System

Abstract

A system is provided.SOLUTION: A system including means for recording daily behavior data of a child, means for transmitting the recorded data to a server, means for inputting the received data to a machine learning algorithm and analyzing a behavior pattern of the child, means for generating a customized learning activity based on an analysis result, means for delivering the generated learning activity to a terminal, means for performing the delivered activity by the child, means for recording a performance result and transmitting the performance result to the server, and means for analyzing the performance result, evaluating an effect of the activity, and optimizing a next suggestion.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] The current situation in the traditional education system is that it lacks concrete methods for discovering and nurturing the diverse talents and interests of each individual child. Uniform educational methods and curricula prevent children's potential from being discovered and maximized. Furthermore, providing education that meets individual needs requires a great deal of effort and time from teachers and parents, so there is a need for methods to automate and streamline this process. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. By providing a means for recording data on children's daily behavior and a means for transmitting the recorded data to a server, children's behaviors and reactions are systematically collected. Next, a means is provided for inputting the received data into a machine learning algorithm in the server to analyze children's behavioral patterns. By adding a means for generating customized learning activities based on the analysis results and a means for distributing the generated learning activities to a terminal, it is possible to automatically provide personalized education. Furthermore, a means is provided for children to perform the distributed activities, and the results of the performance are recorded and transmitted to the server. A system is then constructed that has a means for analyzing the results, evaluating the effectiveness of the activities, and optimizing suggestions for the next time. This provides an educational system that can bring out and efficiently develop each child's talents and interests.

[0006] Furthermore, by including a means to identify a child's interests and areas of expertise based on the analysis results and suggest learning activities based on these, more accurate individual responses will be possible.Furthermore, by adding a means to capture a child's facial expressions and emotions using facial recognition technology and record their concentration level and reactions based on this, comprehensive educational support that takes emotional reactions into consideration will be realized.

[0007] "Children's daily behavioral data" refers to information that records a child's actions and reactions in their daily life and learning activities, including time spent studying, attention span, the content they show interest in, posture, facial expressions, and emotional changes.

[0008] The "server" is a centralized device that processes and analyzes the received data and generates and distributes appropriate educational activities based on the results.

[0009] "Recording means" refers to the equipment, software, and methods used to collect and store data on children's daily behavior.

[0010] "Transmitting means" refers to a communication device or method for transferring collected data to another device or system, such as a server.

[0011] "Machine learning algorithms" are mathematical models and calculation methods that analyze collected data and estimate children's behavioral patterns and potential abilities.

[0012] "Behavioral patterns" refer to specific habits and tendencies observed in a child's series of actions and reactions, and are information that can be used to analyze interests and areas of expertise based on this.

[0013] "Customized learning activities" refer to educational content and training methods that are optimized for each individual child based on the analysis results, and include workbooks, games, and project-style teaching materials.

[0014] "Distribution means" refers to a method or device for providing the generated learning activity to a child's terminal.

[0015] "Implementation recorder" refers to a device or method for recording and storing a child's performance and responses as they participate in a learning activity.

[0016] "Evaluation means" refers to the methods and devices used to analyze the collected implementation results and determine whether the learning activity was effective.

[0017] "Facial recognition technology" is a technology used to analyze children's facial expressions and emotions, and involves capturing and analyzing facial features using cameras and software.

[0018] "Attention and responsiveness" refers to a child's level of concentration and emotional and physical responses during a learning activity. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This system collects data on children's daily activities, analyzes their individual talents and interests, and provides customized educational activities based on the collected data. This system is primarily composed of users (children), terminals, and a server.

[0041] System Configuration

[0042] 1. Terminal

[0043] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions, and use facial recognition and behavioral recognition technology to record children's daily actions and reactions. For example, tablets record operation logs and study time when children use learning apps, while smartwatches collect data including exercise volume and heart rate.

[0044] 2. Server

[0045] The server receives data sent from the device and analyzes it using a machine learning algorithm. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns to identify each child's potential abilities and interests. Based on the results of this analysis, it generates customized learning activities and materials and sends them to the device.

[0046] 3. Users

[0047] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[0048] Program processing

[0049] 1. Data Collection

[0050] When a child uses the device, it records activity logs, behavioral data, facial expression data, etc. in real time. It also uses facial recognition technology to capture the child's emotions and concentration, which are also collected as data.

[0051] 2. Data Transmission

[0052] The device encrypts the collected data and periodically uploads it to a server, ensuring data integrity and security.

[0053] 3. Data analysis

[0054] The server inputs the received data into a machine learning model to analyze the child's behavioral patterns. For example, if the child shows a high interest in math calculation problems, it is assumed that the child has mathematical talent.

[0055] 4. Activity Generation and Suggestion

[0056] Based on the analysis results, the server generates customized learning activities, including exercises, games, and projects tailored to the child's interests and strengths, which are then sent to the device and presented to the child.

[0057] 5. Feedback and Adjustments

[0058] The user (child) performs the provided activity, and their results and reactions are recorded on the device again. The recorded data is sent to the server and analyzed. Based on the results, the next learning suggestion is further optimized.

[0059] Specific examples

[0060] For example, suppose a child is using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions (concentration, confusion, enjoyment, etc.) while using the app. This data is sent to a server, where a machine learning model analyzes it and determines that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games and provides them to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[0061] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] Devices: Record data on children's daily activities. Specifically, the tablet captures the operation log of the learning app (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data while using the app (e.g., focused, confused, enjoying). The smartwatch records data such as heart rate, exercise volume, and frequency of use.

[0065] Step 2:

[0066] Terminal: The recorded data is encrypted and periodically sent to the server. For example, when the collected data reaches a certain volume or at a specified time interval, the data is uploaded to the server. This ensures the integrity and security of the data.

[0067] Step 3:

[0068] Server: Stores the received data in a database, safely storing and managing the data and preparing it to be fed to machine learning algorithms as needed.

[0069] Step 4:

[0070] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns. Specifically, based on the dataset, methods such as classifiers and regression analysis are used to identify the child's strengths, areas of interest, and learning approaches.

[0071] Step 5:

[0072] Server: Based on the analysis, it generates customized learning activities. For example, for a child who shows an interest in math, it creates challenging math problems or math games. For a child interested in creative expression, it generates art projects or design assignments.

[0073] Step 6:

[0074] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[0075] Step 7:

[0076] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[0077] Step 8:

[0078] Device: Records the results of the learning activities the child has performed. Specifically, it records the answer time, correct answer rate, changes in emotions and facial expressions, etc., for further analysis.

[0079] Step 9:

[0080] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[0081] Step 10:

[0082] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity, such as the degree of improvement in learning outcomes, changes in the rate of correct answers to math problems, and changes in children's concentration and emotions.

[0083] Step 11:

[0084] Server: Generates feedback based on the analysis results and optimizes the next learning activity suggestion. Depending on the evaluation, adjusts the difficulty and content of the activity and prepares for the next cycle. The server updates the next learning activity and returns to step 1.

[0085] Through the above processing steps, the present invention brings out the potential and talents of children and realizes efficient and effective individualized education.

[0086] Example 1

[0087] 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."

[0088] Conventional educational support systems have struggled to efficiently analyze each child's talents and interests and provide customized educational activities based on those insights. Furthermore, they lacked the technology to create an effective feedback loop while ensuring the security and consistency of collected data. This made it difficult to maximize each child's learning efficiency.

[0089] 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.

[0090] In this invention, the server includes means for inputting received data into a machine learning algorithm and analyzing behavioral patterns, means for generating customized educational activities based on the analysis results using machine learning, and means for analyzing the implementation results, evaluating the effectiveness of the educational activities, and optimizing suggestions for the next time. This makes it possible to efficiently analyze the talents and interests of individual children and provide customized educational activities based on them.

[0091] "Children's daily behavioral data" refers to data related to the behavior of children in their daily lives and educational activities, and includes operation logs of learning applications, answer results, amount of exercise, heart rate, facial expressions, etc.

[0092] The "database" is an information management system that centrally stores received behavioral data and allows searching and analysis as needed.

[0093] "Encryption" is a technology that prevents transmitted data from being deciphered by third parties, and is a means of ensuring data security.

[0094] "Server" means a computer system that receives and stores data sent from a device, analyzes it, and generates activity data.

[0095] A "machine learning algorithm" is a collection of mathematical methods and programs that learn patterns and characteristics from data and make predictions and classifications.

[0096] "Behavioral pattern analysis" is the process of identifying patterns in a child's behavior and reactions based on collected behavioral data, revealing their potential abilities and interests.

[0097] "Customized educational activities" are learning activities and materials specially designed based on a child's characteristics and interests, with the aim of enhancing learning efficiency.

[0098] "Delivery of educational activities" is the process of sending the generated customized learning activities and materials to the device and making them available to the child.

[0099] "Recording implementation results" refers to storing the results and reactions of children when they perform educational activities on the device, which is used to optimize suggestions for the next time.

[0100] "Analysis of feedback data" is a data analysis process to evaluate the effectiveness of educational activities based on the results of implementation and improve the content of proposals for the next time.

[0101] "Facial recognition technology" is a technology that uses sensors and cameras to automatically identify an individual's face and analyze their facial expressions and emotions.

[0102] "Recording concentration and reaction" refers to recording changes in attention and emotions while a child is engaged in educational activities, based on facial expression data obtained using facial recognition technology.

[0103] The present invention is a system that collects data on children's daily behavior, analyzes their individual talents and interests, and provides customized educational activities based on that data. It is composed of users (children), parents, terminals, and a server.

[0104] Terminal

[0105] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. Facial recognition and behavioral recognition technologies are used to record children's daily actions and reactions. For example, the tablet records the operation log and study time when a child uses a learning app, while the smartwatch collects exercise volume and heart rate data.

[0106] The device locally encrypts the collected data and uploads it to the server at regular intervals. This encryption ensures the integrity and security of the data. Specifically, the device is set to send data to the server every night.

[0107] server

[0108] The server receives the data sent from the device and stores it in a database. Based on this stored data, it uses machine learning algorithms to analyze behavioral patterns. Specifically, the server analyzes the received behavioral data to identify each child's potential abilities and interests. For example, a child who shows a high interest in math calculation problems is deemed to have mathematical talent.

[0109] A machine learning algorithm is used to generate customized educational activities based on the analysis results. For example, a generative AI model (e.g., GPT-3) is used to generate optimal learning activities by inputting the following prompt sentence:

[0110] Prompt Sentence Examples

[0111] "Based on the following data, please suggest the best math learning activity for this child:

[0112] Answer time: Average answer time for each question is 30 seconds

[0113] Correct answer rate: 95%

[0114] Facial expressions: Concentration (70%), Confusion (20%), Happiness (10%)

[0115] Suggest new math activities that will interest your child."

[0116] Delivery and implementation of educational activities

[0117] The generated educational activity is sent to the device and provided to the child. The user (child) performs the provided educational activity. The device again records the results and reactions during this activity. For example, it acquires and records the percentage of correct answers, the time it takes to answer, and facial expression data (enjoyed, confused, etc.).

[0118] Feedback and Optimization

[0119] The recorded data on the results is then sent back to the server, which uses this new data to provide feedback and evaluate the effectiveness of the educational activity. The next suggestion is then further optimized based on this feedback.

[0120] As a concrete example, consider a child using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions while using the app. This data is sent to a server and analyzed by a machine learning model. The analysis reveals that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games, which it then provides to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[0121] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Program processing flow

[0124] Step 1:

[0125] Data collection

[0126] The devices (tablets and smartwatches) collect behavioral data through the user's (child's) activities. Specifically, the tablets record the operation log of the learning application, study time, answer results, etc., while the smartwatch records exercise volume and heart rate. In addition, the camera sensor captures facial expression data (concentration, confusion, enjoyment, etc.) in real time and analyzes it using facial recognition technology.

[0127] Input: Children's operation log, study time, answer results, exercise amount, heart rate, facial expression data

[0128] Output: A set of collected behavioral data

[0129] Operation: Data acquisition from sensors and cameras, initial analysis, and local storage

[0130] Step 2:

[0131] Data transmission

[0132] The device locally encrypts the collected data and uploads it to the server at regular intervals. Specifically, the device is scheduled to send encrypted data every night, ensuring the integrity and security of the data.

[0133] Input: Encrypted behavioral data

[0134] Output: Behavioral data sent to the server

[0135] Operation: Data encryption process, uploading encrypted data to server

[0136] Step 3:

[0137] Data reception and storage

[0138] The server receives the behavioral data sent from the device and stores it in a database as a log, allowing the data required for subsequent analysis steps to be managed in a centralized manner.

[0139] Input: Behavioral data sent from the device

[0140] Output: Behavioral data stored in a database

[0141] Action: Writing data to the database

[0142] Step 4:

[0143] Data analysis

[0144] The server inputs the behavioral data stored in the database into a machine learning algorithm to perform analysis. This extracts the child's behavioral patterns and identifies their potential abilities and interests. For example, the server analyzes the child's learning patterns and evaluates their mathematical talent based on their reaction time to math problems, the percentage of correct answers, and facial expression data.

[0145] Input: Behavioral data stored in a database

[0146] Output: Behavioral pattern analysis results

[0147] Action: Input data into machine learning models, analyze behavioral patterns, and extract results

[0148] Step 5:

[0149] Activity Creation

[0150] Based on the analysis results, the server uses a generative AI model to generate customized educational activities. In this process, specific prompts are input into the generative AI model (e.g., GPT-3) to create optimal learning activities. For example, "This child has a high interest in math, so I'd like to suggest some challenging math problems and creative math games."

[0151] Input: behavior pattern analysis results, prompt text

[0152] Output: Customized educational activities

[0153] Operation: Input prompts to the generative AI model, generate educational activities

[0154] Step 6:

[0155] Activity Broadcast

[0156] The generated educational activity is sent from the server to the terminal and provided to the child.

[0157] Input: Generated educational activities

[0158] Output: Educational activities delivered to devices

[0159] Action: Delivering educational activities to devices

[0160] Step 7:

[0161] Activity implementation

[0162] The user (child) performs the provided educational activity, and the device records the results, such as the percentage of correct answers, the time it took to answer, and facial expression data (such as happy or confused).

[0163] Input: Educational activity status

[0164] Output: Implementation result data

[0165] Behavior: Collecting and recording behavioral data

[0166] Step 8:

[0167] Feedback and Adjustments

[0168] The server receives the implementation result data sent from the device again and analyzes it as feedback data. Based on the analysis results, the next educational activity is optimized.

[0169] Input: Implementation result data

[0170] Output: Optimized next teaching activity

[0171] Actions: Analyzing feedback data and optimizing educational activities

[0172] The above is the flow of the program processing of the present invention and the specific operation of each step, which optimizes the learning process for each child and provides effective educational support.

[0173] (Application example 1)

[0174] 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."

[0175] Traditional educational systems have struggled to provide customized educational activities based on each child's individual talents and interests. Furthermore, uniform educational programs fail to capture children's interests and lead to insufficient learning outcomes. Furthermore, educational activities within educational facilities face the challenge of being unable to grasp children's real-time behavior and emotions and instantly customize educational activities based on them.

[0176] 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.

[0177] In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm to analyze the child's behavioral patterns, means for generating customized educational activities based on the analysis results, means for distributing the generated educational activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the educational activities and optimize suggestions for the next time, means for recording the child's gaze, behavior, and voice commands in real time using a smart device, and means for providing a customized interactive experience within the educational facility. This makes it possible to provide customized educational activities based on the child's interests and talents in real time and optimize educational effectiveness.

[0178] "Children's daily behavioral data" refers to data that records various actions and reactions that children perform in their daily lives.

[0179] "Means for recording" refers to devices or systems for electronically storing behavioral data, emotional data, etc.

[0180] "Means for transmitting to a server" refers to a combination of hardware and software for transferring data from a terminal to a server.

[0181] A "machine learning algorithm" is an algorithm that extracts patterns and knowledge from data and uses them to make predictions and classifications.

[0182] "Means of analysis" refers to devices and software that use machine learning algorithms to analyze data and extract meaningful information.

[0183] "Customized educational activities" refer to educational activities that are specifically designed based on the talents and interests of each individual child.

[0184] "Means for delivering to the device" refers to the technology or device used to transfer the generated educational activity to the user's device.

[0185] "Implementation means" refers to the equipment or technology that allows children to actually carry out the delivered educational activity.

[0186] "Means for recording the results of an activity and transmitting them to a server" refers to devices or technologies for saving data after the activity is completed and transmitting that data to a server.

[0187] "Means for evaluating the effectiveness of educational activities and optimizing proposals for the next time" refers to technologies and devices that analyze the results of implementation and use those results to make the next educational activity more effective.

[0188] "Smart devices" refer to portable electronic devices equipped with communication functions and sensors that are capable of collecting data and interacting with users.

[0189] "Means for recording gaze, actions, and voice commands in real time" refers to technologies and devices that instantly collect and store a user's gaze movements, body movements, and voice instructions.

[0190] "Means for providing customized interactive experiences within educational facilities" refers to technologies and devices used in educational facilities to design and provide participatory educational activities based on children's interests and talents.

[0191] This system collects and analyzes data on children's daily activities and provides customized educational activities based on their individual talents and interests. The system mainly consists of a terminal, a server, and a user.

[0192] System Configuration

[0193] 1. Terminal

[0194] The devices used include portable electronic devices such as tablets, smartwatches, smart glasses, and head-mounted displays (HMDs). These devices are equipped with sensors and cameras to record behavioral and emotional data, and use facial recognition and behavioral recognition technologies. For example, smart glasses record eye movements and facial expressions, while smartwatches measure heart rate and exercise volume. This data is collected in real time, and the devices encrypt and send it to a server.

[0195] 2. Server

[0196] The server receives the data sent from the device and analyzes it using a machine learning algorithm (e.g., TensorFlow). The received data is stored in a database (e.g., MySQL). The server analyzes the data and identifies the child's behavioral patterns and areas of interest. Based on the results of this analysis, the server generates customized educational activities and delivers them to the device. In addition, the server reanalyzes the user's feedback data to optimize suggestions for the next educational activity.

[0197] 3. Users

[0198] Users (children and their parents or educators) carry out educational activities provided via the device. The child's activities and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activities and further optimize suggestions for the next time.

[0199] Specific examples

[0200] A concrete example is an interactive experience using smart glasses and HMDs in a science museum's educational facilities. When a child walks around the educational facility and spends a long time in front of a particular exhibit, the smart glasses collect behavioral data and an increase in heart rate. This data is sent to a server and analyzed using machine learning algorithms. If the server determines that the child has a strong interest in the exhibit, it generates a customized interactive experience based on that interest (e.g., additional explanations or related mini-games) and delivers it to the smart glasses.

[0201] For example, a prompt to a generative AI model might look like this:

[0202] "Analyze children's behavior data in the fossil exhibit area and generate customized educational programs about fossils."

[0203] This system makes it possible to provide customized educational activities in real time that are tailored to each child's individual interests and talents, maximizing educational effectiveness.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1:

[0206] The device records the child's daily behavior data in real time.

[0207] Specifically, devices such as smart glasses and smart watches use sensors and cameras to collect eye movements, heart rate, voice commands, body movements, and facial expressions.

[0208] Input: Child's gaze data, heart rate data, voice commands, body movement data, facial expression data

[0209] Output: raw recorded data

[0210] Step 2:

[0211] The terminal encrypts the recorded data and transmits it to the server.

[0212] Specifically, data is encrypted using the SSL / TLS protocol and uploaded to a server via Wi-Fi.

[0213] Input: raw recorded data

[0214] Output: Encrypted data

[0215] Step 3:

[0216] The server inputs the received data into a machine learning algorithm to analyze the child's behavioral patterns.

[0217] Specifically, it uses TensorFlow to analyze data and identify children's areas of interest and behavioral patterns.

[0218] Input: Encrypted data

[0219] Output: Analysis results (areas of interest, behavioral patterns)

[0220] Step 4:

[0221] The server generates customized educational activities based on the analysis results.

[0222] Specifically, generative AI models are used to create problem sets, interactive games, projects, and more tailored to specific areas of interest.

[0223] Input: Analysis results

[0224] Output: Customized educational activities

[0225] Step 5:

[0226] The server distributes the generated educational activities to the terminals.

[0227] Specifically, the device receives educational activities, notifies the user appropriately, and provides visual and audio guidance as necessary.

[0228] Input: Customized Educational Activities

[0229] Output: Delivered educational activity

[0230] Step 6:

[0231] The user (child) performs the educational activity that is delivered to them.

[0232] Specifically, they participate in interactive experiences displayed using smart glasses or HMDs and run applications.

[0233] Input: Delivered educational activity

[0234] Output: Activity execution results

[0235] Step 7:

[0236] The terminal records the implementation results and transmits them to the server.

[0237] Specifically, sensors record the results and reactions of each child's activity, and the necessary data is then encrypted and uploaded to the server.

[0238] Input: Activity execution result

[0239] Output: Encrypted execution data

[0240] Step 8:

[0241] The server analyzes the results of the implementation, evaluates the effectiveness of the educational activity, and optimizes the next proposal.

[0242] Specifically, the received data is analyzed and the next educational activity is further customized based on the results.

[0243] Input: Encrypted implementation data

[0244] Output: Next suggested activity

[0245] 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.

[0246] This invention is a system that collects and analyzes children's daily behavior data to provide learning activities customized to their individual talents and interests. In addition, by combining it with an emotion engine, it acquires and analyzes the user's emotion data to provide more accurate educational support. The system consists of a user (child), a terminal, and a server.

[0247] System Configuration

[0248] 1. Terminal

[0249] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[0250] 2. Server

[0251] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[0252] 3. Users

[0253] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[0254] Program processing

[0255] 1. Data Collection

[0256] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[0257] 2. Data Transmission

[0258] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[0259] 3. Data analysis

[0260] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[0261] 4. Activity Generation and Suggestion

[0262] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[0263] 5. Activity Distribution

[0264] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[0265] 6. Activity implementation

[0266] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[0267] 7. Recording of implementation results

[0268] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[0269] 8. Send results

[0270] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[0271] 9. Evaluation and Adjustment

[0272] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[0273] Specific examples

[0274] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[0275] The processing flow will be explained below.

[0276] Step 1:

[0277] Device: Records children's daily behavioral and emotional data. Specifically, the tablet captures learning app operation logs (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data (e.g., concentration, confusion, enjoyment) in real time. The smartwatch collects data such as heart rate, exercise volume, and frequency of use. The emotion engine uses facial recognition and voice analysis technology to detect the user's emotions (e.g., joy, sadness, surprise).

[0278] Step 2:

[0279] Device: The recorded behavioral and emotional data is encrypted and periodically sent to the server. The data is uploaded to the server when the collected data reaches a certain volume or at specified intervals to ensure secure communication.

[0280] Step 3:

[0281] Server: Stores the received data in a database, safely storing and managing the data and preparing it to serve the machine learning algorithms and sentiment engines as needed.

[0282] Step 4:

[0283] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns and emotional data. Specifically, behavioral data such as study time, accuracy rate, and answer time are combined with emotional data analyzed by the emotion engine to identify the child's favorite subjects, areas of interest, and current emotional state.

[0284] Step 5:

[0285] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging calculation problems and math games. It also generates activities with emotional feedback to respond to changes in emotions.

[0286] Step 6:

[0287] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[0288] Step 7:

[0289] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks. Activities with emotional feedback respond to emotional changes during learning.

[0290] Step 8:

[0291] Device: Records the results of the child's learning activities. Specifically, it records the answer time, accuracy rate, changes in emotions and facial expressions, etc., for further analysis. The emotion engine monitors emotional changes during learning in real time.

[0292] Step 9:

[0293] Terminal: The results of the experiment are encrypted and sent to the server. At this time, both behavioral data and emotional data are uploaded to the server.

[0294] Step 10:

[0295] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. Specifically, it evaluates learning outcomes (e.g., improvement in correct answer rate, reduction in answer time) and emotional changes (e.g., increased enjoyment and concentration during learning), and generates feedback based on the analysis results.

[0296] Step 11:

[0297] Server: Optimizes the next learning activity suggestion based on the feedback. Depending on the evaluation, the difficulty and content of the activity are adjusted and reflected in the next learning suggestion. The server updates the next learning activity, realizing cyclical operation of the system.

[0298] In this way, the system of the present invention, which combines an emotion engine, analyzes children's behavioral data and emotion data and provides optimal learning activities for each individual child, thereby providing effective educational support.

[0299] Example 2

[0300] 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."

[0301] Conventional learning support systems have difficulty providing customized learning activities that fully consider each child's individual talents, interests, and emotional state. As a result, there is a problem in that they are unable to provide effective support to increase children's motivation to learn.

[0302] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0303] In this invention, the server includes a means for storing the received data in a database, a means for inputting the stored data into a machine learning algorithm to analyze the child's behavioral patterns, and a means for generating customized learning activities using a generative AI model based on the analysis results, thereby enabling highly accurate educational support that takes into account the individual talents, interests, and emotional states of each child.

[0304] "Children's daily behavioral data" refers to data about the actions and behaviors that children perform during their daily lives and learning activities.

[0305] "Recording means" refers to devices or methods that capture data on a child's daily behavior and store that information.

[0306] "Transmitting means" refers to a device or method for transferring recorded data to a receiving device such as a server.

[0307] "Means for storing received data in a database" refers to a device or method by which the server records and stores data received from a terminal in a database.

[0308] A "machine learning algorithm" is an algorithm that analyzes data and automatically learns patterns and regularities to predict or classify outcomes.

[0309] A "generative AI model" is an artificial intelligence model that processes information like a human and generates answers to new data or problems.

[0310] "Customized learning activities" refer to learning tasks and exercises that are appropriately tailored based on each child's abilities, interests, and emotions.

[0311] "Means for distribution" refers to a device or method for transmitting the learning activity generated by the server to the terminal and providing it to the child.

[0312] "Means for recording results" refers to a device or method for saving the results of a child's learning activities.

[0313] "Means for analyzing implementation results" refers to devices or methods for analyzing data on children's learning activities and identifying their effectiveness and areas for improvement.

[0314] "Facial recognition technology" refers to technology that uses a camera or sensor to detect a person's face and identify their individual facial expressions and features.

[0315] "Voice analysis technology" refers to technology that uses a microphone or audio receiving device to analyze audio signals and identify their content and characteristics.

[0316] "Concentration" refers to an indicator of a child's attention and dedication to a given task or activity.

[0317] A "prompt" refers to the instructions or input text that a generative AI model uses to generate new data or answers.

[0318] This invention relates to a system that collects and analyzes children's daily behavioral data to provide customized learning activities based on their individual talents and interests. By combining it with an emotion engine, it acquires and analyzes the user's emotional data to provide more accurate educational support.

[0319] System Configuration

[0320] 1. Terminal

[0321] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the ability to detect emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[0322] 2. Server

[0323] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[0324] 3. Users

[0325] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[0326] Program processing

[0327] The specific operation of the system is explained below. The system mainly functions through the following processes: data collection, data transmission, data storage, data analysis, activity generation, activity distribution, activity implementation, recording of implementation results, result transmission, evaluation and adjustment.

[0328] 1. Data Collection

[0329] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[0330] 2. Data Transmission

[0331] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[0332] 3. Data storage

[0333] Server: The server stores the received data in a database, adds new entries to the database, and checks the integrity of the data.

[0334] 4. Data Analysis

[0335] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[0336] 5. Activity Generation and Suggestion

[0337] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[0338] 6. Activity Distribution

[0339] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[0340] 7. Activity implementation

[0341] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[0342] 8. Recording of implementation results

[0343] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[0344] 9. Send results

[0345] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[0346] 10. Evaluation and Adjustment

[0347] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[0348] Specific examples

[0349] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[0350] Prompt Sentence Examples

[0351] "Please suggest the best learning activities for children who are interested in mathematics and who enjoy engaging in them with a smile."

[0352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0353] Specific processing steps of the program

[0354] Step 1: Data collection

[0355] Devices: Records real-time activity logs, behavioral data, and emotional data as children engage in learning activities. Devices used include tablets and smartwatches.

[0356] Input: Operation information of the learning app, facial expression images from the camera, audio data from the microphone, and biometric information from the smartwatch.

[0357] Data processing: Facial recognition technology is used to analyze facial expressions and detect emotions such as "concentration," "confusion," and "happiness." Voice analysis technology is used to determine emotions from the tone of voice.

[0358] Output: Behavioral data integrating learning operation logs, facial expression data, voice data, and biometric data.

[0359] Step 2: Send data

[0360] Terminal: The recorded data is encrypted and periodically sent to the server.

[0361] Input: Integrated behavioral data.

[0362] Data processing: Encrypting data and sending it through a secure communication channel.

[0363] Output: Encrypted behavioral data.

[0364] Step 3: Save data

[0365] Server: Stores the received data in a database.

[0366] Input: Encrypted behavioral data.

[0367] Data processing: Decrypt the data and store it in the database in the appropriate format.

[0368] Output: Behavioral data stored in a database.

[0369] Step 4: Data analysis

[0370] Server: Analyzes the received data using machine learning algorithms and an emotion engine.

[0371] Input: Behavioral and emotional data from the database.

[0372] Data processing: Using machine learning algorithms to analyze behavioral patterns and identify areas of expertise and interest. Using an emotion engine to analyze emotional fluctuations.

[0373] Output: Analysis results (child's strengths, interests, emotional state).

[0374] Step 5: Activity generation and proposal

[0375] Server: Based on the analysis results, a generative AI model is used to generate customized learning activities.

[0376] Input: Analysis results (areas of expertise, areas of interest, emotional state).

[0377] Data processing: Use a generative AI model to create learning activities suitable for children. Enter the prompt "Suggest the best learning activities for a child who is interested in math and smiles when they engage in it."

[0378] Output: A customized learning activity.

[0379] Step 6: Activity Delivery

[0380] Server: Delivers the generated learning activities to the devices.

[0381] Input: The generated learning activity.

[0382] Data processing: Encrypting activity in a proper format and sending it to your child's device.

[0383] Output: Encrypted learning activity.

[0384] Step 7: Implement the activity

[0385] User (child): Carries out learning activities provided on the device.

[0386] Input: Delivered learning activity.

[0387] Data processing: Conduct the activity and record the answer time, correct answer rate, and emotional state.

[0388] Output: Learning activity outcome data.

[0389] Step 8: Record your results

[0390] Device: Records the results of the learning activities your child performs.

[0391] Input: Learning activity outcome data.

[0392] Data processing: Integrate the outcome data and prepare for the next analysis.

[0393] Output: Consolidated outcome data.

[0394] Step 9: Send results

[0395] Terminal: The recorded performance data is encrypted and sent to the server.

[0396] Input: Integrated outcome data.

[0397] Data processing: The results data will be encrypted and sent.

[0398] Output: Encrypted outcome data.

[0399] Step 10: Evaluate and adjust

[0400] Server: Analyzes the collected implementation results, evaluates the effectiveness of the activity, and optimizes proposals for the next time.

[0401] Input: Outcome data from the database.

[0402] Data processing: Evaluate learning outcomes and emotional fluctuations, and generate feedback to optimize the next learning activity.

[0403] Output: Feedback of optimized learning activities.

[0404] As described above, detailed data processing and calculations are carried out at each step of this system, enabling optimal learning activities to be provided for children.

[0405] (Application example 2)

[0406] 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."

[0407] Conventional educational systems have struggled to provide customized learning activities tailored to individual children's interests and talents. They also lack the ability to grasp changes in children's emotions and interests in real time and provide appropriate feedback accordingly. Furthermore, it has been difficult to integrate users' purchasing behavior and emotional data in virtual stores to provide personalized product recommendations.

[0408] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm and analyzing the child's behavioral patterns, means for generating customized learning activities based on the analysis results, means for distributing the generated learning activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting the results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the activities and optimizing the next suggestions, and means for recording the child's purchasing behavior data and emotional data and making product suggestions based on the results. This makes it possible to provide educational support tailored to each child's talents and interests, and to analyze emotions in real time in virtual stores and make optimal product suggestions.

[0409] "Children's daily behavioral data" refers to data such as study time, answer time, correct answer rate, heart rate, and amount of exercise recorded when using electronic devices such as tablets and smartwatches.

[0410] "Means for transmitting to a server" refers to a communication means by which the terminal encrypts data collected in real time or at specified time intervals and securely uploads it to a server.

[0411] "Means for inputting into machine learning algorithms to analyze children's behavioral patterns" refers to analytical means, including classifiers and regression models, that use the collected data to identify children's behavioral characteristics and patterns.

[0412] The "means for generating customized learning activities" refers to a means for creating learning tasks and exercises that are tailored to the individual talents and interests of each child based on the analysis results.

[0413] The "means for delivering learning activities to devices" refers to a communication means for encrypting the generated learning assignments and sending them to devices such as tablets and smartwatches used by children.

[0414] The "means for children to carry out the distributed activities" refers to the means for providing learning activities for children to carry out through a terminal and recording the results.

[0415] The "means for recording the results of the learning and sending them to the server" refers to a means for recording the results and reactions of the learning activities performed by the child and periodically sending them to the server.

[0416] "Means for analyzing implementation results, evaluating the effectiveness of the activity, and optimizing the next proposal" refers to means for analyzing collected implementation result data, evaluating the effectiveness of the learning activity, and optimizing the content of the next learning activity based on the evaluation results.

[0417] "Children's purchasing behavior data" is data including a user's operation log, browsing time, number of clicks, etc. in a virtual store.

[0418] "Emotion data" refers to data related to emotions extracted from the user's facial expressions and voice obtained using voice analysis and face recognition technology.

[0419] The "means for making product suggestions" is a means for recommending optimal products to users based on the analyzed purchasing behavior data and emotional data.

[0420] The present invention is a system that collects and analyzes purchasing behavior data and emotional data of individual users in a virtual store to make optimal product recommendations. This system is composed of users, terminals, and a server.

[0421] System Configuration

[0422] 1. Terminal

[0423] The devices used are portable electronic devices such as smartphones and smart glasses. These devices are equipped with sensors and cameras to record purchasing behavior data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The smartphone records the operation log and browsing time of the purchasing app, while the smart glasses track eye movements and collect facial expression data.

[0424] 2. Server

[0425] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model for analysis. The server analyzes purchasing behavior patterns and emotion data to identify individual users' interests, preferences, and current emotional state. Based on the analysis results, it generates customized product suggestions and sends them to the device.

[0426] 3. Users

[0427] The user receives product suggestions provided via the device. The user's shopping behavior and reactions in the virtual store are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the product suggestions and optimize the next suggestions.

[0428] Explanation of specific measures

[0429] 1. Data Collection

[0430] The device records activity logs and emotional data in real time as the user uses it. For example, a smartphone captures the operation log of a virtual store app (browsing time, number of clicks) and obtains facial expression data (excitement, joy, confusion, etc.) using an emotion engine. Smart glasses collect eye-tracking data and changes in facial expressions.

[0431] 2. Data Transmission

[0432] The device encrypts the recorded data and periodically sends it to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[0433] 3. Data analysis

[0434] The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it identifies the user's interests and preferences using methods such as classifiers and regression analysis based on a purchasing behavior dataset, and analyzes their emotional state (e.g., excitement, joy, confusion) based on an emotion dataset.

[0435] 4. Product proposal generation and distribution

[0436] The server generates customized product suggestions based on the analysis results. For example, for a user who shows a strong interest in a particular product and tends to purchase it with joy, related products and accessories will be recommended. The emotion engine also responds to emotional changes during shopping. The generated product suggestions are encrypted in an appropriate format and sent to the user's device.

[0437] Program processing

[0438] The server runs the programs described above for data collection, data transmission, data analysis, and product proposal generation and distribution. The main hardware used is a multi-function server, an internet connection, and the user's smartphone or smart glasses. The software uses OpenCV for face recognition technology, Keras for emotion recognition models, and the Requests library for data transmission.

[0439] Specific examples

[0440] For example, imagine a user in a market is browsing a virtual store using smart glasses. The glasses record eye-tracking data and facial expression data (surprise, joy, confusion, etc.). The emotion engine recognizes the user's joy from a smile and sends the data to the server. An AI model on the server analyzes the data and finds that the user is highly interested in a new product. Based on this information, the server can suggest related new product lines and discount offers. A specific prompt might be, "It seems you're interested in our new products. How about these accessories?"

[0441] As described above, the present invention provides a system that analyzes user purchasing behavior and emotional data in real time and makes optimal product suggestions to individual users.

[0442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0443] Step 1:

[0444] When a user uses the virtual store app, the device records purchasing behavior data (operation log, browsing time, number of clicks) and emotional data (facial expression data, eye tracking data) in real time.Specifically, it uses a camera, microphone, and touch sensor to capture the user's facial expressions, voice, and operation status.

[0445] Input: User operation log, facial expression data, gaze data

[0446] Output: Recorded data

[0447] Step 2:

[0448] The device sends the recorded data to a server. The data is encrypted and periodically uploaded to the server using a secure communication protocol (e.g., HTTPS). The data is sent at specified time intervals when it reaches a certain volume.

[0449] Input: Recorded data

[0450] Output: Encrypted data

[0451] Step 3:

[0452] The server stores the received data in a database, where it is kept in an organized format for use in analysis.

[0453] Input: Encrypted data

[0454] Output: Data stored in the database

[0455] Step 4:

[0456] The server inputs the stored data into machine learning algorithms and emotion engines to analyze the user's purchasing behavior patterns and emotions. For example, it uses classifiers and regression analysis based on behavioral data to identify the user's interests and preferences, and inputs emotion data (facial expressions, voice, etc.) into emotion recognition models to identify the user's emotional state.

[0457] Input: Saved data

[0458] Output: Analysis results (purchase behavior patterns, emotional state)

[0459] Step 5:

[0460] The server generates customized product recommendations based on the analysis results, using the generative AI model to create prompts and suggest the best products and related accessories for the user.

[0461] Input: Analysis results

[0462] Output: Product proposal

[0463] Step 6:

[0464] The server delivers the generated product proposals to the terminal. The product proposals are encrypted and sent to the user's terminal, allowing the user to receive the proposals in real time.

[0465] Input: Product proposal

[0466] Output: Encrypted proposal data

[0467] Step 7:

[0468] The user receives the product suggestions provided to the terminal and performs shopping in the virtual store. Specifically, the user browses products according to the product suggestions and considers purchasing them.

[0469] Input: Encrypted proposal data

[0470] Output: User behavior data

[0471] Step 8:

[0472] The device then records the user's new purchasing behavior and emotional data and sends it to the server, which then repeats the process and optimizes the recommendations.

[0473] Input: User behavior data, emotion data

[0474] Output: Recorded data

[0475] The above are the specific processing steps for carrying out the invention.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 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.

[0482] 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).

[0483] 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.

[0484] 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.

[0485] 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).

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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."

[0492] This system collects data on children's daily activities, analyzes their individual talents and interests, and provides customized educational activities based on the collected data. This system is primarily composed of users (children), terminals, and a server.

[0493] System Configuration

[0494] 1. Terminal

[0495] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions, and use facial recognition and behavioral recognition technology to record children's daily actions and reactions. For example, tablets record operation logs and study time when children use learning apps, while smartwatches collect data including exercise volume and heart rate.

[0496] 2. Server

[0497] The server receives data sent from the device and analyzes it using a machine learning algorithm. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns to identify each child's potential abilities and interests. Based on the results of this analysis, it generates customized learning activities and materials and sends them to the device.

[0498] 3. Users

[0499] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[0500] Program processing

[0501] 1. Data Collection

[0502] When a child uses the device, it records activity logs, behavioral data, facial expression data, etc. in real time. It also uses facial recognition technology to capture the child's emotions and concentration, which are also collected as data.

[0503] 2. Data Transmission

[0504] The device encrypts the collected data and periodically uploads it to a server, ensuring data integrity and security.

[0505] 3. Data analysis

[0506] The server inputs the received data into a machine learning model to analyze the child's behavioral patterns. For example, if the child shows a high interest in math calculation problems, it is assumed that the child has mathematical talent.

[0507] 4. Activity Generation and Suggestion

[0508] Based on the analysis results, the server generates customized learning activities, including exercises, games, and projects tailored to the child's interests and strengths, which are then sent to the device and presented to the child.

[0509] 5. Feedback and Adjustments

[0510] The user (child) performs the provided activity, and their results and reactions are recorded on the device again. The recorded data is sent to the server and analyzed. Based on the results, the next learning suggestion is further optimized.

[0511] Specific examples

[0512] For example, suppose a child is using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions (concentration, confusion, enjoyment, etc.) while using the app. This data is sent to a server, where a machine learning model analyzes it and determines that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games and provides them to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[0513] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] Devices: Record data on children's daily activities. Specifically, the tablet captures the operation log of the learning app (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data while using the app (e.g., focused, confused, enjoying). The smartwatch records data such as heart rate, exercise volume, and frequency of use.

[0517] Step 2:

[0518] Terminal: The recorded data is encrypted and periodically sent to the server. For example, when the collected data reaches a certain volume or at a specified time interval, the data is uploaded to the server. This ensures the integrity and security of the data.

[0519] Step 3:

[0520] Server: Stores the received data in a database, safely storing and managing the data and preparing it to be fed to machine learning algorithms as needed.

[0521] Step 4:

[0522] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns. Specifically, based on the dataset, methods such as classifiers and regression analysis are used to identify the child's strengths, areas of interest, and learning approaches.

[0523] Step 5:

[0524] Server: Based on the analysis, it generates customized learning activities. For example, for a child who shows an interest in math, it creates challenging math problems or math games. For a child interested in creative expression, it generates art projects or design assignments.

[0525] Step 6:

[0526] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[0527] Step 7:

[0528] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[0529] Step 8:

[0530] Device: Records the results of the learning activities the child has performed. Specifically, it records the answer time, correct answer rate, changes in emotions and facial expressions, etc., for further analysis.

[0531] Step 9:

[0532] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[0533] Step 10:

[0534] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity, such as the degree of improvement in learning outcomes, changes in the rate of correct answers to math problems, and changes in children's concentration and emotions.

[0535] Step 11:

[0536] Server: Generates feedback based on the analysis results and optimizes the next learning activity suggestion. Depending on the evaluation, adjusts the difficulty and content of the activity and prepares for the next cycle. The server updates the next learning activity and returns to step 1.

[0537] Through the above processing steps, the present invention brings out the potential and talents of children and realizes efficient and effective individualized education.

[0538] Example 1

[0539] 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."

[0540] Conventional educational support systems have struggled to efficiently analyze each child's talents and interests and provide customized educational activities based on those insights. Furthermore, they lacked the technology to create an effective feedback loop while ensuring the security and consistency of collected data. This made it difficult to maximize each child's learning efficiency.

[0541] 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.

[0542] In this invention, the server includes means for inputting received data into a machine learning algorithm and analyzing behavioral patterns, means for generating customized educational activities based on the analysis results using machine learning, and means for analyzing the implementation results, evaluating the effectiveness of the educational activities, and optimizing suggestions for the next time. This makes it possible to efficiently analyze the talents and interests of individual children and provide customized educational activities based on them.

[0543] "Children's daily behavioral data" refers to data related to the behavior of children in their daily lives and educational activities, and includes operation logs of learning applications, answer results, amount of exercise, heart rate, facial expressions, etc.

[0544] The "database" is an information management system that centrally stores received behavioral data and allows searching and analysis as needed.

[0545] "Encryption" is a technology that prevents transmitted data from being deciphered by third parties, and is a means of ensuring data security.

[0546] "Server" means a computer system that receives and stores data sent from a device, analyzes it, and generates activity data.

[0547] A "machine learning algorithm" is a collection of mathematical methods and programs that learn patterns and characteristics from data and make predictions and classifications.

[0548] "Behavioral pattern analysis" is the process of identifying patterns in a child's behavior and reactions based on collected behavioral data, revealing their potential abilities and interests.

[0549] "Customized educational activities" are learning activities and materials specially designed based on a child's characteristics and interests, with the aim of enhancing learning efficiency.

[0550] "Delivery of educational activities" is the process of sending the generated customized learning activities and materials to the device and making them available to the child.

[0551] "Recording implementation results" refers to storing the results and reactions of children when they perform educational activities on the device, which is used to optimize suggestions for the next time.

[0552] "Analysis of feedback data" is a data analysis process to evaluate the effectiveness of educational activities based on the results of implementation and improve the content of proposals for the next time.

[0553] "Facial recognition technology" is a technology that uses sensors and cameras to automatically identify an individual's face and analyze their facial expressions and emotions.

[0554] "Recording concentration and reaction" refers to recording changes in attention and emotions while a child is engaged in educational activities, based on facial expression data obtained using facial recognition technology.

[0555] The present invention is a system that collects data on children's daily behavior, analyzes their individual talents and interests, and provides customized educational activities based on that data. It is composed of users (children), parents, terminals, and a server.

[0556] Terminal

[0557] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. Facial recognition and behavioral recognition technologies are used to record children's daily actions and reactions. For example, the tablet records the operation log and study time when a child uses a learning app, while the smartwatch collects exercise volume and heart rate data.

[0558] The device locally encrypts the collected data and uploads it to the server at regular intervals. This encryption ensures the integrity and security of the data. Specifically, the device is set to send data to the server every night.

[0559] server

[0560] The server receives the data sent from the device and stores it in a database. Based on this stored data, it uses machine learning algorithms to analyze behavioral patterns. Specifically, the server analyzes the received behavioral data to identify each child's potential abilities and interests. For example, a child who shows a high interest in math calculation problems is deemed to have mathematical talent.

[0561] A machine learning algorithm is used to generate customized educational activities based on the analysis results. For example, a generative AI model (e.g., GPT-3) is used to generate optimal learning activities by inputting the following prompt sentence:

[0562] Prompt Sentence Examples

[0563] "Based on the following data, please suggest the best math learning activity for this child:

[0564] Answer time: Average answer time for each question is 30 seconds

[0565] Correct answer rate: 95%

[0566] Facial expressions: Concentration (70%), Confusion (20%), Happiness (10%)

[0567] Suggest new math activities that will interest your child."

[0568] Delivery and implementation of educational activities

[0569] The generated educational activity is sent to the device and provided to the child. The user (child) performs the provided educational activity. The device again records the results and reactions during this activity. For example, it acquires and records the percentage of correct answers, the time it takes to answer, and facial expression data (enjoyed, confused, etc.).

[0570] Feedback and Optimization

[0571] The recorded data on the results is then sent back to the server, which uses this new data to provide feedback and evaluate the effectiveness of the educational activity. The next suggestion is then further optimized based on this feedback.

[0572] As a concrete example, consider a child using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions while using the app. This data is sent to a server and analyzed by a machine learning model. The analysis reveals that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games, which it then provides to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[0573] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[0574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0575] Program processing flow

[0576] Step 1:

[0577] Data collection

[0578] The devices (tablets and smartwatches) collect behavioral data through the user's (child's) activities. Specifically, the tablets record the operation log of the learning application, study time, answer results, etc., while the smartwatch records exercise volume and heart rate. In addition, the camera sensor captures facial expression data (concentration, confusion, enjoyment, etc.) in real time and analyzes it using facial recognition technology.

[0579] Input: Children's operation log, study time, answer results, exercise amount, heart rate, facial expression data

[0580] Output: A set of collected behavioral data

[0581] Operation: Data acquisition from sensors and cameras, initial analysis, and local storage

[0582] Step 2:

[0583] Data transmission

[0584] The device locally encrypts the collected data and uploads it to the server at regular intervals. Specifically, the device is scheduled to send encrypted data every night, ensuring the integrity and security of the data.

[0585] Input: Encrypted behavioral data

[0586] Output: Behavioral data sent to the server

[0587] Operation: Data encryption process, uploading encrypted data to server

[0588] Step 3:

[0589] Data reception and storage

[0590] The server receives the behavioral data sent from the device and stores it in a database as a log, allowing the data required for subsequent analysis steps to be managed in a centralized manner.

[0591] Input: Behavioral data sent from the device

[0592] Output: Behavioral data stored in a database

[0593] Action: Writing data to the database

[0594] Step 4:

[0595] Data analysis

[0596] The server inputs the behavioral data stored in the database into a machine learning algorithm to perform analysis. This extracts the child's behavioral patterns and identifies their potential abilities and interests. For example, the server analyzes the child's learning patterns and evaluates their mathematical talent based on their reaction time to math problems, the percentage of correct answers, and facial expression data.

[0597] Input: Behavioral data stored in a database

[0598] Output: Behavioral pattern analysis results

[0599] Action: Input data into machine learning models, analyze behavioral patterns, and extract results

[0600] Step 5:

[0601] Activity Creation

[0602] Based on the analysis results, the server uses a generative AI model to generate customized educational activities. In this process, specific prompts are input into the generative AI model (e.g., GPT-3) to create optimal learning activities. For example, "This child has a high interest in math, so I'd like to suggest some challenging math problems and creative math games."

[0603] Input: behavior pattern analysis results, prompt text

[0604] Output: Customized educational activities

[0605] Operation: Input prompts to the generative AI model, generate educational activities

[0606] Step 6:

[0607] Activity Broadcast

[0608] The generated educational activity is sent from the server to the terminal and provided to the child.

[0609] Input: Generated educational activities

[0610] Output: Educational activities delivered to devices

[0611] Action: Delivering educational activities to devices

[0612] Step 7:

[0613] Activity implementation

[0614] The user (child) performs the provided educational activity, and the device records the results, such as the percentage of correct answers, the time it took to answer, and facial expression data (such as happy or confused).

[0615] Input: Educational activity status

[0616] Output: Implementation result data

[0617] Behavior: Collecting and recording behavioral data

[0618] Step 8:

[0619] Feedback and Adjustments

[0620] The server receives the implementation result data sent from the device again and analyzes it as feedback data. Based on the analysis results, the next educational activity is optimized.

[0621] Input: Implementation result data

[0622] Output: Optimized next teaching activity

[0623] Actions: Analyzing feedback data and optimizing educational activities

[0624] The above is the flow of the program processing of the present invention and the specific operation of each step, which optimizes the learning process for each child and provides effective educational support.

[0625] (Application example 1)

[0626] 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."

[0627] Traditional educational systems have struggled to provide customized educational activities based on each child's individual talents and interests. Furthermore, uniform educational programs fail to capture children's interests and lead to insufficient learning outcomes. Furthermore, educational activities within educational facilities face the challenge of being unable to grasp children's real-time behavior and emotions and instantly customize educational activities based on them.

[0628] 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.

[0629] In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm to analyze the child's behavioral patterns, means for generating customized educational activities based on the analysis results, means for distributing the generated educational activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the educational activities and optimize suggestions for the next time, means for recording the child's gaze, behavior, and voice commands in real time using a smart device, and means for providing a customized interactive experience within the educational facility. This makes it possible to provide customized educational activities based on the child's interests and talents in real time and optimize educational effectiveness.

[0630] "Children's daily behavioral data" refers to data that records various actions and reactions that children perform in their daily lives.

[0631] "Means for recording" refers to devices or systems for electronically storing behavioral data, emotional data, etc.

[0632] "Means for transmitting to a server" refers to a combination of hardware and software for transferring data from a terminal to a server.

[0633] A "machine learning algorithm" is an algorithm that extracts patterns and knowledge from data and uses them to make predictions and classifications.

[0634] "Means of analysis" refers to devices and software that use machine learning algorithms to analyze data and extract meaningful information.

[0635] "Customized educational activities" refer to educational activities that are specifically designed based on the talents and interests of each individual child.

[0636] "Means for delivering to the device" refers to the technology or device used to transfer the generated educational activity to the user's device.

[0637] "Implementation means" refers to the equipment or technology that allows children to actually carry out the delivered educational activity.

[0638] "Means for recording the results of an activity and transmitting them to a server" refers to devices or technologies for saving data after the activity is completed and transmitting that data to a server.

[0639] "Means for evaluating the effectiveness of educational activities and optimizing proposals for the next time" refers to technologies and devices that analyze the results of implementation and use those results to make the next educational activity more effective.

[0640] "Smart devices" refer to portable electronic devices equipped with communication functions and sensors that are capable of collecting data and interacting with users.

[0641] "Means for recording gaze, actions, and voice commands in real time" refers to technologies and devices that instantly collect and store a user's gaze movements, body movements, and voice instructions.

[0642] "Means for providing customized interactive experiences within educational facilities" refers to technologies and devices used in educational facilities to design and provide participatory educational activities based on children's interests and talents.

[0643] This system collects and analyzes data on children's daily activities and provides customized educational activities based on their individual talents and interests. The system mainly consists of a terminal, a server, and a user.

[0644] System Configuration

[0645] 1. Terminal

[0646] The devices used include portable electronic devices such as tablets, smartwatches, smart glasses, and head-mounted displays (HMDs). These devices are equipped with sensors and cameras to record behavioral and emotional data, and use facial recognition and behavioral recognition technologies. For example, smart glasses record eye movements and facial expressions, while smartwatches measure heart rate and exercise volume. This data is collected in real time, and the devices encrypt and send it to a server.

[0647] 2. Server

[0648] The server receives the data sent from the device and analyzes it using a machine learning algorithm (e.g., TensorFlow). The received data is stored in a database (e.g., MySQL). The server analyzes the data and identifies the child's behavioral patterns and areas of interest. Based on the results of this analysis, the server generates customized educational activities and delivers them to the device. In addition, the server reanalyzes the user's feedback data to optimize suggestions for the next educational activity.

[0649] 3. Users

[0650] Users (children and their parents or educators) carry out educational activities provided via the device. The child's activities and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activities and further optimize suggestions for the next time.

[0651] Specific examples

[0652] A concrete example is an interactive experience using smart glasses and HMDs in a science museum's educational facilities. When a child walks around the educational facility and spends a long time in front of a particular exhibit, the smart glasses collect behavioral data and an increase in heart rate. This data is sent to a server and analyzed using machine learning algorithms. If the server determines that the child has a strong interest in the exhibit, it generates a customized interactive experience based on that interest (e.g., additional explanations or related mini-games) and delivers it to the smart glasses.

[0653] For example, a prompt to a generative AI model might look like this:

[0654] "Analyze children's behavior data in the fossil exhibit area and generate customized educational programs about fossils."

[0655] This system makes it possible to provide customized educational activities in real time that are tailored to each child's individual interests and talents, maximizing educational effectiveness.

[0656] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0657] Step 1:

[0658] The device records the child's daily behavior data in real time.

[0659] Specifically, devices such as smart glasses and smart watches use sensors and cameras to collect eye movements, heart rate, voice commands, body movements, and facial expressions.

[0660] Input: Child's gaze data, heart rate data, voice commands, body movement data, facial expression data

[0661] Output: raw recorded data

[0662] Step 2:

[0663] The terminal encrypts the recorded data and transmits it to the server.

[0664] Specifically, data is encrypted using the SSL / TLS protocol and uploaded to a server via Wi-Fi.

[0665] Input: raw recorded data

[0666] Output: Encrypted data

[0667] Step 3:

[0668] The server inputs the received data into a machine learning algorithm to analyze the child's behavioral patterns.

[0669] Specifically, it uses TensorFlow to analyze data and identify children's areas of interest and behavioral patterns.

[0670] Input: Encrypted data

[0671] Output: Analysis results (areas of interest, behavioral patterns)

[0672] Step 4:

[0673] The server generates customized educational activities based on the analysis results.

[0674] Specifically, generative AI models are used to create problem sets, interactive games, projects, and more tailored to specific areas of interest.

[0675] Input: Analysis results

[0676] Output: Customized educational activities

[0677] Step 5:

[0678] The server distributes the generated educational activities to the terminals.

[0679] Specifically, the device receives educational activities, notifies the user appropriately, and provides visual and audio guidance as necessary.

[0680] Input: Customized Educational Activities

[0681] Output: Delivered educational activity

[0682] Step 6:

[0683] The user (child) performs the educational activity that is delivered to them.

[0684] Specifically, they participate in interactive experiences displayed using smart glasses or HMDs and run applications.

[0685] Input: Delivered educational activity

[0686] Output: Activity execution results

[0687] Step 7:

[0688] The terminal records the implementation results and transmits them to the server.

[0689] Specifically, sensors record the results and reactions of each child's activity, and the necessary data is then encrypted and uploaded to the server.

[0690] Input: Activity execution result

[0691] Output: Encrypted execution data

[0692] Step 8:

[0693] The server analyzes the results of the implementation, evaluates the effectiveness of the educational activity, and optimizes the next proposal.

[0694] Specifically, the received data is analyzed and the next educational activity is further customized based on the results.

[0695] Input: Encrypted implementation data

[0696] Output: Next suggested activity

[0697] 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.

[0698] This invention is a system that collects and analyzes children's daily behavior data to provide learning activities customized to their individual talents and interests. In addition, by combining it with an emotion engine, it acquires and analyzes the user's emotion data to provide more accurate educational support. The system consists of a user (child), a terminal, and a server.

[0699] System Configuration

[0700] 1. Terminal

[0701] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[0702] 2. Server

[0703] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[0704] 3. Users

[0705] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[0706] Program processing

[0707] 1. Data Collection

[0708] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[0709] 2. Data Transmission

[0710] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[0711] 3. Data analysis

[0712] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[0713] 4. Activity Generation and Suggestion

[0714] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[0715] 5. Activity Distribution

[0716] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[0717] 6. Activity implementation

[0718] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[0719] 7. Recording of implementation results

[0720] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[0721] 8. Send results

[0722] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[0723] 9. Evaluation and Adjustment

[0724] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[0725] Specific examples

[0726] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[0727] The processing flow will be explained below.

[0728] Step 1:

[0729] Device: Records children's daily behavioral and emotional data. Specifically, the tablet captures learning app operation logs (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data (e.g., concentration, confusion, enjoyment) in real time. The smartwatch collects data such as heart rate, exercise volume, and frequency of use. The emotion engine uses facial recognition and voice analysis technology to detect the user's emotions (e.g., joy, sadness, surprise).

[0730] Step 2:

[0731] Device: The recorded behavioral and emotional data is encrypted and periodically sent to the server. The data is uploaded to the server when the collected data reaches a certain volume or at specified intervals to ensure secure communication.

[0732] Step 3:

[0733] Server: Stores the received data in a database, safely storing and managing the data and preparing it to serve the machine learning algorithms and sentiment engines as needed.

[0734] Step 4:

[0735] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns and emotional data. Specifically, behavioral data such as study time, accuracy rate, and answer time are combined with emotional data analyzed by the emotion engine to identify the child's favorite subjects, areas of interest, and current emotional state.

[0736] Step 5:

[0737] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging calculation problems and math games. It also generates activities with emotional feedback to respond to changes in emotions.

[0738] Step 6:

[0739] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[0740] Step 7:

[0741] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks. Activities with emotional feedback respond to emotional changes during learning.

[0742] Step 8:

[0743] Device: Records the results of the child's learning activities. Specifically, it records the answer time, accuracy rate, changes in emotions and facial expressions, etc., for further analysis. The emotion engine monitors emotional changes during learning in real time.

[0744] Step 9:

[0745] Terminal: The results of the experiment are encrypted and sent to the server. At this time, both behavioral data and emotional data are uploaded to the server.

[0746] Step 10:

[0747] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. Specifically, it evaluates learning outcomes (e.g., improvement in correct answer rate, reduction in answer time) and emotional changes (e.g., increased enjoyment and concentration during learning), and generates feedback based on the analysis results.

[0748] Step 11:

[0749] Server: Optimizes the next learning activity suggestion based on the feedback. Depending on the evaluation, the difficulty and content of the activity are adjusted and reflected in the next learning suggestion. The server updates the next learning activity, realizing cyclical operation of the system.

[0750] In this way, the system of the present invention, which combines an emotion engine, analyzes children's behavioral data and emotion data and provides optimal learning activities for each individual child, thereby providing effective educational support.

[0751] Example 2

[0752] 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."

[0753] Conventional learning support systems have difficulty providing customized learning activities that fully consider each child's individual talents, interests, and emotional state. As a result, there is a problem in that they are unable to provide effective support to increase children's motivation to learn.

[0754] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0755] In this invention, the server includes a means for storing the received data in a database, a means for inputting the stored data into a machine learning algorithm to analyze the child's behavioral patterns, and a means for generating customized learning activities using a generative AI model based on the analysis results, thereby enabling highly accurate educational support that takes into account the individual talents, interests, and emotional states of each child.

[0756] "Children's daily behavioral data" refers to data about the actions and behaviors that children perform during their daily lives and learning activities.

[0757] "Recording means" refers to devices or methods that capture data on a child's daily behavior and store that information.

[0758] "Transmitting means" refers to a device or method for transferring recorded data to a receiving device such as a server.

[0759] "Means for storing received data in a database" refers to a device or method by which the server records and stores data received from a terminal in a database.

[0760] A "machine learning algorithm" is an algorithm that analyzes data and automatically learns patterns and regularities to predict or classify outcomes.

[0761] A "generative AI model" is an artificial intelligence model that processes information like a human and generates answers to new data or problems.

[0762] "Customized learning activities" refer to learning tasks and exercises that are appropriately tailored based on each child's abilities, interests, and emotions.

[0763] "Means for distribution" refers to a device or method for transmitting the learning activity generated by the server to the terminal and providing it to the child.

[0764] "Means for recording results" refers to a device or method for saving the results of a child's learning activities.

[0765] "Means for analyzing implementation results" refers to devices or methods for analyzing data on children's learning activities and identifying their effectiveness and areas for improvement.

[0766] "Facial recognition technology" refers to technology that uses a camera or sensor to detect a person's face and identify their individual facial expressions and features.

[0767] "Voice analysis technology" refers to technology that uses a microphone or audio receiving device to analyze audio signals and identify their content and characteristics.

[0768] "Concentration" refers to an indicator of a child's attention and dedication to a given task or activity.

[0769] A "prompt" refers to the instructions or input text that a generative AI model uses to generate new data or answers.

[0770] This invention relates to a system that collects and analyzes children's daily behavioral data to provide customized learning activities based on their individual talents and interests. By combining it with an emotion engine, it acquires and analyzes the user's emotional data to provide more accurate educational support.

[0771] System Configuration

[0772] 1. Terminal

[0773] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the ability to detect emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[0774] 2. Server

[0775] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[0776] 3. Users

[0777] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[0778] Program processing

[0779] The specific operation of the system is explained below. The system mainly functions through the following processes: data collection, data transmission, data storage, data analysis, activity generation, activity distribution, activity implementation, recording of implementation results, result transmission, evaluation and adjustment.

[0780] 1. Data Collection

[0781] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[0782] 2. Data Transmission

[0783] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[0784] 3. Data storage

[0785] Server: The server stores the received data in a database, adds new entries to the database, and checks the integrity of the data.

[0786] 4. Data Analysis

[0787] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[0788] 5. Activity Generation and Suggestion

[0789] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[0790] 6. Activity Distribution

[0791] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[0792] 7. Activity implementation

[0793] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[0794] 8. Recording of implementation results

[0795] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[0796] 9. Send results

[0797] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[0798] 10. Evaluation and Adjustment

[0799] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[0800] Specific examples

[0801] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[0802] Prompt Sentence Examples

[0803] "Please suggest the best learning activities for children who are interested in mathematics and who enjoy engaging in them with a smile."

[0804] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0805] Specific processing steps of the program

[0806] Step 1: Data collection

[0807] Devices: Records real-time activity logs, behavioral data, and emotional data as children engage in learning activities. Devices used include tablets and smartwatches.

[0808] Input: Operation information of the learning app, facial expression images from the camera, audio data from the microphone, and biometric information from the smartwatch.

[0809] Data processing: Facial recognition technology is used to analyze facial expressions and detect emotions such as "concentration," "confusion," and "happiness." Voice analysis technology is used to determine emotions from the tone of voice.

[0810] Output: Behavioral data integrating learning operation logs, facial expression data, voice data, and biometric data.

[0811] Step 2: Send data

[0812] Terminal: The recorded data is encrypted and periodically sent to the server.

[0813] Input: Integrated behavioral data.

[0814] Data processing: Encrypting data and sending it through a secure communication channel.

[0815] Output: Encrypted behavioral data.

[0816] Step 3: Save data

[0817] Server: Stores the received data in a database.

[0818] Input: Encrypted behavioral data.

[0819] Data processing: Decrypt the data and store it in the database in the appropriate format.

[0820] Output: Behavioral data stored in a database.

[0821] Step 4: Data analysis

[0822] Server: Analyzes the received data using machine learning algorithms and an emotion engine.

[0823] Input: Behavioral and emotional data from the database.

[0824] Data processing: Using machine learning algorithms to analyze behavioral patterns and identify areas of expertise and interest. Using an emotion engine to analyze emotional fluctuations.

[0825] Output: Analysis results (child's strengths, interests, emotional state).

[0826] Step 5: Activity generation and proposal

[0827] Server: Based on the analysis results, a generative AI model is used to generate customized learning activities.

[0828] Input: Analysis results (areas of expertise, areas of interest, emotional state).

[0829] Data processing: Use a generative AI model to create learning activities suitable for children. Enter the prompt "Suggest the best learning activities for a child who is interested in math and smiles when they engage in it."

[0830] Output: A customized learning activity.

[0831] Step 6: Activity Delivery

[0832] Server: Delivers the generated learning activities to the devices.

[0833] Input: The generated learning activity.

[0834] Data processing: Encrypting activity in a proper format and sending it to your child's device.

[0835] Output: Encrypted learning activity.

[0836] Step 7: Implement the activity

[0837] User (child): Carries out learning activities provided on the device.

[0838] Input: Delivered learning activity.

[0839] Data processing: Conduct the activity and record the answer time, correct answer rate, and emotional state.

[0840] Output: Learning activity outcome data.

[0841] Step 8: Record your results

[0842] Device: Records the results of the learning activities your child performs.

[0843] Input: Learning activity outcome data.

[0844] Data processing: Integrate the outcome data and prepare for the next analysis.

[0845] Output: Consolidated outcome data.

[0846] Step 9: Send results

[0847] Terminal: The recorded performance data is encrypted and sent to the server.

[0848] Input: Integrated outcome data.

[0849] Data processing: The results data will be encrypted and sent.

[0850] Output: Encrypted outcome data.

[0851] Step 10: Evaluate and adjust

[0852] Server: Analyzes the collected implementation results, evaluates the effectiveness of the activity, and optimizes proposals for the next time.

[0853] Input: Outcome data from the database.

[0854] Data processing: Evaluate learning outcomes and emotional fluctuations, and generate feedback to optimize the next learning activity.

[0855] Output: Feedback of optimized learning activities.

[0856] As described above, detailed data processing and calculations are carried out at each step of this system, enabling optimal learning activities to be provided for children.

[0857] (Application example 2)

[0858] 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."

[0859] Conventional educational systems have struggled to provide customized learning activities tailored to individual children's interests and talents. They also lack the ability to grasp changes in children's emotions and interests in real time and provide appropriate feedback accordingly. Furthermore, it has been difficult to integrate users' purchasing behavior and emotional data in virtual stores to provide personalized product recommendations.

[0860] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm and analyzing the child's behavioral patterns, means for generating customized learning activities based on the analysis results, means for distributing the generated learning activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting the results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the activities and optimizing the next suggestions, and means for recording the child's purchasing behavior data and emotional data and making product suggestions based on the results. This makes it possible to provide educational support tailored to each child's talents and interests, and to analyze emotions in real time in virtual stores and make optimal product suggestions.

[0861] "Children's daily behavioral data" refers to data such as study time, answer time, correct answer rate, heart rate, and amount of exercise recorded when using electronic devices such as tablets and smartwatches.

[0862] "Means for transmitting to a server" refers to a communication means by which the terminal encrypts data collected in real time or at specified time intervals and securely uploads it to a server.

[0863] "Means for inputting into machine learning algorithms to analyze children's behavioral patterns" refers to analytical means, including classifiers and regression models, that use the collected data to identify children's behavioral characteristics and patterns.

[0864] The "means for generating customized learning activities" refers to a means for creating learning tasks and exercises that are tailored to the individual talents and interests of each child based on the analysis results.

[0865] The "means for delivering learning activities to devices" refers to a communication means for encrypting the generated learning assignments and sending them to devices such as tablets and smartwatches used by children.

[0866] The "means for children to carry out the distributed activities" refers to the means for providing learning activities for children to carry out through a terminal and recording the results.

[0867] The "means for recording the results of the learning and sending them to the server" refers to a means for recording the results and reactions of the learning activities performed by the child and periodically sending them to the server.

[0868] "Means for analyzing implementation results, evaluating the effectiveness of the activity, and optimizing the next proposal" refers to means for analyzing collected implementation result data, evaluating the effectiveness of the learning activity, and optimizing the content of the next learning activity based on the evaluation results.

[0869] "Children's purchasing behavior data" is data including a user's operation log, browsing time, number of clicks, etc. in a virtual store.

[0870] "Emotion data" refers to data related to emotions extracted from the user's facial expressions and voice obtained using voice analysis and face recognition technology.

[0871] The "means for making product suggestions" is a means for recommending optimal products to users based on the analyzed purchasing behavior data and emotional data.

[0872] The present invention is a system that collects and analyzes purchasing behavior data and emotional data of individual users in a virtual store to make optimal product recommendations. This system is composed of users, terminals, and a server.

[0873] System Configuration

[0874] 1. Terminal

[0875] The devices used are portable electronic devices such as smartphones and smart glasses. These devices are equipped with sensors and cameras to record purchasing behavior data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The smartphone records the operation log and browsing time of the purchasing app, while the smart glasses track eye movements and collect facial expression data.

[0876] 2. Server

[0877] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model for analysis. The server analyzes purchasing behavior patterns and emotion data to identify individual users' interests, preferences, and current emotional state. Based on the analysis results, it generates customized product suggestions and sends them to the device.

[0878] 3. Users

[0879] The user receives product suggestions provided via the device. The user's shopping behavior and reactions in the virtual store are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the product suggestions and optimize the next suggestions.

[0880] Explanation of specific measures

[0881] 1. Data Collection

[0882] The device records activity logs and emotional data in real time as the user uses it. For example, a smartphone captures the operation log of a virtual store app (browsing time, number of clicks) and obtains facial expression data (excitement, joy, confusion, etc.) using an emotion engine. Smart glasses collect eye-tracking data and changes in facial expressions.

[0883] 2. Data Transmission

[0884] The device encrypts the recorded data and periodically sends it to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[0885] 3. Data analysis

[0886] The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it identifies the user's interests and preferences using methods such as classifiers and regression analysis based on a purchasing behavior dataset, and analyzes their emotional state (e.g., excitement, joy, confusion) based on an emotion dataset.

[0887] 4. Product proposal generation and distribution

[0888] The server generates customized product suggestions based on the analysis results. For example, for a user who shows a strong interest in a particular product and tends to purchase it with joy, related products and accessories will be recommended. The emotion engine also responds to emotional changes during shopping. The generated product suggestions are encrypted in an appropriate format and sent to the user's device.

[0889] Program processing

[0890] The server runs the programs described above for data collection, data transmission, data analysis, and product proposal generation and distribution. The main hardware used is a multi-function server, an internet connection, and the user's smartphone or smart glasses. The software uses OpenCV for face recognition technology, Keras for emotion recognition models, and the Requests library for data transmission.

[0891] Specific examples

[0892] For example, imagine a user in a market is browsing a virtual store using smart glasses. The glasses record eye-tracking data and facial expression data (surprise, joy, confusion, etc.). The emotion engine recognizes the user's joy from a smile and sends the data to the server. An AI model on the server analyzes the data and finds that the user is highly interested in a new product. Based on this information, the server can suggest related new product lines and discount offers. A specific prompt might be, "It seems you're interested in our new products. How about these accessories?"

[0893] As described above, the present invention provides a system that analyzes user purchasing behavior and emotional data in real time and makes optimal product suggestions to individual users.

[0894] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0895] Step 1:

[0896] When a user uses the virtual store app, the device records purchasing behavior data (operation log, browsing time, number of clicks) and emotional data (facial expression data, eye tracking data) in real time.Specifically, it uses a camera, microphone, and touch sensor to capture the user's facial expressions, voice, and operation status.

[0897] Input: User operation log, facial expression data, gaze data

[0898] Output: Recorded data

[0899] Step 2:

[0900] The device sends the recorded data to a server. The data is encrypted and periodically uploaded to the server using a secure communication protocol (e.g., HTTPS). The data is sent at specified time intervals when it reaches a certain volume.

[0901] Input: Recorded data

[0902] Output: Encrypted data

[0903] Step 3:

[0904] The server stores the received data in a database, where it is kept in an organized format for use in analysis.

[0905] Input: Encrypted data

[0906] Output: Data stored in the database

[0907] Step 4:

[0908] The server inputs the stored data into machine learning algorithms and emotion engines to analyze the user's purchasing behavior patterns and emotions. For example, it uses classifiers and regression analysis based on behavioral data to identify the user's interests and preferences, and inputs emotion data (facial expressions, voice, etc.) into emotion recognition models to identify the user's emotional state.

[0909] Input: Saved data

[0910] Output: Analysis results (purchase behavior patterns, emotional state)

[0911] Step 5:

[0912] The server generates customized product recommendations based on the analysis results, using the generative AI model to create prompts and suggest the best products and related accessories for the user.

[0913] Input: Analysis results

[0914] Output: Product proposal

[0915] Step 6:

[0916] The server delivers the generated product proposals to the terminal. The product proposals are encrypted and sent to the user's terminal, allowing the user to receive the proposals in real time.

[0917] Input: Product proposal

[0918] Output: Encrypted proposal data

[0919] Step 7:

[0920] The user receives the product suggestions provided to the terminal and performs shopping in the virtual store. Specifically, the user browses products according to the product suggestions and considers purchasing them.

[0921] Input: Encrypted proposal data

[0922] Output: User behavior data

[0923] Step 8:

[0924] The device then records the user's new purchasing behavior and emotional data and sends it to the server, which then repeats the process and optimizes the recommendations.

[0925] Input: User behavior data, emotion data

[0926] Output: Recorded data

[0927] The above are the specific processing steps for carrying out the invention.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] [Third embodiment]

[0932] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0933] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0934] 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).

[0935] 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.

[0936] 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.

[0937] 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).

[0938] 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.

[0939] 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.

[0940] 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.

[0941] 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.

[0942] 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.

[0943] 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."

[0944] This system collects data on children's daily activities, analyzes their individual talents and interests, and provides customized educational activities based on the collected data. This system is primarily composed of users (children), terminals, and a server.

[0945] System Configuration

[0946] 1. Terminal

[0947] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions, and use facial recognition and behavioral recognition technology to record children's daily actions and reactions. For example, tablets record operation logs and study time when children use learning apps, while smartwatches collect data including exercise volume and heart rate.

[0948] 2. Server

[0949] The server receives data sent from the device and analyzes it using a machine learning algorithm. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns to identify each child's potential abilities and interests. Based on the results of this analysis, it generates customized learning activities and materials and sends them to the device.

[0950] 3. Users

[0951] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[0952] Program processing

[0953] 1. Data Collection

[0954] When a child uses the device, it records activity logs, behavioral data, facial expression data, etc. in real time. It also uses facial recognition technology to capture the child's emotions and concentration, which are also collected as data.

[0955] 2. Data Transmission

[0956] The device encrypts the collected data and periodically uploads it to a server, ensuring data integrity and security.

[0957] 3. Data analysis

[0958] The server inputs the received data into a machine learning model to analyze the child's behavioral patterns. For example, if the child shows a high interest in math calculation problems, it is assumed that the child has mathematical talent.

[0959] 4. Activity Generation and Suggestion

[0960] Based on the analysis results, the server generates customized learning activities, including exercises, games, and projects tailored to the child's interests and strengths, which are then sent to the device and presented to the child.

[0961] 5. Feedback and Adjustments

[0962] The user (child) performs the provided activity, and their results and reactions are recorded on the device again. The recorded data is sent to the server and analyzed. Based on the results, the next learning suggestion is further optimized.

[0963] Specific examples

[0964] For example, suppose a child is using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions (concentration, confusion, enjoyment, etc.) while using the app. This data is sent to a server, where a machine learning model analyzes it and determines that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games and provides them to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[0965] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[0966] The processing flow will be explained below.

[0967] Step 1:

[0968] Devices: Record data on children's daily activities. Specifically, the tablet captures the operation log of the learning app (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data while using the app (e.g., focused, confused, enjoying). The smartwatch records data such as heart rate, exercise volume, and frequency of use.

[0969] Step 2:

[0970] Terminal: The recorded data is encrypted and periodically sent to the server. For example, when the collected data reaches a certain volume or at a specified time interval, the data is uploaded to the server. This ensures the integrity and security of the data.

[0971] Step 3:

[0972] Server: Stores the received data in a database, safely storing and managing the data and preparing it to be fed to machine learning algorithms as needed.

[0973] Step 4:

[0974] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns. Specifically, based on the dataset, methods such as classifiers and regression analysis are used to identify the child's strengths, areas of interest, and learning approaches.

[0975] Step 5:

[0976] Server: Based on the analysis, it generates customized learning activities. For example, for a child who shows an interest in math, it creates challenging math problems or math games. For a child interested in creative expression, it generates art projects or design assignments.

[0977] Step 6:

[0978] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[0979] Step 7:

[0980] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[0981] Step 8:

[0982] Device: Records the results of the learning activities the child has performed. Specifically, it records the answer time, correct answer rate, changes in emotions and facial expressions, etc., for further analysis.

[0983] Step 9:

[0984] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[0985] Step 10:

[0986] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity, such as the degree of improvement in learning outcomes, changes in the rate of correct answers to math problems, and changes in children's concentration and emotions.

[0987] Step 11:

[0988] Server: Generates feedback based on the analysis results and optimizes the next learning activity suggestion. Depending on the evaluation, adjusts the difficulty and content of the activity and prepares for the next cycle. The server updates the next learning activity and returns to step 1.

[0989] Through the above processing steps, the present invention brings out the potential and talents of children and realizes efficient and effective individualized education.

[0990] Example 1

[0991] 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."

[0992] Conventional educational support systems have struggled to efficiently analyze each child's talents and interests and provide customized educational activities based on those insights. Furthermore, they lacked the technology to create an effective feedback loop while ensuring the security and consistency of collected data. This made it difficult to maximize each child's learning efficiency.

[0993] 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.

[0994] In this invention, the server includes means for inputting received data into a machine learning algorithm and analyzing behavioral patterns, means for generating customized educational activities based on the analysis results using machine learning, and means for analyzing the implementation results, evaluating the effectiveness of the educational activities, and optimizing suggestions for the next time. This makes it possible to efficiently analyze the talents and interests of individual children and provide customized educational activities based on them.

[0995] "Children's daily behavioral data" refers to data related to the behavior of children in their daily lives and educational activities, and includes operation logs of learning applications, answer results, amount of exercise, heart rate, facial expressions, etc.

[0996] The "database" is an information management system that centrally stores received behavioral data and allows searching and analysis as needed.

[0997] "Encryption" is a technology that prevents transmitted data from being deciphered by third parties, and is a means of ensuring data security.

[0998] "Server" means a computer system that receives and stores data sent from a device, analyzes it, and generates activity data.

[0999] A "machine learning algorithm" is a collection of mathematical methods and programs that learn patterns and characteristics from data and make predictions and classifications.

[1000] "Behavioral pattern analysis" is the process of identifying patterns in a child's behavior and reactions based on collected behavioral data, revealing their potential abilities and interests.

[1001] "Customized educational activities" are learning activities and materials specially designed based on a child's characteristics and interests, with the aim of enhancing learning efficiency.

[1002] "Delivery of educational activities" is the process of sending the generated customized learning activities and materials to the device and making them available to the child.

[1003] "Recording implementation results" refers to storing the results and reactions of children when they perform educational activities on the device, which is used to optimize suggestions for the next time.

[1004] "Analysis of feedback data" is a data analysis process to evaluate the effectiveness of educational activities based on the results of implementation and improve the content of proposals for the next time.

[1005] "Facial recognition technology" is a technology that uses sensors and cameras to automatically identify an individual's face and analyze their facial expressions and emotions.

[1006] "Recording concentration and reaction" refers to recording changes in attention and emotions while a child is engaged in educational activities, based on facial expression data obtained using facial recognition technology.

[1007] The present invention is a system that collects data on children's daily behavior, analyzes their individual talents and interests, and provides customized educational activities based on that data. It is composed of users (children), parents, terminals, and a server.

[1008] Terminal

[1009] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. Facial recognition and behavioral recognition technologies are used to record children's daily actions and reactions. For example, the tablet records the operation log and study time when a child uses a learning app, while the smartwatch collects exercise volume and heart rate data.

[1010] The device locally encrypts the collected data and uploads it to the server at regular intervals. This encryption ensures the integrity and security of the data. Specifically, the device is set to send data to the server every night.

[1011] server

[1012] The server receives the data sent from the device and stores it in a database. Based on this stored data, it uses machine learning algorithms to analyze behavioral patterns. Specifically, the server analyzes the received behavioral data to identify each child's potential abilities and interests. For example, a child who shows a high interest in math calculation problems is deemed to have mathematical talent.

[1013] A machine learning algorithm is used to generate customized educational activities based on the analysis results. For example, a generative AI model (e.g., GPT-3) is used to generate optimal learning activities by inputting the following prompt sentence:

[1014] Prompt Sentence Examples

[1015] "Based on the following data, please suggest the best math learning activity for this child:

[1016] Answer time: Average answer time for each question is 30 seconds

[1017] Correct answer rate: 95%

[1018] Facial expressions: Concentration (70%), Confusion (20%), Happiness (10%)

[1019] Suggest new math activities that will interest your child."

[1020] Delivery and implementation of educational activities

[1021] The generated educational activity is sent to the device and provided to the child. The user (child) performs the provided educational activity. The device again records the results and reactions during this activity. For example, it acquires and records the percentage of correct answers, the time it takes to answer, and facial expression data (enjoyed, confused, etc.).

[1022] Feedback and Optimization

[1023] The recorded data on the results is then sent back to the server, which uses this new data to provide feedback and evaluate the effectiveness of the educational activity. The next suggestion is then further optimized based on this feedback.

[1024] As a concrete example, consider a child using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions while using the app. This data is sent to a server and analyzed by a machine learning model. The analysis reveals that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games, which it then provides to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[1025] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[1026] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1027] Program processing flow

[1028] Step 1:

[1029] Data collection

[1030] The devices (tablets and smartwatches) collect behavioral data through the user's (child's) activities. Specifically, the tablets record the operation log of the learning application, study time, answer results, etc., while the smartwatch records exercise volume and heart rate. In addition, the camera sensor captures facial expression data (concentration, confusion, enjoyment, etc.) in real time and analyzes it using facial recognition technology.

[1031] Input: Children's operation log, study time, answer results, exercise amount, heart rate, facial expression data

[1032] Output: A set of collected behavioral data

[1033] Operation: Data acquisition from sensors and cameras, initial analysis, and local storage

[1034] Step 2:

[1035] Data transmission

[1036] The device locally encrypts the collected data and uploads it to the server at regular intervals. Specifically, the device is scheduled to send encrypted data every night, ensuring the integrity and security of the data.

[1037] Input: Encrypted behavioral data

[1038] Output: Behavioral data sent to the server

[1039] Operation: Data encryption process, uploading encrypted data to server

[1040] Step 3:

[1041] Data reception and storage

[1042] The server receives the behavioral data sent from the device and stores it in a database as a log, allowing the data required for subsequent analysis steps to be managed in a centralized manner.

[1043] Input: Behavioral data sent from the device

[1044] Output: Behavioral data stored in a database

[1045] Action: Writing data to the database

[1046] Step 4:

[1047] Data analysis

[1048] The server inputs the behavioral data stored in the database into a machine learning algorithm to perform analysis. This extracts the child's behavioral patterns and identifies their potential abilities and interests. For example, the server analyzes the child's learning patterns and evaluates their mathematical talent based on their reaction time to math problems, the percentage of correct answers, and facial expression data.

[1049] Input: Behavioral data stored in a database

[1050] Output: Behavioral pattern analysis results

[1051] Action: Input data into machine learning models, analyze behavioral patterns, and extract results

[1052] Step 5:

[1053] Activity Creation

[1054] Based on the analysis results, the server uses a generative AI model to generate customized educational activities. In this process, specific prompts are input into the generative AI model (e.g., GPT-3) to create optimal learning activities. For example, "This child has a high interest in math, so I'd like to suggest some challenging math problems and creative math games."

[1055] Input: behavior pattern analysis results, prompt text

[1056] Output: Customized educational activities

[1057] Operation: Input prompts to the generative AI model, generate educational activities

[1058] Step 6:

[1059] Activity Broadcast

[1060] The generated educational activity is sent from the server to the terminal and provided to the child.

[1061] Input: Generated educational activities

[1062] Output: Educational activities delivered to devices

[1063] Action: Delivering educational activities to devices

[1064] Step 7:

[1065] Activity implementation

[1066] The user (child) performs the provided educational activity, and the device records the results, such as the percentage of correct answers, the time it took to answer, and facial expression data (such as happy or confused).

[1067] Input: Educational activity status

[1068] Output: Implementation result data

[1069] Behavior: Collecting and recording behavioral data

[1070] Step 8:

[1071] Feedback and Adjustments

[1072] The server receives the implementation result data sent from the device again and analyzes it as feedback data. Based on the analysis results, the next educational activity is optimized.

[1073] Input: Implementation result data

[1074] Output: Optimized next teaching activity

[1075] Actions: Analyzing feedback data and optimizing educational activities

[1076] The above is the flow of the program processing of the present invention and the specific operation of each step, which optimizes the learning process for each child and provides effective educational support.

[1077] (Application example 1)

[1078] 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."

[1079] Traditional educational systems have struggled to provide customized educational activities based on each child's individual talents and interests. Furthermore, uniform educational programs fail to capture children's interests and lead to insufficient learning outcomes. Furthermore, educational activities within educational facilities face the challenge of being unable to grasp children's real-time behavior and emotions and instantly customize educational activities based on them.

[1080] 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.

[1081] In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm to analyze the child's behavioral patterns, means for generating customized educational activities based on the analysis results, means for distributing the generated educational activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the educational activities and optimize suggestions for the next time, means for recording the child's gaze, behavior, and voice commands in real time using a smart device, and means for providing a customized interactive experience within the educational facility. This makes it possible to provide customized educational activities based on the child's interests and talents in real time and optimize educational effectiveness.

[1082] "Children's daily behavioral data" refers to data that records various actions and reactions that children perform in their daily lives.

[1083] "Means for recording" refers to devices or systems for electronically storing behavioral data, emotional data, etc.

[1084] "Means for transmitting to a server" refers to a combination of hardware and software for transferring data from a terminal to a server.

[1085] A "machine learning algorithm" is an algorithm that extracts patterns and knowledge from data and uses them to make predictions and classifications.

[1086] "Means of analysis" refers to devices and software that use machine learning algorithms to analyze data and extract meaningful information.

[1087] "Customized educational activities" refer to educational activities that are specifically designed based on the talents and interests of each individual child.

[1088] "Means for delivering to the device" refers to the technology or device used to transfer the generated educational activity to the user's device.

[1089] "Implementation means" refers to the equipment or technology that allows children to actually carry out the delivered educational activity.

[1090] "Means for recording the results of an activity and transmitting them to a server" refers to devices or technologies for saving data after the activity is completed and transmitting that data to a server.

[1091] "Means for evaluating the effectiveness of educational activities and optimizing proposals for the next time" refers to technologies and devices that analyze the results of implementation and use those results to make the next educational activity more effective.

[1092] "Smart devices" refer to portable electronic devices equipped with communication functions and sensors that are capable of collecting data and interacting with users.

[1093] "Means for recording gaze, actions, and voice commands in real time" refers to technologies and devices that instantly collect and store a user's gaze movements, body movements, and voice instructions.

[1094] "Means for providing customized interactive experiences within educational facilities" refers to technologies and devices used in educational facilities to design and provide participatory educational activities based on children's interests and talents.

[1095] This system collects and analyzes data on children's daily activities and provides customized educational activities based on their individual talents and interests. The system mainly consists of a terminal, a server, and a user.

[1096] System Configuration

[1097] 1. Terminal

[1098] The devices used include portable electronic devices such as tablets, smartwatches, smart glasses, and head-mounted displays (HMDs). These devices are equipped with sensors and cameras to record behavioral and emotional data, and use facial recognition and behavioral recognition technologies. For example, smart glasses record eye movements and facial expressions, while smartwatches measure heart rate and exercise volume. This data is collected in real time, and the devices encrypt and send it to a server.

[1099] 2. Server

[1100] The server receives the data sent from the device and analyzes it using a machine learning algorithm (e.g., TensorFlow). The received data is stored in a database (e.g., MySQL). The server analyzes the data and identifies the child's behavioral patterns and areas of interest. Based on the results of this analysis, the server generates customized educational activities and delivers them to the device. In addition, the server reanalyzes the user's feedback data to optimize suggestions for the next educational activity.

[1101] 3. Users

[1102] Users (children and their parents or educators) carry out educational activities provided via the device. The child's activities and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activities and further optimize suggestions for the next time.

[1103] Specific examples

[1104] A concrete example is an interactive experience using smart glasses and HMDs in a science museum's educational facilities. When a child walks around the educational facility and spends a long time in front of a particular exhibit, the smart glasses collect behavioral data and an increase in heart rate. This data is sent to a server and analyzed using machine learning algorithms. If the server determines that the child has a strong interest in the exhibit, it generates a customized interactive experience based on that interest (e.g., additional explanations or related mini-games) and delivers it to the smart glasses.

[1105] For example, a prompt to a generative AI model might look like this:

[1106] "Analyze children's behavior data in the fossil exhibit area and generate customized educational programs about fossils."

[1107] This system makes it possible to provide customized educational activities in real time that are tailored to each child's individual interests and talents, maximizing educational effectiveness.

[1108] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1109] Step 1:

[1110] The device records the child's daily behavior data in real time.

[1111] Specifically, devices such as smart glasses and smart watches use sensors and cameras to collect eye movements, heart rate, voice commands, body movements, and facial expressions.

[1112] Input: Child's gaze data, heart rate data, voice commands, body movement data, facial expression data

[1113] Output: raw recorded data

[1114] Step 2:

[1115] The terminal encrypts the recorded data and transmits it to the server.

[1116] Specifically, data is encrypted using the SSL / TLS protocol and uploaded to a server via Wi-Fi.

[1117] Input: raw recorded data

[1118] Output: Encrypted data

[1119] Step 3:

[1120] The server inputs the received data into a machine learning algorithm to analyze the child's behavioral patterns.

[1121] Specifically, it uses TensorFlow to analyze data and identify children's areas of interest and behavioral patterns.

[1122] Input: Encrypted data

[1123] Output: Analysis results (areas of interest, behavioral patterns)

[1124] Step 4:

[1125] The server generates customized educational activities based on the analysis results.

[1126] Specifically, generative AI models are used to create problem sets, interactive games, projects, and more tailored to specific areas of interest.

[1127] Input: Analysis results

[1128] Output: Customized educational activities

[1129] Step 5:

[1130] The server distributes the generated educational activities to the terminals.

[1131] Specifically, the device receives educational activities, notifies the user appropriately, and provides visual and audio guidance as necessary.

[1132] Input: Customized Educational Activities

[1133] Output: Delivered educational activity

[1134] Step 6:

[1135] The user (child) performs the educational activity that is delivered to them.

[1136] Specifically, they participate in interactive experiences displayed using smart glasses or HMDs and run applications.

[1137] Input: Delivered educational activity

[1138] Output: Activity execution results

[1139] Step 7:

[1140] The terminal records the implementation results and transmits them to the server.

[1141] Specifically, sensors record the results and reactions of each child's activity, and the necessary data is then encrypted and uploaded to the server.

[1142] Input: Activity execution result

[1143] Output: Encrypted execution data

[1144] Step 8:

[1145] The server analyzes the results of the implementation, evaluates the effectiveness of the educational activity, and optimizes the next proposal.

[1146] Specifically, the received data is analyzed and the next educational activity is further customized based on the results.

[1147] Input: Encrypted implementation data

[1148] Output: Next suggested activity

[1149] 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.

[1150] This invention is a system that collects and analyzes children's daily behavior data to provide learning activities customized to their individual talents and interests. In addition, by combining it with an emotion engine, it acquires and analyzes the user's emotion data to provide more accurate educational support. The system consists of a user (child), a terminal, and a server.

[1151] System Configuration

[1152] 1. Terminal

[1153] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[1154] 2. Server

[1155] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[1156] 3. Users

[1157] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[1158] Program processing

[1159] 1. Data Collection

[1160] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[1161] 2. Data Transmission

[1162] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[1163] 3. Data analysis

[1164] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[1165] 4. Activity Generation and Suggestion

[1166] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[1167] 5. Activity Distribution

[1168] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[1169] 6. Activity implementation

[1170] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[1171] 7. Recording of implementation results

[1172] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[1173] 8. Send results

[1174] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[1175] 9. Evaluation and Adjustment

[1176] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[1177] Specific examples

[1178] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[1179] The processing flow will be explained below.

[1180] Step 1:

[1181] Device: Records children's daily behavioral and emotional data. Specifically, the tablet captures learning app operation logs (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data (e.g., concentration, confusion, enjoyment) in real time. The smartwatch collects data such as heart rate, exercise volume, and frequency of use. The emotion engine uses facial recognition and voice analysis technology to detect the user's emotions (e.g., joy, sadness, surprise).

[1182] Step 2:

[1183] Device: The recorded behavioral and emotional data is encrypted and periodically sent to the server. The data is uploaded to the server when the collected data reaches a certain volume or at specified intervals to ensure secure communication.

[1184] Step 3:

[1185] Server: Stores the received data in a database, safely storing and managing the data and preparing it to serve the machine learning algorithms and sentiment engines as needed.

[1186] Step 4:

[1187] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns and emotional data. Specifically, behavioral data such as study time, accuracy rate, and answer time are combined with emotional data analyzed by the emotion engine to identify the child's favorite subjects, areas of interest, and current emotional state.

[1188] Step 5:

[1189] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging calculation problems and math games. It also generates activities with emotional feedback to respond to changes in emotions.

[1190] Step 6:

[1191] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[1192] Step 7:

[1193] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks. Activities with emotional feedback respond to emotional changes during learning.

[1194] Step 8:

[1195] Device: Records the results of the child's learning activities. Specifically, it records the answer time, accuracy rate, changes in emotions and facial expressions, etc., for further analysis. The emotion engine monitors emotional changes during learning in real time.

[1196] Step 9:

[1197] Terminal: The results of the experiment are encrypted and sent to the server. At this time, both behavioral data and emotional data are uploaded to the server.

[1198] Step 10:

[1199] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. Specifically, it evaluates learning outcomes (e.g., improvement in correct answer rate, reduction in answer time) and emotional changes (e.g., increased enjoyment and concentration during learning), and generates feedback based on the analysis results.

[1200] Step 11:

[1201] Server: Optimizes the next learning activity suggestion based on the feedback. Depending on the evaluation, the difficulty and content of the activity are adjusted and reflected in the next learning suggestion. The server updates the next learning activity, realizing cyclical operation of the system.

[1202] In this way, the system of the present invention, which combines an emotion engine, analyzes children's behavioral data and emotion data and provides optimal learning activities for each individual child, thereby providing effective educational support.

[1203] Example 2

[1204] 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."

[1205] Conventional learning support systems have difficulty providing customized learning activities that fully consider each child's individual talents, interests, and emotional state. As a result, there is a problem in that they are unable to provide effective support to increase children's motivation to learn.

[1206] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1207] In this invention, the server includes a means for storing the received data in a database, a means for inputting the stored data into a machine learning algorithm to analyze the child's behavioral patterns, and a means for generating customized learning activities using a generative AI model based on the analysis results, thereby enabling highly accurate educational support that takes into account the individual talents, interests, and emotional states of each child.

[1208] "Children's daily behavioral data" refers to data about the actions and behaviors that children perform during their daily lives and learning activities.

[1209] "Recording means" refers to devices or methods that capture data on a child's daily behavior and store that information.

[1210] "Transmitting means" refers to a device or method for transferring recorded data to a receiving device such as a server.

[1211] "Means for storing received data in a database" refers to a device or method by which the server records and stores data received from a terminal in a database.

[1212] A "machine learning algorithm" is an algorithm that analyzes data and automatically learns patterns and regularities to predict or classify outcomes.

[1213] A "generative AI model" is an artificial intelligence model that processes information like a human and generates answers to new data or problems.

[1214] "Customized learning activities" refer to learning tasks and exercises that are appropriately tailored based on each child's abilities, interests, and emotions.

[1215] "Means for distribution" refers to a device or method for transmitting the learning activity generated by the server to the terminal and providing it to the child.

[1216] "Means for recording results" refers to a device or method for saving the results of a child's learning activities.

[1217] "Means for analyzing implementation results" refers to devices or methods for analyzing data on children's learning activities and identifying their effectiveness and areas for improvement.

[1218] "Facial recognition technology" refers to technology that uses a camera or sensor to detect a person's face and identify their individual facial expressions and features.

[1219] "Voice analysis technology" refers to technology that uses a microphone or audio receiving device to analyze audio signals and identify their content and characteristics.

[1220] "Concentration" refers to an indicator of a child's attention and dedication to a given task or activity.

[1221] A "prompt" refers to the instructions or input text that a generative AI model uses to generate new data or answers.

[1222] This invention relates to a system that collects and analyzes children's daily behavioral data to provide customized learning activities based on their individual talents and interests. By combining it with an emotion engine, it acquires and analyzes the user's emotional data to provide more accurate educational support.

[1223] System Configuration

[1224] 1. Terminal

[1225] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the ability to detect emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[1226] 2. Server

[1227] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[1228] 3. Users

[1229] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[1230] Program processing

[1231] The specific operation of the system is explained below. The system mainly functions through the following processes: data collection, data transmission, data storage, data analysis, activity generation, activity distribution, activity implementation, recording of implementation results, result transmission, evaluation and adjustment.

[1232] 1. Data Collection

[1233] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[1234] 2. Data Transmission

[1235] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[1236] 3. Data storage

[1237] Server: The server stores the received data in a database, adds new entries to the database, and checks the integrity of the data.

[1238] 4. Data Analysis

[1239] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[1240] 5. Activity Generation and Suggestion

[1241] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[1242] 6. Activity Distribution

[1243] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[1244] 7. Activity implementation

[1245] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[1246] 8. Recording of implementation results

[1247] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[1248] 9. Send results

[1249] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[1250] 10. Evaluation and Adjustment

[1251] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[1252] Specific examples

[1253] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[1254] Prompt Sentence Examples

[1255] "Please suggest the best learning activities for children who are interested in mathematics and who enjoy engaging in them with a smile."

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] Specific processing steps of the program

[1258] Step 1: Data collection

[1259] Devices: Records real-time activity logs, behavioral data, and emotional data as children engage in learning activities. Devices used include tablets and smartwatches.

[1260] Input: Operation information of the learning app, facial expression images from the camera, audio data from the microphone, and biometric information from the smartwatch.

[1261] Data processing: Facial recognition technology is used to analyze facial expressions and detect emotions such as "concentration," "confusion," and "happiness." Voice analysis technology is used to determine emotions from the tone of voice.

[1262] Output: Behavioral data integrating learning operation logs, facial expression data, voice data, and biometric data.

[1263] Step 2: Send data

[1264] Terminal: The recorded data is encrypted and periodically sent to the server.

[1265] Input: Integrated behavioral data.

[1266] Data processing: Encrypting data and sending it through a secure communication channel.

[1267] Output: Encrypted behavioral data.

[1268] Step 3: Save data

[1269] Server: Stores the received data in a database.

[1270] Input: Encrypted behavioral data.

[1271] Data processing: Decrypt the data and store it in the database in the appropriate format.

[1272] Output: Behavioral data stored in a database.

[1273] Step 4: Data analysis

[1274] Server: Analyzes the received data using machine learning algorithms and an emotion engine.

[1275] Input: Behavioral and emotional data from the database.

[1276] Data processing: Using machine learning algorithms to analyze behavioral patterns and identify areas of expertise and interest. Using an emotion engine to analyze emotional fluctuations.

[1277] Output: Analysis results (child's strengths, interests, emotional state).

[1278] Step 5: Activity generation and proposal

[1279] Server: Based on the analysis results, a generative AI model is used to generate customized learning activities.

[1280] Input: Analysis results (areas of expertise, areas of interest, emotional state).

[1281] Data processing: Use a generative AI model to create learning activities suitable for children. Enter the prompt "Suggest the best learning activities for a child who is interested in math and smiles when they engage in it."

[1282] Output: A customized learning activity.

[1283] Step 6: Activity Delivery

[1284] Server: Delivers the generated learning activities to the devices.

[1285] Input: The generated learning activity.

[1286] Data processing: Encrypting activity in a proper format and sending it to your child's device.

[1287] Output: Encrypted learning activity.

[1288] Step 7: Implement the activity

[1289] User (child): Carries out learning activities provided on the device.

[1290] Input: Delivered learning activity.

[1291] Data processing: Conduct the activity and record the answer time, correct answer rate, and emotional state.

[1292] Output: Learning activity outcome data.

[1293] Step 8: Record your results

[1294] Device: Records the results of the learning activities your child performs.

[1295] Input: Learning activity outcome data.

[1296] Data processing: Integrate the outcome data and prepare for the next analysis.

[1297] Output: Consolidated outcome data.

[1298] Step 9: Send results

[1299] Terminal: The recorded performance data is encrypted and sent to the server.

[1300] Input: Integrated outcome data.

[1301] Data processing: The results data will be encrypted and sent.

[1302] Output: Encrypted outcome data.

[1303] Step 10: Evaluate and adjust

[1304] Server: Analyzes the collected implementation results, evaluates the effectiveness of the activity, and optimizes proposals for the next time.

[1305] Input: Outcome data from the database.

[1306] Data processing: Evaluate learning outcomes and emotional fluctuations, and generate feedback to optimize the next learning activity.

[1307] Output: Feedback of optimized learning activities.

[1308] As described above, detailed data processing and calculations are carried out at each step of this system, enabling optimal learning activities to be provided for children.

[1309] (Application example 2)

[1310] 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."

[1311] Conventional educational systems have struggled to provide customized learning activities tailored to individual children's interests and talents. They also lack the ability to grasp changes in children's emotions and interests in real time and provide appropriate feedback accordingly. Furthermore, it has been difficult to integrate users' purchasing behavior and emotional data in virtual stores to provide personalized product recommendations.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm and analyzing the child's behavioral patterns, means for generating customized learning activities based on the analysis results, means for distributing the generated learning activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting the results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the activities and optimizing the next suggestions, and means for recording the child's purchasing behavior data and emotional data and making product suggestions based on the results. This makes it possible to provide educational support tailored to each child's talents and interests, and to analyze emotions in real time in virtual stores and make optimal product suggestions.

[1313] "Children's daily behavioral data" refers to data such as study time, answer time, correct answer rate, heart rate, and amount of exercise recorded when using electronic devices such as tablets and smartwatches.

[1314] "Means for transmitting to a server" refers to a communication means by which the terminal encrypts data collected in real time or at specified time intervals and securely uploads it to a server.

[1315] "Means for inputting into machine learning algorithms to analyze children's behavioral patterns" refers to analytical means, including classifiers and regression models, that use the collected data to identify children's behavioral characteristics and patterns.

[1316] The "means for generating customized learning activities" refers to a means for creating learning tasks and exercises that are tailored to the individual talents and interests of each child based on the analysis results.

[1317] The "means for delivering learning activities to devices" refers to a communication means for encrypting the generated learning assignments and sending them to devices such as tablets and smartwatches used by children.

[1318] The "means for children to carry out the distributed activities" refers to the means for providing learning activities for children to carry out through a terminal and recording the results.

[1319] The "means for recording the results of the learning and sending them to the server" refers to a means for recording the results and reactions of the learning activities performed by the child and periodically sending them to the server.

[1320] "Means for analyzing implementation results, evaluating the effectiveness of the activity, and optimizing the next proposal" refers to means for analyzing collected implementation result data, evaluating the effectiveness of the learning activity, and optimizing the content of the next learning activity based on the evaluation results.

[1321] "Children's purchasing behavior data" is data including a user's operation log, browsing time, number of clicks, etc. in a virtual store.

[1322] "Emotion data" refers to data related to emotions extracted from the user's facial expressions and voice obtained using voice analysis and face recognition technology.

[1323] The "means for making product suggestions" is a means for recommending optimal products to users based on the analyzed purchasing behavior data and emotional data.

[1324] The present invention is a system that collects and analyzes purchasing behavior data and emotional data of individual users in a virtual store to make optimal product recommendations. This system is composed of users, terminals, and a server.

[1325] System Configuration

[1326] 1. Terminal

[1327] The devices used are portable electronic devices such as smartphones and smart glasses. These devices are equipped with sensors and cameras to record purchasing behavior data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The smartphone records the operation log and browsing time of the purchasing app, while the smart glasses track eye movements and collect facial expression data.

[1328] 2. Server

[1329] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model for analysis. The server analyzes purchasing behavior patterns and emotion data to identify individual users' interests, preferences, and current emotional state. Based on the analysis results, it generates customized product suggestions and sends them to the device.

[1330] 3. Users

[1331] The user receives product suggestions provided via the device. The user's shopping behavior and reactions in the virtual store are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the product suggestions and optimize the next suggestions.

[1332] Explanation of specific measures

[1333] 1. Data Collection

[1334] The device records activity logs and emotional data in real time as the user uses it. For example, a smartphone captures the operation log of a virtual store app (browsing time, number of clicks) and obtains facial expression data (excitement, joy, confusion, etc.) using an emotion engine. Smart glasses collect eye-tracking data and changes in facial expressions.

[1335] 2. Data Transmission

[1336] The device encrypts the recorded data and periodically sends it to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[1337] 3. Data analysis

[1338] The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it identifies the user's interests and preferences using methods such as classifiers and regression analysis based on a purchasing behavior dataset, and analyzes their emotional state (e.g., excitement, joy, confusion) based on an emotion dataset.

[1339] 4. Product proposal generation and distribution

[1340] The server generates customized product suggestions based on the analysis results. For example, for a user who shows a strong interest in a particular product and tends to purchase it with joy, related products and accessories will be recommended. The emotion engine also responds to emotional changes during shopping. The generated product suggestions are encrypted in an appropriate format and sent to the user's device.

[1341] Program processing

[1342] The server runs the programs described above for data collection, data transmission, data analysis, and product proposal generation and distribution. The main hardware used is a multi-function server, an internet connection, and the user's smartphone or smart glasses. The software uses OpenCV for face recognition technology, Keras for emotion recognition models, and the Requests library for data transmission.

[1343] Specific examples

[1344] For example, imagine a user in a market is browsing a virtual store using smart glasses. The glasses record eye-tracking data and facial expression data (surprise, joy, confusion, etc.). The emotion engine recognizes the user's joy from a smile and sends the data to the server. An AI model on the server analyzes the data and finds that the user is highly interested in a new product. Based on this information, the server can suggest related new product lines and discount offers. A specific prompt might be, "It seems you're interested in our new products. How about these accessories?"

[1345] As described above, the present invention provides a system that analyzes user purchasing behavior and emotional data in real time and makes optimal product suggestions to individual users.

[1346] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1347] Step 1:

[1348] When a user uses the virtual store app, the device records purchasing behavior data (operation log, browsing time, number of clicks) and emotional data (facial expression data, eye tracking data) in real time.Specifically, it uses a camera, microphone, and touch sensor to capture the user's facial expressions, voice, and operation status.

[1349] Input: User operation log, facial expression data, gaze data

[1350] Output: Recorded data

[1351] Step 2:

[1352] The device sends the recorded data to a server. The data is encrypted and periodically uploaded to the server using a secure communication protocol (e.g., HTTPS). The data is sent at specified time intervals when it reaches a certain volume.

[1353] Input: Recorded data

[1354] Output: Encrypted data

[1355] Step 3:

[1356] The server stores the received data in a database, where it is kept in an organized format for use in analysis.

[1357] Input: Encrypted data

[1358] Output: Data stored in the database

[1359] Step 4:

[1360] The server inputs the stored data into machine learning algorithms and emotion engines to analyze the user's purchasing behavior patterns and emotions. For example, it uses classifiers and regression analysis based on behavioral data to identify the user's interests and preferences, and inputs emotion data (facial expressions, voice, etc.) into emotion recognition models to identify the user's emotional state.

[1361] Input: Saved data

[1362] Output: Analysis results (purchase behavior patterns, emotional state)

[1363] Step 5:

[1364] The server generates customized product recommendations based on the analysis results, using the generative AI model to create prompts and suggest the best products and related accessories for the user.

[1365] Input: Analysis results

[1366] Output: Product proposal

[1367] Step 6:

[1368] The server delivers the generated product proposals to the terminal. The product proposals are encrypted and sent to the user's terminal, allowing the user to receive the proposals in real time.

[1369] Input: Product proposal

[1370] Output: Encrypted proposal data

[1371] Step 7:

[1372] The user receives the product suggestions provided to the terminal and performs shopping in the virtual store. Specifically, the user browses products according to the product suggestions and considers purchasing them.

[1373] Input: Encrypted proposal data

[1374] Output: User behavior data

[1375] Step 8:

[1376] The device then records the user's new purchasing behavior and emotional data and sends it to the server, which then repeats the process and optimizes the recommendations.

[1377] Input: User behavior data, emotion data

[1378] Output: Recorded data

[1379] The above are the specific processing steps for carrying out the invention.

[1380] 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.

[1381] 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.

[1382] 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.

[1383] [Fourth embodiment]

[1384] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1385] 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.

[1386] 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).

[1387] 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.

[1388] 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.

[1389] 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).

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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."

[1397] This system collects data on children's daily activities, analyzes their individual talents and interests, and provides customized educational activities based on the collected data. This system is primarily composed of users (children), terminals, and a server.

[1398] System Configuration

[1399] 1. Terminal

[1400] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions, and use facial recognition and behavioral recognition technology to record children's daily actions and reactions. For example, tablets record operation logs and study time when children use learning apps, while smartwatches collect data including exercise volume and heart rate.

[1401] 2. Server

[1402] The server receives data sent from the device and analyzes it using a machine learning algorithm. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns to identify each child's potential abilities and interests. Based on the results of this analysis, it generates customized learning activities and materials and sends them to the device.

[1403] 3. Users

[1404] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[1405] Program processing

[1406] 1. Data Collection

[1407] When a child uses the device, it records activity logs, behavioral data, facial expression data, etc. in real time. It also uses facial recognition technology to capture the child's emotions and concentration, which are also collected as data.

[1408] 2. Data Transmission

[1409] The device encrypts the collected data and periodically uploads it to a server, ensuring data integrity and security.

[1410] 3. Data analysis

[1411] The server inputs the received data into a machine learning model to analyze the child's behavioral patterns. For example, if the child shows a high interest in math calculation problems, it is assumed that the child has mathematical talent.

[1412] 4. Activity Generation and Suggestion

[1413] Based on the analysis results, the server generates customized learning activities, including exercises, games, and projects tailored to the child's interests and strengths, which are then sent to the device and presented to the child.

[1414] 5. Feedback and Adjustments

[1415] The user (child) performs the provided activity, and their results and reactions are recorded on the device again. The recorded data is sent to the server and analyzed. Based on the results, the next learning suggestion is further optimized.

[1416] Specific examples

[1417] For example, suppose a child is using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions (concentration, confusion, enjoyment, etc.) while using the app. This data is sent to a server, where a machine learning model analyzes it and determines that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games and provides them to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[1418] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[1419] The processing flow will be explained below.

[1420] Step 1:

[1421] Devices: Record data on children's daily activities. Specifically, the tablet captures the operation log of the learning app (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data while using the app (e.g., focused, confused, enjoying). The smartwatch records data such as heart rate, exercise volume, and frequency of use.

[1422] Step 2:

[1423] Terminal: The recorded data is encrypted and periodically sent to the server. For example, when the collected data reaches a certain volume or at a specified time interval, the data is uploaded to the server. This ensures the integrity and security of the data.

[1424] Step 3:

[1425] Server: Stores the received data in a database, safely storing and managing the data and preparing it to be fed to machine learning algorithms as needed.

[1426] Step 4:

[1427] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns. Specifically, based on the dataset, methods such as classifiers and regression analysis are used to identify the child's strengths, areas of interest, and learning approaches.

[1428] Step 5:

[1429] Server: Based on the analysis, it generates customized learning activities. For example, for a child who shows an interest in math, it creates challenging math problems or math games. For a child interested in creative expression, it generates art projects or design assignments.

[1430] Step 6:

[1431] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[1432] Step 7:

[1433] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[1434] Step 8:

[1435] Device: Records the results of the learning activities the child has performed. Specifically, it records the answer time, correct answer rate, changes in emotions and facial expressions, etc., for further analysis.

[1436] Step 9:

[1437] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[1438] Step 10:

[1439] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity, such as the degree of improvement in learning outcomes, changes in the rate of correct answers to math problems, and changes in children's concentration and emotions.

[1440] Step 11:

[1441] Server: Generates feedback based on the analysis results and optimizes the next learning activity suggestion. Depending on the evaluation, adjusts the difficulty and content of the activity and prepares for the next cycle. The server updates the next learning activity and returns to step 1.

[1442] Through the above processing steps, the present invention brings out the potential and talents of children and realizes efficient and effective individualized education.

[1443] Example 1

[1444] 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."

[1445] Conventional educational support systems have struggled to efficiently analyze each child's talents and interests and provide customized educational activities based on those insights. Furthermore, they lacked the technology to create an effective feedback loop while ensuring the security and consistency of collected data. This made it difficult to maximize each child's learning efficiency.

[1446] 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.

[1447] In this invention, the server includes means for inputting received data into a machine learning algorithm and analyzing behavioral patterns, means for generating customized educational activities based on the analysis results using machine learning, and means for analyzing the implementation results, evaluating the effectiveness of the educational activities, and optimizing suggestions for the next time. This makes it possible to efficiently analyze the talents and interests of individual children and provide customized educational activities based on them.

[1448] "Children's daily behavioral data" refers to data related to the behavior of children in their daily lives and educational activities, and includes operation logs of learning applications, answer results, amount of exercise, heart rate, facial expressions, etc.

[1449] The "database" is an information management system that centrally stores received behavioral data and allows searching and analysis as needed.

[1450] "Encryption" is a technology that prevents transmitted data from being deciphered by third parties, and is a means of ensuring data security.

[1451] "Server" means a computer system that receives and stores data sent from a device, analyzes it, and generates activity data.

[1452] A "machine learning algorithm" is a collection of mathematical methods and programs that learn patterns and characteristics from data and make predictions and classifications.

[1453] "Behavioral pattern analysis" is the process of identifying patterns in a child's behavior and reactions based on collected behavioral data, revealing their potential abilities and interests.

[1454] "Customized educational activities" are learning activities and materials specially designed based on a child's characteristics and interests, with the aim of enhancing learning efficiency.

[1455] "Delivery of educational activities" is the process of sending the generated customized learning activities and materials to the device and making them available to the child.

[1456] "Recording implementation results" refers to storing the results and reactions of children when they perform educational activities on the device, which is used to optimize suggestions for the next time.

[1457] "Analysis of feedback data" is a data analysis process to evaluate the effectiveness of educational activities based on the results of implementation and improve the content of proposals for the next time.

[1458] "Facial recognition technology" is a technology that uses sensors and cameras to automatically identify an individual's face and analyze their facial expressions and emotions.

[1459] "Recording concentration and reaction" refers to recording changes in attention and emotions while a child is engaged in educational activities, based on facial expression data obtained using facial recognition technology.

[1460] The present invention is a system that collects data on children's daily behavior, analyzes their individual talents and interests, and provides customized educational activities based on that data. It is composed of users (children), parents, terminals, and a server.

[1461] Terminal

[1462] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. Facial recognition and behavioral recognition technologies are used to record children's daily actions and reactions. For example, the tablet records the operation log and study time when a child uses a learning app, while the smartwatch collects exercise volume and heart rate data.

[1463] The device locally encrypts the collected data and uploads it to the server at regular intervals. This encryption ensures the integrity and security of the data. Specifically, the device is set to send data to the server every night.

[1464] server

[1465] The server receives the data sent from the device and stores it in a database. Based on this stored data, it uses machine learning algorithms to analyze behavioral patterns. Specifically, the server analyzes the received behavioral data to identify each child's potential abilities and interests. For example, a child who shows a high interest in math calculation problems is deemed to have mathematical talent.

[1466] A machine learning algorithm is used to generate customized educational activities based on the analysis results. For example, a generative AI model (e.g., GPT-3) is used to generate optimal learning activities by inputting the following prompt sentence:

[1467] Prompt Sentence Examples

[1468] "Based on the following data, please suggest the best math learning activity for this child:

[1469] Answer time: Average answer time for each question is 30 seconds

[1470] Correct answer rate: 95%

[1471] Facial expressions: Concentration (70%), Confusion (20%), Happiness (10%)

[1472] Suggest new math activities that will interest your child."

[1473] Delivery and implementation of educational activities

[1474] The generated educational activity is sent to the device and provided to the child. The user (child) performs the provided educational activity. The device again records the results and reactions during this activity. For example, it acquires and records the percentage of correct answers, the time it takes to answer, and facial expression data (enjoyed, confused, etc.).

[1475] Feedback and Optimization

[1476] The recorded data on the results is then sent back to the server, which uses this new data to provide feedback and evaluate the effectiveness of the educational activity. The next suggestion is then further optimized based on this feedback.

[1477] As a concrete example, consider a child using a math learning app on a tablet. The tablet records the child's response time, accuracy rate, and facial expressions while using the app. This data is sent to a server and analyzed by a machine learning model. The analysis reveals that the child has a high level of interest and ability in mathematical problems. The server then generates more challenging math problems and creative math games, which it then provides to the device as the next learning activity. By implementing this activity and providing feedback on the results, the accuracy and effectiveness of the suggestions are improved over time.

[1478] In this way, the present invention realizes an innovative system that draws out the talents and interests of each child and provides efficient and effective educational support.

[1479] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1480] Program processing flow

[1481] Step 1:

[1482] Data collection

[1483] The devices (tablets and smartwatches) collect behavioral data through the user's (child's) activities. Specifically, the tablets record the operation log of the learning application, study time, answer results, etc., while the smartwatch records exercise volume and heart rate. In addition, the camera sensor captures facial expression data (concentration, confusion, enjoyment, etc.) in real time and analyzes it using facial recognition technology.

[1484] Input: Children's operation log, study time, answer results, exercise amount, heart rate, facial expression data

[1485] Output: A set of collected behavioral data

[1486] Operation: Data acquisition from sensors and cameras, initial analysis, and local storage

[1487] Step 2:

[1488] Data transmission

[1489] The device locally encrypts the collected data and uploads it to the server at regular intervals. Specifically, the device is scheduled to send encrypted data every night, ensuring the integrity and security of the data.

[1490] Input: Encrypted behavioral data

[1491] Output: Behavioral data sent to the server

[1492] Operation: Data encryption process, uploading encrypted data to server

[1493] Step 3:

[1494] Data reception and storage

[1495] The server receives the behavioral data sent from the device and stores it in a database as a log, allowing the data required for subsequent analysis steps to be managed in a centralized manner.

[1496] Input: Behavioral data sent from the device

[1497] Output: Behavioral data stored in a database

[1498] Action: Writing data to the database

[1499] Step 4:

[1500] Data analysis

[1501] The server inputs the behavioral data stored in the database into a machine learning algorithm to perform analysis. This extracts the child's behavioral patterns and identifies their potential abilities and interests. For example, the server analyzes the child's learning patterns and evaluates their mathematical talent based on their reaction time to math problems, the percentage of correct answers, and facial expression data.

[1502] Input: Behavioral data stored in a database

[1503] Output: Behavioral pattern analysis results

[1504] Action: Input data into machine learning models, analyze behavioral patterns, and extract results

[1505] Step 5:

[1506] Activity Creation

[1507] Based on the analysis results, the server uses a generative AI model to generate customized educational activities. In this process, specific prompts are input into the generative AI model (e.g., GPT-3) to create optimal learning activities. For example, "This child has a high interest in math, so I'd like to suggest some challenging math problems and creative math games."

[1508] Input: behavior pattern analysis results, prompt text

[1509] Output: Customized educational activities

[1510] Operation: Input prompts to the generative AI model, generate educational activities

[1511] Step 6:

[1512] Activity Broadcast

[1513] The generated educational activity is sent from the server to the terminal and provided to the child.

[1514] Input: Generated educational activities

[1515] Output: Educational activities delivered to devices

[1516] Action: Delivering educational activities to devices

[1517] Step 7:

[1518] Activity implementation

[1519] The user (child) performs the provided educational activity, and the device records the results, such as the percentage of correct answers, the time it took to answer, and facial expression data (such as happy or confused).

[1520] Input: Educational activity status

[1521] Output: Implementation result data

[1522] Behavior: Collecting and recording behavioral data

[1523] Step 8:

[1524] Feedback and Adjustments

[1525] The server receives the implementation result data sent from the device again and analyzes it as feedback data. Based on the analysis results, the next educational activity is optimized.

[1526] Input: Implementation result data

[1527] Output: Optimized next teaching activity

[1528] Actions: Analyzing feedback data and optimizing educational activities

[1529] The above is the flow of the program processing of the present invention and the specific operation of each step, which optimizes the learning process for each child and provides effective educational support.

[1530] (Application example 1)

[1531] 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."

[1532] Traditional educational systems have struggled to provide customized educational activities based on each child's individual talents and interests. Furthermore, uniform educational programs fail to capture children's interests and lead to insufficient learning outcomes. Furthermore, educational activities within educational facilities face the challenge of being unable to grasp children's real-time behavior and emotions and instantly customize educational activities based on them.

[1533] 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.

[1534] In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm to analyze the child's behavioral patterns, means for generating customized educational activities based on the analysis results, means for distributing the generated educational activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the educational activities and optimize suggestions for the next time, means for recording the child's gaze, behavior, and voice commands in real time using a smart device, and means for providing a customized interactive experience within the educational facility. This makes it possible to provide customized educational activities based on the child's interests and talents in real time and optimize educational effectiveness.

[1535] "Children's daily behavioral data" refers to data that records various actions and reactions that children perform in their daily lives.

[1536] "Means for recording" refers to devices or systems for electronically storing behavioral data, emotional data, etc.

[1537] "Means for transmitting to a server" refers to a combination of hardware and software for transferring data from a terminal to a server.

[1538] A "machine learning algorithm" is an algorithm that extracts patterns and knowledge from data and uses them to make predictions and classifications.

[1539] "Means of analysis" refers to devices and software that use machine learning algorithms to analyze data and extract meaningful information.

[1540] "Customized educational activities" refer to educational activities that are specifically designed based on the talents and interests of each individual child.

[1541] "Means for delivering to the device" refers to the technology or device used to transfer the generated educational activity to the user's device.

[1542] "Implementation means" refers to the equipment or technology that allows children to actually carry out the delivered educational activity.

[1543] "Means for recording the results of an activity and transmitting them to a server" refers to devices or technologies for saving data after the activity is completed and transmitting that data to a server.

[1544] "Means for evaluating the effectiveness of educational activities and optimizing proposals for the next time" refers to technologies and devices that analyze the results of implementation and use those results to make the next educational activity more effective.

[1545] "Smart devices" refer to portable electronic devices equipped with communication functions and sensors that are capable of collecting data and interacting with users.

[1546] "Means for recording gaze, actions, and voice commands in real time" refers to technologies and devices that instantly collect and store a user's gaze movements, body movements, and voice instructions.

[1547] "Means for providing customized interactive experiences within educational facilities" refers to technologies and devices used in educational facilities to design and provide participatory educational activities based on children's interests and talents.

[1548] This system collects and analyzes data on children's daily activities and provides customized educational activities based on their individual talents and interests. The system mainly consists of a terminal, a server, and a user.

[1549] System Configuration

[1550] 1. Terminal

[1551] The devices used include portable electronic devices such as tablets, smartwatches, smart glasses, and head-mounted displays (HMDs). These devices are equipped with sensors and cameras to record behavioral and emotional data, and use facial recognition and behavioral recognition technologies. For example, smart glasses record eye movements and facial expressions, while smartwatches measure heart rate and exercise volume. This data is collected in real time, and the devices encrypt and send it to a server.

[1552] 2. Server

[1553] The server receives the data sent from the device and analyzes it using a machine learning algorithm (e.g., TensorFlow). The received data is stored in a database (e.g., MySQL). The server analyzes the data and identifies the child's behavioral patterns and areas of interest. Based on the results of this analysis, the server generates customized educational activities and delivers them to the device. In addition, the server reanalyzes the user's feedback data to optimize suggestions for the next educational activity.

[1554] 3. Users

[1555] Users (children and their parents or educators) carry out educational activities provided via the device. The child's activities and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activities and further optimize suggestions for the next time.

[1556] Specific examples

[1557] A concrete example is an interactive experience using smart glasses and HMDs in a science museum's educational facilities. When a child walks around the educational facility and spends a long time in front of a particular exhibit, the smart glasses collect behavioral data and an increase in heart rate. This data is sent to a server and analyzed using machine learning algorithms. If the server determines that the child has a strong interest in the exhibit, it generates a customized interactive experience based on that interest (e.g., additional explanations or related mini-games) and delivers it to the smart glasses.

[1558] For example, a prompt to a generative AI model might look like this:

[1559] "Analyze children's behavior data in the fossil exhibit area and generate customized educational programs about fossils."

[1560] This system makes it possible to provide customized educational activities in real time that are tailored to each child's individual interests and talents, maximizing educational effectiveness.

[1561] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1562] Step 1:

[1563] The device records the child's daily behavior data in real time.

[1564] Specifically, devices such as smart glasses and smart watches use sensors and cameras to collect eye movements, heart rate, voice commands, body movements, and facial expressions.

[1565] Input: Child's gaze data, heart rate data, voice commands, body movement data, facial expression data

[1566] Output: raw recorded data

[1567] Step 2:

[1568] The terminal encrypts the recorded data and transmits it to the server.

[1569] Specifically, data is encrypted using the SSL / TLS protocol and uploaded to a server via Wi-Fi.

[1570] Input: raw recorded data

[1571] Output: Encrypted data

[1572] Step 3:

[1573] The server inputs the received data into a machine learning algorithm to analyze the child's behavioral patterns.

[1574] Specifically, it uses TensorFlow to analyze data and identify children's areas of interest and behavioral patterns.

[1575] Input: Encrypted data

[1576] Output: Analysis results (areas of interest, behavioral patterns)

[1577] Step 4:

[1578] The server generates customized educational activities based on the analysis results.

[1579] Specifically, generative AI models are used to create problem sets, interactive games, projects, and more tailored to specific areas of interest.

[1580] Input: Analysis results

[1581] Output: Customized educational activities

[1582] Step 5:

[1583] The server distributes the generated educational activities to the terminals.

[1584] Specifically, the device receives educational activities, notifies the user appropriately, and provides visual and audio guidance as necessary.

[1585] Input: Customized Educational Activities

[1586] Output: Delivered educational activity

[1587] Step 6:

[1588] The user (child) performs the educational activity that is delivered to them.

[1589] Specifically, they participate in interactive experiences displayed using smart glasses or HMDs and run applications.

[1590] Input: Delivered educational activity

[1591] Output: Activity execution results

[1592] Step 7:

[1593] The terminal records the implementation results and transmits them to the server.

[1594] Specifically, sensors record the results and reactions of each child's activity, and the necessary data is then encrypted and uploaded to the server.

[1595] Input: Activity execution result

[1596] Output: Encrypted execution data

[1597] Step 8:

[1598] The server analyzes the results of the implementation, evaluates the effectiveness of the educational activity, and optimizes the next proposal.

[1599] Specifically, the received data is analyzed and the next educational activity is further customized based on the results.

[1600] Input: Encrypted implementation data

[1601] Output: Next suggested activity

[1602] 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.

[1603] This invention is a system that collects and analyzes children's daily behavior data to provide learning activities customized to their individual talents and interests. In addition, by combining it with an emotion engine, it acquires and analyzes the user's emotion data to provide more accurate educational support. The system consists of a user (child), a terminal, and a server.

[1604] System Configuration

[1605] 1. Terminal

[1606] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[1607] 2. Server

[1608] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[1609] 3. Users

[1610] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[1611] Program processing

[1612] 1. Data Collection

[1613] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[1614] 2. Data Transmission

[1615] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[1616] 3. Data analysis

[1617] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[1618] 4. Activity Generation and Suggestion

[1619] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[1620] 5. Activity Distribution

[1621] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[1622] 6. Activity implementation

[1623] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[1624] 7. Recording of implementation results

[1625] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[1626] 8. Send results

[1627] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[1628] 9. Evaluation and Adjustment

[1629] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[1630] Specific examples

[1631] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[1632] The processing flow will be explained below.

[1633] Step 1:

[1634] Device: Records children's daily behavioral and emotional data. Specifically, the tablet captures learning app operation logs (e.g., study time, answer time, number of correct / incorrect answers) and facial expression data (e.g., concentration, confusion, enjoyment) in real time. The smartwatch collects data such as heart rate, exercise volume, and frequency of use. The emotion engine uses facial recognition and voice analysis technology to detect the user's emotions (e.g., joy, sadness, surprise).

[1635] Step 2:

[1636] Device: The recorded behavioral and emotional data is encrypted and periodically sent to the server. The data is uploaded to the server when the collected data reaches a certain volume or at specified intervals to ensure secure communication.

[1637] Step 3:

[1638] Server: Stores the received data in a database, safely storing and managing the data and preparing it to serve the machine learning algorithms and sentiment engines as needed.

[1639] Step 4:

[1640] Server: The stored data is input into a machine learning algorithm to analyze the child's behavioral patterns and emotional data. Specifically, behavioral data such as study time, accuracy rate, and answer time are combined with emotional data analyzed by the emotion engine to identify the child's favorite subjects, areas of interest, and current emotional state.

[1641] Step 5:

[1642] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging calculation problems and math games. It also generates activities with emotional feedback to respond to changes in emotions.

[1643] Step 6:

[1644] Server: Delivers the generated customized learning activities to the device. Encrypts the activities in the appropriate format and sends them to the child's device.

[1645] Step 7:

[1646] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks. Activities with emotional feedback respond to emotional changes during learning.

[1647] Step 8:

[1648] Device: Records the results of the child's learning activities. Specifically, it records the answer time, accuracy rate, changes in emotions and facial expressions, etc., for further analysis. The emotion engine monitors emotional changes during learning in real time.

[1649] Step 9:

[1650] Terminal: The results of the experiment are encrypted and sent to the server. At this time, both behavioral data and emotional data are uploaded to the server.

[1651] Step 10:

[1652] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. Specifically, it evaluates learning outcomes (e.g., improvement in correct answer rate, reduction in answer time) and emotional changes (e.g., increased enjoyment and concentration during learning), and generates feedback based on the analysis results.

[1653] Step 11:

[1654] Server: Optimizes the next learning activity suggestion based on the feedback. Depending on the evaluation, the difficulty and content of the activity are adjusted and reflected in the next learning suggestion. The server updates the next learning activity, realizing cyclical operation of the system.

[1655] In this way, the system of the present invention, which combines an emotion engine, analyzes children's behavioral data and emotion data and provides optimal learning activities for each individual child, thereby providing effective educational support.

[1656] Example 2

[1657] 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."

[1658] Conventional learning support systems have difficulty providing customized learning activities that fully consider each child's individual talents, interests, and emotional state. As a result, there is a problem in that they are unable to provide effective support to increase children's motivation to learn.

[1659] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1660] In this invention, the server includes a means for storing the received data in a database, a means for inputting the stored data into a machine learning algorithm to analyze the child's behavioral patterns, and a means for generating customized learning activities using a generative AI model based on the analysis results, thereby enabling highly accurate educational support that takes into account the individual talents, interests, and emotional states of each child.

[1661] "Children's daily behavioral data" refers to data about the actions and behaviors that children perform during their daily lives and learning activities.

[1662] "Recording means" refers to devices or methods that capture data on a child's daily behavior and store that information.

[1663] "Transmitting means" refers to a device or method for transferring recorded data to a receiving device such as a server.

[1664] "Means for storing received data in a database" refers to a device or method by which the server records and stores data received from a terminal in a database.

[1665] A "machine learning algorithm" is an algorithm that analyzes data and automatically learns patterns and regularities to predict or classify outcomes.

[1666] A "generative AI model" is an artificial intelligence model that processes information like a human and generates answers to new data or problems.

[1667] "Customized learning activities" refer to learning tasks and exercises that are appropriately tailored based on each child's abilities, interests, and emotions.

[1668] "Means for distribution" refers to a device or method for transmitting the learning activity generated by the server to the terminal and providing it to the child.

[1669] "Means for recording results" refers to a device or method for saving the results of a child's learning activities.

[1670] "Means for analyzing implementation results" refers to devices or methods for analyzing data on children's learning activities and identifying their effectiveness and areas for improvement.

[1671] "Facial recognition technology" refers to technology that uses a camera or sensor to detect a person's face and identify their individual facial expressions and features.

[1672] "Voice analysis technology" refers to technology that uses a microphone or audio receiving device to analyze audio signals and identify their content and characteristics.

[1673] "Concentration" refers to an indicator of a child's attention and dedication to a given task or activity.

[1674] A "prompt" refers to the instructions or input text that a generative AI model uses to generate new data or answers.

[1675] This invention relates to a system that collects and analyzes children's daily behavioral data to provide customized learning activities based on their individual talents and interests. By combining it with an emotion engine, it acquires and analyzes the user's emotional data to provide more accurate educational support.

[1676] System Configuration

[1677] 1. Terminal

[1678] The devices used are portable electronic devices such as tablets and smartwatches. These devices are equipped with sensors and cameras to record behavioral data and emotions. In particular, the emotion engine has the ability to detect emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The tablet records the operation log of the learning app and study time, while the smartwatch collects exercise volume and heart rate data.

[1679] 2. Server

[1680] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model during analysis. The server analyzes behavioral patterns and emotional data to identify each child's potential abilities, interests, and current emotional state. Based on the analysis results, it generates customized learning activities and educational materials and sends them to the device.

[1681] 3. Users

[1682] Users (children and their parents or educators) carry out learning activities provided via the device. The child's progress and results are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the activity and optimize the next learning activity.

[1683] Program processing

[1684] The specific operation of the system is explained below. The system mainly functions through the following processes: data collection, data transmission, data storage, data analysis, activity generation, activity distribution, activity implementation, recording of implementation results, result transmission, evaluation and adjustment.

[1685] 1. Data Collection

[1686] Device: When a child uses the device, it records activity logs, behavioral data, and emotional data in real time. For example, a tablet captures a child's learning app operation log (study time, answer time, number of correct / incorrect answers) and uses an emotion engine to obtain facial expression data (concentration, confusion, joy, sadness, etc.). A smartwatch collects heart rate and exercise data.

[1687] 2. Data Transmission

[1688] Terminal: The recorded data is encrypted and periodically sent to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[1689] 3. Data storage

[1690] Server: The server stores the received data in a database, adds new entries to the database, and checks the integrity of the data.

[1691] 4. Data Analysis

[1692] Server: The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it uses classifiers and regression analysis to identify a child's favorite subjects and areas of interest based on the behavioral dataset, and analyzes their emotional state (e.g., joy, confusion, concentration) based on the emotion dataset.

[1693] 5. Activity Generation and Suggestion

[1694] Server: Generates customized learning activities based on the analysis results. For example, for a child who is found to be interested in mathematics and who approaches it with joy, it creates more challenging math problems and math games. The emotion engine also responds to emotional changes during the learning activity.

[1695] 6. Activity Distribution

[1696] Server: Delivers the generated learning activities to the device, encrypts the activities in the appropriate format, and sends them to the child's device.

[1697] 7. Activity implementation

[1698] User (child): Carries out learning activities provided on the device. Children use tablets or smartwatches to complete suggested learning tasks.

[1699] 8. Recording of implementation results

[1700] Device: Records the results of the learning activities the child performs. For example, the answer time, correct answer rate, changes in emotions and facial expressions, etc. are recorded again for the next analysis.

[1701] 9. Send results

[1702] Terminal: The results of the learning are encrypted and sent to the server, allowing the data of the learning activity to be safely stored on the server.

[1703] 10. Evaluation and Adjustment

[1704] Server: Analyzes the collected implementation results and evaluates the effectiveness of the activity. For example, it evaluates the degree to which learning outcomes have improved, changes in the rate of correct answers, changes in emotions, etc. It generates feedback based on the analysis results and optimizes suggestions for the next learning activity. This makes it possible to provide optimal educational support based on the learning effect and the child's emotional state.

[1705] Specific examples

[1706] For example, suppose a child is using a math learning app on a tablet. The tablet records data on the time it takes to answer, the accuracy rate, and facial expressions (concentration, confusion, enjoyment) while using the app. The emotion engine recognizes enjoyment from a smile and difficulty from a confused expression. This data is sent to a server, where an AI model analyzes it and determines that the child has a high interest and ability in math problems. The server then generates more challenging math problems and creative math games and provides appropriate emotional feedback. As the child performs these activities and receives feedback on their results and emotional responses, new suggestions are gradually optimized. In this way, the present invention realizes an innovative system that draws out the talents and interests of individual children and provides efficient and effective educational support.

[1707] Prompt Sentence Examples

[1708] "Please suggest the best learning activities for children who are interested in mathematics and who enjoy engaging in them with a smile."

[1709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1710] Specific processing steps of the program

[1711] Step 1: Data collection

[1712] Devices: Records real-time activity logs, behavioral data, and emotional data as children engage in learning activities. Devices used include tablets and smartwatches.

[1713] Input: Operation information of the learning app, facial expression images from the camera, audio data from the microphone, and biometric information from the smartwatch.

[1714] Data processing: Facial recognition technology is used to analyze facial expressions and detect emotions such as "concentration," "confusion," and "happiness." Voice analysis technology is used to determine emotions from the tone of voice.

[1715] Output: Behavioral data integrating learning operation logs, facial expression data, voice data, and biometric data.

[1716] Step 2: Send data

[1717] Terminal: The recorded data is encrypted and periodically sent to the server.

[1718] Input: Integrated behavioral data.

[1719] Data processing: Encrypting data and sending it through a secure communication channel.

[1720] Output: Encrypted behavioral data.

[1721] Step 3: Save data

[1722] Server: Stores the received data in a database.

[1723] Input: Encrypted behavioral data.

[1724] Data processing: Decrypt the data and store it in the database in the appropriate format.

[1725] Output: Behavioral data stored in a database.

[1726] Step 4: Data analysis

[1727] Server: Analyzes the received data using machine learning algorithms and an emotion engine.

[1728] Input: Behavioral and emotional data from the database.

[1729] Data processing: Using machine learning algorithms to analyze behavioral patterns and identify areas of expertise and interest. Using an emotion engine to analyze emotional fluctuations.

[1730] Output: Analysis results (child's strengths, interests, emotional state).

[1731] Step 5: Activity generation and proposal

[1732] Server: Based on the analysis results, a generative AI model is used to generate customized learning activities.

[1733] Input: Analysis results (areas of expertise, areas of interest, emotional state).

[1734] Data processing: Use a generative AI model to create learning activities suitable for children. Enter the prompt "Suggest the best learning activities for a child who is interested in math and smiles when they engage in it."

[1735] Output: A customized learning activity.

[1736] Step 6: Activity Delivery

[1737] Server: Delivers the generated learning activities to the devices.

[1738] Input: The generated learning activity.

[1739] Data processing: Encrypting activity in a proper format and sending it to your child's device.

[1740] Output: Encrypted learning activity.

[1741] Step 7: Implement the activity

[1742] User (child): Carries out learning activities provided on the device.

[1743] Input: Delivered learning activity.

[1744] Data processing: Conduct the activity and record the answer time, correct answer rate, and emotional state.

[1745] Output: Learning activity outcome data.

[1746] Step 8: Record your results

[1747] Device: Records the results of the learning activities your child performs.

[1748] Input: Learning activity outcome data.

[1749] Data processing: Integrate the outcome data and prepare for the next analysis.

[1750] Output: Consolidated outcome data.

[1751] Step 9: Send results

[1752] Terminal: The recorded performance data is encrypted and sent to the server.

[1753] Input: Integrated outcome data.

[1754] Data processing: The results data will be encrypted and sent.

[1755] Output: Encrypted outcome data.

[1756] Step 10: Evaluate and adjust

[1757] Server: Analyzes the collected implementation results, evaluates the effectiveness of the activity, and optimizes proposals for the next time.

[1758] Input: Outcome data from the database.

[1759] Data processing: Evaluate learning outcomes and emotional fluctuations, and generate feedback to optimize the next learning activity.

[1760] Output: Feedback of optimized learning activities.

[1761] As described above, detailed data processing and calculations are carried out at each step of this system, enabling optimal learning activities to be provided for children.

[1762] (Application example 2)

[1763] 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."

[1764] Conventional educational systems have struggled to provide customized learning activities tailored to individual children's interests and talents. They also lack the ability to grasp changes in children's emotions and interests in real time and provide appropriate feedback accordingly. Furthermore, it has been difficult to integrate users' purchasing behavior and emotional data in virtual stores to provide personalized product recommendations.

[1765] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for recording data on a child's daily behavior, means for transmitting the recorded data to the server, means for inputting the received data into a machine learning algorithm and analyzing the child's behavioral patterns, means for generating customized learning activities based on the analysis results, means for distributing the generated learning activities to a terminal, means for the child to perform the distributed activities, means for recording and transmitting the results of the activities to the server, means for analyzing the results of the activities to evaluate the effectiveness of the activities and optimizing the next suggestions, and means for recording the child's purchasing behavior data and emotional data and making product suggestions based on the results. This makes it possible to provide educational support tailored to each child's talents and interests, and to analyze emotions in real time in virtual stores and make optimal product suggestions.

[1766] "Children's daily behavioral data" refers to data such as study time, answer time, correct answer rate, heart rate, and amount of exercise recorded when using electronic devices such as tablets and smartwatches.

[1767] "Means for transmitting to a server" refers to a communication means by which the terminal encrypts data collected in real time or at specified time intervals and securely uploads it to a server.

[1768] "Means for inputting into machine learning algorithms to analyze children's behavioral patterns" refers to analytical means, including classifiers and regression models, that use the collected data to identify children's behavioral characteristics and patterns.

[1769] The "means for generating customized learning activities" refers to a means for creating learning tasks and exercises that are tailored to the individual talents and interests of each child based on the analysis results.

[1770] The "means for delivering learning activities to devices" refers to a communication means for encrypting the generated learning assignments and sending them to devices such as tablets and smartwatches used by children.

[1771] The "means for children to carry out the distributed activities" refers to the means for providing learning activities for children to carry out through a terminal and recording the results.

[1772] The "means for recording the results of the learning and sending them to the server" refers to a means for recording the results and reactions of the learning activities performed by the child and periodically sending them to the server.

[1773] "Means for analyzing implementation results, evaluating the effectiveness of the activity, and optimizing the next proposal" refers to means for analyzing collected implementation result data, evaluating the effectiveness of the learning activity, and optimizing the content of the next learning activity based on the evaluation results.

[1774] "Children's purchasing behavior data" is data including a user's operation log, browsing time, number of clicks, etc. in a virtual store.

[1775] "Emotion data" refers to data related to emotions extracted from the user's facial expressions and voice obtained using voice analysis and face recognition technology.

[1776] The "means for making product suggestions" is a means for recommending optimal products to users based on the analyzed purchasing behavior data and emotional data.

[1777] The present invention is a system that collects and analyzes purchasing behavior data and emotional data of individual users in a virtual store to make optimal product recommendations. This system is composed of users, terminals, and a server.

[1778] System Configuration

[1779] 1. Terminal

[1780] The devices used are portable electronic devices such as smartphones and smart glasses. These devices are equipped with sensors and cameras to record purchasing behavior data and emotions. In particular, the emotion engine has the function of detecting emotions from the user's facial expressions and voice using facial recognition and voice analysis technologies. The smartphone records the operation log and browsing time of the purchasing app, while the smart glasses track eye movements and collect facial expression data.

[1781] 2. Server

[1782] The server receives the data sent from the device and analyzes it using machine learning algorithms and an emotion engine. The received data is stored in a database and is input into the machine learning model for analysis. The server analyzes purchasing behavior patterns and emotion data to identify individual users' interests, preferences, and current emotional state. Based on the analysis results, it generates customized product suggestions and sends them to the device.

[1783] 3. Users

[1784] The user receives product suggestions provided via the device. The user's shopping behavior and reactions in the virtual store are recorded on the device, and the data is sent to the server. The server uses this data to evaluate the effectiveness of the product suggestions and optimize the next suggestions.

[1785] Explanation of specific measures

[1786] 1. Data Collection

[1787] The device records activity logs and emotional data in real time as the user uses it. For example, a smartphone captures the operation log of a virtual store app (browsing time, number of clicks) and obtains facial expression data (excitement, joy, confusion, etc.) using an emotion engine. Smart glasses collect eye-tracking data and changes in facial expressions.

[1788] 2. Data Transmission

[1789] The device encrypts the recorded data and periodically sends it to the server. When the collected data reaches a certain volume or at specified intervals, the data is uploaded to the server to ensure secure communication.

[1790] 3. Data analysis

[1791] The server stores the received data in a database and analyzes it using machine learning algorithms and an emotion engine. For example, it identifies the user's interests and preferences using methods such as classifiers and regression analysis based on a purchasing behavior dataset, and analyzes their emotional state (e.g., excitement, joy, confusion) based on an emotion dataset.

[1792] 4. Product proposal generation and distribution

[1793] The server generates customized product suggestions based on the analysis results. For example, for a user who shows a strong interest in a particular product and tends to purchase it with joy, related products and accessories will be recommended. The emotion engine also responds to emotional changes during shopping. The generated product suggestions are encrypted in an appropriate format and sent to the user's device.

[1794] Program processing

[1795] The server runs the programs described above for data collection, data transmission, data analysis, and product proposal generation and distribution. The main hardware used is a multi-function server, an internet connection, and the user's smartphone or smart glasses. The software uses OpenCV for face recognition technology, Keras for emotion recognition models, and the Requests library for data transmission.

[1796] Specific examples

[1797] For example, imagine a user in a market is browsing a virtual store using smart glasses. The glasses record eye-tracking data and facial expression data (surprise, joy, confusion, etc.). The emotion engine recognizes the user's joy from a smile and sends the data to the server. An AI model on the server analyzes the data and finds that the user is highly interested in a new product. Based on this information, the server can suggest related new product lines and discount offers. A specific prompt might be, "It seems you're interested in our new products. How about these accessories?"

[1798] As described above, the present invention provides a system that analyzes user purchasing behavior and emotional data in real time and makes optimal product suggestions to individual users.

[1799] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1800] Step 1:

[1801] When a user uses the virtual store app, the device records purchasing behavior data (operation log, browsing time, number of clicks) and emotional data (facial expression data, eye tracking data) in real time.Specifically, it uses a camera, microphone, and touch sensor to capture the user's facial expressions, voice, and operation status.

[1802] Input: User operation log, facial expression data, gaze data

[1803] Output: Recorded data

[1804] Step 2:

[1805] The device sends the recorded data to a server. The data is encrypted and periodically uploaded to the server using a secure communication protocol (e.g., HTTPS). The data is sent at specified time intervals when it reaches a certain volume.

[1806] Input: Recorded data

[1807] Output: Encrypted data

[1808] Step 3:

[1809] The server stores the received data in a database, where it is kept in an organized format for use in analysis.

[1810] Input: Encrypted data

[1811] Output: Data stored in the database

[1812] Step 4:

[1813] The server inputs the stored data into machine learning algorithms and emotion engines to analyze the user's purchasing behavior patterns and emotions. For example, it uses classifiers and regression analysis based on behavioral data to identify the user's interests and preferences, and inputs emotion data (facial expressions, voice, etc.) into emotion recognition models to identify the user's emotional state.

[1814] Input: Saved data

[1815] Output: Analysis results (purchase behavior patterns, emotional state)

[1816] Step 5:

[1817] The server generates customized product recommendations based on the analysis results, using the generative AI model to create prompts and suggest the best products and related accessories for the user.

[1818] Input: Analysis results

[1819] Output: Product proposal

[1820] Step 6:

[1821] The server delivers the generated product proposals to the terminal. The product proposals are encrypted and sent to the user's terminal, allowing the user to receive the proposals in real time.

[1822] Input: Product proposal

[1823] Output: Encrypted proposal data

[1824] Step 7:

[1825] The user receives the product suggestions provided to the terminal and performs shopping in the virtual store. Specifically, the user browses products according to the product suggestions and considers purchasing them.

[1826] Input: Encrypted proposal data

[1827] Output: User behavior data

[1828] Step 8:

[1829] The device then records the user's new purchasing behavior and emotional data and sends it to the server, which then repeats the process and optimizes the recommendations.

[1830] Input: User behavior data, emotion data

[1831] Output: Recorded data

[1832] The above are the specific processing steps for carrying out the invention.

[1833] 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...

Claims

1. A means for recording data on a child's daily behavior; means for transmitting the recorded data to a server; a means for inputting the received data into a machine learning algorithm to analyze the child's behavioral patterns; means for generating customized learning activities based on the analysis results; means for delivering the generated learning activity to a terminal; a means for the child to carry out the delivered activity; A means for recording the implementation results and transmitting them to a server; A means to analyze the results of the implementation, evaluate the effectiveness of the activity, and optimize the next proposal. A system including:

2. The system according to claim 1, further comprising means for identifying the child's interests and areas of expertise based on the analysis results and suggesting learning activities in accordance therewith.

3. 10. The system of claim 1, further comprising means for capturing the child's facial expressions and emotions using facial recognition technology and recording the child's concentration and reactions based thereon.

Images