System

Abstract

To provide a system for collecting sensor data from an IoT device, performing preprocessing, and generating shaped sensor data.SOLUTION: A system comprising means for collecting sensor data from an IoT device, means for performing pre-processing to generate shaped sensor data, means for updating a generated AI model based on the pre-processed sensor data, means for generating a training plan using the generated AI model, means for generating a diet plan using the generated AI model, means for monitoring sensor data in real-time to detect anomalies, means for generating an alert message when an anomaly is detected, means for transmitting the training plan, the diet plan, and the alert message to a user terminal, and means for displaying the information transmitted to the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Athletes, coaches, and training staff have difficulty creating optimal training and dietary plans based on individual athletes' physical strength, technique, exercise volume, and other parameters. This can lead to inadequate performance improvement and health management, and it can also make it difficult to maintain long-term performance and reduce injury risk. Conventional methods lack the ability to analyze data in real time or automatically generate plans tailored to individual athletes, preventing many athletes from achieving optimal performance. [Means for solving the problem]

[0005] The present invention provides a means for collecting sensor data from IoT devices, preprocessing it, and generating formatted sensor data. It also includes a means for updating a generative AI model based on the preprocessed sensor data. It also provides a means for generating training and meal plans using the generative AI model. The system includes a means for monitoring sensor data in real time to detect anomalies, a means for generating warning messages when an anomaly is detected, and a means for transmitting and displaying this information to a user terminal, thereby enabling the provision of optimal training and meal plans for individual athletes and health management. The system also includes a means for receiving feedback data from the user terminal and integrating it with preprocessed data, and a means for generating or modifying plans based on the user's nutritional information and physical condition information, thereby dynamically adjusting plans for individual athletes in real time. These means enable efficient management of athletes' performance and health, reducing injury risk and improving long-term outcomes.

[0006] An "IoT device" is an electronic device that is connected to the Internet and has the ability to collect sensor data and send it to a server.

[0007] "Sensor data" refers to data such as an athlete's heart rate, exercise volume, calorie consumption, location information, and sleep patterns measured by IoT devices.

[0008] "Preprocessing" is the process of shaping sensor data, removing outliers, filling in incomplete data, converting data types, etc.

[0009] A "generative AI model" is a model that uses machine learning algorithms to predict an athlete's training effects and health status.

[0010] A "training plan" is a training schedule and content generated based on a generative AI model, with the aim of improving an athlete's physical strength and technique.

[0011] A "meal plan" is a meal menu and schedule that is generated based on a generative AI model and is tailored to an athlete's nutritional balance and calorie consumption.

[0012] "Monitoring" is the process of monitoring sensor data in real time to detect abnormal values ​​or abnormal behavior.

[0013] A "warning message" is the content of an alert generated by the server when an abnormality is detected by monitoring, and is a message that informs athletes and coaches of the situation.

[0014] A "user terminal" is an electronic device used by a user to receive and display information, such as a smartphone or tablet.

[0015] "Feedback data" refers to information entered by the user, such as the athlete's diet and physical condition, and is used by the system to generate the next plan. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The system of the present invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific embodiments are described below.

[0038] Data collection and transmission

[0039] Device:

[0040] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect sensor data in real time, and the collected data is sent to a server via communication protocols such as Bluetooth or WiFi.

[0041] Data Preprocessing

[0042] server:

[0043] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is stored in a database for subsequent processing.

[0044] Data analysis and AI model updates

[0045] server:

[0046] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. The extracted features are used to update the generative AI model. The generative AI model is then used to predict the athlete's training effects and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[0047] Generate training and meal plans

[0048] server:

[0049] The server uses the updated AI model to generate optimal training and meal plans for each athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[0050] Monitoring and generating warning messages

[0051] server:

[0052] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[0053] User Feedback

[0054] Servers and devices:

[0055] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[0056] Receiving feedback data and updating the model

[0057] Users and servers:

[0058] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, so it is reflected dynamically in real time.

[0059] As a concrete example, consider an athlete who wants a new weekend training plan.

[0060] 1. User: The athlete sends a request for a new plan from their device.

[0061] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[0062] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[0063] 4. Server: Sends the generated training plan to the user's device.

[0064] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[0065] By taking specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance, providing optimal training and diet plans.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[0069] Step 2:

[0070] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[0071] Step 3:

[0072] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[0073] Step 4:

[0074] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[0075] Step 5:

[0076] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[0077] Step 6:

[0078] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[0079] Step 7:

[0080] Server: Uses the updated AI model to generate optimal training plans for athletes, for example, determining next week's training schedule based on the athlete's current fitness level and past training history.

[0081] Step 8:

[0082] Server: Similarly, AI models are used to generate optimal meal plans, for example, by taking into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[0083] Step 9:

[0084] Server: The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality.

[0085] Step 10:

[0086] Server: Generates a warning message when an abnormality is detected, for example, "Your heart rate is too high, you need to rest."

[0087] Step 11:

[0088] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[0089] Step 12:

[0090] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[0091] Step 13:

[0092] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[0093] Step 14:

[0094] Terminal: User feedback data is sent to the server.

[0095] Step 15:

[0096] Server: Receives feedback data and integrates it with pre-processed sensor data.

[0097] Step 16:

[0098] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[0099] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and dietary plans for each individual athlete.

[0100] Example 1

[0101] 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."

[0102] Using IoT devices to monitor athletes' performance and health and provide optimal training and meal plans based on that data is crucial for creating plans that meet the needs of individual athletes. However, there are few systems that consistently execute complex processes such as real-time data collection, preprocessing, updating AI models, generating plans, detecting anomalies, and integrating feedback data. This makes it difficult to efficiently manage athletes' training and nutrition.

[0103] 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.

[0104] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for extracting features from the preprocessed sensor data, means for updating a generative AI model based on the features, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for receiving meal content and physical condition information as user feedback data and generating or modifying a meal plan based on the data. This makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[0105] An "IoT device" is a physical device that can connect to the internet and collect, transmit, and share data. Examples include smart bands, heart rate monitors, and GPS tracking devices.

[0106] "Sensor data" refers to information such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns measured by IoT devices.

[0107] "Preprocessing" refers to the process of converting sensor data into a standard format by removing outliers, filling in incomplete data, converting data types, etc.

[0108] "Features" are computable attributes or properties extracted from preprocessed sensor data that can be used by machine learning algorithms. Examples include average and maximum heart rate, and cumulative exercise volume.

[0109] A "generative AI model" is a model created using machine learning algorithms to make predictions and classifications based on data. It is used to predict the training effects and health status of athletes.

[0110] A "training plan" is a plan created using a generative AI model that shows an athlete's optimal exercise schedule and training content.

[0111] A "meal plan" is a plan created using a generative AI model that takes into account an athlete's daily diet and nutritional balance.

[0112] "Real-time monitoring" refers to the state in which sensor data is continuously monitored and abnormalities or specific conditions can be detected immediately.

[0113] A "warning message" is a notification message that is generated when an abnormality is detected during the monitoring process, and includes content that alerts the user.

[0114] "User Device" means a device used by an Athlete or Personnel to receive and display information. Examples include smartphones and tablets.

[0115] "Feedback data" refers to information such as dietary habits and physical condition that users enter on a daily basis, and is used to improve the accuracy of the generative AI model.

[0116] "Preprocessed sensor data" refers to sensor data that has undergone preprocessing such as removing outliers and interpolating data, and has been converted into a standard format.

[0117] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific implementation of this system is described below.

[0118] Configuration and Usage

[0119] Device application and data collection

[0120] Users (athletes) wear IoT devices such as smart bands, heart rate monitors, and GPS tracking devices. These devices measure data such as heart rate, exercise volume, calorie consumption, location, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi.

[0121] Data Preprocessing

[0122] The server receives raw data sent from each IoT device and performs preprocessing such as detecting and removing outliers, filling in incomplete data, and converting data types, so that the data is formatted into a standard format. This preprocessed data is stored in a database for subsequent processing.

[0123] Data analysis and AI model updates

[0124] The server extracts features from the preprocessed data stored in the database. Examples include average and maximum heart rate values ​​and cumulative exercise volume. Based on these features, the generative AI model is updated. This model update uses machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). The updated generative AI model is then used to predict the athlete's training effects and health status.

[0125] Generate training and meal plans

[0126] The server uses a generative AI model to generate optimal training and meal plans for each individual athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[0127] Real-time monitoring and alerts

[0128] The server monitors the sensor data in real time. If an abnormality is detected, such as if the heart rate exceeds a certain threshold, a warning message is generated and sent to the user's device. The message might say something like, "Your heart rate is too high, so you need to rest."

[0129] Collecting and synthesizing feedback

[0130] Users input feedback data (e.g., what they ate today and their physical condition) using devices such as smartphones or tablets. This feedback is sent to the server and integrated with preprocessed sensor data. This integrated data is used to update the generative AI model and generate plans for the next time, so it is reflected dynamically in real time.

[0131] Specific examples

[0132] A concrete example would be an athlete wanting a new weekend training plan.

[0133] 1. The user (athlete) sends a request for a new plan from their device.

[0134] 2. The server analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[0135] 3. The server generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[0136] 4. The server sends the generated training plan to the user's device.

[0137] 5. The training plan will be displayed on the device and the athlete will train according to the plan.

[0138] Prompt Sentence Examples

[0139] "Write a program that generates an optimal training plan based on an athlete's heart rate and exercise data from the past week."

[0140] By performing detailed and specific operations at each processing step, this invention makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1: Data collection and transmission

[0143] The device (the athlete wearing the IoT device) measures data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi. Specifically, the smart band measures heart rate every five seconds and transfers this data to a smartphone app. The app then sends the data to the server, so the input becomes real-time measured sensor data, and the output becomes the data sent to the server.

[0144] Step 2: Preprocessing the data

[0145] The server receives raw data sent from each IoT device. Because this data may contain outliers, preprocessing is performed, including detecting and removing outliers, completing incomplete data, and converting data types. Specifically, upper and lower limits are set for the data to detect outliers, and data outside these limits is removed. Missing data is completed with the average value, so the input is the raw data sent to the server, and the output is preprocessed data. This preprocessed data is stored in a database.

[0146] Step 3: Data analysis and feature extraction

[0147] The server extracts features from the preprocessed data. These include, for example, the average and maximum heart rate, and the cumulative amount of exercise. Specifically, it plots the time variation of heart rate on a graph, detects peaks, and evaluates the intensity of training. The input is the preprocessed data, and the output is the extracted features.

[0148] Step 4: Update the generative AI model

[0149] The server updates the generative AI model based on the extracted features. Machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) are used. Specifically, the server inputs the time change in heart rate and the cumulative value of exercise volume into the AI ​​model, and then retrains the model. The input is the extracted features, and the output is the updated generative AI model.

[0150] Step 5: Create a training and meal plan

[0151] The server uses an updated generative AI model to generate optimal training and meal plans for each individual athlete. It determines the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data. Specific operations include setting running distance and rest days when generating a training plan, and taking calories and nutritional balance into account when creating a meal plan. The input is an updated generative AI model and real-time data, and the output is the generated training plan and meal plan.

[0152] Step 6: Real-time monitoring and alerting

[0153] The server monitors sensor data in real time. If an abnormality is detected based on the sensor data, such as when the heart rate exceeds a certain threshold, a warning message is generated. Specifically, if the heart rate exceeds 180, a message such as "Rest is required" is generated and the athlete is notified. The input is the real-time sensor data, and the output is the generated warning message.

[0154] Step 7: User feedback

[0155] The server sends the generated training plan, meal plan, and warning messages to the user's device. The device receives this information and displays it on the screen. Specifically, the training plan is displayed on the calendar on the smartphone app, and reminders are sent to the athlete using the notification function. The input is the generated training plan, meal plan, and warning messages, and the output is this information displayed on the device.

[0156] Step 8: Receiving and consolidating feedback data

[0157] Users use devices such as smartphones or tablets to input feedback data (e.g., what they ate today and their physical condition information). The server receives this data and integrates it with preprocessed sensor data. Specifically, the athlete enters the details of what they ate today into the app, and this data is analyzed by the server and reflected in the next meal plan. The input is the feedback data sent from the user's device, and the output is the integrated data. The integrated data is then used for the next update of the generative AI model.

[0158] (Application example 1)

[0159] 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."

[0160] When operating factory robots, it is important to monitor their performance and health in real time and generate optimal maintenance plans. However, current systems make it difficult to efficiently collect and analyze this data and take appropriate measures. Factory robots, in particular, have a wide variety of sensor data, so data integration and accurate analysis are required. Furthermore, when an abnormality is detected, it is essential to generate warning messages for rapid response and to notify the optimal maintenance plan. Technology to solve this problem is needed.

[0161] 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.

[0162] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for collecting sensor data from a factory robot and monitoring temperature, vibration, current, etc., means for monitoring the performance and health status of the factory robot in real time and generating a warning message when an anomaly is detected, means for generating an optimal maintenance plan for the factory robot using the generative AI model, means for notifying appropriate maintenance actions based on the sensor data of the factory robot, and means for displaying the information transmitted to the user terminal. This enables real-time monitoring of the performance and health status of factory robots, enabling the generation of appropriate maintenance plans and rapid response to abnormalities.

[0163] An "IoT device" is a physical device that can collect, send, or receive data over the Internet.

[0164] "Sensor data" refers to data measured and collected by various sensors, and includes information such as temperature, vibration, and current.

[0165] "Preprocessing" is the process of performing operations on raw data, such as removing outliers, filling in incomplete data, and converting data types, to prepare the data in a form suitable for analysis.

[0166] A "generative AI model" is a model built using machine learning algorithms to generate patterns and predictions from data.

[0167] A "Training Plan" is a plan that shows the optimal training schedule and content for an athlete and equipment.

[0168] A "meal plan" is a plan that shows the meal content and schedule optimized to maintain an athlete's health and improve their performance.

[0169] An "abnormality" is a state in which a value or pattern outside the normal range is detected from collected sensor data.

[0170] A "warning message" is a notification message that is generated when an anomaly is detected, informing the user of the existence of a problem and the necessary action to be taken.

[0171] A "user terminal" is a device used by a user, such as a smartphone or tablet, that displays information from the system.

[0172] "Robot performance" is an indicator of how efficiently and accurately a robot can perform a given task.

[0173] "Health status" refers to the normal operating condition of each part of the robot and the entire system.

[0174] A "maintenance plan" is a specific work plan for inspections, repairs, part replacements, etc. required to maintain the proper operation of a robot.

[0175] The present invention provides a system for monitoring the performance and health status of factory robots in real time and generating an optimal maintenance plan. Specific embodiments of the system are described below.

[0176] Data collection and transmission

[0177] Device:

[0178] Factory robots are equipped with various sensors, such as temperature sensors, vibration sensors, and current sensors. These sensors measure the status of each part of the robot and the overall system, and collect data in real time. The collected sensor data is sent to a server via communication protocols such as Bluetooth and WiFi.

[0179] Data Preprocessing

[0180] server:

[0181] The server receives the sensor data sent from each sensor and performs preprocessing, which includes removing outliers, filling in incomplete data, converting data types, etc. The preprocessed data is then converted into a standard format and stored in a database.

[0182] Data analysis and AI model updates

[0183] server:

[0184] Features are extracted from the preprocessed data and used to update the generative AI model. For example, features such as temperature changes over time or cumulative vibration values ​​can be used. The updated generative AI model is then used to detect anomalies in factory robots, predict performance, and generate maintenance plans. Machine learning algorithms (e.g., deep learning and random forests) are used to create the generative AI model.

[0185] Generate a maintenance plan

[0186] server:

[0187] Using a generative AI model, the system generates an optimal maintenance plan based on the condition of factory robots. For example, it suggests the timing of part replacement and adjustment items based on the degree of deterioration of each part of the robot and the frequency of abnormality detection.

[0188] Monitoring and generating warning messages

[0189] server:

[0190] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the vibration sensor exceeds a certain threshold, it generates a message saying, "Vibration is too high, immediate inspection required."

[0191] User Feedback

[0192] Servers and devices:

[0193] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action in real time.

[0194] Receiving feedback data and updating the model

[0195] Users and servers:

[0196] The results of the maintenance work and feedback data (e.g., work content and robot status information) are sent from the user device to the server, where they are combined with preprocessed sensor data and used for the next model update and plan generation.

[0197] Hardware and software used

[0198] Hardware:

[0199] IoT devices: temperature sensors, vibration sensors, current sensors

[0200] Server: Data preprocessing and AI model operation

[0201] software:

[0202] Python (data collection, preprocessing, modeling)

[0203] Libraries: NumPy, Pandas, scikit-learn, Keras

[0204] Communication protocol: Bluetooth, WiFi

[0205] Specific examples

[0206] For example, if a factory robot detects a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, the server will immediately detect the abnormality and generate a warning message stating, "Vibration is too high and requires immediate inspection," and send it to the user terminal.

[0207] Prompt Sentence Examples

[0208] "If the sensors attached to a factory robot detect a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, detect the abnormality and immediately generate a maintenance plan."

[0209] In this way, the system enables real-time monitoring of the performance and health of factory robots, enabling the creation of optimal maintenance plans and rapid response to abnormalities.

[0210] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0211] Step 1:

[0212] Data collection and transmission

[0213] Device:

[0214] Various sensor data is collected in real time from temperature sensors, vibration sensors, current sensors, etc. attached to factory robots, and the collected data is sent to a server via communication protocols such as Bluetooth and WiFi.

[0215] Input: Measurement data of each sensor (e.g. temperature, vibration, current)

[0216] Output: Sensor data sent to the server

[0217] Step 2:

[0218] Data Preprocessing

[0219] server:

[0220] The server preprocesses the raw data received from each sensor, removing outliers, completing incomplete data, converting data types, and formatting it into a standard format. The preprocessed data is then stored in a database.

[0221] Input: Raw data (measurement data sent from each sensor)

[0222] Output: Preprocessed data (outlier removal, data imputation, and data formatting)

[0223] Step 3:

[0224] Feature extraction and AI model updating

[0225] server:

[0226] Extract features (e.g., temperature change over time, cumulative vibration value) from preprocessed data. Update the generative AI model using the extracted features. Machine learning algorithms used here include deep learning and random forests.

[0227] Input: Preprocessed data

[0228] Output: Updated generative AI model

[0229] Step 4:

[0230] Generate a maintenance plan

[0231] server:

[0232] Based on the updated generative AI model, the server generates an optimal maintenance plan (e.g., part replacement timing and adjustment items) according to the state of the factory robot. The generated maintenance plan is sent to the user's device.

[0233] Input: Updated generative AI model, real-time data from each sensor

[0234] Output: Optimal maintenance plan

[0235] Step 5:

[0236] Real-time monitoring and warning message generation

[0237] server:

[0238] The server monitors sensor data in real time and immediately generates a warning message if an abnormality is detected. For example, if a vibration sensor exceeds a threshold, a warning message stating "Vibration is too high, immediate inspection is required" is generated and sent to the user's device.

[0239] Input: Real-time sensor data

[0240] Output: Warning message

[0241] Step 6:

[0242] User Feedback

[0243] Servers and devices:

[0244] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action immediately.

[0245] Inputs: Maintenance plan, warning message

[0246] Output: Information displayed on the terminal screen

[0247] Step 7:

[0248] Receiving feedback data and updating the model

[0249] Users and servers:

[0250] The user inputs the results of maintenance work and feedback (e.g., work content, robot status information) from the terminal. This data is sent to the server and integrated with preprocessed sensor data. The integrated data is used for the next model update and plan generation.

[0251] Input: Feedback data from users

[0252] Output: Integrated data (preprocessed sensor data + feedback data)

[0253] In this way, the system enables real-time performance and health monitoring of factory robot operations, the generation of optimal maintenance plans, and rapid response to abnormalities.

[0254] 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.

[0255] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Furthermore, the system also incorporates an emotion engine to recognize the user's emotions, enabling the provision of even more personalized plans. Specific embodiments are described below.

[0256] Data collection and transmission

[0257] Device:

[0258] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure their heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect the measured sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[0259] Data Preprocessing

[0260] server:

[0261] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is then stored in a database for subsequent processing.

[0262] Data analysis and AI model updates

[0263] server:

[0264] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. It then updates the generative AI model based on the extracted features. The generative AI model is then used to predict the athlete's training effect and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, the server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and integrates the results with the preprocessed sensor data and feedback data.

[0265] Generate training and meal plans

[0266] server:

[0267] The server uses the updated AI model to generate optimal training and meal plans for each athlete. For example, the next week's training schedule and daily meal menu are determined based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[0268] Monitoring and generating warning messages

[0269] server:

[0270] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[0271] User Feedback

[0272] Servers and devices:

[0273] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[0274] Receiving feedback data and updating the model

[0275] Users and servers:

[0276] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[0277] As a concrete example, consider an athlete who wants a new weekend training plan.

[0278] 1. User: The athlete sends a request for a new plan from their device.

[0279] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, food records, and emotional data.

[0280] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[0281] 4. Server: Sends the generated training plan to the user's device.

[0282] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[0283] By performing specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance and provides optimal training and meal plans. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take the user's emotional state into consideration, realizing a more personalized service.

[0284] The processing flow will be explained below.

[0285] Step 1:

[0286] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[0287] Step 2:

[0288] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[0289] Step 3:

[0290] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[0291] Step 4:

[0292] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[0293] Step 5:

[0294] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[0295] Step 6:

[0296] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[0297] Step 7:

[0298] Server: Analyzes emotional data from the user's voice and facial expressions using an emotion engine. The emotion engine uses voice recognition and image recognition technologies.

[0299] Step 8:

[0300] Server: Integrates the emotion data recognized by the emotion engine with preprocessed sensor data and feature data.

[0301] Step 9:

[0302] Server: Uses the updated AI model to generate the optimal training plan for the athlete. For example, it determines the next week's training schedule based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[0303] Step 10:

[0304] Server: Similarly, it uses AI models to generate optimal meal plans, for example, proposing meal menus that take into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[0305] Step 11:

[0306] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality and generates a message saying, "Your heart rate is too high, so you need to rest."

[0307] Step 12:

[0308] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[0309] Step 13:

[0310] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[0311] Step 14:

[0312] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[0313] Step 15:

[0314] Terminal: User feedback data is sent to the server.

[0315] Step 16:

[0316] Server: Receives feedback data and integrates it with pre-processed sensor data.

[0317] Step 17:

[0318] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[0319] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and meal plans for each individual athlete. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take into account the user's emotional state, achieving a more personalized service.

[0320] Example 2

[0321] 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."

[0322] Conventional athlete training and health management systems lack real-time monitoring, making it difficult to provide optimal training and diet plans tailored to each individual athlete's condition. They also lack the ability to generate personalized plans that take into account the user's emotional state. This has resulted in problems with the inability to efficiently and effectively improve performance and manage health.

[0323] 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.

[0324] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for acquiring user emotion data using an emotion analysis engine and integrating it with the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time and detecting anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, meal plan, and warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for personalizing training plans and meal plans based on the user emotion data, thereby enabling real-time monitoring and providing personalized training plans and meal plans that take the user's emotional state into account.

[0325] An "IoT device" is an electronic device that is connected to the Internet and collects data about the user's activities and environment.

[0326] "Sensor data" refers to measurement data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns collected by IoT devices.

[0327] "Preprocessing" is the process of formatting collected sensor data, removing outliers, filling in missing values, and converting data types.

[0328] A "generative AI model" is a model that uses machine learning algorithms to predict an athlete's training effects and health status, and generate optimal training and meal plans.

[0329] An "emotion analysis engine" is an engine that analyzes emotional data from a user's voice and facial expressions and integrates the results with other data.

[0330] A "training plan" is an exercise schedule created to improve an athlete's performance and maintain their health.

[0331] A "meal plan" is a meal menu created with the purpose of improving an athlete's health and training effectiveness.

[0332] "Real-time monitoring" is the process of constantly monitoring sensor data and acquiring and analyzing the data in real time.

[0333] A "warning message" is a notification message that is generated when an abnormality is detected during real-time monitoring.

[0334] "User devices" are electronic devices such as smartphones and tablets used by athletes.

[0335] "Feedback data" refers to data such as dietary details and physical condition information that is input by the user via the terminal.

[0336] This invention is a system that utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time, and provides optimal training and meal plans. Furthermore, by combining it with an emotion analysis engine, it is possible to provide personalized plans that take the user's emotional state into account.

[0337] Hardware and software used

[0338] 1. IoT devices: Use electronic devices such as heart rate monitors, smart bands, and GPS tracking devices. These devices are worn by athletes and collect real-time sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[0339] 2. Server: Used for preprocessing, data analysis, updating AI models, generating warning messages, and generating training and meal plans. Equipped with machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) and a sentiment analysis engine.

[0340] 3. User terminal: Uses electronic devices such as smartphones and tablets. These terminals display training plans, meal plans, and warning messages sent from the server, and receive feedback data from the user (e.g., dietary details and physical condition information).

[0341] Specific Embodiments

[0342] Data collection and transmission

[0343] Device: Athletes wear heart rate monitors or smart bands. These devices transmit collected sensor data to a server via Bluetooth or WiFi. For example, a smart band measures heart rate every second and uploads the data to a server in real time via a smartphone.

[0344] Data Preprocessing

[0345] Server: Receives sensor data and performs preprocessing on the data. For example, it removes outliers (such as 0 BPM), fills in missing data, and converts the sensor data into a standard format. This preprocessed data is stored in a database and used for subsequent analysis.

[0346] Data analysis and AI model updates

[0347] Server: Extracts features from preprocessed data and updates the generative AI model. Machine learning algorithms are used to predict training effects and health status, and an emotion analysis engine is used to analyze the user's emotional data. For example, a user can enter their emotional records into a smartphone app, and the model is updated based on that data.

[0348] Generate training and meal plans

[0349] Server: Using the updated AI model, it generates optimal training and meal plans for each athlete. For example, it generates a plan based on the athlete's current fitness level and past training history, such as "30 minutes of running on Mondays and 45 minutes of strength training on Wednesdays," and includes high-protein foods in the meal plan.

[0350] Monitoring and generating warning messages

[0351] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if an athlete's heart rate exceeds 180 BPM, a warning message saying "Your heart rate is too high, you need to rest" is generated and sent to the athlete's smartphone.

[0352] User Feedback

[0353] Server and device: The server sends the generated training plan, meal plan, and warning messages to the user's device. This information is displayed on the user's device screen. For example, a smartphone might display "Today's training is a 30-minute run," and the athlete will then execute that plan.

[0354] Receiving feedback data and updating the model

[0355] User and server: The user uses a smartphone app to input feedback data. For example, they input information about what they ate today and their physical condition, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time. For example, the data the user inputs for "Today's Meals" is sent to the server and reflected in the next meal plan.

[0356] Examples of prompt statements

[0357] 1. How can IoT devices be used to collect heart rate and exercise data in real time?

[0358] 2. How can I preprocess the received data to remove outliers?

[0359] 3. Explain how to extract features from data and update a machine learning model.

[0360] 4. How can you generate optimal training and meal plans based on an athlete's data?

[0361] 5. How can I monitor sensor data in real time and generate warning messages when anomalies are detected?

[0362] 6. Explain how to send generated plans and warning messages to the user's device.

[0363] 7. Explain how you can receive feedback data from users and update your model.

[0364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0365] Step 1:

[0366] Data collection and transmission

[0367] Device: Athletes wear heart rate monitors or smart bands. These devices collect real-time sensor data such as heart rate, activity, calorie expenditure, location, and sleep patterns. The collected data is sent via Bluetooth or WiFi to the user's smartphone, which periodically uploads this data to a server.

[0368] Input: Sensor data obtained from IoT devices (heart rate, exercise amount, etc.)

[0369] Output: Collected sensor data sent to the server

[0370] How it works: The smart band measures your heart rate every second and sends the data to your smartphone via Bluetooth, which then uploads the data to a server in real time via WiFi.

[0371] Step 2:

[0372] Data Preprocessing

[0373] Server: Receives sensor data and preprocesses it. Preprocessing involves detecting and removing outliers, completing incomplete data, and converting data types. The preprocessed data is stored in a database for further processing.

[0374] Input: Sensor data collected in step 1

[0375] Output: Preprocessed sensor data

[0376] Specific operation: The server screens the received data to detect outliers such as a heart rate of 0 BPM and missing data, and then removes or complements them. After removing the outliers, the data is converted into a standard format (e.g., JSON format) and stored in a database.

[0377] Step 3:

[0378] Data analysis and AI model updates

[0379] Server: Extracts features from the preprocessed data and updates the generative AI model using a machine learning algorithm. During this process, the server analyzes the user's heart rate fluctuation patterns and cumulative exercise volume. It also uses a sentiment analysis engine to obtain and integrate user sentiment data.

[0380] Input: Preprocessed sensor data, user emotion data

[0381] Output: Updated generative AI model

[0382] How it works: Every night, the server runs a machine learning algorithm (e.g., deep learning) and updates the model based on data from the past 24 hours. It also integrates emotional data entered by users into the smartphone app to improve the accuracy of the model.

[0383] Step 4:

[0384] Generate training and meal plans

[0385] Server: Using the updated generative AI model, the server generates optimal training and meal plans for each athlete, based on the user's current fitness level, past training history, real-time sensor data, and emotional data.

[0386] Input: Updated generative AI model, user fitness data, sensor data, and emotion data

[0387] Output: personalized training and meal plans

[0388] How it works: The server generates this week's training plan based on last week's data. For example, a schedule and meal plan such as "30 minutes of running on Monday, 45 minutes of strength training on Wednesday" are automatically generated.

[0389] Step 5:

[0390] Monitoring and generating warning messages

[0391] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it generates a message saying, "Your heart rate is too high, you need to rest."

[0392] Input: Real-time sensor data

[0393] Output: Warning message

[0394] Specific operation: When the heart rate of the smart band exceeds 180 BPM while running, the server will immediately generate an alert and notify the smartphone.

[0395] Step 6:

[0396] User Feedback

[0397] Server and device: The server sends the generated training plan, meal plan, and warning message to the user's device and displays them on the device, allowing athletes and coaches to take optimal actions in real time.

[0398] Input: Training plans, meal plans, and warning messages sent from the server

[0399] Output: Information displayed on the user's terminal

[0400] Specific operation: Once a week, the server sends a new plan to the smartphone app, and the athlete receives a notification on their device saying, "A new training plan has been updated."

[0401] Step 7:

[0402] Receiving feedback data and updating the model

[0403] User and Server: The user inputs feedback data from their device and sends it to the server, which then combines this feedback data with preprocessed sensor data and uses it for the next model update.

[0404] Input: User feedback data (meal details, health information, etc.)

[0405] Output: Preprocessed feedback data, updated generative AI model

[0406] Specific operation: The user inputs "Today's Meal" into the smartphone app, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time, dynamically updating them in real time.

[0407] (Application example 2)

[0408] 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."

[0409] In modern factories, it is important to accurately monitor the operating status, efficiency, and maintenance demand of automated equipment, especially robots, in real time and provide optimal operation schedules and maintenance plans. Conventional systems often manage these elements individually, making integrated and dynamic management difficult. While combining these elements with an emotion engine makes it possible to provide plans that take the user's emotional state into account, no system has yet applied this to factory automation equipment. Therefore, there is a need for a system that can provide an integrated system for efficient operation and maintenance management of factory automation equipment.

[0410] 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 the operating status, efficiency, and maintenance demand of the factory's automated equipment in real time, means for generating an optimal operation schedule and maintenance plan using a generative AI model, and means for collecting feedback on the robot's operation and reflecting it in the next plan. This enables efficient operation and maintenance of the factory's automated equipment.

[0411] "IoT devices" refers to a wide range of physical devices and sensors connected to the Internet that can collect data and communicate with other devices and systems.

[0412] "Sensor data" refers to various types of data measured and collected by IoT devices, including temperature, heart rate, exercise volume, and calorie consumption.

[0413] "Preprocessing" refers to the processing performed on collected raw data to make it easier to analyze, including removing outliers, filling in incomplete data, and converting data types.

[0414] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes specific predictions or generates results from new data.

[0415] "Training Plan" refers to a plan created based on a generative AI model to optimize an athlete's training content.

[0416] "Meal plan" refers to a meal plan created based on a generative AI model, taking into account the athlete's nutritional balance.

[0417] "Real-time" refers to events or data being processed almost immediately after they occur, with almost no delay.

[0418] A "warning message" refers to a message sent to the user to warn them when the system detects an abnormality.

[0419] "User terminal" refers to a device that a user directly operates to display and input information, and examples include smartphones and tablets.

[0420] "Factory automation equipment" refers to various automated devices and robots used within factories to streamline the manufacturing process.

[0421] "Operational status" refers to information that indicates the current operating status of equipment or robots.

[0422] "Efficiency" refers to an indicator that shows how productive and efficient a device or robot is.

[0423] "Maintenance demand" refers to the need for maintenance and upkeep required to keep equipment and robots operating properly.

[0424] "Operation schedule" refers to a plan of optimal operating times and work content for equipment and robots, created based on a generative AI model.

[0425] "Feedback" refers to opinions and information provided by users or systems regarding the operating status of equipment or robots.

[0426] The system of this invention integrates IoT devices, generative AI models, and emotion engines to realize efficient operation and maintenance of automated equipment and robots in factories. The overall system configuration is as follows:

[0427] Data collection and transmission

[0428] Terminals and IoT devices:

[0429] Factory automation equipment is equipped with various sensors, such as temperature sensors, operation rate monitors, vibration sensors, etc. These IoT devices collect sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[0430] Data Preprocessing

[0431] server:

[0432] The server receives sensor data sent from each IoT device. The received data is then formatted into a standard format by removing outliers, completing incomplete data, and converting data types. The preprocessed data is then stored in a database.

[0433] Data analysis and AI model updates

[0434] server:

[0435] The server extracts features from the preprocessed data and updates the generative AI model. The generative AI model is then used to predict the operating efficiency and maintenance demand of automated equipment using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, an emotion engine is used to integrate feedback data and sensor data, enabling more accurate predictions.

[0436] Generate maintenance plans and operation schedules

[0437] server:

[0438] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data.

[0439] Monitoring and generating warning messages

[0440] server:

[0441] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and an inspection is required immediately."

[0442] User Feedback

[0443] Servers and devices:

[0444] The server generates operation schedules, maintenance plans, and warning messages, which are then sent to the user's terminal, where they are displayed to the factory manager, allowing him or her to take optimal action in real time.

[0445] Receiving feedback data and updating the model

[0446] Users and servers:

[0447] Users use their devices to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed sensor data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[0448] As a specific example, a case where the temperature of a gear of a device becomes abnormally high will be described.

[0449] 1. User: The administrator submits a request for a new maintenance plan from a terminal.

[0450] 2. Server: Analyzes real-time temperature sensor data, utilization and vibration data from the past week, and feedback data.

[0451] 3. Server: Generates an optimal maintenance plan (e.g., "Inspection is required immediately, prepare replacement parts") based on the generative AI model.

[0452] 4. Server: Sends the generated maintenance plan to the user's device.

[0453] 5. Terminal: The maintenance plan is displayed on the user's terminal, and the administrator works according to the plan.

[0454] Example prompt sentence:

[0455] "The temperature of the robot's gears is abnormally high. Should I take the specified action?" "Generate an optimal maintenance plan based on recent activity data."

[0456] This system dynamically and comprehensively manages the operational efficiency and maintenance of automated factory equipment, providing optimal operation schedules and maintenance plans. By combining it with an emotion engine, it is possible to take user feedback data into account to generate even more accurate predictions and plans.

[0457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0458] Step 1:

[0459] Data collection and transmission

[0460] The server collects real-time sensor data from various sensors (e.g., temperature sensors, utilization rate monitors, vibration sensors) attached to automated equipment in the factory. This data is sent to the server via communication protocols such as Bluetooth or WiFi. The input is the raw data from the sensors, and the output is the data sent to the server.

[0461] Step 2:

[0462] Data Preprocessing

[0463] The server preprocesses the received sensor data. During this process, outliers are removed, incomplete data is filled, and data types are converted to form a standard format. The input is sensor data, and the output is preprocessed data. Specific operations include removing abnormally high temperature data and filling in missing data points with the average value.

[0464] Step 3:

[0465] Feature extraction and AI model updating

[0466] The server extracts features from the preprocessed data and updates the generative AI model based on these. These features include, for example, the rate of change of temperature and the cumulative value of operating time. The input is the preprocessed data, and the output is the updated generative AI model. Specifically, the numerical values ​​of each sensor data are input into a machine learning algorithm to train the model.

[0467] Step 4:

[0468] Data integration using emotion engines

[0469] The server uses an emotion engine to integrate feedback data and sensor data. The emotion engine analyzes user feedback (e.g., that a device is not working properly) and integrates it with sensor data. The inputs are feedback data and sensor data, and the output is the integrated data. Specifically, it performs text analysis on the feedback data and raises the alert level if it contains specific keywords.

[0470] Step 5:

[0471] Generate maintenance plans and operation schedules

[0472] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data. The input is the integrated data, and the output is the operation schedule and maintenance plan.

[0473] Step 6:

[0474] Monitoring and generating warning messages

[0475] The server monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and inspection is required immediately." The input is real-time sensor data, and the output is a warning message.

[0476] Step 7:

[0477] Sending and displaying information to user terminals

[0478] The operation schedules, maintenance plans, and warning messages generated by the server are sent to the user's terminal. The terminal displays this information on its screen, allowing the factory manager to take optimal action in real time. The input is the generated information, and the output is the display on the user's terminal.

[0479] Step 8:

[0480] Collecting feedback data and updating the model

[0481] Users use their terminals to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time. The input is feedback data, and the output is integrated data.

[0482] 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.

[0483] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0484] 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.

[0485] [Second embodiment]

[0486] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0487] 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.

[0488] 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).

[0489] 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.

[0490] 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.

[0491] 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).

[0492] 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.

[0493] 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.

[0494] 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.

[0495] 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.

[0496] In the smart glasses 214, 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.

[0497] 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."

[0498] The system of the present invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific embodiments are described below.

[0499] Data collection and transmission

[0500] Device:

[0501] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect sensor data in real time, and the collected data is sent to a server via communication protocols such as Bluetooth or WiFi.

[0502] Data Preprocessing

[0503] server:

[0504] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is stored in a database for subsequent processing.

[0505] Data analysis and AI model updates

[0506] server:

[0507] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. The extracted features are used to update the generative AI model. The generative AI model is then used to predict the athlete's training effects and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[0508] Generate training and meal plans

[0509] server:

[0510] The server uses the updated AI model to generate optimal training and meal plans for each athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[0511] Monitoring and generating warning messages

[0512] server:

[0513] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[0514] User Feedback

[0515] Servers and devices:

[0516] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[0517] Receiving feedback data and updating the model

[0518] Users and servers:

[0519] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, so it is reflected dynamically in real time.

[0520] As a concrete example, consider an athlete who wants a new weekend training plan.

[0521] 1. User: The athlete sends a request for a new plan from their device.

[0522] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[0523] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[0524] 4. Server: Sends the generated training plan to the user's device.

[0525] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[0526] By taking specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance, providing optimal training and diet plans.

[0527] The processing flow will be explained below.

[0528] Step 1:

[0529] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[0530] Step 2:

[0531] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[0532] Step 3:

[0533] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[0534] Step 4:

[0535] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[0536] Step 5:

[0537] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[0538] Step 6:

[0539] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[0540] Step 7:

[0541] Server: Uses the updated AI model to generate optimal training plans for athletes, for example, determining next week's training schedule based on the athlete's current fitness level and past training history.

[0542] Step 8:

[0543] Server: Similarly, AI models are used to generate optimal meal plans, for example, by taking into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[0544] Step 9:

[0545] Server: The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality.

[0546] Step 10:

[0547] Server: Generates a warning message when an abnormality is detected, for example, "Your heart rate is too high, you need to rest."

[0548] Step 11:

[0549] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[0550] Step 12:

[0551] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[0552] Step 13:

[0553] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[0554] Step 14:

[0555] Terminal: User feedback data is sent to the server.

[0556] Step 15:

[0557] Server: Receives feedback data and integrates it with pre-processed sensor data.

[0558] Step 16:

[0559] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[0560] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and dietary plans for each individual athlete.

[0561] Example 1

[0562] 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."

[0563] Using IoT devices to monitor athletes' performance and health and provide optimal training and meal plans based on that data is crucial for creating plans that meet the needs of individual athletes. However, there are few systems that consistently execute complex processes such as real-time data collection, preprocessing, updating AI models, generating plans, detecting anomalies, and integrating feedback data. This makes it difficult to efficiently manage athletes' training and nutrition.

[0564] 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.

[0565] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for extracting features from the preprocessed sensor data, means for updating a generative AI model based on the features, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for receiving meal content and physical condition information as user feedback data and generating or modifying a meal plan based on the data. This makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[0566] An "IoT device" is a physical device that can connect to the internet and collect, transmit, and share data. Examples include smart bands, heart rate monitors, and GPS tracking devices.

[0567] "Sensor data" refers to information such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns measured by IoT devices.

[0568] "Preprocessing" refers to the process of converting sensor data into a standard format by removing outliers, filling in incomplete data, converting data types, etc.

[0569] "Features" are computable attributes or properties extracted from preprocessed sensor data that can be used by machine learning algorithms. Examples include average and maximum heart rate, and cumulative exercise volume.

[0570] A "generative AI model" is a model created using machine learning algorithms to make predictions and classifications based on data. It is used to predict the training effects and health status of athletes.

[0571] A "training plan" is a plan created using a generative AI model that shows an athlete's optimal exercise schedule and training content.

[0572] A "meal plan" is a plan created using a generative AI model that takes into account an athlete's daily diet and nutritional balance.

[0573] "Real-time monitoring" refers to the state in which sensor data is continuously monitored and abnormalities or specific conditions can be detected immediately.

[0574] A "warning message" is a notification message that is generated when an abnormality is detected during the monitoring process, and includes content that alerts the user.

[0575] "User Device" means a device used by an Athlete or Personnel to receive and display information. Examples include smartphones and tablets.

[0576] "Feedback data" refers to information such as dietary habits and physical condition that users enter on a daily basis, and is used to improve the accuracy of the generative AI model.

[0577] "Preprocessed sensor data" refers to sensor data that has undergone preprocessing such as removing outliers and interpolating data, and has been converted into a standard format.

[0578] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific implementation of this system is described below.

[0579] Configuration and Usage

[0580] Device application and data collection

[0581] Users (athletes) wear IoT devices such as smart bands, heart rate monitors, and GPS tracking devices. These devices measure data such as heart rate, exercise volume, calorie consumption, location, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi.

[0582] Data Preprocessing

[0583] The server receives raw data sent from each IoT device and performs preprocessing such as detecting and removing outliers, filling in incomplete data, and converting data types, so that the data is formatted into a standard format. This preprocessed data is stored in a database for subsequent processing.

[0584] Data analysis and AI model updates

[0585] The server extracts features from the preprocessed data stored in the database. Examples include average and maximum heart rate values ​​and cumulative exercise volume. Based on these features, the generative AI model is updated. This model update uses machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). The updated generative AI model is then used to predict the athlete's training effects and health status.

[0586] Generate training and meal plans

[0587] The server uses a generative AI model to generate optimal training and meal plans for each individual athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[0588] Real-time monitoring and alerts

[0589] The server monitors the sensor data in real time. If an abnormality is detected, such as if the heart rate exceeds a certain threshold, a warning message is generated and sent to the user's device. The message might say something like, "Your heart rate is too high, so you need to rest."

[0590] Collecting and synthesizing feedback

[0591] Users input feedback data (e.g., what they ate today and their physical condition) using devices such as smartphones or tablets. This feedback is sent to the server and integrated with preprocessed sensor data. This integrated data is used to update the generative AI model and generate plans for the next time, so it is reflected dynamically in real time.

[0592] Specific examples

[0593] A concrete example would be an athlete wanting a new weekend training plan.

[0594] 1. The user (athlete) sends a request for a new plan from their device.

[0595] 2. The server analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[0596] 3. The server generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[0597] 4. The server sends the generated training plan to the user's device.

[0598] 5. The training plan will be displayed on the device and the athlete will train according to the plan.

[0599] Prompt Sentence Examples

[0600] "Write a program that generates an optimal training plan based on an athlete's heart rate and exercise data from the past week."

[0601] By performing detailed and specific operations at each processing step, this invention makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[0602] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0603] Step 1: Data collection and transmission

[0604] The device (the athlete wearing the IoT device) measures data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi. Specifically, the smart band measures heart rate every five seconds and transfers this data to a smartphone app. The app then sends the data to the server, so the input becomes real-time measured sensor data, and the output becomes the data sent to the server.

[0605] Step 2: Preprocessing the data

[0606] The server receives raw data sent from each IoT device. Because this data may contain outliers, preprocessing is performed, including detecting and removing outliers, completing incomplete data, and converting data types. Specifically, upper and lower limits are set for the data to detect outliers, and data outside these limits is removed. Missing data is completed with the average value, so the input is the raw data sent to the server, and the output is preprocessed data. This preprocessed data is stored in a database.

[0607] Step 3: Data analysis and feature extraction

[0608] The server extracts features from the preprocessed data. These include, for example, the average and maximum heart rate, and the cumulative amount of exercise. Specifically, it plots the time variation of heart rate on a graph, detects peaks, and evaluates the intensity of training. The input is the preprocessed data, and the output is the extracted features.

[0609] Step 4: Update the generative AI model

[0610] The server updates the generative AI model based on the extracted features. Machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) are used. Specifically, the server inputs the time change in heart rate and the cumulative value of exercise volume into the AI ​​model, and then retrains the model. The input is the extracted features, and the output is the updated generative AI model.

[0611] Step 5: Create a training and meal plan

[0612] The server uses an updated generative AI model to generate optimal training and meal plans for each individual athlete. It determines the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data. Specific operations include setting running distance and rest days when generating a training plan, and taking calories and nutritional balance into account when creating a meal plan. The input is an updated generative AI model and real-time data, and the output is the generated training plan and meal plan.

[0613] Step 6: Real-time monitoring and alerting

[0614] The server monitors sensor data in real time. If an abnormality is detected based on the sensor data, such as when the heart rate exceeds a certain threshold, a warning message is generated. Specifically, if the heart rate exceeds 180, a message such as "Rest is required" is generated and the athlete is notified. The input is the real-time sensor data, and the output is the generated warning message.

[0615] Step 7: User feedback

[0616] The server sends the generated training plan, meal plan, and warning messages to the user's device. The device receives this information and displays it on the screen. Specifically, the training plan is displayed on the calendar on the smartphone app, and reminders are sent to the athlete using the notification function. The input is the generated training plan, meal plan, and warning messages, and the output is this information displayed on the device.

[0617] Step 8: Receiving and consolidating feedback data

[0618] Users use devices such as smartphones or tablets to input feedback data (e.g., what they ate today and their physical condition information). The server receives this data and integrates it with preprocessed sensor data. Specifically, the athlete enters the details of what they ate today into the app, and this data is analyzed by the server and reflected in the next meal plan. The input is the feedback data sent from the user's device, and the output is the integrated data. The integrated data is then used for the next update of the generative AI model.

[0619] (Application example 1)

[0620] 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."

[0621] When operating factory robots, it is important to monitor their performance and health in real time and generate optimal maintenance plans. However, current systems make it difficult to efficiently collect and analyze this data and take appropriate measures. Factory robots, in particular, have a wide variety of sensor data, so data integration and accurate analysis are required. Furthermore, when an abnormality is detected, it is essential to generate warning messages for rapid response and to notify the optimal maintenance plan. Technology to solve this problem is needed.

[0622] 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.

[0623] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for collecting sensor data from a factory robot and monitoring temperature, vibration, current, etc., means for monitoring the performance and health status of the factory robot in real time and generating a warning message when an anomaly is detected, means for generating an optimal maintenance plan for the factory robot using the generative AI model, means for notifying appropriate maintenance actions based on the sensor data of the factory robot, and means for displaying the information transmitted to the user terminal. This enables real-time monitoring of the performance and health status of factory robots, enabling the generation of appropriate maintenance plans and rapid response to abnormalities.

[0624] An "IoT device" is a physical device that can collect, send, or receive data over the Internet.

[0625] "Sensor data" refers to data measured and collected by various sensors, and includes information such as temperature, vibration, and current.

[0626] "Preprocessing" is the process of performing operations on raw data, such as removing outliers, filling in incomplete data, and converting data types, to prepare the data in a form suitable for analysis.

[0627] A "generative AI model" is a model built using machine learning algorithms to generate patterns and predictions from data.

[0628] A "Training Plan" is a plan that shows the optimal training schedule and content for an athlete and equipment.

[0629] A "meal plan" is a plan that shows the meal content and schedule optimized to maintain an athlete's health and improve their performance.

[0630] An "abnormality" is a state in which a value or pattern outside the normal range is detected from collected sensor data.

[0631] A "warning message" is a notification message that is generated when an anomaly is detected, informing the user of the existence of a problem and the necessary action to be taken.

[0632] A "user terminal" is a device used by a user, such as a smartphone or tablet, that displays information from the system.

[0633] "Robot performance" is an indicator of how efficiently and accurately a robot can perform a given task.

[0634] "Health status" refers to the normal operating condition of each part of the robot and the entire system.

[0635] A "maintenance plan" is a specific work plan for inspections, repairs, part replacements, etc. required to maintain the proper operation of a robot.

[0636] The present invention provides a system for monitoring the performance and health status of factory robots in real time and generating an optimal maintenance plan. Specific embodiments of the system are described below.

[0637] Data collection and transmission

[0638] Device:

[0639] Factory robots are equipped with various sensors, such as temperature sensors, vibration sensors, and current sensors. These sensors measure the status of each part of the robot and the overall system, and collect data in real time. The collected sensor data is sent to a server via communication protocols such as Bluetooth and WiFi.

[0640] Data Preprocessing

[0641] server:

[0642] The server receives the sensor data sent from each sensor and performs preprocessing, which includes removing outliers, filling in incomplete data, converting data types, etc. The preprocessed data is then converted into a standard format and stored in a database.

[0643] Data analysis and AI model updates

[0644] server:

[0645] Features are extracted from the preprocessed data and used to update the generative AI model. For example, features such as temperature changes over time or cumulative vibration values ​​can be used. The updated generative AI model is then used to detect anomalies in factory robots, predict performance, and generate maintenance plans. Machine learning algorithms (e.g., deep learning and random forests) are used to create the generative AI model.

[0646] Generate a maintenance plan

[0647] server:

[0648] Using a generative AI model, the system generates an optimal maintenance plan based on the condition of factory robots. For example, it suggests the timing of part replacement and adjustment items based on the degree of deterioration of each part of the robot and the frequency of abnormality detection.

[0649] Monitoring and generating warning messages

[0650] server:

[0651] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the vibration sensor exceeds a certain threshold, it generates a message saying, "Vibration is too high, immediate inspection required."

[0652] User Feedback

[0653] Servers and devices:

[0654] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action in real time.

[0655] Receiving feedback data and updating the model

[0656] Users and servers:

[0657] The results of the maintenance work and feedback data (e.g., work content and robot status information) are sent from the user device to the server, where they are combined with preprocessed sensor data and used for the next model update and plan generation.

[0658] Hardware and software used

[0659] Hardware:

[0660] IoT devices: temperature sensors, vibration sensors, current sensors

[0661] Server: Data preprocessing and AI model operation

[0662] software:

[0663] Python (data collection, preprocessing, modeling)

[0664] Libraries: NumPy, Pandas, scikit-learn, Keras

[0665] Communication protocol: Bluetooth, WiFi

[0666] Specific examples

[0667] For example, if a factory robot detects a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, the server will immediately detect the abnormality and generate a warning message stating, "Vibration is too high and requires immediate inspection," and send it to the user terminal.

[0668] Prompt Sentence Examples

[0669] "If the sensors attached to a factory robot detect a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, detect the abnormality and immediately generate a maintenance plan."

[0670] In this way, the system enables real-time monitoring of the performance and health of factory robots, enabling the creation of optimal maintenance plans and rapid response to abnormalities.

[0671] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0672] Step 1:

[0673] Data collection and transmission

[0674] Device:

[0675] Various sensor data is collected in real time from temperature sensors, vibration sensors, current sensors, etc. attached to factory robots, and the collected data is sent to a server via communication protocols such as Bluetooth and WiFi.

[0676] Input: Measurement data of each sensor (e.g. temperature, vibration, current)

[0677] Output: Sensor data sent to the server

[0678] Step 2:

[0679] Data Preprocessing

[0680] server:

[0681] The server preprocesses the raw data received from each sensor, removing outliers, completing incomplete data, converting data types, and formatting it into a standard format. The preprocessed data is then stored in a database.

[0682] Input: Raw data (measurement data sent from each sensor)

[0683] Output: Preprocessed data (outlier removal, data imputation, and data formatting)

[0684] Step 3:

[0685] Feature extraction and AI model updating

[0686] server:

[0687] Extract features (e.g., temperature change over time, cumulative vibration value) from preprocessed data. Update the generative AI model using the extracted features. Machine learning algorithms used here include deep learning and random forests.

[0688] Input: Preprocessed data

[0689] Output: Updated generative AI model

[0690] Step 4:

[0691] Generate a maintenance plan

[0692] server:

[0693] Based on the updated generative AI model, the server generates an optimal maintenance plan (e.g., part replacement timing and adjustment items) according to the state of the factory robot. The generated maintenance plan is sent to the user's device.

[0694] Input: Updated generative AI model, real-time data from each sensor

[0695] Output: Optimal maintenance plan

[0696] Step 5:

[0697] Real-time monitoring and warning message generation

[0698] server:

[0699] The server monitors sensor data in real time and immediately generates a warning message if an abnormality is detected. For example, if a vibration sensor exceeds a threshold, a warning message stating "Vibration is too high, immediate inspection is required" is generated and sent to the user's device.

[0700] Input: Real-time sensor data

[0701] Output: Warning message

[0702] Step 6:

[0703] User Feedback

[0704] Servers and devices:

[0705] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action immediately.

[0706] Inputs: Maintenance plan, warning message

[0707] Output: Information displayed on the terminal screen

[0708] Step 7:

[0709] Receiving feedback data and updating the model

[0710] Users and servers:

[0711] The user inputs the results of maintenance work and feedback (e.g., work content, robot status information) from the terminal. This data is sent to the server and integrated with preprocessed sensor data. The integrated data is used for the next model update and plan generation.

[0712] Input: Feedback data from users

[0713] Output: Integrated data (preprocessed sensor data + feedback data)

[0714] In this way, the system enables real-time performance and health monitoring of factory robot operations, the generation of optimal maintenance plans, and rapid response to abnormalities.

[0715] 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.

[0716] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Furthermore, the system also incorporates an emotion engine to recognize the user's emotions, enabling the provision of even more personalized plans. Specific embodiments are described below.

[0717] Data collection and transmission

[0718] Device:

[0719] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure their heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect the measured sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[0720] Data Preprocessing

[0721] server:

[0722] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is then stored in a database for subsequent processing.

[0723] Data analysis and AI model updates

[0724] server:

[0725] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. It then updates the generative AI model based on the extracted features. The generative AI model is then used to predict the athlete's training effect and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, the server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and integrates the results with the preprocessed sensor data and feedback data.

[0726] Generate training and meal plans

[0727] server:

[0728] The server uses the updated AI model to generate optimal training and meal plans for each athlete. For example, the next week's training schedule and daily meal menu are determined based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[0729] Monitoring and generating warning messages

[0730] server:

[0731] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[0732] User Feedback

[0733] Servers and devices:

[0734] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[0735] Receiving feedback data and updating the model

[0736] Users and servers:

[0737] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[0738] As a concrete example, consider an athlete who wants a new weekend training plan.

[0739] 1. User: The athlete sends a request for a new plan from their device.

[0740] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, food records, and emotional data.

[0741] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[0742] 4. Server: Sends the generated training plan to the user's device.

[0743] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[0744] By performing specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance and provides optimal training and meal plans. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take the user's emotional state into consideration, realizing a more personalized service.

[0745] The processing flow will be explained below.

[0746] Step 1:

[0747] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[0748] Step 2:

[0749] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[0750] Step 3:

[0751] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[0752] Step 4:

[0753] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[0754] Step 5:

[0755] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[0756] Step 6:

[0757] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[0758] Step 7:

[0759] Server: Analyzes emotional data from the user's voice and facial expressions using an emotion engine. The emotion engine uses voice recognition and image recognition technologies.

[0760] Step 8:

[0761] Server: Integrates the emotion data recognized by the emotion engine with preprocessed sensor data and feature data.

[0762] Step 9:

[0763] Server: Uses the updated AI model to generate the optimal training plan for the athlete. For example, it determines the next week's training schedule based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[0764] Step 10:

[0765] Server: Similarly, it uses AI models to generate optimal meal plans, for example, proposing meal menus that take into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[0766] Step 11:

[0767] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality and generates a message saying, "Your heart rate is too high, so you need to rest."

[0768] Step 12:

[0769] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[0770] Step 13:

[0771] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[0772] Step 14:

[0773] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[0774] Step 15:

[0775] Terminal: User feedback data is sent to the server.

[0776] Step 16:

[0777] Server: Receives feedback data and integrates it with pre-processed sensor data.

[0778] Step 17:

[0779] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[0780] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and meal plans for each individual athlete. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take into account the user's emotional state, achieving a more personalized service.

[0781] Example 2

[0782] 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."

[0783] Conventional athlete training and health management systems lack real-time monitoring, making it difficult to provide optimal training and diet plans tailored to each individual athlete's condition. They also lack the ability to generate personalized plans that take into account the user's emotional state. This has resulted in problems with the inability to efficiently and effectively improve performance and manage health.

[0784] 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.

[0785] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for acquiring user emotion data using an emotion analysis engine and integrating it with the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time and detecting anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, meal plan, and warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for personalizing training plans and meal plans based on the user emotion data, thereby enabling real-time monitoring and providing personalized training plans and meal plans that take the user's emotional state into account.

[0786] An "IoT device" is an electronic device that is connected to the Internet and collects data about the user's activities and environment.

[0787] "Sensor data" refers to measurement data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns collected by IoT devices.

[0788] "Preprocessing" is the process of formatting collected sensor data, removing outliers, filling in missing values, and converting data types.

[0789] A "generative AI model" is a model that uses machine learning algorithms to predict an athlete's training effects and health status, and generate optimal training and meal plans.

[0790] An "emotion analysis engine" is an engine that analyzes emotional data from a user's voice and facial expressions and integrates the results with other data.

[0791] A "training plan" is an exercise schedule created to improve an athlete's performance and maintain their health.

[0792] A "meal plan" is a meal menu created with the purpose of improving an athlete's health and training effectiveness.

[0793] "Real-time monitoring" is the process of constantly monitoring sensor data and acquiring and analyzing the data in real time.

[0794] A "warning message" is a notification message that is generated when an abnormality is detected during real-time monitoring.

[0795] "User devices" are electronic devices such as smartphones and tablets used by athletes.

[0796] "Feedback data" refers to data such as dietary details and physical condition information that is input by the user via the terminal.

[0797] This invention is a system that utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time, and provides optimal training and meal plans. Furthermore, by combining it with an emotion analysis engine, it is possible to provide personalized plans that take the user's emotional state into account.

[0798] Hardware and software used

[0799] 1. IoT devices: Use electronic devices such as heart rate monitors, smart bands, and GPS tracking devices. These devices are worn by athletes and collect real-time sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[0800] 2. Server: Used for preprocessing, data analysis, updating AI models, generating warning messages, and generating training and meal plans. Equipped with machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) and a sentiment analysis engine.

[0801] 3. User terminal: Uses electronic devices such as smartphones and tablets. These terminals display training plans, meal plans, and warning messages sent from the server, and receive feedback data from the user (e.g., dietary details and physical condition information).

[0802] Specific Embodiments

[0803] Data collection and transmission

[0804] Device: Athletes wear heart rate monitors or smart bands. These devices transmit collected sensor data to a server via Bluetooth or WiFi. For example, a smart band measures heart rate every second and uploads the data to a server in real time via a smartphone.

[0805] Data Preprocessing

[0806] Server: Receives sensor data and performs preprocessing on the data. For example, it removes outliers (such as 0 BPM), fills in missing data, and converts the sensor data into a standard format. This preprocessed data is stored in a database and used for subsequent analysis.

[0807] Data analysis and AI model updates

[0808] Server: Extracts features from preprocessed data and updates the generative AI model. Machine learning algorithms are used to predict training effects and health status, and an emotion analysis engine is used to analyze the user's emotional data. For example, a user can enter their emotional records into a smartphone app, and the model is updated based on that data.

[0809] Generate training and meal plans

[0810] Server: Using the updated AI model, it generates optimal training and meal plans for each athlete. For example, it generates a plan based on the athlete's current fitness level and past training history, such as "30 minutes of running on Mondays and 45 minutes of strength training on Wednesdays," and includes high-protein foods in the meal plan.

[0811] Monitoring and generating warning messages

[0812] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if an athlete's heart rate exceeds 180 BPM, a warning message saying "Your heart rate is too high, you need to rest" is generated and sent to the athlete's smartphone.

[0813] User Feedback

[0814] Server and device: The server sends the generated training plan, meal plan, and warning messages to the user's device. This information is displayed on the user's device screen. For example, a smartphone might display "Today's training is a 30-minute run," and the athlete will then execute that plan.

[0815] Receiving feedback data and updating the model

[0816] User and server: The user uses a smartphone app to input feedback data. For example, they input information about what they ate today and their physical condition, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time. For example, the data the user inputs for "Today's Meals" is sent to the server and reflected in the next meal plan.

[0817] Examples of prompt statements

[0818] 1. How can IoT devices be used to collect heart rate and exercise data in real time?

[0819] 2. How can I preprocess the received data to remove outliers?

[0820] 3. Explain how to extract features from data and update a machine learning model.

[0821] 4. How can you generate optimal training and meal plans based on an athlete's data?

[0822] 5. How can I monitor sensor data in real time and generate warning messages when anomalies are detected?

[0823] 6. Explain how to send generated plans and warning messages to the user's device.

[0824] 7. Explain how you can receive feedback data from users and update your model.

[0825] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0826] Step 1:

[0827] Data collection and transmission

[0828] Device: Athletes wear heart rate monitors or smart bands. These devices collect real-time sensor data such as heart rate, activity, calorie expenditure, location, and sleep patterns. The collected data is sent via Bluetooth or WiFi to the user's smartphone, which periodically uploads this data to a server.

[0829] Input: Sensor data obtained from IoT devices (heart rate, exercise amount, etc.)

[0830] Output: Collected sensor data sent to the server

[0831] How it works: The smart band measures your heart rate every second and sends the data to your smartphone via Bluetooth, which then uploads the data to a server in real time via WiFi.

[0832] Step 2:

[0833] Data Preprocessing

[0834] Server: Receives sensor data and preprocesses it. Preprocessing involves detecting and removing outliers, completing incomplete data, and converting data types. The preprocessed data is stored in a database for further processing.

[0835] Input: Sensor data collected in step 1

[0836] Output: Preprocessed sensor data

[0837] Specific operation: The server screens the received data to detect outliers such as a heart rate of 0 BPM and missing data, and then removes or complements them. After removing the outliers, the data is converted into a standard format (e.g., JSON format) and stored in a database.

[0838] Step 3:

[0839] Data analysis and AI model updates

[0840] Server: Extracts features from the preprocessed data and updates the generative AI model using a machine learning algorithm. During this process, the server analyzes the user's heart rate fluctuation patterns and cumulative exercise volume. It also uses a sentiment analysis engine to obtain and integrate user sentiment data.

[0841] Input: Preprocessed sensor data, user emotion data

[0842] Output: Updated generative AI model

[0843] How it works: Every night, the server runs a machine learning algorithm (e.g., deep learning) and updates the model based on data from the past 24 hours. It also integrates emotional data entered by users into the smartphone app to improve the accuracy of the model.

[0844] Step 4:

[0845] Generate training and meal plans

[0846] Server: Using the updated generative AI model, the server generates optimal training and meal plans for each athlete, based on the user's current fitness level, past training history, real-time sensor data, and emotional data.

[0847] Input: Updated generative AI model, user fitness data, sensor data, and emotion data

[0848] Output: personalized training and meal plans

[0849] How it works: The server generates this week's training plan based on last week's data. For example, a schedule and meal plan such as "30 minutes of running on Monday, 45 minutes of strength training on Wednesday" are automatically generated.

[0850] Step 5:

[0851] Monitoring and generating warning messages

[0852] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it generates a message saying, "Your heart rate is too high, you need to rest."

[0853] Input: Real-time sensor data

[0854] Output: Warning message

[0855] Specific operation: When the heart rate of the smart band exceeds 180 BPM while running, the server will immediately generate an alert and notify the smartphone.

[0856] Step 6:

[0857] User Feedback

[0858] Server and device: The server sends the generated training plan, meal plan, and warning message to the user's device and displays them on the device, allowing athletes and coaches to take optimal actions in real time.

[0859] Input: Training plans, meal plans, and warning messages sent from the server

[0860] Output: Information displayed on the user's terminal

[0861] Specific operation: Once a week, the server sends a new plan to the smartphone app, and the athlete receives a notification on their device saying, "A new training plan has been updated."

[0862] Step 7:

[0863] Receiving feedback data and updating the model

[0864] User and Server: The user inputs feedback data from their device and sends it to the server, which then combines this feedback data with preprocessed sensor data and uses it for the next model update.

[0865] Input: User feedback data (meal details, health information, etc.)

[0866] Output: Preprocessed feedback data, updated generative AI model

[0867] Specific operation: The user inputs "Today's Meal" into the smartphone app, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time, dynamically updating them in real time.

[0868] (Application example 2)

[0869] 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."

[0870] In modern factories, it is important to accurately monitor the operating status, efficiency, and maintenance demand of automated equipment, especially robots, in real time and provide optimal operation schedules and maintenance plans. Conventional systems often manage these elements individually, making integrated and dynamic management difficult. While combining these elements with an emotion engine makes it possible to provide plans that take the user's emotional state into account, no system has yet applied this to factory automation equipment. Therefore, there is a need for a system that can provide an integrated system for efficient operation and maintenance management of factory automation equipment.

[0871] 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 the operating status, efficiency, and maintenance demand of the factory's automated equipment in real time, means for generating an optimal operation schedule and maintenance plan using a generative AI model, and means for collecting feedback on the robot's operation and reflecting it in the next plan. This enables efficient operation and maintenance of the factory's automated equipment.

[0872] "IoT devices" refers to a wide range of physical devices and sensors connected to the Internet that can collect data and communicate with other devices and systems.

[0873] "Sensor data" refers to various types of data measured and collected by IoT devices, including temperature, heart rate, exercise volume, and calorie consumption.

[0874] "Preprocessing" refers to the processing performed on collected raw data to make it easier to analyze, including removing outliers, filling in incomplete data, and converting data types.

[0875] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes specific predictions or generates results from new data.

[0876] "Training Plan" refers to a plan created based on a generative AI model to optimize an athlete's training content.

[0877] "Meal plan" refers to a meal plan created based on a generative AI model, taking into account the athlete's nutritional balance.

[0878] "Real-time" refers to events or data being processed almost immediately after they occur, with almost no delay.

[0879] A "warning message" refers to a message sent to the user to warn them when the system detects an abnormality.

[0880] "User terminal" refers to a device that a user directly operates to display and input information, and examples include smartphones and tablets.

[0881] "Factory automation equipment" refers to various automated devices and robots used within factories to streamline the manufacturing process.

[0882] "Operational status" refers to information that indicates the current operating status of equipment or robots.

[0883] "Efficiency" refers to an indicator that shows how productive and efficient a device or robot is.

[0884] "Maintenance demand" refers to the need for maintenance and upkeep required to keep equipment and robots operating properly.

[0885] "Operation schedule" refers to a plan of optimal operating times and work content for equipment and robots, created based on a generative AI model.

[0886] "Feedback" refers to opinions and information provided by users or systems regarding the operating status of equipment or robots.

[0887] The system of this invention integrates IoT devices, generative AI models, and emotion engines to realize efficient operation and maintenance of automated equipment and robots in factories. The overall system configuration is as follows:

[0888] Data collection and transmission

[0889] Terminals and IoT devices:

[0890] Factory automation equipment is equipped with various sensors, such as temperature sensors, operation rate monitors, vibration sensors, etc. These IoT devices collect sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[0891] Data Preprocessing

[0892] server:

[0893] The server receives sensor data sent from each IoT device. The received data is then formatted into a standard format by removing outliers, completing incomplete data, and converting data types. The preprocessed data is then stored in a database.

[0894] Data analysis and AI model updates

[0895] server:

[0896] The server extracts features from the preprocessed data and updates the generative AI model. The generative AI model is then used to predict the operating efficiency and maintenance demand of automated equipment using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, an emotion engine is used to integrate feedback data and sensor data, enabling more accurate predictions.

[0897] Generate maintenance plans and operation schedules

[0898] server:

[0899] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data.

[0900] Monitoring and generating warning messages

[0901] server:

[0902] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and an inspection is required immediately."

[0903] User Feedback

[0904] Servers and devices:

[0905] The server generates operation schedules, maintenance plans, and warning messages, which are then sent to the user's terminal, where they are displayed to the factory manager, allowing him or her to take optimal action in real time.

[0906] Receiving feedback data and updating the model

[0907] Users and servers:

[0908] Users use their devices to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed sensor data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[0909] As a specific example, a case where the temperature of a gear of a device becomes abnormally high will be described.

[0910] 1. User: The administrator submits a request for a new maintenance plan from a terminal.

[0911] 2. Server: Analyzes real-time temperature sensor data, utilization and vibration data from the past week, and feedback data.

[0912] 3. Server: Generates an optimal maintenance plan (e.g., "Inspection is required immediately, prepare replacement parts") based on the generative AI model.

[0913] 4. Server: Sends the generated maintenance plan to the user's device.

[0914] 5. Terminal: The maintenance plan is displayed on the user's terminal, and the administrator works according to the plan.

[0915] Example prompt sentence:

[0916] "The temperature of the robot's gears is abnormally high. Should I take the specified action?" "Generate an optimal maintenance plan based on recent activity data."

[0917] This system dynamically and comprehensively manages the operational efficiency and maintenance of automated factory equipment, providing optimal operation schedules and maintenance plans. By combining it with an emotion engine, it is possible to take user feedback data into account to generate even more accurate predictions and plans.

[0918] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0919] Step 1:

[0920] Data collection and transmission

[0921] The server collects real-time sensor data from various sensors (e.g., temperature sensors, utilization rate monitors, vibration sensors) attached to automated equipment in the factory. This data is sent to the server via communication protocols such as Bluetooth or WiFi. The input is the raw data from the sensors, and the output is the data sent to the server.

[0922] Step 2:

[0923] Data Preprocessing

[0924] The server preprocesses the received sensor data. During this process, outliers are removed, incomplete data is filled, and data types are converted to form a standard format. The input is sensor data, and the output is preprocessed data. Specific operations include removing abnormally high temperature data and filling in missing data points with the average value.

[0925] Step 3:

[0926] Feature extraction and AI model updating

[0927] The server extracts features from the preprocessed data and updates the generative AI model based on these. These features include, for example, the rate of change of temperature and the cumulative value of operating time. The input is the preprocessed data, and the output is the updated generative AI model. Specifically, the numerical values ​​of each sensor data are input into a machine learning algorithm to train the model.

[0928] Step 4:

[0929] Data integration using emotion engines

[0930] The server uses an emotion engine to integrate feedback data and sensor data. The emotion engine analyzes user feedback (e.g., that a device is not working properly) and integrates it with sensor data. The inputs are feedback data and sensor data, and the output is the integrated data. Specifically, it performs text analysis on the feedback data and raises the alert level if it contains specific keywords.

[0931] Step 5:

[0932] Generate maintenance plans and operation schedules

[0933] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data. The input is the integrated data, and the output is the operation schedule and maintenance plan.

[0934] Step 6:

[0935] Monitoring and generating warning messages

[0936] The server monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and inspection is required immediately." The input is real-time sensor data, and the output is a warning message.

[0937] Step 7:

[0938] Sending and displaying information to user terminals

[0939] The operation schedules, maintenance plans, and warning messages generated by the server are sent to the user's terminal. The terminal displays this information on its screen, allowing the factory manager to take optimal action in real time. The input is the generated information, and the output is the display on the user's terminal.

[0940] Step 8:

[0941] Collecting feedback data and updating the model

[0942] Users use their terminals to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time. The input is feedback data, and the output is integrated data.

[0943] 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.

[0944] 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.

[0945] 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.

[0946] [Third embodiment]

[0947] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0948] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0949] 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).

[0950] 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.

[0951] 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.

[0952] 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).

[0953] 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.

[0954] 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.

[0955] 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.

[0956] 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.

[0957] 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.

[0958] 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."

[0959] The system of the present invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific embodiments are described below.

[0960] Data collection and transmission

[0961] Device:

[0962] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect sensor data in real time, and the collected data is sent to a server via communication protocols such as Bluetooth or WiFi.

[0963] Data Preprocessing

[0964] server:

[0965] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is stored in a database for subsequent processing.

[0966] Data analysis and AI model updates

[0967] server:

[0968] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. The extracted features are used to update the generative AI model. The generative AI model is then used to predict the athlete's training effects and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[0969] Generate training and meal plans

[0970] server:

[0971] The server uses the updated AI model to generate optimal training and meal plans for each athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[0972] Monitoring and generating warning messages

[0973] server:

[0974] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[0975] User Feedback

[0976] Servers and devices:

[0977] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[0978] Receiving feedback data and updating the model

[0979] Users and servers:

[0980] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, so it is reflected dynamically in real time.

[0981] As a concrete example, consider an athlete who wants a new weekend training plan.

[0982] 1. User: The athlete sends a request for a new plan from their device.

[0983] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[0984] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[0985] 4. Server: Sends the generated training plan to the user's device.

[0986] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[0987] By taking specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance, providing optimal training and diet plans.

[0988] The processing flow will be explained below.

[0989] Step 1:

[0990] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[0991] Step 2:

[0992] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[0993] Step 3:

[0994] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[0995] Step 4:

[0996] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[0997] Step 5:

[0998] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[0999] Step 6:

[1000] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[1001] Step 7:

[1002] Server: Uses the updated AI model to generate optimal training plans for athletes, for example, determining next week's training schedule based on the athlete's current fitness level and past training history.

[1003] Step 8:

[1004] Server: Similarly, AI models are used to generate optimal meal plans, for example, by taking into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[1005] Step 9:

[1006] Server: The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality.

[1007] Step 10:

[1008] Server: Generates a warning message when an abnormality is detected, for example, "Your heart rate is too high, you need to rest."

[1009] Step 11:

[1010] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[1011] Step 12:

[1012] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[1013] Step 13:

[1014] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[1015] Step 14:

[1016] Terminal: User feedback data is sent to the server.

[1017] Step 15:

[1018] Server: Receives feedback data and integrates it with pre-processed sensor data.

[1019] Step 16:

[1020] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[1021] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and dietary plans for each individual athlete.

[1022] Example 1

[1023] 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."

[1024] Using IoT devices to monitor athletes' performance and health and provide optimal training and meal plans based on that data is crucial for creating plans that meet the needs of individual athletes. However, there are few systems that consistently execute complex processes such as real-time data collection, preprocessing, updating AI models, generating plans, detecting anomalies, and integrating feedback data. This makes it difficult to efficiently manage athletes' training and nutrition.

[1025] 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.

[1026] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for extracting features from the preprocessed sensor data, means for updating a generative AI model based on the features, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for receiving meal content and physical condition information as user feedback data and generating or modifying a meal plan based on the data. This makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[1027] An "IoT device" is a physical device that can connect to the internet and collect, transmit, and share data. Examples include smart bands, heart rate monitors, and GPS tracking devices.

[1028] "Sensor data" refers to information such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns measured by IoT devices.

[1029] "Preprocessing" refers to the process of converting sensor data into a standard format by removing outliers, filling in incomplete data, converting data types, etc.

[1030] "Features" are computable attributes or properties extracted from preprocessed sensor data that can be used by machine learning algorithms. Examples include average and maximum heart rate, and cumulative exercise volume.

[1031] A "generative AI model" is a model created using machine learning algorithms to make predictions and classifications based on data. It is used to predict the training effects and health status of athletes.

[1032] A "training plan" is a plan created using a generative AI model that shows an athlete's optimal exercise schedule and training content.

[1033] A "meal plan" is a plan created using a generative AI model that takes into account an athlete's daily diet and nutritional balance.

[1034] "Real-time monitoring" refers to the state in which sensor data is continuously monitored and abnormalities or specific conditions can be detected immediately.

[1035] A "warning message" is a notification message that is generated when an abnormality is detected during the monitoring process, and includes content that alerts the user.

[1036] "User Device" means a device used by an Athlete or Personnel to receive and display information. Examples include smartphones and tablets.

[1037] "Feedback data" refers to information such as dietary habits and physical condition that users enter on a daily basis, and is used to improve the accuracy of the generative AI model.

[1038] "Preprocessed sensor data" refers to sensor data that has undergone preprocessing such as removing outliers and interpolating data, and has been converted into a standard format.

[1039] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific implementation of this system is described below.

[1040] Configuration and Usage

[1041] Device application and data collection

[1042] Users (athletes) wear IoT devices such as smart bands, heart rate monitors, and GPS tracking devices. These devices measure data such as heart rate, exercise volume, calorie consumption, location, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi.

[1043] Data Preprocessing

[1044] The server receives raw data sent from each IoT device and performs preprocessing such as detecting and removing outliers, filling in incomplete data, and converting data types, so that the data is formatted into a standard format. This preprocessed data is stored in a database for subsequent processing.

[1045] Data analysis and AI model updates

[1046] The server extracts features from the preprocessed data stored in the database. Examples include average and maximum heart rate values ​​and cumulative exercise volume. Based on these features, the generative AI model is updated. This model update uses machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). The updated generative AI model is then used to predict the athlete's training effects and health status.

[1047] Generate training and meal plans

[1048] The server uses a generative AI model to generate optimal training and meal plans for each individual athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[1049] Real-time monitoring and alerts

[1050] The server monitors the sensor data in real time. If an abnormality is detected, such as if the heart rate exceeds a certain threshold, a warning message is generated and sent to the user's device. The message might say something like, "Your heart rate is too high, so you need to rest."

[1051] Collecting and synthesizing feedback

[1052] Users input feedback data (e.g., what they ate today and their physical condition) using devices such as smartphones or tablets. This feedback is sent to the server and integrated with preprocessed sensor data. This integrated data is used to update the generative AI model and generate plans for the next time, so it is reflected dynamically in real time.

[1053] Specific examples

[1054] A concrete example would be an athlete wanting a new weekend training plan.

[1055] 1. The user (athlete) sends a request for a new plan from their device.

[1056] 2. The server analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[1057] 3. The server generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[1058] 4. The server sends the generated training plan to the user's device.

[1059] 5. The training plan will be displayed on the device and the athlete will train according to the plan.

[1060] Prompt Sentence Examples

[1061] "Write a program that generates an optimal training plan based on an athlete's heart rate and exercise data from the past week."

[1062] By performing detailed and specific operations at each processing step, this invention makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[1063] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1064] Step 1: Data collection and transmission

[1065] The device (the athlete wearing the IoT device) measures data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi. Specifically, the smart band measures heart rate every five seconds and transfers this data to a smartphone app. The app then sends the data to the server, so the input becomes real-time measured sensor data, and the output becomes the data sent to the server.

[1066] Step 2: Preprocessing the data

[1067] The server receives raw data sent from each IoT device. Because this data may contain outliers, preprocessing is performed, including detecting and removing outliers, completing incomplete data, and converting data types. Specifically, upper and lower limits are set for the data to detect outliers, and data outside these limits is removed. Missing data is completed with the average value, so the input is the raw data sent to the server, and the output is preprocessed data. This preprocessed data is stored in a database.

[1068] Step 3: Data analysis and feature extraction

[1069] The server extracts features from the preprocessed data. These include, for example, the average and maximum heart rate, and the cumulative amount of exercise. Specifically, it plots the time variation of heart rate on a graph, detects peaks, and evaluates the intensity of training. The input is the preprocessed data, and the output is the extracted features.

[1070] Step 4: Update the generative AI model

[1071] The server updates the generative AI model based on the extracted features. Machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) are used. Specifically, the server inputs the time change in heart rate and the cumulative value of exercise volume into the AI ​​model, and then retrains the model. The input is the extracted features, and the output is the updated generative AI model.

[1072] Step 5: Create a training and meal plan

[1073] The server uses an updated generative AI model to generate optimal training and meal plans for each individual athlete. It determines the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data. Specific operations include setting running distance and rest days when generating a training plan, and taking calories and nutritional balance into account when creating a meal plan. The input is an updated generative AI model and real-time data, and the output is the generated training plan and meal plan.

[1074] Step 6: Real-time monitoring and alerting

[1075] The server monitors sensor data in real time. If an abnormality is detected based on the sensor data, such as when the heart rate exceeds a certain threshold, a warning message is generated. Specifically, if the heart rate exceeds 180, a message such as "Rest is required" is generated and the athlete is notified. The input is the real-time sensor data, and the output is the generated warning message.

[1076] Step 7: User feedback

[1077] The server sends the generated training plan, meal plan, and warning messages to the user's device. The device receives this information and displays it on the screen. Specifically, the training plan is displayed on the calendar on the smartphone app, and reminders are sent to the athlete using the notification function. The input is the generated training plan, meal plan, and warning messages, and the output is this information displayed on the device.

[1078] Step 8: Receiving and consolidating feedback data

[1079] Users use devices such as smartphones or tablets to input feedback data (e.g., what they ate today and their physical condition information). The server receives this data and integrates it with preprocessed sensor data. Specifically, the athlete enters the details of what they ate today into the app, and this data is analyzed by the server and reflected in the next meal plan. The input is the feedback data sent from the user's device, and the output is the integrated data. The integrated data is then used for the next update of the generative AI model.

[1080] (Application example 1)

[1081] 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."

[1082] When operating factory robots, it is important to monitor their performance and health in real time and generate optimal maintenance plans. However, current systems make it difficult to efficiently collect and analyze this data and take appropriate measures. Factory robots, in particular, have a wide variety of sensor data, so data integration and accurate analysis are required. Furthermore, when an abnormality is detected, it is essential to generate warning messages for rapid response and to notify the optimal maintenance plan. Technology to solve this problem is needed.

[1083] 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.

[1084] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for collecting sensor data from a factory robot and monitoring temperature, vibration, current, etc., means for monitoring the performance and health status of the factory robot in real time and generating a warning message when an anomaly is detected, means for generating an optimal maintenance plan for the factory robot using the generative AI model, means for notifying appropriate maintenance actions based on the sensor data of the factory robot, and means for displaying the information transmitted to the user terminal. This enables real-time monitoring of the performance and health status of factory robots, enabling the generation of appropriate maintenance plans and rapid response to abnormalities.

[1085] An "IoT device" is a physical device that can collect, send, or receive data over the Internet.

[1086] "Sensor data" refers to data measured and collected by various sensors, and includes information such as temperature, vibration, and current.

[1087] "Preprocessing" is the process of performing operations on raw data, such as removing outliers, filling in incomplete data, and converting data types, to prepare the data in a form suitable for analysis.

[1088] A "generative AI model" is a model built using machine learning algorithms to generate patterns and predictions from data.

[1089] A "Training Plan" is a plan that shows the optimal training schedule and content for an athlete and equipment.

[1090] A "meal plan" is a plan that shows the meal content and schedule optimized to maintain an athlete's health and improve their performance.

[1091] An "abnormality" is a state in which a value or pattern outside the normal range is detected from collected sensor data.

[1092] A "warning message" is a notification message that is generated when an anomaly is detected, informing the user of the existence of a problem and the necessary action to be taken.

[1093] A "user terminal" is a device used by a user, such as a smartphone or tablet, that displays information from the system.

[1094] "Robot performance" is an indicator of how efficiently and accurately a robot can perform a given task.

[1095] "Health status" refers to the normal operating condition of each part of the robot and the entire system.

[1096] A "maintenance plan" is a specific work plan for inspections, repairs, part replacements, etc. required to maintain the proper operation of a robot.

[1097] The present invention provides a system for monitoring the performance and health status of factory robots in real time and generating an optimal maintenance plan. Specific embodiments of the system are described below.

[1098] Data collection and transmission

[1099] Device:

[1100] Factory robots are equipped with various sensors, such as temperature sensors, vibration sensors, and current sensors. These sensors measure the status of each part of the robot and the overall system, and collect data in real time. The collected sensor data is sent to a server via communication protocols such as Bluetooth and WiFi.

[1101] Data Preprocessing

[1102] server:

[1103] The server receives the sensor data sent from each sensor and performs preprocessing, which includes removing outliers, filling in incomplete data, converting data types, etc. The preprocessed data is then converted into a standard format and stored in a database.

[1104] Data analysis and AI model updates

[1105] server:

[1106] Features are extracted from the preprocessed data and used to update the generative AI model. For example, features such as temperature changes over time or cumulative vibration values ​​can be used. The updated generative AI model is then used to detect anomalies in factory robots, predict performance, and generate maintenance plans. Machine learning algorithms (e.g., deep learning and random forests) are used to create the generative AI model.

[1107] Generate a maintenance plan

[1108] server:

[1109] Using a generative AI model, the system generates an optimal maintenance plan based on the condition of factory robots. For example, it suggests the timing of part replacement and adjustment items based on the degree of deterioration of each part of the robot and the frequency of abnormality detection.

[1110] Monitoring and generating warning messages

[1111] server:

[1112] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the vibration sensor exceeds a certain threshold, it generates a message saying, "Vibration is too high, immediate inspection required."

[1113] User Feedback

[1114] Servers and devices:

[1115] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action in real time.

[1116] Receiving feedback data and updating the model

[1117] Users and servers:

[1118] The results of the maintenance work and feedback data (e.g., work content and robot status information) are sent from the user device to the server, where they are combined with preprocessed sensor data and used for the next model update and plan generation.

[1119] Hardware and software used

[1120] Hardware:

[1121] IoT devices: temperature sensors, vibration sensors, current sensors

[1122] Server: Data preprocessing and AI model operation

[1123] software:

[1124] Python (data collection, preprocessing, modeling)

[1125] Libraries: NumPy, Pandas, scikit-learn, Keras

[1126] Communication protocol: Bluetooth, WiFi

[1127] Specific examples

[1128] For example, if a factory robot detects a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, the server will immediately detect the abnormality and generate a warning message stating, "Vibration is too high and requires immediate inspection," and send it to the user terminal.

[1129] Prompt Sentence Examples

[1130] "If the sensors attached to a factory robot detect a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, detect the abnormality and immediately generate a maintenance plan."

[1131] In this way, the system enables real-time monitoring of the performance and health of factory robots, enabling the creation of optimal maintenance plans and rapid response to abnormalities.

[1132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1133] Step 1:

[1134] Data collection and transmission

[1135] Device:

[1136] Various sensor data is collected in real time from temperature sensors, vibration sensors, current sensors, etc. attached to factory robots, and the collected data is sent to a server via communication protocols such as Bluetooth and WiFi.

[1137] Input: Measurement data of each sensor (e.g. temperature, vibration, current)

[1138] Output: Sensor data sent to the server

[1139] Step 2:

[1140] Data Preprocessing

[1141] server:

[1142] The server preprocesses the raw data received from each sensor, removing outliers, completing incomplete data, converting data types, and formatting it into a standard format. The preprocessed data is then stored in a database.

[1143] Input: Raw data (measurement data sent from each sensor)

[1144] Output: Preprocessed data (outlier removal, data imputation, and data formatting)

[1145] Step 3:

[1146] Feature extraction and AI model updating

[1147] server:

[1148] Extract features (e.g., temperature change over time, cumulative vibration value) from preprocessed data. Update the generative AI model using the extracted features. Machine learning algorithms used here include deep learning and random forests.

[1149] Input: Preprocessed data

[1150] Output: Updated generative AI model

[1151] Step 4:

[1152] Generate a maintenance plan

[1153] server:

[1154] Based on the updated generative AI model, the server generates an optimal maintenance plan (e.g., part replacement timing and adjustment items) according to the state of the factory robot. The generated maintenance plan is sent to the user's device.

[1155] Input: Updated generative AI model, real-time data from each sensor

[1156] Output: Optimal maintenance plan

[1157] Step 5:

[1158] Real-time monitoring and warning message generation

[1159] server:

[1160] The server monitors sensor data in real time and immediately generates a warning message if an abnormality is detected. For example, if a vibration sensor exceeds a threshold, a warning message stating "Vibration is too high, immediate inspection is required" is generated and sent to the user's device.

[1161] Input: Real-time sensor data

[1162] Output: Warning message

[1163] Step 6:

[1164] User Feedback

[1165] Servers and devices:

[1166] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action immediately.

[1167] Inputs: Maintenance plan, warning message

[1168] Output: Information displayed on the terminal screen

[1169] Step 7:

[1170] Receiving feedback data and updating the model

[1171] Users and servers:

[1172] The user inputs the results of maintenance work and feedback (e.g., work content, robot status information) from the terminal. This data is sent to the server and integrated with preprocessed sensor data. The integrated data is used for the next model update and plan generation.

[1173] Input: Feedback data from users

[1174] Output: Integrated data (preprocessed sensor data + feedback data)

[1175] In this way, the system enables real-time performance and health monitoring of factory robot operations, the generation of optimal maintenance plans, and rapid response to abnormalities.

[1176] 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.

[1177] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Furthermore, the system also incorporates an emotion engine to recognize the user's emotions, enabling the provision of even more personalized plans. Specific embodiments are described below.

[1178] Data collection and transmission

[1179] Device:

[1180] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure their heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect the measured sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[1181] Data Preprocessing

[1182] server:

[1183] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is then stored in a database for subsequent processing.

[1184] Data analysis and AI model updates

[1185] server:

[1186] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. It then updates the generative AI model based on the extracted features. The generative AI model is then used to predict the athlete's training effect and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, the server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and integrates the results with the preprocessed sensor data and feedback data.

[1187] Generate training and meal plans

[1188] server:

[1189] The server uses the updated AI model to generate optimal training and meal plans for each athlete. For example, the next week's training schedule and daily meal menu are determined based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[1190] Monitoring and generating warning messages

[1191] server:

[1192] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[1193] User Feedback

[1194] Servers and devices:

[1195] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[1196] Receiving feedback data and updating the model

[1197] Users and servers:

[1198] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[1199] As a concrete example, consider an athlete who wants a new weekend training plan.

[1200] 1. User: The athlete sends a request for a new plan from their device.

[1201] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, food records, and emotional data.

[1202] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[1203] 4. Server: Sends the generated training plan to the user's device.

[1204] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[1205] By performing specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance and provides optimal training and meal plans. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take the user's emotional state into consideration, realizing a more personalized service.

[1206] The processing flow will be explained below.

[1207] Step 1:

[1208] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[1209] Step 2:

[1210] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[1211] Step 3:

[1212] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[1213] Step 4:

[1214] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[1215] Step 5:

[1216] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[1217] Step 6:

[1218] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[1219] Step 7:

[1220] Server: Analyzes emotional data from the user's voice and facial expressions using an emotion engine. The emotion engine uses voice recognition and image recognition technologies.

[1221] Step 8:

[1222] Server: Integrates the emotion data recognized by the emotion engine with preprocessed sensor data and feature data.

[1223] Step 9:

[1224] Server: Uses the updated AI model to generate the optimal training plan for the athlete. For example, it determines the next week's training schedule based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[1225] Step 10:

[1226] Server: Similarly, it uses AI models to generate optimal meal plans, for example, proposing meal menus that take into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[1227] Step 11:

[1228] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality and generates a message saying, "Your heart rate is too high, so you need to rest."

[1229] Step 12:

[1230] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[1231] Step 13:

[1232] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[1233] Step 14:

[1234] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[1235] Step 15:

[1236] Terminal: User feedback data is sent to the server.

[1237] Step 16:

[1238] Server: Receives feedback data and integrates it with pre-processed sensor data.

[1239] Step 17:

[1240] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[1241] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and meal plans for each individual athlete. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take into account the user's emotional state, achieving a more personalized service.

[1242] Example 2

[1243] 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."

[1244] Conventional athlete training and health management systems lack real-time monitoring, making it difficult to provide optimal training and diet plans tailored to each individual athlete's condition. They also lack the ability to generate personalized plans that take into account the user's emotional state. This has resulted in problems with the inability to efficiently and effectively improve performance and manage health.

[1245] 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.

[1246] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for acquiring user emotion data using an emotion analysis engine and integrating it with the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time and detecting anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, meal plan, and warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for personalizing training plans and meal plans based on the user emotion data, thereby enabling real-time monitoring and providing personalized training plans and meal plans that take the user's emotional state into account.

[1247] An "IoT device" is an electronic device that is connected to the Internet and collects data about the user's activities and environment.

[1248] "Sensor data" refers to measurement data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns collected by IoT devices.

[1249] "Preprocessing" is the process of formatting collected sensor data, removing outliers, filling in missing values, and converting data types.

[1250] A "generative AI model" is a model that uses machine learning algorithms to predict an athlete's training effects and health status, and generate optimal training and meal plans.

[1251] An "emotion analysis engine" is an engine that analyzes emotional data from a user's voice and facial expressions and integrates the results with other data.

[1252] A "training plan" is an exercise schedule created to improve an athlete's performance and maintain their health.

[1253] A "meal plan" is a meal menu created with the purpose of improving an athlete's health and training effectiveness.

[1254] "Real-time monitoring" is the process of constantly monitoring sensor data and acquiring and analyzing the data in real time.

[1255] A "warning message" is a notification message that is generated when an abnormality is detected during real-time monitoring.

[1256] "User devices" are electronic devices such as smartphones and tablets used by athletes.

[1257] "Feedback data" refers to data such as dietary details and physical condition information that is input by the user via the terminal.

[1258] This invention is a system that utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time, and provides optimal training and meal plans. Furthermore, by combining it with an emotion analysis engine, it is possible to provide personalized plans that take the user's emotional state into account.

[1259] Hardware and software used

[1260] 1. IoT devices: Use electronic devices such as heart rate monitors, smart bands, and GPS tracking devices. These devices are worn by athletes and collect real-time sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[1261] 2. Server: Used for preprocessing, data analysis, updating AI models, generating warning messages, and generating training and meal plans. Equipped with machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) and a sentiment analysis engine.

[1262] 3. User terminal: Uses electronic devices such as smartphones and tablets. These terminals display training plans, meal plans, and warning messages sent from the server, and receive feedback data from the user (e.g., dietary details and physical condition information).

[1263] Specific Embodiments

[1264] Data collection and transmission

[1265] Device: Athletes wear heart rate monitors or smart bands. These devices transmit collected sensor data to a server via Bluetooth or WiFi. For example, a smart band measures heart rate every second and uploads the data to a server in real time via a smartphone.

[1266] Data Preprocessing

[1267] Server: Receives sensor data and performs preprocessing on the data. For example, it removes outliers (such as 0 BPM), fills in missing data, and converts the sensor data into a standard format. This preprocessed data is stored in a database and used for subsequent analysis.

[1268] Data analysis and AI model updates

[1269] Server: Extracts features from preprocessed data and updates the generative AI model. Machine learning algorithms are used to predict training effects and health status, and an emotion analysis engine is used to analyze the user's emotional data. For example, a user can enter their emotional records into a smartphone app, and the model is updated based on that data.

[1270] Generate training and meal plans

[1271] Server: Using the updated AI model, it generates optimal training and meal plans for each athlete. For example, it generates a plan based on the athlete's current fitness level and past training history, such as "30 minutes of running on Mondays and 45 minutes of strength training on Wednesdays," and includes high-protein foods in the meal plan.

[1272] Monitoring and generating warning messages

[1273] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if an athlete's heart rate exceeds 180 BPM, a warning message saying "Your heart rate is too high, you need to rest" is generated and sent to the athlete's smartphone.

[1274] User Feedback

[1275] Server and device: The server sends the generated training plan, meal plan, and warning messages to the user's device. This information is displayed on the user's device screen. For example, a smartphone might display "Today's training is a 30-minute run," and the athlete will then execute that plan.

[1276] Receiving feedback data and updating the model

[1277] User and server: The user uses a smartphone app to input feedback data. For example, they input information about what they ate today and their physical condition, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time. For example, the data the user inputs for "Today's Meals" is sent to the server and reflected in the next meal plan.

[1278] Examples of prompt statements

[1279] 1. How can IoT devices be used to collect heart rate and exercise data in real time?

[1280] 2. How can I preprocess the received data to remove outliers?

[1281] 3. Explain how to extract features from data and update a machine learning model.

[1282] 4. How can you generate optimal training and meal plans based on an athlete's data?

[1283] 5. How can I monitor sensor data in real time and generate warning messages when anomalies are detected?

[1284] 6. Explain how to send generated plans and warning messages to the user's device.

[1285] 7. Explain how you can receive feedback data from users and update your model.

[1286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1287] Step 1:

[1288] Data collection and transmission

[1289] Device: Athletes wear heart rate monitors or smart bands. These devices collect real-time sensor data such as heart rate, activity, calorie expenditure, location, and sleep patterns. The collected data is sent via Bluetooth or WiFi to the user's smartphone, which periodically uploads this data to a server.

[1290] Input: Sensor data obtained from IoT devices (heart rate, exercise amount, etc.)

[1291] Output: Collected sensor data sent to the server

[1292] How it works: The smart band measures your heart rate every second and sends the data to your smartphone via Bluetooth, which then uploads the data to a server in real time via WiFi.

[1293] Step 2:

[1294] Data Preprocessing

[1295] Server: Receives sensor data and preprocesses it. Preprocessing involves detecting and removing outliers, completing incomplete data, and converting data types. The preprocessed data is stored in a database for further processing.

[1296] Input: Sensor data collected in step 1

[1297] Output: Preprocessed sensor data

[1298] Specific operation: The server screens the received data to detect outliers such as a heart rate of 0 BPM and missing data, and then removes or complements them. After removing the outliers, the data is converted into a standard format (e.g., JSON format) and stored in a database.

[1299] Step 3:

[1300] Data analysis and AI model updates

[1301] Server: Extracts features from the preprocessed data and updates the generative AI model using a machine learning algorithm. During this process, the server analyzes the user's heart rate fluctuation patterns and cumulative exercise volume. It also uses a sentiment analysis engine to obtain and integrate user sentiment data.

[1302] Input: Preprocessed sensor data, user emotion data

[1303] Output: Updated generative AI model

[1304] How it works: Every night, the server runs a machine learning algorithm (e.g., deep learning) and updates the model based on data from the past 24 hours. It also integrates emotional data entered by users into the smartphone app to improve the accuracy of the model.

[1305] Step 4:

[1306] Generate training and meal plans

[1307] Server: Using the updated generative AI model, the server generates optimal training and meal plans for each athlete, based on the user's current fitness level, past training history, real-time sensor data, and emotional data.

[1308] Input: Updated generative AI model, user fitness data, sensor data, and emotion data

[1309] Output: personalized training and meal plans

[1310] How it works: The server generates this week's training plan based on last week's data. For example, a schedule and meal plan such as "30 minutes of running on Monday, 45 minutes of strength training on Wednesday" are automatically generated.

[1311] Step 5:

[1312] Monitoring and generating warning messages

[1313] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it generates a message saying, "Your heart rate is too high, you need to rest."

[1314] Input: Real-time sensor data

[1315] Output: Warning message

[1316] Specific operation: When the heart rate of the smart band exceeds 180 BPM while running, the server will immediately generate an alert and notify the smartphone.

[1317] Step 6:

[1318] User Feedback

[1319] Server and device: The server sends the generated training plan, meal plan, and warning message to the user's device and displays them on the device, allowing athletes and coaches to take optimal actions in real time.

[1320] Input: Training plans, meal plans, and warning messages sent from the server

[1321] Output: Information displayed on the user's terminal

[1322] Specific operation: Once a week, the server sends a new plan to the smartphone app, and the athlete receives a notification on their device saying, "A new training plan has been updated."

[1323] Step 7:

[1324] Receiving feedback data and updating the model

[1325] User and Server: The user inputs feedback data from their device and sends it to the server, which then combines this feedback data with preprocessed sensor data and uses it for the next model update.

[1326] Input: User feedback data (meal details, health information, etc.)

[1327] Output: Preprocessed feedback data, updated generative AI model

[1328] Specific operation: The user inputs "Today's Meal" into the smartphone app, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time, dynamically updating them in real time.

[1329] (Application example 2)

[1330] 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."

[1331] In modern factories, it is important to accurately monitor the operating status, efficiency, and maintenance demand of automated equipment, especially robots, in real time and provide optimal operation schedules and maintenance plans. Conventional systems often manage these elements individually, making integrated and dynamic management difficult. While combining these elements with an emotion engine makes it possible to provide plans that take the user's emotional state into account, no system has yet applied this to factory automation equipment. Therefore, there is a need for a system that can provide an integrated system for efficient operation and maintenance management of factory automation equipment.

[1332] 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 the operating status, efficiency, and maintenance demand of the factory's automated equipment in real time, means for generating an optimal operation schedule and maintenance plan using a generative AI model, and means for collecting feedback on the robot's operation and reflecting it in the next plan. This enables efficient operation and maintenance of the factory's automated equipment.

[1333] "IoT devices" refers to a wide range of physical devices and sensors connected to the Internet that can collect data and communicate with other devices and systems.

[1334] "Sensor data" refers to various types of data measured and collected by IoT devices, including temperature, heart rate, exercise volume, and calorie consumption.

[1335] "Preprocessing" refers to the processing performed on collected raw data to make it easier to analyze, including removing outliers, filling in incomplete data, and converting data types.

[1336] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes specific predictions or generates results from new data.

[1337] "Training Plan" refers to a plan created based on a generative AI model to optimize an athlete's training content.

[1338] "Meal plan" refers to a meal plan created based on a generative AI model, taking into account the athlete's nutritional balance.

[1339] "Real-time" refers to events or data being processed almost immediately after they occur, with almost no delay.

[1340] A "warning message" refers to a message sent to the user to warn them when the system detects an abnormality.

[1341] "User terminal" refers to a device that a user directly operates to display and input information, and examples include smartphones and tablets.

[1342] "Factory automation equipment" refers to various automated devices and robots used within factories to streamline the manufacturing process.

[1343] "Operational status" refers to information that indicates the current operating status of equipment or robots.

[1344] "Efficiency" refers to an indicator that shows how productive and efficient a device or robot is.

[1345] "Maintenance demand" refers to the need for maintenance and upkeep required to keep equipment and robots operating properly.

[1346] "Operation schedule" refers to a plan of optimal operating times and work content for equipment and robots, created based on a generative AI model.

[1347] "Feedback" refers to opinions and information provided by users or systems regarding the operating status of equipment or robots.

[1348] The system of this invention integrates IoT devices, generative AI models, and emotion engines to realize efficient operation and maintenance of automated equipment and robots in factories. The overall system configuration is as follows:

[1349] Data collection and transmission

[1350] Terminals and IoT devices:

[1351] Factory automation equipment is equipped with various sensors, such as temperature sensors, operation rate monitors, vibration sensors, etc. These IoT devices collect sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[1352] Data Preprocessing

[1353] server:

[1354] The server receives sensor data sent from each IoT device. The received data is then formatted into a standard format by removing outliers, completing incomplete data, and converting data types. The preprocessed data is then stored in a database.

[1355] Data analysis and AI model updates

[1356] server:

[1357] The server extracts features from the preprocessed data and updates the generative AI model. The generative AI model is then used to predict the operating efficiency and maintenance demand of automated equipment using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, an emotion engine is used to integrate feedback data and sensor data, enabling more accurate predictions.

[1358] Generate maintenance plans and operation schedules

[1359] server:

[1360] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data.

[1361] Monitoring and generating warning messages

[1362] server:

[1363] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and an inspection is required immediately."

[1364] User Feedback

[1365] Servers and devices:

[1366] The server generates operation schedules, maintenance plans, and warning messages, which are then sent to the user's terminal, where they are displayed to the factory manager, allowing him or her to take optimal action in real time.

[1367] Receiving feedback data and updating the model

[1368] Users and servers:

[1369] Users use their devices to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed sensor data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[1370] As a specific example, a case where the temperature of a gear of a device becomes abnormally high will be described.

[1371] 1. User: The administrator submits a request for a new maintenance plan from a terminal.

[1372] 2. Server: Analyzes real-time temperature sensor data, utilization and vibration data from the past week, and feedback data.

[1373] 3. Server: Generates an optimal maintenance plan (e.g., "Inspection is required immediately, prepare replacement parts") based on the generative AI model.

[1374] 4. Server: Sends the generated maintenance plan to the user's device.

[1375] 5. Terminal: The maintenance plan is displayed on the user's terminal, and the administrator works according to the plan.

[1376] Example prompt sentence:

[1377] "The temperature of the robot's gears is abnormally high. Should I take the specified action?" "Generate an optimal maintenance plan based on recent activity data."

[1378] This system dynamically and comprehensively manages the operational efficiency and maintenance of automated factory equipment, providing optimal operation schedules and maintenance plans. By combining it with an emotion engine, it is possible to take user feedback data into account to generate even more accurate predictions and plans.

[1379] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1380] Step 1:

[1381] Data collection and transmission

[1382] The server collects real-time sensor data from various sensors (e.g., temperature sensors, utilization rate monitors, vibration sensors) attached to automated equipment in the factory. This data is sent to the server via communication protocols such as Bluetooth or WiFi. The input is the raw data from the sensors, and the output is the data sent to the server.

[1383] Step 2:

[1384] Data Preprocessing

[1385] The server preprocesses the received sensor data. During this process, outliers are removed, incomplete data is filled, and data types are converted to form a standard format. The input is sensor data, and the output is preprocessed data. Specific operations include removing abnormally high temperature data and filling in missing data points with the average value.

[1386] Step 3:

[1387] Feature extraction and AI model updating

[1388] The server extracts features from the preprocessed data and updates the generative AI model based on these. These features include, for example, the rate of change of temperature and the cumulative value of operating time. The input is the preprocessed data, and the output is the updated generative AI model. Specifically, the numerical values ​​of each sensor data are input into a machine learning algorithm to train the model.

[1389] Step 4:

[1390] Data integration using emotion engines

[1391] The server uses an emotion engine to integrate feedback data and sensor data. The emotion engine analyzes user feedback (e.g., that a device is not working properly) and integrates it with sensor data. The inputs are feedback data and sensor data, and the output is the integrated data. Specifically, it performs text analysis on the feedback data and raises the alert level if it contains specific keywords.

[1392] Step 5:

[1393] Generate maintenance plans and operation schedules

[1394] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data. The input is the integrated data, and the output is the operation schedule and maintenance plan.

[1395] Step 6:

[1396] Monitoring and generating warning messages

[1397] The server monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and inspection is required immediately." The input is real-time sensor data, and the output is a warning message.

[1398] Step 7:

[1399] Sending and displaying information to user terminals

[1400] The operation schedules, maintenance plans, and warning messages generated by the server are sent to the user's terminal. The terminal displays this information on its screen, allowing the factory manager to take optimal action in real time. The input is the generated information, and the output is the display on the user's terminal.

[1401] Step 8:

[1402] Collecting feedback data and updating the model

[1403] Users use their terminals to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time. The input is feedback data, and the output is integrated data.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] [Fourth embodiment]

[1408] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1409] 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.

[1410] 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).

[1411] 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.

[1412] 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.

[1413] 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).

[1414] 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.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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."

[1421] The system of the present invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific embodiments are described below.

[1422] Data collection and transmission

[1423] Device:

[1424] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect sensor data in real time, and the collected data is sent to a server via communication protocols such as Bluetooth or WiFi.

[1425] Data Preprocessing

[1426] server:

[1427] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is stored in a database for subsequent processing.

[1428] Data analysis and AI model updates

[1429] server:

[1430] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. The extracted features are used to update the generative AI model. The generative AI model is then used to predict the athlete's training effects and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[1431] Generate training and meal plans

[1432] server:

[1433] The server uses the updated AI model to generate optimal training and meal plans for each athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[1434] Monitoring and generating warning messages

[1435] server:

[1436] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[1437] User Feedback

[1438] Servers and devices:

[1439] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[1440] Receiving feedback data and updating the model

[1441] Users and servers:

[1442] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, so it is reflected dynamically in real time.

[1443] As a concrete example, consider an athlete who wants a new weekend training plan.

[1444] 1. User: The athlete sends a request for a new plan from their device.

[1445] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[1446] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[1447] 4. Server: Sends the generated training plan to the user's device.

[1448] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[1449] By taking specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance, providing optimal training and diet plans.

[1450] The processing flow will be explained below.

[1451] Step 1:

[1452] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[1453] Step 2:

[1454] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[1455] Step 3:

[1456] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[1457] Step 4:

[1458] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[1459] Step 5:

[1460] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[1461] Step 6:

[1462] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[1463] Step 7:

[1464] Server: Uses the updated AI model to generate optimal training plans for athletes, for example, determining next week's training schedule based on the athlete's current fitness level and past training history.

[1465] Step 8:

[1466] Server: Similarly, AI models are used to generate optimal meal plans, for example, by taking into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[1467] Step 9:

[1468] Server: The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality.

[1469] Step 10:

[1470] Server: Generates a warning message when an abnormality is detected, for example, "Your heart rate is too high, you need to rest."

[1471] Step 11:

[1472] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[1473] Step 12:

[1474] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[1475] Step 13:

[1476] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[1477] Step 14:

[1478] Terminal: User feedback data is sent to the server.

[1479] Step 15:

[1480] Server: Receives feedback data and integrates it with pre-processed sensor data.

[1481] Step 16:

[1482] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[1483] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and dietary plans for each individual athlete.

[1484] Example 1

[1485] 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."

[1486] Using IoT devices to monitor athletes' performance and health and provide optimal training and meal plans based on that data is crucial for creating plans that meet the needs of individual athletes. However, there are few systems that consistently execute complex processes such as real-time data collection, preprocessing, updating AI models, generating plans, detecting anomalies, and integrating feedback data. This makes it difficult to efficiently manage athletes' training and nutrition.

[1487] 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.

[1488] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for extracting features from the preprocessed sensor data, means for updating a generative AI model based on the features, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for receiving meal content and physical condition information as user feedback data and generating or modifying a meal plan based on the data. This makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[1489] An "IoT device" is a physical device that can connect to the internet and collect, transmit, and share data. Examples include smart bands, heart rate monitors, and GPS tracking devices.

[1490] "Sensor data" refers to information such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns measured by IoT devices.

[1491] "Preprocessing" refers to the process of converting sensor data into a standard format by removing outliers, filling in incomplete data, converting data types, etc.

[1492] "Features" are computable attributes or properties extracted from preprocessed sensor data that can be used by machine learning algorithms. Examples include average and maximum heart rate, and cumulative exercise volume.

[1493] A "generative AI model" is a model created using machine learning algorithms to make predictions and classifications based on data. It is used to predict the training effects and health status of athletes.

[1494] A "training plan" is a plan created using a generative AI model that shows an athlete's optimal exercise schedule and training content.

[1495] A "meal plan" is a plan created using a generative AI model that takes into account an athlete's daily diet and nutritional balance.

[1496] "Real-time monitoring" refers to the state in which sensor data is continuously monitored and abnormalities or specific conditions can be detected immediately.

[1497] A "warning message" is a notification message that is generated when an abnormality is detected during the monitoring process, and includes content that alerts the user.

[1498] "User Device" means a device used by an Athlete or Personnel to receive and display information. Examples include smartphones and tablets.

[1499] "Feedback data" refers to information such as dietary habits and physical condition that users enter on a daily basis, and is used to improve the accuracy of the generative AI model.

[1500] "Preprocessed sensor data" refers to sensor data that has undergone preprocessing such as removing outliers and interpolating data, and has been converted into a standard format.

[1501] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Specific implementation of this system is described below.

[1502] Configuration and Usage

[1503] Device application and data collection

[1504] Users (athletes) wear IoT devices such as smart bands, heart rate monitors, and GPS tracking devices. These devices measure data such as heart rate, exercise volume, calorie consumption, location, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi.

[1505] Data Preprocessing

[1506] The server receives raw data sent from each IoT device and performs preprocessing such as detecting and removing outliers, filling in incomplete data, and converting data types, so that the data is formatted into a standard format. This preprocessed data is stored in a database for subsequent processing.

[1507] Data analysis and AI model updates

[1508] The server extracts features from the preprocessed data stored in the database. Examples include average and maximum heart rate values ​​and cumulative exercise volume. Based on these features, the generative AI model is updated. This model update uses machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). The updated generative AI model is then used to predict the athlete's training effects and health status.

[1509] Generate training and meal plans

[1510] The server uses a generative AI model to generate optimal training and meal plans for each individual athlete, such as determining the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data.

[1511] Real-time monitoring and alerts

[1512] The server monitors the sensor data in real time. If an abnormality is detected, such as if the heart rate exceeds a certain threshold, a warning message is generated and sent to the user's device. The message might say something like, "Your heart rate is too high, so you need to rest."

[1513] Collecting and synthesizing feedback

[1514] Users input feedback data (e.g., what they ate today and their physical condition) using devices such as smartphones or tablets. This feedback is sent to the server and integrated with preprocessed sensor data. This integrated data is used to update the generative AI model and generate plans for the next time, so it is reflected dynamically in real time.

[1515] Specific examples

[1516] A concrete example would be an athlete wanting a new weekend training plan.

[1517] 1. The user (athlete) sends a request for a new plan from their device.

[1518] 2. The server analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, and food records.

[1519] 3. The server generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[1520] 4. The server sends the generated training plan to the user's device.

[1521] 5. The training plan will be displayed on the device and the athlete will train according to the plan.

[1522] Prompt Sentence Examples

[1523] "Write a program that generates an optimal training plan based on an athlete's heart rate and exercise data from the past week."

[1524] By performing detailed and specific operations at each processing step, this invention makes it possible to efficiently manage athletes' health and performance and provide optimal training and meal plans in real time.

[1525] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1526] Step 1: Data collection and transmission

[1527] The device (the athlete wearing the IoT device) measures data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns. This measurement data is sent to a server via Bluetooth or WiFi. Specifically, the smart band measures heart rate every five seconds and transfers this data to a smartphone app. The app then sends the data to the server, so the input becomes real-time measured sensor data, and the output becomes the data sent to the server.

[1528] Step 2: Preprocessing the data

[1529] The server receives raw data sent from each IoT device. Because this data may contain outliers, preprocessing is performed, including detecting and removing outliers, completing incomplete data, and converting data types. Specifically, upper and lower limits are set for the data to detect outliers, and data outside these limits is removed. Missing data is completed with the average value, so the input is the raw data sent to the server, and the output is preprocessed data. This preprocessed data is stored in a database.

[1530] Step 3: Data analysis and feature extraction

[1531] The server extracts features from the preprocessed data. These include, for example, the average and maximum heart rate, and the cumulative amount of exercise. Specifically, it plots the time variation of heart rate on a graph, detects peaks, and evaluates the intensity of training. The input is the preprocessed data, and the output is the extracted features.

[1532] Step 4: Update the generative AI model

[1533] The server updates the generative AI model based on the extracted features. Machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) are used. Specifically, the server inputs the time change in heart rate and the cumulative value of exercise volume into the AI ​​model, and then retrains the model. The input is the extracted features, and the output is the updated generative AI model.

[1534] Step 5: Create a training and meal plan

[1535] The server uses an updated generative AI model to generate optimal training and meal plans for each individual athlete. It determines the next week's training schedule and daily meal menu based on the athlete's current fitness level, past training history, and real-time sensor data. Specific operations include setting running distance and rest days when generating a training plan, and taking calories and nutritional balance into account when creating a meal plan. The input is an updated generative AI model and real-time data, and the output is the generated training plan and meal plan.

[1536] Step 6: Real-time monitoring and alerting

[1537] The server monitors sensor data in real time. If an abnormality is detected based on the sensor data, such as when the heart rate exceeds a certain threshold, a warning message is generated. Specifically, if the heart rate exceeds 180, a message such as "Rest is required" is generated and the athlete is notified. The input is the real-time sensor data, and the output is the generated warning message.

[1538] Step 7: User feedback

[1539] The server sends the generated training plan, meal plan, and warning messages to the user's device. The device receives this information and displays it on the screen. Specifically, the training plan is displayed on the calendar on the smartphone app, and reminders are sent to the athlete using the notification function. The input is the generated training plan, meal plan, and warning messages, and the output is this information displayed on the device.

[1540] Step 8: Receiving and consolidating feedback data

[1541] Users use devices such as smartphones or tablets to input feedback data (e.g., what they ate today and their physical condition information). The server receives this data and integrates it with preprocessed sensor data. Specifically, the athlete enters the details of what they ate today into the app, and this data is analyzed by the server and reflected in the next meal plan. The input is the feedback data sent from the user's device, and the output is the integrated data. The integrated data is then used for the next update of the generative AI model.

[1542] (Application example 1)

[1543] 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."

[1544] When operating factory robots, it is important to monitor their performance and health in real time and generate optimal maintenance plans. However, current systems make it difficult to efficiently collect and analyze this data and take appropriate measures. Factory robots, in particular, have a wide variety of sensor data, so data integration and accurate analysis are required. Furthermore, when an abnormality is detected, it is essential to generate warning messages for rapid response and to notify the optimal maintenance plan. Technology to solve this problem is needed.

[1545] 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.

[1546] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time to detect anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, the meal plan, and the warning message to a user terminal, means for collecting sensor data from a factory robot and monitoring temperature, vibration, current, etc., means for monitoring the performance and health status of the factory robot in real time and generating a warning message when an anomaly is detected, means for generating an optimal maintenance plan for the factory robot using the generative AI model, means for notifying appropriate maintenance actions based on the sensor data of the factory robot, and means for displaying the information transmitted to the user terminal. This enables real-time monitoring of the performance and health status of factory robots, enabling the generation of appropriate maintenance plans and rapid response to abnormalities.

[1547] An "IoT device" is a physical device that can collect, send, or receive data over the Internet.

[1548] "Sensor data" refers to data measured and collected by various sensors, and includes information such as temperature, vibration, and current.

[1549] "Preprocessing" is the process of performing operations on raw data, such as removing outliers, filling in incomplete data, and converting data types, to prepare the data in a form suitable for analysis.

[1550] A "generative AI model" is a model built using machine learning algorithms to generate patterns and predictions from data.

[1551] A "Training Plan" is a plan that shows the optimal training schedule and content for an athlete and equipment.

[1552] A "meal plan" is a plan that shows the meal content and schedule optimized to maintain an athlete's health and improve their performance.

[1553] An "abnormality" is a state in which a value or pattern outside the normal range is detected from collected sensor data.

[1554] A "warning message" is a notification message that is generated when an anomaly is detected, informing the user of the existence of a problem and the necessary action to be taken.

[1555] A "user terminal" is a device used by a user, such as a smartphone or tablet, that displays information from the system.

[1556] "Robot performance" is an indicator of how efficiently and accurately a robot can perform a given task.

[1557] "Health status" refers to the normal operating condition of each part of the robot and the entire system.

[1558] A "maintenance plan" is a specific work plan for inspections, repairs, part replacements, etc. required to maintain the proper operation of a robot.

[1559] The present invention provides a system for monitoring the performance and health status of factory robots in real time and generating an optimal maintenance plan. Specific embodiments of the system are described below.

[1560] Data collection and transmission

[1561] Device:

[1562] Factory robots are equipped with various sensors, such as temperature sensors, vibration sensors, and current sensors. These sensors measure the status of each part of the robot and the overall system, and collect data in real time. The collected sensor data is sent to a server via communication protocols such as Bluetooth and WiFi.

[1563] Data Preprocessing

[1564] server:

[1565] The server receives the sensor data sent from each sensor and performs preprocessing, which includes removing outliers, filling in incomplete data, converting data types, etc. The preprocessed data is then converted into a standard format and stored in a database.

[1566] Data analysis and AI model updates

[1567] server:

[1568] Features are extracted from the preprocessed data and used to update the generative AI model. For example, features such as temperature changes over time or cumulative vibration values ​​can be used. The updated generative AI model is then used to detect anomalies in factory robots, predict performance, and generate maintenance plans. Machine learning algorithms (e.g., deep learning and random forests) are used to create the generative AI model.

[1569] Generate a maintenance plan

[1570] server:

[1571] Using a generative AI model, the system generates an optimal maintenance plan based on the condition of factory robots. For example, it suggests the timing of part replacement and adjustment items based on the degree of deterioration of each part of the robot and the frequency of abnormality detection.

[1572] Monitoring and generating warning messages

[1573] server:

[1574] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the vibration sensor exceeds a certain threshold, it generates a message saying, "Vibration is too high, immediate inspection required."

[1575] User Feedback

[1576] Servers and devices:

[1577] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action in real time.

[1578] Receiving feedback data and updating the model

[1579] Users and servers:

[1580] The results of the maintenance work and feedback data (e.g., work content and robot status information) are sent from the user device to the server, where they are combined with preprocessed sensor data and used for the next model update and plan generation.

[1581] Hardware and software used

[1582] Hardware:

[1583] IoT devices: temperature sensors, vibration sensors, current sensors

[1584] Server: Data preprocessing and AI model operation

[1585] software:

[1586] Python (data collection, preprocessing, modeling)

[1587] Libraries: NumPy, Pandas, scikit-learn, Keras

[1588] Communication protocol: Bluetooth, WiFi

[1589] Specific examples

[1590] For example, if a factory robot detects a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, the server will immediately detect the abnormality and generate a warning message stating, "Vibration is too high and requires immediate inspection," and send it to the user terminal.

[1591] Prompt Sentence Examples

[1592] "If the sensors attached to a factory robot detect a temperature of 80 degrees, vibration of 0.6, and current of 6 amps, detect the abnormality and immediately generate a maintenance plan."

[1593] In this way, the system enables real-time monitoring of the performance and health of factory robots, enabling the creation of optimal maintenance plans and rapid response to abnormalities.

[1594] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1595] Step 1:

[1596] Data collection and transmission

[1597] Device:

[1598] Various sensor data is collected in real time from temperature sensors, vibration sensors, current sensors, etc. attached to factory robots, and the collected data is sent to a server via communication protocols such as Bluetooth and WiFi.

[1599] Input: Measurement data of each sensor (e.g. temperature, vibration, current)

[1600] Output: Sensor data sent to the server

[1601] Step 2:

[1602] Data Preprocessing

[1603] server:

[1604] The server preprocesses the raw data received from each sensor, removing outliers, completing incomplete data, converting data types, and formatting it into a standard format. The preprocessed data is then stored in a database.

[1605] Input: Raw data (measurement data sent from each sensor)

[1606] Output: Preprocessed data (outlier removal, data imputation, and data formatting)

[1607] Step 3:

[1608] Feature extraction and AI model updating

[1609] server:

[1610] Extract features (e.g., temperature change over time, cumulative vibration value) from preprocessed data. Update the generative AI model using the extracted features. Machine learning algorithms used here include deep learning and random forests.

[1611] Input: Preprocessed data

[1612] Output: Updated generative AI model

[1613] Step 4:

[1614] Generate a maintenance plan

[1615] server:

[1616] Based on the updated generative AI model, the server generates an optimal maintenance plan (e.g., part replacement timing and adjustment items) according to the state of the factory robot. The generated maintenance plan is sent to the user's device.

[1617] Input: Updated generative AI model, real-time data from each sensor

[1618] Output: Optimal maintenance plan

[1619] Step 5:

[1620] Real-time monitoring and warning message generation

[1621] server:

[1622] The server monitors sensor data in real time and immediately generates a warning message if an abnormality is detected. For example, if a vibration sensor exceeds a threshold, a warning message stating "Vibration is too high, immediate inspection is required" is generated and sent to the user's device.

[1623] Input: Real-time sensor data

[1624] Output: Warning message

[1625] Step 6:

[1626] User Feedback

[1627] Servers and devices:

[1628] The maintenance plan and warning messages generated by the server are sent to the user's terminal, where they are displayed on the screen, allowing the maintenance staff to take appropriate action immediately.

[1629] Inputs: Maintenance plan, warning message

[1630] Output: Information displayed on the terminal screen

[1631] Step 7:

[1632] Receiving feedback data and updating the model

[1633] Users and servers:

[1634] The user inputs the results of maintenance work and feedback (e.g., work content, robot status information) from the terminal. This data is sent to the server and integrated with preprocessed sensor data. The integrated data is used for the next model update and plan generation.

[1635] Input: Feedback data from users

[1636] Output: Integrated data (preprocessed sensor data + feedback data)

[1637] In this way, the system enables real-time performance and health monitoring of factory robot operations, the generation of optimal maintenance plans, and rapid response to abnormalities.

[1638] 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.

[1639] The system of this invention utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time and generate optimal training and meal plans. Furthermore, the system also incorporates an emotion engine to recognize the user's emotions, enabling the provision of even more personalized plans. Specific embodiments are described below.

[1640] Data collection and transmission

[1641] Device:

[1642] Athletes wear various IoT devices (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) to measure their heart rate, exercise volume, calorie consumption, location information, sleep patterns, etc. These devices collect the measured sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[1643] Data Preprocessing

[1644] server:

[1645] The server receives sensor data sent from each IoT device. The received data is preprocessed and converted into a standard format. This process includes removing outliers, filling in incomplete data, and converting data types. The preprocessed data is then stored in a database for subsequent processing.

[1646] Data analysis and AI model updates

[1647] server:

[1648] The server extracts features from the preprocessed data, such as changes in heart rate over time and cumulative exercise volume. It then updates the generative AI model based on the extracted features. The generative AI model is then used to predict the athlete's training effect and health status using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, the server uses an emotion engine to analyze the user's emotions from their voice and facial expressions, and integrates the results with the preprocessed sensor data and feedback data.

[1649] Generate training and meal plans

[1650] server:

[1651] The server uses the updated AI model to generate optimal training and meal plans for each athlete. For example, the next week's training schedule and daily meal menu are determined based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[1652] Monitoring and generating warning messages

[1653] server:

[1654] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it will consider this an abnormality and generate a message saying, "Your heart rate is too high, so you need to rest."

[1655] User Feedback

[1656] Servers and devices:

[1657] The training plans, meal plans, and warning messages generated by the server are sent to the user's device (such as a smartphone or tablet), where this information is displayed on the screen, allowing athletes and coaches to take optimal action in real time.

[1658] Receiving feedback data and updating the model

[1659] Users and servers:

[1660] The user uses a device to input feedback data, such as what they ate that day and their physical condition. This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[1661] As a concrete example, consider an athlete who wants a new weekend training plan.

[1662] 1. User: The athlete sends a request for a new plan from their device.

[1663] 2. Server: Analyzes real-time heart rate data, exercise volume and calorie consumption over the past week, food records, and emotional data.

[1664] 3. Server: Generates an optimal training plan (e.g., "30 minutes of running on Mondays, 45 minutes of strength training on Wednesdays") based on the generative AI model.

[1665] 4. Server: Sends the generated training plan to the user's device.

[1666] 5. Device: The training plan is displayed on the user's device, and the athlete trains according to the plan.

[1667] By performing specific and detailed actions at each processing step, the system efficiently manages athletes' health and performance and provides optimal training and meal plans. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take the user's emotional state into consideration, realizing a more personalized service.

[1668] The processing flow will be explained below.

[1669] Step 1:

[1670] Devices: IoT devices worn by athletes (e.g., smart bands, heart rate monitors, GPS tracking devices, etc.) measure sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[1671] Step 2:

[1672] Terminal: Each IoT device transmits the measured sensor data to the server in real time. This transmission is done using communication protocols such as Bluetooth or WiFi.

[1673] Step 3:

[1674] Server: The server receives the sensor data sent from each IoT device. The server receives the data through API.

[1675] Step 4:

[1676] Server: Preprocesses the received data and converts it into a standard format, removing outliers, imputing incomplete data, converting data types, etc.

[1677] Step 5:

[1678] Server: Extracts features from preprocessed data. For example, calculates changes in heart rate over time and cumulative exercise volume.

[1679] Step 6:

[1680] Server: Updates the generative AI model based on the extracted features. The generative AI model is used to predict the training effect and health status of athletes using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.).

[1681] Step 7:

[1682] Server: Analyzes emotional data from the user's voice and facial expressions using an emotion engine. The emotion engine uses voice recognition and image recognition technologies.

[1683] Step 8:

[1684] Server: Integrates the emotion data recognized by the emotion engine with preprocessed sensor data and feature data.

[1685] Step 9:

[1686] Server: Uses the updated AI model to generate the optimal training plan for the athlete. For example, it determines the next week's training schedule based on the athlete's current fitness level, past training history, real-time sensor data, and emotional data.

[1687] Step 10:

[1688] Server: Similarly, it uses AI models to generate optimal meal plans, for example, proposing meal menus that take into account an athlete's daily calorie expenditure, weight, and nutritional balance.

[1689] Step 11:

[1690] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it is considered an abnormality and generates a message saying, "Your heart rate is too high, so you need to rest."

[1691] Step 12:

[1692] Server: Sends generated training plans, meal plans, and warning messages to the user's device.

[1693] Step 13:

[1694] Device: The user device (e.g., smartphone, tablet) displays the information received from the server on its screen, allowing athletes and coaches to take optimal action in real time.

[1695] Step 14:

[1696] User: The user uses their own device to input feedback data (e.g., what they ate today and their physical condition).

[1697] Step 15:

[1698] Terminal: User feedback data is sent to the server.

[1699] Step 16:

[1700] Server: Receives feedback data and integrates it with pre-processed sensor data.

[1701] Step 17:

[1702] Server: Further updates the generative AI model based on the integrated data and uses it to generate the next training plan or meal plan.

[1703] Through these steps, the system efficiently manages athletes' health and performance, providing optimal training and meal plans for each individual athlete. Furthermore, by combining it with an emotion engine, it is possible to provide plans that take into account the user's emotional state, achieving a more personalized service.

[1704] Example 2

[1705] 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."

[1706] Conventional athlete training and health management systems lack real-time monitoring, making it difficult to provide optimal training and diet plans tailored to each individual athlete's condition. They also lack the ability to generate personalized plans that take into account the user's emotional state. This has resulted in problems with the inability to efficiently and effectively improve performance and manage health.

[1707] 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.

[1708] In this invention, the server includes means for collecting sensor data from IoT devices, means for preprocessing and generating formatted sensor data, means for updating a generative AI model based on the preprocessed sensor data, means for acquiring user emotion data using an emotion analysis engine and integrating it with the preprocessed sensor data, means for generating a training plan using the generative AI model, means for generating a meal plan using the generative AI model, means for monitoring the sensor data in real time and detecting anomalies, means for generating a warning message when an anomaly is detected, means for transmitting the training plan, meal plan, and warning message to a user terminal, means for displaying the information transmitted to the user terminal, means for receiving user feedback data from the user terminal and integrating it with the preprocessed sensor data, means for further updating the generative AI model based on the integrated data, and means for personalizing training plans and meal plans based on the user emotion data, thereby enabling real-time monitoring and providing personalized training plans and meal plans that take the user's emotional state into account.

[1709] An "IoT device" is an electronic device that is connected to the Internet and collects data about the user's activities and environment.

[1710] "Sensor data" refers to measurement data such as heart rate, exercise volume, calorie consumption, location information, and sleep patterns collected by IoT devices.

[1711] "Preprocessing" is the process of formatting collected sensor data, removing outliers, filling in missing values, and converting data types.

[1712] A "generative AI model" is a model that uses machine learning algorithms to predict an athlete's training effects and health status, and generate optimal training and meal plans.

[1713] An "emotion analysis engine" is an engine that analyzes emotional data from a user's voice and facial expressions and integrates the results with other data.

[1714] A "training plan" is an exercise schedule created to improve an athlete's performance and maintain their health.

[1715] A "meal plan" is a meal menu created with the purpose of improving an athlete's health and training effectiveness.

[1716] "Real-time monitoring" is the process of constantly monitoring sensor data and acquiring and analyzing the data in real time.

[1717] A "warning message" is a notification message that is generated when an abnormality is detected during real-time monitoring.

[1718] "User devices" are electronic devices such as smartphones and tablets used by athletes.

[1719] "Feedback data" refers to data such as dietary details and physical condition information that is input by the user via the terminal.

[1720] This invention is a system that utilizes IoT devices and generative AI models to monitor athletes' performance and health in real time, and provides optimal training and meal plans. Furthermore, by combining it with an emotion analysis engine, it is possible to provide personalized plans that take the user's emotional state into account.

[1721] Hardware and software used

[1722] 1. IoT devices: Use electronic devices such as heart rate monitors, smart bands, and GPS tracking devices. These devices are worn by athletes and collect real-time sensor data such as heart rate, activity, calorie burn, location, and sleep patterns.

[1723] 2. Server: Used for preprocessing, data analysis, updating AI models, generating warning messages, and generating training and meal plans. Equipped with machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.) and a sentiment analysis engine.

[1724] 3. User terminal: Uses electronic devices such as smartphones and tablets. These terminals display training plans, meal plans, and warning messages sent from the server, and receive feedback data from the user (e.g., dietary details and physical condition information).

[1725] Specific Embodiments

[1726] Data collection and transmission

[1727] Device: Athletes wear heart rate monitors or smart bands. These devices transmit collected sensor data to a server via Bluetooth or WiFi. For example, a smart band measures heart rate every second and uploads the data to a server in real time via a smartphone.

[1728] Data Preprocessing

[1729] Server: Receives sensor data and performs preprocessing on the data. For example, it removes outliers (such as 0 BPM), fills in missing data, and converts the sensor data into a standard format. This preprocessed data is stored in a database and used for subsequent analysis.

[1730] Data analysis and AI model updates

[1731] Server: Extracts features from preprocessed data and updates the generative AI model. Machine learning algorithms are used to predict training effects and health status, and an emotion analysis engine is used to analyze the user's emotional data. For example, a user can enter their emotional records into a smartphone app, and the model is updated based on that data.

[1732] Generate training and meal plans

[1733] Server: Using the updated AI model, it generates optimal training and meal plans for each athlete. For example, it generates a plan based on the athlete's current fitness level and past training history, such as "30 minutes of running on Mondays and 45 minutes of strength training on Wednesdays," and includes high-protein foods in the meal plan.

[1734] Monitoring and generating warning messages

[1735] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if an athlete's heart rate exceeds 180 BPM, a warning message saying "Your heart rate is too high, you need to rest" is generated and sent to the athlete's smartphone.

[1736] User Feedback

[1737] Server and device: The server sends the generated training plan, meal plan, and warning messages to the user's device. This information is displayed on the user's device screen. For example, a smartphone might display "Today's training is a 30-minute run," and the athlete will then execute that plan.

[1738] Receiving feedback data and updating the model

[1739] User and server: The user uses a smartphone app to input feedback data. For example, they input information about what they ate today and their physical condition, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time. For example, the data the user inputs for "Today's Meals" is sent to the server and reflected in the next meal plan.

[1740] Examples of prompt statements

[1741] 1. How can IoT devices be used to collect heart rate and exercise data in real time?

[1742] 2. How can I preprocess the received data to remove outliers?

[1743] 3. Explain how to extract features from data and update a machine learning model.

[1744] 4. How can you generate optimal training and meal plans based on an athlete's data?

[1745] 5. How can I monitor sensor data in real time and generate warning messages when anomalies are detected?

[1746] 6. Explain how to send generated plans and warning messages to the user's device.

[1747] 7. Explain how you can receive feedback data from users and update your model.

[1748] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1749] Step 1:

[1750] Data collection and transmission

[1751] Device: Athletes wear heart rate monitors or smart bands. These devices collect real-time sensor data such as heart rate, activity, calorie expenditure, location, and sleep patterns. The collected data is sent via Bluetooth or WiFi to the user's smartphone, which periodically uploads this data to a server.

[1752] Input: Sensor data obtained from IoT devices (heart rate, exercise amount, etc.)

[1753] Output: Collected sensor data sent to the server

[1754] How it works: The smart band measures your heart rate every second and sends the data to your smartphone via Bluetooth, which then uploads the data to a server in real time via WiFi.

[1755] Step 2:

[1756] Data Preprocessing

[1757] Server: Receives sensor data and preprocesses it. Preprocessing involves detecting and removing outliers, completing incomplete data, and converting data types. The preprocessed data is stored in a database for further processing.

[1758] Input: Sensor data collected in step 1

[1759] Output: Preprocessed sensor data

[1760] Specific operation: The server screens the received data to detect outliers such as a heart rate of 0 BPM and missing data, and then removes or complements them. After removing the outliers, the data is converted into a standard format (e.g., JSON format) and stored in a database.

[1761] Step 3:

[1762] Data analysis and AI model updates

[1763] Server: Extracts features from the preprocessed data and updates the generative AI model using a machine learning algorithm. During this process, the server analyzes the user's heart rate fluctuation patterns and cumulative exercise volume. It also uses a sentiment analysis engine to obtain and integrate user sentiment data.

[1764] Input: Preprocessed sensor data, user emotion data

[1765] Output: Updated generative AI model

[1766] How it works: Every night, the server runs a machine learning algorithm (e.g., deep learning) and updates the model based on data from the past 24 hours. It also integrates emotional data entered by users into the smartphone app to improve the accuracy of the model.

[1767] Step 4:

[1768] Generate training and meal plans

[1769] Server: Using the updated generative AI model, the server generates optimal training and meal plans for each athlete, based on the user's current fitness level, past training history, real-time sensor data, and emotional data.

[1770] Input: Updated generative AI model, user fitness data, sensor data, and emotion data

[1771] Output: personalized training and meal plans

[1772] How it works: The server generates this week's training plan based on last week's data. For example, a schedule and meal plan such as "30 minutes of running on Monday, 45 minutes of strength training on Wednesday" are automatically generated.

[1773] Step 5:

[1774] Monitoring and generating warning messages

[1775] Server: Monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the heart rate exceeds a certain threshold, it generates a message saying, "Your heart rate is too high, you need to rest."

[1776] Input: Real-time sensor data

[1777] Output: Warning message

[1778] Specific operation: When the heart rate of the smart band exceeds 180 BPM while running, the server will immediately generate an alert and notify the smartphone.

[1779] Step 6:

[1780] User Feedback

[1781] Server and device: The server sends the generated training plan, meal plan, and warning message to the user's device and displays them on the device, allowing athletes and coaches to take optimal actions in real time.

[1782] Input: Training plans, meal plans, and warning messages sent from the server

[1783] Output: Information displayed on the user's terminal

[1784] Specific operation: Once a week, the server sends a new plan to the smartphone app, and the athlete receives a notification on their device saying, "A new training plan has been updated."

[1785] Step 7:

[1786] Receiving feedback data and updating the model

[1787] User and Server: The user inputs feedback data from their device and sends it to the server, which then combines this feedback data with preprocessed sensor data and uses it for the next model update.

[1788] Input: User feedback data (meal details, health information, etc.)

[1789] Output: Preprocessed feedback data, updated generative AI model

[1790] Specific operation: The user inputs "Today's Meal" into the smartphone app, and the data is sent to the server. The server uses this data to update the model and generate plans for the next time, dynamically updating them in real time.

[1791] (Application example 2)

[1792] 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."

[1793] In modern factories, it is important to accurately monitor the operating status, efficiency, and maintenance demand of automated equipment, especially robots, in real time and provide optimal operation schedules and maintenance plans. Conventional systems often manage these elements individually, making integrated and dynamic management difficult. While combining these elements with an emotion engine makes it possible to provide plans that take the user's emotional state into account, no system has yet applied this to factory automation equipment. Therefore, there is a need for a system that can provide an integrated system for efficient operation and maintenance management of factory automation equipment.

[1794] 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 the operating status, efficiency, and maintenance demand of the factory's automated equipment in real time, means for generating an optimal operation schedule and maintenance plan using a generative AI model, and means for collecting feedback on the robot's operation and reflecting it in the next plan. This enables efficient operation and maintenance of the factory's automated equipment.

[1795] "IoT devices" refers to a wide range of physical devices and sensors connected to the Internet that can collect data and communicate with other devices and systems.

[1796] "Sensor data" refers to various types of data measured and collected by IoT devices, including temperature, heart rate, exercise volume, and calorie consumption.

[1797] "Preprocessing" refers to the processing performed on collected raw data to make it easier to analyze, including removing outliers, filling in incomplete data, and converting data types.

[1798] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and makes specific predictions or generates results from new data.

[1799] "Training Plan" refers to a plan created based on a generative AI model to optimize an athlete's training content.

[1800] "Meal plan" refers to a meal plan created based on a generative AI model, taking into account the athlete's nutritional balance.

[1801] "Real-time" refers to events or data being processed almost immediately after they occur, with almost no delay.

[1802] A "warning message" refers to a message sent to the user to warn them when the system detects an abnormality.

[1803] "User terminal" refers to a device that a user directly operates to display and input information, and examples include smartphones and tablets.

[1804] "Factory automation equipment" refers to various automated devices and robots used within factories to streamline the manufacturing process.

[1805] "Operational status" refers to information that indicates the current operating status of equipment or robots.

[1806] "Efficiency" refers to an indicator that shows how productive and efficient a device or robot is.

[1807] "Maintenance demand" refers to the need for maintenance and upkeep required to keep equipment and robots operating properly.

[1808] "Operation schedule" refers to a plan of optimal operating times and work content for equipment and robots, created based on a generative AI model.

[1809] "Feedback" refers to opinions and information provided by users or systems regarding the operating status of equipment or robots.

[1810] The system of this invention integrates IoT devices, generative AI models, and emotion engines to realize efficient operation and maintenance of automated equipment and robots in factories. The overall system configuration is as follows:

[1811] Data collection and transmission

[1812] Terminals and IoT devices:

[1813] Factory automation equipment is equipped with various sensors, such as temperature sensors, operation rate monitors, vibration sensors, etc. These IoT devices collect sensor data in real time and send it to a server via communication protocols such as Bluetooth or WiFi.

[1814] Data Preprocessing

[1815] server:

[1816] The server receives sensor data sent from each IoT device. The received data is then formatted into a standard format by removing outliers, completing incomplete data, and converting data types. The preprocessed data is then stored in a database.

[1817] Data analysis and AI model updates

[1818] server:

[1819] The server extracts features from the preprocessed data and updates the generative AI model. The generative AI model is then used to predict the operating efficiency and maintenance demand of automated equipment using machine learning algorithms (e.g., deep learning, decision trees, random forests, etc.). Furthermore, an emotion engine is used to integrate feedback data and sensor data, enabling more accurate predictions.

[1820] Generate maintenance plans and operation schedules

[1821] server:

[1822] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data.

[1823] Monitoring and generating warning messages

[1824] server:

[1825] The server monitors the sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and an inspection is required immediately."

[1826] User Feedback

[1827] Servers and devices:

[1828] The server generates operation schedules, maintenance plans, and warning messages, which are then sent to the user's terminal, where they are displayed to the factory manager, allowing him or her to take optimal action in real time.

[1829] Receiving feedback data and updating the model

[1830] Users and servers:

[1831] Users use their devices to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed sensor data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time.

[1832] As a specific example, a case where the temperature of a gear of a device becomes abnormally high will be described.

[1833] 1. User: The administrator submits a request for a new maintenance plan from a terminal.

[1834] 2. Server: Analyzes real-time temperature sensor data, utilization and vibration data from the past week, and feedback data.

[1835] 3. Server: Generates an optimal maintenance plan (e.g., "Inspection is required immediately, prepare replacement parts") based on the generative AI model.

[1836] 4. Server: Sends the generated maintenance plan to the user's device.

[1837] 5. Terminal: The maintenance plan is displayed on the user's terminal, and the administrator works according to the plan.

[1838] Example prompt sentence:

[1839] "The temperature of the robot's gears is abnormally high. Should I take the specified action?" "Generate an optimal maintenance plan based on recent activity data."

[1840] This system dynamically and comprehensively manages the operational efficiency and maintenance of automated factory equipment, providing optimal operation schedules and maintenance plans. By combining it with an emotion engine, it is possible to take user feedback data into account to generate even more accurate predictions and plans.

[1841] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1842] Step 1:

[1843] Data collection and transmission

[1844] The server collects real-time sensor data from various sensors (e.g., temperature sensors, utilization rate monitors, vibration sensors) attached to automated equipment in the factory. This data is sent to the server via communication protocols such as Bluetooth or WiFi. The input is the raw data from the sensors, and the output is the data sent to the server.

[1845] Step 2:

[1846] Data Preprocessing

[1847] The server preprocesses the received sensor data. During this process, outliers are removed, incomplete data is filled, and data types are converted to form a standard format. The input is sensor data, and the output is preprocessed data. Specific operations include removing abnormally high temperature data and filling in missing data points with the average value.

[1848] Step 3:

[1849] Feature extraction and AI model updating

[1850] The server extracts features from the preprocessed data and updates the generative AI model based on these. These features include, for example, the rate of change of temperature and the cumulative value of operating time. The input is the preprocessed data, and the output is the updated generative AI model. Specifically, the numerical values ​​of each sensor data are input into a machine learning algorithm to train the model.

[1851] Step 4:

[1852] Data integration using emotion engines

[1853] The server uses an emotion engine to integrate feedback data and sensor data. The emotion engine analyzes user feedback (e.g., that a device is not working properly) and integrates it with sensor data. The inputs are feedback data and sensor data, and the output is the integrated data. Specifically, it performs text analysis on the feedback data and raises the alert level if it contains specific keywords.

[1854] Step 5:

[1855] Generate maintenance plans and operation schedules

[1856] The server uses the updated AI model to generate optimal operation schedules and maintenance plans for each piece of automated equipment. For example, the next maintenance schedule and daily operation plan are determined based on the equipment's current operating status, past operating history, real-time sensor data, and feedback data. The input is the integrated data, and the output is the operation schedule and maintenance plan.

[1857] Step 6:

[1858] Monitoring and generating warning messages

[1859] The server monitors sensor data in real time and generates a warning message if an abnormality is detected. For example, if the temperature of a gear exceeds a certain threshold, it generates a message saying, "The temperature is abnormally high and inspection is required immediately." The input is real-time sensor data, and the output is a warning message.

[1860] Step 7:

[1861] Sending and displaying information to user terminals

[1862] The operation schedules, maintenance plans, and warning messages generated by the server are sent to the user's terminal. The terminal displays this information on its screen, allowing the factory manager to take optimal action in real time. The input is the generated information, and the output is the display on the user's terminal.

[1863] Step 8:

[1864] Collecting feedback data and updating the model

[1865] Users use their terminals to input feedback data (e.g., recent maintenance work results, equipment status, etc.). This data is sent to the server and integrated with pre-processed data. The integrated data is used for the next model update and plan generation, and is reflected dynamically in real time. The input is feedback data, and the output is integrated data.

[1866] 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.

[1867] 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.

[1868] 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 robot 414.

[1869] 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.

[1870] 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.

[1871] 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.

[1872] 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).

[1873] 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. ...

Claims

1. a means for collecting sensor data from IoT devices; means for preprocessing and generating shaped sensor data; A means for updating the generative AI model based on preprocessed sensor data; and a means for generating a training plan using the generative AI model; a means for generating a meal plan using a generative AI model; A means for monitoring sensor data in real time and detecting anomalies; means for generating a warning message when an anomaly is detected; means for transmitting training plans, meal plans, and alert messages to a user device; means for displaying the transmitted information at a user terminal; A system including:

2. means for receiving user feedback data from a user terminal and integrating the data with the preprocessed sensor data; The system of claim 1 , further comprising: means for further updating the generative AI model based on the integrated data.

3. The system according to claim 1 , further comprising means for generating or modifying a meal plan based on the user's feedback data, if the feedback data includes dietary content and physical condition information.

Images