dedicated application. This application has the function of sending the data to a database such as Firebase Firestore.

[0876] The server then collects the data and stores it in a database. The collected data is analyzed using GPT-4 and other machine learning algorithms (e.g., scikit-learn). The analysis involves extracting a child's learning patterns and behavioral trends. For example, analyzing high math grades or music performance records can identify a child's mathematical or musical talents.

[0877] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This information is organized in the form of a report and provided to the user. The report includes the child's current performance, a comparison with the Japanese average, and recommended study methods.

[0878] The server then creates a customized coaching plan based on the identified strengths and talents: for example, a math-savvy child might have a plan that includes math puzzles and advanced problem-solving activities, while a musically-inclined child might have a plan that includes music theory lessons and instrument practice.

[0879] Furthermore, the customized coaching plan is implemented in a virtual reality space. Unity is used to create the virtual environment, which provides an immersive learning experience for children through a head-mounted display (e.g., Oculus Rift, PlayStation VR). Within this virtual environment, children can solve problems, conduct experiments, and play music.

[0880] For example, if a student is interested in science and art, the user enters that information into the application. The server analyzes this information and provides plans for science experiments and art projects in a virtual reality space. The student can learn in a virtual laboratory or art studio.

[0881] An example of a prompt is as follows:

[0882] Analyze student learning data and create lesson plans focused on science and art. Deliver virtual reality learning experiences that include science experiments and art projects.

[0883] The system provides an effective learning environment by offering customized plans tailored to each child's individual learning needs and by providing an interactive and immersive learning experience in a virtual reality space.

[0884] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0885] Step 1:

[0886] Users use a dedicated smartphone application to enter their child's learning data (test results, extracurricular activity results, daily behavior records, etc.).

[0887] Input: Test results, extracurricular activity results, daily activity records, etc.

[0888] Output: The collected training data is ready to be sent to the server.

[0889] Step 2:

[0890] The device sends the collected data to a database such as Firebase Firestore.

[0891] Input: Training data entered by the user.

[0892] Output: Training data stored securely in a database.

[0893] How it works: The smartphone application sends data to FIREBASE, where it is stored securely and quickly.

[0894] Step 3:

[0895] The server retrieves the collected data from the database and performs complex analysis of the data using generative AI (GPT-4) and machine learning algorithms (scikit-learn).

[0896] Input: Training data stored in a database.

[0897] Output: Analysis results that extract children's learning patterns and behavioral tendencies.

[0898] Specific operation: The server issues a query to the database and analyzes the data using analytical algorithms.

[0899] Step 4:

[0900] Based on the analysis results, the server identifies the child's potential talents and areas of expertise and organizes them in a report format.

[0901] Input: Analysis results.

[0902] Output: A report on your child's potential talents and areas of expertise.

[0903] Specific operation: The generative AI evaluates the analysis results and creates a report in a format that is easy for the user to understand.

[0904] Step 5:

[0905] Create a customized coaching plan based on the server's identified strengths and talents.

[0906] Input: Potential talent and strengths report.

[0907] Output: A customized coaching plan.

[0908] Specific operation: The server uses a guidance template to generate a plan tailored to individual learning needs.

[0909] Step 6:

[0910] The server implements the customized coaching plan in a virtual reality space and provides it using a head-mounted display.

[0911] Enter: a customized coaching plan.

[0912] Output: A learning experience in a virtual reality space.

[0913] Specific Action: Use Unity to build a virtual environment and reflect specific learning activities in a virtual reality space.

[0914] Step 7:

[0915] The user allows the child to experience virtual reality learning through a head-mounted display.

[0916] Input: Learning experiences in virtual reality spaces.

[0917] Output: Interactive learning activities that children can experience firsthand.

[0918] Specific actions: Children wear a head-mounted display and learn and experiment in a virtual environment.

[0919] 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.

[0920] This invention combines a system that uses generative AI to collect and analyze children's learning data, identifies potential talents and areas of strength, and provides personalized coaching plans with an emotion engine. This system enables a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0921] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0922] The server then collects the data sent from the device and securely stores it in a database. At the same time, the device acquires the user's facial expression, voice, and text data and analyzes them through an emotion engine. The emotion engine then uses this data to recognize the user's emotional state in real time and transmits the results to the server.

[0923] The server integrates the learning data and the emotional data obtained by the emotion engine, and performs a comprehensive analysis using generative AI. This analysis uses machine learning algorithms and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[0924] Next, the server uses the analysis results to identify the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress while performing that task, the server can reconsider coaching in that area.

[0925] The server then uses the results of these analyses to create a customized coaching plan. By incorporating emotional data, it can determine the most effective learning method for each child. For example, if a child performs well in low-stress situations, it can recommend a relaxing learning environment.

[0926] The server then sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user can regularly check progress and enter additional data as needed, allowing the system to provide continuous, optimized support.

[0927] For example, if Student A is interested in math and music, the user can input this data into their device and the server will analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine will also determine that Student A has a high stress level. Based on this information, the server will create a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provide it to the user. The user can then implement this plan to maximize Student A's talents.

[0928] This system enables personalized learning approaches based on a child's talents and areas of expertise, and also provides educational support that takes into account their emotional state, improving children's learning efficiency and helping them to continue learning with sustained high motivation.

[0929] The processing flow will be explained below.

[0930] Step 1:

[0931] Users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, areas of interest, etc. The device provides a dedicated application or web interface, making it easy for users to input data.

[0932] Step 2:

[0933] The device sends the input learning data to the server, which uses encryption technology to ensure the security of the data. The server receives the data and stores it in a database.

[0934] Step 3:

[0935] The device transmits the learning data and simultaneously acquires the user's facial expression, voice, and text data, which are collected in real time with the user's consent.

[0936] Step 4:

[0937] The device sends the collected facial, voice, and text data to the emotion engine, which analyzes the data and determines the user's emotional state. The determination results include emotions such as stress, excitement, and relaxation.

[0938] Step 5:

[0939] The emotion engine sends the determined emotional state to the server, which combines the learning data with the emotion data and stores it securely.

[0940] Step 6:

[0941] The server inputs the collected learning data and emotional data into the AI ​​generator, which then performs a comprehensive analysis using machine learning algorithms and data mining techniques to derive a comprehensive result that takes into account the child's learning patterns, behavioral tendencies, and emotional state.

[0942] Step 7:

[0943] Based on the analysis results, the server identifies the child's potential talents and areas of strength. This identification process takes into account not only their academic progress but also their emotional state, providing a comprehensive assessment. For example, if a child demonstrates high performance in a particular task but experiences high stress when performing that task, the server can reconsider the coaching content in that area.

[0944] Step 8:

[0945] The server then creates a customized coaching plan based on the identified talents and areas of strength. The plan includes specific learning activities and materials to use, and incorporates emotional data to determine how a child will learn most effectively. For example, if a child performs better in a relaxed environment, the server will recommend learning methods that take advantage of that environment.

[0946] Step 9:

[0947] The server then sends the created customized coaching plan to the terminal, through which the user can access and implement the plan.

[0948] Step 10:

[0949] The user then integrates the coaching plan received from the device into their child's daily learning activities. The user periodically checks progress and enters additional data as needed, allowing the system to provide continuous, optimized support.

[0950] For example, if Student A is interested in math and music, the user can input this data into their device and the server can analyze it to determine that Student A has high math grades and excellent musical performance skills. Meanwhile, the emotion engine can also determine that Student A has high stress levels. Based on this information, the server creates a plan for Student A that includes math puzzles with relaxation exercises and fun music practice methods, and provides it to the user. The user can then implement this plan to maximize Student A's talents. This system enables personalized learning approaches based on a child's talents and areas of expertise, and can also provide educational support that takes their emotional state into account.

[0951] Example 2

[0952] 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."

[0953] Current education systems struggle to provide personalized educational approaches that fully consider each child's learning progress and emotional state. This can result in ineffectively drawing out a child's talents and areas of expertise, leading to a decline in learning efficiency and motivation. Furthermore, creating learning plans without considering a child's emotional state risks increasing stress and anxiety. Therefore, there is a need for a system that can comprehensively analyze learning data and emotional data to bring out a child's potential talents.

[0954] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generation AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means including an emotion engine for collecting and analyzing emotion data, and means for integrating and analyzing the emotion data and the learning data. This provides an individualized learning approach based on the child's talents and areas of expertise and enables educational support that takes into account the child's emotional state, thereby improving learning efficiency and maintaining sustainable motivation.

[0955] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data, particularly utilizing machine learning and natural language processing.

[0956] "Educational data" refers to various educational data such as a child's learning progress, test results, extracurricular activity results, and areas of interest.

[0957] "Composite analysis methods" are methods that integrate collected data and analyze it from multiple perspectives using machine learning algorithms and data mining techniques.

[0958] "Potential talent" refers to a child's abilities and characteristics that are not currently clearly manifested but have the potential to blossom with appropriate support.

[0959] "Strengths" refer to specific academic areas or activities in which a child excels more than others.

[0960] "Customized coaching plan" refers to an individualized educational support program created based on a specific individual's learning and emotional data.

[0961] "Emotional data" refers to data that indicates the psychological state of a user obtained from facial expressions, voice, and text.

[0962] "Emotion engine" refers to software or a system for analyzing collected emotional data and recognizing emotional states.

[0963] "Means for integrated analysis" refers to a method for processing training data and emotion data in a unified manner and conducting comprehensive analysis.

[0964] "Machine learning algorithms" refer to computational methods and models that learn patterns and rules from data and make predictions and classifications.

[0965] "Data mining technology" refers to an analytical method for extracting useful information and insights from large data sets.

[0966] This invention combines an emotion engine with a system that uses a generative AI model to collect and analyze children's learning data, identify potential talents and areas of expertise, and then provides customized coaching plans. This allows for a more effective educational approach that takes into account not only a child's learning progress but also their emotional state.

[0967] First, users (parents or educators) input their children's learning data via the device. This data includes daily learning progress, test results, extracurricular activity results, and the children's areas of interest. The device provides dedicated applications and web interfaces to make it easy for users to input data. For example, if Student A is interested in mathematics and music, that information is also entered.

[0968] The device then temporarily stores the learning data entered by the user and sends it to a server via the internet. At the same time, the device also collects facial expressions and voice data from the user via a camera and microphone. This data is then analyzed in real time by the emotion engine.

[0969] The server receives the training data and emotion data sent from the device and stores them in a secure database. The server uses, for example, an SQL database as the database. The server performs an initial analysis, checks the consistency of the data, and verifies whether any data is missing.

[0970] The emotion engine analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. For example, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and sends the analysis results to the server.

[0971] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (such as GPT-4 or BERT). This analysis uses machine learning algorithms (such as random forests or k-nearest neighbors) and data mining techniques (such as puppetry). Based on the analysis results, the server identifies a child's potential talents and areas of expertise. For example, it may be discovered that Student A has high grades in math, but experiences increased stress during tests.

[0972] The server then uses these analysis results to create a customized coaching plan, which could include things like math puzzles incorporating relaxation exercises or music practice strategies for calmer emotional situations. For example, the generative AI model might be prompted with the following prompt: "Generate a new coaching plan for Student A based on his or her latest emotional state and learning progress."

[0973] The server then sends the generated customized coaching plan to the device. The user can access the plan through the device and incorporate it into their child's daily learning activities. The user periodically checks their child's learning progress and emotional state and inputs new data as needed. This allows the system to provide continuously optimized support.

[0974] This system provides an individualized learning approach and enables educational support that takes into account children's emotional state, thereby improving children's learning efficiency and maintaining sustained motivation.

[0975] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0976] Step 1:

[0977] Users enter their child's learning data using a dedicated application or web interface. This data includes daily learning progress, test results, extracurricular activity results, and areas of interest. For example, they enter information such as "Math test result: 90 points, Music lesson results: 50 minutes of piano practice." The entered data is temporarily stored on the device.

[0978] Step 2:

[0979] The device temporarily stores the learning data entered by the user and then sends it to a server via the Internet. Specifically, data such as learning progress and test results are packaged in packets in JSON format and sent to the server using a secure protocol (e.g., HTTPS). The input is the learning data, and the output is the data packet sent to the server.

[0980] Step 3:

[0981] The device also simultaneously collects the user's facial and voice data. It uses a camera and microphone to capture facial and voice data and sends it to the emotion engine for real-time analysis. Specifically, it sends video data to a facial recognition API and voice data to an emotion analysis API. The input is facial and voice data, and the output is a dataset of the analysis results.

[0982] Step 4:

[0983] The server receives the training data and emotion data sent from the device and stores them in a secure database (e.g., SQL database). Before storing the data in the database, the server first checks the integrity of the data and confirms that there is no missing data. The input is the data received from the device, and the output is a notification that storage to the database is complete.

[0984] Step 5:

[0985] The emotion engine in the server analyzes the user's facial expressions, voice, and text data sent from the device to recognize the user's emotional state. Specifically, it uses facial recognition technology to identify emotions such as joy, anger, and stress, and stores these analysis results in a database. The input is emotion data, and the output is analyzed emotion information.

[0986] Step 6:

[0987] The server integrates the collected learning data and emotion data and performs a complex analysis using a generative AI model (e.g., GPT-4 or BERT). Specifically, it analyzes children's learning patterns and behavioral trends using machine learning algorithms (e.g., random forests and k-nearest neighbors) and data mining techniques. The input is the integrated learning data and emotion data, and the output is the analysis results.

[0988] Step 7:

[0989] The server creates a customized coaching plan based on the analysis results. For example, it may include math puzzles incorporating relaxation exercises or music practice methods in emotionally calm situations. Specifically, the generative AI model receives a prompt: "Generate a new coaching plan based on Student A's latest emotional state and learning progress." The input is the analysis results, and the output is a customized coaching plan.

[0990] Step 8:

[0991] The server sends the generated customized coaching plan to the terminal. The user can access this plan through the terminal and incorporate it into their daily learning activities. Specifically, the plan is displayed through an application or web interface, and the user can reflect it in their learning activities. The input is the customized coaching plan, and the output is information on how it is applied to the user's learning activities.

[0992] Step 9:

[0993] The user periodically checks their learning progress and emotional state and inputs new data as needed. This allows the system to always provide optimized support based on the latest data. The input is new learning data and emotional data, and the output is updated data sent to the server.

[0994] This system improves children's learning efficiency and enables them to continue learning with sustained high motivation.

[0995] (Application example 2)

[0996] 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."

[0997] Conventional learning support systems often only consider a child's learning progress and ignore their emotional state, resulting in suboptimal learning performance. This makes it difficult for parents and educators to create personalized educational plans for each child, making it difficult to provide effective learning support. Furthermore, the lack of real-time emotional state monitoring makes it difficult to quickly identify and address learning stressors.

[0998] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a child's learning data using a generative AI, means for comprehensively analyzing the collected data, means for identifying the child's potential talents and areas of expertise based on the analysis results, means for creating a customized coaching plan based on the identified areas, means for providing the customized coaching plan, means for analyzing the child's emotional state using an emotion engine and for integrated processing of the learning data and the emotional data, means for a parent or educator to input learning data through a terminal and monitor the emotional state, and means for transmitting a customized coaching plan to the terminal based on the data analysis results and continuously optimizing it. This enables the provision of more effective and personalized educational support that takes into account not only the child's learning progress but also their emotional state.

[0999] "Generative AI" is a technology that uses artificial intelligence to generate new data and information from large amounts of data.

[1000] "Learning data" refers to various information related to learning activities, such as a child's learning progress, test results, extracurricular activity data, and emotional state data written in diary format.

[1001] "Complex analysis" means integrating collected learning data and emotional data and analyzing them using machine learning algorithms and facial recognition technology.

[1002] "Potential talent" refers to abilities or areas of expertise that are not yet apparent but have the potential to be demonstrated with the right environment and guidance.

[1003] "Strengths" refer to areas of study or activity in which a child can perform particularly well.

[1004] A "customized coaching plan" is a specific plan that identifies and implements the teaching methods and learning tasks that are best suited to each individual child.

[1005] An "emotion engine" refers to a system that uses facial recognition technology and voice analysis to analyze a user's emotional state in real time.

[1006] "Device" refers to an electronic device, such as a smartphone, tablet, or computer, used by a parent or educator to input learning data or monitor emotional states.

[1007] "Integrated processing" means processing multiple types of collected data in a unified manner and conducting comprehensive analysis.

[1008] "Monitoring" means collecting and analyzing data in real time or near real time and observing the results.

[1009] "Continuous optimization" means constantly improving systems and plans based on acquired data and analysis results.

[1010] This invention is a system that uses generative AI to collect and analyze children's learning data, combines it with an emotion engine, and provides personalized coaching plans. Specific methods for implementing the system are described below.

[1011] First, the user (parent or educator) must enter their child's learning data through a device, which can be a smartphone, tablet, or computer. This data includes daily learning progress, test results, extracurricular activity results, and emotional states recorded in diary format. This allows the user to centrally manage their child's learning activities and emotional states.

[1012] The device then uses a camera or microphone to collect facial and voice data from the child. This data is then analyzed by an emotion engine to recognize the child's emotional state in real time. The emotion engine uses machine learning libraries such as TensorFlow and Keras, and includes a combination of facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library).

[1013] The device transmits the collected learning and emotional data to a server, which securely stores this data in a database and performs a complex analysis using a generative AI model. This analysis uses machine learning algorithms and facial recognition technology, and data mining techniques to derive the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state.

[1014] Based on the analysis, the server identifies potential talents and areas of strength for the child. For example, if a child shows high achievement in math or music but is experiencing stress, the server can adjust coaching in those areas.

[1015] Finally, the server creates a customized coaching plan and sends it to the device. The user can access the plan through the device and continuously support their learning activities. The user can also add new data from time to time, allowing the system to continuously optimize the plan.

[1016] As a concrete example, consider the case where Student A is interested in math and music. In this case, a parent or educator inputs this data into the device, and the server analyzes it. The analysis results show that Student A has high math grades and excellent musical performance skills, but the emotion engine identifies high stress levels. Based on this information, the server creates and provides a plan to the user that includes math puzzles with relaxation exercises and music practice methods that allow students to learn while having fun.

[1017] The server then uses this data to run a generative AI model based on the following example prompt: "These are the results of a math test. Please analyze the data, including my emotional state, to generate a low-stress, effective study plan."

[1018] Through the above process, the present invention is able to provide effective and personalized educational support that takes into account not only a child's learning progress but also their emotional state.

[1019] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1020] Step 1:

[1021] The user uses a device to input their child's learning data. This data includes daily learning progress, test results, extracurricular activity results, and emotional states described in diary format. The input data is designed to be easily entered through the device's interface. The output of the input data is saved as learning data for use in subsequent processing steps.

[1022] Step 2:

[1023] The device uses a camera or microphone to collect facial and voice data from the child. This data is acquired in real time and sent to the emotion engine. The emotion engine analyzes the collected image and voice data to recognize the child's emotional state. Specifically, it uses facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., the transformers library). The input is facial and voice data, and the output is the analysis result of the child's emotional state.

[1024] Step 3:

[1025] The device sends the collected training data and emotion data to a server, which stores this data securely in a database. The input is the training data and emotion data, and the output is a database entry stored on the server.

[1026] Step 4:

[1027] The server uses a generative AI model to perform a complex analysis of the collected data. This analysis uses machine learning algorithms and facial recognition technology. Data mining technology is used to determine the optimal educational approach, taking into account the child's learning patterns, behavioral tendencies, and emotional state. The input is the stored learning data and emotional data, and the output is the analysis results.

[1028] Step 5:

[1029] The server identifies the child's potential talents and areas of strength based on the analysis results. This process takes into account performance data in specific academic subjects and activities, as well as emotional state, to make a comprehensive assessment. The input is the analysis results, and the output is the identified talents and areas of strength.

[1030] Step 6:

[1031] The server creates a customized coaching plan based on the identified areas. For example, if the person is feeling stressed, it suggests learning methods that incorporate stress reduction techniques. Specific learning tasks and teaching methods are determined at this stage. The input is the identified talents and areas of strength, and the output is a customized coaching plan.

[1032] Step 7:

[1033] The server sends the customized coaching plan to the device. The user can access the plan through the device and incorporate it into the child's learning activities. The device can also monitor the progress of the implemented plan and add new data. The input is the customized coaching plan, and the output is the specific learning activities that the user will carry out.

[1034] Through the above steps, the present invention can provide personalized educational support that takes into consideration a child's learning progress and emotional state in an integrated manner.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1040] 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.

[1041] 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).

[1042] 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.

[1043] 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."

[1044] 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.

[1045] 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).

[1046] 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.

[1047] 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.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] 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.

[1052] 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.

[1053] 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.

[1054] 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.

[1055] 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.

[1056] The following is further disclosed regarding the above embodiment.

[1057] (Claim 1)

[1058] A means of collecting children's learning data using generative AI,

[1059] A means of analyzing the collected data in a comprehensive manner,

[1060] A means to identify children's potential talents and areas of expertise based on the analysis results;

[1061] A means to create a customized coaching plan based on the areas identified;

[1062] A means to provide customized coaching plans;

[1063] A system including:

[1064] (Claim 2)

[1065] 2. The system of claim 1, wherein the child's learning data includes test results and extracurricular activity data.

[1066] (Claim 3)

[1067] 2. The system of claim 1, wherein the analysis uses a machine learning algorithm.

[1068] "Example 1"

[1069] (Claim 1)

[1070] means for inputting child learning data via an input interface;

[1071] A means for storing the input data in a database;

[1072] A means of complex analysis of collected data using generative AI models; and

[1073] A means to identify children's potential talents and areas of expertise based on the analysis results;

[1074] A means to create a customized education plan based on the areas identified;

[1075] A means to provide customized educational plans;

[1076] A system including:

[1077] (Claim 2)

[1078] 2. The system of claim 1, wherein the child's learning data includes test scores, extracurricular activity results, and daily behavior records.

[1079] (Claim 3)

[1080] 2. The system of claim 1, wherein the analysis uses machine learning algorithms and data mining techniques.

[1081] "Application Example 1"

[1082] (Claim 1)

[1083] A means of collecting children's learning data using generative AI,

[1084] A means of analyzing the collected data in a comprehensive manner,

[1085] A means to identify children's potential talents and areas of expertise based on the analysis results;

[1086] A means to create a customized coaching plan based on the areas identified;

[1087] A means to provide customized learning experiences in virtual reality spaces; and

[1088] A system including:

[1089] (Claim 2)

[1090] 2. The system of claim 1, wherein the child's learning data includes test results and extracurricular activity data.

[1091] (Claim 3)

[1092] 2. The system of claim 1, wherein the analysis uses a machine learning algorithm.

[1093] "Example 2: Combining Emotion Engines"

[1094] (Claim 1)

[1095] A means of collecting children's learning data using generative AI,

[1096] A means of analyzing the collected data in a comprehensive manner,

[1097] A means to identify children's potential talents and areas of expertise based on the analysis results;

[1098] A means to create a customized coaching plan based on the areas identified;

[1099] A means to provide customized coaching plans;

[1100] means including an emotion engine for collecting and analyzing emotion data;

[1101] A means for integrating and analyzing emotion data and learning data;

[1102] A system including:

[1103] (Claim 2)

[1104] 10. The system of claim 1, wherein the child's learning data includes test results, extracurricular activity data, and areas of interest data.

[1105] (Claim 3)

[1106] 2. The system of claim 1, wherein the analysis uses machine learning algorithms and data mining techniques.

[1107] "Application example 2 when combining emotion engines"

[1108] (Claim 1)

[1109] A means of collecting children's learning data using generative AI,

[1110] A means of analyzing the collected data in a comprehensive manner,

[1111] A means to identify children's potential talents and areas of expertise based on the analysis results;

[1112] A means to create a customized coaching plan based on the areas identified;

[1113] A means to provide customized coaching plans;

[1114] A means for analyzing the emotional state of a child using an emotion engine and processing the learning data and the emotion data in an integrated manner;

[1115] A means for parents or educators to input learning data and monitor emotional states through a terminal;

[1116] A means to send customized coaching plans based on data analysis results to the device and continuously optimize them;

[1117] A system including:

[1118] (Claim 2)

[1119] 10. The system of claim 1, wherein the child's learning data includes test results, extracurricular activity data, and emotional state data written in diary format.

[1120] (Claim 3)

[1121] 2. The system of claim 1, wherein the analysis uses machine learning algorithms and facial recognition technology. [Explanation of symbols]

[1122] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting children's learning data using generative AI, A means of analyzing the collected data in a comprehensive manner, A means to identify children's potential talents and areas of expertise based on the analysis results; A means to create a customized coaching plan based on the areas identified; A means to provide customized coaching plans; A system including:

2. 10. The system of claim 1, wherein the child's learning data includes test results and extracurricular activity data.

3. The system of claim 1 , wherein the analysis uses a machine learning algorithm.

Images