System

Abstract

A system is provided.SOLUTION: A system, comprising: means for analyzing collected learning data of a user; means for constructing a prediction model based on the learning data; means for generating a personalized learning plan using the prediction model; means for monitoring a learning progress of the user based on the learning plan; means for identifying a free time from schedule information of the user; means for suggesting a care based on the free time; and means for notifying the user of the 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] Creating an optimal study plan that allows users to study efficiently and effectively is difficult and requires a lot of time and effort. It is also challenging to provide appropriate mental health care at the right time to reduce stress and fatigue during the course of study. This can lead to problems such as reduced learning efficiency and discouragement of continued study. The objective of this invention is to provide a system that efficiently manages a user's learning progress and provides appropriate mental health care. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system as follows. First, the system comprises means for analyzing collected learning data of a user. Next, the system comprises means for constructing a predictive model based on the learning data, and means for generating an individual learning plan using this predictive model. The system also comprises means for monitoring the user's learning progress based on the generated learning plan. In addition, the system comprises means for identifying free time from the user's schedule information, and means for suggesting mental health care to the user based on that free time. These suggestions are customized based on the user's preferences and past history. The system also comprises means for notifying the user of the suggestions. This configuration allows the user to study efficiently and effectively, and receiving appropriate mental health care promotes continued study.

[0006] "Collection" refers to the process of gathering learning data and schedule information from users.

[0007] "Study data" refers to information related to the user's study, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[0008] "Analysis" is the process of analyzing collected data and extracting meaningful information from it.

[0009] A "predictive model" is a mathematical model constructed to predict a user's future learning progress and required learning volume based on past data.

[0010] A "study plan" is a schedule and content plan set up to help a user efficiently progress through their studies.

[0011] "Study progress" is an indicator that shows how far a user has progressed toward their set study plan.

[0012] "Monitoring" refers to the process of tracking a user's learning activities in real time and checking their progress.

[0013] "Schedule information" refers to information about the user's plans and timetables in daily life.

[0014] "Free time" is time in a user's schedule when no specific activities are scheduled.

[0015] "Mental health" refers to activities and suggestions to support users' mental and emotional well-being.

[0016] A "suggestion" is a recommendation to a user for an action or activity.

[0017] "Notification" refers to the means or process of informing users of offers or information.

[0018] "Customization" means tailoring services and offers based on a user's individual preferences and past history. [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] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Below, we will explain the outline and specific examples of the program for this system.

[0041] System Overview

[0042] 1. Collecting training data

[0043] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[0044] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[0045] 2. Analysis of training data

[0046] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[0047] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[0048] 3. Building a predictive model

[0049] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[0050] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[0051] 4. Generate a learning plan

[0052] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[0053] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0054] 5. Monitoring your learning progress

[0055] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[0056] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[0057] 6. Analyzing Schedule Information

[0058] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[0059] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[0060] 7. Generating mental health care proposals

[0061] The server then provides personalized mental health care suggestions to the user based on the identified free time, which are customized based on past history and user preferences.

[0062] Example: The server suggests to user A that they "take a short meditation" or "listen to relaxing music" between 3:00 and 4:00 PM.

[0063] 8. Notice to Users

[0064] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[0065] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[0066] In this way, this system generates an optimal study plan based on the user's study data, monitors progress, and provides psychological support at appropriate times, thereby improving the user's study efficiency and persistence.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] Users begin studying through their devices, and data such as study content, start time, end time, and correct answer rate are automatically recorded.

[0070] Step 2:

[0071] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[0072] Step 3:

[0073] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[0074] Step 4:

[0075] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[0076] Step 5:

[0077] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[0078] Step 6:

[0079] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[0080] Step 7:

[0081] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[0082] Step 8:

[0083] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[0084] Step 9:

[0085] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[0086] Step 10:

[0087] The server runs an algorithm to suggest mental health care based on the user's free time, and the suggestions are customized based on the user's preferences and past history.

[0088] Step 11:

[0089] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, audio alert, or email.

[0090] Step 12:

[0091] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[0092] Example 1

[0093] 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."

[0094] In modern society, there is a demand for specific plans and support to help individual learners continue their studies efficiently and sustainably. However, many systems only provide general learning plans, making it difficult to provide individual learning plans tailored to individual learning tendencies and schedules. It is also difficult to properly track learning progress and provide psychological support. This creates challenges that prevent learners from progressing efficiently and hinders improvement in learning outcomes.

[0095] 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.

[0096] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental health care based on the free time, means for notifying the user of the suggestions, means for recording the learning progress in real time and transmitting the recording results to the server, means for applying a machine learning algorithm to improve the user's learning efficiency based on the collected and analyzed data, and means for customizing mental health care suggestions based on the user's past history and preferences. This allows the server to provide appropriate individual learning plans and psychological care, enabling the user to progress in their studies efficiently and sustainably.

[0097] "Collected user learning data" is data recorded when a user engages in learning activities, including study time, study content, correct answer rate, and learning achievement level.

[0098] "Means for analyzing" means a set of machine learning algorithms and related software for evaluating the collected learning data and identifying the user's learning trends and progress.

[0099] A "means for constructing a predictive model" is a configuration of software and algorithms for generating a model for predicting a user's future learning performance based on the analyzed learning data.

[0100] The "means for generating personalized learning plans" is a system that uses predictive models to generate detailed learning schedules and curricula tailored to the individual learning needs of each user.

[0101] The "means for monitoring learning progress" refers to a device and a program for recording the learning activities actually performed by the user in real time, transmitting the data to a server, and supervising the progress against the learning plan.

[0102] The "means for identifying free time" is software that analyzes the user's schedule information and identifies free time that can be used for study or mental care.

[0103] The "means for suggesting mental care" is a system that suggests activities that promote relaxation and concentration suitable for a specified free time based on the user's preferences and past history.

[0104] The "means for notifying the user of suggestions" refers to a device or program for notifying the user of mental health care suggestions from the server via a pop-up, a voice alert, an email, or the like.

[0105] "Means for recording learning progress in real time and transmitting the recorded results to a server" refers to a terminal and software configuration for recording a user's learning activities in real time and automatically transmitting the data to a server.

[0106] "Means for applying machine learning algorithms" refers to programs and models for utilizing machine learning techniques to improve learning efficiency based on collected and analyzed user learning data.

[0107] "Means for customizing mental health care suggestions based on the user's past history and preferences" is a system for suggesting optimal mental health care activities based on the user's past behavioral history and registered preferences.

[0108] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve a user's learning efficiency. The following describes an embodiment of this system.

[0109] The main components of the system include a server, user terminals, and various software for data analysis. Specific software used includes machine learning libraries such as Python, TensorFlow, and PyTorch. The server also has a database that stores and manages user learning data.

[0110] The server collects learning data from the user's device. This learning data includes learning time, learning content, correct answer rate, and learning achievement level. The data collected by the device is sent to the server in real time, and the server stores it in a database.

[0111] The server then analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress. For example, the server can identify the user's strengths and weaknesses and reflect this in their study plan.

[0112] Based on the analysis results, the server builds a predictive model using TensorFlow and PyTorch to predict future learning performance based on the user's past learning data and current progress. This model forms the basis for planning future learning schedules.

[0113] The server uses the predictive model to generate a personalized study plan for each user, including specific subjects and study times, designed to maximize the user's learning efficiency. For example, the server generates a two-week schedule for User A, with 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0114] As the user studies, the device records their progress in real time and sends it to the server, which then monitors the progress of the study plan and adjusts it as needed.

[0115] The server also analyzes the user's schedule information to identify free time that cannot be used for studying. Once free time is identified, the server makes personalized suggestions for the user's mental health care. These suggestions are customized based on past history and the user's preferences. For example, the server might suggest to User A that they "do a short meditation session" or "listen to relaxing music" between 3:00 and 4:00 PM.

[0116] The server sends mental health advice to the user via a pop-up notification, voice alert, or email. For example, at 3 p.m., the device displays a pop-up notification prompting the user to listen to relaxing music.

[0117] Some examples of specific prompts include:

[0118] "Based on User A's learning data, please analyze his math accuracy rate over the past year and predict the amount of study time he will need in the next two weeks."

[0119] According to the present invention, the user can study efficiently and continuously, and can receive mental health care at an appropriate time.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] The server collects learning data from the user's device. The device automatically sends the data to the server when the user finishes learning. The collected data includes learning time, learning content, correct answer rate, and learning achievement. The input is a record of the user's learning activities, and the output is learning data stored on the server.

[0123] Specific operation: The device records data on the user's math study for 45 minutes, with an 80% accuracy rate. When the user finishes studying, the device sends this data to the server, which stores it in a database.

[0124] Step 2:

[0125] The server analyzes the collected learning data. For the analysis, Python is used to evaluate the user's learning tendency and progress using machine learning algorithms. The input is the learning data collected in the previous step, and the output is the analysis results.

[0126] Specific operation: The server analyzes the training data using the Python library and determines that User A is good at math but not so good at history.

[0127] Step 3:

[0128] The server builds a predictive model based on the analysis results. This model is built using TensorFlow and predicts future learning performance. The input is the analysis results, and the output is the predictive model.

[0129] Specific operation: Based on User A's past learning data, the server uses TensorFlow to build a model that predicts how much learning will be required in the next two weeks.

[0130] Step 4:

[0131] The server uses the predictive model to generate a personalized learning plan, including specific learning content and time. The input is the predictive model, and the output is the user's personalized learning plan.

[0132] Specific operation: Based on the predictive model, the server generates a detailed two-week schedule for User A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history study.

[0133] Step 5:

[0134] The device records the user's progress in real time as they study and sends it to the server. The input is the user's study activity, and the output is the recorded study data sent to the server.

[0135] How it works: When a user starts studying, the device records the study time and content in real time. When the user finishes studying, the device sends the data to the server, which then updates the progress.

[0136] Step 6:

[0137] The server analyzes the user's schedule information and identifies available free time. The schedule information is obtained from the terminal. The input is the schedule information, and the output is the available free time.

[0138] What happens: The server collects and analyzes data from User A's calendar application. It determines that there is free time between 3:00 PM and 4:00 PM.

[0139] Step 7:

[0140] The server then provides personalized mental health care suggestions based on the identified free time. The suggestions are customized based on the user's past history and preferences. The inputs are free time and the user's past history and preferences, and the output is mental health care suggestions.

[0141] Specific operation: Based on User A's past history, the server suggests a short meditation session or listening to relaxing music between 3:00 and 4:00 PM.

[0142] Step 8:

[0143] The terminal notifies the user of the mental health care suggestions from the server. The notification can be done by a pop-up, a voice alert, or an email. The input is the mental health care suggestion, and the output is the information to be notified to the user.

[0144] What it does: At 3 PM, the device will display a pop-up notification, prompting the user to listen to relaxing music.

[0145] (Application example 1)

[0146] 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."

[0147] In today's learning environment, analyzing individual learning data and providing appropriate learning plans is essential for users to study efficiently and effectively. However, previous systems have not been able to provide personalized care that takes into account each user's individual learning tendencies and progress. Furthermore, there are limited ways for learners to receive psychological support at the appropriate time, which can lead to reduced learning efficiency. Furthermore, real-time content delivery using smart devices remains a challenge.

[0148] 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.

[0149] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for providing appropriate learning content and mental care content to improve learning efficiency based on the learning data, and means for delivering content in real time via a head-mounted display or a smartphone.

[0150] This will enable the provision of optimal learning plans and mental care based on individual users' learning data, improving learning efficiency and mental health. In addition, real-time content delivery using smart devices will make the learning experience more flexible and effective.

[0151] "Collection" refers to the act of collecting user learning data from the terminal to a central server.

[0152] "Analysis" is the process of evaluating a user's learning trends and progress based on collected learning data.

[0153] A "predictive model" is a mathematical or statistical model for predicting a user's future learning progress based on the analysis results.

[0154] A "study plan" is a schedule generated using a predictive model that details a user's individual learning content and time allocation.

[0155] "Study progress" is a concept that refers to the progress and level of achievement of a user as they proceed with their actual studies.

[0156] "Schedule information" is data that indicates the user's schedule and time allocation. This information is obtained from a calendar application or the like.

[0157] "Free time" is a period of time that is identified from schedule information and is free to be used for study or other activities.

[0158] "Mental health care" is a concept that refers to suggesting activities and content to improve users' mental health.

[0159] "Real-time" refers to a situation in which data or content is processed and delivered immediately, without delay.

[0160] "Content delivery" is the act of delivering digital content such as music, video, and text for learning and mental health care to user devices.

[0161] "Smart devices" refer to information processing devices, including mobile terminals and wearable devices that can connect to the Internet.

[0162] The system for implementing this invention collects and analyzes user learning data and provides psychological care. This system mainly consists of a server, a user terminal, and a smart device (e.g., a smartphone or a head-mounted display).

[0163] 1. Collecting training data

[0164] The server collects learning data from users' terminals and smart devices. This learning data includes learning time, learning content, correct answer rate, and learning achievement. Specifically, the data is collected in real time using Firebase and Google Analytics and sent to the cloud.

[0165] 2. Analysis of training data

[0166] The server analyzes the collected learning data using machine learning algorithms (e.g., TensorFlow), which evaluates the user's learning trends and progress and identifies their strengths and weaknesses.

[0167] 3. Building a predictive model

[0168] Based on the analysis results, the server builds a model to predict the user's learning progress. This model uses TensorFlow to predict the user's future learning status.

[0169] 4. Generate a learning plan

[0170] The server uses the built predictive model to generate a personalized study plan for the user, detailing which subjects should be studied and for how many hours.

[0171] 5. Monitoring your learning progress

[0172] The server records the user's progress in real time as they study and stores it in the cloud via Firebase, allowing the user to monitor their progress in their study plan.

[0173] 6. Analyzing Schedule Information

[0174] The server identifies available study time by analyzing the user's schedule information, which is obtained from the user's calendar application.

[0175] 7. Generating mental health care proposals

[0176] The server then provides personalized mental health suggestions based on the identified free time. These suggestions are customized based on past history and user preferences. Examples include short meditation sessions or listening to relaxing music.

[0177] 8. Notice to Users

[0178] The server sends mental health care suggestions as push notifications to the user's terminal or smart device, allowing the user to receive mental health care at the appropriate time.

[0179] As a concrete example, consider a user studying math using a smartphone app. After completing 45 minutes of studying, the app sends data to a server. The server analyzes the data, determines that the user is tired, and suggests a meditation session.

[0180] Prompt Sentence Examples

[0181] text

[0182] User A completed 45 minutes of math study today but seems a little tired. You suggest a short meditation session from 3:00 PM - 4:00 PM. After the meditation, relaxation music will begin playing.

[0183] The system allows users to receive optimal learning plans and mental health care to improve learning efficiency, and makes the learning experience flexible and effective by delivering content in real time using smart devices.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The server collects learning data from users' terminals and smart devices.

[0187] Input: Study time, study content, correct answer rate, learning achievement

[0188] Output: Collected training data

[0189] What it does: It uses Firebase and Google Analytics to send data generated by users as they learn to the cloud in real time.

[0190] Step 2:

[0191] The server analyzes the collected learning data.

[0192] Input: Collected training data

[0193] Output: User's learning tendency and progress

[0194] How it works: It uses machine learning algorithms such as TensorFlow to analyze data and identify the user's strengths and weaknesses.

[0195] Step 3:

[0196] The server builds a predictive model based on the analysis results.

[0197] Input: User's learning habits and progress

[0198] Output: Learning progress prediction model

[0199] Specific operation: Using TensorFlow, we build a model that uses the analysis results to predict the user's future learning progress.

[0200] Step 4:

[0201] The server uses the predictive model to generate a personalized learning plan.

[0202] Input: Learning progress prediction model

[0203] Output: Individualized Learning Plan

[0204] Specific behavior: Based on the user's strong and weak subjects, a schedule is generated detailing which subjects should be studied and for how long.

[0205] Step 5:

[0206] The server monitors the user's progress in real time as they actually study.

[0207] Input: User training data

[0208] Output: Learning progress

[0209] What it does: Stores and monitors user learning progress in the cloud through Firebase.

[0210] Step 6:

[0211] The server analyzes the user's schedule information.

[0212] Input: User's schedule information

[0213] Output: Identifying free time

[0214] What it does: Retrieves schedule data from a calendar application and parses it to identify available times.

[0215] Step 7:

[0216] The server generates psychological care suggestions based on the identified free time.

[0217] Input: Availability, user preferences and past history

[0218] Output: Mental care suggestions

[0219] What it does: Creates a plan to provide care, such as a short meditation session or listening to relaxing music, based on the user's past history and preferences.

[0220] Step 8:

[0221] The server notifies the user's terminal or smart device of mental care suggestions.

[0222] Input: Mental care suggestions

[0223] Output: User notification

[0224] Specific behavior: Use the push notification function of the smart device to notify the user of care suggestions. Specifically, the following prompt is displayed: "User A completed 45 minutes of math study today, but seems a little tired. We suggest a short meditation session from 3:00 PM to 4:00 PM. After the meditation, relaxation music will begin playing."

[0225] 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.

[0226] This invention is a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Furthermore, this system uses an emotion engine to recognize the user's emotions and customizes the mental health care proposals more effectively.

[0227] System Overview

[0228] 1. Collecting training data

[0229] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[0230] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[0231] 2. Analysis of training data

[0232] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[0233] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[0234] 3. Building a predictive model

[0235] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[0236] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[0237] 4. Generate a learning plan

[0238] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[0239] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0240] 5. Monitoring your learning progress

[0241] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[0242] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[0243] 6. Analyzing Schedule Information

[0244] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[0245] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[0246] 7. Emotion Recognition with Emotion Engine

[0247] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes the data and recognizes the user's emotional state.

[0248] Example: From User A's facial expressions and tone of voice as he / she progresses with his / her studies, the emotion engine recognizes that User A is feeling tired or stressed.

[0249] 8. Generating mental health care proposals

[0250] The server then proposes personalized mental health care to the user based on the identified free time and the emotional data recognized by the emotion engine.The proposals are customized based on the user's past history and preferences.

[0251] Example: The server suggests a short meditation session or listening to relaxing music for User A's free time between 3:00 and 4:00 PM. Because the server recognizes that User A is feeling tired and stressed, the suggestions include activities that have a high relaxation effect.

[0252] 9. Notice to Users

[0253] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[0254] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[0255] This system is designed to improve users' learning efficiency and mental health by conducting a comprehensive process from analyzing learning data to building predictive models, generating and monitoring learning plans, recognizing users' emotions using an emotion engine, and generating and notifying them of mental care suggestions.

[0256] The processing flow will be explained below.

[0257] Step 1:

[0258] Users begin studying through their device, which automatically records data such as the study content, start time, end time, and correct answer rate.

[0259] Step 2:

[0260] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[0261] Step 3:

[0262] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[0263] Step 4:

[0264] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[0265] Step 5:

[0266] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[0267] Step 6:

[0268] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[0269] Step 7:

[0270] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[0271] Step 8:

[0272] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[0273] Step 9:

[0274] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[0275] Step 10:

[0276] The device captures the user's facial expressions, voice tone, and behavioral data, which are then transmitted to a server in real time.

[0277] Step 11:

[0278] The server analyzes the received facial expressions, voice tone, and behavioral data using an emotion engine to recognize the user's emotional state.

[0279] Step 12:

[0280] The server generates psychological care suggestions based on the user's free time and recognized emotional data, and these suggestions are customized based on the user's preferences and past history.

[0281] Step 13:

[0282] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, voice alert, or email.

[0283] Step 14:

[0284] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[0285] Example 2

[0286] 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."

[0287] In recent years, many systems have been developed to improve learners' learning outcomes, but few systems not only generate efficient learning plans but also take into consideration the learner's mental health. In particular, there is a demand for systems that can recognize the user's emotional state in real time and suggest appropriate mental care. To solve this problem, a system is needed that can analyze learning data, monitor progress, recognize emotions, and suggest individual care in an integrated manner.

[0288] 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.

[0289] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, emotion recognition means for recognizing the user's emotional state, means for personalized mental care suggestions based on the emotional state recognized by the emotion recognition means, and means for notifying the user of the suggestions. This not only improves the user's learning efficiency but also maintains their mental health while studying, thereby improving the overall quality of the learning experience.

[0290] "Study data" refers to information about a user's learning activities, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[0291] A "predictive model" is a computational model constructed to predict a user's future learning progress based on collected and analyzed learning data.

[0292] A "study plan" is a schedule generated using a predictive model that details which subjects a user should study and when.

[0293] "Schedule information" is information related to the user's time management, and mainly includes plans recorded on a calendar or timetable.

[0294] "Free time" is identified from the user's schedule information and refers to unallocated time that can be used for study or mental health care.

[0295] "Mental care" refers to suggestions and activities to maintain and improve the user's mental health, with the aim of relaxation and stress reduction.

[0296] "Emotion recognition means" refers to functions and technologies for analyzing a user's facial expressions, voice tone, and behavioral data to recognize the user's emotional state.

[0297] "Personalized recommendations" refers to providing individually optimized mental health recommendations based on the user's emotional state, past history, and preferences.

[0298] This invention is a learning support system for improving a user's learning efficiency and mental health. This system collects and analyzes learning data, builds a predictive model, generates an individual learning plan, monitors progress, recognizes emotions, and provides mental health care suggestions in a series of steps.

[0299] The system mainly consists of a server, a terminal, and a user. A specific embodiment of the system is shown below.

[0300] The server first collects learning data from the user's device. The collected learning data includes study time, learning content, correct answer rate, and learning achievement. For example, if a user achieves 80% correct answers on a math test, the data is sent to the server.

[0301] Next, the server analyzes the collected learning data using machine learning algorithms. The purpose of the analysis is to identify the user's learning tendencies, strong and weak subjects. Specifically, the data is analyzed using clustering and classifiers. The server analyzes the user's data and determines, for example, that the user is good at math and science, but weak at history.

[0302] Based on the analysis results, the server builds a model to predict the user's learning progress. This model predicts future study time and effort based on past data. For example, it generates a model that says, "You'll need 10 hours of math and 8 hours of science in the next two weeks."

[0303] Based on the predictive model, the server generates an individualized study plan, detailing which subjects to study and when to study them. The server generates a schedule of 45 minutes of math, 30 minutes of science, and 60 minutes of history each day for the next two weeks.

[0304] The device records the user's progress in real time as they study and sends the data to the server. For example, if a user studies mathematics on the device for 30 minutes, the data is immediately sent to the server and the learning progress is updated. In this way, the server monitors the progress of the learning plan.

[0305] Additionally, the server analyzes the user's schedule information, typically obtained from a calendar or timetable, to identify available study time. For example, the server may identify an available time slot between 3:00 PM and 4:00 PM.

[0306] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, if the user looks anxious, the emotion engine detects "stress."

[0307] The server then suggests personalized mental health care activities based on the identified free time and the emotional data recognized by the emotion engine. The suggestions are customized based on the user's past history and preferences. For example, it suggests specific activities such as "relieve stress by listening to relaxing music at 3 p.m."

[0308] Finally, the device notifies the user of the mental health care suggestions from the server via a pop-up, a voice alert, or an email. For example, the device may display a pop-up notification to the user at 3:00 PM, prompting them to start their mental health care activities.

[0309] In this way, the system of the present invention improves the user's learning efficiency and mental health through a series of processes, thereby enhancing the quality of the overall learning experience.

[0310] Example prompt sentence:

[0311] "Please explain how you can analyze a user's emotional state in real time and optimize their learning schedule."

[0312] "Please tell me how to design a system that integrates user learning data and emotional data to personalize mental health care suggestions."

[0313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0314] Step 1:

[0315] Data collection

[0316] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[0317] Input: Data from the user's learning app (e.g., study time and correct answer rate)

[0318] Output: Training data stored on the server

[0319] Specific operation: When a user scores 80% on a math test, the data is sent from the device to the server.

[0320] Step 2:

[0321] Data analysis

[0322] The server analyzes the collected learning data using machine learning algorithms.

[0323] Input: The training data collected in step 1

[0324] Output: User's learning tendency, favorite subjects, and favorite subjects (e.g., user is good at math, but not good at history)

[0325] What it does: The server analyzes the data using clustering and classifiers to determine that the user is good at math and science, but bad at history.

[0326] Step 3:

[0327] Building predictive models

[0328] Based on the analysis results, the server builds a model to predict the user's future learning progress.

[0329] Input: Analysis result from step 2

[0330] Output: A model that predicts future study time and effort (e.g., 10 hours of math and 8 hours of science needed in the next two weeks)

[0331] Specific operation: The server generates a model that predicts future study time based on past data.

[0332] Step 4:

[0333] Generate a lesson plan

[0334] The server generates an individualized learning plan based on the predictive model.

[0335] Input: Predictive model from step 3

[0336] Output: Individualized learning plan (e.g., 45 minutes of math, 30 minutes of science, and 60 minutes of history each day)

[0337] Specific operation: The server generates the user's schedule for the next two weeks and sends it to the device.

[0338] Step 5:

[0339] Monitoring learning progress

[0340] As the user actually studies, the device records their progress in real time and sends it to the server.

[0341] Input: The actual study time and content of the user

[0342] Output: Learning progress data sent to the server

[0343] What it does: When a user studies math on their device for 30 minutes, the data is immediately sent to the server and their learning progress is updated.

[0344] Step 6:

[0345] Schedule information analysis

[0346] The server analyzes the user's schedule information and identifies free time that can be used for studying.

[0347] Input: User's schedule information (e.g., calendar app)

[0348] Output: Identify available times (e.g., available times between 3:00 PM and 4:00 PM)

[0349] What happens: The server analyzes the calendar app data to identify free time.

[0350] Step 7:

[0351] emotion recognition

[0352] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes it.

[0353] Input: User facial expressions, voice tone, and behavioral data

[0354] Output: Recognizing the user's emotional state (e.g., recognizing that the user is stressed)

[0355] How it works: The user uses the device's camera and microphone to capture facial expressions and voice data in real time, which is then sent to the server and analyzed by the emotion engine.

[0356] Step 8:

[0357] Generating mental health care proposals

[0358] The server then proposes personalized mental care for the user based on the identified free time and the emotional data recognized by the emotion engine.

[0359] Input: Free time from step 6, Emotion data recognized from step 7

[0360] Output: Personalized mental health recommendations (e.g., listening to relaxing music at 3 PM)

[0361] How it works: The server suggests listening to relaxing music or meditating based on the user's free time and current emotional state.

[0362] Step 9:

[0363] User Notification

[0364] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[0365] Input: Mental care suggestions from the server

[0366] Output: Notify user (e.g., show a popup notification at 3 PM)

[0367] What it does: The device displays a pop-up notification to the user at 3 PM, encouraging them to start mental health activities.

[0368] (Application example 2)

[0369] 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."

[0370] Conventional learning support systems have had the challenge of making it difficult to simultaneously improve users' learning efficiency and mental health. Similar challenges exist in managing the efficiency of robots and human workers in factories. Specifically, there is a lack of an overall system that can analyze the work data of robots and workers individually to improve efficiency while also providing mental care, raising concerns about reduced work efficiency and reduced work performance due to stress.

[0371] The identification process by the identification 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 analyzing collected user learning data, means for constructing a prediction model based on the learning data, means for generating an individual learning plan using the prediction model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for collecting and analyzing robot work data, means for generating a new work plan based on the robot's work efficiency, means for recognizing the worker's emotional state and suggesting mental care, and means for notifying the worker of the suggestion. This makes it possible to provide mental care tailored to each individual's emotional state while improving the learning and work efficiency of users and workers.

[0372] A "server" is a computer that provides services to other computers over a network.

[0373] "Study data" is information related to the user's study, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[0374] A "predictive model" is a model for predicting future learning progress and the amount of learning required based on collected data.

[0375] A "study plan" is a plan that details a user's individual study schedule and content based on a predictive model.

[0376] "Study progress" refers to the progress of how far the user has actually progressed in their studies.

[0377] "Schedule information" refers to calendar information and time management data that includes the user's daily schedule.

[0378] "Free time" is a time period extracted from the user's schedule information that can be used for studying or relaxing.

[0379] "Mental care" refers to suggestions and activities for relaxation and stress relief provided to maintain the user's mental health.

[0380] "Notification" refers to conveying information to the user, and is done using means such as a pop-up, audio alert, or email.

[0381] "Work data" is information about work performed by robots and workers in a factory, and includes information about efficiency and progress.

[0382] "Emotional state" refers to the worker's current mental state and is recognized from facial expressions, tone of voice, and behavioral data.

[0383] A "work plan" is a plan that indicates an efficient work schedule and content, newly generated based on the robot's work efficiency.

[0384] The present invention provides a system for improving the work efficiency of robots working in factories and the mental health of human workers. The following describes an embodiment of this system.

[0385] System program generation

[0386] The system can be implemented using Python, and its main processes include data collection, data analysis, predictive model construction, learning plan generation, learning progress monitoring, emotional state recognition, and mental health care suggestion generation and notification.

[0387] Processing Description

[0388] 1. Data Collection

[0389] The server collects user learning data, robot work data, and worker emotion data. The learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[0390] Specifically, training data is collected from a training application, and work data is collected from the factory's production management system. Emotion data is collected using cameras and voice analysis. Specific hardware examples include the OpenVINO platform for emotion detection and the Google Cloud Speech-to-Text API for voice analysis.

[0391] 2. Data Analysis

[0392] The server uses machine learning algorithms to analyze the collected data, which in turn evaluates the user's learning habits, the robot's work efficiency, and the worker's stress level.

[0393] Specifically, you can use Python data analysis libraries such as "Pandas" and "Scikit-learn."

[0394] 3. Building a predictive model

[0395] Based on the analysis results, the server builds a model that predicts future learning progress and work efficiency.

[0396] For example, regression analysis is used to predict learning progress, and time series analysis is applied to predict the work efficiency of a robot.

[0397] 4. Creating a learning plan and work plan

[0398] The server uses the predictive model to generate an individualized learning plan, detailing which subjects to study and when, and a new work plan, which tells the robot which tasks to prioritize.

[0399] Specifically, learning plans are notified to the "learning management system," and work plans are reflected in the "factory management system."

[0400] 5. Monitoring learning and work progress

[0401] As the user and robot actually learn or work, the terminal records their progress in real time and sends it to the server.

[0402] This data will be analyzed again and the plan adjusted as needed.

[0403] 6. Generating and notifying mental health care suggestions

[0404] The server then proposes personalized mental care to users and workers based on the emotion data recognized by the emotion engine and schedule information. Suggestions include short periods of meditation and listening to relaxing music. These suggestions are then sent to the users' and workers' devices.

[0405] As an example of specific suggestions, tired workers might be advised to "meditate for 10 minutes" or "practice deep breathing."

[0406] Specific examples

[0407] For example, based on data collected from the past year's use of a learning application, the server can determine that User A is good at math and science but not so good at history. Based on this, the server can generate a daily study plan consisting of 45 minutes of math, 30 minutes of science, and 60 minutes of history. If the device recognizes a tired expression while studying, it will suggest relaxation meditation and notify the user of this information via a pop-up.

[0408] Prompt Sentence Examples

[0409] Based on the data below, please generate a Python program that will detect the emotions of high-stress workers and provide appropriate mental health care suggestions.

[0410] Data: {"id": 2, "stress_level": 85}

[0411] Tools needed for emotion detection: camera, audio analysis

[0412] Mental care suggestions: Take a break from work, listen to relaxing music, take deep breaths

[0413] The above is an embodiment of the present invention.

[0414] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0415] Step 1:

[0416] The server collects data from the user's device and the factory's production management system. Data collection includes the user's study time, study content, correct answer rate, learning achievement level, robot work data, and worker emotional data. Inputs include user and robot operation data, and emotional data from cameras and voice analysis devices. This data is sent to the server and temporarily stored.

[0417] Step 2:

[0418] The server analyzes the collected data using Python's "Pandas" and "Scikit-learn" as the analysis method. Specifically, it processes and calculates the data to evaluate the user's learning tendency, the robot's work efficiency, and the worker's stress level. All collected data is used as input, and the analysis results are obtained as output.

[0419] Step 3:

[0420] The server builds a predictive model based on the analysis results. This model predicts future learning progress and work efficiency. Regression analysis and time series analysis algorithms are used to build the predictive model. The analysis results are received as input, and a predictive model is generated as output.

[0421] Step 4:

[0422] The server uses the constructed predictive model to generate a study plan for the user and a work plan for the robot. The study plan indicates the user's required study schedule, while the work plan indicates the robot's work priorities. Specifically, the study plan for the user details which subjects should be studied and for how long each day, while the work plan for the robot determines the order in which tasks should be performed. Using the predictive model as input, an individual plan is generated as output.

[0423] Step 5:

[0424] The terminal records the progress of the user or robot as they learn or work in real time and sends it to the server. The progress data record includes timestamps and a list of completed tasks. The real-time progress data is received as input, and the progress record is sent to the server as output.

[0425] Step 6:

[0426] The server analyzes the schedule information of users and workers to identify free time. The schedule information is obtained from the terminal, and calendar data is used for analysis. The server receives the schedule information as input and identifies free time as output.

[0427] Step 7:

[0428] The server uses an emotion engine to recognize the worker's emotional state. The emotion engine analyzes the worker's facial expressions and tone of voice from camera and voice analysis data to determine the worker's emotional state. Emotion data is used as input, and the recognized emotional state is output.

[0429] Step 8:

[0430] The server generates mental health suggestions based on the identified free time and emotional state, such as listening to music for relaxation or practicing meditation. Using free time and emotional state as input, the suggestions are generated as output.

[0431] Step 9:

[0432] The terminal notifies the user or worker of the generated mental health care suggestions by means of a pop-up, voice alert, email, etc. The terminal receives the mental health care suggestions as input and notifies the user or worker as output.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] [Second embodiment]

[0437] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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."

[0449] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Below, we will explain the outline and specific examples of the program for this system.

[0450] System Overview

[0451] 1. Collecting training data

[0452] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[0453] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[0454] 2. Analysis of training data

[0455] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[0456] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[0457] 3. Building a predictive model

[0458] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[0459] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[0460] 4. Generate a learning plan

[0461] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[0462] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0463] 5. Monitoring your learning progress

[0464] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[0465] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[0466] 6. Analyzing Schedule Information

[0467] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[0468] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[0469] 7. Generating mental health care proposals

[0470] The server then provides personalized mental health care suggestions to the user based on the identified free time, which are customized based on past history and user preferences.

[0471] Example: The server suggests to user A that they "take a short meditation" or "listen to relaxing music" between 3:00 and 4:00 PM.

[0472] 8. Notice to Users

[0473] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[0474] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[0475] In this way, this system generates an optimal study plan based on the user's study data, monitors progress, and provides psychological support at appropriate times, thereby improving the user's study efficiency and persistence.

[0476] The processing flow will be explained below.

[0477] Step 1:

[0478] Users begin studying through their devices, and data such as study content, start time, end time, and correct answer rate are automatically recorded.

[0479] Step 2:

[0480] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[0481] Step 3:

[0482] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[0483] Step 4:

[0484] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[0485] Step 5:

[0486] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[0487] Step 6:

[0488] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[0489] Step 7:

[0490] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[0491] Step 8:

[0492] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[0493] Step 9:

[0494] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[0495] Step 10:

[0496] The server runs an algorithm to suggest mental health care based on the user's free time, and the suggestions are customized based on the user's preferences and past history.

[0497] Step 11:

[0498] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, audio alert, or email.

[0499] Step 12:

[0500] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[0501] Example 1

[0502] 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."

[0503] In modern society, there is a demand for specific plans and support to help individual learners continue their studies efficiently and sustainably. However, many systems only provide general learning plans, making it difficult to provide individual learning plans tailored to individual learning tendencies and schedules. It is also difficult to properly track learning progress and provide psychological support. This creates challenges that prevent learners from progressing efficiently and hinders improvement in learning outcomes.

[0504] 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.

[0505] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental health care based on the free time, means for notifying the user of the suggestions, means for recording the learning progress in real time and transmitting the recording results to the server, means for applying a machine learning algorithm to improve the user's learning efficiency based on the collected and analyzed data, and means for customizing mental health care suggestions based on the user's past history and preferences. This allows the server to provide appropriate individual learning plans and psychological care, enabling the user to progress in their studies efficiently and sustainably.

[0506] "Collected user learning data" is data recorded when a user engages in learning activities, including study time, study content, correct answer rate, and learning achievement level.

[0507] "Means for analyzing" means a set of machine learning algorithms and related software for evaluating the collected learning data and identifying the user's learning trends and progress.

[0508] A "means for constructing a predictive model" is a configuration of software and algorithms for generating a model for predicting a user's future learning performance based on the analyzed learning data.

[0509] The "means for generating personalized learning plans" is a system that uses predictive models to generate detailed learning schedules and curricula tailored to the individual learning needs of each user.

[0510] The "means for monitoring learning progress" refers to a device and a program for recording the learning activities actually performed by the user in real time, transmitting the data to a server, and supervising the progress against the learning plan.

[0511] The "means for identifying free time" is software that analyzes the user's schedule information and identifies free time that can be used for study or mental care.

[0512] The "means for suggesting mental care" is a system that suggests activities that promote relaxation and concentration suitable for a specified free time based on the user's preferences and past history.

[0513] The "means for notifying the user of suggestions" refers to a device or program for notifying the user of mental health care suggestions from the server via a pop-up, a voice alert, an email, or the like.

[0514] "Means for recording learning progress in real time and transmitting the recorded results to a server" refers to a terminal and software configuration for recording a user's learning activities in real time and automatically transmitting the data to a server.

[0515] "Means for applying machine learning algorithms" refers to programs and models for utilizing machine learning techniques to improve learning efficiency based on collected and analyzed user learning data.

[0516] "Means for customizing mental health care suggestions based on the user's past history and preferences" is a system for suggesting optimal mental health care activities based on the user's past behavioral history and registered preferences.

[0517] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve a user's learning efficiency. The following describes an embodiment of this system.

[0518] The main components of the system include a server, user terminals, and various software for data analysis. Specific software used includes machine learning libraries such as Python, TensorFlow, and PyTorch. The server also has a database that stores and manages user learning data.

[0519] The server collects learning data from the user's device. This learning data includes learning time, learning content, correct answer rate, and learning achievement level. The data collected by the device is sent to the server in real time, and the server stores it in a database.

[0520] The server then analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress. For example, the server can identify the user's strengths and weaknesses and reflect this in their study plan.

[0521] Based on the analysis results, the server builds a predictive model using TensorFlow and PyTorch to predict future learning performance based on the user's past learning data and current progress. This model forms the basis for planning future learning schedules.

[0522] The server uses the predictive model to generate a personalized study plan for each user, including specific subjects and study times, designed to maximize the user's learning efficiency. For example, the server generates a two-week schedule for User A, with 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0523] As the user studies, the device records their progress in real time and sends it to the server, which then monitors the progress of the study plan and adjusts it as needed.

[0524] The server also analyzes the user's schedule information to identify free time that cannot be used for studying. Once free time is identified, the server makes personalized suggestions for the user's mental health care. These suggestions are customized based on past history and the user's preferences. For example, the server might suggest to User A that they "do a short meditation session" or "listen to relaxing music" between 3:00 and 4:00 PM.

[0525] The server sends mental health advice to the user via a pop-up notification, voice alert, or email. For example, at 3 p.m., the device displays a pop-up notification prompting the user to listen to relaxing music.

[0526] Some examples of specific prompts include:

[0527] "Based on User A's learning data, please analyze his math accuracy rate over the past year and predict the amount of study time he will need in the next two weeks."

[0528] According to the present invention, the user can study efficiently and continuously, and can receive mental health care at an appropriate time.

[0529] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0530] Step 1:

[0531] The server collects learning data from the user's device. The device automatically sends the data to the server when the user finishes learning. The collected data includes learning time, learning content, correct answer rate, and learning achievement. The input is a record of the user's learning activities, and the output is learning data stored on the server.

[0532] Specific operation: The device records data on the user's math study for 45 minutes, with an 80% accuracy rate. When the user finishes studying, the device sends this data to the server, which stores it in a database.

[0533] Step 2:

[0534] The server analyzes the collected learning data. For the analysis, Python is used to evaluate the user's learning tendency and progress using machine learning algorithms. The input is the learning data collected in the previous step, and the output is the analysis results.

[0535] Specific operation: The server analyzes the training data using the Python library and determines that User A is good at math but not so good at history.

[0536] Step 3:

[0537] The server builds a predictive model based on the analysis results. This model is built using TensorFlow and predicts future learning performance. The input is the analysis results, and the output is the predictive model.

[0538] Specific operation: Based on User A's past learning data, the server uses TensorFlow to build a model that predicts how much learning will be required in the next two weeks.

[0539] Step 4:

[0540] The server uses the predictive model to generate a personalized learning plan, including specific learning content and time. The input is the predictive model, and the output is the user's personalized learning plan.

[0541] Specific operation: Based on the predictive model, the server generates a detailed two-week schedule for User A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history study.

[0542] Step 5:

[0543] The device records the user's progress in real time as they study and sends it to the server. The input is the user's study activity, and the output is the recorded study data sent to the server.

[0544] How it works: When a user starts studying, the device records the study time and content in real time. When the user finishes studying, the device sends the data to the server, which then updates the progress.

[0545] Step 6:

[0546] The server analyzes the user's schedule information and identifies available free time. The schedule information is obtained from the terminal. The input is the schedule information, and the output is the available free time.

[0547] What happens: The server collects and analyzes data from User A's calendar application. It determines that there is free time between 3:00 PM and 4:00 PM.

[0548] Step 7:

[0549] The server then provides personalized mental health care suggestions based on the identified free time. The suggestions are customized based on the user's past history and preferences. The inputs are free time and the user's past history and preferences, and the output is mental health care suggestions.

[0550] Specific operation: Based on User A's past history, the server suggests a short meditation session or listening to relaxing music between 3:00 and 4:00 PM.

[0551] Step 8:

[0552] The terminal notifies the user of the mental health care suggestions from the server. The notification can be done by a pop-up, a voice alert, or an email. The input is the mental health care suggestion, and the output is the information to be notified to the user.

[0553] What it does: At 3 PM, the device will display a pop-up notification, prompting the user to listen to relaxing music.

[0554] (Application example 1)

[0555] 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."

[0556] In today's learning environment, analyzing individual learning data and providing appropriate learning plans is essential for users to study efficiently and effectively. However, previous systems have not been able to provide personalized care that takes into account each user's individual learning tendencies and progress. Furthermore, there are limited ways for learners to receive psychological support at the appropriate time, which can lead to reduced learning efficiency. Furthermore, real-time content delivery using smart devices remains a challenge.

[0557] 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.

[0558] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for providing appropriate learning content and mental care content to improve learning efficiency based on the learning data, and means for delivering content in real time via a head-mounted display or a smartphone.

[0559] This will enable the provision of optimal learning plans and mental care based on individual users' learning data, improving learning efficiency and mental health. In addition, real-time content delivery using smart devices will make the learning experience more flexible and effective.

[0560] "Collection" refers to the act of collecting user learning data from the terminal to a central server.

[0561] "Analysis" is the process of evaluating a user's learning trends and progress based on collected learning data.

[0562] A "predictive model" is a mathematical or statistical model for predicting a user's future learning progress based on the analysis results.

[0563] A "study plan" is a schedule generated using a predictive model that details a user's individual learning content and time allocation.

[0564] "Study progress" is a concept that refers to the progress and level of achievement of a user as they proceed with their actual studies.

[0565] "Schedule information" is data that indicates the user's schedule and time allocation. This information is obtained from a calendar application or the like.

[0566] "Free time" is a period of time that is identified from schedule information and is free to be used for study or other activities.

[0567] "Mental health care" is a concept that refers to suggesting activities and content to improve users' mental health.

[0568] "Real-time" refers to a situation in which data or content is processed and delivered immediately, without delay.

[0569] "Content delivery" is the act of delivering digital content such as music, video, and text for learning and mental health care to user devices.

[0570] "Smart devices" refer to information processing devices, including mobile terminals and wearable devices that can connect to the Internet.

[0571] The system for implementing this invention collects and analyzes user learning data and provides psychological care. This system mainly consists of a server, a user terminal, and a smart device (e.g., a smartphone or a head-mounted display).

[0572] 1. Collecting training data

[0573] The server collects learning data from users' terminals and smart devices. This learning data includes learning time, learning content, correct answer rate, and learning achievement. Specifically, the data is collected in real time using Firebase and Google Analytics and sent to the cloud.

[0574] 2. Analysis of training data

[0575] The server analyzes the collected learning data using machine learning algorithms (e.g., TensorFlow), which evaluates the user's learning trends and progress and identifies their strengths and weaknesses.

[0576] 3. Building a predictive model

[0577] Based on the analysis results, the server builds a model to predict the user's learning progress. This model uses TensorFlow to predict the user's future learning status.

[0578] 4. Generate a learning plan

[0579] The server uses the built predictive model to generate a personalized study plan for the user, detailing which subjects should be studied and for how many hours.

[0580] 5. Monitoring your learning progress

[0581] The server records the user's progress in real time as they study and stores it in the cloud via Firebase, allowing the user to monitor their progress in their study plan.

[0582] 6. Analyzing Schedule Information

[0583] The server identifies available study time by analyzing the user's schedule information, which is obtained from the user's calendar application.

[0584] 7. Generating mental health care proposals

[0585] The server then provides personalized mental health suggestions based on the identified free time. These suggestions are customized based on past history and user preferences. Examples include short meditation sessions or listening to relaxing music.

[0586] 8. Notice to Users

[0587] The server sends mental health care suggestions as push notifications to the user's terminal or smart device, allowing the user to receive mental health care at the appropriate time.

[0588] As a concrete example, consider a user studying math using a smartphone app. After completing 45 minutes of studying, the app sends data to a server. The server analyzes the data, determines that the user is tired, and suggests a meditation session.

[0589] Prompt Sentence Examples

[0590] text

[0591] User A completed 45 minutes of math study today but seems a little tired. You suggest a short meditation session from 3:00 PM - 4:00 PM. After the meditation, relaxation music will begin playing.

[0592] The system allows users to receive optimal learning plans and mental health care to improve learning efficiency, and makes the learning experience flexible and effective by delivering content in real time using smart devices.

[0593] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0594] Step 1:

[0595] The server collects learning data from users' terminals and smart devices.

[0596] Input: Study time, study content, correct answer rate, learning achievement

[0597] Output: Collected training data

[0598] What it does: It uses Firebase and Google Analytics to send data generated by users as they learn to the cloud in real time.

[0599] Step 2:

[0600] The server analyzes the collected learning data.

[0601] Input: Collected training data

[0602] Output: User's learning tendency and progress

[0603] How it works: It uses machine learning algorithms such as TensorFlow to analyze data and identify the user's strengths and weaknesses.

[0604] Step 3:

[0605] The server builds a predictive model based on the analysis results.

[0606] Input: User's learning habits and progress

[0607] Output: Learning progress prediction model

[0608] Specific operation: Using TensorFlow, we build a model that uses the analysis results to predict the user's future learning progress.

[0609] Step 4:

[0610] The server uses the predictive model to generate a personalized learning plan.

[0611] Input: Learning progress prediction model

[0612] Output: Individualized Learning Plan

[0613] Specific behavior: Based on the user's strong and weak subjects, a schedule is generated detailing which subjects should be studied and for how long.

[0614] Step 5:

[0615] The server monitors the user's progress in real time as they actually study.

[0616] Input: User training data

[0617] Output: Learning progress

[0618] What it does: Stores and monitors user learning progress in the cloud through Firebase.

[0619] Step 6:

[0620] The server analyzes the user's schedule information.

[0621] Input: User's schedule information

[0622] Output: Identifying free time

[0623] What it does: Retrieves schedule data from a calendar application and parses it to identify available times.

[0624] Step 7:

[0625] The server generates psychological care suggestions based on the identified free time.

[0626] Input: Availability, user preferences and past history

[0627] Output: Mental care suggestions

[0628] What it does: Creates a plan to provide care, such as a short meditation session or listening to relaxing music, based on the user's past history and preferences.

[0629] Step 8:

[0630] The server notifies the user's terminal or smart device of mental care suggestions.

[0631] Input: Mental care suggestions

[0632] Output: User notification

[0633] Specific behavior: Use the push notification function of the smart device to notify the user of care suggestions. Specifically, the following prompt is displayed: "User A completed 45 minutes of math study today, but seems a little tired. We suggest a short meditation session from 3:00 PM to 4:00 PM. After the meditation, relaxation music will begin playing."

[0634] 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.

[0635] This invention is a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Furthermore, this system uses an emotion engine to recognize the user's emotions and customizes the mental health care proposals more effectively.

[0636] System Overview

[0637] 1. Collecting training data

[0638] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[0639] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[0640] 2. Analysis of training data

[0641] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[0642] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[0643] 3. Building a predictive model

[0644] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[0645] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[0646] 4. Generate a learning plan

[0647] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[0648] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0649] 5. Monitoring your learning progress

[0650] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[0651] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[0652] 6. Analyzing Schedule Information

[0653] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[0654] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[0655] 7. Emotion Recognition with Emotion Engine

[0656] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes the data and recognizes the user's emotional state.

[0657] Example: From User A's facial expressions and tone of voice as he / she progresses with his / her studies, the emotion engine recognizes that User A is feeling tired or stressed.

[0658] 8. Generating mental health care proposals

[0659] The server then proposes personalized mental health care to the user based on the identified free time and the emotional data recognized by the emotion engine.The proposals are customized based on the user's past history and preferences.

[0660] Example: The server suggests a short meditation session or listening to relaxing music for User A's free time between 3:00 and 4:00 PM. Because the server recognizes that User A is feeling tired and stressed, the suggestions include activities that have a high relaxation effect.

[0661] 9. Notice to Users

[0662] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[0663] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[0664] This system is designed to improve users' learning efficiency and mental health by conducting a comprehensive process from analyzing learning data to building predictive models, generating and monitoring learning plans, recognizing users' emotions using an emotion engine, and generating and notifying them of mental care suggestions.

[0665] The processing flow will be explained below.

[0666] Step 1:

[0667] Users begin studying through their device, which automatically records data such as the study content, start time, end time, and correct answer rate.

[0668] Step 2:

[0669] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[0670] Step 3:

[0671] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[0672] Step 4:

[0673] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[0674] Step 5:

[0675] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[0676] Step 6:

[0677] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[0678] Step 7:

[0679] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[0680] Step 8:

[0681] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[0682] Step 9:

[0683] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[0684] Step 10:

[0685] The device captures the user's facial expressions, voice tone, and behavioral data, which are then transmitted to a server in real time.

[0686] Step 11:

[0687] The server analyzes the received facial expressions, voice tone, and behavioral data using an emotion engine to recognize the user's emotional state.

[0688] Step 12:

[0689] The server generates psychological care suggestions based on the user's free time and recognized emotional data, and these suggestions are customized based on the user's preferences and past history.

[0690] Step 13:

[0691] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, voice alert, or email.

[0692] Step 14:

[0693] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[0694] Example 2

[0695] 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."

[0696] In recent years, many systems have been developed to improve learners' learning outcomes, but few systems not only generate efficient learning plans but also take into consideration the learner's mental health. In particular, there is a demand for systems that can recognize the user's emotional state in real time and suggest appropriate mental care. To solve this problem, a system is needed that can analyze learning data, monitor progress, recognize emotions, and suggest individual care in an integrated manner.

[0697] 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.

[0698] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, emotion recognition means for recognizing the user's emotional state, means for personalized mental care suggestions based on the emotional state recognized by the emotion recognition means, and means for notifying the user of the suggestions. This not only improves the user's learning efficiency but also maintains their mental health while studying, thereby improving the overall quality of the learning experience.

[0699] "Study data" refers to information about a user's learning activities, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[0700] A "predictive model" is a computational model constructed to predict a user's future learning progress based on collected and analyzed learning data.

[0701] A "study plan" is a schedule generated using a predictive model that details which subjects a user should study and when.

[0702] "Schedule information" is information related to the user's time management, and mainly includes plans recorded on a calendar or timetable.

[0703] "Free time" is identified from the user's schedule information and refers to unallocated time that can be used for study or mental health care.

[0704] "Mental care" refers to suggestions and activities to maintain and improve the user's mental health, with the aim of relaxation and stress reduction.

[0705] "Emotion recognition means" refers to functions and technologies for analyzing a user's facial expressions, voice tone, and behavioral data to recognize the user's emotional state.

[0706] "Personalized recommendations" refers to providing individually optimized mental health recommendations based on the user's emotional state, past history, and preferences.

[0707] This invention is a learning support system for improving a user's learning efficiency and mental health. This system collects and analyzes learning data, builds a predictive model, generates an individual learning plan, monitors progress, recognizes emotions, and provides mental health care suggestions in a series of steps.

[0708] The system mainly consists of a server, a terminal, and a user. A specific embodiment of the system is shown below.

[0709] The server first collects learning data from the user's device. The collected learning data includes study time, learning content, correct answer rate, and learning achievement. For example, if a user achieves 80% correct answers on a math test, the data is sent to the server.

[0710] Next, the server analyzes the collected learning data using machine learning algorithms. The purpose of the analysis is to identify the user's learning tendencies, strong and weak subjects. Specifically, the data is analyzed using clustering and classifiers. The server analyzes the user's data and determines, for example, that the user is good at math and science, but weak at history.

[0711] Based on the analysis results, the server builds a model to predict the user's learning progress. This model predicts future study time and effort based on past data. For example, it generates a model that says, "You'll need 10 hours of math and 8 hours of science in the next two weeks."

[0712] Based on the predictive model, the server generates an individualized study plan, detailing which subjects to study and when to study them. The server generates a schedule of 45 minutes of math, 30 minutes of science, and 60 minutes of history each day for the next two weeks.

[0713] The device records the user's progress in real time as they study and sends the data to the server. For example, if a user studies mathematics on the device for 30 minutes, the data is immediately sent to the server and the learning progress is updated. In this way, the server monitors the progress of the learning plan.

[0714] Additionally, the server analyzes the user's schedule information, typically obtained from a calendar or timetable, to identify available study time. For example, the server may identify an available time slot between 3:00 PM and 4:00 PM.

[0715] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, if the user looks anxious, the emotion engine detects "stress."

[0716] The server then suggests personalized mental health care activities based on the identified free time and the emotional data recognized by the emotion engine. The suggestions are customized based on the user's past history and preferences. For example, it suggests specific activities such as "relieve stress by listening to relaxing music at 3 p.m."

[0717] Finally, the device notifies the user of the mental health care suggestions from the server via a pop-up, a voice alert, or an email. For example, the device may display a pop-up notification to the user at 3:00 PM, prompting them to start their mental health care activities.

[0718] In this way, the system of the present invention improves the user's learning efficiency and mental health through a series of processes, thereby enhancing the quality of the overall learning experience.

[0719] Example prompt sentence:

[0720] "Please explain how you can analyze a user's emotional state in real time and optimize their learning schedule."

[0721] "Please tell me how to design a system that integrates user learning data and emotional data to personalize mental health care suggestions."

[0722] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0723] Step 1:

[0724] Data collection

[0725] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[0726] Input: Data from the user's learning app (e.g., study time and correct answer rate)

[0727] Output: Training data stored on the server

[0728] Specific operation: When a user scores 80% on a math test, the data is sent from the device to the server.

[0729] Step 2:

[0730] Data analysis

[0731] The server analyzes the collected learning data using machine learning algorithms.

[0732] Input: The training data collected in step 1

[0733] Output: User's learning tendency, favorite subjects, and favorite subjects (e.g., user is good at math, but not good at history)

[0734] What it does: The server analyzes the data using clustering and classifiers to determine that the user is good at math and science, but bad at history.

[0735] Step 3:

[0736] Building predictive models

[0737] Based on the analysis results, the server builds a model to predict the user's future learning progress.

[0738] Input: Analysis result from step 2

[0739] Output: A model that predicts future study time and effort (e.g., 10 hours of math and 8 hours of science needed in the next two weeks)

[0740] Specific operation: The server generates a model that predicts future study time based on past data.

[0741] Step 4:

[0742] Generate a lesson plan

[0743] The server generates an individualized learning plan based on the predictive model.

[0744] Input: Predictive model from step 3

[0745] Output: Individualized learning plan (e.g., 45 minutes of math, 30 minutes of science, and 60 minutes of history each day)

[0746] Specific operation: The server generates the user's schedule for the next two weeks and sends it to the device.

[0747] Step 5:

[0748] Monitoring learning progress

[0749] As the user actually studies, the device records their progress in real time and sends it to the server.

[0750] Input: The actual study time and content of the user

[0751] Output: Learning progress data sent to the server

[0752] What it does: When a user studies math on their device for 30 minutes, the data is immediately sent to the server and their learning progress is updated.

[0753] Step 6:

[0754] Schedule information analysis

[0755] The server analyzes the user's schedule information and identifies free time that can be used for studying.

[0756] Input: User's schedule information (e.g., calendar app)

[0757] Output: Identify available times (e.g., available times between 3:00 PM and 4:00 PM)

[0758] What happens: The server analyzes the calendar app data to identify free time.

[0759] Step 7:

[0760] emotion recognition

[0761] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes it.

[0762] Input: User facial expressions, voice tone, and behavioral data

[0763] Output: Recognizing the user's emotional state (e.g., recognizing that the user is stressed)

[0764] How it works: The user uses the device's camera and microphone to capture facial expressions and voice data in real time, which is then sent to the server and analyzed by the emotion engine.

[0765] Step 8:

[0766] Generating mental health care proposals

[0767] The server then proposes personalized mental care for the user based on the identified free time and the emotional data recognized by the emotion engine.

[0768] Input: Free time from step 6, Emotion data recognized from step 7

[0769] Output: Personalized mental health recommendations (e.g., listening to relaxing music at 3 PM)

[0770] How it works: The server suggests listening to relaxing music or meditating based on the user's free time and current emotional state.

[0771] Step 9:

[0772] User Notification

[0773] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[0774] Input: Mental care suggestions from the server

[0775] Output: Notify user (e.g., show a popup notification at 3 PM)

[0776] What it does: The device displays a pop-up notification to the user at 3 PM, encouraging them to start mental health activities.

[0777] (Application example 2)

[0778] 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."

[0779] Conventional learning support systems have had the challenge of making it difficult to simultaneously improve users' learning efficiency and mental health. Similar challenges exist in managing the efficiency of robots and human workers in factories. Specifically, there is a lack of an overall system that can analyze the work data of robots and workers individually to improve efficiency while also providing mental care, raising concerns about reduced work efficiency and reduced work performance due to stress.

[0780] The identification process by the identification 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 analyzing collected user learning data, means for constructing a prediction model based on the learning data, means for generating an individual learning plan using the prediction model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for collecting and analyzing robot work data, means for generating a new work plan based on the robot's work efficiency, means for recognizing the worker's emotional state and suggesting mental care, and means for notifying the worker of the suggestion. This makes it possible to provide mental care tailored to each individual's emotional state while improving the learning and work efficiency of users and workers.

[0781] A "server" is a computer that provides services to other computers over a network.

[0782] "Study data" is information related to the user's study, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[0783] A "predictive model" is a model for predicting future learning progress and the amount of learning required based on collected data.

[0784] A "study plan" is a plan that details a user's individual study schedule and content based on a predictive model.

[0785] "Study progress" refers to the progress of how far the user has actually progressed in their studies.

[0786] "Schedule information" refers to calendar information and time management data that includes the user's daily schedule.

[0787] "Free time" is a time period extracted from the user's schedule information that can be used for studying or relaxing.

[0788] "Mental care" refers to suggestions and activities for relaxation and stress relief provided to maintain the user's mental health.

[0789] "Notification" refers to conveying information to the user, and is done using means such as a pop-up, audio alert, or email.

[0790] "Work data" is information about work performed by robots and workers in a factory, and includes information about efficiency and progress.

[0791] "Emotional state" refers to the worker's current mental state and is recognized from facial expressions, tone of voice, and behavioral data.

[0792] A "work plan" is a plan that indicates an efficient work schedule and content, newly generated based on the robot's work efficiency.

[0793] The present invention provides a system for improving the work efficiency of robots working in factories and the mental health of human workers. The following describes an embodiment of this system.

[0794] System program generation

[0795] The system can be implemented using Python, and its main processes include data collection, data analysis, predictive model construction, learning plan generation, learning progress monitoring, emotional state recognition, and mental health care suggestion generation and notification.

[0796] Processing Description

[0797] 1. Data Collection

[0798] The server collects user learning data, robot work data, and worker emotion data. The learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[0799] Specifically, training data is collected from a training application, and work data is collected from the factory's production management system. Emotion data is collected using cameras and voice analysis. Specific hardware examples include the OpenVINO platform for emotion detection and the Google Cloud Speech-to-Text API for voice analysis.

[0800] 2. Data Analysis

[0801] The server uses machine learning algorithms to analyze the collected data, which in turn evaluates the user's learning habits, the robot's work efficiency, and the worker's stress level.

[0802] Specifically, you can use Python data analysis libraries such as "Pandas" and "Scikit-learn."

[0803] 3. Building a predictive model

[0804] Based on the analysis results, the server builds a model that predicts future learning progress and work efficiency.

[0805] For example, regression analysis is used to predict learning progress, and time series analysis is applied to predict the work efficiency of a robot.

[0806] 4. Creating a learning plan and work plan

[0807] The server uses the predictive model to generate an individualized learning plan, detailing which subjects to study and when, and a new work plan, which tells the robot which tasks to prioritize.

[0808] Specifically, learning plans are notified to the "learning management system," and work plans are reflected in the "factory management system."

[0809] 5. Monitoring learning and work progress

[0810] As the user and robot actually learn or work, the terminal records their progress in real time and sends it to the server.

[0811] This data will be analyzed again and the plan adjusted as needed.

[0812] 6. Generating and notifying mental health care suggestions

[0813] The server then proposes personalized mental care to users and workers based on the emotion data recognized by the emotion engine and schedule information. Suggestions include short periods of meditation and listening to relaxing music. These suggestions are then sent to the users' and workers' devices.

[0814] As an example of specific suggestions, tired workers might be advised to "meditate for 10 minutes" or "practice deep breathing."

[0815] Specific examples

[0816] For example, based on data collected from the past year's use of a learning application, the server can determine that User A is good at math and science but not so good at history. Based on this, the server can generate a daily study plan consisting of 45 minutes of math, 30 minutes of science, and 60 minutes of history. If the device recognizes a tired expression while studying, it will suggest relaxation meditation and notify the user of this information via a pop-up.

[0817] Prompt Sentence Examples

[0818] Based on the data below, please generate a Python program that will detect the emotions of high-stress workers and provide appropriate mental health care suggestions.

[0819] Data: {"id": 2, "stress_level": 85}

[0820] Tools needed for emotion detection: camera, audio analysis

[0821] Mental care suggestions: Take a break from work, listen to relaxing music, take deep breaths

[0822] The above is an embodiment of the present invention.

[0823] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0824] Step 1:

[0825] The server collects data from the user's device and the factory's production management system. Data collection includes the user's study time, study content, correct answer rate, learning achievement level, robot work data, and worker emotional data. Inputs include user and robot operation data, and emotional data from cameras and voice analysis devices. This data is sent to the server and temporarily stored.

[0826] Step 2:

[0827] The server analyzes the collected data using Python's "Pandas" and "Scikit-learn" as the analysis method. Specifically, it processes and calculates the data to evaluate the user's learning tendency, the robot's work efficiency, and the worker's stress level. All collected data is used as input, and the analysis results are obtained as output.

[0828] Step 3:

[0829] The server builds a predictive model based on the analysis results. This model predicts future learning progress and work efficiency. Regression analysis and time series analysis algorithms are used to build the predictive model. The analysis results are received as input, and a predictive model is generated as output.

[0830] Step 4:

[0831] The server uses the constructed predictive model to generate a study plan for the user and a work plan for the robot. The study plan indicates the user's required study schedule, while the work plan indicates the robot's work priorities. Specifically, the study plan for the user details which subjects should be studied and for how long each day, while the work plan for the robot determines the order in which tasks should be performed. Using the predictive model as input, an individual plan is generated as output.

[0832] Step 5:

[0833] The terminal records the progress of the user or robot as they learn or work in real time and sends it to the server. The progress data record includes timestamps and a list of completed tasks. The real-time progress data is received as input, and the progress record is sent to the server as output.

[0834] Step 6:

[0835] The server analyzes the schedule information of users and workers to identify free time. The schedule information is obtained from the terminal, and calendar data is used for analysis. The server receives the schedule information as input and identifies free time as output.

[0836] Step 7:

[0837] The server uses an emotion engine to recognize the worker's emotional state. The emotion engine analyzes the worker's facial expressions and tone of voice from camera and voice analysis data to determine the worker's emotional state. Emotion data is used as input, and the recognized emotional state is output.

[0838] Step 8:

[0839] The server generates mental health suggestions based on the identified free time and emotional state, such as listening to music for relaxation or practicing meditation. Using free time and emotional state as input, the suggestions are generated as output.

[0840] Step 9:

[0841] The terminal notifies the user or worker of the generated mental health care suggestions by means of a pop-up, voice alert, email, etc. The terminal receives the mental health care suggestions as input and notifies the user or worker as output.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] [Third embodiment]

[0846] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0847] 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.

[0848] 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).

[0849] 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.

[0850] 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.

[0851] 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).

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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."

[0858] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Below, we will explain the outline and specific examples of the program for this system.

[0859] System Overview

[0860] 1. Collecting training data

[0861] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[0862] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[0863] 2. Analysis of training data

[0864] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[0865] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[0866] 3. Building a predictive model

[0867] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[0868] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[0869] 4. Generate a learning plan

[0870] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[0871] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0872] 5. Monitoring your learning progress

[0873] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[0874] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[0875] 6. Analyzing Schedule Information

[0876] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[0877] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[0878] 7. Generating mental health care proposals

[0879] The server then provides personalized mental health care suggestions to the user based on the identified free time, which are customized based on past history and user preferences.

[0880] Example: The server suggests to user A that they "take a short meditation" or "listen to relaxing music" between 3:00 and 4:00 PM.

[0881] 8. Notice to Users

[0882] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[0883] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[0884] In this way, this system generates an optimal study plan based on the user's study data, monitors progress, and provides psychological support at appropriate times, thereby improving the user's study efficiency and persistence.

[0885] The processing flow will be explained below.

[0886] Step 1:

[0887] Users begin studying through their devices, and data such as study content, start time, end time, and correct answer rate are automatically recorded.

[0888] Step 2:

[0889] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[0890] Step 3:

[0891] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[0892] Step 4:

[0893] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[0894] Step 5:

[0895] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[0896] Step 6:

[0897] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[0898] Step 7:

[0899] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[0900] Step 8:

[0901] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[0902] Step 9:

[0903] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[0904] Step 10:

[0905] The server runs an algorithm to suggest mental health care based on the user's free time, and the suggestions are customized based on the user's preferences and past history.

[0906] Step 11:

[0907] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, audio alert, or email.

[0908] Step 12:

[0909] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[0910] Example 1

[0911] 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."

[0912] In modern society, there is a demand for specific plans and support to help individual learners continue their studies efficiently and sustainably. However, many systems only provide general learning plans, making it difficult to provide individual learning plans tailored to individual learning tendencies and schedules. It is also difficult to properly track learning progress and provide psychological support. This creates challenges that prevent learners from progressing efficiently and hinders improvement in learning outcomes.

[0913] 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.

[0914] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental health care based on the free time, means for notifying the user of the suggestions, means for recording the learning progress in real time and transmitting the recording results to the server, means for applying a machine learning algorithm to improve the user's learning efficiency based on the collected and analyzed data, and means for customizing mental health care suggestions based on the user's past history and preferences. This allows the server to provide appropriate individual learning plans and psychological care, enabling the user to progress in their studies efficiently and sustainably.

[0915] "Collected user learning data" is data recorded when a user engages in learning activities, including study time, study content, correct answer rate, and learning achievement level.

[0916] "Means for analyzing" means a set of machine learning algorithms and related software for evaluating the collected learning data and identifying the user's learning trends and progress.

[0917] A "means for constructing a predictive model" is a configuration of software and algorithms for generating a model for predicting a user's future learning performance based on the analyzed learning data.

[0918] The "means for generating personalized learning plans" is a system that uses predictive models to generate detailed learning schedules and curricula tailored to the individual learning needs of each user.

[0919] The "means for monitoring learning progress" refers to a device and a program for recording the learning activities actually performed by the user in real time, transmitting the data to a server, and supervising the progress against the learning plan.

[0920] The "means for identifying free time" is software that analyzes the user's schedule information and identifies free time that can be used for study or mental care.

[0921] The "means for suggesting mental care" is a system that suggests activities that promote relaxation and concentration suitable for a specified free time based on the user's preferences and past history.

[0922] The "means for notifying the user of suggestions" refers to a device or program for notifying the user of mental health care suggestions from the server via a pop-up, a voice alert, an email, or the like.

[0923] "Means for recording learning progress in real time and transmitting the recorded results to a server" refers to a terminal and software configuration for recording a user's learning activities in real time and automatically transmitting the data to a server.

[0924] "Means for applying machine learning algorithms" refers to programs and models for utilizing machine learning techniques to improve learning efficiency based on collected and analyzed user learning data.

[0925] "Means for customizing mental health care suggestions based on the user's past history and preferences" is a system for suggesting optimal mental health care activities based on the user's past behavioral history and registered preferences.

[0926] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve a user's learning efficiency. The following describes an embodiment of this system.

[0927] The main components of the system include a server, user terminals, and various software for data analysis. Specific software used includes machine learning libraries such as Python, TensorFlow, and PyTorch. The server also has a database that stores and manages user learning data.

[0928] The server collects learning data from the user's device. This learning data includes learning time, learning content, correct answer rate, and learning achievement level. The data collected by the device is sent to the server in real time, and the server stores it in a database.

[0929] The server then analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress. For example, the server can identify the user's strengths and weaknesses and reflect this in their study plan.

[0930] Based on the analysis results, the server builds a predictive model using TensorFlow and PyTorch to predict future learning performance based on the user's past learning data and current progress. This model forms the basis for planning future learning schedules.

[0931] The server uses the predictive model to generate a personalized study plan for each user, including specific subjects and study times, designed to maximize the user's learning efficiency. For example, the server generates a two-week schedule for User A, with 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[0932] As the user studies, the device records their progress in real time and sends it to the server, which then monitors the progress of the study plan and adjusts it as needed.

[0933] The server also analyzes the user's schedule information to identify free time that cannot be used for studying. Once free time is identified, the server makes personalized suggestions for the user's mental health care. These suggestions are customized based on past history and the user's preferences. For example, the server might suggest to User A that they "do a short meditation session" or "listen to relaxing music" between 3:00 and 4:00 PM.

[0934] The server sends mental health advice to the user via a pop-up notification, voice alert, or email. For example, at 3 p.m., the device displays a pop-up notification prompting the user to listen to relaxing music.

[0935] Some examples of specific prompts include:

[0936] "Based on User A's learning data, please analyze his math accuracy rate over the past year and predict the amount of study time he will need in the next two weeks."

[0937] According to the present invention, the user can study efficiently and continuously, and can receive mental health care at an appropriate time.

[0938] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0939] Step 1:

[0940] The server collects learning data from the user's device. The device automatically sends the data to the server when the user finishes learning. The collected data includes learning time, learning content, correct answer rate, and learning achievement. The input is a record of the user's learning activities, and the output is learning data stored on the server.

[0941] Specific operation: The device records data on the user's math study for 45 minutes, with an 80% accuracy rate. When the user finishes studying, the device sends this data to the server, which stores it in a database.

[0942] Step 2:

[0943] The server analyzes the collected learning data. For the analysis, Python is used to evaluate the user's learning tendency and progress using machine learning algorithms. The input is the learning data collected in the previous step, and the output is the analysis results.

[0944] Specific operation: The server analyzes the training data using the Python library and determines that User A is good at math but not so good at history.

[0945] Step 3:

[0946] The server builds a predictive model based on the analysis results. This model is built using TensorFlow and predicts future learning performance. The input is the analysis results, and the output is the predictive model.

[0947] Specific operation: Based on User A's past learning data, the server uses TensorFlow to build a model that predicts how much learning will be required in the next two weeks.

[0948] Step 4:

[0949] The server uses the predictive model to generate a personalized learning plan, including specific learning content and time. The input is the predictive model, and the output is the user's personalized learning plan.

[0950] Specific operation: Based on the predictive model, the server generates a detailed two-week schedule for User A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history study.

[0951] Step 5:

[0952] The device records the user's progress in real time as they study and sends it to the server. The input is the user's study activity, and the output is the recorded study data sent to the server.

[0953] How it works: When a user starts studying, the device records the study time and content in real time. When the user finishes studying, the device sends the data to the server, which then updates the progress.

[0954] Step 6:

[0955] The server analyzes the user's schedule information and identifies available free time. The schedule information is obtained from the terminal. The input is the schedule information, and the output is the available free time.

[0956] What happens: The server collects and analyzes data from User A's calendar application. It determines that there is free time between 3:00 PM and 4:00 PM.

[0957] Step 7:

[0958] The server then provides personalized mental health care suggestions based on the identified free time. The suggestions are customized based on the user's past history and preferences. The inputs are free time and the user's past history and preferences, and the output is mental health care suggestions.

[0959] Specific operation: Based on User A's past history, the server suggests a short meditation session or listening to relaxing music between 3:00 and 4:00 PM.

[0960] Step 8:

[0961] The terminal notifies the user of the mental health care suggestions from the server. The notification can be done by a pop-up, a voice alert, or an email. The input is the mental health care suggestion, and the output is the information to be notified to the user.

[0962] What it does: At 3 PM, the device will display a pop-up notification, prompting the user to listen to relaxing music.

[0963] (Application example 1)

[0964] 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."

[0965] In today's learning environment, analyzing individual learning data and providing appropriate learning plans is essential for users to study efficiently and effectively. However, previous systems have not been able to provide personalized care that takes into account each user's individual learning tendencies and progress. Furthermore, there are limited ways for learners to receive psychological support at the appropriate time, which can lead to reduced learning efficiency. Furthermore, real-time content delivery using smart devices remains a challenge.

[0966] 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.

[0967] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for providing appropriate learning content and mental care content to improve learning efficiency based on the learning data, and means for delivering content in real time via a head-mounted display or a smartphone.

[0968] This will enable the provision of optimal learning plans and mental care based on individual users' learning data, improving learning efficiency and mental health. In addition, real-time content delivery using smart devices will make the learning experience more flexible and effective.

[0969] "Collection" refers to the act of collecting user learning data from the terminal to a central server.

[0970] "Analysis" is the process of evaluating a user's learning trends and progress based on collected learning data.

[0971] A "predictive model" is a mathematical or statistical model for predicting a user's future learning progress based on the analysis results.

[0972] A "study plan" is a schedule generated using a predictive model that details a user's individual learning content and time allocation.

[0973] "Study progress" is a concept that refers to the progress and level of achievement of a user as they proceed with their actual studies.

[0974] "Schedule information" is data that indicates the user's schedule and time allocation. This information is obtained from a calendar application or the like.

[0975] "Free time" is a period of time that is identified from schedule information and is free to be used for study or other activities.

[0976] "Mental health care" is a concept that refers to suggesting activities and content to improve users' mental health.

[0977] "Real-time" refers to a situation in which data or content is processed and delivered immediately, without delay.

[0978] "Content delivery" is the act of delivering digital content such as music, video, and text for learning and mental health care to user devices.

[0979] "Smart devices" refer to information processing devices, including mobile terminals and wearable devices that can connect to the Internet.

[0980] The system for implementing this invention collects and analyzes user learning data and provides psychological care. This system mainly consists of a server, a user terminal, and a smart device (e.g., a smartphone or a head-mounted display).

[0981] 1. Collecting training data

[0982] The server collects learning data from users' terminals and smart devices. This learning data includes learning time, learning content, correct answer rate, and learning achievement. Specifically, the data is collected in real time using Firebase and Google Analytics and sent to the cloud.

[0983] 2. Analysis of training data

[0984] The server analyzes the collected learning data using machine learning algorithms (e.g., TensorFlow), which evaluates the user's learning trends and progress and identifies their strengths and weaknesses.

[0985] 3. Building a predictive model

[0986] Based on the analysis results, the server builds a model to predict the user's learning progress. This model uses TensorFlow to predict the user's future learning status.

[0987] 4. Generate a learning plan

[0988] The server uses the built predictive model to generate a personalized study plan for the user, detailing which subjects should be studied and for how many hours.

[0989] 5. Monitoring your learning progress

[0990] The server records the user's progress in real time as they study and stores it in the cloud via Firebase, allowing the user to monitor their progress in their study plan.

[0991] 6. Analyzing Schedule Information

[0992] The server identifies available study time by analyzing the user's schedule information, which is obtained from the user's calendar application.

[0993] 7. Generating mental health care proposals

[0994] The server then provides personalized mental health suggestions based on the identified free time. These suggestions are customized based on past history and user preferences. Examples include short meditation sessions or listening to relaxing music.

[0995] 8. Notice to Users

[0996] The server sends mental health care suggestions as push notifications to the user's terminal or smart device, allowing the user to receive mental health care at the appropriate time.

[0997] As a concrete example, consider a user studying math using a smartphone app. After completing 45 minutes of studying, the app sends data to a server. The server analyzes the data, determines that the user is tired, and suggests a meditation session.

[0998] Prompt Sentence Examples

[0999] text

[1000] User A completed 45 minutes of math study today but seems a little tired. You suggest a short meditation session from 3:00 PM - 4:00 PM. After the meditation, relaxation music will begin playing.

[1001] The system allows users to receive optimal learning plans and mental health care to improve learning efficiency, and makes the learning experience flexible and effective by delivering content in real time using smart devices.

[1002] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1003] Step 1:

[1004] The server collects learning data from users' terminals and smart devices.

[1005] Input: Study time, study content, correct answer rate, learning achievement

[1006] Output: Collected training data

[1007] What it does: It uses Firebase and Google Analytics to send data generated by users as they learn to the cloud in real time.

[1008] Step 2:

[1009] The server analyzes the collected learning data.

[1010] Input: Collected training data

[1011] Output: User's learning tendency and progress

[1012] How it works: It uses machine learning algorithms such as TensorFlow to analyze data and identify the user's strengths and weaknesses.

[1013] Step 3:

[1014] The server builds a predictive model based on the analysis results.

[1015] Input: User's learning habits and progress

[1016] Output: Learning progress prediction model

[1017] Specific operation: Using TensorFlow, we build a model that uses the analysis results to predict the user's future learning progress.

[1018] Step 4:

[1019] The server uses the predictive model to generate a personalized learning plan.

[1020] Input: Learning progress prediction model

[1021] Output: Individualized Learning Plan

[1022] Specific behavior: Based on the user's strong and weak subjects, a schedule is generated detailing which subjects should be studied and for how long.

[1023] Step 5:

[1024] The server monitors the user's progress in real time as they actually study.

[1025] Input: User training data

[1026] Output: Learning progress

[1027] What it does: Stores and monitors user learning progress in the cloud through Firebase.

[1028] Step 6:

[1029] The server analyzes the user's schedule information.

[1030] Input: User's schedule information

[1031] Output: Identifying free time

[1032] What it does: Retrieves schedule data from a calendar application and parses it to identify available times.

[1033] Step 7:

[1034] The server generates psychological care suggestions based on the identified free time.

[1035] Input: Availability, user preferences and past history

[1036] Output: Mental care suggestions

[1037] What it does: Creates a plan to provide care, such as a short meditation session or listening to relaxing music, based on the user's past history and preferences.

[1038] Step 8:

[1039] The server notifies the user's terminal or smart device of mental care suggestions.

[1040] Input: Mental care suggestions

[1041] Output: User notification

[1042] Specific behavior: Use the push notification function of the smart device to notify the user of care suggestions. Specifically, the following prompt is displayed: "User A completed 45 minutes of math study today, but seems a little tired. We suggest a short meditation session from 3:00 PM to 4:00 PM. After the meditation, relaxation music will begin playing."

[1043] 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.

[1044] This invention is a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Furthermore, this system uses an emotion engine to recognize the user's emotions and customizes the mental health care proposals more effectively.

[1045] System Overview

[1046] 1. Collecting training data

[1047] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[1048] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[1049] 2. Analysis of training data

[1050] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[1051] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[1052] 3. Building a predictive model

[1053] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[1054] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[1055] 4. Generate a learning plan

[1056] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[1057] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[1058] 5. Monitoring your learning progress

[1059] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[1060] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[1061] 6. Analyzing Schedule Information

[1062] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[1063] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[1064] 7. Emotion Recognition with Emotion Engine

[1065] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes the data and recognizes the user's emotional state.

[1066] Example: From User A's facial expressions and tone of voice as he / she progresses with his / her studies, the emotion engine recognizes that User A is feeling tired or stressed.

[1067] 8. Generating mental health care proposals

[1068] The server then proposes personalized mental health care to the user based on the identified free time and the emotional data recognized by the emotion engine.The proposals are customized based on the user's past history and preferences.

[1069] Example: The server suggests a short meditation session or listening to relaxing music for User A's free time between 3:00 and 4:00 PM. Because the server recognizes that User A is feeling tired and stressed, the suggestions include activities that have a high relaxation effect.

[1070] 9. Notice to Users

[1071] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[1072] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[1073] This system is designed to improve users' learning efficiency and mental health by conducting a comprehensive process from analyzing learning data to building predictive models, generating and monitoring learning plans, recognizing users' emotions using an emotion engine, and generating and notifying them of mental care suggestions.

[1074] The processing flow will be explained below.

[1075] Step 1:

[1076] Users begin studying through their device, which automatically records data such as the study content, start time, end time, and correct answer rate.

[1077] Step 2:

[1078] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[1079] Step 3:

[1080] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[1081] Step 4:

[1082] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[1083] Step 5:

[1084] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[1085] Step 6:

[1086] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[1087] Step 7:

[1088] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[1089] Step 8:

[1090] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[1091] Step 9:

[1092] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[1093] Step 10:

[1094] The device captures the user's facial expressions, voice tone, and behavioral data, which are then transmitted to a server in real time.

[1095] Step 11:

[1096] The server analyzes the received facial expressions, voice tone, and behavioral data using an emotion engine to recognize the user's emotional state.

[1097] Step 12:

[1098] The server generates psychological care suggestions based on the user's free time and recognized emotional data, and these suggestions are customized based on the user's preferences and past history.

[1099] Step 13:

[1100] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, voice alert, or email.

[1101] Step 14:

[1102] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[1103] Example 2

[1104] 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."

[1105] In recent years, many systems have been developed to improve learners' learning outcomes, but few systems not only generate efficient learning plans but also take into consideration the learner's mental health. In particular, there is a demand for systems that can recognize the user's emotional state in real time and suggest appropriate mental care. To solve this problem, a system is needed that can analyze learning data, monitor progress, recognize emotions, and suggest individual care in an integrated manner.

[1106] 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.

[1107] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, emotion recognition means for recognizing the user's emotional state, means for personalized mental care suggestions based on the emotional state recognized by the emotion recognition means, and means for notifying the user of the suggestions. This not only improves the user's learning efficiency but also maintains their mental health while studying, thereby improving the overall quality of the learning experience.

[1108] "Study data" refers to information about a user's learning activities, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[1109] A "predictive model" is a computational model constructed to predict a user's future learning progress based on collected and analyzed learning data.

[1110] A "study plan" is a schedule generated using a predictive model that details which subjects a user should study and when.

[1111] "Schedule information" is information related to the user's time management, and mainly includes plans recorded on a calendar or timetable.

[1112] "Free time" is identified from the user's schedule information and refers to unallocated time that can be used for study or mental health care.

[1113] "Mental care" refers to suggestions and activities to maintain and improve the user's mental health, with the aim of relaxation and stress reduction.

[1114] "Emotion recognition means" refers to functions and technologies for analyzing a user's facial expressions, voice tone, and behavioral data to recognize the user's emotional state.

[1115] "Personalized recommendations" refers to providing individually optimized mental health recommendations based on the user's emotional state, past history, and preferences.

[1116] This invention is a learning support system for improving a user's learning efficiency and mental health. This system collects and analyzes learning data, builds a predictive model, generates an individual learning plan, monitors progress, recognizes emotions, and provides mental health care suggestions in a series of steps.

[1117] The system mainly consists of a server, a terminal, and a user. A specific embodiment of the system is shown below.

[1118] The server first collects learning data from the user's device. The collected learning data includes study time, learning content, correct answer rate, and learning achievement. For example, if a user achieves 80% correct answers on a math test, the data is sent to the server.

[1119] Next, the server analyzes the collected learning data using machine learning algorithms. The purpose of the analysis is to identify the user's learning tendencies, strong and weak subjects. Specifically, the data is analyzed using clustering and classifiers. The server analyzes the user's data and determines, for example, that the user is good at math and science, but weak at history.

[1120] Based on the analysis results, the server builds a model to predict the user's learning progress. This model predicts future study time and effort based on past data. For example, it generates a model that says, "You'll need 10 hours of math and 8 hours of science in the next two weeks."

[1121] Based on the predictive model, the server generates an individualized study plan, detailing which subjects to study and when to study them. The server generates a schedule of 45 minutes of math, 30 minutes of science, and 60 minutes of history each day for the next two weeks.

[1122] The device records the user's progress in real time as they study and sends the data to the server. For example, if a user studies mathematics on the device for 30 minutes, the data is immediately sent to the server and the learning progress is updated. In this way, the server monitors the progress of the learning plan.

[1123] Additionally, the server analyzes the user's schedule information, typically obtained from a calendar or timetable, to identify available study time. For example, the server may identify an available time slot between 3:00 PM and 4:00 PM.

[1124] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, if the user looks anxious, the emotion engine detects "stress."

[1125] The server then suggests personalized mental health care activities based on the identified free time and the emotional data recognized by the emotion engine. The suggestions are customized based on the user's past history and preferences. For example, it suggests specific activities such as "relieve stress by listening to relaxing music at 3 p.m."

[1126] Finally, the device notifies the user of the mental health care suggestions from the server via a pop-up, a voice alert, or an email. For example, the device may display a pop-up notification to the user at 3:00 PM, prompting them to start their mental health care activities.

[1127] In this way, the system of the present invention improves the user's learning efficiency and mental health through a series of processes, thereby enhancing the quality of the overall learning experience.

[1128] Example prompt sentence:

[1129] "Please explain how you can analyze a user's emotional state in real time and optimize their learning schedule."

[1130] "Please tell me how to design a system that integrates user learning data and emotional data to personalize mental health care suggestions."

[1131] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1132] Step 1:

[1133] Data collection

[1134] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[1135] Input: Data from the user's learning app (e.g., study time and correct answer rate)

[1136] Output: Training data stored on the server

[1137] Specific operation: When a user scores 80% on a math test, the data is sent from the device to the server.

[1138] Step 2:

[1139] Data analysis

[1140] The server analyzes the collected learning data using machine learning algorithms.

[1141] Input: The training data collected in step 1

[1142] Output: User's learning tendency, favorite subjects, and favorite subjects (e.g., user is good at math, but not good at history)

[1143] What it does: The server analyzes the data using clustering and classifiers to determine that the user is good at math and science, but bad at history.

[1144] Step 3:

[1145] Building predictive models

[1146] Based on the analysis results, the server builds a model to predict the user's future learning progress.

[1147] Input: Analysis result from step 2

[1148] Output: A model that predicts future study time and effort (e.g., 10 hours of math and 8 hours of science needed in the next two weeks)

[1149] Specific operation: The server generates a model that predicts future study time based on past data.

[1150] Step 4:

[1151] Generate a lesson plan

[1152] The server generates an individualized learning plan based on the predictive model.

[1153] Input: Predictive model from step 3

[1154] Output: Individualized learning plan (e.g., 45 minutes of math, 30 minutes of science, and 60 minutes of history each day)

[1155] Specific operation: The server generates the user's schedule for the next two weeks and sends it to the device.

[1156] Step 5:

[1157] Monitoring learning progress

[1158] As the user actually studies, the device records their progress in real time and sends it to the server.

[1159] Input: The actual study time and content of the user

[1160] Output: Learning progress data sent to the server

[1161] What it does: When a user studies math on their device for 30 minutes, the data is immediately sent to the server and their learning progress is updated.

[1162] Step 6:

[1163] Schedule information analysis

[1164] The server analyzes the user's schedule information and identifies free time that can be used for studying.

[1165] Input: User's schedule information (e.g., calendar app)

[1166] Output: Identify available times (e.g., available times between 3:00 PM and 4:00 PM)

[1167] What happens: The server analyzes the calendar app data to identify free time.

[1168] Step 7:

[1169] emotion recognition

[1170] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes it.

[1171] Input: User facial expressions, voice tone, and behavioral data

[1172] Output: Recognizing the user's emotional state (e.g., recognizing that the user is stressed)

[1173] How it works: The user uses the device's camera and microphone to capture facial expressions and voice data in real time, which is then sent to the server and analyzed by the emotion engine.

[1174] Step 8:

[1175] Generating mental health care proposals

[1176] The server then proposes personalized mental care for the user based on the identified free time and the emotional data recognized by the emotion engine.

[1177] Input: Free time from step 6, Emotion data recognized from step 7

[1178] Output: Personalized mental health recommendations (e.g., listening to relaxing music at 3 PM)

[1179] How it works: The server suggests listening to relaxing music or meditating based on the user's free time and current emotional state.

[1180] Step 9:

[1181] User Notification

[1182] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[1183] Input: Mental care suggestions from the server

[1184] Output: Notify user (e.g., show a popup notification at 3 PM)

[1185] What it does: The device displays a pop-up notification to the user at 3 PM, encouraging them to start mental health activities.

[1186] (Application example 2)

[1187] 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."

[1188] Conventional learning support systems have had the challenge of making it difficult to simultaneously improve users' learning efficiency and mental health. Similar challenges exist in managing the efficiency of robots and human workers in factories. Specifically, there is a lack of an overall system that can analyze the work data of robots and workers individually to improve efficiency while also providing mental care, raising concerns about reduced work efficiency and reduced work performance due to stress.

[1189] The identification process by the identification 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 analyzing collected user learning data, means for constructing a prediction model based on the learning data, means for generating an individual learning plan using the prediction model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for collecting and analyzing robot work data, means for generating a new work plan based on the robot's work efficiency, means for recognizing the worker's emotional state and suggesting mental care, and means for notifying the worker of the suggestion. This makes it possible to provide mental care tailored to each individual's emotional state while improving the learning and work efficiency of users and workers.

[1190] A "server" is a computer that provides services to other computers over a network.

[1191] "Study data" is information related to the user's study, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[1192] A "predictive model" is a model for predicting future learning progress and the amount of learning required based on collected data.

[1193] A "study plan" is a plan that details a user's individual study schedule and content based on a predictive model.

[1194] "Study progress" refers to the progress of how far the user has actually progressed in their studies.

[1195] "Schedule information" refers to calendar information and time management data that includes the user's daily schedule.

[1196] "Free time" is a time period extracted from the user's schedule information that can be used for studying or relaxing.

[1197] "Mental care" refers to suggestions and activities for relaxation and stress relief provided to maintain the user's mental health.

[1198] "Notification" refers to conveying information to the user, and is done using means such as a pop-up, audio alert, or email.

[1199] "Work data" is information about work performed by robots and workers in a factory, and includes information about efficiency and progress.

[1200] "Emotional state" refers to the worker's current mental state and is recognized from facial expressions, tone of voice, and behavioral data.

[1201] A "work plan" is a plan that indicates an efficient work schedule and content, newly generated based on the robot's work efficiency.

[1202] The present invention provides a system for improving the work efficiency of robots working in factories and the mental health of human workers. The following describes an embodiment of this system.

[1203] System program generation

[1204] The system can be implemented using Python, and its main processes include data collection, data analysis, predictive model construction, learning plan generation, learning progress monitoring, emotional state recognition, and mental health care suggestion generation and notification.

[1205] Processing Description

[1206] 1. Data Collection

[1207] The server collects user learning data, robot work data, and worker emotion data. The learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[1208] Specifically, training data is collected from a training application, and work data is collected from the factory's production management system. Emotion data is collected using cameras and voice analysis. Specific hardware examples include the OpenVINO platform for emotion detection and the Google Cloud Speech-to-Text API for voice analysis.

[1209] 2. Data Analysis

[1210] The server uses machine learning algorithms to analyze the collected data, which in turn evaluates the user's learning habits, the robot's work efficiency, and the worker's stress level.

[1211] Specifically, you can use Python data analysis libraries such as "Pandas" and "Scikit-learn."

[1212] 3. Building a predictive model

[1213] Based on the analysis results, the server builds a model that predicts future learning progress and work efficiency.

[1214] For example, regression analysis is used to predict learning progress, and time series analysis is applied to predict the work efficiency of a robot.

[1215] 4. Creating a learning plan and work plan

[1216] The server uses the predictive model to generate an individualized learning plan, detailing which subjects to study and when, and a new work plan, which tells the robot which tasks to prioritize.

[1217] Specifically, learning plans are notified to the "learning management system," and work plans are reflected in the "factory management system."

[1218] 5. Monitoring learning and work progress

[1219] As the user and robot actually learn or work, the terminal records their progress in real time and sends it to the server.

[1220] This data will be analyzed again and the plan adjusted as needed.

[1221] 6. Generating and notifying mental health care suggestions

[1222] The server then proposes personalized mental care to users and workers based on the emotion data recognized by the emotion engine and schedule information. Suggestions include short periods of meditation and listening to relaxing music. These suggestions are then sent to the users' and workers' devices.

[1223] As an example of specific suggestions, tired workers might be advised to "meditate for 10 minutes" or "practice deep breathing."

[1224] Specific examples

[1225] For example, based on data collected from the past year's use of a learning application, the server can determine that User A is good at math and science but not so good at history. Based on this, the server can generate a daily study plan consisting of 45 minutes of math, 30 minutes of science, and 60 minutes of history. If the device recognizes a tired expression while studying, it will suggest relaxation meditation and notify the user of this information via a pop-up.

[1226] Prompt Sentence Examples

[1227] Based on the data below, please generate a Python program that will detect the emotions of high-stress workers and provide appropriate mental health care suggestions.

[1228] Data: {"id": 2, "stress_level": 85}

[1229] Tools needed for emotion detection: camera, audio analysis

[1230] Mental care suggestions: Take a break from work, listen to relaxing music, take deep breaths

[1231] The above is an embodiment of the present invention.

[1232] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1233] Step 1:

[1234] The server collects data from the user's device and the factory's production management system. Data collection includes the user's study time, study content, correct answer rate, learning achievement level, robot work data, and worker emotional data. Inputs include user and robot operation data, and emotional data from cameras and voice analysis devices. This data is sent to the server and temporarily stored.

[1235] Step 2:

[1236] The server analyzes the collected data using Python's "Pandas" and "Scikit-learn" as the analysis method. Specifically, it processes and calculates the data to evaluate the user's learning tendency, the robot's work efficiency, and the worker's stress level. All collected data is used as input, and the analysis results are obtained as output.

[1237] Step 3:

[1238] The server builds a predictive model based on the analysis results. This model predicts future learning progress and work efficiency. Regression analysis and time series analysis algorithms are used to build the predictive model. The analysis results are received as input, and a predictive model is generated as output.

[1239] Step 4:

[1240] The server uses the constructed predictive model to generate a study plan for the user and a work plan for the robot. The study plan indicates the user's required study schedule, while the work plan indicates the robot's work priorities. Specifically, the study plan for the user details which subjects should be studied and for how long each day, while the work plan for the robot determines the order in which tasks should be performed. Using the predictive model as input, an individual plan is generated as output.

[1241] Step 5:

[1242] The terminal records the progress of the user or robot as they learn or work in real time and sends it to the server. The progress data record includes timestamps and a list of completed tasks. The real-time progress data is received as input, and the progress record is sent to the server as output.

[1243] Step 6:

[1244] The server analyzes the schedule information of users and workers to identify free time. The schedule information is obtained from the terminal, and calendar data is used for analysis. The server receives the schedule information as input and identifies free time as output.

[1245] Step 7:

[1246] The server uses an emotion engine to recognize the worker's emotional state. The emotion engine analyzes the worker's facial expressions and tone of voice from camera and voice analysis data to determine the worker's emotional state. Emotion data is used as input, and the recognized emotional state is output.

[1247] Step 8:

[1248] The server generates mental health suggestions based on the identified free time and emotional state, such as listening to music for relaxation or practicing meditation. Using free time and emotional state as input, the suggestions are generated as output.

[1249] Step 9:

[1250] The terminal notifies the user or worker of the generated mental health care suggestions by means of a pop-up, voice alert, email, etc. The terminal receives the mental health care suggestions as input and notifies the user or worker as output.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] [Fourth embodiment]

[1255] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1256] 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.

[1257] 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).

[1258] 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.

[1259] 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.

[1260] 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).

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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."

[1268] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Below, we will explain the outline and specific examples of the program for this system.

[1269] System Overview

[1270] 1. Collecting training data

[1271] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[1272] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[1273] 2. Analysis of training data

[1274] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[1275] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[1276] 3. Building a predictive model

[1277] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[1278] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[1279] 4. Generate a learning plan

[1280] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[1281] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[1282] 5. Monitoring your learning progress

[1283] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[1284] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[1285] 6. Analyzing Schedule Information

[1286] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[1287] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[1288] 7. Generating mental health care proposals

[1289] The server then provides personalized mental health care suggestions to the user based on the identified free time, which are customized based on past history and user preferences.

[1290] Example: The server suggests to user A that they "take a short meditation" or "listen to relaxing music" between 3:00 and 4:00 PM.

[1291] 8. Notice to Users

[1292] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[1293] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[1294] In this way, this system generates an optimal study plan based on the user's study data, monitors progress, and provides psychological support at appropriate times, thereby improving the user's study efficiency and persistence.

[1295] The processing flow will be explained below.

[1296] Step 1:

[1297] Users begin studying through their devices, and data such as study content, start time, end time, and correct answer rate are automatically recorded.

[1298] Step 2:

[1299] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[1300] Step 3:

[1301] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[1302] Step 4:

[1303] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[1304] Step 5:

[1305] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[1306] Step 6:

[1307] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[1308] Step 7:

[1309] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[1310] Step 8:

[1311] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[1312] Step 9:

[1313] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[1314] Step 10:

[1315] The server runs an algorithm to suggest mental health care based on the user's free time, and the suggestions are customized based on the user's preferences and past history.

[1316] Step 11:

[1317] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, audio alert, or email.

[1318] Step 12:

[1319] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[1320] Example 1

[1321] 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."

[1322] In modern society, there is a demand for specific plans and support to help individual learners continue their studies efficiently and sustainably. However, many systems only provide general learning plans, making it difficult to provide individual learning plans tailored to individual learning tendencies and schedules. It is also difficult to properly track learning progress and provide psychological support. This creates challenges that prevent learners from progressing efficiently and hinders improvement in learning outcomes.

[1323] 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.

[1324] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental health care based on the free time, means for notifying the user of the suggestions, means for recording the learning progress in real time and transmitting the recording results to the server, means for applying a machine learning algorithm to improve the user's learning efficiency based on the collected and analyzed data, and means for customizing mental health care suggestions based on the user's past history and preferences. This allows the server to provide appropriate individual learning plans and psychological care, enabling the user to progress in their studies efficiently and sustainably.

[1325] "Collected user learning data" is data recorded when a user engages in learning activities, including study time, study content, correct answer rate, and learning achievement level.

[1326] "Means for analyzing" means a set of machine learning algorithms and related software for evaluating the collected learning data and identifying the user's learning trends and progress.

[1327] A "means for constructing a predictive model" is a configuration of software and algorithms for generating a model for predicting a user's future learning performance based on the analyzed learning data.

[1328] The "means for generating personalized learning plans" is a system that uses predictive models to generate detailed learning schedules and curricula tailored to the individual learning needs of each user.

[1329] The "means for monitoring learning progress" refers to a device and a program for recording the learning activities actually performed by the user in real time, transmitting the data to a server, and supervising the progress against the learning plan.

[1330] The "means for identifying free time" is software that analyzes the user's schedule information and identifies free time that can be used for study or mental care.

[1331] The "means for suggesting mental care" is a system that suggests activities that promote relaxation and concentration suitable for a specified free time based on the user's preferences and past history.

[1332] The "means for notifying the user of suggestions" refers to a device or program for notifying the user of mental health care suggestions from the server via a pop-up, a voice alert, an email, or the like.

[1333] "Means for recording learning progress in real time and transmitting the recorded results to a server" refers to a terminal and software configuration for recording a user's learning activities in real time and automatically transmitting the data to a server.

[1334] "Means for applying machine learning algorithms" refers to programs and models for utilizing machine learning techniques to improve learning efficiency based on collected and analyzed user learning data.

[1335] "Means for customizing mental health care suggestions based on the user's past history and preferences" is a system for suggesting optimal mental health care activities based on the user's past behavioral history and registered preferences.

[1336] The present invention relates to a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve a user's learning efficiency. The following describes an embodiment of this system.

[1337] The main components of the system include a server, user terminals, and various software for data analysis. Specific software used includes machine learning libraries such as Python, TensorFlow, and PyTorch. The server also has a database that stores and manages user learning data.

[1338] The server collects learning data from the user's device. This learning data includes learning time, learning content, correct answer rate, and learning achievement level. The data collected by the device is sent to the server in real time, and the server stores it in a database.

[1339] The server then analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress. For example, the server can identify the user's strengths and weaknesses and reflect this in their study plan.

[1340] Based on the analysis results, the server builds a predictive model using TensorFlow and PyTorch to predict future learning performance based on the user's past learning data and current progress. This model forms the basis for planning future learning schedules.

[1341] The server uses the predictive model to generate a personalized study plan for each user, including specific subjects and study times, designed to maximize the user's learning efficiency. For example, the server generates a two-week schedule for User A, with 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[1342] As the user studies, the device records their progress in real time and sends it to the server, which then monitors the progress of the study plan and adjusts it as needed.

[1343] The server also analyzes the user's schedule information to identify free time that cannot be used for studying. Once free time is identified, the server makes personalized suggestions for the user's mental health care. These suggestions are customized based on past history and the user's preferences. For example, the server might suggest to User A that they "do a short meditation session" or "listen to relaxing music" between 3:00 and 4:00 PM.

[1344] The server sends mental health advice to the user via a pop-up notification, voice alert, or email. For example, at 3 p.m., the device displays a pop-up notification prompting the user to listen to relaxing music.

[1345] Some examples of specific prompts include:

[1346] "Based on User A's learning data, please analyze his math accuracy rate over the past year and predict the amount of study time he will need in the next two weeks."

[1347] According to the present invention, the user can study efficiently and continuously, and can also receive mental health care at an appropriate time.

[1348] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1349] Step 1:

[1350] The server collects learning data from the user's device. The device automatically sends the data to the server when the user finishes learning. The collected data includes learning time, learning content, correct answer rate, and learning achievement. The input is a record of the user's learning activities, and the output is learning data stored on the server.

[1351] Specific operation: The device records data on the user's math study for 45 minutes, with an 80% accuracy rate. When the user finishes studying, the device sends this data to the server, which stores it in a database.

[1352] Step 2:

[1353] The server analyzes the collected learning data. For the analysis, Python is used to evaluate the user's learning tendency and progress using machine learning algorithms. The input is the learning data collected in the previous step, and the output is the analysis results.

[1354] Specific operation: The server analyzes the training data using the Python library and determines that User A is good at math but not so good at history.

[1355] Step 3:

[1356] The server builds a predictive model based on the analysis results. This model is built using TensorFlow and predicts future learning performance. The input is the analysis results, and the output is the predictive model.

[1357] Specific operation: Based on User A's past learning data, the server uses TensorFlow to build a model that predicts how much learning will be required in the next two weeks.

[1358] Step 4:

[1359] The server uses the predictive model to generate a personalized learning plan, including specific learning content and time. The input is the predictive model, and the output is the user's personalized learning plan.

[1360] Specific operation: Based on the predictive model, the server generates a detailed two-week schedule for User A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history study.

[1361] Step 5:

[1362] The device records the user's progress in real time as they study and sends it to the server. The input is the user's study activity, and the output is the recorded study data sent to the server.

[1363] How it works: When a user starts studying, the device records the study time and content in real time. When the user finishes studying, the device sends the data to the server, which then updates the progress.

[1364] Step 6:

[1365] The server analyzes the user's schedule information and identifies available free time. The schedule information is obtained from the terminal. The input is the schedule information, and the output is the available free time.

[1366] What happens: The server collects and analyzes data from User A's calendar application. It determines that there is free time between 3:00 PM and 4:00 PM.

[1367] Step 7:

[1368] The server then provides personalized mental health care suggestions based on the identified free time. The suggestions are customized based on the user's past history and preferences. The inputs are free time and the user's past history and preferences, and the output is mental health care suggestions.

[1369] Specific operation: Based on User A's past history, the server suggests a short meditation session or listening to relaxing music between 3:00 and 4:00 PM.

[1370] Step 8:

[1371] The terminal notifies the user of the mental health care suggestions from the server. The notification can be done by a pop-up, a voice alert, or an email. The input is the mental health care suggestion, and the output is the information to be notified to the user.

[1372] What it does: At 3 PM, the device will display a pop-up notification, prompting the user to listen to relaxing music.

[1373] (Application example 1)

[1374] 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."

[1375] In today's learning environment, analyzing individual learning data and providing appropriate learning plans is essential for users to study efficiently and effectively. However, previous systems have not been able to provide personalized care that takes into account each user's individual learning tendencies and progress. Furthermore, there are limited ways for learners to receive psychological support at the appropriate time, which can lead to reduced learning efficiency. Furthermore, real-time content delivery using smart devices remains a challenge.

[1376] 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.

[1377] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for providing appropriate learning content and mental care content to improve learning efficiency based on the learning data, and means for delivering content in real time via a head-mounted display or a smartphone.

[1378] This will enable the provision of optimal learning plans and mental care based on individual users' learning data, improving learning efficiency and mental health. In addition, real-time content delivery using smart devices will make the learning experience more flexible and effective.

[1379] "Collection" refers to the act of collecting user learning data from the terminal to a central server.

[1380] "Analysis" is the process of evaluating a user's learning trends and progress based on collected learning data.

[1381] A "predictive model" is a mathematical or statistical model for predicting a user's future learning progress based on the analysis results.

[1382] A "study plan" is a schedule generated using a predictive model that details a user's individual learning content and time allocation.

[1383] "Study progress" is a concept that refers to the progress and level of achievement of a user as they proceed with their actual studies.

[1384] "Schedule information" is data that indicates the user's schedule and time allocation. This information is obtained from a calendar application or the like.

[1385] "Free time" is a period of time that is identified from schedule information and is free to be used for study or other activities.

[1386] "Mental health care" is a concept that refers to suggesting activities and content to improve users' mental health.

[1387] "Real-time" refers to a situation in which data or content is processed and delivered immediately, without delay.

[1388] "Content delivery" is the act of delivering digital content such as music, video, and text for learning and mental health care to user devices.

[1389] "Smart devices" refer to information processing devices, including mobile terminals and wearable devices that can connect to the Internet.

[1390] The system for implementing this invention collects and analyzes user learning data and provides psychological care. This system mainly consists of a server, a user terminal, and a smart device (e.g., a smartphone or a head-mounted display).

[1391] 1. Collecting training data

[1392] The server collects learning data from users' terminals and smart devices. This learning data includes learning time, learning content, correct answer rate, and learning achievement. Specifically, the data is collected in real time using Firebase and Google Analytics and sent to the cloud.

[1393] 2. Analysis of training data

[1394] The server analyzes the collected learning data using machine learning algorithms (e.g., TensorFlow), which evaluates the user's learning trends and progress and identifies their strengths and weaknesses.

[1395] 3. Building a predictive model

[1396] Based on the analysis results, the server builds a model to predict the user's learning progress. This model uses TensorFlow to predict the user's future learning status.

[1397] 4. Generate a learning plan

[1398] The server uses the built predictive model to generate a personalized study plan for the user, detailing which subjects should be studied and for how many hours.

[1399] 5. Monitoring your learning progress

[1400] The server records the user's progress in real time as they study and stores it in the cloud via Firebase, allowing the user to monitor their progress in their study plan.

[1401] 6. Analyzing Schedule Information

[1402] The server identifies available study time by analyzing the user's schedule information, which is obtained from the user's calendar application.

[1403] 7. Generating mental health care proposals

[1404] The server then provides personalized mental health suggestions based on the identified free time. These suggestions are customized based on past history and user preferences. Examples include short meditation sessions or listening to relaxing music.

[1405] 8. Notice to Users

[1406] The server sends mental health care suggestions as push notifications to the user's terminal or smart device, allowing the user to receive mental health care at the appropriate time.

[1407] As a concrete example, consider a user studying math using a smartphone app. After completing 45 minutes of studying, the app sends data to a server. The server analyzes the data, determines that the user is tired, and suggests a meditation session.

[1408] Prompt Sentence Examples

[1409] text

[1410] User A completed 45 minutes of math study today but seems a little tired. You suggest a short meditation session from 3:00 PM - 4:00 PM. After the meditation, relaxation music will begin playing.

[1411] The system allows users to receive optimal learning plans and mental health care to improve learning efficiency, and makes the learning experience flexible and effective by delivering content in real time using smart devices.

[1412] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1413] Step 1:

[1414] The server collects learning data from users' terminals and smart devices.

[1415] Input: Study time, study content, correct answer rate, learning achievement

[1416] Output: Collected training data

[1417] What it does: It uses Firebase and Google Analytics to send data generated by users as they learn to the cloud in real time.

[1418] Step 2:

[1419] The server analyzes the collected learning data.

[1420] Input: Collected training data

[1421] Output: User's learning tendency and progress

[1422] How it works: It uses machine learning algorithms such as TensorFlow to analyze data and identify the user's strengths and weaknesses.

[1423] Step 3:

[1424] The server builds a predictive model based on the analysis results.

[1425] Input: User's learning habits and progress

[1426] Output: Learning progress prediction model

[1427] Specific operation: Using TensorFlow, we build a model that uses the analysis results to predict the user's future learning progress.

[1428] Step 4:

[1429] The server uses the predictive model to generate a personalized learning plan.

[1430] Input: Learning progress prediction model

[1431] Output: Individualized Learning Plan

[1432] Specific behavior: Based on the user's strong and weak subjects, a schedule is generated detailing which subjects should be studied and for how long.

[1433] Step 5:

[1434] The server monitors the user's progress in real time as they actually study.

[1435] Input: User training data

[1436] Output: Learning progress

[1437] What it does: Stores and monitors user learning progress in the cloud through Firebase.

[1438] Step 6:

[1439] The server analyzes the user's schedule information.

[1440] Input: User's schedule information

[1441] Output: Identifying free time

[1442] What it does: Retrieves schedule data from a calendar application and parses it to identify available times.

[1443] Step 7:

[1444] The server generates psychological care suggestions based on the identified free time.

[1445] Input: Availability, user preferences and past history

[1446] Output: Mental care suggestions

[1447] What it does: Creates a plan to provide care, such as a short meditation session or listening to relaxing music, based on the user's past history and preferences.

[1448] Step 8:

[1449] The server notifies the user's terminal or smart device of mental care suggestions.

[1450] Input: Mental care suggestions

[1451] Output: User notification

[1452] Specific behavior: Use the push notification function of the smart device to notify the user of care suggestions. Specifically, the following prompt is displayed: "User A completed 45 minutes of math study today, but seems a little tired. We suggest a short meditation session from 3:00 PM to 4:00 PM. After the meditation, relaxation music will begin playing."

[1453] 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.

[1454] This invention is a system that analyzes learning data, generates and adjusts learning plans, and proposes personalized mental health care to improve the user's learning efficiency. Furthermore, this system uses an emotion engine to recognize the user's emotions and customizes the mental health care proposals more effectively.

[1455] System Overview

[1456] 1. Collecting training data

[1457] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[1458] Example: The server collects data such as how much time User A spent on each subject each day over the past year, and what his / her correct answer rate was during that time.

[1459] 2. Analysis of training data

[1460] The server analyzes the collected learning data using machine learning algorithms to evaluate the user's learning trends and progress.

[1461] Example: The server analyzes user A's data and determines that he is good at math and science, but poor at history.

[1462] 3. Building a predictive model

[1463] Based on the analysis results, the server builds a model to predict the user's learning progress, which forms the basis for planning future learning plans.

[1464] Example: The server builds a model to predict how much learning User A needs to do in the next two weeks.

[1465] 4. Generate a learning plan

[1466] The server uses the predictive model to generate a personalized study plan for the user, detailing which subjects to study and when.

[1467] Example: The server generates a two-week schedule for user A, which includes 45 minutes of math, 30 minutes of science, and 60 minutes of history each day.

[1468] 5. Monitoring your learning progress

[1469] The device records the user's progress in real time as they study and sends it to the server, which then monitors the progress of the study plan.

[1470] Example: When user A actually finishes studying for the day, the device sends the data to the server, and the server records the study progress based on that data.

[1471] 6. Analyzing Schedule Information

[1472] The server analyzes the user's schedule information and identifies free time that cannot be used for studying. The schedule information is obtained from the terminal.

[1473] Example: The server analyzes User A's calendar application and determines that he has free time between 3:00 and 4:00 PM.

[1474] 7. Emotion Recognition with Emotion Engine

[1475] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes the data and recognizes the user's emotional state.

[1476] Example: From User A's facial expressions and tone of voice as he / she progresses with his / her studies, the emotion engine recognizes that User A is feeling tired or stressed.

[1477] 8. Generating mental health care proposals

[1478] The server then proposes personalized mental health care to the user based on the identified free time and the emotional data recognized by the emotion engine.The proposals are customized based on the user's past history and preferences.

[1479] Example: The server suggests a short meditation session or listening to relaxing music for User A's free time between 3:00 and 4:00 PM. Because the server recognizes that User A is feeling tired and stressed, the suggestions include activities that have a high relaxation effect.

[1480] 9. Notice to Users

[1481] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[1482] Example: The device notifies user A of a 3:00 PM notification with a pop-up, prompting him to start mental health care activities.

[1483] This system is designed to improve users' learning efficiency and mental health by conducting a comprehensive process from analyzing learning data to building predictive models, generating and monitoring learning plans, recognizing users' emotions using an emotion engine, and generating and notifying them of mental care suggestions.

[1484] The processing flow will be explained below.

[1485] Step 1:

[1486] Users begin studying through their device, which automatically records data such as the study content, start time, end time, and correct answer rate.

[1487] Step 2:

[1488] The device collects the user's learning data in real time and sends it to the server, including the learning time, learning content, correct answer rate, and learning achievement level.

[1489] Step 3:

[1490] The server analyzes the received learning data and stores it in a database. As a result of the analysis, information such as the areas in which the user is strong or weak is extracted.

[1491] Step 4:

[1492] Based on the collected learning data, the server uses machine learning algorithms to build a predictive model that predicts the user's learning progress and the amount of learning required.

[1493] Step 5:

[1494] Based on the predictive model, the server generates a learning plan for each user, including the learning content, study time, and achievement goals.

[1495] Step 6:

[1496] The server sends the generated study plan to the user's device and notifies the user, who can then check the details of the study plan on their device.

[1497] Step 7:

[1498] The device records the user's progress as they study, and the progress data is sent to the server at regular intervals.

[1499] Step 8:

[1500] The server monitors the user's learning progress, compares the predicted model with the actual progress, and adjusts the plan if progress is falling behind.

[1501] Step 9:

[1502] The server analyzes the user's schedule information and identifies free time. The schedule information is obtained from a calendar app or similar.

[1503] Step 10:

[1504] The device captures the user's facial expressions, voice tone, and behavioral data, which are then transmitted to a server in real time.

[1505] Step 11:

[1506] The server analyzes the received facial expressions, voice tone, and behavioral data using an emotion engine to recognize the user's emotional state.

[1507] Step 12:

[1508] The server generates psychological care suggestions based on the user's free time and recognized emotional data, and these suggestions are customized based on the user's preferences and past history.

[1509] Step 13:

[1510] The server sends the generated mental health care suggestions to the user's device and notifies the user via a pop-up, voice alert, or email.

[1511] Step 14:

[1512] The user performs the suggested psychological care activity, and after completing the activity, the information is sent to the server via the terminal.

[1513] Example 2

[1514] 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."

[1515] In recent years, many systems have been developed to improve learners' learning outcomes, but few systems not only generate efficient learning plans but also take into consideration the learner's mental health. In particular, there is a demand for systems that can recognize the user's emotional state in real time and suggest appropriate mental care. To solve this problem, a system is needed that can analyze learning data, monitor progress, recognize emotions, and suggest individual care in an integrated manner.

[1516] 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.

[1517] In this invention, the server includes means for analyzing collected user learning data, means for constructing a predictive model based on the learning data, means for generating an individual learning plan using the predictive model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, emotion recognition means for recognizing the user's emotional state, means for personalized mental care suggestions based on the emotional state recognized by the emotion recognition means, and means for notifying the user of the suggestions. This not only improves the user's learning efficiency but also maintains their mental health while studying, thereby improving the overall quality of the learning experience.

[1518] "Study data" refers to information about a user's learning activities, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[1519] A "predictive model" is a computational model constructed to predict a user's future learning progress based on collected and analyzed learning data.

[1520] A "study plan" is a schedule generated using a predictive model that details which subjects a user should study and when.

[1521] "Schedule information" is information related to the user's time management, and mainly includes plans recorded on a calendar or timetable.

[1522] "Free time" is identified from the user's schedule information and refers to unallocated time that can be used for study or mental health care.

[1523] "Mental care" refers to suggestions and activities to maintain and improve the user's mental health, with the aim of relaxation and stress reduction.

[1524] "Emotion recognition means" refers to functions and technologies for analyzing a user's facial expressions, voice tone, and behavioral data to recognize the user's emotional state.

[1525] "Personalized recommendations" refers to providing individually optimized mental health recommendations based on the user's emotional state, past history, and preferences.

[1526] This invention is a learning support system for improving a user's learning efficiency and mental health. This system collects and analyzes learning data, builds a predictive model, generates an individual learning plan, monitors progress, recognizes emotions, and provides mental health care suggestions in a series of steps.

[1527] The system mainly consists of a server, a terminal, and a user. A specific embodiment of the system is shown below.

[1528] The server first collects learning data from the user's device. The collected learning data includes study time, learning content, correct answer rate, and learning achievement. For example, if a user achieves 80% correct answers on a math test, the data is sent to the server.

[1529] Next, the server analyzes the collected learning data using machine learning algorithms. The purpose of the analysis is to identify the user's learning tendencies, strong and weak subjects. Specifically, the data is analyzed using clustering and classifiers. The server analyzes the user's data and determines, for example, that the user is good at math and science, but weak at history.

[1530] Based on the analysis results, the server builds a model to predict the user's learning progress. This model predicts future study time and effort based on past data. For example, it generates a model that says, "You'll need 10 hours of math and 8 hours of science in the next two weeks."

[1531] Based on the predictive model, the server generates an individualized study plan, detailing which subjects to study and when to study them. The server generates a schedule of 45 minutes of math, 30 minutes of science, and 60 minutes of history each day for the next two weeks.

[1532] The device records the user's progress in real time as they study and sends the data to the server. For example, if a user studies mathematics on the device for 30 minutes, the data is immediately sent to the server and the learning progress is updated. In this way, the server monitors the progress of the learning plan.

[1533] Additionally, the server analyzes the user's schedule information, typically obtained from a calendar or timetable, to identify available study time. For example, the server may identify an available time slot between 3:00 PM and 4:00 PM.

[1534] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, if the user looks anxious, the emotion engine detects "stress."

[1535] The server then suggests personalized mental health care activities based on the identified free time and the emotional data recognized by the emotion engine. The suggestions are customized based on the user's past history and preferences. For example, it suggests specific activities such as "relieve stress by listening to relaxing music at 3 p.m."

[1536] Finally, the device notifies the user of the mental health care suggestions from the server via a pop-up, a voice alert, or an email. For example, the device may display a pop-up notification to the user at 3:00 PM, prompting them to start their mental health care activities.

[1537] In this way, the system of the present invention improves the user's learning efficiency and mental health through a series of processes, thereby enhancing the quality of the overall learning experience.

[1538] Example prompt sentence:

[1539] "Please explain how you can analyze a user's emotional state in real time and optimize their learning schedule."

[1540] "Please tell me how to design a system that integrates user learning data and emotional data to personalize mental health care suggestions."

[1541] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1542] Step 1:

[1543] Data collection

[1544] The server collects learning data from the user's device, including learning time, learning content, correct answer rate, and learning achievement level.

[1545] Input: Data from the user's learning app (e.g., study time and correct answer rate)

[1546] Output: Training data stored on the server

[1547] Specific operation: When a user scores 80% on a math test, the data is sent from the device to the server.

[1548] Step 2:

[1549] Data analysis

[1550] The server analyzes the collected learning data using machine learning algorithms.

[1551] Input: The training data collected in step 1

[1552] Output: User's learning tendency, favorite subjects, and favorite subjects (e.g., user is good at math, but not good at history)

[1553] What it does: The server analyzes the data using clustering and classifiers to determine that the user is good at math and science, but bad at history.

[1554] Step 3:

[1555] Building predictive models

[1556] Based on the analysis results, the server builds a model to predict the user's future learning progress.

[1557] Input: Analysis result from step 2

[1558] Output: A model that predicts future study time and effort (e.g., 10 hours of math and 8 hours of science needed in the next two weeks)

[1559] Specific operation: The server generates a model that predicts future study time based on past data.

[1560] Step 4:

[1561] Generate a lesson plan

[1562] The server generates an individualized learning plan based on the predictive model.

[1563] Input: Predictive model from step 3

[1564] Output: Individualized learning plan (e.g., 45 minutes of math, 30 minutes of science, and 60 minutes of history each day)

[1565] Specific operation: The server generates the user's schedule for the next two weeks and sends it to the device.

[1566] Step 5:

[1567] Monitoring learning progress

[1568] As the user actually studies, the device records their progress in real time and sends it to the server.

[1569] Input: The actual study time and content of the user

[1570] Output: Learning progress data sent to the server

[1571] What it does: When a user studies math on their device for 30 minutes, the data is immediately sent to the server and their learning progress is updated.

[1572] Step 6:

[1573] Schedule information analysis

[1574] The server analyzes the user's schedule information and identifies free time that can be used for studying.

[1575] Input: User's schedule information (e.g., calendar app)

[1576] Output: Identify available times (e.g., available times between 3:00 PM and 4:00 PM)

[1577] What happens: The server analyzes the calendar app data to identify free time.

[1578] Step 7:

[1579] emotion recognition

[1580] The device captures the user's facial expressions, voice tone, and behavioral data and sends the data to the server, where the emotion engine analyzes it.

[1581] Input: User facial expressions, voice tone, and behavioral data

[1582] Output: Recognizing the user's emotional state (e.g., recognizing that the user is stressed)

[1583] How it works: The user uses the device's camera and microphone to capture facial expressions and voice data in real time, which is then sent to the server and analyzed by the emotion engine.

[1584] Step 8:

[1585] Generating mental health care proposals

[1586] The server then proposes personalized mental care for the user based on the identified free time and the emotional data recognized by the emotion engine.

[1587] Input: Free time from step 6, Emotion data recognized from step 7

[1588] Output: Personalized mental health recommendations (e.g., listening to relaxing music at 3 PM)

[1589] How it works: The server suggests listening to relaxing music or meditating based on the user's free time and current emotional state.

[1590] Step 9:

[1591] User Notification

[1592] The device notifies the user of mental health care suggestions from the server via a pop-up, audio alert, or email.

[1593] Input: Mental care suggestions from the server

[1594] Output: Notify user (e.g., show a popup notification at 3 PM)

[1595] What it does: The device displays a pop-up notification to the user at 3 PM, encouraging them to start mental health activities.

[1596] (Application example 2)

[1597] 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."

[1598] Conventional learning support systems have had the challenge of making it difficult to simultaneously improve users' learning efficiency and mental health. Similar challenges exist in managing the efficiency of robots and human workers in factories. Specifically, there is a lack of an overall system that can analyze the work data of robots and workers individually to improve efficiency while also providing mental care, raising concerns about reduced work efficiency and reduced work performance due to stress.

[1599] The identification process by the identification 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 analyzing collected user learning data, means for constructing a prediction model based on the learning data, means for generating an individual learning plan using the prediction model, means for monitoring the user's learning progress based on the learning plan, means for identifying free time from the user's schedule information, means for suggesting mental care based on the free time, means for notifying the user of the suggestion, means for collecting and analyzing robot work data, means for generating a new work plan based on the robot's work efficiency, means for recognizing the worker's emotional state and suggesting mental care, and means for notifying the worker of the suggestion. This makes it possible to provide mental care tailored to each individual's emotional state while improving the learning and work efficiency of users and workers.

[1600] A "server" is a computer that provides services to other computers over a network.

[1601] "Study data" is information related to the user's study, and specifically includes study time, study content, correct answer rate, and learning achievement level.

[1602] A "predictive model" is a model for predicting future learning progress and the amount of learning required based on collected data.

[1603] A "study plan" is a plan that details a user's individual study schedule and content based on a predictive model.

[1604] "Study progress" refers to the progress of how far the user has actually progressed in their studies.

[1605] "Schedule information" refers to calendar information and time management data that includes the user's daily schedule.

[1606] "Free time" is a time period extracted from the user's schedule information that can be used for studying or relaxing.

[1607] "Mental care" refers to suggestions and activities for relaxation and stress relief provided to maintain the user's mental health.

[1608] "Notification" refers to conveying information to the user, and is done using means such as a pop-up, audio alert, or email.

[1609] "Work data" is information about work performed by robots and workers in a factory, and includes information about efficiency and progress.

[1610] "Emotional state" refers to the worker's current mental state and is recognized from facial expressions, tone of voice, and behavioral data.

[1611] A "work plan" is a plan that indicates an efficient work schedule and content, newly generated based on the robot's work efficiency.

[1612] The present invention provides a system for improving the work efficiency of robots working in factories and the mental health of human workers. The following describes an embodiment of this system.

[1613] System program generation

[1614] The system can be implemented using Python, and its main processes include data collection, data analysis, predictive model construction, learning plan generation, learning progress monitoring, emotional state recognition, and mental health care suggestion generation and notification.

[1615] Processing Description

[1616] 1. Data Collection

[1617] The server collects user learning data, robot work data, and worker emotion data. The learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[1618] Specifically, training data is collected from a training application, and work data is collected from the factory's production management system. Emotion data is collected using cameras and voice analysis. Specific hardware examples include the OpenVINO platform for emotion detection and the Google Cloud Speech-to-Text API for voice analysis.

[1619] 2. Data Analysis

[1620] The server uses machine learning algorithms to analyze the collected data, which in turn evaluates the user's learning habits, the robot's work efficiency, and the worker's stress level.

[1621] Specifically, you can use Python data analysis libraries such as "Pandas" and "Scikit-learn."

[1622] 3. Building a predictive model

[1623] Based on the analysis results, the server builds a model that predicts future learning progress and work efficiency.

[1624] For example, regression analysis is used to predict learning progress, and time series analysis is applied to predict the work efficiency of a robot.

[1625] 4. Creating a learning plan and work plan

[1626] The server uses the predictive model to generate an individualized learning plan, detailing which subjects to study and when, and a new work plan, which tells the robot which tasks to prioritize.

[1627] Specifically, learning plans are notified to the "learning management system," and work plans are reflected in the "factory management system."

[1628] 5. Monitoring learning and work progress

[1629] As the user and robot actually learn or work, the terminal records their progress in real time and sends it to the server.

[1630] This data will be analyzed again and the plan adjusted as needed.

[1631] 6. Generating and notifying mental health care suggestions

[1632] The server then proposes personalized mental care to users and workers based on the emotion data recognized by the emotion engine and schedule information. Suggestions include short periods of meditation and listening to relaxing music. These suggestions are then sent to the users' and workers' devices.

[1633] As an example of specific suggestions, tired workers might be advised to "meditate for 10 minutes" or "practice deep breathing."

[1634] Specific examples

[1635] For example, based on data collected from the past year's use of a learning application, the server can determine that User A is good at math and science but not so good at history. Based on this, the server can generate a daily study plan consisting of 45 minutes of math, 30 minutes of science, and 60 minutes of history. If the device recognizes a tired expression while studying, it will suggest relaxation meditation and notify the user of this information via a pop-up.

[1636] Prompt Sentence Examples

[1637] Based on the data below, please generate a Python program that will detect the emotions of high-stress workers and provide appropriate mental health care suggestions.

[1638] Data: {"id": 2, "stress_level": 85}

[1639] Tools needed for emotion detection: camera, audio analysis

[1640] Mental care suggestions: Take a break from work, listen to relaxing music, take deep breaths

[1641] The above is an embodiment of the present invention.

[1642] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1643] Step 1:

[1644] The server collects data from the user's device and the factory's production management system. Data collection includes the user's study time, study content, correct answer rate, learning achievement level, robot work data, and worker emotional data. Inputs include user and robot operation data, and emotional data from cameras and voice analysis devices. This data is sent to the server and temporarily stored.

[1645] Step 2:

[1646] The server analyzes the collected data using Python's "Pandas" and "Scikit-learn" as the analysis method. Specifically, it processes and calculates the data to evaluate the user's learning tendency, the robot's work efficiency, and the worker's stress level. All collected data is used as input, and the analysis results are obtained as output.

[1647] Step 3:

[1648] The server builds a predictive model based on the analysis results. This model predicts future learning progress and work efficiency. Regression analysis and time series analysis algorithms are used to build the predictive model. The analysis results are received as input, and a predictive model is generated as output.

[1649] Step 4:

[1650] The server uses the constructed predictive model to generate a study plan for the user and a work plan for the robot. The study plan indicates the user's required study schedule, while the work plan indicates the robot's work priorities. Specifically, the study plan for the user details which subjects should be studied and for how long each day, while the work plan for the robot determines the order in which tasks should be performed. Using the predictive model as input, an individual plan is generated as output.

[1651] Step 5:

[1652] The terminal records the progress of the user or robot as they learn or work in real time and sends it to the server. The progress data record includes timestamps and a list of completed tasks. The real-time progress data is received as input, and the progress record is sent to the server as output.

[1653] Step 6:

[1654] The server analyzes the schedule information of users and workers to identify free time. The schedule information is obtained from the terminal, and calendar data is used for analysis. The server receives the schedule information as input and identifies free time as output.

[1655] Step 7:

[1656] The server uses an emotion engine to recognize the worker's emotional state. The emotion engine analyzes the worker's facial expressions and tone of voice from camera and voice analysis data to determine the worker's emotional state. Emotion data is used as input, and the recognized emotional state is output.

[1657] Step 8:

[1658] The server generates mental health suggestions based on the identified free time and emotional state, such as listening to music for relaxation or practicing meditation. Using free time and emotional state as input, the suggestions are generated as output.

[1659] Step 9:

[1660] The terminal notifies the user or worker of the generated mental health care suggestions by means of a pop-up, voice alert, email, etc. The terminal receives the mental health care suggestions as input and notifies the user or worker as output.

[1661] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1662] 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.

[1663] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1664] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1665] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1666] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1667] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1668] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1669] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1670] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1671] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1672] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1673] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1674] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1675] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1676] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1677] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1678] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1679] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1680] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1681] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1682] Regarding the above embodiments, the following is further disclosed.

[1683] (Claim 1)

[1684] Means for analyzing the collected learning data of the user,

[1685] Means for constructing a prediction model based on the learning data,

[1686] Means for generating an individual learning plan using the prediction model,

[1687] Means for monitoring the learning progress of the user based on the learning plan,

[1688] Means for identifying free time from the user's schedule information,

[1689] Means for proposing mental care based on the free time,

[1690] Means for notifying the user of the proposal,

[1691] A system including the above.

[1692] (Claim 2)

[1693] The system according to claim 1, wherein the learning data includes learning time, learning content, correct answer rate, and learning achievement.

[1694] (Claim 3)

[1695] The system according to claim 1, wherein the mental care proposal is customized based on the user's preferences and past history.

[1696] "Example 1"

[1697] (Claim 1) <00051�0> Means for analyzing the collected learning data of the user,

[1699] means for constructing a prediction model based on the training data;

[1700] means for generating a personalized learning plan using the predictive model;

[1701] means for monitoring the user's learning progress based on the learning plan;

[1702] means for identifying free time from the user's schedule information;

[1703] means for suggesting mental care based on the free time;

[1704] means for notifying a user of said proposal;

[1705] a means for recording the learning progress in real time and transmitting the recording results to a server;

[1706] means for applying a machine learning algorithm to improve the user's learning efficiency based on the collected and analyzed data;

[1707] A means for customizing mental health care recommendations based on the user's past history and preferences; and

[1708] A system including:

[1709] (Claim 2)

[1710] 2. The system according to claim 1, wherein the learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[1711] (Claim 3)

[1712] 10. The system of claim 1, wherein the psychological care suggestions are customized based on the user's preferences and past history.

[1713] "Application Example 1"

[1714] (Claim 1)

[1715] A means for analyzing the collected user learning data;

[1716] means for constructing a prediction model based on the training data;

[1717] means for generating a personalized learning plan using the predictive model;

[1718] means for monitoring the user's learning progress based on the learning plan;

[1719] means for identifying free time from the user's schedule information;

[1720] means for suggesting mental care based on the free time;

[1721] means for notifying a user of said proposal;

[1722] A means for providing appropriate learning content and mental care content to improve learning efficiency based on learning data;

[1723] A means to deliver content in real time via head-mounted displays and smartphones,

[1724] A system including:

[1725] (Claim 2)

[1726] 2. The system according to claim 1, wherein the learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[1727] (Claim 3)

[1728] 10. The system of claim 1, wherein the psychological care suggestions are customized based on the user's preferences and past history.

[1729] "Example 2: Combining Emotion Engines"

[1730] (Claim 1)

[1731] A means for analyzing the collected user learning data;

[1732] means for constructing a prediction model based on the training data;

[1733] means for generating a personalized learning plan using the predictive model;

[1734] means for monitoring the user's learning progress based on the learning plan;

[1735] means for identifying free time from the user's schedule information;

[1736] means for suggesting mental care based on the free time;

[1737] emotion recognition means for recognizing an emotional state of a user;

[1738] a means for suggesting personalized mental care based on the emotional state recognized by the emotion recognition means;

[1739] means for notifying a user of said proposal;

[1740] A system including:

[1741] (Claim 2)

[1742] 2. The system according to claim 1, wherein the learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[1743] (Claim 3)

[1744] 10. The system of claim 1, wherein the psychological care suggestions are customized based on the user's preferences and past history.

[1745] "Application example 2 when combining emotion engines"

[1746] (Claim 1)

[1747] A means for analyzing the collected user learning data;

[1748] means for constructing a prediction model based on the training data;

[1749] means for generating a personalized learning plan using the predictive model;

[1750] means for monitoring the user's learning progress based on the learning plan;

[1751] means for identifying free time from the user's schedule information;

[1752] means for suggesting mental care based on the free time;

[1753] means for notifying a user of said proposal;

[1754] A means for collecting and analyzing robot work data;

[1755] means for generating a new work plan based on the work efficiency of the robot;

[1756] A means of recognizing the emotional state of workers and suggesting psychological care;

[1757] means for notifying a worker of said proposal;

[1758] A system including:

[1759] (Claim 2)

[1760] 2. The system according to claim 1, wherein the learning data includes learning time, learning content, correct answer rate, and learning achievement level.

[1761] (Claim 3)

[1762] 10. The system of claim 1, wherein the psychological care suggestions are customized based on the user's preferences and past history. [Explanation of symbols]

[1763] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing the collected user learning data; means for constructing a prediction model based on the training data; means for generating a personalized learning plan using the predictive model; means for monitoring the user's learning progress based on the learning plan; means for identifying free time from the user's schedule information; means for suggesting mental care based on the free time; means for notifying a user of said proposal; A system including:

2. 2. The system according to claim 1, wherein the learning data includes learning time, learning content, correct answer rate, and learning achievement level.

3. 10. The system of claim 1, wherein the psychological care suggestions are customized based on the user's preferences and past history.

Images