System

Abstract

A system is provided.SOLUTION: A system comprising: means for monitoring behavior and emotional state of a child and collecting data in real-time; means for analyzing the collected data and generating an individualized support plan for the child; means for providing audio and visual feedback based on the individualized support plan in real-time; and means for continuously updating a machine learning model based on the collected data and the individualized support plan.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] Children with developmental disabilities often experience difficulties with learning and communication in standard educational environments. While these children require individualized support, the lack of resources for support classes and support staff is a major issue. Traditional methods place a heavy burden on support staff and teachers, and support is often inadequate, resulting in learning delays and school absenteeism among children. Furthermore, variations in support among local governments are also a problem, necessitating the development of unified and effective support. [Means for solving the problem]

[0005] The present invention provides a system that monitors a child's behavior and emotional state and analyzes the collected data in real time. Specifically, the system includes a means for a terminal to monitor the child's behavior and emotional state and transmit the data to a server. The server analyzes the received data and generates an individualized support plan. The system further includes a means for sending feedback instructions to the terminal based on the generated individualized support plan, and the terminal executes audio and visual output based on the feedback instructions. This enables appropriate guidance and encouragement to be provided in real time to children in need of support. The system also provides a means for automatically adjusting the support plan for subsequent lessons by storing information entered by a teacher or support staff on the server and analyzing it using a machine learning algorithm. In this way, individualized and appropriate support can be provided to children with developmental disabilities, ensuring equal educational opportunities.

[0006] A "terminal" is a device that monitors a child's behavior and emotional state, collects data in real time, and provides audio and visual feedback.

[0007] A "server" is a device or system that analyzes data sent from a terminal, generates an individual support plan, and sends feedback instructions to the terminal.

[0008] "Children" refers to children and students who require special educational support, including those with developmental disabilities.

[0009] "Monitoring" is the process of using a device to observe a child's behavior and emotional state and collect the data.

[0010] "Data" refers to information collected through monitoring, such as children's behavior, facial expressions, speech, and attitudes.

[0011] "Analysis" is the process of understanding the child's behavior and emotional state based on the data received by the server and determining appropriate support methods.

[0012] An "individual support plan" is a specific plan based on analyzed data to provide optimal guidance and support for each child.

[0013] "Feedback" refers to the audio and visual responses and guidance provided to the child from the device based on the individual assistance plan.

[0014] A "machine learning model" is an algorithm that the server continuously learns from collected data and automatically improves and updates appropriate support methods.

[0015] A "teacher" is a professional who provides instruction and support to children in educational institutions.

[0016] "Support staff" are staff who provide auxiliary or specialized support to children with special needs. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention provides a system for providing individualized and appropriate support to children with developmental disabilities, which includes the following configuration and operation.

[0039] System configuration

[0040] 1. Server

[0041] A central processing unit that analyzes data and generates individualized support plans.

[0042] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[0043] 2. Terminal

[0044] A device used in classrooms to monitor children's behavior and emotional state in real time.

[0045] It has means for providing audio and visual feedback.

[0046] 3. Users

[0047] A teacher or support worker who inputs and checks the child's situation and support details.

[0048] Program processing

[0049] Data collection

[0050] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[0051] For example, it detects information such as "Mr. A has a confused expression."

[0052] Data Transfer

[0053] The device sends the collected data, including the child's behavior, facial expressions, and speech, to a server.

[0054] Data analysis

[0055] The server analyzes the child's current emotional state and behavioral patterns based on the received data.

[0056] For example, it may be determined that "Mr. A has difficulty writing kanji."

[0057] Generate an individual support plan

[0058] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[0059] For example, it generates a specific plan such as "Provide support for A-kun to write kanji slowly."

[0060] Feedback Instructions

[0061] The server transmits feedback instructions to the terminal based on the generated individual support plan.

[0062] For example, you can give instructions such as, "Tell A, 'It's okay to write slowly.'"

[0063] Providing Feedback

[0064] The terminal provides audio and visual feedback in real time based on feedback instructions sent from the server.

[0065] For example, audio instructions such as, "A-kun, it's okay to write slowly."

[0066] Continuous learning and updates

[0067] The server uses machine learning algorithms to continuously update the model based on the collected data and feedback.

[0068] For example, learning from past data to provide more effective feedback in the next lesson.

[0069] Specific examples

[0070] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0071] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0072] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0073] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[0074] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0075] Example 2: Autism Spectrum Disorder (ASD)

[0076] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0077] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0078] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0079] 4. The device will say, "This is a new challenge. Let's start with this."

[0080] In this way, this system works in collaboration between the server, terminal, and user to provide individually appropriate support, effectively improving the learning environment for children with developmental disabilities.

[0081] The processing flow will be explained below.

[0082] Step 1:

[0083] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[0084] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[0085] Step 2:

[0086] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[0087] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[0088] Step 3:

[0089] The terminal transmits the collected behavioral and emotional data to a server.

[0090] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[0091] Step 4:

[0092] The server analyzes the received data and determines the child's emotional state and behavioral patterns.

[0093] Example: "Mr. A is not good at writing kanji and is confused."

[0094] Step 5:

[0095] The server generates an individual support plan based on the analysis results.

[0096] Example: The support plan is decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[0097] Step 6:

[0098] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[0099] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[0100] Step 7:

[0101] The terminal provides real-time audio and visual feedback based on instructions from the server.

[0102] Example: "A-kun, it's okay to write slowly," provides audio guidance and visual support.

[0103] Step 8:

[0104] The server continuously collects data on the child's reactions after the feedback is provided and uses machine learning models to optimize the support method.

[0105] For example, the system learns data such as "Mr. A was able to write kanji when we spoke to him slowly."

[0106] Step 9:

[0107] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[0108] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[0109] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[0110] Example 1

[0111] 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."

[0112] Currently, individual support for children with developmental disorders generally relies on the experience and intuition of teachers and support staff. As a result, support content is often inconsistent and ineffective. It is also extremely difficult to monitor children's behavior and emotional state in real time and provide appropriate feedback. Furthermore, there is no system for evaluating the effectiveness of support methods and continuously optimizing them, making it difficult to improve the quality of support. To address these challenges, a system is needed to provide consistent and effective support to children with developmental disorders.

[0113] 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.

[0114] In this invention, the server includes: a device that monitors a child's behavior and emotional state in real time using a camera or sensor and collects the data; a device that transmits the collected data to the server; a server that analyzes the child's emotional state and behavioral patterns based on the received data; a server that generates an individualized support plan based on the analysis results; a server that transmits feedback instructions to the device based on the generated individualized support plan; a server that provides audio and visual feedback in real time based on the feedback instructions sent from the server; and a server that continuously updates a model using a machine learning algorithm based on the collected data and feedback results. This makes it possible to provide individually appropriate support in real time, scientifically evaluate the effectiveness of the support, and continuously optimize it.

[0115] The "terminal" is a device that monitors a child's behavior and emotional state using cameras and sensors and transmits the collected data to a server.

[0116] The "server" is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the terminal.

[0117] A "camera" is a device that captures a child's facial and body movements to collect data in real time.

[0118] A "sensor" is a device used to monitor a child's behavior and emotional state, such as through motion detection and voice analysis.

[0119] "Data collection" means that the device uses cameras and sensors to monitor the child's behavior and emotional state in real time and record the information.

[0120] "Data transmission" means that the terminal transfers the collected data to the server.

[0121] "Data analysis" refers to identifying and analyzing the child's emotional state and behavioral patterns based on the data received by the server.

[0122] "Generation of an individual support plan" means that the server formulates the most appropriate support method for the child based on the analysis results.

[0123] "Feedback instructions" are specific behavioral or verbal instructions that are sent to the terminal based on the individual support plan generated by the server.

[0124] "Audio and visual feedback" refers to feedback that the terminal provides to the child in real time by means of audio output, screen display, etc., based on instructions from the server.

[0125] A "machine learning algorithm" is a software technology that uses large amounts of data to learn models and optimize data analysis and support plans.

[0126] "Model updating" means retraining the machine learning algorithm based on new data collected to continuously improve the accuracy of assistance.

[0127] This invention is a system for providing individualized and appropriate support to children with developmental disabilities, and is composed of three elements: a server, a terminal, and a user. This system monitors the child's behavior and emotional state in real time, analyzes the data, and provides an optimal support plan, thereby achieving individualized and appropriate support.

[0128] System configuration

[0129] server

[0130] The server is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the device. The server is equipped with a high-performance processor and performs data analysis using Python and R. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms that infer emotions from the child's facial expressions.

[0131] Terminal

[0132] The device is a device that monitors a child's behavior and emotional state using cameras and sensors and sends the collected data to a server. The device is equipped with a camera and motion detection sensors, and captures and records the child's facial expressions and movements in real time. The device converts the collected data into packet data at regular intervals and sends it to the server using a secure communication protocol such as HTTPS.

[0133] User

[0134] The user is a teacher or support worker who inputs and checks the child's condition and the support content. The user inputs information through the terminal interface and saves it on the server. This allows the situation to be tracked in real time and effective support to be provided.

[0135] Specific examples

[0136] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0137] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0138] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0139] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[0140] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0141] Example 2: Autism Spectrum Disorder (ASD)

[0142] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0143] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0144] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0145] 4. The device will say, "This is a new challenge. Let's start with this."

[0146] Example prompts for generative AI models

[0147] 1. "Concerning a system that finds the best support method for children with developmental disabilities, please explain the roles and specific operations of the server, device, and user."

[0148] 2. Please explain in detail the processing steps of a system that provides individually appropriate support to children with developmental disabilities, and also state how the system operates in the cases of ADHD and ASD, as examples.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1:

[0151] The device monitors the child's behavior and emotional state. Specifically, it uses a camera to recognize the child's face and analyzes their emotional state from their facial expressions. It also uses a motion detection sensor to track their body movements in real time. This process uses image analysis and motion detection software. The input is real-time data of the child's face and movements, and the output is analyzed emotional state and behavioral data.

[0152] Step 2:

[0153] The device sends the collected and analyzed data to a server. The collected data includes the child's behavior, facial expressions, and speech. The device converts this data into packet data and sends it to the server using a secure communication protocol such as HTTPS. The input is the collected emotional state and behavior data, and the output is the data packets sent to the server.

[0154] Step 3:

[0155] The server analyzes the received data. Specifically, it uses Python or R to analyze the information stored in the database and uses machine learning algorithms such as TensorFlow or PyTorch to identify the child's emotional state and behavioral patterns. The input is the data packet sent to the server, and the output is the analyzed emotional state and behavioral patterns.

[0156] Step 4:

[0157] The server generates an individualized support plan based on the analysis results. For example, if it determines that a child has difficulty writing kanji, it will create a specific plan such as "providing support for writing slowly." This plan is customized based on a pre-prepared support plan template. The input is the analyzed emotional state and behavioral patterns, and the output is a specific individualized support plan.

[0158] Step 5:

[0159] The server sends feedback instructions to the device based on the generated individual support plan. For example, it sends audio instructions such as "It's okay to write slowly" or visual instructions such as "Let's move on to the next step." These instructions are converted back into packet data and sent to the device in encrypted form. The input is the generated individual support plan, and the output is the feedback instructions sent to the device.

[0160] Step 6:

[0161] The device provides audio and visual feedback in real time based on the feedback instructions sent from the server. The device plays back audio instructions using a synthesized speech device and displays visual instructions using a display or projector. For example, the device may say, "It's okay to write slowly," and display "Let's move on to the next step" on the screen. The input is the feedback instructions sent from the server, and the output is the audio and visual feedback to the child.

[0162] Step 7:

[0163] The server uses a machine learning algorithm to continuously update the model based on the collected data and feedback results. Specifically, it integrates past data with new data to retrain the model and provide more effective feedback in the next lesson. The input is the feedback results and additional data, and the output is the updated machine learning model.

[0164] (Application example 1)

[0165] 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."

[0166] Conventional systems have had difficulty providing appropriate feedback in real time to children who require individual assistance or to machines whose work status needs to be monitored. Furthermore, there has been a lack of systems that can quickly detect abnormalities and provide appropriate instructions, which reduces the effectiveness of assistance and production efficiency. The purpose of this invention is to solve these problems and improve the accuracy and speed of individual assistance and abnormality detection.

[0167] 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.

[0168] In this invention, the server includes means for monitoring behavior and status and collecting data in real time, means for analyzing the collected data and generating an individualized support plan, means for providing audio and visual feedback in real time based on the individualized support plan, means for continuously updating the generation AI model based on the collected data and the individualized support plan, and means for monitoring the working status of the machine, detecting abnormalities in real time, and issuing a stop instruction. This makes it possible to provide optimal support in real time to subjects requiring individual support, and to quickly detect and respond to machine abnormalities.

[0169] An "action" refers to a series of movements or operations performed by a machine or a user.

[0170] "Status" refers to the current situation or condition of a machine or user, and abnormalities or peculiarities are detected through monitoring.

[0171] "Real-time" refers to a method of instantly collecting, analyzing, and providing feedback on current information.

[0172] "Data" refers to collected information about behavior and conditions, which is analyzed to generate a support plan.

[0173] "Collection" refers to the act of compiling information about monitored behaviors and conditions.

[0174] "Analysis" is the process of understanding the content of the collected data and generating the necessary support plan.

[0175] An "individual support plan" refers to a plan that includes the optimal support content and instructions for each individual based on analyzed data.

[0176] "Generation" refers to the act of creating a new support plan based on collected data and analysis results.

[0177] "Feedback" is the process of providing audio and visual instructions and information to the subject based on the generated support plan.

[0178] "Voice feedback" is a means of conveying instructions to a subject using voice based on the generated assistance plan.

[0179] "Visual feedback" is a means of conveying instructions to a subject using visual information based on a generated assistance plan.

[0180] "Generative AI model" refers to a model used to generate a continuously updated assistance plan based on machine learning algorithms.

[0181] A "machine learning algorithm" is a method for automatically learning patterns and relationships from data and generating support plans based on that information.

[0182] "Updating" is the process of continuously improving the generative AI model based on new data and results collected to provide the optimal assistance plan.

[0183] "Monitoring" refers to the act of observing a subject's behavior or condition and collecting data.

[0184] "Anomaly detection" is the process of identifying unusual behavior or conditions from monitored data and taking appropriate action.

[0185] The present invention is a system that monitors behavior and status in real time and provides appropriate support to individuals. The system functions in cooperation with a server, a terminal, and a user.

[0186] 1. Server

[0187] The server is a central processing unit that analyzes data and generates individualized support plans. It runs machine learning algorithms and continuously optimizes support methods based on the collected data. The basic components are a high-performance processor, sufficient memory capacity, and a database management system. Specifically, machine learning libraries such as TensorFlow and Keras are used.

[0188] 2. Terminal

[0189] The devices monitor the behavior and status of the robot and collect data in real time. Specifically, these devices include cameras and sensors. The devices send the collected data to a server and receive feedback instructions from the server. OpenCV is used to process camera footage in real time, and the Paho MQTT library is used to communicate with the server.

[0190] 3. Users

[0191] The user inputs and confirms the target's situation and the support content. The user inputs the data through the device, and the information is stored on the server. The server analyzes this data and the collected data to determine the appropriate support method.

[0192] Specific examples

[0193] Detecting abnormalities on the production line and providing work guidance

[0194] 1. Data Collection:

[0195] A camera installed on the terminal monitors the operation of machines on the production line and captures video in real time.

[0196] 2. Data Transfer:

[0197] Data collected on the device is sent to the server using MQTT.

[0198] 3. Data Analysis:

[0199] The data received by the server is analyzed to evaluate the machine's operating status. For example, an anomaly detection model using TensorFlow can be used to detect machine malfunctions and problems.

[0200] 4. Generate an Individual Support Plan:

[0201] Based on the analysis results, the server generates an individualized support plan and sends feedback to the device.

[0202] 5. Providing Feedback:

[0203] The device provides real-time feedback, for example, audio prompts and visual instructions.

[0204] Prompt Sentence Examples

[0205] Example prompts to give to a generative AI model:

[0206] I would like to design a system that monitors the work status of robots in a factory and automatically issues a stop command when an abnormality is detected. I would like the system to meet the following conditions:

[0207] 1. Use machine learning models to capture camera footage in real time and detect abnormal behavior.

[0208] 2. Data is sent to the server via MQTT.

[0209] 3. Provide feedback to the robot based on the results of the analysis on the server.

[0210] The system of the present invention monitors the operating status of the machine in real time, and when an abnormality is detected, it can provide prompt and appropriate feedback. Furthermore, by continuously optimizing the assistance method, it can realize effective assistance that meets individual needs.

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] The device monitors the operation of the machines on the production line and captures video in real time. The input is a camera image and the output is image data. The device uses the camera to acquire the video data and processes the images using the OpenCV library.

[0214] Step 2:

[0215] The image data collected by the device is sent to the server using the MQTT protocol. The input is the captured image data, and the output is the data sent to the server. The device uses the Paho MQTT library to compress the converted image data and send it to the server.

[0216] Step 3:

[0217] The server analyzes the received data and evaluates the machine's operating status. The input is image data received from the terminal, and the output is machine status information as the analysis result. The server uses TensorFlow to run machine learning models, analyze the image data, and detect abnormalities.

[0218] Step 4:

[0219] The server generates an individualized support plan based on the analysis results and sends feedback instructions to the device. The input is the machine status information, and the output is the generated support plan. The server creates the support plan and sends feedback instructions to the device using the MQTT protocol.

[0220] Step 5:

[0221] The terminal provides real-time feedback based on the feedback instructions received from the server. The input is the feedback instruction from the server, and the output is audio or visual feedback to the user or machine. The terminal executes the instructions using an audio output device or display, and stops the machine if an abnormality is detected.

[0222] 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.

[0223] The present invention provides a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[0224] System configuration

[0225] 1. Server

[0226] A central processing unit that analyzes data and generates individualized support plans.

[0227] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[0228] An emotion engine is used to perform a detailed analysis of the child's emotional state.

[0229] 2. Terminal

[0230] A device used in classrooms to monitor children's behavior and emotional state in real time.

[0231] It has means for providing audio and visual feedback.

[0232] 3. Users

[0233] A teacher or support worker who inputs and checks the child's situation and support details.

[0234] Program processing

[0235] Data collection

[0236] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[0237] For example, it detects information such as "Mr. A has a confused expression."

[0238] Data Transfer

[0239] The terminal transmits the collected behavioral and emotional data to a server.

[0240] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[0241] Data analysis

[0242] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[0243] For example, it may be determined that "Mr. A is not good at writing kanji and is confused."

[0244] Generate an individual support plan

[0245] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[0246] For example, the support plan may be decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[0247] Feedback Instructions

[0248] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[0249] For example, tell the device, "Instruct it to say to A-kun, 'It's okay to write slowly.'"

[0250] Providing Feedback

[0251] The terminal provides real-time audio and visual feedback based on instructions from the server.

[0252] For example, the system provides audio guidance such as, "A-kun, it's okay to write slowly," and visual support.

[0253] Continuous learning and updates

[0254] The server continuously optimizes using machine learning models based on the collected data and feedback.

[0255] For example, it learns data such as "Mr. A was able to write kanji when he was spoken to slowly."

[0256] Specific examples

[0257] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0258] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0259] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0260] 3. The server analyzes the received data using an emotion engine and generates an individual support plan that states, "Check A's progress every five minutes and praise him."

[0261] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0262] Example 2: Autism Spectrum Disorder (ASD)

[0263] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0264] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0265] 3. Using its emotion engine, the server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0266] 4. The device will say, "This is a new challenge. Let's start with this."

[0267] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[0268] The processing flow will be explained below.

[0269] Step 1:

[0270] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[0271] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[0272] Step 2:

[0273] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[0274] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[0275] Step 3:

[0276] The terminal transmits the collected behavioral and emotional data to a server.

[0277] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[0278] Step 4:

[0279] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[0280] Example: The emotion engine analyzes that "Mr. A is confused" and determines that "his concentration is declining."

[0281] Step 5:

[0282] The server generates an individual support plan based on the analysis results.

[0283] Example: The support plan is decided as follows: "For Mr. A, we will provide assistance with dictation and check his progress every five minutes."

[0284] Step 6:

[0285] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[0286] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[0287] Step 7:

[0288] The terminal provides real-time audio and visual feedback based on instructions from the server.

[0289] Example: "A-kun, it's okay to write slowly," is given as audio guidance, and visual support is also displayed.

[0290] Step 8:

[0291] After providing the feedback, the device monitors the child's reaction again and sends the data to the server.

[0292] Example: Confirm that "A-kun is responding to the audio feedback and concentrating again" and send that data to the server.

[0293] Step 9:

[0294] The server then analyzes whether the feedback was effective based on the received data and updates the machine learning model.

[0295] Example: Learning from data that "Mr. A's concentration improved after receiving feedback" will improve the support plan for future support.

[0296] Step 10:

[0297] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[0298] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[0299] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[0300] Example 2

[0301] 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."

[0302] Until now, there has been a lack of effective and efficient methods for providing individualized support to children with developmental disorders. In particular, there has been a need for a system that can monitor a child's behavior and emotional state in real time, generate an individualized support plan based on that information, and provide feedback at the appropriate time. Furthermore, there has been a need for a machine learning model that can continuously optimize the system based on the collected data.

[0303] 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.

[0304] In this invention, the server includes means for monitoring a child's behavior and emotional state in real time using a camera or sensor and collecting data, means for transmitting the collected data to the server, means for the server to analyze the received data using an emotion engine, means for generating an individualized support plan based on the analysis results, means for transmitting feedback instructions for the generated individualized support plan to the terminal, means for the terminal to provide audio and visual feedback in real time based on the instructions, and means for continuously optimizing a machine learning model based on the collected data and feedback results. This makes it possible to provide individualized and appropriate support to children with developmental disabilities and effectively improve their learning environment.

[0305] "Child behavior and emotional state" refers to the actions and attitudes a child displays, as well as their emotional state at the time. Behavior includes movements and speech, and emotional state includes happiness, anger, sadness, confusion, etc.

[0306] "Cameras and sensors" are devices used to sense a child's behavior and emotional state. Cameras capture video and facial expressions, and sensors collect physiological data such as heart rate and temperature.

[0307] "Server" is a central processing unit that analyzes collected data, generates and manages individual support plans, and provides feedback.

[0308] An "emotion engine" refers to an algorithm or program that analyzes collected data and determines a child's emotional state.

[0309] An "individualized support plan" is a plan that includes support methods and feedback that are most appropriate for a child based on the child's behavior and emotional state.

[0310] "Feedback instructions" refers to data or messages that instruct how to provide feedback to a child based on the generated individualized support plan.

[0311] "Audio and visual feedback" refers to the means of providing assistance and guidance to a child through audio messages and visuals on a display.

[0312] A "machine learning model" refers to a statistical model or algorithm that uses collected data to continuously derive the optimal support method.

[0313] "Real-time" refers to data collection, analysis, and feedback being provided immediately with little to no delay.

[0314] The present invention is a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[0315] System configuration

[0316] 1. Server

[0317] Hardware: High-performance central processing unit (e.g., Intel Xeon processor)

[0318] Software: Machine learning algorithms, emotion engine

[0319] Functions: Data analysis, generation of individualized support plans, sending feedback instructions, optimization of machine learning models

[0320] 2. Terminal

[0321] Hardware: Cameras, sensors, audio output devices, displays

[0322] Software: Data collection applications, feedback provision applications

[0323] Functions: Monitor behavior and emotional state, collect and transmit data, provide audio and visual feedback

[0324] 3. Users

[0325] Role: Teacher or support worker

[0326] Function: Enter and check the child's situation and support details

[0327] Program processing

[0328] Data collection

[0329] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[0330] For example, the device uses a camera to record the child's facial expressions and movements, and if the child looks confused, for example, it will recognize that expression and generate data. It also uses sensors to collect physiological data such as heart rate and body temperature. For example, if the heart rate increases, the device will determine that the child is excited.

[0331] Data Transfer

[0332] The device sends collected behavioral and emotional data to a server. The collected data is time-stamped, allowing changes over time to be tracked. For example, if a confused expression or an elevated heart rate is detected, the data is sent immediately.

[0333] Data analysis

[0334] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data. For example, if data labeled as confusion is paired with an increase in heart rate, the server will determine that the child is "confused." It also compares this with past data, and if it is determined that the child has frequently experienced confusion when writing kanji in the past, it will determine that the child "has difficulty writing kanji."

[0335] Generate an individual support plan

[0336] The server generates an individualized support plan based on the analysis results. This plan includes the most appropriate support method for the child. For example, a support plan might be created that states, "For A-kun, we will provide support for dictation and check progress every five minutes."

[0337] Providing Feedback

[0338] The device provides real-time audio and visual feedback based on instructions from the server. For example, it may provide audio guidance such as "A-kun, it's okay to write slowly," and show an animation on the display showing the stroke order for kanji characters.

[0339] Continuous learning and updates

[0340] The server continuously optimizes the machine learning model based on the collected data and feedback. For example, data such as "Mr. A learned to write kanji when spoken to slowly" is used as feedback, and the model is regularly trained to improve its accuracy.

[0341] Examples of prompts to input to a generative AI model based on concrete examples

[0342] ADHD prompt:

[0343] Teach your child how to support them when they lose focus, including specific examples of when to check their progress every five minutes and when to praise them.

[0344] Prompt statement for ASD:

[0345] Please tell me how to support a child on the autism spectrum when they are overwhelmed by a new task. Please provide examples of specific commands or prompts to use first.

[0346] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1: Collect data

[0349] The device monitors the child's behavior and emotional state in real time using cameras and sensors. Camera footage and sensor data (e.g., heart rate and body temperature) are taken as input and collected as data. Specifically, the camera captures the child's facial expressions and movements, and the sensors measure physiological data. The collected data includes information such as "Mr. A's facial expression looks confused" and "His heart rate has increased." This data is saved with a timestamp.

[0350] Step 2: Transferring data

[0351] The device sends the collected behavioral and emotional data to the server. The input is the data collected in step 1, and the output is sending the data to the server. Specifically, the device uploads the collected data in real time and transfers it to the server along with a timestamp. For example, data such as "Mr. A has a confused expression" or "his heart rate is rising" is sent to the server.

[0352] Step 3: Analyze the data

[0353] The server uses an emotion engine to analyze the child's emotional state and behavioral patterns based on the received data. The input is the data sent from the device, and the output is the analysis results. Specifically, the server activates the emotion engine and analyzes the data. For example, if there is data labeled as confusion and an increase in heart rate, it will judge the child as "confused." It will also compare this with past data and draw the overall conclusion that "writing kanji is difficult."

[0354] Step 4: Generate an individual support plan

[0355] The server generates an individualized support plan based on the analysis results. The input is the results of the data analysis, and the output is the individualized support plan. Specifically, the server runs an algorithm based on the analysis results and creates an individualized support plan. For example, it generates a specific support plan that states, "Mr. A needs help with dictation, and progress will be checked every five minutes."

[0356] Step 5: Feedback Instructions

[0357] The server sends feedback instructions for the generated individual support plan to the terminal. The input is the generated individual support plan, and the output is sending feedback instructions to the terminal. In concrete terms, the server sends instructions to the terminal on how to provide feedback. It sends instructions such as "Tell Mr. A that it's okay to write slowly."

[0358] Step 6: Provide feedback

[0359] The device provides real-time audio and visual feedback based on instructions from the server. The input is the feedback instruction from the server, and the output is the execution of the audio and visual feedback. Specifically, the device reads out an audio message and gives audio guidance such as "A-kun, it's okay to write slowly." It also displays an animation showing the stroke order of kanji characters on the display.

[0360] Step 7: Continuous learning and updating

[0361] The server continuously optimizes the machine learning model based on the collected data and feedback results. The input is the feedback results and new data, and the output is an updated machine learning model. Specifically, the server trains the machine learning model using newly collected data to improve the accuracy of the model. For example, the server uses the feedback data, "Mr. A has become able to write kanji when spoken to slowly," to update the model.

[0362] (Application example 2)

[0363] 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."

[0364] Improving the work efficiency and safety of workers in factories is an important issue for many companies. However, it is difficult to grasp the state and emotions of individual workers in real time and provide support accordingly. In particular, when workers become fatigued after working for long periods of time, there is a problem that work efficiency decreases and safety risks increase if they are not given timely breaks or support.

[0365] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for monitoring movements and emotional states and collecting data in real time, means for analyzing the collected data and generating an individual support plan, means for providing audio and visual feedback in real time based on the individual support plan, means for continuously updating a machine learning model based on the collected data and the individual support plan, means for collecting and analyzing movement and facial expression data of workers, means for generating a support plan to improve work efficiency and safety based on the analysis results, and means for providing feedback to workers in real time based on the support plan. This makes it possible to grasp the worker's fatigue state and work efficiency in real time and provide breaks and support at appropriate times.

[0366] "Movement" is a series of movements or movements that a worker makes with their hands and body.

[0367] "Emotional state" refers to the psychological state or state of mind of the worker, including, for example, fatigue and stress.

[0368] "Terminal" means a device for collecting data and presenting analysis results, and may include a camera, microphone, and display.

[0369] "Server" refers to a central processing unit that analyzes data and generates support plans, and is a computer that operates on the cloud.

[0370] "Data collection" refers to obtaining information about behavior and emotional state using devices such as cameras and sensors.

[0371] "Analysis" is the process of using algorithms to analyze information based on collected data and derive meaningful results.

[0372] An "individual support plan" is a plan that specifies the support content appropriate for each worker based on the analysis results.

[0373] "Feedback" refers to instructions and advice given to workers based on the individual support plan, and is given through audio or visual means.

[0374] A "machine learning model" is an algorithm that continuously improves the accuracy of analysis based on collected data.

[0375] A "support plan" is a plan for the specific support provided to workers to improve work efficiency and safety.

[0376] The present invention provides a system for improving the efficiency and safety of workers in factories. The system monitors their movements and emotional states, analyzes the collected data, and generates an individualized assistance plan for each worker. The system also provides real-time audio and visual feedback based on the generated assistance plan, and continuously updates a machine learning model based on the collected data and the assistance plan.

[0377] 1. Hardware and Software Used

[0378] The system uses the following hardware and software:

[0379] Hardware

[0380] High-resolution camera: Used to monitor the movements and facial expressions of workers in real time.

[0381] Microphone: Used to collect the voice of the worker.

[0382] Sensors: Used to measure the worker's body temperature and heart rate.

[0383] Display: Used to provide visual feedback.

[0384] software

[0385] Python: Used for data analysis and running machine learning algorithms.

[0386] OpenCV: A library used to analyze image data.

[0387] FaceAPI: A library for analyzing worker facial expressions.

[0388] TensorFlow: Used to train and optimize machine learning models.

[0389] 2. System Operation Mechanism

[0390] The server analyzes data collected by high-resolution cameras, microphones, and sensors, and determines the worker's condition based on that information. For example, the following process is performed:

[0391] Data processing and calculation

[0392] Data collection: The device monitors the worker's movements and emotional state and collects data in real time.

[0393] For example, it detects the facial expression of a worker showing signs of fatigue and the frequency of manual work.

[0394] Data transfer: The terminal sends the collected data to the server.

[0395] For example, the worker's movement data and facial expression data are transferred to the server.

[0396] Data analysis: Based on the received data, the server analyzes the worker's condition using FaceAPI and OpenCV.

[0397] For example, it is determined that "Worker A is tired."

[0398] Generation of an individualized support plan: The server generates an individualized support plan based on the analysis results.

[0399] For example, create a support plan such as "Worker A will have a 30-minute break."

[0400] Feedback instruction: The server sends feedback instructions for the generated assistance plan to the terminal.

[0401] For example, "Instruct worker A to take a 30-minute break."

[0402] Providing feedback: The device provides audio and visual feedback in real time based on instructions from the server.

[0403] For example, "It's break time now" is announced aloud and displayed on the screen.

[0404] Continuous learning and updates: The server optimizes the machine learning model based on the collected data and feedback.

[0405] For example, the machine learning model is updated based on data that indicates "work efficiency improved after breaks."

[0406] 3. Specific Examples

[0407] As a concrete example, consider a scenario where fatigue caused by long-term work is detected and appropriate breaks are advised:

[0408] Example 1: Fatigue from long hours of work

[0409] 1. Workers were monitored to detect signs of fatigue (e.g., facial slackness and frequent yawning).

[0410] 2. The server determines that "a break is needed" and instructs "a 30-minute break."

[0411] 3. The terminal notifies the worker, "It's break time. Please take a 30-minute break."

[0412] Prompts for generative AI models

[0413] An example prompt is:

[0414] Prompt statement:

[0415] "Using the behavioral and facial expression data of a worker working in a factory as input data, generate a feedback program for an assistive robot to improve work efficiency. This program will have the function of determining the worker's fatigue level and suggesting appropriate break times. Also, clarify the hardware and software to be used and include specific examples from a real-life scenario."

[0416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0417] Step 1:

[0418] Data collection: The device uses high-resolution cameras, microphones, and sensors to collect data on the worker's movements, facial expressions, body temperature, heart rate, and other aspects in real time. Camera footage, audio, body temperature, heart rate, and other data are collected as input data. This makes it possible to understand the worker's current condition in detail. The collected data is obtained as output.

[0419] Step 2:

[0420] Data Transfer: The device sends the collected data to the server via Wi-Fi or other communication means. As input, there is the data collected in step 1. The data is converted into an appropriate format and sent to the server. As output, the transmitted data reaches the server and moves to the next analysis step.

[0421] Step 3:

[0422] Data analysis: The server analyzes the received data using image analysis libraries such as OpenCV and FaceAPI, and machine learning algorithms (such as TensorFlow). The input is data on movements and emotional states sent from the device. Based on this, data calculations and analysis are performed to determine the worker's condition. The output is an analysis result such as "Worker A is tired."

[0423] Step 4:

[0424] Generation of individual support plan: Based on the analysis results, the server generates an individual support plan suited to the worker's condition. The input is the analysis results obtained in step 3. A machine learning model is used to determine the optimal support method. The output is a specific support plan such as "Worker A is recommended to take a 30-minute break."

[0425] Step 5:

[0426] Feedback instruction: The server sends the generated assistance plan to the terminal and instructs the worker to provide feedback. The input is the assistance plan generated in step 4. This is sent to the terminal as a feedback instruction. The output is the feedback instruction sent to the terminal.

[0427] Step 6:

[0428] Providing feedback: The terminal provides audio and visual feedback in real time based on the feedback instructions from the server. For example, it may display "It's break time now. Please take a 30-minute break" on the display and provide a similar instruction via audio. The input is the feedback instruction sent from the server. The output is the feedback provided to the worker.

[0429] Step 7:

[0430] Continuous learning and updating: The server optimizes the machine learning model based on the collected data and feedback results. The inputs are effectiveness measurement data and feedback results. Using these, the machine learning model algorithm is continuously trained and updated to improve the accuracy of the support method. The output is an optimized machine learning model.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] [Second embodiment]

[0435] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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."

[0447] The present invention provides a system for providing individualized and appropriate support to children with developmental disabilities, which includes the following configuration and operation.

[0448] System configuration

[0449] 1. Server

[0450] A central processing unit that analyzes data and generates individualized support plans.

[0451] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[0452] 2. Terminal

[0453] A device used in classrooms to monitor children's behavior and emotional state in real time.

[0454] It has means for providing audio and visual feedback.

[0455] 3. Users

[0456] A teacher or support worker who inputs and checks the child's situation and support details.

[0457] Program processing

[0458] Data collection

[0459] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[0460] For example, it detects information such as "Mr. A has a confused expression."

[0461] Data Transfer

[0462] The device sends the collected data, including the child's behavior, facial expressions, and speech, to a server.

[0463] Data analysis

[0464] The server analyzes the child's current emotional state and behavioral patterns based on the received data.

[0465] For example, it may be determined that "Mr. A has difficulty writing kanji."

[0466] Generate an individual support plan

[0467] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[0468] For example, it generates a specific plan such as "Provide support for A-kun to write kanji slowly."

[0469] Feedback Instructions

[0470] The server transmits feedback instructions to the terminal based on the generated individual support plan.

[0471] For example, you can give instructions such as, "Tell A, 'It's okay to write slowly.'"

[0472] Providing Feedback

[0473] The terminal provides audio and visual feedback in real time based on feedback instructions sent from the server.

[0474] For example, audio instructions such as, "A-kun, it's okay to write slowly."

[0475] Continuous learning and updates

[0476] The server uses machine learning algorithms to continuously update the model based on the collected data and feedback.

[0477] For example, learning from past data to provide more effective feedback in the next lesson.

[0478] Specific examples

[0479] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0480] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0481] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0482] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[0483] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0484] Example 2: Autism Spectrum Disorder (ASD)

[0485] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0486] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0487] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0488] 4. The device will say, "This is a new challenge. Let's start with this."

[0489] In this way, this system works in collaboration between the server, terminal, and user to provide individually appropriate support, effectively improving the learning environment for children with developmental disabilities.

[0490] The processing flow will be explained below.

[0491] Step 1:

[0492] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[0493] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[0494] Step 2:

[0495] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[0496] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[0497] Step 3:

[0498] The terminal transmits the collected behavioral and emotional data to a server.

[0499] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[0500] Step 4:

[0501] The server analyzes the received data and determines the child's emotional state and behavioral patterns.

[0502] Example: "Mr. A is not good at writing kanji and is confused."

[0503] Step 5:

[0504] The server generates an individual support plan based on the analysis results.

[0505] Example: The support plan is decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[0506] Step 6:

[0507] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[0508] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[0509] Step 7:

[0510] The terminal provides real-time audio and visual feedback based on instructions from the server.

[0511] Example: "A-kun, it's okay to write slowly," provides audio guidance and visual support.

[0512] Step 8:

[0513] The server continuously collects data on the child's reactions after the feedback is provided and uses machine learning models to optimize the support method.

[0514] For example, the system learns data such as "Mr. A was able to write kanji when we spoke to him slowly."

[0515] Step 9:

[0516] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[0517] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[0518] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[0519] Example 1

[0520] 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."

[0521] Currently, individual support for children with developmental disorders generally relies on the experience and intuition of teachers and support staff. As a result, support content is often inconsistent and ineffective. It is also extremely difficult to monitor children's behavior and emotional state in real time and provide appropriate feedback. Furthermore, there is no system for evaluating the effectiveness of support methods and continuously optimizing them, making it difficult to improve the quality of support. To address these challenges, a system is needed to provide consistent and effective support to children with developmental disorders.

[0522] 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.

[0523] In this invention, the server includes: a device that monitors a child's behavior and emotional state in real time using a camera or sensor and collects the data; a device that transmits the collected data to the server; a server that analyzes the child's emotional state and behavioral patterns based on the received data; a server that generates an individualized support plan based on the analysis results; a server that transmits feedback instructions to the device based on the generated individualized support plan; a server that provides audio and visual feedback in real time based on the feedback instructions sent from the server; and a server that continuously updates a model using a machine learning algorithm based on the collected data and feedback results. This makes it possible to provide individually appropriate support in real time, scientifically evaluate the effectiveness of the support, and continuously optimize it.

[0524] The "terminal" is a device that monitors a child's behavior and emotional state using cameras and sensors and transmits the collected data to a server.

[0525] The "server" is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the terminal.

[0526] A "camera" is a device that captures a child's facial and body movements to collect data in real time.

[0527] A "sensor" is a device used to monitor a child's behavior and emotional state, such as through motion detection and voice analysis.

[0528] "Data collection" means that the device uses cameras and sensors to monitor the child's behavior and emotional state in real time and record the information.

[0529] "Data transmission" means that the terminal transfers the collected data to the server.

[0530] "Data analysis" refers to identifying and analyzing the child's emotional state and behavioral patterns based on the data received by the server.

[0531] "Generation of an individual support plan" means that the server formulates the most appropriate support method for the child based on the analysis results.

[0532] "Feedback instructions" are specific behavioral or verbal instructions that are sent to the terminal based on the individual support plan generated by the server.

[0533] "Audio and visual feedback" refers to feedback that the terminal provides to the child in real time by means of audio output, screen display, etc., based on instructions from the server.

[0534] A "machine learning algorithm" is a software technology that uses large amounts of data to learn models and optimize data analysis and support plans.

[0535] "Model updating" means retraining the machine learning algorithm based on new data collected to continuously improve the accuracy of assistance.

[0536] This invention is a system for providing individualized and appropriate support to children with developmental disabilities, and is composed of three elements: a server, a terminal, and a user. This system monitors the child's behavior and emotional state in real time, analyzes the data, and provides an optimal support plan, thereby achieving individualized and appropriate support.

[0537] System configuration

[0538] server

[0539] The server is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the device. The server is equipped with a high-performance processor and performs data analysis using Python and R. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms that infer emotions from the child's facial expressions.

[0540] Terminal

[0541] The device is a device that monitors a child's behavior and emotional state using cameras and sensors and sends the collected data to a server. The device is equipped with a camera and motion detection sensors, and captures and records the child's facial expressions and movements in real time. The device converts the collected data into packet data at regular intervals and sends it to the server using a secure communication protocol such as HTTPS.

[0542] User

[0543] The user is a teacher or support worker who inputs and checks the child's condition and the support content. The user inputs information through the terminal interface and saves it on the server. This allows the situation to be tracked in real time and effective support to be provided.

[0544] Specific examples

[0545] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0546] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0547] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0548] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[0549] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0550] Example 2: Autism Spectrum Disorder (ASD)

[0551] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0552] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0553] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0554] 4. The device will say, "This is a new challenge. Let's start with this."

[0555] Example prompts for generative AI models

[0556] 1. "Concerning a system that finds the best support method for children with developmental disabilities, please explain the roles and specific operations of the server, device, and user."

[0557] 2. Please explain in detail the processing steps of a system that provides individually appropriate support to children with developmental disabilities, and also state how the system operates in the cases of ADHD and ASD, as examples.

[0558] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0559] Step 1:

[0560] The device monitors the child's behavior and emotional state. Specifically, it uses a camera to recognize the child's face and analyzes their emotional state from their facial expressions. It also uses a motion detection sensor to track their body movements in real time. This process uses image analysis and motion detection software. The input is real-time data of the child's face and movements, and the output is analyzed emotional state and behavioral data.

[0561] Step 2:

[0562] The device sends the collected and analyzed data to a server. The collected data includes the child's behavior, facial expressions, and speech. The device converts this data into packet data and sends it to the server using a secure communication protocol such as HTTPS. The input is the collected emotional state and behavior data, and the output is the data packets sent to the server.

[0563] Step 3:

[0564] The server analyzes the received data. Specifically, it uses Python or R to analyze the information stored in the database and uses machine learning algorithms such as TensorFlow or PyTorch to identify the child's emotional state and behavioral patterns. The input is the data packet sent to the server, and the output is the analyzed emotional state and behavioral patterns.

[0565] Step 4:

[0566] The server generates an individualized support plan based on the analysis results. For example, if it determines that a child has difficulty writing kanji, it will create a specific plan such as "providing support for writing slowly." This plan is customized based on a pre-prepared support plan template. The input is the analyzed emotional state and behavioral patterns, and the output is a specific individualized support plan.

[0567] Step 5:

[0568] The server sends feedback instructions to the device based on the generated individual support plan. For example, it sends audio instructions such as "It's okay to write slowly" or visual instructions such as "Let's move on to the next step." These instructions are converted back into packet data and sent to the device in encrypted form. The input is the generated individual support plan, and the output is the feedback instructions sent to the device.

[0569] Step 6:

[0570] The device provides audio and visual feedback in real time based on the feedback instructions sent from the server. The device plays back audio instructions using a synthesized speech device and displays visual instructions using a display or projector. For example, the device may say, "It's okay to write slowly," and display "Let's move on to the next step" on the screen. The input is the feedback instructions sent from the server, and the output is the audio and visual feedback to the child.

[0571] Step 7:

[0572] The server uses a machine learning algorithm to continuously update the model based on the collected data and feedback results. Specifically, it integrates past data with new data to retrain the model and provide more effective feedback in the next lesson. The input is the feedback results and additional data, and the output is the updated machine learning model.

[0573] (Application example 1)

[0574] 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."

[0575] Conventional systems have had difficulty providing appropriate feedback in real time to children who require individual assistance or to machines whose work status needs to be monitored. Furthermore, there has been a lack of systems that can quickly detect abnormalities and provide appropriate instructions, which reduces the effectiveness of assistance and production efficiency. The purpose of this invention is to solve these problems and improve the accuracy and speed of individual assistance and abnormality detection.

[0576] 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.

[0577] In this invention, the server includes means for monitoring behavior and status and collecting data in real time, means for analyzing the collected data and generating an individualized support plan, means for providing audio and visual feedback in real time based on the individualized support plan, means for continuously updating the generation AI model based on the collected data and the individualized support plan, and means for monitoring the working status of the machine, detecting abnormalities in real time, and issuing a stop instruction. This makes it possible to provide optimal support in real time to subjects requiring individual support, and to quickly detect and respond to machine abnormalities.

[0578] An "action" refers to a series of movements or operations performed by a machine or a user.

[0579] "Status" refers to the current situation or condition of a machine or user, and abnormalities or peculiarities are detected through monitoring.

[0580] "Real-time" refers to a method of instantly collecting, analyzing, and providing feedback on current information.

[0581] "Data" refers to collected information about behavior and conditions, which is analyzed to generate a support plan.

[0582] "Collection" refers to the act of compiling information about monitored behaviors and conditions.

[0583] "Analysis" is the process of understanding the content of the collected data and generating the necessary support plan.

[0584] An "individual support plan" refers to a plan that includes the optimal support content and instructions for each individual based on analyzed data.

[0585] "Generation" refers to the act of creating a new support plan based on collected data and analysis results.

[0586] "Feedback" is the process of providing audio and visual instructions and information to the subject based on the generated support plan.

[0587] "Voice feedback" is a means of conveying instructions to a subject using voice based on the generated assistance plan.

[0588] "Visual feedback" is a means of conveying instructions to a subject using visual information based on a generated assistance plan.

[0589] "Generative AI model" refers to a model used to generate a continuously updated assistance plan based on machine learning algorithms.

[0590] A "machine learning algorithm" is a method for automatically learning patterns and relationships from data and generating support plans based on that information.

[0591] "Updating" is the process of continuously improving the generative AI model based on new data and results collected to provide the optimal assistance plan.

[0592] "Monitoring" refers to the act of observing a subject's behavior or condition and collecting data.

[0593] "Anomaly detection" is the process of identifying unusual behavior or conditions from monitored data and taking appropriate action.

[0594] The present invention is a system that monitors behavior and status in real time and provides appropriate support to individuals. The system functions in cooperation with a server, a terminal, and a user.

[0595] 1. Server

[0596] The server is a central processing unit that analyzes data and generates individualized support plans. It runs machine learning algorithms and continuously optimizes support methods based on the collected data. The basic components are a high-performance processor, sufficient memory capacity, and a database management system. Specifically, machine learning libraries such as TensorFlow and Keras are used.

[0597] 2. Terminal

[0598] The devices monitor the behavior and status of the robot and collect data in real time. Specifically, these devices include cameras and sensors. The devices send the collected data to a server and receive feedback instructions from the server. OpenCV is used to process camera footage in real time, and the Paho MQTT library is used to communicate with the server.

[0599] 3. Users

[0600] The user inputs and confirms the target's situation and the support content. The user inputs the data through the device, and the information is stored on the server. The server analyzes this data and the collected data to determine the appropriate support method.

[0601] Specific examples

[0602] Detecting abnormalities on the production line and providing work guidance

[0603] 1. Data Collection:

[0604] A camera installed on the terminal monitors the operation of machines on the production line and captures video in real time.

[0605] 2. Data Transfer:

[0606] Data collected on the device is sent to the server using MQTT.

[0607] 3. Data Analysis:

[0608] The data received by the server is analyzed to evaluate the machine's operating status. For example, an anomaly detection model using TensorFlow can be used to detect machine malfunctions and problems.

[0609] 4. Generate an Individual Support Plan:

[0610] Based on the analysis results, the server generates an individualized support plan and sends feedback to the device.

[0611] 5. Providing Feedback:

[0612] The device provides real-time feedback, for example, audio prompts and visual instructions.

[0613] Prompt Sentence Examples

[0614] Example prompts to give to a generative AI model:

[0615] I would like to design a system that monitors the work status of robots in a factory and automatically issues a stop command when an abnormality is detected. I would like the system to meet the following conditions:

[0616] 1. Use machine learning models to capture camera footage in real time and detect abnormal behavior.

[0617] 2. Data is sent to the server via MQTT.

[0618] 3. Provide feedback to the robot based on the results of the analysis on the server.

[0619] The system of the present invention monitors the operating status of the machine in real time, and when an abnormality is detected, it can provide prompt and appropriate feedback. Furthermore, by continuously optimizing the assistance method, it can realize effective assistance that meets individual needs.

[0620] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0621] Step 1:

[0622] The device monitors the operation of the machines on the production line and captures video in real time. The input is a camera image and the output is image data. The device uses the camera to acquire the video data and processes the images using the OpenCV library.

[0623] Step 2:

[0624] The image data collected by the device is sent to the server using the MQTT protocol. The input is the captured image data, and the output is the data sent to the server. The device uses the Paho MQTT library to compress the converted image data and send it to the server.

[0625] Step 3:

[0626] The server analyzes the received data and evaluates the machine's operating status. The input is image data received from the terminal, and the output is machine status information as the analysis result. The server uses TensorFlow to run machine learning models, analyze the image data, and detect abnormalities.

[0627] Step 4:

[0628] The server generates an individualized support plan based on the analysis results and sends feedback instructions to the device. The input is the machine status information, and the output is the generated support plan. The server creates the support plan and sends feedback instructions to the device using the MQTT protocol.

[0629] Step 5:

[0630] The terminal provides real-time feedback based on the feedback instructions received from the server. The input is the feedback instruction from the server, and the output is audio or visual feedback to the user or machine. The terminal executes the instructions using an audio output device or display, and stops the machine if an abnormality is detected.

[0631] 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.

[0632] The present invention provides a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[0633] System configuration

[0634] 1. Server

[0635] A central processing unit that analyzes data and generates individualized support plans.

[0636] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[0637] An emotion engine is used to perform a detailed analysis of the child's emotional state.

[0638] 2. Terminal

[0639] A device used in classrooms to monitor children's behavior and emotional state in real time.

[0640] It has means for providing audio and visual feedback.

[0641] 3. Users

[0642] A teacher or support worker who inputs and checks the child's situation and support details.

[0643] Program processing

[0644] Data collection

[0645] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[0646] For example, it detects information such as "Mr. A has a confused expression."

[0647] Data Transfer

[0648] The terminal transmits the collected behavioral and emotional data to a server.

[0649] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[0650] Data analysis

[0651] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[0652] For example, it may be determined that "Mr. A is not good at writing kanji and is confused."

[0653] Generate an individual support plan

[0654] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[0655] For example, the support plan may be decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[0656] Feedback Instructions

[0657] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[0658] For example, tell the device, "Instruct it to say to A-kun, 'It's okay to write slowly.'"

[0659] Providing Feedback

[0660] The terminal provides real-time audio and visual feedback based on instructions from the server.

[0661] For example, the system provides audio guidance such as, "A-kun, it's okay to write slowly," and visual support.

[0662] Continuous learning and updates

[0663] The server continuously optimizes using machine learning models based on the collected data and feedback.

[0664] For example, it learns data such as "Mr. A was able to write kanji when he was spoken to slowly."

[0665] Specific examples

[0666] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0667] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0668] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0669] 3. The server analyzes the received data using an emotion engine and generates an individual support plan that states, "Check A's progress every five minutes and praise him."

[0670] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0671] Example 2: Autism Spectrum Disorder (ASD)

[0672] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0673] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0674] 3. Using its emotion engine, the server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0675] 4. The device will say, "This is a new challenge. Let's start with this."

[0676] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[0677] The processing flow will be explained below.

[0678] Step 1:

[0679] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[0680] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[0681] Step 2:

[0682] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[0683] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[0684] Step 3:

[0685] The terminal transmits the collected behavioral and emotional data to a server.

[0686] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[0687] Step 4:

[0688] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[0689] Example: The emotion engine analyzes that "Mr. A is confused" and determines that "his concentration is declining."

[0690] Step 5:

[0691] The server generates an individual support plan based on the analysis results.

[0692] Example: The support plan is decided as follows: "For Mr. A, we will provide assistance with dictation and check his progress every five minutes."

[0693] Step 6:

[0694] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[0695] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[0696] Step 7:

[0697] The terminal provides real-time audio and visual feedback based on instructions from the server.

[0698] Example: "A-kun, it's okay to write slowly," is given as audio guidance, and visual support is also displayed.

[0699] Step 8:

[0700] After providing the feedback, the device monitors the child's reaction again and sends the data to the server.

[0701] Example: Confirm that "A-kun is responding to the audio feedback and concentrating again" and send that data to the server.

[0702] Step 9:

[0703] The server then analyzes whether the feedback was effective based on the received data and updates the machine learning model.

[0704] Example: Learning from data that "Mr. A's concentration improved after receiving feedback" will improve the support plan for future support.

[0705] Step 10:

[0706] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[0707] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[0708] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[0709] Example 2

[0710] 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."

[0711] Until now, there has been a lack of effective and efficient methods for providing individualized support to children with developmental disorders. In particular, there has been a need for a system that can monitor a child's behavior and emotional state in real time, generate an individualized support plan based on that information, and provide feedback at the appropriate time. Furthermore, there has been a need for a machine learning model that can continuously optimize the system based on the collected data.

[0712] 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.

[0713] In this invention, the server includes means for monitoring a child's behavior and emotional state in real time using a camera or sensor and collecting data, means for transmitting the collected data to the server, means for the server to analyze the received data using an emotion engine, means for generating an individualized support plan based on the analysis results, means for transmitting feedback instructions for the generated individualized support plan to the terminal, means for the terminal to provide audio and visual feedback in real time based on the instructions, and means for continuously optimizing a machine learning model based on the collected data and feedback results. This makes it possible to provide individualized and appropriate support to children with developmental disabilities and effectively improve their learning environment.

[0714] "Child behavior and emotional state" refers to the actions and attitudes a child displays, as well as their emotional state at the time. Behavior includes movements and speech, and emotional state includes happiness, anger, sadness, confusion, etc.

[0715] "Cameras and sensors" are devices used to sense a child's behavior and emotional state. Cameras capture video and facial expressions, and sensors collect physiological data such as heart rate and temperature.

[0716] "Server" is a central processing unit that analyzes collected data, generates and manages individual support plans, and provides feedback.

[0717] An "emotion engine" refers to an algorithm or program that analyzes collected data and determines a child's emotional state.

[0718] An "individualized support plan" is a plan that includes support methods and feedback that are most appropriate for a child based on the child's behavior and emotional state.

[0719] "Feedback instructions" refers to data or messages that instruct how to provide feedback to a child based on the generated individualized support plan.

[0720] "Audio and visual feedback" refers to the means of providing assistance and guidance to a child through audio messages and visuals on a display.

[0721] A "machine learning model" refers to a statistical model or algorithm that uses collected data to continuously derive the optimal support method.

[0722] "Real-time" refers to data collection, analysis, and feedback being provided immediately with little to no delay.

[0723] The present invention is a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[0724] System configuration

[0725] 1. Server

[0726] Hardware: High-performance central processing unit (e.g., Intel Xeon processor)

[0727] Software: Machine learning algorithms, emotion engine

[0728] Functions: Data analysis, generation of individualized support plans, sending feedback instructions, optimization of machine learning models

[0729] 2. Terminal

[0730] Hardware: Cameras, sensors, audio output devices, displays

[0731] Software: Data collection applications, feedback provision applications

[0732] Functions: Monitor behavior and emotional state, collect and transmit data, provide audio and visual feedback

[0733] 3. Users

[0734] Role: Teacher or support worker

[0735] Function: Enter and check the child's situation and support details

[0736] Program processing

[0737] Data collection

[0738] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[0739] For example, the device uses a camera to record the child's facial expressions and movements, and if the child looks confused, for example, it will recognize that expression and generate data. It also uses sensors to collect physiological data such as heart rate and body temperature. For example, if the heart rate increases, the device will determine that the child is excited.

[0740] Data Transfer

[0741] The device sends collected behavioral and emotional data to a server. The collected data is time-stamped, allowing changes over time to be tracked. For example, if a confused expression or an elevated heart rate is detected, the data is sent immediately.

[0742] Data analysis

[0743] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data. For example, if data labeled as confusion is paired with an increase in heart rate, the server will determine that the child is "confused." It also compares this with past data, and if it is determined that the child has frequently experienced confusion when writing kanji in the past, it will determine that the child "has difficulty writing kanji."

[0744] Generate an individual support plan

[0745] The server generates an individualized support plan based on the analysis results. This plan includes the most appropriate support method for the child. For example, a support plan might be created that states, "For A-kun, we will provide support for dictation and check progress every five minutes."

[0746] Providing Feedback

[0747] The device provides real-time audio and visual feedback based on instructions from the server. For example, it may provide audio guidance such as "A-kun, it's okay to write slowly," and show an animation on the display showing the stroke order for kanji characters.

[0748] Continuous learning and updates

[0749] The server continuously optimizes the machine learning model based on the collected data and feedback. For example, data such as "Mr. A learned to write kanji when spoken to slowly" is used as feedback, and the model is regularly trained to improve its accuracy.

[0750] Examples of prompts to input to a generative AI model based on concrete examples

[0751] ADHD prompt:

[0752] Teach your child how to support them when they lose focus, including specific examples of when to check their progress every five minutes and when to praise them.

[0753] Prompt statement for ASD:

[0754] Please tell me how to support a child on the autism spectrum when they are overwhelmed by a new task. Please provide examples of specific commands or prompts to use first.

[0755] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[0756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0757] Step 1: Collect data

[0758] The device monitors the child's behavior and emotional state in real time using cameras and sensors. Camera footage and sensor data (e.g., heart rate and body temperature) are taken as input and collected as data. Specifically, the camera captures the child's facial expressions and movements, and the sensors measure physiological data. The collected data includes information such as "Mr. A's facial expression looks confused" and "His heart rate has increased." This data is saved with a timestamp.

[0759] Step 2: Transferring data

[0760] The device sends the collected behavioral and emotional data to the server. The input is the data collected in step 1, and the output is sending the data to the server. Specifically, the device uploads the collected data in real time and transfers it to the server along with a timestamp. For example, data such as "Mr. A has a confused expression" or "his heart rate is rising" is sent to the server.

[0761] Step 3: Analyze the data

[0762] The server uses an emotion engine to analyze the child's emotional state and behavioral patterns based on the received data. The input is the data sent from the device, and the output is the analysis results. Specifically, the server activates the emotion engine and analyzes the data. For example, if there is data labeled as confusion and an increase in heart rate, it will judge the child as "confused." It will also compare this with past data and draw the overall conclusion that "writing kanji is difficult."

[0763] Step 4: Generate an individual support plan

[0764] The server generates an individualized support plan based on the analysis results. The input is the results of the data analysis, and the output is the individualized support plan. Specifically, the server runs an algorithm based on the analysis results and creates an individualized support plan. For example, it generates a specific support plan that states, "Mr. A needs help with dictation, and progress will be checked every five minutes."

[0765] Step 5: Feedback Instructions

[0766] The server sends feedback instructions for the generated individual support plan to the terminal. The input is the generated individual support plan, and the output is sending feedback instructions to the terminal. In concrete terms, the server sends instructions to the terminal on how to provide feedback. It sends instructions such as "Tell Mr. A that it's okay to write slowly."

[0767] Step 6: Provide feedback

[0768] The device provides real-time audio and visual feedback based on instructions from the server. The input is the feedback instruction from the server, and the output is the execution of the audio and visual feedback. Specifically, the device reads out an audio message and gives audio guidance such as "A-kun, it's okay to write slowly." It also displays an animation showing the stroke order of kanji characters on the display.

[0769] Step 7: Continuous learning and updating

[0770] The server continuously optimizes the machine learning model based on the collected data and feedback results. The input is the feedback results and new data, and the output is an updated machine learning model. Specifically, the server trains the machine learning model using newly collected data to improve the accuracy of the model. For example, the server uses the feedback data, "Mr. A has become able to write kanji when spoken to slowly," to update the model.

[0771] (Application example 2)

[0772] 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."

[0773] Improving the work efficiency and safety of workers in factories is an important issue for many companies. However, it is difficult to grasp the state and emotions of individual workers in real time and provide support accordingly. In particular, when workers become fatigued after working for long periods of time, there is a problem that work efficiency decreases and safety risks increase if they are not given timely breaks or support.

[0774] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for monitoring movements and emotional states and collecting data in real time, means for analyzing the collected data and generating an individual support plan, means for providing audio and visual feedback in real time based on the individual support plan, means for continuously updating a machine learning model based on the collected data and the individual support plan, means for collecting and analyzing movement and facial expression data of workers, means for generating a support plan to improve work efficiency and safety based on the analysis results, and means for providing feedback to workers in real time based on the support plan. This makes it possible to grasp the worker's fatigue state and work efficiency in real time and provide breaks and support at appropriate times.

[0775] "Movement" is a series of movements or movements that a worker makes with their hands and body.

[0776] "Emotional state" refers to the psychological state or state of mind of the worker, including, for example, fatigue and stress.

[0777] "Terminal" means a device for collecting data and presenting analysis results, and may include a camera, microphone, and display.

[0778] "Server" refers to a central processing unit that analyzes data and generates support plans, and is a computer that operates on the cloud.

[0779] "Data collection" refers to obtaining information about behavior and emotional state using devices such as cameras and sensors.

[0780] "Analysis" is the process of using algorithms to analyze information based on collected data and derive meaningful results.

[0781] An "individual support plan" is a plan that specifies the support content appropriate for each worker based on the analysis results.

[0782] "Feedback" refers to instructions and advice given to workers based on the individual support plan, and is given through audio or visual means.

[0783] A "machine learning model" is an algorithm that continuously improves the accuracy of analysis based on collected data.

[0784] A "support plan" is a plan for the specific support provided to workers to improve work efficiency and safety.

[0785] The present invention provides a system for improving the efficiency and safety of workers in factories. The system monitors their movements and emotional states, analyzes the collected data, and generates an individualized assistance plan for each worker. The system also provides real-time audio and visual feedback based on the generated assistance plan, and continuously updates a machine learning model based on the collected data and the assistance plan.

[0786] 1. Hardware and Software Used

[0787] The system uses the following hardware and software:

[0788] Hardware

[0789] High-resolution camera: Used to monitor the movements and facial expressions of workers in real time.

[0790] Microphone: Used to collect the voice of the worker.

[0791] Sensors: Used to measure the worker's body temperature and heart rate.

[0792] Display: Used to provide visual feedback.

[0793] software

[0794] Python: Used for data analysis and running machine learning algorithms.

[0795] OpenCV: A library used to analyze image data.

[0796] FaceAPI: A library for analyzing worker facial expressions.

[0797] TensorFlow: Used to train and optimize machine learning models.

[0798] 2. System Operation Mechanism

[0799] The server analyzes data collected by high-resolution cameras, microphones, and sensors, and determines the worker's condition based on that information. For example, the following process is performed:

[0800] Data processing and calculation

[0801] Data collection: The device monitors the worker's movements and emotional state and collects data in real time.

[0802] For example, it detects the facial expression of a worker showing signs of fatigue and the frequency of manual work.

[0803] Data transfer: The terminal sends the collected data to the server.

[0804] For example, the worker's movement data and facial expression data are transferred to the server.

[0805] Data analysis: Based on the received data, the server analyzes the worker's condition using FaceAPI and OpenCV.

[0806] For example, it is determined that "Worker A is tired."

[0807] Generation of an individualized support plan: The server generates an individualized support plan based on the analysis results.

[0808] For example, create a support plan such as "Worker A will have a 30-minute break."

[0809] Feedback instruction: The server sends feedback instructions for the generated assistance plan to the terminal.

[0810] For example, "Instruct worker A to take a 30-minute break."

[0811] Providing feedback: The device provides audio and visual feedback in real time based on instructions from the server.

[0812] For example, "It's break time now" is announced aloud and displayed on the screen.

[0813] Continuous learning and updates: The server optimizes the machine learning model based on the collected data and feedback.

[0814] For example, the machine learning model is updated based on data that indicates "work efficiency improved after breaks."

[0815] 3. Specific Examples

[0816] As a concrete example, consider a scenario where fatigue caused by long-term work is detected and appropriate breaks are advised:

[0817] Example 1: Fatigue from long hours of work

[0818] 1. Workers were monitored to detect signs of fatigue (e.g., facial slackness and frequent yawning).

[0819] 2. The server determines that "a break is needed" and instructs "a 30-minute break."

[0820] 3. The terminal notifies the worker, "It's break time. Please take a 30-minute break."

[0821] Prompts for generative AI models

[0822] An example prompt is:

[0823] Prompt statement:

[0824] "Using the behavioral and facial expression data of a worker working in a factory as input data, generate a feedback program for an assistive robot to improve work efficiency. This program will have the function of determining the worker's fatigue level and suggesting appropriate break times. Also, clarify the hardware and software to be used and include specific examples from a real-life scenario."

[0825] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0826] Step 1:

[0827] Data collection: The device uses high-resolution cameras, microphones, and sensors to collect data on the worker's movements, facial expressions, body temperature, heart rate, and other aspects in real time. Camera footage, audio, body temperature, heart rate, and other data are collected as input data. This makes it possible to understand the worker's current condition in detail. The collected data is obtained as output.

[0828] Step 2:

[0829] Data Transfer: The device sends the collected data to the server via Wi-Fi or other communication means. As input, there is the data collected in step 1. The data is converted into an appropriate format and sent to the server. As output, the transmitted data reaches the server and moves to the next analysis step.

[0830] Step 3:

[0831] Data analysis: The server analyzes the received data using image analysis libraries such as OpenCV and FaceAPI, and machine learning algorithms (such as TensorFlow). The input is data on movements and emotional states sent from the device. Based on this, data calculations and analysis are performed to determine the worker's condition. The output is an analysis result such as "Worker A is tired."

[0832] Step 4:

[0833] Generation of individual support plan: Based on the analysis results, the server generates an individual support plan suited to the worker's condition. The input is the analysis results obtained in step 3. A machine learning model is used to determine the optimal support method. The output is a specific support plan such as "Worker A is recommended to take a 30-minute break."

[0834] Step 5:

[0835] Feedback instruction: The server sends the generated assistance plan to the terminal and instructs the worker to provide feedback. The input is the assistance plan generated in step 4. This is sent to the terminal as a feedback instruction. The output is the feedback instruction sent to the terminal.

[0836] Step 6:

[0837] Providing feedback: The terminal provides audio and visual feedback in real time based on the feedback instructions from the server. For example, it may display "It's break time now. Please take a 30-minute break" on the display and provide a similar instruction via audio. The input is the feedback instruction sent from the server. The output is the feedback provided to the worker.

[0838] Step 7:

[0839] Continuous learning and updating: The server optimizes the machine learning model based on the collected data and feedback results. The inputs are effectiveness measurement data and feedback results. Using these, the machine learning model algorithm is continuously trained and updated to improve the accuracy of the support method. The output is an optimized machine learning model.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] [Third embodiment]

[0844] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0845] 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.

[0846] 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).

[0847] 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.

[0848] 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.

[0849] 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).

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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."

[0856] The present invention provides a system for providing individualized and appropriate support to children with developmental disabilities, which includes the following configuration and operation.

[0857] System configuration

[0858] 1. Server

[0859] A central processing unit that analyzes data and generates individualized support plans.

[0860] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[0861] 2. Terminal

[0862] A device used in classrooms to monitor children's behavior and emotional state in real time.

[0863] It has means for providing audio and visual feedback.

[0864] 3. Users

[0865] A teacher or support worker who inputs and checks the child's situation and support details.

[0866] Program processing

[0867] Data collection

[0868] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[0869] For example, it detects information such as "Mr. A has a confused expression."

[0870] Data Transfer

[0871] The device sends the collected data, including the child's behavior, facial expressions, and speech, to a server.

[0872] Data analysis

[0873] The server analyzes the child's current emotional state and behavioral patterns based on the received data.

[0874] For example, it may be determined that "Mr. A has difficulty writing kanji."

[0875] Generate an individual support plan

[0876] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[0877] For example, it generates a specific plan such as "Provide support for A-kun to write kanji slowly."

[0878] Feedback Instructions

[0879] The server transmits feedback instructions to the terminal based on the generated individual support plan.

[0880] For example, you can give instructions such as, "Tell A, 'It's okay to write slowly.'"

[0881] Providing Feedback

[0882] The terminal provides audio and visual feedback in real time based on feedback instructions sent from the server.

[0883] For example, audio instructions such as, "A-kun, it's okay to write slowly."

[0884] Continuous learning and updates

[0885] The server uses machine learning algorithms to continuously update the model based on the collected data and feedback.

[0886] For example, learning from past data to provide more effective feedback in the next lesson.

[0887] Specific examples

[0888] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0889] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0890] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0891] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[0892] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0893] Example 2: Autism Spectrum Disorder (ASD)

[0894] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0895] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0896] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0897] 4. The device will say, "This is a new challenge. Let's start with this."

[0898] In this way, this system works in collaboration between the server, terminal, and user to provide individually appropriate support, effectively improving the learning environment for children with developmental disabilities.

[0899] The processing flow will be explained below.

[0900] Step 1:

[0901] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[0902] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[0903] Step 2:

[0904] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[0905] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[0906] Step 3:

[0907] The terminal transmits the collected behavioral and emotional data to a server.

[0908] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[0909] Step 4:

[0910] The server analyzes the received data and determines the child's emotional state and behavioral patterns.

[0911] Example: "Mr. A is not good at writing kanji and is confused."

[0912] Step 5:

[0913] The server generates an individual support plan based on the analysis results.

[0914] Example: The support plan is decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[0915] Step 6:

[0916] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[0917] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[0918] Step 7:

[0919] The terminal provides real-time audio and visual feedback based on instructions from the server.

[0920] Example: "A-kun, it's okay to write slowly," provides audio guidance and visual support.

[0921] Step 8:

[0922] The server continuously collects data on the child's reactions after the feedback is provided and uses machine learning models to optimize the support method.

[0923] For example, the system learns data such as "Mr. A was able to write kanji when we spoke to him slowly."

[0924] Step 9:

[0925] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[0926] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[0927] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[0928] Example 1

[0929] 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."

[0930] Currently, individual support for children with developmental disorders generally relies on the experience and intuition of teachers and support staff. As a result, support content is often inconsistent and ineffective. It is also extremely difficult to monitor children's behavior and emotional state in real time and provide appropriate feedback. Furthermore, there is no system for evaluating the effectiveness of support methods and continuously optimizing them, making it difficult to improve the quality of support. To address these challenges, a system is needed to provide consistent and effective support to children with developmental disorders.

[0931] 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.

[0932] In this invention, the server includes: a device that monitors a child's behavior and emotional state in real time using a camera or sensor and collects the data; a device that transmits the collected data to the server; a server that analyzes the child's emotional state and behavioral patterns based on the received data; a server that generates an individualized support plan based on the analysis results; a server that transmits feedback instructions to the device based on the generated individualized support plan; a server that provides audio and visual feedback in real time based on the feedback instructions sent from the server; and a server that continuously updates a model using a machine learning algorithm based on the collected data and feedback results. This makes it possible to provide individually appropriate support in real time, scientifically evaluate the effectiveness of the support, and continuously optimize it.

[0933] The "terminal" is a device that monitors a child's behavior and emotional state using cameras and sensors and transmits the collected data to a server.

[0934] The "server" is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the terminal.

[0935] A "camera" is a device that captures a child's facial and body movements to collect data in real time.

[0936] A "sensor" is a device used to monitor a child's behavior and emotional state, such as through motion detection and voice analysis.

[0937] "Data collection" means that the device uses cameras and sensors to monitor the child's behavior and emotional state in real time and record the information.

[0938] "Data transmission" means that the terminal transfers the collected data to the server.

[0939] "Data analysis" refers to identifying and analyzing the child's emotional state and behavioral patterns based on the data received by the server.

[0940] "Generation of an individual support plan" means that the server formulates the most appropriate support method for the child based on the analysis results.

[0941] "Feedback instructions" are specific behavioral or verbal instructions that are sent to the terminal based on the individual support plan generated by the server.

[0942] "Audio and visual feedback" refers to feedback that the terminal provides to the child in real time by means of audio output, screen display, etc., based on instructions from the server.

[0943] A "machine learning algorithm" is a software technology that uses large amounts of data to learn models and optimize data analysis and support plans.

[0944] "Model updating" means retraining the machine learning algorithm based on new data collected to continuously improve the accuracy of assistance.

[0945] This invention is a system for providing individualized and appropriate support to children with developmental disabilities, and is composed of three elements: a server, a terminal, and a user. This system monitors the child's behavior and emotional state in real time, analyzes the data, and provides an optimal support plan, thereby achieving individualized and appropriate support.

[0946] System configuration

[0947] server

[0948] The server is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the device. The server is equipped with a high-performance processor and performs data analysis using Python and R. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms that infer emotions from the child's facial expressions.

[0949] Terminal

[0950] The device is a device that monitors a child's behavior and emotional state using cameras and sensors and sends the collected data to a server. The device is equipped with a camera and motion detection sensors, and captures and records the child's facial expressions and movements in real time. The device converts the collected data into packet data at regular intervals and sends it to the server using a secure communication protocol such as HTTPS.

[0951] User

[0952] The user is a teacher or support worker who inputs and checks the child's condition and the support content. The user inputs information through the terminal interface and saves it on the server. This allows the situation to be tracked in real time and effective support to be provided.

[0953] Specific examples

[0954] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[0955] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[0956] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[0957] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[0958] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[0959] Example 2: Autism Spectrum Disorder (ASD)

[0960] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[0961] 2. The device captures Mr. A's confused expression and sends the data to the server.

[0962] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[0963] 4. The device will say, "This is a new challenge. Let's start with this."

[0964] Example prompts for generative AI models

[0965] 1. "Concerning a system that finds the best support method for children with developmental disabilities, please explain the roles and specific operations of the server, device, and user."

[0966] 2. Please explain in detail the processing steps of a system that provides individually appropriate support to children with developmental disabilities, and also state how the system operates in the cases of ADHD and ASD, as examples.

[0967] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0968] Step 1:

[0969] The device monitors the child's behavior and emotional state. Specifically, it uses a camera to recognize the child's face and analyzes their emotional state from their facial expressions. It also uses a motion detection sensor to track their body movements in real time. This process uses image analysis and motion detection software. The input is real-time data of the child's face and movements, and the output is analyzed emotional state and behavioral data.

[0970] Step 2:

[0971] The device sends the collected and analyzed data to a server. The collected data includes the child's behavior, facial expressions, and speech. The device converts this data into packet data and sends it to the server using a secure communication protocol such as HTTPS. The input is the collected emotional state and behavior data, and the output is the data packets sent to the server.

[0972] Step 3:

[0973] The server analyzes the received data. Specifically, it uses Python or R to analyze the information stored in the database and uses machine learning algorithms such as TensorFlow or PyTorch to identify the child's emotional state and behavioral patterns. The input is the data packet sent to the server, and the output is the analyzed emotional state and behavioral patterns.

[0974] Step 4:

[0975] The server generates an individualized support plan based on the analysis results. For example, if it determines that a child has difficulty writing kanji, it will create a specific plan such as "providing support for writing slowly." This plan is customized based on a pre-prepared support plan template. The input is the analyzed emotional state and behavioral patterns, and the output is a specific individualized support plan.

[0976] Step 5:

[0977] The server sends feedback instructions to the device based on the generated individual support plan. For example, it sends audio instructions such as "It's okay to write slowly" or visual instructions such as "Let's move on to the next step." These instructions are converted back into packet data and sent to the device in encrypted form. The input is the generated individual support plan, and the output is the feedback instructions sent to the device.

[0978] Step 6:

[0979] The device provides audio and visual feedback in real time based on the feedback instructions sent from the server. The device plays back audio instructions using a synthesized speech device and displays visual instructions using a display or projector. For example, the device may say, "It's okay to write slowly," and display "Let's move on to the next step" on the screen. The input is the feedback instructions sent from the server, and the output is the audio and visual feedback to the child.

[0980] Step 7:

[0981] The server uses a machine learning algorithm to continuously update the model based on the collected data and feedback results. Specifically, it integrates past data with new data to retrain the model and provide more effective feedback in the next lesson. The input is the feedback results and additional data, and the output is the updated machine learning model.

[0982] (Application example 1)

[0983] 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."

[0984] Conventional systems have had difficulty providing appropriate feedback in real time to children who require individual assistance or to machines whose work status needs to be monitored. Furthermore, there has been a lack of systems that can quickly detect abnormalities and provide appropriate instructions, which reduces the effectiveness of assistance and production efficiency. The purpose of this invention is to solve these problems and improve the accuracy and speed of individual assistance and abnormality detection.

[0985] 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.

[0986] In this invention, the server includes means for monitoring behavior and status and collecting data in real time, means for analyzing the collected data and generating an individualized support plan, means for providing audio and visual feedback in real time based on the individualized support plan, means for continuously updating the generation AI model based on the collected data and the individualized support plan, and means for monitoring the working status of the machine, detecting abnormalities in real time, and issuing a stop instruction. This makes it possible to provide optimal support in real time to subjects requiring individual support, and to quickly detect and respond to machine abnormalities.

[0987] An "action" refers to a series of movements or operations performed by a machine or a user.

[0988] "Status" refers to the current situation or condition of a machine or user, and abnormalities or peculiarities are detected through monitoring.

[0989] "Real-time" refers to a method of instantly collecting, analyzing, and providing feedback on current information.

[0990] "Data" refers to collected information about behavior and conditions, which is analyzed to generate a support plan.

[0991] "Collection" refers to the act of compiling information about monitored behaviors and conditions.

[0992] "Analysis" is the process of understanding the content of the collected data and generating the necessary support plan.

[0993] An "individual support plan" refers to a plan that includes the optimal support content and instructions for each individual based on analyzed data.

[0994] "Generation" refers to the act of creating a new support plan based on collected data and analysis results.

[0995] "Feedback" is the process of providing audio and visual instructions and information to the subject based on the generated support plan.

[0996] "Voice feedback" is a means of conveying instructions to a subject using voice based on the generated assistance plan.

[0997] "Visual feedback" is a means of conveying instructions to a subject using visual information based on a generated assistance plan.

[0998] "Generative AI model" refers to a model used to generate a continuously updated assistance plan based on machine learning algorithms.

[0999] A "machine learning algorithm" is a method for automatically learning patterns and relationships from data and generating support plans based on that information.

[1000] "Updating" is the process of continuously improving the generative AI model based on new data and results collected to provide the optimal assistance plan.

[1001] "Monitoring" refers to the act of observing a subject's behavior or condition and collecting data.

[1002] "Anomaly detection" is the process of identifying unusual behavior or conditions from monitored data and taking appropriate action.

[1003] The present invention is a system that monitors behavior and status in real time and provides appropriate support to individuals. The system functions in cooperation with a server, a terminal, and a user.

[1004] 1. Server

[1005] The server is a central processing unit that analyzes data and generates individualized support plans. It runs machine learning algorithms and continuously optimizes support methods based on the collected data. The basic components are a high-performance processor, sufficient memory capacity, and a database management system. Specifically, machine learning libraries such as TensorFlow and Keras are used.

[1006] 2. Terminal

[1007] The devices monitor the behavior and status of the robot and collect data in real time. Specifically, these devices include cameras and sensors. The devices send the collected data to a server and receive feedback instructions from the server. OpenCV is used to process camera footage in real time, and the Paho MQTT library is used to communicate with the server.

[1008] 3. Users

[1009] The user inputs and confirms the target's situation and the support content. The user inputs the data through the device, and the information is stored on the server. The server analyzes this data and the collected data to determine the appropriate support method.

[1010] Specific examples

[1011] Detecting abnormalities on the production line and providing work guidance

[1012] 1. Data Collection:

[1013] A camera installed on the terminal monitors the operation of machines on the production line and captures video in real time.

[1014] 2. Data Transfer:

[1015] Data collected on the device is sent to the server using MQTT.

[1016] 3. Data Analysis:

[1017] The data received by the server is analyzed to evaluate the machine's operating status. For example, an anomaly detection model using TensorFlow can be used to detect machine malfunctions and problems.

[1018] 4. Generate an Individual Support Plan:

[1019] Based on the analysis results, the server generates an individualized support plan and sends feedback to the device.

[1020] 5. Providing Feedback:

[1021] The device provides real-time feedback, for example, audio prompts and visual instructions.

[1022] Prompt Sentence Examples

[1023] Example prompts to give to a generative AI model:

[1024] I would like to design a system that monitors the work status of robots in a factory and automatically issues a stop command when an abnormality is detected. I would like the system to meet the following conditions:

[1025] 1. Use machine learning models to capture camera footage in real time and detect abnormal behavior.

[1026] 2. Data is sent to the server via MQTT.

[1027] 3. Provide feedback to the robot based on the results of the analysis on the server.

[1028] The system of the present invention monitors the operating status of the machine in real time, and when an abnormality is detected, it can provide prompt and appropriate feedback. Furthermore, by continuously optimizing the assistance method, it can realize effective assistance that meets individual needs.

[1029] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1030] Step 1:

[1031] The device monitors the operation of the machines on the production line and captures video in real time. The input is a camera image and the output is image data. The device uses the camera to acquire the video data and processes the images using the OpenCV library.

[1032] Step 2:

[1033] The image data collected by the device is sent to the server using the MQTT protocol. The input is the captured image data, and the output is the data sent to the server. The device uses the Paho MQTT library to compress the converted image data and send it to the server.

[1034] Step 3:

[1035] The server analyzes the received data and evaluates the machine's operating status. The input is image data received from the terminal, and the output is machine status information as the analysis result. The server uses TensorFlow to run machine learning models, analyze the image data, and detect abnormalities.

[1036] Step 4:

[1037] The server generates an individualized support plan based on the analysis results and sends feedback instructions to the device. The input is the machine status information, and the output is the generated support plan. The server creates the support plan and sends feedback instructions to the device using the MQTT protocol.

[1038] Step 5:

[1039] The terminal provides real-time feedback based on the feedback instructions received from the server. The input is the feedback instruction from the server, and the output is audio or visual feedback to the user or machine. The terminal executes the instructions using an audio output device or display, and stops the machine if an abnormality is detected.

[1040] 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.

[1041] The present invention provides a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[1042] System configuration

[1043] 1. Server

[1044] A central processing unit that analyzes data and generates individualized support plans.

[1045] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[1046] An emotion engine is used to perform a detailed analysis of the child's emotional state.

[1047] 2. Terminal

[1048] A device used in classrooms to monitor children's behavior and emotional state in real time.

[1049] It has means for providing audio and visual feedback.

[1050] 3. Users

[1051] A teacher or support worker who inputs and checks the child's situation and support details.

[1052] Program processing

[1053] Data collection

[1054] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[1055] For example, it detects information such as "Mr. A has a confused expression."

[1056] Data Transfer

[1057] The terminal transmits the collected behavioral and emotional data to a server.

[1058] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[1059] Data analysis

[1060] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[1061] For example, it may be determined that "Mr. A is not good at writing kanji and is confused."

[1062] Generate an individual support plan

[1063] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[1064] For example, the support plan may be decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[1065] Feedback Instructions

[1066] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[1067] For example, tell the device, "Instruct it to say to A-kun, 'It's okay to write slowly.'"

[1068] Providing Feedback

[1069] The terminal provides real-time audio and visual feedback based on instructions from the server.

[1070] For example, the system provides audio guidance such as, "A-kun, it's okay to write slowly," and visual support.

[1071] Continuous learning and updates

[1072] The server continuously optimizes using machine learning models based on the collected data and feedback.

[1073] For example, it learns data such as "Mr. A was able to write kanji when he was spoken to slowly."

[1074] Specific examples

[1075] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[1076] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[1077] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[1078] 3. The server analyzes the received data using an emotion engine and generates an individual support plan that states, "Check A's progress every five minutes and praise him."

[1079] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[1080] Example 2: Autism Spectrum Disorder (ASD)

[1081] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[1082] 2. The device captures Mr. A's confused expression and sends the data to the server.

[1083] 3. Using its emotion engine, the server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[1084] 4. The device will say, "This is a new challenge. Let's start with this."

[1085] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[1086] The processing flow will be explained below.

[1087] Step 1:

[1088] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[1089] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[1090] Step 2:

[1091] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[1092] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[1093] Step 3:

[1094] The terminal transmits the collected behavioral and emotional data to a server.

[1095] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[1096] Step 4:

[1097] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[1098] Example: The emotion engine analyzes that "Mr. A is confused" and determines that "his concentration is declining."

[1099] Step 5:

[1100] The server generates an individual support plan based on the analysis results.

[1101] Example: The support plan is decided as follows: "For Mr. A, we will provide assistance with dictation and check his progress every five minutes."

[1102] Step 6:

[1103] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[1104] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[1105] Step 7:

[1106] The terminal provides real-time audio and visual feedback based on instructions from the server.

[1107] Example: "A-kun, it's okay to write slowly," is given as audio guidance, and visual support is also displayed.

[1108] Step 8:

[1109] After providing the feedback, the device monitors the child's reaction again and sends the data to the server.

[1110] Example: Confirm that "A-kun is responding to the audio feedback and concentrating again" and send that data to the server.

[1111] Step 9:

[1112] The server then analyzes whether the feedback was effective based on the received data and updates the machine learning model.

[1113] Example: Learning from data that "Mr. A's concentration improved after receiving feedback" will improve the support plan for future support.

[1114] Step 10:

[1115] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[1116] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[1117] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[1118] Example 2

[1119] 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."

[1120] Until now, there has been a lack of effective and efficient methods for providing individualized support to children with developmental disorders. In particular, there has been a need for a system that can monitor a child's behavior and emotional state in real time, generate an individualized support plan based on that information, and provide feedback at the appropriate time. Furthermore, there has been a need for a machine learning model that can continuously optimize the system based on the collected data.

[1121] 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.

[1122] In this invention, the server includes means for monitoring a child's behavior and emotional state in real time using a camera or sensor and collecting data, means for transmitting the collected data to the server, means for the server to analyze the received data using an emotion engine, means for generating an individualized support plan based on the analysis results, means for transmitting feedback instructions for the generated individualized support plan to the terminal, means for the terminal to provide audio and visual feedback in real time based on the instructions, and means for continuously optimizing a machine learning model based on the collected data and feedback results. This makes it possible to provide individualized and appropriate support to children with developmental disabilities and effectively improve their learning environment.

[1123] "Child behavior and emotional state" refers to the actions and attitudes a child displays, as well as their emotional state at the time. Behavior includes movements and speech, and emotional state includes happiness, anger, sadness, confusion, etc.

[1124] "Cameras and sensors" are devices used to sense a child's behavior and emotional state. Cameras capture video and facial expressions, and sensors collect physiological data such as heart rate and temperature.

[1125] "Server" is a central processing unit that analyzes collected data, generates and manages individual support plans, and provides feedback.

[1126] An "emotion engine" refers to an algorithm or program that analyzes collected data and determines a child's emotional state.

[1127] An "individualized support plan" is a plan that includes support methods and feedback that are most appropriate for a child based on the child's behavior and emotional state.

[1128] "Feedback instructions" refers to data or messages that instruct how to provide feedback to a child based on the generated individualized support plan.

[1129] "Audio and visual feedback" refers to the means of providing assistance and guidance to a child through audio messages and visuals on a display.

[1130] A "machine learning model" refers to a statistical model or algorithm that uses collected data to continuously derive the optimal support method.

[1131] "Real-time" refers to data collection, analysis, and feedback being provided immediately with little to no delay.

[1132] The present invention is a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[1133] System configuration

[1134] 1. Server

[1135] Hardware: High-performance central processing unit (e.g., Intel Xeon processor)

[1136] Software: Machine learning algorithms, emotion engine

[1137] Functions: Data analysis, generation of individualized support plans, sending feedback instructions, optimization of machine learning models

[1138] 2. Terminal

[1139] Hardware: Cameras, sensors, audio output devices, displays

[1140] Software: Data collection applications, feedback provision applications

[1141] Functions: Monitor behavior and emotional state, collect and transmit data, provide audio and visual feedback

[1142] 3. Users

[1143] Role: Teacher or support worker

[1144] Function: Enter and check the child's situation and support details

[1145] Program processing

[1146] Data collection

[1147] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[1148] For example, the device uses a camera to record the child's facial expressions and movements, and if the child looks confused, for example, it will recognize that expression and generate data. It also uses sensors to collect physiological data such as heart rate and body temperature. For example, if the heart rate increases, the device will determine that the child is excited.

[1149] Data Transfer

[1150] The device sends collected behavioral and emotional data to a server. The collected data is time-stamped, allowing changes over time to be tracked. For example, if a confused expression or an elevated heart rate is detected, the data is sent immediately.

[1151] Data analysis

[1152] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data. For example, if data labeled as confusion is paired with an increase in heart rate, the server will determine that the child is "confused." It also compares this with past data, and if it is determined that the child has frequently experienced confusion when writing kanji in the past, it will determine that the child "has difficulty writing kanji."

[1153] Generate an individual support plan

[1154] The server generates an individualized support plan based on the analysis results. This plan includes the most appropriate support method for the child. For example, a support plan might be created that states, "For A-kun, we will provide support for dictation and check progress every five minutes."

[1155] Providing Feedback

[1156] The device provides real-time audio and visual feedback based on instructions from the server. For example, it may provide audio guidance such as "A-kun, it's okay to write slowly," and show an animation on the display showing the stroke order for kanji characters.

[1157] Continuous learning and updates

[1158] The server continuously optimizes the machine learning model based on the collected data and feedback. For example, data such as "Mr. A learned to write kanji when spoken to slowly" is used as feedback, and the model is regularly trained to improve its accuracy.

[1159] Examples of prompts to input to a generative AI model based on concrete examples

[1160] ADHD prompt:

[1161] Teach your child how to support them when they lose focus, including specific examples of when to check their progress every five minutes and when to praise them.

[1162] Prompt statement for ASD:

[1163] Please tell me how to support a child on the autism spectrum when they are overwhelmed by a new task. Please provide examples of specific commands or prompts to use first.

[1164] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[1165] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1166] Step 1: Collect data

[1167] The device monitors the child's behavior and emotional state in real time using cameras and sensors. Camera footage and sensor data (e.g., heart rate and body temperature) are taken as input and collected as data. Specifically, the camera captures the child's facial expressions and movements, and the sensors measure physiological data. The collected data includes information such as "Mr. A's facial expression looks confused" and "His heart rate has increased." This data is saved with a timestamp.

[1168] Step 2: Transferring data

[1169] The device sends the collected behavioral and emotional data to the server. The input is the data collected in step 1, and the output is sending the data to the server. Specifically, the device uploads the collected data in real time and transfers it to the server along with a timestamp. For example, data such as "Mr. A has a confused expression" or "his heart rate is rising" is sent to the server.

[1170] Step 3: Analyze the data

[1171] The server uses an emotion engine to analyze the child's emotional state and behavioral patterns based on the received data. The input is the data sent from the device, and the output is the analysis results. Specifically, the server activates the emotion engine and analyzes the data. For example, if there is data labeled as confusion and an increase in heart rate, it will judge the child as "confused." It will also compare this with past data and draw the overall conclusion that "writing kanji is difficult."

[1172] Step 4: Generate an individual support plan

[1173] The server generates an individualized support plan based on the analysis results. The input is the results of the data analysis, and the output is the individualized support plan. Specifically, the server runs an algorithm based on the analysis results and creates an individualized support plan. For example, it generates a specific support plan that states, "Mr. A needs help with dictation, and progress will be checked every five minutes."

[1174] Step 5: Feedback Instructions

[1175] The server sends feedback instructions for the generated individual support plan to the terminal. The input is the generated individual support plan, and the output is sending feedback instructions to the terminal. In concrete terms, the server sends instructions to the terminal on how to provide feedback. It sends instructions such as "Tell Mr. A that it's okay to write slowly."

[1176] Step 6: Provide feedback

[1177] The device provides real-time audio and visual feedback based on instructions from the server. The input is the feedback instruction from the server, and the output is the execution of the audio and visual feedback. Specifically, the device reads out an audio message and gives audio guidance such as "A-kun, it's okay to write slowly." It also displays an animation showing the stroke order of kanji characters on the display.

[1178] Step 7: Continuous learning and updating

[1179] The server continuously optimizes the machine learning model based on the collected data and feedback results. The input is the feedback results and new data, and the output is an updated machine learning model. Specifically, the server trains the machine learning model using newly collected data to improve the accuracy of the model. For example, the server uses the feedback data, "Mr. A has become able to write kanji when spoken to slowly," to update the model.

[1180] (Application example 2)

[1181] 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."

[1182] Improving the work efficiency and safety of workers in factories is an important issue for many companies. However, it is difficult to grasp the state and emotions of individual workers in real time and provide support accordingly. In particular, when workers become fatigued after working for long periods of time, there is a problem that work efficiency decreases and safety risks increase if they are not given timely breaks or support.

[1183] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for monitoring movements and emotional states and collecting data in real time, means for analyzing the collected data and generating an individual support plan, means for providing audio and visual feedback in real time based on the individual support plan, means for continuously updating a machine learning model based on the collected data and the individual support plan, means for collecting and analyzing movement and facial expression data of workers, means for generating a support plan to improve work efficiency and safety based on the analysis results, and means for providing feedback to workers in real time based on the support plan. This makes it possible to grasp the worker's fatigue state and work efficiency in real time and provide breaks and support at appropriate times.

[1184] "Movement" is a series of movements or movements that a worker makes with their hands and body.

[1185] "Emotional state" refers to the psychological state or state of mind of the worker, including, for example, fatigue and stress.

[1186] "Terminal" means a device for collecting data and presenting analysis results, and may include a camera, microphone, and display.

[1187] "Server" refers to a central processing unit that analyzes data and generates support plans, and is a computer that operates on the cloud.

[1188] "Data collection" refers to obtaining information about behavior and emotional state using devices such as cameras and sensors.

[1189] "Analysis" is the process of using algorithms to analyze information based on collected data and derive meaningful results.

[1190] An "individual support plan" is a plan that specifies the support content appropriate for each worker based on the analysis results.

[1191] "Feedback" refers to instructions and advice given to workers based on the individual support plan, and is given through audio or visual means.

[1192] A "machine learning model" is an algorithm that continuously improves the accuracy of analysis based on collected data.

[1193] A "support plan" is a plan for the specific support provided to workers to improve work efficiency and safety.

[1194] The present invention provides a system for improving the efficiency and safety of workers in factories. The system monitors their movements and emotional states, analyzes the collected data, and generates an individualized assistance plan for each worker. The system also provides real-time audio and visual feedback based on the generated assistance plan, and continuously updates a machine learning model based on the collected data and the assistance plan.

[1195] 1. Hardware and Software Used

[1196] The system uses the following hardware and software:

[1197] Hardware

[1198] High-resolution camera: Used to monitor the movements and facial expressions of workers in real time.

[1199] Microphone: Used to collect the voice of the worker.

[1200] Sensors: Used to measure the worker's body temperature and heart rate.

[1201] Display: Used to provide visual feedback.

[1202] software

[1203] Python: Used for data analysis and running machine learning algorithms.

[1204] OpenCV: A library used to analyze image data.

[1205] FaceAPI: A library for analyzing worker facial expressions.

[1206] TensorFlow: Used to train and optimize machine learning models.

[1207] 2. System Operation Mechanism

[1208] The server analyzes data collected by high-resolution cameras, microphones, and sensors, and determines the worker's condition based on that information. For example, the following process is performed:

[1209] Data processing and calculation

[1210] Data collection: The device monitors the worker's movements and emotional state and collects data in real time.

[1211] For example, it detects the facial expression of a worker showing signs of fatigue and the frequency of manual work.

[1212] Data transfer: The terminal sends the collected data to the server.

[1213] For example, the worker's movement data and facial expression data are transferred to the server.

[1214] Data analysis: Based on the received data, the server analyzes the worker's condition using FaceAPI and OpenCV.

[1215] For example, it is determined that "Worker A is tired."

[1216] Generation of an individualized support plan: The server generates an individualized support plan based on the analysis results.

[1217] For example, create a support plan such as "Worker A will have a 30-minute break."

[1218] Feedback instruction: The server sends feedback instructions for the generated assistance plan to the terminal.

[1219] For example, "Instruct worker A to take a 30-minute break."

[1220] Providing feedback: The device provides audio and visual feedback in real time based on instructions from the server.

[1221] For example, "It's break time now" is announced aloud and displayed on the screen.

[1222] Continuous learning and updates: The server optimizes the machine learning model based on the collected data and feedback.

[1223] For example, the machine learning model is updated based on data that indicates "work efficiency improved after breaks."

[1224] 3. Specific Examples

[1225] As a concrete example, consider a scenario where fatigue caused by long-term work is detected and appropriate breaks are advised:

[1226] Example 1: Fatigue from long hours of work

[1227] 1. Workers were monitored to detect signs of fatigue (e.g., facial slackness and frequent yawning).

[1228] 2. The server determines that "a break is needed" and instructs "a 30-minute break."

[1229] 3. The terminal notifies the worker, "It's break time. Please take a 30-minute break."

[1230] Prompts for generative AI models

[1231] An example prompt is:

[1232] Prompt statement:

[1233] "Using the behavioral and facial expression data of a worker working in a factory as input data, generate a feedback program for an assistive robot to improve work efficiency. This program will have the function of determining the worker's fatigue level and suggesting appropriate break times. Also, clarify the hardware and software to be used and include specific examples from a real-life scenario."

[1234] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1235] Step 1:

[1236] Data collection: The device uses high-resolution cameras, microphones, and sensors to collect data on the worker's movements, facial expressions, body temperature, heart rate, and other aspects in real time. Camera footage, audio, body temperature, heart rate, and other data are collected as input data. This makes it possible to understand the worker's current condition in detail. The collected data is obtained as output.

[1237] Step 2:

[1238] Data Transfer: The device sends the collected data to the server via Wi-Fi or other communication means. As input, there is the data collected in step 1. The data is converted into an appropriate format and sent to the server. As output, the transmitted data reaches the server and moves to the next analysis step.

[1239] Step 3:

[1240] Data analysis: The server analyzes the received data using image analysis libraries such as OpenCV and FaceAPI, and machine learning algorithms (such as TensorFlow). The input is data on movements and emotional states sent from the device. Based on this, data calculations and analysis are performed to determine the worker's condition. The output is an analysis result such as "Worker A is tired."

[1241] Step 4:

[1242] Generation of individual support plan: Based on the analysis results, the server generates an individual support plan suited to the worker's condition. The input is the analysis results obtained in step 3. A machine learning model is used to determine the optimal support method. The output is a specific support plan such as "Worker A is recommended to take a 30-minute break."

[1243] Step 5:

[1244] Feedback instruction: The server sends the generated assistance plan to the terminal and instructs the worker to provide feedback. The input is the assistance plan generated in step 4. This is sent to the terminal as a feedback instruction. The output is the feedback instruction sent to the terminal.

[1245] Step 6:

[1246] Providing feedback: The terminal provides audio and visual feedback in real time based on the feedback instructions from the server. For example, it may display "It's break time now. Please take a 30-minute break" on the display and provide a similar instruction via audio. The input is the feedback instruction sent from the server. The output is the feedback provided to the worker.

[1247] Step 7:

[1248] Continuous learning and updating: The server optimizes the machine learning model based on the collected data and feedback results. The inputs are effectiveness measurement data and feedback results. Using these, the machine learning model algorithm is continuously trained and updated to improve the accuracy of the support method. The output is an optimized machine learning model.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] [Fourth embodiment]

[1253] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1254] 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.

[1255] 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).

[1256] 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.

[1257] 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.

[1258] 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).

[1259] 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.

[1260] 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.

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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."

[1266] The present invention provides a system for providing individualized and appropriate support to children with developmental disabilities, which includes the following configuration and operation.

[1267] System configuration

[1268] 1. Server

[1269] A central processing unit that analyzes data and generates individualized support plans.

[1270] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[1271] 2. Terminal

[1272] A device used in classrooms to monitor children's behavior and emotional state in real time.

[1273] It has means for providing audio and visual feedback.

[1274] 3. Users

[1275] A teacher or support worker who inputs and checks the child's situation and support details.

[1276] Program processing

[1277] Data collection

[1278] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[1279] For example, it detects information such as "Mr. A has a confused expression."

[1280] Data Transfer

[1281] The device sends the collected data, including the child's behavior, facial expressions, and speech, to a server.

[1282] Data analysis

[1283] The server analyzes the child's current emotional state and behavioral patterns based on the received data.

[1284] For example, it may be determined that "Mr. A has difficulty writing kanji."

[1285] Generate an individual support plan

[1286] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[1287] For example, it generates a specific plan such as "Provide support for A-kun to write kanji slowly."

[1288] Feedback Instructions

[1289] The server transmits feedback instructions to the terminal based on the generated individual support plan.

[1290] For example, you can give instructions such as, "Tell A, 'It's okay to write slowly.'"

[1291] Providing Feedback

[1292] The terminal provides audio and visual feedback in real time based on feedback instructions sent from the server.

[1293] For example, audio instructions such as, "A-kun, it's okay to write slowly."

[1294] Continuous learning and updates

[1295] The server uses machine learning algorithms to continuously update the model based on the collected data and feedback.

[1296] For example, learning from past data to provide more effective feedback in the next lesson.

[1297] Specific examples

[1298] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[1299] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[1300] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[1301] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[1302] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[1303] Example 2: Autism Spectrum Disorder (ASD)

[1304] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[1305] 2. The device captures Mr. A's confused expression and sends the data to the server.

[1306] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[1307] 4. The device will say, "This is a new challenge. Let's start with this."

[1308] In this way, this system works in collaboration between the server, terminal, and user to provide individually appropriate support, effectively improving the learning environment for children with developmental disabilities.

[1309] The processing flow will be explained below.

[1310] Step 1:

[1311] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[1312] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[1313] Step 2:

[1314] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[1315] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[1316] Step 3:

[1317] The terminal transmits the collected behavioral and emotional data to a server.

[1318] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[1319] Step 4:

[1320] The server analyzes the received data and determines the child's emotional state and behavioral patterns.

[1321] Example: "Mr. A is not good at writing kanji and is confused."

[1322] Step 5:

[1323] The server generates an individual support plan based on the analysis results.

[1324] Example: The support plan is decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[1325] Step 6:

[1326] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[1327] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[1328] Step 7:

[1329] The terminal provides real-time audio and visual feedback based on instructions from the server.

[1330] Example: "A-kun, it's okay to write slowly," provides audio guidance and visual support.

[1331] Step 8:

[1332] The server continuously collects data on the child's reactions after the feedback is provided and uses machine learning models to optimize the support method.

[1333] For example, the system learns data such as "Mr. A was able to write kanji when we spoke to him slowly."

[1334] Step 9:

[1335] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[1336] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[1337] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[1338] Example 1

[1339] 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."

[1340] Currently, individual support for children with developmental disorders generally relies on the experience and intuition of teachers and support staff. As a result, support content is often inconsistent and ineffective. It is also extremely difficult to monitor children's behavior and emotional state in real time and provide appropriate feedback. Furthermore, there is no system for evaluating the effectiveness of support methods and continuously optimizing them, making it difficult to improve the quality of support. To address these challenges, a system is needed to provide consistent and effective support to children with developmental disorders.

[1341] 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.

[1342] In this invention, the server includes: a device that monitors a child's behavior and emotional state in real time using a camera or sensor and collects the data; a device that transmits the collected data to the server; a server that analyzes the child's emotional state and behavioral patterns based on the received data; a server that generates an individualized support plan based on the analysis results; a server that transmits feedback instructions to the device based on the generated individualized support plan; a server that provides audio and visual feedback in real time based on the feedback instructions sent from the server; and a server that continuously updates a model using a machine learning algorithm based on the collected data and feedback results. This makes it possible to provide individually appropriate support in real time, scientifically evaluate the effectiveness of the support, and continuously optimize it.

[1343] The "terminal" is a device that monitors a child's behavior and emotional state using cameras and sensors and transmits the collected data to a server.

[1344] The "server" is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the terminal.

[1345] A "camera" is a device that captures a child's facial and body movements to collect data in real time.

[1346] A "sensor" is a device used to monitor a child's behavior and emotional state, such as through motion detection and voice analysis.

[1347] "Data collection" means that the device uses cameras and sensors to monitor the child's behavior and emotional state in real time and record the information.

[1348] "Data transmission" means that the terminal transfers the collected data to the server.

[1349] "Data analysis" refers to identifying and analyzing the child's emotional state and behavioral patterns based on the data received by the server.

[1350] "Generation of an individual support plan" means that the server formulates the most appropriate support method for the child based on the analysis results.

[1351] "Feedback instructions" are specific behavioral or verbal instructions that are sent to the terminal based on the individual support plan generated by the server.

[1352] "Audio and visual feedback" refers to feedback that the terminal provides to the child in real time by means of audio output, screen display, etc., based on instructions from the server.

[1353] A "machine learning algorithm" is a software technology that uses large amounts of data to learn models and optimize data analysis and support plans.

[1354] "Model updating" means retraining the machine learning algorithm based on new data collected to continuously improve the accuracy of assistance.

[1355] This invention is a system for providing individualized and appropriate support to children with developmental disabilities, and is composed of three elements: a server, a terminal, and a user. This system monitors the child's behavior and emotional state in real time, analyzes the data, and provides an optimal support plan, thereby achieving individualized and appropriate support.

[1356] System configuration

[1357] server

[1358] The server is a device that analyzes the child's emotional state and behavioral patterns based on the received data, generates an individual support plan, and sends feedback instructions to the device. The server is equipped with a high-performance processor and performs data analysis using Python and R. Specifically, it uses deep learning frameworks such as TensorFlow and PyTorch to run machine learning algorithms that infer emotions from the child's facial expressions.

[1359] Terminal

[1360] The device is a device that monitors a child's behavior and emotional state using cameras and sensors and sends the collected data to a server. The device is equipped with a camera and motion detection sensors, and captures and records the child's facial expressions and movements in real time. The device converts the collected data into packet data at regular intervals and sends it to the server using a secure communication protocol such as HTTPS.

[1361] User

[1362] The user is a teacher or support worker who inputs and checks the child's condition and the support content. The user inputs information through the terminal interface and saves it on the server. This allows the situation to be tracked in real time and effective support to be provided.

[1363] Specific examples

[1364] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[1365] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[1366] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[1367] 3. The server analyzes the received data and generates an individual support plan that states, "Check Mr. A's progress every five minutes and praise him."

[1368] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[1369] Example 2: Autism Spectrum Disorder (ASD)

[1370] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[1371] 2. The device captures Mr. A's confused expression and sends the data to the server.

[1372] 3. The server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[1373] 4. The device will say, "This is a new challenge. Let's start with this."

[1374] Example prompts for generative AI models

[1375] 1. "Concerning a system that finds the best support method for children with developmental disabilities, please explain the roles and specific operations of the server, device, and user."

[1376] 2. Please explain in detail the processing steps of a system that provides individually appropriate support to children with developmental disabilities, and also state how the system operates in the cases of ADHD and ASD, as examples.

[1377] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1378] Step 1:

[1379] The device monitors the child's behavior and emotional state. Specifically, it uses a camera to recognize the child's face and analyzes their emotional state from their facial expressions. It also uses a motion detection sensor to track their body movements in real time. This process uses image analysis and motion detection software. The input is real-time data of the child's face and movements, and the output is analyzed emotional state and behavioral data.

[1380] Step 2:

[1381] The device sends the collected and analyzed data to a server. The collected data includes the child's behavior, facial expressions, and speech. The device converts this data into packet data and sends it to the server using a secure communication protocol such as HTTPS. The input is the collected emotional state and behavior data, and the output is the data packets sent to the server.

[1382] Step 3:

[1383] The server analyzes the received data. Specifically, it uses Python or R to analyze the information stored in the database and uses machine learning algorithms such as TensorFlow or PyTorch to identify the child's emotional state and behavioral patterns. The input is the data packet sent to the server, and the output is the analyzed emotional state and behavioral patterns.

[1384] Step 4:

[1385] The server generates an individualized support plan based on the analysis results. For example, if it determines that a child has difficulty writing kanji, it will create a specific plan such as "providing support for writing slowly." This plan is customized based on a pre-prepared support plan template. The input is the analyzed emotional state and behavioral patterns, and the output is a specific individualized support plan.

[1386] Step 5:

[1387] The server sends feedback instructions to the device based on the generated individual support plan. For example, it sends audio instructions such as "It's okay to write slowly" or visual instructions such as "Let's move on to the next step." These instructions are converted back into packet data and sent to the device in encrypted form. The input is the generated individual support plan, and the output is the feedback instructions sent to the device.

[1388] Step 6:

[1389] The device provides audio and visual feedback in real time based on the feedback instructions sent from the server. The device plays back audio instructions using a synthesized speech device and displays visual instructions using a display or projector. For example, the device may say, "It's okay to write slowly," and display "Let's move on to the next step" on the screen. The input is the feedback instructions sent from the server, and the output is the audio and visual feedback to the child.

[1390] Step 7:

[1391] The server uses a machine learning algorithm to continuously update the model based on the collected data and feedback results. Specifically, it integrates past data with new data to retrain the model and provide more effective feedback in the next lesson. The input is the feedback results and additional data, and the output is the updated machine learning model.

[1392] (Application example 1)

[1393] 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."

[1394] Conventional systems have had difficulty providing appropriate feedback in real time to children who require individual assistance or to machines whose work status needs to be monitored. Furthermore, there has been a lack of systems that can quickly detect abnormalities and provide appropriate instructions, which reduces the effectiveness of assistance and production efficiency. The purpose of this invention is to solve these problems and improve the accuracy and speed of individual assistance and abnormality detection.

[1395] 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.

[1396] In this invention, the server includes means for monitoring behavior and status and collecting data in real time, means for analyzing the collected data and generating an individualized support plan, means for providing audio and visual feedback in real time based on the individualized support plan, means for continuously updating the generation AI model based on the collected data and the individualized support plan, and means for monitoring the working status of the machine, detecting abnormalities in real time, and issuing a stop instruction. This makes it possible to provide optimal support in real time to subjects requiring individual support, and to quickly detect and respond to machine abnormalities.

[1397] An "action" refers to a series of movements or operations performed by a machine or a user.

[1398] "Status" refers to the current situation or condition of a machine or user, and abnormalities or peculiarities are detected through monitoring.

[1399] "Real-time" refers to a method of instantly collecting, analyzing, and providing feedback on current information.

[1400] "Data" refers to collected information about behavior and conditions, which is analyzed to generate a support plan.

[1401] "Collection" refers to the act of compiling information about monitored behaviors and conditions.

[1402] "Analysis" is the process of understanding the content of the collected data and generating the necessary support plan.

[1403] An "individual support plan" refers to a plan that includes the optimal support content and instructions for each individual based on analyzed data.

[1404] "Generation" refers to the act of creating a new support plan based on collected data and analysis results.

[1405] "Feedback" is the process of providing audio and visual instructions and information to the subject based on the generated support plan.

[1406] "Voice feedback" is a means of conveying instructions to a subject using voice based on the generated assistance plan.

[1407] "Visual feedback" is a means of conveying instructions to a subject using visual information based on a generated assistance plan.

[1408] "Generative AI model" refers to a model used to generate a continuously updated assistance plan based on machine learning algorithms.

[1409] A "machine learning algorithm" is a method for automatically learning patterns and relationships from data and generating support plans based on that information.

[1410] "Updating" is the process of continuously improving the generative AI model based on new data and results collected to provide the optimal assistance plan.

[1411] "Monitoring" refers to the act of observing a subject's behavior or condition and collecting data.

[1412] "Anomaly detection" is the process of identifying unusual behavior or conditions from monitored data and taking appropriate action.

[1413] The present invention is a system that monitors behavior and status in real time and provides appropriate support to individuals. The system functions in cooperation with a server, a terminal, and a user.

[1414] 1. Server

[1415] The server is a central processing unit that analyzes data and generates individualized support plans. It runs machine learning algorithms and continuously optimizes support methods based on the collected data. The basic components are a high-performance processor, sufficient memory capacity, and a database management system. Specifically, machine learning libraries such as TensorFlow and Keras are used.

[1416] 2. Terminal

[1417] The devices monitor the behavior and status of the robot and collect data in real time. Specifically, these devices include cameras and sensors. The devices send the collected data to a server and receive feedback instructions from the server. OpenCV is used to process camera footage in real time, and the Paho MQTT library is used to communicate with the server.

[1418] 3. Users

[1419] The user inputs and confirms the target's situation and the support content. The user inputs the data through the device, and the information is stored on the server. The server analyzes this data and the collected data to determine the appropriate support method.

[1420] Specific examples

[1421] Detecting abnormalities on the production line and providing work guidance

[1422] 1. Data Collection:

[1423] A camera installed on the terminal monitors the operation of machines on the production line and captures video in real time.

[1424] 2. Data Transfer:

[1425] Data collected on the device is sent to the server using MQTT.

[1426] 3. Data Analysis:

[1427] The data received by the server is analyzed to evaluate the machine's operating status. For example, an anomaly detection model using TensorFlow can be used to detect machine malfunctions and problems.

[1428] 4. Generate an Individual Support Plan:

[1429] Based on the analysis results, the server generates an individualized support plan and sends feedback to the device.

[1430] 5. Providing Feedback:

[1431] The device provides real-time feedback, for example, audio prompts and visual instructions.

[1432] Prompt Sentence Examples

[1433] Example prompts to give to a generative AI model:

[1434] I would like to design a system that monitors the work status of robots in a factory and automatically issues a stop command when an abnormality is detected. I would like the system to meet the following conditions:

[1435] 1. Use machine learning models to capture camera footage in real time and detect abnormal behavior.

[1436] 2. Data is sent to the server via MQTT.

[1437] 3. Provide feedback to the robot based on the results of the analysis on the server.

[1438] The system of the present invention monitors the operating status of the machine in real time, and when an abnormality is detected, it can provide prompt and appropriate feedback. Furthermore, by continuously optimizing the assistance method, it can realize effective assistance that meets individual needs.

[1439] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1440] Step 1:

[1441] The device monitors the operation of the machines on the production line and captures video in real time. The input is a camera image and the output is image data. The device uses the camera to acquire the video data and processes the images using the OpenCV library.

[1442] Step 2:

[1443] The image data collected by the device is sent to the server using the MQTT protocol. The input is the captured image data, and the output is the data sent to the server. The device uses the Paho MQTT library to compress the converted image data and send it to the server.

[1444] Step 3:

[1445] The server analyzes the received data and evaluates the machine's operating status. The input is image data received from the terminal, and the output is machine status information as the analysis result. The server uses TensorFlow to run machine learning models, analyze the image data, and detect abnormalities.

[1446] Step 4:

[1447] The server generates an individualized support plan based on the analysis results and sends feedback instructions to the device. The input is the machine status information, and the output is the generated support plan. The server creates the support plan and sends feedback instructions to the device using the MQTT protocol.

[1448] Step 5:

[1449] The terminal provides real-time feedback based on the feedback instructions received from the server. The input is the feedback instruction from the server, and the output is audio or visual feedback to the user or machine. The terminal executes the instructions using an audio output device or display, and stops the machine if an abnormality is detected.

[1450] 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.

[1451] The present invention provides a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[1452] System configuration

[1453] 1. Server

[1454] A central processing unit that analyzes data and generates individualized support plans.

[1455] It runs machine learning algorithms to continuously optimize assistance methods based on collected data.

[1456] An emotion engine is used to perform a detailed analysis of the child's emotional state.

[1457] 2. Terminal

[1458] A device used in classrooms to monitor children's behavior and emotional state in real time.

[1459] It has means for providing audio and visual feedback.

[1460] 3. Users

[1461] A teacher or support worker who inputs and checks the child's situation and support details.

[1462] Program processing

[1463] Data collection

[1464] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[1465] For example, it detects information such as "Mr. A has a confused expression."

[1466] Data Transfer

[1467] The terminal transmits the collected behavioral and emotional data to a server.

[1468] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[1469] Data analysis

[1470] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[1471] For example, it may be determined that "Mr. A is not good at writing kanji and is confused."

[1472] Generate an individual support plan

[1473] The server generates an individualized support plan based on the analysis results, which includes the most appropriate support methods for the child.

[1474] For example, the support plan may be decided as follows: "For Mr. A, we will provide support for writing and check his progress every five minutes."

[1475] Feedback Instructions

[1476] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[1477] For example, tell the device, "Instruct it to say to A-kun, 'It's okay to write slowly.'"

[1478] Providing Feedback

[1479] The terminal provides real-time audio and visual feedback based on instructions from the server.

[1480] For example, the system provides audio guidance such as, "A-kun, it's okay to write slowly," and visual support.

[1481] Continuous learning and updates

[1482] The server continuously optimizes using machine learning models based on the collected data and feedback.

[1483] For example, it learns data such as "Mr. A was able to write kanji when he was spoken to slowly."

[1484] Specific examples

[1485] Example 1: Attention Deficit Hyperactivity Disorder (ADHD)

[1486] 1. At the beginning of class, the user (teacher) inputs into the system that Mr. A tends to lose concentration.

[1487] 2. The device monitors A-kun's behavior, collects data on his frequent periods of restlessness, and sends it to the server.

[1488] 3. The server analyzes the received data using an emotion engine and generates an individual support plan that states, "Check A's progress every five minutes and praise him."

[1489] 4. The device provides feedback every five minutes saying, "Your break is almost here, hang in there."

[1490] Example 2: Autism Spectrum Disorder (ASD)

[1491] 1. The user (support staff) inputs into the system that a new assignment is about to begin.

[1492] 2. The device captures Mr. A's confused expression and sends the data to the server.

[1493] 3. Using its emotion engine, the server determines that "Mr. A is confused about the assignment" and generates an individual support plan that instructs him to "start with this first."

[1494] 4. The device will say, "This is a new challenge. Let's start with this."

[1495] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[1496] The processing flow will be explained below.

[1497] Step 1:

[1498] Users (teachers and support staff) enter the child's situation into the system before the start of class.

[1499] For example, record, "A may have difficulty maintaining concentration and needs assistance writing Kanji."

[1500] Step 2:

[1501] The devices use cameras and sensors in the classroom to monitor children's behavior and emotional state in real time.

[1502] Example: The camera observes A-kun's behavior and captures his expressions of confusion and hesitation.

[1503] Step 3:

[1504] The terminal transmits the collected behavioral and emotional data to a server.

[1505] Example: Information such as "Mr. A has a confused expression while writing kanji" is sent as data.

[1506] Step 4:

[1507] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data.

[1508] Example: The emotion engine analyzes that "Mr. A is confused" and determines that "his concentration is declining."

[1509] Step 5:

[1510] The server generates an individual support plan based on the analysis results.

[1511] Example: The support plan is decided as follows: "For Mr. A, we will provide assistance with dictation and check his progress every five minutes."

[1512] Step 6:

[1513] The server transmits a feedback instruction for the generated individual support plan to the terminal.

[1514] Example: Tell the device to "instruct A to say, 'It's okay to write slowly.'"

[1515] Step 7:

[1516] The terminal provides real-time audio and visual feedback based on instructions from the server.

[1517] Example: "A-kun, it's okay to write slowly," is given as audio guidance, and visual support is also displayed.

[1518] Step 8:

[1519] After providing the feedback, the device monitors the child's reaction again and sends the data to the server.

[1520] Example: Confirm that "A-kun is responding to the audio feedback and concentrating again" and send that data to the server.

[1521] Step 9:

[1522] The server then analyzes whether the feedback was effective based on the received data and updates the machine learning model.

[1523] Example: Learning from data that "Mr. A's concentration improved after receiving feedback" will improve the support plan for future support.

[1524] Step 10:

[1525] After the lesson, users (teachers and support staff) input their observation results into the server as feedback.

[1526] For example, you might record, "Mr. A showed progress when we encouraged him, but his motivation improved when we praised him more frequently."

[1527] In this way, through detailed operations at each step, the system provides individualized and appropriate support to children with developmental disabilities, improving their learning environment.

[1528] Example 2

[1529] 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."

[1530] Until now, there has been a lack of effective and efficient methods for providing individualized support to children with developmental disorders. In particular, there has been a need for a system that can monitor a child's behavior and emotional state in real time, generate an individualized support plan based on that information, and provide feedback at the appropriate time. Furthermore, there has been a need for a machine learning model that can continuously optimize the system based on the collected data.

[1531] 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.

[1532] In this invention, the server includes means for monitoring a child's behavior and emotional state in real time using a camera or sensor and collecting data, means for transmitting the collected data to the server, means for the server to analyze the received data using an emotion engine, means for generating an individualized support plan based on the analysis results, means for transmitting feedback instructions for the generated individualized support plan to the terminal, means for the terminal to provide audio and visual feedback in real time based on the instructions, and means for continuously optimizing a machine learning model based on the collected data and feedback results. This makes it possible to provide individualized and appropriate support to children with developmental disabilities and effectively improve their learning environment.

[1533] "Child behavior and emotional state" refers to the actions and attitudes a child displays, as well as their emotional state at the time. Behavior includes movements and speech, and emotional state includes happiness, anger, sadness, confusion, etc.

[1534] "Cameras and sensors" are devices used to sense a child's behavior and emotional state. Cameras capture video and facial expressions, and sensors collect physiological data such as heart rate and temperature.

[1535] "Server" is a central processing unit that analyzes collected data, generates and manages individual support plans, and provides feedback.

[1536] An "emotion engine" refers to an algorithm or program that analyzes collected data and determines a child's emotional state.

[1537] An "individualized support plan" is a plan that includes support methods and feedback that are most appropriate for a child based on the child's behavior and emotional state.

[1538] "Feedback instructions" refers to data or messages that instruct how to provide feedback to a child based on the generated individualized support plan.

[1539] "Audio and visual feedback" refers to the means of providing assistance and guidance to a child through audio messages and visuals on a display.

[1540] A "machine learning model" refers to a statistical model or algorithm that uses collected data to continuously derive the optimal support method.

[1541] "Real-time" refers to data collection, analysis, and feedback being provided immediately with little to no delay.

[1542] The present invention is a system for providing individualized support to children with developmental disabilities. The system monitors the child's behavior and emotional state, analyzes the collected data, and generates an individualized support plan. The system then provides real-time feedback based on the generated individualized support plan and continuously optimizes a machine learning model. The system incorporates an emotion engine that analyzes the child's emotions.

[1543] System configuration

[1544] 1. Server

[1545] Hardware: High-performance central processing unit (e.g., Intel Xeon processor)

[1546] Software: Machine learning algorithms, emotion engine

[1547] Functions: Data analysis, generation of individualized support plans, sending feedback instructions, optimization of machine learning models

[1548] 2. Terminal

[1549] Hardware: Cameras, sensors, audio output devices, displays

[1550] Software: Data collection applications, feedback provision applications

[1551] Functions: Monitor behavior and emotional state, collect and transmit data, provide audio and visual feedback

[1552] 3. Users

[1553] Role: Teacher or support worker

[1554] Function: Enter and check the child's situation and support details

[1555] Program processing

[1556] Data collection

[1557] The device uses cameras and sensors to monitor the child's behavior and emotional state in real time and collects the data.

[1558] For example, the device uses a camera to record the child's facial expressions and movements, and if the child looks confused, for example, it will recognize that expression and generate data. It also uses sensors to collect physiological data such as heart rate and body temperature. For example, if the heart rate increases, the device will determine that the child is excited.

[1559] Data Transfer

[1560] The device sends collected behavioral and emotional data to a server. The collected data is time-stamped, allowing changes over time to be tracked. For example, if a confused expression or an elevated heart rate is detected, the data is sent immediately.

[1561] Data analysis

[1562] The server uses an emotion engine to analyze the child's current emotional state and behavioral patterns based on the received data. For example, if data labeled as confusion is paired with an increase in heart rate, the server will determine that the child is "confused." It also compares this with past data, and if it is determined that the child has frequently experienced confusion when writing kanji in the past, it will determine that the child "has difficulty writing kanji."

[1563] Generate an individual support plan

[1564] The server generates an individualized support plan based on the analysis results. This plan includes the most appropriate support method for the child. For example, a support plan might be created that states, "For A-kun, we will provide support for dictation and check progress every five minutes."

[1565] Providing Feedback

[1566] The device provides real-time audio and visual feedback based on instructions from the server. For example, it may provide audio guidance such as "A-kun, it's okay to write slowly," and show an animation on the display showing the stroke order for kanji characters.

[1567] Continuous learning and updates

[1568] The server continuously optimizes the machine learning model based on the collected data and feedback. For example, data such as "Mr. A learned to write kanji when spoken to slowly" is used as feedback, and the model is regularly trained to improve its accuracy.

[1569] Examples of prompts to input to a generative AI model based on concrete examples

[1570] ADHD prompt:

[1571] Teach your child how to support them when they lose focus, including specific examples of when to check their progress every five minutes and when to praise them.

[1572] Prompt statement for ASD:

[1573] Please tell me how to support a child on the autism spectrum when they are overwhelmed by a new task. Please provide examples of specific commands or prompts to use first.

[1574] In this way, this system works in cooperation between the server, the terminal, and the user, using an emotion engine to analyze children's emotional states in detail and provide individual, appropriate support, thereby effectively improving the learning environment for children with developmental disabilities.

[1575] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1576] Step 1: Collect data

[1577] The device monitors the child's behavior and emotional state in real time using cameras and sensors. Camera footage and sensor data (e.g., heart rate and body temperature) are taken as input and collected as data. Specifically, the camera captures the child's facial expressions and movements, and the sensors measure physiological data. The collected data includes information such as "Mr. A's facial expression looks confused" and "His heart rate has increased." This data is saved with a timestamp.

[1578] Step 2: Transferring data

[1579] The device sends the collected behavioral and emotional data to the server. The input is the data collected in step 1, and the output is sending the data to the server. Specifically, the device uploads the collected data in real time and transfers it to the server along with a timestamp. For example, data such as "Mr. A has a confused expression" or "his heart rate is rising" is sent to the server.

[1580] Step 3: Analyze the data

[1581] The server uses an emotion engine to analyze the child's emotional state and behavioral patterns based on the received data. The input is the data sent from the device, and the output is the analysis results. Specifically, the server activates the emotion engine and analyzes the data. For example, if there is data labeled as confusion and an increase in heart rate, it will judge the child as "confused." It will also compare this with past data and draw the overall conclusion that "writing kanji is difficult."

[1582] Step 4: Generate an individual support plan

[1583] The server generates an individualized support plan based on the analysis results. The input is the results of the data analysis, and the output is the individualized support plan. Specifically, the server runs an algorithm based on the analysis results and creates an individualized support plan. For example, it generates a specific support plan that states, "Mr. A needs help with dictation, and progress will be checked every five minutes."

[1584] Step 5: Feedback Instructions

[1585] The server sends feedback instructions for the generated individual support plan to the terminal. The input is the generated individual support plan, and the output is sending feedback instructions to the terminal. In concrete terms, the server sends instructions to the terminal on how to provide feedback. It sends instructions such as "Tell Mr. A that it's okay to write slowly."

[1586] Step 6: Provide feedback

[1587] The device provides real-time audio and visual feedback based on instructions from the server. The input is the feedback instruction from the server, and the output is the execution of the audio and visual feedback. Specifically, the device reads out an audio message and gives audio guidance such as "A-kun, it's okay to write slowly." It also displays an animation showing the stroke order of kanji characters on the display.

[1588] Step 7: Continuous learning and updating

[1589] The server continuously optimizes the machine learning model based on the collected data and feedback results. The input is the feedback results and new data, and the output is an updated machine learning model. Specifically, the server trains the machine learning model using newly collected data to improve the accuracy of the model. For example, the server uses the feedback data, "Mr. A has become able to write kanji when spoken to slowly," to update the model.

[1590] (Application example 2)

[1591] 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."

[1592] Improving the work efficiency and safety of workers in factories is an important issue for many companies. However, it is difficult to grasp the state and emotions of individual workers in real time and provide support accordingly. In particular, when workers become fatigued after working for long periods of time, there is a problem that work efficiency decreases and safety risks increase if they are not given timely breaks or support.

[1593] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for monitoring movements and emotional states and collecting data in real time, means for analyzing the collected data and generating an individual support plan, means for providing audio and visual feedback in real time based on the individual support plan, means for continuously updating a machine learning model based on the collected data and the individual support plan, means for collecting and analyzing movement and facial expression data of workers, means for generating a support plan to improve work efficiency and safety based on the analysis results, and means for providing feedback to workers in real time based on the support plan. This makes it possible to grasp the worker's fatigue state and work efficiency in real time and provide breaks and support at appropriate times.

[1594] "Movement" is a series of movements or movements that a worker makes with their hands and body.

[1595] "Emotional state" refers to the psychological state or state of mind of the worker, including, for example, fatigue and stress.

[1596] "Terminal" means a device for collecting data and presenting analysis results, and may include a camera, microphone, and display.

[1597] "Server" refers to a central processing unit that analyzes data and generates support plans, and is a computer that operates on the cloud.

[1598] "Data collection" refers to obtaining information about behavior and emotional state using devices such as cameras and sensors.

[1599] "Analysis" is the process of using algorithms to analyze information based on collected data and derive meaningful results.

[1600] An "individual support plan" is a plan that specifies the support content appropriate for each worker based on the analysis results.

[1601] "Feedback" refers to instructions and advice given to workers based on the individual support plan, and is given through audio or visual means.

[1602] A "machine learning model" is an algorithm that continuously improves the accuracy of analysis based on collected data.

[1603] A "support plan" is a plan for the specific support provided to workers to improve work efficiency and safety.

[1604] The present invention provides a system for improving the efficiency and safety of workers in factories. The system monitors their movements and emotional states, analyzes the collected data, and generates an individualized assistance plan for each worker. The system also provides real-time audio and visual feedback based on the generated assistance plan, and continuously updates a machine learning model based on the collected data and the assistance plan.

[1605] 1. Hardware and Software Used

[1606] The system uses the following hardware and software:

[1607] Hardware

[1608] High-resolution camera: Used to monitor the movements and facial expressions of workers in real time.

[1609] Microphone: Used to collect the voice of the worker.

[1610] Sensors: Used to measure the worker's body temperature and heart rate.

[1611] Display: Used to provide visual feedback.

[1612] software

[1613] Python: Used for data analysis and running machine learning algorithms.

[1614] OpenCV: A library used to analyze image data.

[1615] FaceAPI: A library for analyzing worker facial expressions.

[1616] TensorFlow: Used to train and optimize machine learning models.

[1617] 2. System Operation Mechanism

[1618] The server analyzes data collected by high-resolution cameras, microphones, and sensors, and determines the worker's condition based on that information. For example, the following process is performed:

[1619] Data processing and calculation

[1620] Data collection: The device monitors the worker's movements and emotional state and collects data in real time.

[1621] For example, it detects the facial expression of a worker showing signs of fatigue and the frequency of manual work.

[1622] Data transfer: The terminal sends the collected data to the server.

[1623] For example, the worker's movement data and facial expression data are transferred to the server.

[1624] Data analysis: Based on the received data, the server analyzes the worker's condition using FaceAPI and OpenCV.

[1625] For example, it is determined that "Worker A is tired."

[1626] Generation of an individualized support plan: The server generates an individualized support plan based on the analysis results.

[1627] For example, create a support plan such as "Worker A will have a 30-minute break."

[1628] Feedback instruction: The server sends feedback instructions for the generated assistance plan to the terminal.

[1629] For example, "Instruct worker A to take a 30-minute break."

[1630] Providing feedback: The device provides audio and visual feedback in real time based on instructions from the server.

[1631] For example, "It's break time now" is announced aloud and displayed on the screen.

[1632] Continuous learning and updates: The server optimizes the machine learning model based on the collected data and feedback.

[1633] For example, the machine learning model is updated based on data that indicates "work efficiency improved after breaks."

[1634] 3. Specific Examples

[1635] As a concrete example, consider a scenario where fatigue caused by long-term work is detected and appropriate breaks are advised:

[1636] Example 1: Fatigue from long hours of work

[1637] 1. Workers were monitored to detect signs of fatigue (e.g., facial slackness and frequent yawning).

[1638] 2. The server determines that "a break is needed" and instructs "a 30-minute break."

[1639] 3. The terminal notifies the worker, "It's break time. Please take a 30-minute break."

[1640] Prompts for generative AI models

[1641] An example prompt is:

[1642] Prompt statement:

[1643] "Using the behavioral and facial expression data of a worker working in a factory as input data, generate a feedback program for an assistive robot to improve work efficiency. This program will have the function of determining the worker's fatigue level and suggesting appropriate break times. Also, clarify the hardware and software to be used and include specific examples from a real-life scenario."

[1644] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1645] Step 1:

[1646] Data collection: The device uses high-resolution cameras, microphones, and sensors to collect data on the worker's movements, facial expressions, body temperature, heart rate, and other aspects in real time. Camera footage, audio, body temperature, heart rate, and other data are collected as input data. This makes it possible to understand the worker's current condition in detail. The collected data is obtained as output.

[1647] Step 2:

[1648] Data Transfer: The device sends the collected data to the server via Wi-Fi or other communication means. As input, there is the data collected in step 1. The data is converted into an appropriate format and sent to the server. As output, the transmitted data reaches the server and moves to the next analysis step.

[1649] Step 3:

[1650] Data analysis: The server analyzes the received data using image analysis libraries such as OpenCV and FaceAPI, and machine learning algorithms (such as TensorFlow). The input is data on movements and emotional states sent from the device. Based on this, data calculations and analysis are performed to determine the worker's condition. The output is an analysis result such as "Worker A is tired."

[1651] Step 4:

[1652] Generation of individual support plan: Based on the analysis results, the server generates an individual support plan suited to the worker's condition. The input is the analysis results obtained in step 3. A machine learning model is used to determine the optimal support method. The output is a specific support plan such as "Worker A is recommended to take a 30-minute break."

[1653] Step 5:

[1654] Feedback instruction: The server sends the generated assistance plan to the terminal and instructs the worker to provide feedback. The input is the assistance plan generated in step 4. This is sent to the terminal as a feedback instruction. The output is the feedback instruction sent to the terminal.

[1655] Step 6:

[1656] Providing feedback: The terminal provides audio and visual feedback in real time based on the feedback instructions from the server. For example, it may display "It's break time now. Please take a 30-minute break" on the display and provide a similar instruction via audio. The input is the feedback instruction sent from the server. The output is the feedback provided to the worker.

[1657] Step 7:

[1658] Continuous learning and updating: The server optimizes the machine learning model based on the collected data and feedback results. The inputs are effectiveness measurement data and feedback results. Using these, the machine learning model algorithm is continuously trained and updated to improve the accuracy of the support method. The output is an optimized machine learning model.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1664] 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.

[1665] 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).

[1666] 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.

[1667] 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."

[1668] 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.

[1669] 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).

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] 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.

[1680] The following is further disclosed regarding the above embodiment.

[1681] (Claim 1)

[1682] a means of monitoring the child's behavior and emotional state and collecting data in real time;

[1683] a means for analyzing the collected data and generating an individualized support plan for each child;

[1684] a means of providing real-time audio and visual feedback based on the individualized assistance plan;

[1685] A means to continuously update the machine learning model based on collected data and individualized support plans;

[1686] A system including:

[1687] (Claim 2)

[1688] means for the device to monitor the child's behavior and emotional state and transmit the data to a server;

[1689] A means for the server to analyze the received data and generate an individual support plan;

[1690] A means for the server to send feedback instructions to the terminal based on the generated individual support plan;

[1691] means for the terminal to perform audio output based on the feedback instruction;

[1692] 10. The system of claim 1, comprising:

[1693] (Claim 3)

[1694] A means for teachers to input the child's situation and store the information on a server;

[1695] a means for the server to analyze past and current data using machine learning algorithms to determine appropriate assistance methods;

[1696] A means for the server to automatically adjust the support plan for the next lesson based on the updated information on the support method;

[1697] 10. The system of claim 1, comprising:

[1698] "Example 1"

[1699] (Claim 1)

[1700] The device monitors the child's behavior and emotional state in real time using cameras and sensors and collects the data;

[1701] A means for the terminal to transmit the collected data to a server;

[1702] A means for the server to analyze the emotional state and behavioral patterns of the child based on the received data;

[1703] A means for the server to generate an individual support plan based on the analysis result;

[1704] A means for the server to send feedback instructions to the terminal based on the generated individual support plan;

[1705] means for the terminal to provide audio and visual feedback in real time based on feedback instructions sent from the server;

[1706] a means for the server to continuously update the model using a machine learning algorithm based on the collected data and feedback results;

[1707] A system including:

[1708] (Claim 2)

[1709] A means for teachers to input the child's situation and support details and store that information on the server.

[1710] A means for the server to analyze past and current data using a machine learning algorithm and determine an appropriate support method;

[1711] A means for the server to automatically adjust the support plan for the next lesson based on the updated information on the support method;

[1712] 10. The system of claim 1, comprising:

[1713] (Claim 3)

[1714] For children with ADHD, the device will provide feedback by checking progress and praising them every five minutes.

[1715] A way for the device to provide specific instructions to children with ASD when new tasks pose a challenge.

[1716] 10. The system of claim 1, comprising:

[1717] "Application Example 1"

[1718] (Claim 1)

[1719] a means of monitoring behavior and condition and collecting data in real time;

[1720] A means for analyzing the collected data and generating an individualized support plan;

[1721] a means for providing real-time audio and visual feedback based on the individualized assistance plan;

[1722] A means to continuously update the generative AI model based on collected data and individualized support plans; and

[1723] A means for monitoring the working status of the machine, detecting abnormalities in real time, and issuing a stop command;

[1724] A system including:

[1725] (Claim 2)

[1726] A means for the terminal to monitor the behavior and state and transmit the data to a server;

[1727] A means for the server to analyze the received data and generate an individual support plan;

[1728] A means for the server to send feedback instructions to the terminal based on the generated individual support plan;

[1729] means for the terminal to perform audio output based on the feedback instruction;

[1730] A means for the terminal to monitor the work status in real time and immediately transmit data to the server when an abnormality is detected;

[1731] A means for the server to analyze the abnormality, generate a necessary stop instruction, and send it to the terminal;

[1732] 10. The system of claim 1, comprising:

[1733] (Claim 3)

[1734] a means for the user to input a situation and store the information on a server;

[1735] a means for the server to analyze past and current data using machine learning algorithms to determine appropriate assistance methods;

[1736] A means for the server to automatically adjust the next support plan based on the updated information of the support method;

[1737] 10. The system of claim 1, comprising:

[1738] "Example 2: Combining Emotion Engines"

[1739] (Claim 1)

[1740] A means of monitoring and collecting data on children's behavior and emotional state in real time using cameras and sensors;

[1741] means for transmitting the collected data to a server;

[1742] A means for the server to analyze the received data using an emotion engine;

[1743] A means for generating an individual support plan based on the analysis results;

[1744] A means for transmitting feedback instructions of the generated individual support plan to the terminal;

[1745] a means for the device to provide audio and visual feedback in real time based on the instruction;

[1746] A means to continuously optimize the machine learning model based on the collected data and feedback results; and

[1747] A system including:

[1748] (Claim 2)

[1749] means for the device to monitor the child's behavior and emotional state and transmit the data to a server;

[1750] A means for the server to analyze the received data and generate an individual support plan;

[1751] A means for the server to send feedback instructions to the terminal based on the generated individual support plan;

[1752] means for the terminal to provide audio and visual feedback based on the feedback instruction;

[1753] 10. The system of claim 1, comprising:

[1754] (Claim 3)

[1755] A means for educators to input the child's situation and store the information on a server;

[1756] a means for the server to analyze past and current data using machine learning algorithms to determine appropriate assistance methods;

[1757] A means for the server to automatically adjust the support plan for the next lesson based on the updated information on the support method;

[1758] 10. The system of claim 1, comprising:

[1759] "Application example 2 when combining emotion engines"

[1760] (Claim 1)

[1761] a means for monitoring motion and emotional state and collecting data in real time;

[1762] A means for analyzing the collected data and generating an individualized support plan;

[1763] a means of providing real-time audio and visual feedback based on the individualized assistance plan;

[1764] A means to continuously update the machine learning model based on collected data and individualized support plans;

[1765] A means for collecting and analyzing data on worker movements and facial expressions;

[1766] A means for generating a support plan to improve work efficiency and safety based on the analysis results;

[1767] a means of providing real-time feedback to workers based on their support plans;

[1768] A system including:

[1769] (Claim 2)

[1770] means for the device to monitor its motion and emotional state and transmit the data to a server;

[1771] A means for the server to analyze the received data and generate an individual support plan;

[1772] A means for the server to send feedback instructions to the terminal based on the generated individual support plan;

[1773] means for the terminal to perform audio output based on the feedback instruction;

[1774] A means for the terminal to collect data on the worker's movements and facial expressions and transmit the data to a server;

[1775] a means for the server to generate a support plan for improving work efficiency and safety based on the analyzed data and to transmit a feedback instruction to the terminal;

[1776] means for providing audio and visual feedback based on the feedback instruction;

[1777] 10. The system of claim 1, comprising:

[1778] (Claim 3)

[1779] a means for inputting the status of the worker through an input device and storing the information in a server;

[1780] a means by which the server uses machine learning algorithms to analyze past and current data to determine appropriate support methods;

[1781] a means for the server to automatically adjust the support plan for the next task based on the updated information on the support method;

[1782] 10. The system of claim 1, comprising: [Explanation of symbols]

[1783] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of monitoring the child's behavior and emotional state and collecting data in real time; a means for analyzing the collected data and generating an individualized support plan for each child; a means of providing real-time audio and visual feedback based on the individualized assistance plan; A means to continuously update the machine learning model based on collected data and individualized support plans; A system including:

2. means for the device to monitor the child's behavior and emotional state and transmit the data to a server; A means for the server to analyze the received data and generate an individual support plan; A means for the server to send feedback instructions to the terminal based on the generated individual support plan; means for the terminal to perform audio output based on the feedback instruction; The system of claim 1 , comprising:

3. A means for teachers to input the child's situation and store the information on a server; a means for the server to analyze past and current data using machine learning algorithms to determine appropriate assistance methods; A means for the server to automatically adjust the support plan for the next lesson based on the updated information on the support method; The system of claim 1 , comprising:

Images