System

Abstract

A system is provided.SOLUTION: A system comprising means for receiving data collected from sensors installed in a farm, means for pre-processing the received sensor data into a format suitable for analysis, means for artificial intelligence to analyze abnormal behavior and temperature changes using the pre-processed data and score risk, means for generating and notifying alerts if the risk score exceeds a certain threshold, means for suggesting prevention and countermeasures based on the risk score, and means for collecting feedback data from users and updating the artificial intelligence's models.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] Early detection of avian influenza is difficult for poultry farmers, public institutions, and research institutes, and the spread of infection can result in significant damage. Furthermore, the timing of implementing preventive measures is often delayed, making appropriate risk management difficult. Furthermore, there is a need for a method to efficiently and comprehensively analyze data from multiple aquaculture farms to grasp and predict the overall infection situation. Current technology lacks systems to address these issues, so it is necessary to build a system that can provide appropriate early detection and propose preventive measures. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving data collected from sensors installed in aquaculture farms, a means for preprocessing the received sensor data and converting it into a format suitable for analysis, a means for using artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature using the preprocessed data to generate a risk score, a means for generating and notifying alerts when the risk score exceeds a certain threshold, a means for proposing prevention and countermeasures based on the risk score, and a means for collecting feedback data from users and updating the AI ​​model. The system also includes a means for analyzing the preprocessed data in real time to detect abnormal behavior, and a means for aggregating data collected from multiple aquaculture farms to analyze and predict the overall situation. This system enables early detection of avian influenza, rapid alert notification, proposing effective prevention measures, and understanding the overall infection situation, thereby solving the problem.

[0006] A "sensor" is a device that detects a physical condition and collects that information as data.

[0007] "Data preprocessing" is the process of converting data collected from sensors into a format suitable for analysis.

[0008] "Artificial intelligence" is a technology that enables computer systems to autonomously learn and perform specific tasks.

[0009] "Abnormal behavior" refers to a situation in which a chicken is behaving differently than normal.

[0010] "Temperature fluctuations" refers to a condition in which a chicken's body temperature rises or falls outside of its normal range.

[0011] The "risk score" is a numerical representation of the risk of developing avian influenza.

[0012] An "alert" is a warning message that is sent to the user when a certain condition is met.

[0013] "Prevention and control measures" are specific procedures and measures to prevent the onset of avian influenza.

[0014] "Feedback data" refers to data reporting the results and status of measures taken by users.

[0015] "Model updating" is the process of using collected feedback data to refine artificial intelligence algorithms and improve analytical accuracy.

[0016] "Real-time" refers to a situation where there is minimal delay between the time the data is collected and the time it is analyzed.

[0017] "Multiple farms" refers to multiple independent farming facilities.

[0018] "Data aggregation" refers to the centralization of data collected from multiple sensors.

[0019] "Situation analysis and prediction" refers to understanding the current situation and estimating future infection risks based on collected data. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time. This system involves a series of processes that collect data from sensors installed in aquaculture farms, analyze the data, calculate a risk score, and issue an alert. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[0042] Data Collection and Transmission

[0043] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[0044] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[0045] Data Preprocessing and Analysis

[0046] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[0047] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[0048] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[0049] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0050] Alert notifications and countermeasure suggestions

[0051] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0052] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0053] 5. Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[0054] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[0055] Feedback Collection and Machine Learning

[0056] 6. User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[0057] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[0058] 7. Server: The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[0059] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[0060] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Terminal: Various sensors (temperature sensors, humidity sensors, motion sensors) and cameras installed in the farm collect data.

[0064] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[0065] Step 2:

[0066] Terminal: Sends collected data to the server at regular intervals.

[0067] Specific operation: Temperature data, humidity data, and behavioral data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[0068] Step 3:

[0069] Server: Checks the received data and stores it in a database.

[0070] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, sends a receipt confirmation response to the terminal.

[0071] Step 4:

[0072] Server: Preprocesses the received data.

[0073] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[0074] Step 5:

[0075] Server: Analyzes the pre-processed data and calculates the risk score.

[0076] How it works: Using an AI algorithm, it analyzes abnormal behavior (e.g., a chicken not moving) and abnormal body temperature values, compares this with past learning data, and calculates a risk score, for example, 80.

[0077] Step 6:

[0078] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[0079] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0080] Step 7:

[0081] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[0082] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[0083] Step 8:

[0084] Users: Receive notifications and take action.

[0085] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[0086] Step 9:

[0087] User: Feedback the results and status of countermeasures to the server via the terminal.

[0088] Specific operation: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application.

[0089] Step 10:

[0090] Server: Stores the received feedback data in a database.

[0091] Specific operation: The feedback data is analyzed and added to the database. It is stored as new data and used to update the analytical model.

[0092] Step 11:

[0093] Server: Updates the artificial intelligence model based on the feedback data.

[0094] What happens: The AI ​​algorithm is retrained using the new data collected to improve analysis accuracy, and the new model is deployed and applied to the next data analysis.

[0095] This system will enable early detection of avian influenza and preventative measures in real time.

[0096] Example 1

[0097] 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."

[0098] Conventional early detection and prevention measures for avian influenza at aquaculture farms rely on manual observation and incomplete data collection, making it difficult to make quick and accurate judgments. Furthermore, when abnormalities are discovered, response measures are often limited and inconsistent. This results in delayed detection of abnormalities and a high risk of infection spreading. Furthermore, the inability to effectively utilize collected data also delays improvements in the accuracy of future preventive measures.

[0099] 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.

[0100] In this invention, the server includes: means for periodically receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score; means for generating an alert and notifying the user when the risk score exceeds a set threshold; means for issuing the alert and suggesting specific prevention and countermeasures; and means for collecting feedback data from users and updating the AI ​​model to improve the accuracy of the analysis. This enables early detection of avian influenza and effective preventive measures, enables rapid response when abnormalities are discovered, and enables improved accuracy of future preventive measures.

[0101] A "farm" is a specially established environment for raising useful organisms such as livestock and fish.

[0102] A "sensor" is a device that detects changes in physical or chemical quantities and outputs them as an electrical signal.

[0103] "Data" refers to a record of information detected by the sensor, and specifically includes information such as temperature, humidity, movement, and video.

[0104] "Receiving" is the act of acquiring data transmitted from a remote location.

[0105] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis. Specifically, this includes data normalization and filtering of outliers.

[0106] "Artificial intelligence" refers to technologies and systems that learn from large amounts of data to solve specific tasks or problems.

[0107] "Abnormal behavior" refers to a behavioral pattern that deviates from normal, such as a sudden decrease in physical activity.

[0108] "Temperature changes" are when a chicken's body temperature rises or falls outside of its normal range.

[0109] A "risk score" is a numerical representation of the risk of an abnormality occurring, calculated from sensor data.

[0110] The "threshold" is the boundary value at which the risk score is judged to be abnormal from a normal state.

[0111] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[0112] "Prevention and control" refers to measures taken before or immediately after an abnormality occurs, and specifically includes quarantining chickens and antiviral treatment.

[0113] "Feedback data" refers to data that reports the results and status of a user's implementation of a measure.

[0114] "Model updating" means using feedback data to retrain the artificial intelligence algorithm and improve the accuracy of the analysis.

[0115] This invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing alerts. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis.

[0116] First, we will explain the overall configuration of this system. The system consists of terminals installed in the farm, which consist of temperature sensors, humidity sensors, motion sensors, and cameras, and a server that processes and analyzes the received data. These devices communicate via the Internet to collect and analyze data.

[0117] Data collection

[0118] Terminal: Temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and sends the data to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second. The data is then sent to the server every minute.

[0119] Data Transfer

[0120] Terminal: Sends collected data to a server via a network. Data transfer can be real-time or periodically, allowing for rapid analysis. For example, data can be transferred to the server every minute via the farm's Wi-Fi network.

[0121] Data Preprocessing

[0122] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. It also removes noise from the obtained temperature data and divides and labels the behavioral data by frame.

[0123] Data analysis

[0124] Server: Using the preprocessed data, an AI algorithm analyzes abnormal behavior and changes in body temperature and generates a risk score. Abnormal behavior is judged by comparing it with past data and a risk score is calculated. As a specific example, the AI ​​model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0125] Alerting and Notification

[0126] Server: If the risk score exceeds a set threshold, an alert is generated and notified to the appropriate user. At this time, a message proposing specific prevention and countermeasures is also sent. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." In addition, a notification is sent suggesting countermeasures such as, "Isolate the chickens and begin antiviral treatment."

[0127] Gathering feedback and updating AI models

[0128] User: Implements countermeasures and reports the results and status to the server as feedback via the device. For example, an administrator may quarantine chickens and then report through the app that their body temperature has returned to normal.

[0129] Server: The AI ​​model is updated using the collected feedback data. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. For example, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[0130] Prompt Sentence Examples

[0131] Examples of prompts to be input to a generative AI model include:

[0132] This question concerns the design of a system for early detection of abnormalities in chickens on a farm. The system uses temperature, humidity, and motion sensors, and cameras to collect data, which is then analyzed on a server. Please explain the names of the specific hardware and software, the data preprocessing method, the anomaly detection algorithm, the alert notification method, and the feedback collection process.

[0133] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: Data collection

[0136] Terminal: Temperature, humidity, and motion sensors, as well as cameras, collect data on the chickens' body temperature, environment, and behavior. Each sensor periodically records data.

[0137] Specific operation: The temperature sensor measures the chicken's body temperature every 10 minutes, the humidity sensor measures the environmental humidity every 5 minutes, the movement sensor checks the chicken's movements every minute, and the camera records the chicken's behavior every second.

[0138] Input: Chicken body temperature, humidity, movement, behavioral video

[0139] Output: Collected data (body temperature data, humidity data, exercise data, video data)

[0140] Step 2: Data Transfer

[0141] Terminal: Sends collected data to the server in real time or periodically.

[0142] Specific operation: The collected data is transferred to the server every minute via the Wi-Fi network.

[0143] Input: Collected data (body temperature data, humidity data, exercise data, video data)

[0144] Output: Data sent to the server

[0145] Step 3: Data Preprocessing

[0146] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis.

[0147] Specific operation: The server performs noise removal and outlier filtering on the received data. The video data is also divided into frames, and each frame is assigned an action label.

[0148] Input: Data sent to the server (body temperature data, humidity data, exercise data, video data)

[0149] Output: Preprocessed data (normalized data, filtered data, labeled video data)

[0150] Step 4: Data analysis

[0151] Server: Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature and calculates a risk score.

[0152] Specific operation: The AI ​​model compares data with past data, detects abnormal behavior and changes in body temperature, and calculates a risk score. For example, if the temperature data is 38.2°C and the person is "immobile," the model calculates a risk score of 80.

[0153] Input: Preprocessed data (normalized data, filtered data, labeled video data)

[0154] Output: Risk score

[0155] Step 5: Alerting and Notification

[0156] Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0157] Specific operation: If the risk score exceeds 50, the server will send an alert message to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0158] Input: Risk Score

[0159] Output: Alert message

[0160] Step 6: Propose a solution

[0161] Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[0162] Specific action: Along with the alert notification, a message containing a countermeasure suggestion to "quarantine the chickens and start antiviral treatment" will be sent to the administrator.

[0163] Input: Risk score, Alert message

[0164] Output: Measure suggestion message

[0165] Step 7: Gather feedback

[0166] User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[0167] Specific operations: After implementing the measures, the administrator uses a smartphone app to enter and send information such as "The chickens were isolated and their body temperatures subsequently returned to normal."

[0168] Input: Countermeasure results, status information

[0169] Output: Feedback data

[0170] Step 8: Update the AI ​​model

[0171] Server: Updates the artificial intelligence model using collected feedback data.

[0172] Specific operation: The server retrains the AI ​​model based on the newly acquired feedback data, further improving the accuracy of analysis.

[0173] Input: Feedback data

[0174] Output: Updated AI model

[0175] (Application example 1)

[0176] 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."

[0177] Conventional methods for early detection and prevention of avian influenza at aquaculture farms rely on data collection and analysis using sensors, but these methods pose challenges in terms of real-time monitoring and prompt notification to managers. Furthermore, there is a lack of a mechanism for updating the AI ​​model based on feedback, resulting in insufficient analysis accuracy. Therefore, a system that enables early detection of abnormal behavior and prompt countermeasures is needed.

[0178] 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.

[0179] In this invention, the server includes means for receiving data collected from sensors installed in the farm, means for preprocessing the received sensor data and converting it into a format suitable for analysis, means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score, means for generating and notifying an alert when the risk score exceeds a certain threshold, means for proposing prevention and countermeasures based on the risk score, means for collecting feedback data from users and updating the AI ​​model, and means for the farm manager to monitor the status of the chickens in real time. This enables real-time status monitoring and prompt notification, as well as improved analysis accuracy based on feedback.

[0180] An "aquaculture farm" is a facility for raising and managing animals such as livestock and farmed fish.

[0181] A "sensor" is a device for measuring variables in the external environment and collecting that data.

[0182] The "data receiving means" is a function for acquiring data transmitted from a sensor.

[0183] "Preprocessing" is the process of converting received data into a form suitable for analysis.

[0184] "Artificial intelligence" is a program that allows a computer to analyze data and detect abnormal behavior or changes in body temperature.

[0185] The "risk score" is an indicator of danger calculated based on abnormal behavior and changes in body temperature.

[0186] The "alert generation means" is a function for issuing a warning when the risk score exceeds a certain threshold.

[0187] "Notification means" is the process by which an administrator is notified of an alert.

[0188] "Preventive measures" are methods for suggesting disease prevention based on risk scores.

[0189] The "measure proposal means" is a function that proposes appropriate measures for problems that may occur.

[0190] A "feedback collection means" is a method for collecting behavioral results from users.

[0191] "Model updating" is the process of improving an artificial intelligence model based on collected feedback data.

[0192] "Real-time monitoring means" is a function that allows farm managers to instantly grasp the status of chickens.

[0193] This invention describes a system for early detection of avian influenza and real-time implementation of preventive measures. This system includes a function to collect and analyze data from sensors installed in aquaculture farms, calculate a risk score, and notify managers of appropriate alerts. In addition, the accuracy of the analysis can be improved by collecting feedback data from users and updating the generative AI model.

[0194] System configuration

[0195] Data Collection and Transmission

[0196] Device:

[0197] Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data from the chickens. Each sensor periodically records the data and transmits it to a server at regular intervals.

[0198] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[0199] Data Preprocessing and Analysis

[0200] server:

[0201] Preprocessing of received sensor data and conversion to a format suitable for analysis, specifically normalizing the data and filtering outliers.

[0202] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[0203] Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature to generate a risk score. Abnormal behavior is judged by comparing it with past data and calculating a risk score.

[0204] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0205] Alert notifications and countermeasure suggestions

[0206] server:

[0207] If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0208] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0209] Send notifications with alerts and specific prevention and action suggestions.

[0210] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[0211] Feedback Collection and Machine Learning

[0212] User:

[0213] Countermeasures are implemented and the results and status are reported as feedback to the server via the device.

[0214] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[0215] server:

[0216] The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[0217] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[0218] Hardware and software used

[0219] Hardware: temperature sensor, humidity sensor, motion sensor, camera, smartphone

[0220] Software: denoising algorithms for data preprocessing, labeling algorithms, and AI models (e.g., models using the machine learning libraries TENSORFLOW® or PyTorch)

[0221] Prompt Sentence Examples

[0222] "Given the temperature readings and activity levels of the chickens, determine the risk score for bird flu infection. Consider higher temperatures and inactivity as higher risk."

[0223] This system allows farm managers to monitor for abnormal signs of avian influenza in real time and take prompt action, significantly reducing the risk of infection spreading.

[0224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0225] Step 1: Data collection

[0226] The terminal collects data from temperature, humidity, and motion sensors and cameras installed in the farm. The input is raw data obtained from the sensors, which typically includes temperature, humidity, movement, and video data. This data is collected at regular intervals and prepared for transmission. The output is a dataset of various environmental conditions and behavioral data.

[0227] Step 2: Send data

[0228] The terminal sends the collected data to the server at regular intervals. The input is the data collected in the previous step. The data is sent to the server via the network. The output is the data received by the server.

[0229] Step 3: Data Preprocessing

[0230] The server converts the received data into a format suitable for analysis. Specifically, it performs noise removal and outlier filtering. The input is the transmitted sensor data, and the output is preprocessed and normalized data. For example, temperature data is normalized, and behavioral data is split into frames and labeled.

[0231] Step 4: Anomaly detection and risk scoring

[0232] The server uses the preprocessed data to analyze abnormal behavior and changes in body temperature using a generative AI model. It calculates a risk score and compares it with past data to determine abnormal behavior. The input is the preprocessed data, and the output is the calculated risk score. Specifically, it detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0233] Step 5: Alerting and Notification

[0234] The server generates an alert when the risk score exceeds a set threshold and notifies the appropriate user. The input is the risk score and a preset threshold, and the output is a notification message. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the individual immediately and take quarantine measures."

[0235] Step 6: Propose a solution

[0236] The server will then provide alerts and suggest specific preventive and countermeasure measures. The input is the risk score and past countermeasure data, and the output is a message proposing countermeasures. For example, the server might suggest countermeasures such as "Isolate the chickens and start antiviral treatment."

[0237] Step 7: Gather feedback

[0238] The user implements the measures and reports the results and situation as feedback to the server via their device. The input is data on the measures actually taken and their results, and the output is sent to the server as feedback data. Specifically, the manager quarantines the chickens and then reports through the app that their body temperature has returned to normal.

[0239] Step 8: Update the model

[0240] The server updates the generative AI model using the collected feedback data. The input is the feedback data, and the output is the updated AI model. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. Specifically, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[0241] 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.

[0242] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time, and includes an emotion engine that recognizes user emotions. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing an alert. Furthermore, emotion data based on user feedback is collected and the artificial intelligence model is updated to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[0243] Data Collection and Transmission

[0244] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[0245] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[0246] Data Preprocessing and Analysis

[0247] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[0248] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[0249] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[0250] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0251] Alert notifications and countermeasure suggestions

[0252] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0253] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0254] 5. Server: Sends notifications along with alerts and suggests specific preventive and countermeasure measures.

[0255] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[0256] 6. Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[0257] Example: If the user's input and behavioral patterns are analyzed and it is determined that they are under high stress, an encouraging message such as "It is important to take immediate action. Please do not rush and follow the instructions" will be sent.

[0258] Feedback Collection and Machine Learning

[0259] 7. User: Receive notification and take action.

[0260] Example: Following the notification, promptly isolate the chickens and implement the specified antiviral measures. After implementing the measures, observe the results.

[0261] 8. User: Feedback the results and status of countermeasures to the server via the terminal.

[0262] Example: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application. The user's emotions are also recorded when giving feedback.

[0263] 9. Server: Stores the received feedback data in a database.

[0264] Example: Analyze user emotion data along with feedback data and add it to the database. Store it as new data and use it to update the analysis model.

[0265] 10. Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[0266] Example: Retraining artificial intelligence algorithms and sentiment engines with new data collected to improve analysis accuracy. Deploying new models to reflect the next data analysis.

[0267] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[0268] The processing flow will be explained below.

[0269] Step 1:

[0270] Terminals: Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data of the chickens.

[0271] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[0272] Step 2:

[0273] Terminal: Sends collected data to the server at regular intervals.

[0274] Specific operation: Temperature data, humidity data, and behavioral data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[0275] Step 3:

[0276] Server: Checks the received data and stores it in a database.

[0277] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, sends a receipt confirmation response to the terminal.

[0278] Step 4:

[0279] Server: Preprocesses the received data.

[0280] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[0281] Step 5:

[0282] Server: Analyzes the pre-processed data and calculates the risk score.

[0283] How it works: Using an AI algorithm, it analyzes abnormal behavior (e.g., a chicken not moving) and abnormal body temperature values, compares this with past learning data, and calculates a risk score, for example, 80.

[0284] Step 6:

[0285] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[0286] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0287] Step 7:

[0288] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[0289] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[0290] Step 8:

[0291] Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[0292] Specific actions: Analyze the user's input and behavioral patterns, and if it determines that the user is under high stress, send an encouraging message such as, "It is important to take immediate action. Don't rush, just follow the instructions."

[0293] Step 9:

[0294] Users: Receive notifications and take action.

[0295] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[0296] Step 10:

[0297] User: Feedback the results and status of countermeasures to the server via the terminal.

[0298] Specific operation: The user inputs and sends feedback data through the application, such as "Isolation work completed, body temperature has returned to the normal range of 39°C." The user's emotions are also recorded when providing feedback.

[0299] Step 11:

[0300] Server: Stores the received feedback data in a database.

[0301] Specific operation: The user's emotional data is analyzed along with the feedback data and added to the database. The data is stored as new data and used to update the analysis model.

[0302] Step 12:

[0303] Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[0304] What happens: Retrain the AI ​​algorithms and sentiment engine with the new data collected to improve analysis accuracy. Deploy the new model and apply it to the next data analysis.

[0305] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[0306] Example 2

[0307] 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."

[0308] When an infectious disease such as avian influenza breaks out at an aquaculture farm, early detection and rapid countermeasures are required. While existing systems can detect some anomalies, they only notify users uniformly and are unable to respond to the individual circumstances and emotions of each user. This can lead to stress for users and delays in taking appropriate countermeasures. Furthermore, the system lacks a mechanism for utilizing feedback data to improve the accuracy of analysis.

[0309] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for analyzing user emotions and customizing the notification content; and means for collecting feedback data and emotion data from users and updating the AI ​​model. This enables early detection and rapid countermeasures for avian influenza, realizes notifications that take user emotions into consideration, and improves analysis accuracy by utilizing feedback data.

[0310] A "sensor" is a device that detects a specific physical quantity of an object and outputs it as an electrical signal.

[0311] "Data receiving means" refers to the function of the equipment or software that acquires and incorporates data transmitted from the sensor.

[0312] "Data preprocessing means" refers to a function that performs processing to convert raw data into a format that is easy to analyze, and specifically includes data normalization and filtering of outliers.

[0313] "Artificial intelligence" is a technology that allows computer systems to learn, reason, and recognize by imitating human intelligence, and in this invention it is used to detect abnormal behavior and calculate risk scores.

[0314] The "abnormal behavior analysis means" is a function that uses preprocessed data to enable artificial intelligence to analyze abnormal behavior and changes in body temperature of chickens.

[0315] The "risk scoring means" is a function that quantifies the risk of abnormality based on the analysis results.

[0316] The "alert generation means" is a function that issues an alert and notifies the user when the risk score exceeds a set threshold.

[0317] The "prevention and countermeasure suggestion means" is a function that suggests specific countermeasures to the user against infectious diseases such as avian influenza based on the analysis results.

[0318] "Emotion analysis means" is a function that analyzes the user's emotions and generates and customizes appropriate notification content based on that information.

[0319] "Feedback collection means" is a function that acquires the results and status of measures implemented by users and incorporates them into the system.

[0320] "Model updating means" is a function that uses collected feedback data to improve and update the artificial intelligence model.

[0321] The present invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes for collecting and analyzing data from multiple sensors installed in aquaculture farms, calculating a risk score, and issuing alerts as necessary. Furthermore, the system is equipped with a function for improving the accuracy of the analysis based on user feedback and emotion data. A specific embodiment of this system is described below.

[0322] Data Collection and Transmission

[0323] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. These sensors record data periodically and send it to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second and sends the data to the server every minute.

[0324] Data Preprocessing

[0325] The server preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. For example, it removes noise from the acquired temperature data and divides and labels the behavioral data into frames.

[0326] Data analysis

[0327] The server uses pre-processed data and an artificial intelligence algorithm to analyze abnormal behavior and changes in body temperature and calculate a risk score. Abnormal behavior is determined by comparing it with past data. For example, if the AI ​​model detects a temperature of 38.2°C and abnormal behavior (immobility), it will calculate a risk score of 80.

[0328] Alert notifications and countermeasure suggestions

[0329] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It also sends a notification suggesting specific preventative measures along with the alert. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." At the same time, the system suggests measures such as "Isolate the chickens and begin antiviral treatment."

[0330] Sentiment analysis and notification customization

[0331] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. For example, if the server analyzes the user's input and behavioral patterns and determines that they are under high stress, it will send an encouraging message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[0332] Gathering feedback and updating machine learning models

[0333] The user receives the notification, takes action, and then sends feedback about the results and situation to the server via their device. For example, the user may quickly quarantine the chickens in accordance with the notification and implement the specified antiviral measures. As a result, feedback data such as "Isolation completed, body temperature has returned to the normal range of 39°C" is sent. The user's emotions are also recorded when providing feedback.

[0334] The server updates the AI ​​model and emotion engine based on the received feedback data and emotion data, for example, by retraining the AI ​​algorithm and emotion engine using the new data collected to improve the accuracy of the analysis, and then deploys the new model to be reflected in the next data analysis.

[0335] Prompt Sentence Examples

[0336] Here are some example prompts to input to a generative AI model:

[0337] "The system uses various sensors installed in the farm to monitor the health of chickens in real time, detects abnormalities early and calculates a risk score. It then sends appropriate alerts and measures. It also analyzes user sentiment and customizes the notification content. Feedback data is used to update the model and improve the accuracy of the analysis."

[0338] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0339] Step 1: Data collection

[0340] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. As input, it takes raw data from each sensor and records it at regular intervals. For example, the temperature sensor measures chicken body temperature every 10 minutes, and the camera records chicken behavior every second. As output, it buffers the collected data and prepares it to be sent to the server.

[0341] Step 2: Send data

[0342] The device sends the collected data to the server at a specified interval. As input, it uses the sensor data buffered on the device and uploads this data to the server as output. For example, the collected temperature data or video data can be sent to the server every minute.

[0343] Step 3: Data Preprocessing

[0344] The server preprocesses the received sensor data. It receives raw data sent from the device as input and generates preprocessed data suitable for analysis as output. This preprocessing includes data normalization, outlier filtering, and noise removal. For example, it removes noise from the obtained temperature data and segments and labels the behavioral data by frame.

[0345] Step 4: Data analysis

[0346] The server uses an artificial intelligence algorithm to analyze the preprocessed data. It uses the preprocessed data as input and analyzes abnormal behavior and changes in body temperature as output to calculate a risk score. For example, an AI model detects a temperature of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0347] Step 5: Alert Generation

[0348] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It uses the risk score as input and generates an alert message as output. For example, if the risk score exceeds 50, an alert message stating "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures" is sent to the administrator's smartphone.

[0349] Step 6: Propose a solution

[0350] The server sends a notification to the user along with the alert, suggesting specific prevention and countermeasures. It uses the risk score and analysis results as input and generates a message suggesting countermeasures as output. For example, it suggests countermeasures such as "Isolate the chickens and start antiviral treatment."

[0351] Step 7: Sentiment Analysis and Notification Customization

[0352] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. It uses the user's feedback and operation history as input and generates a customized notification message as output. For example, if it determines that the user is under high stress, it sends a message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[0353] Step 8: Gather feedback

[0354] The user implements the measures and sends the results and status as feedback to the server. The user inputs the results of their actions as input, and this data is sent to the server as output. For example, feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is sent.

[0355] Step 9: Update the model

[0356] The server uses the received feedback data and emotion data to update the artificial intelligence model and emotion engine. It uses the newly collected data as input and generates an updated model as output. For example, it uses the collected new data to retrain the AI ​​algorithm and emotion engine to improve the accuracy of analysis. It then deploys the new model and applies it to the next data analysis.

[0357] In this way, the system will enable early detection of avian influenza and rapid countermeasures, providing effective support to users.

[0358] (Application example 2)

[0359] 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."

[0360] Conventional systems have been unable to detect abnormalities early or implement sufficient preventative measures at aquaculture farms and manufacturing facilities, making it difficult to respond quickly when an abnormality occurs. Furthermore, conventional anomaly detection systems do not customize notification content based on feedback or user sentiment, and therefore do not provide sufficient support for implementing optimal measures.

[0361] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm or manufacturing facility; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature and equipment operating status using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for collecting feedback data from users and updating the AI ​​model; and means for the AI ​​to analyze the user's emotions and customize the content of the notification. This enables early detection of abnormalities and rapid response, and can propose optimal countermeasures based on the user's emotions.

[0362] An "aquaculture farm" is a facility for raising and managing living organisms such as poultry and fish.

[0363] A "manufacturing facility" is a location such as a factory or workshop where products are produced or assembled.

[0364] A "sensor" is a device that detects environmental data such as temperature, humidity, vibration, and images, as well as operational data, and outputs it as a signal.

[0365] The "means for receiving data" refers to a method or device for inputting data transmitted from a sensor into a server or computer.

[0366] "Means for preprocessing data and converting it into a format suitable for analysis" refers to a method or device that processes received data into an analyzable state by removing noise, normalizing, labeling, etc.

[0367] "Artificial intelligence" refers to algorithms and software that analyze received data and evaluate abnormal behavior, changes in body temperature, and the operating status of equipment.

[0368] A "means for scoring risk" is a method or device that expresses the degree of abnormality or risk as a number based on the results of analysis using artificial intelligence.

[0369] "Means for generating and notifying alerts" refers to a method or device for generating and notifying a user of a warning based on a risk score that exceeds a set threshold.

[0370] The "means for proposing prevention and countermeasures" is a method or device that presents specific prevention measures and countermeasures to the user based on the risk score.

[0371] "Means for collecting feedback data from users" refers to a method or device for incorporating response results and status reports from users into the system.

[0372] "Means for updating artificial intelligence models" refers to methods or devices that improve the accuracy of analytical algorithms or learn new models based on collected feedback data.

[0373] The "means for analyzing emotions and customizing notification content" refers to a method or device that determines emotions from user input and behavioral data and adjusts notification messages to match that emotional state.

[0374] The present invention provides a system for detecting abnormalities in manufacturing facilities and proposing countermeasures based on a system for early detection of avian influenza and implementing preventive measures in real time. This system is implemented in the following manner and configuration.

[0375] First, temperature, humidity, and vibration sensors, as well as cameras, are installed within the manufacturing facility to periodically measure environmental data and the operating status of the equipment and send the data to a server.

[0376] The server receives temperature, humidity, vibration, and image data and preprocesses them. This includes noise removal, data normalization, and frame-by-frame image labeling. The preprocessed data is then analyzed by an artificial intelligence algorithm to quantify abnormal behavior and equipment operating conditions as a risk score.

[0377] If the risk score exceeds a certain threshold, the server generates an alert and sends it to the administrator's smartphone or head-mounted display. The alert suggests specific preventive and countermeasure measures, such as, "The temperature of the refrigerator has exceeded the set range. Please immediately check the site and request repairs."

[0378] The server collects feedback data from users and updates the AI ​​model based on this data. This feedback includes the results of countermeasure implementation and status reports, and also analyzes the user's emotional data. By customizing the notification content according to the user's emotions, the system helps users implement countermeasures without feeling stressed.

[0379] For example, if it determines that a user is in a high stress state, it will send an encouraging message such as, "It is important to take action immediately. Please do not rush and follow the instructions." This function is realized by analyzing the user's input and behavioral patterns using an emotion engine.

[0380] A specific scenario is shown below.

[0381] If the temperature in a freezer warehouse at a manufacturing facility becomes abnormally high, a temperature sensor collects data and sends it to a server. The server removes noise from this data, and an AI model analyzes it. If the risk score exceeds a threshold, the server generates an alert and sends a message to the manager's smartphone saying, "The freezer temperature has exceeded the set range. Please check the site immediately and request repairs." The manager receives this notification and immediately takes action. Feedback is then sent to the server, stating, "Repair work completed, temperature has returned to normal range," along with the user's emotional data. The server updates the AI ​​model based on this data.

[0382] An example of a prompt to use for the generative AI model is as follows:

[0383] "Analyze the following data set and predict the anomaly risk score for this production line.

[0384] Datasets: Temperature data, humidity data, vibration data, image data

[0385] Time range: 30 minutes

[0386] Output: Anomaly risk score, specific explanation of the anomaly cause

[0387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0388] Step 1:

[0389] Sensors collect data such as temperature, humidity, vibration, and images.

[0390] Specifically, the temperature sensor acquires temperature data every 10 minutes, the humidity sensor acquires humidity data every 15 minutes, the vibration sensor acquires vibration data every 5 seconds, and the camera captures images every second. These data are periodically sent to the server.

[0391] Input: Environmental and image data from sensors.

[0392] Output: The raw data sent to the server.

[0393] Step 2:

[0394] The server receives the data sent from the sensor.

[0395] Specifically, the server periodically monitors data from each sensor and receives the data via HTTP requests.

[0396] Input: Raw data sent from the sensor.

[0397] Output: Raw data stored on the server.

[0398] Step 3:

[0399] The server preprocesses the data received.

[0400] Specifically, the process involves noise removal, normalization, and then dividing and labeling the image data by frame.

[0401] Input: Raw data stored in the server.

[0402] Output: Preprocessed data.

[0403] Step 4:

[0404] The server uses the pre-processed data to perform analysis using an AI model.

[0405] Specifically, an artificial intelligence algorithm analyzes pre-processed data, detects abnormal behavior, body temperature, and changes in equipment operating status, and scores the risk.

[0406] Input: Preprocessed data.

[0407] Output: Risk score and analysis results.

[0408] Step 5:

[0409] If the risk score exceeds a certain threshold, the server generates an alert and notifies you.

[0410] Specifically, the system monitors the risk score and, if it exceeds a threshold, sends an alert notification to the administrator's smartphone or head-mounted display.

[0411] Input: Risk score.

[0412] Output: Alert notification.

[0413] Step 6:

[0414] The server suggests prevention and countermeasures based on the risk score.

[0415] Specifically, the system refers to past response examples in a database, selects appropriate preventive measures and countermeasures, and includes them in the notification.

[0416] Inputs: Risk score and past case data.

[0417] Output: Notification of specific preventive measures and countermeasures.

[0418] Step 7:

[0419] The user receives the notification and sends the feedback data to the server.

[0420] Specifically, the user checks the notification via a smartphone or head-mounted display, enters the response results, and sends them.

[0421] Input: Countermeasure execution results and user feedback data.

[0422] Output: Feedback data sent to the server.

[0423] Step 8:

[0424] The server updates the artificial intelligence model based on the feedback data.

[0425] Specifically, the feedback data is analyzed, input into the AI ​​model as new data, and the model is retrained.

[0426] Input: Feedback data.

[0427] Output: The updated AI model.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Second embodiment]

[0432] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0443] 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."

[0444] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time. This system involves a series of processes that collect data from sensors installed in aquaculture farms, analyze the data, calculate a risk score, and issue an alert. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[0445] Data Collection and Transmission

[0446] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[0447] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[0448] Data Preprocessing and Analysis

[0449] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[0450] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[0451] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[0452] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0453] Alert notifications and countermeasure suggestions

[0454] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0455] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0456] 5. Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[0457] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[0458] Feedback Collection and Machine Learning

[0459] 6. User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[0460] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[0461] 7. Server: The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[0462] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[0463] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[0464] The processing flow will be explained below.

[0465] Step 1:

[0466] Terminal: Various sensors (temperature sensors, humidity sensors, motion sensors) and cameras installed in the farm collect data.

[0467] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[0468] Step 2:

[0469] Terminal: Sends collected data to the server at regular intervals.

[0470] Specific operation: Temperature data, humidity data, and behavioral data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[0471] Step 3:

[0472] Server: Checks the received data and stores it in a database.

[0473] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, sends a receipt confirmation response to the terminal.

[0474] Step 4:

[0475] Server: Preprocesses the received data.

[0476] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[0477] Step 5:

[0478] Server: Analyzes the pre-processed data and calculates the risk score.

[0479] How it works: Using an AI algorithm, it analyzes abnormal behavior (e.g., a chicken not moving) and abnormal body temperature values, compares this with past learning data, and calculates a risk score, for example, 80.

[0480] Step 6:

[0481] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[0482] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0483] Step 7:

[0484] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[0485] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[0486] Step 8:

[0487] Users: Receive notifications and take action.

[0488] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[0489] Step 9:

[0490] User: Feedback the results and status of countermeasures to the server via the terminal.

[0491] Specific operation: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application.

[0492] Step 10:

[0493] Server: Stores the received feedback data in a database.

[0494] Specific operation: The feedback data is analyzed and added to the database. It is stored as new data and used to update the analytical model.

[0495] Step 11:

[0496] Server: Updates the artificial intelligence model based on the feedback data.

[0497] What happens: The AI ​​algorithm is retrained using the new data collected to improve analysis accuracy, and the new model is deployed and applied to the next data analysis.

[0498] This system will enable early detection of avian influenza and preventative measures in real time.

[0499] Example 1

[0500] 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."

[0501] Conventional early detection and prevention measures for avian influenza at aquaculture farms rely on manual observation and incomplete data collection, making it difficult to make quick and accurate judgments. Furthermore, when abnormalities are discovered, response measures are often limited and inconsistent. This results in delayed detection of abnormalities and a high risk of infection spreading. Furthermore, the inability to effectively utilize collected data also delays improvements in the accuracy of future preventive measures.

[0502] 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.

[0503] In this invention, the server includes: means for periodically receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score; means for generating an alert and notifying the user when the risk score exceeds a set threshold; means for issuing the alert and suggesting specific prevention and countermeasures; and means for collecting feedback data from users and updating the AI ​​model to improve the accuracy of the analysis. This enables early detection of avian influenza and effective preventive measures, enables rapid response when abnormalities are discovered, and enables improved accuracy of future preventive measures.

[0504] A "farm" is a specially established environment for raising useful organisms such as livestock and fish.

[0505] A "sensor" is a device that detects changes in physical or chemical quantities and outputs them as an electrical signal.

[0506] "Data" refers to a record of information detected by the sensor, and specifically includes information such as temperature, humidity, movement, and video.

[0507] "Receiving" is the act of acquiring data transmitted from a remote location.

[0508] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis. Specifically, this includes data normalization and filtering of outliers.

[0509] "Artificial intelligence" refers to technologies and systems that learn from large amounts of data to solve specific tasks or problems.

[0510] "Abnormal behavior" refers to a behavioral pattern that deviates from normal, such as a sudden decrease in physical activity.

[0511] "Temperature changes" are when a chicken's body temperature rises or falls outside of its normal range.

[0512] A "risk score" is a numerical representation of the risk of an abnormality occurring, calculated from sensor data.

[0513] The "threshold" is the boundary value at which the risk score is judged to be abnormal from a normal state.

[0514] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[0515] "Prevention and control" refers to measures taken before or immediately after an abnormality occurs, and specifically includes quarantining chickens and antiviral treatment.

[0516] "Feedback data" refers to data that reports the results and status of a user's implementation of a measure.

[0517] "Model updating" means using feedback data to retrain the artificial intelligence algorithm and improve the accuracy of the analysis.

[0518] This invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing alerts. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis.

[0519] First, we will explain the overall configuration of this system. The system consists of terminals installed in the farm, which consist of temperature sensors, humidity sensors, motion sensors, and cameras, and a server that processes and analyzes the received data. These devices communicate via the Internet to collect and analyze data.

[0520] Data collection

[0521] Terminal: Temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and sends the data to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second. The data is then sent to the server every minute.

[0522] Data Transfer

[0523] Terminal: Sends collected data to a server via a network. Data transfer can be real-time or periodically, allowing for rapid analysis. For example, data can be transferred to the server every minute via the farm's Wi-Fi network.

[0524] Data Preprocessing

[0525] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. It also removes noise from the obtained temperature data and divides and labels the behavioral data by frame.

[0526] Data analysis

[0527] Server: Using the preprocessed data, an AI algorithm analyzes abnormal behavior and changes in body temperature and generates a risk score. Abnormal behavior is judged by comparing it with past data and a risk score is calculated. As a specific example, the AI ​​model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0528] Alerting and Notification

[0529] Server: If the risk score exceeds a set threshold, an alert is generated and notified to the appropriate user. At this time, a message proposing specific prevention and countermeasures is also sent. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." In addition, a notification is sent suggesting countermeasures such as, "Isolate the chickens and begin antiviral treatment."

[0530] Gathering feedback and updating AI models

[0531] User: Implements countermeasures and reports the results and status to the server as feedback via the device. For example, an administrator may quarantine chickens and then report through the app that their body temperature has returned to normal.

[0532] Server: The AI ​​model is updated using the collected feedback data. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. For example, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[0533] Prompt Sentence Examples

[0534] Examples of prompts to be input to a generative AI model include:

[0535] This question concerns the design of a system for early detection of abnormalities in chickens on a farm. The system uses temperature, humidity, and motion sensors, and cameras to collect data, which is then analyzed on a server. Please explain the names of the specific hardware and software, the data preprocessing method, the anomaly detection algorithm, the alert notification method, and the feedback collection process.

[0536] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[0537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0538] Step 1: Data collection

[0539] Terminal: Temperature, humidity, and motion sensors, as well as cameras, collect data on the chickens' body temperature, environment, and behavior. Each sensor periodically records data.

[0540] Specific operation: The temperature sensor measures the chicken's body temperature every 10 minutes, the humidity sensor measures the environmental humidity every 5 minutes, the movement sensor checks the chicken's movements every minute, and the camera records the chicken's behavior every second.

[0541] Input: Chicken body temperature, humidity, movement, behavioral video

[0542] Output: Collected data (body temperature data, humidity data, exercise data, video data)

[0543] Step 2: Data Transfer

[0544] Terminal: Sends collected data to the server in real time or periodically.

[0545] Specific operation: The collected data is transferred to the server every minute via the Wi-Fi network.

[0546] Input: Collected data (body temperature data, humidity data, exercise data, video data)

[0547] Output: Data sent to the server

[0548] Step 3: Data Preprocessing

[0549] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis.

[0550] Specific operation: The server performs noise removal and outlier filtering on the received data. The video data is also divided into frames, and each frame is assigned an action label.

[0551] Input: Data sent to the server (body temperature data, humidity data, exercise data, video data)

[0552] Output: Preprocessed data (normalized data, filtered data, labeled video data)

[0553] Step 4: Data analysis

[0554] Server: Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature and calculates a risk score.

[0555] Specific operation: The AI ​​model compares data with past data, detects abnormal behavior and changes in body temperature, and calculates a risk score. For example, if the temperature data is 38.2°C and the person is "immobile," the model calculates a risk score of 80.

[0556] Input: Preprocessed data (normalized data, filtered data, labeled video data)

[0557] Output: Risk score

[0558] Step 5: Alerting and Notification

[0559] Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0560] Specific operation: If the risk score exceeds 50, the server will send an alert message to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0561] Input: Risk Score

[0562] Output: Alert message

[0563] Step 6: Propose a solution

[0564] Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[0565] Specific action: Along with the alert notification, a message containing a countermeasure suggestion to "quarantine the chickens and start antiviral treatment" will be sent to the administrator.

[0566] Input: Risk score, Alert message

[0567] Output: Measure suggestion message

[0568] Step 7: Gather feedback

[0569] User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[0570] Specific operations: After implementing the measures, the administrator uses a smartphone app to enter and send information such as "The chickens were isolated and their body temperatures subsequently returned to normal."

[0571] Input: Countermeasure results, status information

[0572] Output: Feedback data

[0573] Step 8: Update the AI ​​model

[0574] Server: Updates the artificial intelligence model using collected feedback data.

[0575] Specific operation: The server retrains the AI ​​model based on the newly acquired feedback data, further improving the accuracy of analysis.

[0576] Input: Feedback data

[0577] Output: Updated AI model

[0578] (Application example 1)

[0579] 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."

[0580] Conventional methods for early detection and prevention of avian influenza at aquaculture farms rely on data collection and analysis using sensors, but these methods pose challenges in terms of real-time monitoring and prompt notification to managers. Furthermore, there is a lack of a mechanism for updating the AI ​​model based on feedback, resulting in insufficient analysis accuracy. Therefore, a system that enables early detection of abnormal behavior and prompt countermeasures is needed.

[0581] 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.

[0582] In this invention, the server includes means for receiving data collected from sensors installed in the farm, means for preprocessing the received sensor data and converting it into a format suitable for analysis, means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score, means for generating and notifying an alert when the risk score exceeds a certain threshold, means for proposing prevention and countermeasures based on the risk score, means for collecting feedback data from users and updating the AI ​​model, and means for the farm manager to monitor the status of the chickens in real time. This enables real-time status monitoring and prompt notification, as well as improved analysis accuracy based on feedback.

[0583] An "aquaculture farm" is a facility for raising and managing animals such as livestock and farmed fish.

[0584] A "sensor" is a device for measuring variables in the external environment and collecting that data.

[0585] The "data receiving means" is a function for acquiring data transmitted from a sensor.

[0586] "Preprocessing" is the process of converting received data into a form suitable for analysis.

[0587] "Artificial intelligence" is a program that allows a computer to analyze data and detect abnormal behavior or changes in body temperature.

[0588] The "risk score" is an indicator of danger calculated based on abnormal behavior and changes in body temperature.

[0589] The "alert generation means" is a function for issuing a warning when the risk score exceeds a certain threshold.

[0590] "Notification means" is the process by which an administrator is notified of an alert.

[0591] "Preventive measures" are methods for suggesting disease prevention based on risk scores.

[0592] The "measure proposal means" is a function that proposes appropriate measures for problems that may occur.

[0593] A "feedback collection means" is a method for collecting behavioral results from users.

[0594] "Model updating" is the process of improving an artificial intelligence model based on collected feedback data.

[0595] "Real-time monitoring means" is a function that allows farm managers to instantly grasp the status of chickens.

[0596] This invention describes a system for early detection of avian influenza and real-time implementation of preventive measures. This system includes a function to collect and analyze data from sensors installed in aquaculture farms, calculate a risk score, and notify managers of appropriate alerts. In addition, the accuracy of the analysis can be improved by collecting feedback data from users and updating the generative AI model.

[0597] System configuration

[0598] Data Collection and Transmission

[0599] Device:

[0600] Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data from the chickens. Each sensor periodically records the data and transmits it to a server at regular intervals.

[0601] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[0602] Data Preprocessing and Analysis

[0603] server:

[0604] Preprocessing of received sensor data and conversion to a format suitable for analysis, specifically normalizing the data and filtering outliers.

[0605] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[0606] Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature to generate a risk score. Abnormal behavior is judged by comparing it with past data and calculating a risk score.

[0607] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0608] Alert notifications and countermeasure suggestions

[0609] server:

[0610] If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0611] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0612] Send notifications with alerts and specific prevention and action suggestions.

[0613] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[0614] Feedback Collection and Machine Learning

[0615] User:

[0616] Countermeasures are implemented and the results and status are reported as feedback to the server via the device.

[0617] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[0618] server:

[0619] The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[0620] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[0621] Hardware and software used

[0622] Hardware: temperature sensor, humidity sensor, motion sensor, camera, smartphone

[0623] Software: denoising algorithms for data preprocessing, labeling algorithms, and AI models (e.g., models using machine learning libraries TensorFlow or PyTorch)

[0624] Prompt Sentence Examples

[0625] "Given the temperature readings and activity levels of the chickens, determine the risk score for bird flu infection. Consider higher temperatures and inactivity as higher risk."

[0626] This system allows farm managers to monitor for abnormal signs of avian influenza in real time and take prompt action, significantly reducing the risk of infection spreading.

[0627] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0628] Step 1: Data collection

[0629] The terminal collects data from temperature, humidity, and motion sensors and cameras installed in the farm. The input is raw data obtained from the sensors, which typically includes temperature, humidity, movement, and video data. This data is collected at regular intervals and prepared for transmission. The output is a dataset of various environmental conditions and behavioral data.

[0630] Step 2: Send data

[0631] The terminal sends the collected data to the server at regular intervals. The input is the data collected in the previous step. The data is sent to the server via the network. The output is the data received by the server.

[0632] Step 3: Data Preprocessing

[0633] The server converts the received data into a format suitable for analysis. Specifically, it performs noise removal and outlier filtering. The input is the transmitted sensor data, and the output is preprocessed and normalized data. For example, temperature data is normalized, and behavioral data is split into frames and labeled.

[0634] Step 4: Anomaly detection and risk scoring

[0635] The server uses the preprocessed data to analyze abnormal behavior and changes in body temperature using a generative AI model. It calculates a risk score and compares it with past data to determine abnormal behavior. The input is the preprocessed data, and the output is the calculated risk score. Specifically, it detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0636] Step 5: Alerting and Notification

[0637] The server generates an alert when the risk score exceeds a set threshold and notifies the appropriate user. The input is the risk score and a preset threshold, and the output is a notification message. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the individual immediately and take quarantine measures."

[0638] Step 6: Propose a solution

[0639] The server will then provide alerts and suggest specific preventive and countermeasure measures. The input is the risk score and past countermeasure data, and the output is a message proposing countermeasures. For example, the server might suggest countermeasures such as "Isolate the chickens and start antiviral treatment."

[0640] Step 7: Gather feedback

[0641] The user implements the measures and reports the results and situation as feedback to the server via their device. The input is data on the measures actually taken and their results, and the output is sent to the server as feedback data. Specifically, the manager quarantines the chickens and then reports through the app that their body temperature has returned to normal.

[0642] Step 8: Update the model

[0643] The server updates the generative AI model using the collected feedback data. The input is the feedback data, and the output is the updated AI model. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. Specifically, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[0644] 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.

[0645] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time, and includes an emotion engine that recognizes user emotions. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing an alert. Furthermore, emotion data based on user feedback is collected and the artificial intelligence model is updated to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[0646] Data Collection and Transmission

[0647] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[0648] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[0649] Data Preprocessing and Analysis

[0650] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[0651] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[0652] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[0653] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0654] Alert notifications and countermeasure suggestions

[0655] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0656] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0657] 5. Server: Sends notifications along with alerts and suggests specific preventive and countermeasure measures.

[0658] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[0659] 6. Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[0660] Example: If the user's input and behavioral patterns are analyzed and it is determined that they are under high stress, an encouraging message such as "It is important to take immediate action. Please do not rush and follow the instructions" will be sent.

[0661] Feedback Collection and Machine Learning

[0662] 7. User: Receive notification and take action.

[0663] Example: Following the notification, promptly isolate the chickens and implement the specified antiviral measures. After implementing the measures, observe the results.

[0664] 8. User: Feedback the results and status of countermeasures to the server via the terminal.

[0665] Example: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application. The user's emotions are also recorded when giving feedback.

[0666] 9. Server: Stores the received feedback data in a database.

[0667] Example: Analyze user emotion data along with feedback data and add it to the database. Store it as new data and use it to update the analysis model.

[0668] 10. Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[0669] Example: Retraining artificial intelligence algorithms and sentiment engines with new data collected to improve analysis accuracy. Deploying new models to reflect the next data analysis.

[0670] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[0671] The processing flow will be explained below.

[0672] Step 1:

[0673] Terminals: Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data of the chickens.

[0674] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[0675] Step 2:

[0676] Terminal: Sends collected data to the server at regular intervals.

[0677] Specific operation: Temperature data, humidity data, and behavioral data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[0678] Step 3:

[0679] Server: Checks the received data and stores it in a database.

[0680] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, sends a receipt confirmation response to the terminal.

[0681] Step 4:

[0682] Server: Preprocesses the received data.

[0683] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[0684] Step 5:

[0685] Server: Analyzes the pre-processed data and calculates the risk score.

[0686] How it works: Using an AI algorithm, it analyzes abnormal behavior (e.g., a chicken not moving) and abnormal body temperature values, compares this with past learning data, and calculates a risk score, for example, 80.

[0687] Step 6:

[0688] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[0689] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0690] Step 7:

[0691] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[0692] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[0693] Step 8:

[0694] Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[0695] Specific actions: Analyze the user's input and behavioral patterns, and if it determines that the user is under high stress, send an encouraging message such as, "It is important to take immediate action. Don't rush, just follow the instructions."

[0696] Step 9:

[0697] Users: Receive notifications and take action.

[0698] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[0699] Step 10:

[0700] User: Feedback the results and status of countermeasures to the server via the terminal.

[0701] Specific operation: The user inputs and sends feedback data through the application, such as "Isolation work completed, body temperature has returned to the normal range of 39°C." The user's emotions are also recorded when providing feedback.

[0702] Step 11:

[0703] Server: Stores the received feedback data in a database.

[0704] Specific operation: The user's emotional data is analyzed along with the feedback data and added to the database. The data is stored as new data and used to update the analysis model.

[0705] Step 12:

[0706] Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[0707] What happens: Retrain the AI ​​algorithms and sentiment engine with the new data collected to improve analysis accuracy. Deploy the new model and apply it to the next data analysis.

[0708] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[0709] Example 2

[0710] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0711] When an infectious disease such as avian influenza breaks out at an aquaculture farm, early detection and rapid countermeasures are required. While existing systems can detect some anomalies, they only notify users uniformly and are unable to respond to the individual circumstances and emotions of each user. This can lead to stress for users and delays in taking appropriate countermeasures. Furthermore, the system lacks a mechanism for utilizing feedback data to improve the accuracy of analysis.

[0712] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for analyzing user emotions and customizing the notification content; and means for collecting feedback data and emotion data from users and updating the AI ​​model. This enables early detection and rapid countermeasures for avian influenza, realizes notifications that take user emotions into consideration, and improves analysis accuracy by utilizing feedback data.

[0713] A "sensor" is a device that detects a specific physical quantity of an object and outputs it as an electrical signal.

[0714] "Data receiving means" refers to the function of the equipment or software that acquires and incorporates data transmitted from the sensor.

[0715] "Data preprocessing means" refers to a function that performs processing to convert raw data into a format that is easy to analyze, and specifically includes data normalization and filtering of outliers.

[0716] "Artificial intelligence" is a technology that allows computer systems to learn, reason, and recognize by imitating human intelligence, and in this invention it is used to detect abnormal behavior and calculate risk scores.

[0717] The "abnormal behavior analysis means" is a function that uses preprocessed data to enable artificial intelligence to analyze abnormal behavior and changes in body temperature of chickens.

[0718] The "risk scoring means" is a function that quantifies the risk of abnormality based on the analysis results.

[0719] The "alert generation means" is a function that issues an alert and notifies the user when the risk score exceeds a set threshold.

[0720] The "prevention and countermeasure suggestion means" is a function that suggests specific countermeasures to the user against infectious diseases such as avian influenza based on the analysis results.

[0721] "Emotion analysis means" is a function that analyzes the user's emotions and generates and customizes appropriate notification content based on that information.

[0722] "Feedback collection means" is a function that acquires the results and status of measures implemented by users and incorporates them into the system.

[0723] "Model updating means" is a function that uses collected feedback data to improve and update the artificial intelligence model.

[0724] The present invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes for collecting and analyzing data from multiple sensors installed in aquaculture farms, calculating a risk score, and issuing alerts as necessary. Furthermore, the system is equipped with a function for improving the accuracy of the analysis based on user feedback and emotion data. A specific embodiment of this system is described below.

[0725] Data Collection and Transmission

[0726] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. These sensors record data periodically and send it to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second and sends the data to the server every minute.

[0727] Data Preprocessing

[0728] The server preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. For example, it removes noise from the acquired temperature data and divides and labels the behavioral data into frames.

[0729] Data analysis

[0730] The server uses pre-processed data and an artificial intelligence algorithm to analyze abnormal behavior and changes in body temperature and calculate a risk score. Abnormal behavior is determined by comparing it with past data. For example, if the AI ​​model detects a temperature of 38.2°C and abnormal behavior (immobility), it will calculate a risk score of 80.

[0731] Alert notifications and countermeasure suggestions

[0732] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It also sends a notification suggesting specific preventative measures along with the alert. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." At the same time, the system suggests measures such as "Isolate the chickens and begin antiviral treatment."

[0733] Sentiment analysis and notification customization

[0734] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. For example, if the server analyzes the user's input and behavioral patterns and determines that they are under high stress, it will send an encouraging message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[0735] Gathering feedback and updating machine learning models

[0736] The user receives the notification, takes action, and then sends feedback about the results and situation to the server via their device. For example, the user may quickly quarantine the chickens in accordance with the notification and implement the specified antiviral measures. As a result, feedback data such as "Isolation completed, body temperature has returned to the normal range of 39°C" is sent. The user's emotions are also recorded when providing feedback.

[0737] The server updates the AI ​​model and emotion engine based on the received feedback data and emotion data, for example, by retraining the AI ​​algorithm and emotion engine using the new data collected to improve the accuracy of the analysis, and then deploys the new model to be reflected in the next data analysis.

[0738] Prompt Sentence Examples

[0739] Here are some example prompts to input to a generative AI model:

[0740] "The system uses various sensors installed in the farm to monitor the health of chickens in real time, detects abnormalities early and calculates a risk score. It then sends appropriate alerts and measures. It also analyzes user sentiment and customizes the notification content. Feedback data is used to update the model and improve the accuracy of the analysis."

[0741] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0742] Step 1: Data collection

[0743] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. As input, it takes raw data from each sensor and records it at regular intervals. For example, the temperature sensor measures chicken body temperature every 10 minutes, and the camera records chicken behavior every second. As output, it buffers the collected data and prepares it to be sent to the server.

[0744] Step 2: Send data

[0745] The device sends the collected data to the server at a specified interval. As input, it uses the sensor data buffered on the device and uploads this data to the server as output. For example, the collected temperature data or video data can be sent to the server every minute.

[0746] Step 3: Data Preprocessing

[0747] The server preprocesses the received sensor data. It receives raw data sent from the device as input and generates preprocessed data suitable for analysis as output. This preprocessing includes data normalization, outlier filtering, and noise removal. For example, it removes noise from the obtained temperature data and segments and labels the behavioral data by frame.

[0748] Step 4: Data analysis

[0749] The server uses an artificial intelligence algorithm to analyze the preprocessed data. It uses the preprocessed data as input and analyzes abnormal behavior and changes in body temperature as output to calculate a risk score. For example, an AI model detects a temperature of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0750] Step 5: Alert Generation

[0751] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It uses the risk score as input and generates an alert message as output. For example, if the risk score exceeds 50, an alert message stating "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures" is sent to the administrator's smartphone.

[0752] Step 6: Propose a solution

[0753] The server sends a notification to the user along with the alert, suggesting specific prevention and countermeasures. It uses the risk score and analysis results as input and generates a message suggesting countermeasures as output. For example, it suggests countermeasures such as "Isolate the chickens and start antiviral treatment."

[0754] Step 7: Sentiment Analysis and Notification Customization

[0755] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. It uses the user's feedback and operation history as input and generates a customized notification message as output. For example, if it determines that the user is under high stress, it sends a message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[0756] Step 8: Gather feedback

[0757] The user implements the measures and sends the results and status as feedback to the server. The user inputs the results of their actions as input, and this data is sent to the server as output. For example, feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is sent.

[0758] Step 9: Update the model

[0759] The server uses the received feedback data and emotion data to update the artificial intelligence model and emotion engine. It uses the newly collected data as input and generates an updated model as output. For example, it uses the collected new data to retrain the AI ​​algorithm and emotion engine to improve the accuracy of analysis. It then deploys the new model and applies it to the next data analysis.

[0760] In this way, the system will enable early detection of avian influenza and rapid countermeasures, providing effective support to users.

[0761] (Application example 2)

[0762] 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."

[0763] Conventional systems have been unable to detect abnormalities early or implement sufficient preventative measures at aquaculture farms and manufacturing facilities, making it difficult to respond quickly when an abnormality occurs. Furthermore, conventional anomaly detection systems do not customize notification content based on feedback or user sentiment, and therefore do not provide sufficient support for implementing optimal measures.

[0764] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm or manufacturing facility; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature and equipment operating status using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for collecting feedback data from users and updating the AI ​​model; and means for the AI ​​to analyze the user's emotions and customize the content of the notification. This enables early detection of abnormalities and rapid response, and can propose optimal countermeasures based on the user's emotions.

[0765] An "aquaculture farm" is a facility for raising and managing living organisms such as poultry and fish.

[0766] A "manufacturing facility" is a location such as a factory or workshop where products are produced or assembled.

[0767] A "sensor" is a device that detects environmental data such as temperature, humidity, vibration, and images, as well as operational data, and outputs it as a signal.

[0768] The "means for receiving data" refers to a method or device for inputting data transmitted from a sensor into a server or computer.

[0769] "Means for preprocessing data and converting it into a format suitable for analysis" refers to a method or device that processes received data into an analyzable state by removing noise, normalizing, labeling, etc.

[0770] "Artificial intelligence" refers to algorithms and software that analyze received data and evaluate abnormal behavior, changes in body temperature, and the operating status of equipment.

[0771] A "means for scoring risk" is a method or device that expresses the degree of abnormality or risk as a number based on the results of analysis using artificial intelligence.

[0772] "Means for generating and notifying alerts" refers to a method or device for generating and notifying a user of a warning based on a risk score that exceeds a set threshold.

[0773] The "means for proposing prevention and countermeasures" is a method or device that presents specific prevention measures and countermeasures to the user based on the risk score.

[0774] "Means for collecting feedback data from users" refers to a method or device for incorporating response results and status reports from users into the system.

[0775] "Means for updating artificial intelligence models" refers to methods or devices that improve the accuracy of analytical algorithms or learn new models based on collected feedback data.

[0776] The "means for analyzing emotions and customizing notification content" refers to a method or device that determines emotions from user input and behavioral data and adjusts notification messages to match that emotional state.

[0777] The present invention provides a system for detecting abnormalities in manufacturing facilities and proposing countermeasures based on a system for early detection of avian influenza and implementing preventive measures in real time. This system is implemented in the following manner and configuration.

[0778] First, temperature, humidity, and vibration sensors, as well as cameras, are installed within the manufacturing facility to periodically measure environmental data and the operating status of the equipment and send the data to a server.

[0779] The server receives temperature, humidity, vibration, and image data and preprocesses them. This includes noise removal, data normalization, and frame-by-frame image labeling. The preprocessed data is then analyzed by an artificial intelligence algorithm to quantify abnormal behavior and equipment operating conditions as a risk score.

[0780] If the risk score exceeds a certain threshold, the server generates an alert and sends it to the administrator's smartphone or head-mounted display. The alert suggests specific preventive and countermeasure measures, such as, "The temperature of the refrigerator has exceeded the set range. Please immediately check the site and request repairs."

[0781] The server collects feedback data from users and updates the AI ​​model based on this data. This feedback includes the results of countermeasure implementation and status reports, and also analyzes the user's emotional data. By customizing the notification content according to the user's emotions, the system helps users implement countermeasures without feeling stressed.

[0782] For example, if it determines that a user is in a high stress state, it will send an encouraging message such as, "It is important to take action immediately. Please do not rush and follow the instructions." This function is realized by analyzing the user's input and behavioral patterns using an emotion engine.

[0783] A specific scenario is shown below.

[0784] If the temperature in a freezer warehouse at a manufacturing facility becomes abnormally high, a temperature sensor collects data and sends it to a server. The server removes noise from this data, and an AI model analyzes it. If the risk score exceeds a threshold, the server generates an alert and sends a message to the manager's smartphone saying, "The freezer temperature has exceeded the set range. Please check the site immediately and request repairs." The manager receives this notification and immediately takes action. Feedback is then sent to the server, stating, "Repair work completed, temperature has returned to normal range," along with the user's emotional data. The server updates the AI ​​model based on this data.

[0785] An example of a prompt to use for the generative AI model is as follows:

[0786] "Analyze the following data set and predict the anomaly risk score for this production line.

[0787] Datasets: Temperature data, humidity data, vibration data, image data

[0788] Time range: 30 minutes

[0789] Output: Anomaly risk score, specific explanation of the anomaly cause

[0790] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0791] Step 1:

[0792] Sensors collect data such as temperature, humidity, vibration, and images.

[0793] Specifically, the temperature sensor acquires temperature data every 10 minutes, the humidity sensor acquires humidity data every 15 minutes, the vibration sensor acquires vibration data every 5 seconds, and the camera captures images every second. These data are periodically sent to the server.

[0794] Input: Environmental and image data from sensors.

[0795] Output: The raw data sent to the server.

[0796] Step 2:

[0797] The server receives the data sent from the sensor.

[0798] Specifically, the server periodically monitors data from each sensor and receives the data via HTTP requests.

[0799] Input: Raw data sent from the sensor.

[0800] Output: Raw data stored on the server.

[0801] Step 3:

[0802] The server preprocesses the data received.

[0803] Specifically, the process involves noise removal, normalization, and then dividing and labeling the image data by frame.

[0804] Input: Raw data stored in the server.

[0805] Output: Preprocessed data.

[0806] Step 4:

[0807] The server uses the pre-processed data to perform analysis using an AI model.

[0808] Specifically, an artificial intelligence algorithm analyzes pre-processed data, detects abnormal behavior, body temperature, and changes in equipment operating status, and scores the risk.

[0809] Input: Preprocessed data.

[0810] Output: Risk score and analysis results.

[0811] Step 5:

[0812] If the risk score exceeds a certain threshold, the server generates an alert and notifies you.

[0813] Specifically, the system monitors the risk score and, if it exceeds a threshold, sends an alert notification to the administrator's smartphone or head-mounted display.

[0814] Input: Risk score.

[0815] Output: Alert notification.

[0816] Step 6:

[0817] The server suggests prevention and countermeasures based on the risk score.

[0818] Specifically, the system refers to past response examples in a database, selects appropriate preventive measures and countermeasures, and includes them in the notification.

[0819] Inputs: Risk score and past case data.

[0820] Output: Notification of specific preventive measures and countermeasures.

[0821] Step 7:

[0822] The user receives the notification and sends the feedback data to the server.

[0823] Specifically, the user checks the notification via a smartphone or head-mounted display, enters the response results, and sends them.

[0824] Input: Countermeasure execution results and user feedback data.

[0825] Output: Feedback data sent to the server.

[0826] Step 8:

[0827] The server updates the artificial intelligence model based on the feedback data.

[0828] Specifically, the feedback data is analyzed, input into the AI ​​model as new data, and the model is retrained.

[0829] Input: Feedback data.

[0830] Output: The updated AI model.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] [Third embodiment]

[0835] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0836] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0837] 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).

[0838] 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.

[0839] 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.

[0840] 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).

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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."

[0847] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time. This system involves a series of processes that collect data from sensors installed in aquaculture farms, analyze the data, calculate a risk score, and issue an alert. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[0848] Data Collection and Transmission

[0849] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[0850] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[0851] Data Preprocessing and Analysis

[0852] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[0853] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[0854] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[0855] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0856] Alert notifications and countermeasure suggestions

[0857] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0858] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0859] 5. Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[0860] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[0861] Feedback Collection and Machine Learning

[0862] 6. User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[0863] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[0864] 7. Server: The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[0865] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[0866] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[0867] The processing flow will be explained below.

[0868] Step 1:

[0869] Terminal: Various sensors (temperature sensors, humidity sensors, motion sensors) and cameras installed in the farm collect data.

[0870] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[0871] Step 2:

[0872] Terminal: Sends collected data to the server at regular intervals.

[0873] Specific operation: Temperature data, humidity data, and behavior data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[0874] Step 3:

[0875] Server: Checks the received data and stores it in a database.

[0876] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, a receipt confirmation response is sent to the terminal.

[0877] Step 4:

[0878] Server: Preprocesses the received data.

[0879] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[0880] Step 5:

[0881] Server: Analyzes the pre-processed data and calculates the risk score.

[0882] How it works: Using an AI algorithm, abnormal behavior (e.g., a chicken not moving) and abnormal body temperature are analyzed. This is compared with past learning data and a risk score is calculated, for example, as 80.

[0883] Step 6:

[0884] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[0885] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0886] Step 7:

[0887] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[0888] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[0889] Step 8:

[0890] Users: Receive notifications and take action.

[0891] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[0892] Step 9:

[0893] User: Feedback the results and status of countermeasures to the server via the terminal.

[0894] Specific operation: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application.

[0895] Step 10:

[0896] Server: Stores the received feedback data in a database.

[0897] Specific operation: The feedback data is analyzed and added to the database. It is stored as new data and used to update the analytical model.

[0898] Step 11:

[0899] Server: Updates the artificial intelligence model based on the feedback data.

[0900] What happens: The AI ​​algorithm is retrained using the new data collected to improve analysis accuracy, and the new model is deployed and applied to the next data analysis.

[0901] This system will enable early detection of avian influenza and preventative measures in real time.

[0902] Example 1

[0903] 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."

[0904] Conventional early detection and prevention measures for avian influenza at aquaculture farms rely on manual observation and incomplete data collection, making it difficult to make quick and accurate judgments. Furthermore, when abnormalities are discovered, response measures are often limited and inconsistent. This results in delayed detection of abnormalities and a high risk of infection spreading. Furthermore, the inability to effectively utilize collected data also delays improvements in the accuracy of future preventive measures.

[0905] 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.

[0906] In this invention, the server includes: means for periodically receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score; means for generating an alert and notifying the user when the risk score exceeds a set threshold; means for issuing the alert and suggesting specific prevention and countermeasures; and means for collecting feedback data from users and updating the AI ​​model to improve the accuracy of the analysis. This enables early detection of avian influenza and effective preventive measures, enables rapid response when abnormalities are discovered, and enables improved accuracy of future preventive measures.

[0907] A "farm" is a specially established environment for raising useful organisms such as livestock and fish.

[0908] A "sensor" is a device that detects changes in physical or chemical quantities and outputs them as an electrical signal.

[0909] "Data" refers to a record of information detected by the sensor, and specifically includes information such as temperature, humidity, movement, and video.

[0910] "Receiving" is the act of acquiring data transmitted from a remote location.

[0911] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis. Specifically, this includes data normalization and filtering of outliers.

[0912] "Artificial intelligence" refers to technologies and systems that learn from large amounts of data to solve specific tasks or problems.

[0913] "Abnormal behavior" refers to a behavioral pattern that deviates from normal, such as a sudden decrease in physical activity.

[0914] "Temperature changes" are when a chicken's body temperature rises or falls outside of its normal range.

[0915] A "risk score" is a numerical representation of the risk of an abnormality occurring, calculated from sensor data.

[0916] The "threshold" is the boundary value at which the risk score is judged to be abnormal from a normal state.

[0917] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[0918] "Prevention and control" refers to measures taken before or immediately after an abnormality occurs, and specifically includes quarantining chickens and antiviral treatment.

[0919] "Feedback data" is data that reports the results and status of a user's implementation of a measure.

[0920] "Model updating" means using feedback data to retrain the artificial intelligence algorithm and improve the accuracy of the analysis.

[0921] This invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing alerts. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis.

[0922] First, we will explain the overall configuration of this system. The system consists of terminals installed in the farm, which consist of temperature sensors, humidity sensors, motion sensors, and cameras, and a server that processes and analyzes the received data. These devices communicate via the Internet to collect and analyze data.

[0923] Data collection

[0924] Terminal: Temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and sends the data to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second. The data is then sent to the server every minute.

[0925] Data Transfer

[0926] Terminal: Sends collected data to a server via a network. Data transfer can be real-time or periodically, allowing for rapid analysis. For example, data can be transferred to the server every minute via the farm's Wi-Fi network.

[0927] Data Preprocessing

[0928] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. It also removes noise from the obtained temperature data and divides and labels the behavioral data by frame.

[0929] Data analysis

[0930] Server: Using the preprocessed data, an AI algorithm analyzes abnormal behavior and changes in body temperature and generates a risk score. Abnormal behavior is judged by comparing it with past data and a risk score is calculated. As a specific example, the AI ​​model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[0931] Alerting and Notification

[0932] Server: If the risk score exceeds a set threshold, an alert is generated and notified to the appropriate user. At this time, a message proposing specific prevention and countermeasures is also sent. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." In addition, a notification is sent suggesting countermeasures such as, "Isolate the chickens and begin antiviral treatment."

[0933] Gathering feedback and updating AI models

[0934] User: Implements countermeasures and reports the results and situation to the server as feedback via the device. For example, an administrator quarantines chickens and then reports through the app that their body temperature has returned to normal.

[0935] Server: The AI ​​model is updated using the collected feedback data. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. For example, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[0936] Prompt Sentence Examples

[0937] Examples of prompts to be input to a generative AI model include:

[0938] This question concerns the design of a system for early detection of abnormalities in chickens on a farm. The system uses temperature, humidity, and motion sensors, and cameras to collect data, which is then analyzed on a server. Please explain the names of the specific hardware and software, the data preprocessing method, the anomaly detection algorithm, the alert notification method, and the feedback collection process.

[0939] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[0940] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0941] Step 1: Data collection

[0942] Terminal: Temperature, humidity, and motion sensors, as well as cameras, collect data on the chickens' body temperature, environment, and behavior. Each sensor periodically records data.

[0943] Specific operation: The temperature sensor measures the chicken's body temperature every 10 minutes, the humidity sensor measures the environmental humidity every 5 minutes, the movement sensor checks the chicken's movements every minute, and the camera records the chicken's behavior every second.

[0944] Input: Chicken body temperature, humidity, movement, behavioral video

[0945] Output: Collected data (body temperature data, humidity data, exercise data, video data)

[0946] Step 2: Data Transfer

[0947] Terminal: Sends collected data to the server in real time or periodically.

[0948] Specific operation: The collected data is transferred to the server every minute via the Wi-Fi network.

[0949] Input: Collected data (body temperature data, humidity data, exercise data, video data)

[0950] Output: Data sent to the server

[0951] Step 3: Data Preprocessing

[0952] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis.

[0953] Specific operation: The server performs noise removal and outlier filtering on the received data. The video data is also divided into frames, and each frame is assigned an action label.

[0954] Input: Data sent to the server (body temperature data, humidity data, exercise data, video data)

[0955] Output: Preprocessed data (normalized data, filtered data, labeled video data)

[0956] Step 4: Data analysis

[0957] Server: Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature and calculates a risk score.

[0958] Specific operation: The AI ​​model compares data with past data, detects abnormal behavior and changes in body temperature, and calculates a risk score. For example, if the temperature data is 38.2°C and the person is "immobile," the model calculates a risk score of 80.

[0959] Input: Preprocessed data (normalized data, filtered data, labeled video data)

[0960] Output: Risk score

[0961] Step 5: Alerting and Notification

[0962] Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[0963] Specific operation: If the risk score exceeds 50, the server will send an alert message to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[0964] Input: Risk Score

[0965] Output: Alert message

[0966] Step 6: Propose a solution

[0967] Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[0968] Specific action: Along with the alert notification, a message containing a countermeasure suggestion to "quarantine the chickens and start antiviral treatment" will be sent to the administrator.

[0969] Input: Risk score, Alert message

[0970] Output: Measures proposed message

[0971] Step 7: Gather feedback

[0972] User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[0973] Specific operations: After implementing the measures, the administrator uses a smartphone app to enter and send information such as "The chickens were isolated and their body temperatures subsequently returned to normal."

[0974] Input: Countermeasure results, status information

[0975] Output: Feedback data

[0976] Step 8: Update the AI ​​model

[0977] Server: Updates the artificial intelligence model using collected feedback data.

[0978] Specific operation: The server retrains the AI ​​model based on the newly acquired feedback data, further improving the accuracy of analysis.

[0979] Input: Feedback data

[0980] Output: Updated AI model

[0981] (Application example 1)

[0982] 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."

[0983] Conventional methods for early detection and prevention of avian influenza at aquaculture farms rely on data collection and analysis using sensors, but these methods pose challenges in terms of real-time monitoring and prompt notification to managers. Furthermore, there is a lack of a mechanism for updating the AI ​​model based on feedback, resulting in insufficient analysis accuracy. Therefore, a system that enables early detection of abnormal behavior and prompt countermeasures is needed.

[0984] 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.

[0985] In this invention, the server includes means for receiving data collected from sensors installed in the farm, means for preprocessing the received sensor data and converting it into a format suitable for analysis, means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score, means for generating and notifying an alert when the risk score exceeds a certain threshold, means for proposing prevention and countermeasures based on the risk score, means for collecting feedback data from users and updating the AI ​​model, and means for the farm manager to monitor the status of the chickens in real time. This enables real-time status monitoring and prompt notification, as well as improved analysis accuracy based on feedback.

[0986] An "aquaculture farm" is a facility for raising and managing animals such as livestock and farmed fish.

[0987] A "sensor" is a device for measuring variables in the external environment and collecting that data.

[0988] The "data receiving means" is a function for acquiring data transmitted from a sensor.

[0989] "Preprocessing" is the process of converting received data into a form suitable for analysis.

[0990] "Artificial intelligence" is a program that allows a computer to analyze data and detect abnormal behavior or changes in body temperature.

[0991] The "risk score" is an indicator of danger calculated based on abnormal behavior and changes in body temperature.

[0992] The "alert generation means" is a function for issuing a warning when the risk score exceeds a certain threshold.

[0993] "Notification means" is the process by which an administrator is notified of an alert.

[0994] "Preventive measures" are methods for suggesting disease prevention based on risk scores.

[0995] The "measure proposal means" is a function that proposes appropriate measures for problems that may occur.

[0996] A "feedback collection means" is a method for collecting behavioral results from users.

[0997] "Model updating" is the process of improving an artificial intelligence model based on collected feedback data.

[0998] "Real-time monitoring means" is a function that allows farm managers to instantly grasp the status of chickens.

[0999] This invention describes a system for early detection of avian influenza and real-time implementation of preventive measures. This system includes a function to collect and analyze data from sensors installed in aquaculture farms, calculate a risk score, and notify managers of appropriate alerts. In addition, the accuracy of the analysis can be improved by collecting feedback data from users and updating the generative AI model.

[1000] System configuration

[1001] Data Collection and Transmission

[1002] Device:

[1003] Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data from the chickens. Each sensor periodically records the data and transmits it to a server at regular intervals.

[1004] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[1005] Data Preprocessing and Analysis

[1006] server:

[1007] Preprocessing of received sensor data and conversion to a format suitable for analysis, specifically normalizing the data and filtering outliers.

[1008] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[1009] Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature to generate a risk score. Abnormal behavior is judged by comparing it with past data and calculating a risk score.

[1010] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1011] Alert notifications and countermeasure suggestions

[1012] server:

[1013] If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[1014] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1015] Send notifications with alerts and specific prevention and action suggestions.

[1016] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[1017] Feedback Collection and Machine Learning

[1018] User:

[1019] Countermeasures are implemented and the results and status are reported as feedback to the server via the device.

[1020] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[1021] server:

[1022] The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[1023] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[1024] Hardware and software used

[1025] Hardware: temperature sensor, humidity sensor, motion sensor, camera, smartphone

[1026] Software: denoising algorithms for data preprocessing, labeling algorithms, and AI models (e.g., models using machine learning libraries TensorFlow or PyTorch)

[1027] Prompt Sentence Examples

[1028] "Given the temperature readings and activity levels of the chickens, determine the risk score for bird flu infection. Consider higher temperatures and inactivity as higher risk."

[1029] This system allows farm managers to monitor for abnormal signs of avian influenza in real time and take prompt action, significantly reducing the risk of infection spreading.

[1030] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1031] Step 1: Data collection

[1032] The terminal collects data from temperature, humidity, and motion sensors and cameras installed in the farm. The input is raw data obtained from the sensors, which typically includes temperature, humidity, movement, and video data. This data is collected at regular intervals and prepared for transmission. The output is a dataset of various environmental conditions and behavioral data.

[1033] Step 2: Send data

[1034] The terminal sends the collected data to the server at regular intervals. The input is the data collected in the previous step. The data is sent to the server via the network. The output is the data received by the server.

[1035] Step 3: Data Preprocessing

[1036] The server converts the received data into a format suitable for analysis. Specifically, it performs noise removal and outlier filtering. The input is the transmitted sensor data, and the output is preprocessed and normalized data. For example, temperature data is normalized, and behavioral data is split into frames and labeled.

[1037] Step 4: Anomaly detection and risk scoring

[1038] The server uses the preprocessed data to analyze abnormal behavior and changes in body temperature using a generative AI model. It calculates a risk score and compares it with past data to determine abnormal behavior. The input is the preprocessed data, and the output is the calculated risk score. Specifically, it detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1039] Step 5: Alerting and Notification

[1040] The server generates an alert when the risk score exceeds a set threshold and notifies the appropriate user. The input is the risk score and a preset threshold, and the output is a notification message. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the individual immediately and take quarantine measures."

[1041] Step 6: Propose a solution

[1042] The server will then provide alerts and suggest specific preventive and countermeasure measures. The input is the risk score and past countermeasure data, and the output is a message proposing countermeasures. For example, the server might suggest countermeasures such as "Isolate the chickens and start antiviral treatment."

[1043] Step 7: Gather feedback

[1044] The user implements the measures and reports the results and situation as feedback to the server via their device. The input is data on the measures actually taken and their results, and the output is sent to the server as feedback data. Specifically, the manager quarantines the chickens and then reports through the app that their body temperature has returned to normal.

[1045] Step 8: Update the model

[1046] The server updates the generative AI model using the collected feedback data. The input is the feedback data, and the output is the updated AI model. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. Specifically, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[1047] 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.

[1048] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time, and includes an emotion engine that recognizes user emotions. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing an alert. Furthermore, emotion data based on user feedback is collected and the artificial intelligence model is updated to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[1049] Data Collection and Transmission

[1050] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[1051] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[1052] Data Preprocessing and Analysis

[1053] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[1054] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[1055] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[1056] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1057] Alert notifications and countermeasure suggestions

[1058] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[1059] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1060] 5. Server: Sends notifications along with alerts and suggests specific preventive and countermeasure measures.

[1061] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[1062] 6. Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[1063] Example: If the user's input and behavioral patterns are analyzed and it is determined that they are under high stress, an encouraging message such as "It is important to take immediate action. Please do not rush and follow the instructions" will be sent.

[1064] Feedback Collection and Machine Learning

[1065] 7. User: Receive notification and take action.

[1066] Example: Following the notification, promptly isolate the chickens and implement the specified antiviral measures. After implementing the measures, observe the results.

[1067] 8. User: Feedback the results and status of countermeasures to the server via the terminal.

[1068] Example: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application. The user's emotions are also recorded when giving feedback.

[1069] 9. Server: Stores the received feedback data in a database.

[1070] Example: Analyze user emotion data along with feedback data and add it to the database. Store it as new data and use it to update the analysis model.

[1071] 10. Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[1072] Example: Retraining artificial intelligence algorithms and sentiment engines with new data collected to improve analysis accuracy. Deploying new models to reflect the next data analysis.

[1073] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[1074] The processing flow will be explained below.

[1075] Step 1:

[1076] Terminals: Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data of the chickens.

[1077] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[1078] Step 2:

[1079] Terminal: Sends collected data to the server at regular intervals.

[1080] Specific operation: Temperature data, humidity data, and behavior data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[1081] Step 3:

[1082] Server: Checks the received data and stores it in a database.

[1083] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, a receipt confirmation response is sent to the terminal.

[1084] Step 4:

[1085] Server: Preprocesses the received data.

[1086] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[1087] Step 5:

[1088] Server: Analyzes the pre-processed data and calculates the risk score.

[1089] How it works: Using an AI algorithm, abnormal behavior (e.g., a chicken not moving) and abnormal body temperature are analyzed. This is compared with past learning data and a risk score is calculated, for example, as 80.

[1090] Step 6:

[1091] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[1092] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1093] Step 7:

[1094] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[1095] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[1096] Step 8:

[1097] Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[1098] Specific actions: Analyze the user's input and behavioral patterns, and if it determines that the user is under high stress, send an encouraging message such as, "It is important to take immediate action. Don't rush, just follow the instructions."

[1099] Step 9:

[1100] Users: Receive notifications and take action.

[1101] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[1102] Step 10:

[1103] User: Feedback the results and status of countermeasures to the server via the terminal.

[1104] Specific operation: The user inputs and sends feedback data through the application, such as "Isolation work completed, body temperature has returned to the normal range of 39°C." The user's emotions are also recorded when providing feedback.

[1105] Step 11:

[1106] Server: Stores the received feedback data in a database.

[1107] Specific operation: The user's emotional data is analyzed along with the feedback data and added to the database. The data is stored as new data and used to update the analysis model.

[1108] Step 12:

[1109] Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[1110] What happens: Retrain the AI ​​algorithms and sentiment engine with the new data collected to improve analysis accuracy. Deploy the new model and apply it to the next data analysis.

[1111] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[1112] Example 2

[1113] 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."

[1114] When an infectious disease such as avian influenza breaks out at an aquaculture farm, early detection and rapid countermeasures are required. While existing systems can detect some anomalies, they only notify users uniformly and are unable to respond to the individual circumstances and emotions of each user. This can lead to stress for users and delays in taking appropriate countermeasures. Furthermore, the system lacks a mechanism for utilizing feedback data to improve the accuracy of analysis.

[1115] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for analyzing user emotions and customizing the notification content; and means for collecting feedback data and emotion data from users and updating the AI ​​model. This enables early detection and rapid countermeasures for avian influenza, realizes notifications that take user emotions into consideration, and improves analysis accuracy by utilizing feedback data.

[1116] A "sensor" is a device that detects a specific physical quantity of an object and outputs it as an electrical signal.

[1117] "Data receiving means" refers to the function of the equipment or software that acquires and incorporates data transmitted from the sensor.

[1118] "Data preprocessing means" refers to a function that performs processing to convert raw data into a format that is easy to analyze, and specifically includes data normalization and filtering of outliers.

[1119] "Artificial intelligence" is a technology that allows computer systems to learn, reason, and recognize by imitating human intelligence, and is used in this invention to detect abnormal behavior and calculate risk scores.

[1120] The "abnormal behavior analysis means" is a function that uses preprocessed data to enable artificial intelligence to analyze abnormal behavior and changes in body temperature of chickens.

[1121] The "risk scoring means" is a function that quantifies the risk of abnormality based on the analysis results.

[1122] The "alert generation means" is a function that issues an alert and notifies the user when the risk score exceeds a set threshold.

[1123] The "prevention and countermeasure suggestion means" is a function that suggests specific countermeasures to the user against infectious diseases such as avian influenza based on the analysis results.

[1124] "Emotion analysis means" is a function that analyzes the user's emotions and generates and customizes appropriate notification content based on that information.

[1125] "Feedback collection means" is a function that acquires the results and status of measures implemented by users and incorporates them into the system.

[1126] "Model updating means" is a function that uses collected feedback data to improve and update the artificial intelligence model.

[1127] The present invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes for collecting and analyzing data from multiple sensors installed in aquaculture farms, calculating a risk score, and issuing alerts as necessary. Furthermore, the system is equipped with a function for improving the accuracy of the analysis based on user feedback and emotion data. A specific embodiment of this system is described below.

[1128] Data Collection and Transmission

[1129] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. These sensors record data periodically and send it to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second and sends the data to the server every minute.

[1130] Data Preprocessing

[1131] The server preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. For example, it removes noise from the acquired temperature data and divides and labels the behavioral data into frames.

[1132] Data analysis

[1133] The server uses pre-processed data and an artificial intelligence algorithm to analyze abnormal behavior and changes in body temperature and calculate a risk score. Abnormal behavior is determined by comparing it with past data. For example, if the AI ​​model detects a temperature of 38.2°C and abnormal behavior (immobility), it will calculate a risk score of 80.

[1134] Alert notifications and countermeasure suggestions

[1135] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It also sends a notification suggesting specific preventative measures along with the alert. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." At the same time, the system suggests measures such as "Isolate the chickens and begin antiviral treatment."

[1136] Sentiment analysis and notification customization

[1137] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. For example, if the server analyzes the user's input and behavioral patterns and determines that they are under high stress, it will send an encouraging message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[1138] Gathering feedback and updating machine learning models

[1139] The user receives the notification, takes action, and then sends feedback about the results and situation to the server via their device. For example, the user may quickly quarantine the chickens in accordance with the notification and implement the specified antiviral measures. As a result, feedback data such as "Isolation completed, body temperature has returned to the normal range of 39°C" is sent. The user's emotions are also recorded when providing feedback.

[1140] The server updates the AI ​​model and emotion engine based on the received feedback data and emotion data, for example, by retraining the AI ​​algorithm and emotion engine using the new data collected to improve the accuracy of the analysis, and then deploys the new model to be reflected in the next data analysis.

[1141] Prompt Sentence Examples

[1142] Here are some example prompts to input to a generative AI model:

[1143] "The system uses various sensors installed in the farm to monitor the health of chickens in real time, detects abnormalities early and calculates a risk score. It then sends appropriate alerts and measures. It also analyzes user sentiment and customizes the notification content. Feedback data is used to update the model and improve the accuracy of the analysis."

[1144] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1145] Step 1: Data collection

[1146] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. As input, it takes raw data from each sensor and records it at regular intervals. For example, the temperature sensor measures chicken body temperature every 10 minutes, and the camera records chicken behavior every second. As output, it buffers the collected data and prepares it to be sent to the server.

[1147] Step 2: Send data

[1148] The device sends the collected data to the server at a specified interval. As input, it uses the sensor data buffered on the device and uploads this data to the server as output. For example, the collected temperature data or video data can be sent to the server every minute.

[1149] Step 3: Data Preprocessing

[1150] The server preprocesses the received sensor data. It receives raw data sent from the device as input and generates preprocessed data suitable for analysis as output. This preprocessing includes data normalization, outlier filtering, and noise removal. For example, it removes noise from the obtained temperature data and segments and labels the behavioral data by frame.

[1151] Step 4: Data analysis

[1152] The server uses an artificial intelligence algorithm to analyze the preprocessed data. It uses the preprocessed data as input and analyzes abnormal behavior and changes in body temperature as output to calculate a risk score. For example, an AI model detects a temperature of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1153] Step 5: Alert Generation

[1154] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It uses the risk score as input and generates an alert message as output. For example, if the risk score exceeds 50, an alert message stating "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures" is sent to the administrator's smartphone.

[1155] Step 6: Propose a solution

[1156] The server sends a notification to the user along with the alert, suggesting specific prevention and countermeasures. It uses the risk score and analysis results as input and generates a message suggesting countermeasures as output. For example, it suggests countermeasures such as "Isolate the chickens and start antiviral treatment."

[1157] Step 7: Sentiment Analysis and Notification Customization

[1158] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. It uses the user's feedback and operation history as input and generates a customized notification message as output. For example, if it determines that the user is under high stress, it sends a message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[1159] Step 8: Gather feedback

[1160] The user implements the measures and sends the results and status as feedback to the server. The user inputs the results of their actions as input, and this data is sent to the server as output. For example, feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is sent.

[1161] Step 9: Update the model

[1162] The server uses the received feedback data and emotion data to update the artificial intelligence model and emotion engine. It uses the newly collected data as input and generates an updated model as output. For example, it uses the collected new data to retrain the AI ​​algorithm and emotion engine to improve the accuracy of analysis. It then deploys the new model and applies it to the next data analysis.

[1163] In this way, the system will enable early detection of avian influenza and rapid countermeasures, providing effective support to users.

[1164] (Application example 2)

[1165] 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."

[1166] Conventional systems have been unable to detect abnormalities early or implement sufficient preventative measures at aquaculture farms and manufacturing facilities, making it difficult to respond quickly when an abnormality occurs. Furthermore, conventional anomaly detection systems do not customize notification content based on feedback or user sentiment, and therefore do not provide sufficient support for implementing optimal measures.

[1167] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm or manufacturing facility; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature and equipment operating status using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for collecting feedback data from users and updating the AI ​​model; and means for the AI ​​to analyze the user's emotions and customize the content of the notification. This enables early detection of abnormalities and rapid response, and can propose optimal countermeasures based on the user's emotions.

[1168] An "aquaculture farm" is a facility for raising and managing living organisms such as poultry and fish.

[1169] A "manufacturing facility" is a location such as a factory or workshop where products are produced or assembled.

[1170] A "sensor" is a device that detects environmental data such as temperature, humidity, vibration, and images, as well as operational data, and outputs it as a signal.

[1171] The "means for receiving data" refers to a method or device for inputting data transmitted from a sensor into a server or computer.

[1172] "Means for preprocessing data and converting it into a format suitable for analysis" refers to a method or device that processes received data into an analyzable state by removing noise, normalizing, labeling, etc.

[1173] "Artificial intelligence" refers to algorithms and software that analyze received data and evaluate abnormal behavior, changes in body temperature, and the operating status of equipment.

[1174] A "means for scoring risk" is a method or device that expresses the degree of abnormality or risk as a number based on the results of analysis using artificial intelligence.

[1175] "Means for generating and notifying alerts" refers to a method or device for generating and notifying a user of a warning based on a risk score that exceeds a set threshold.

[1176] The "means for proposing prevention and countermeasures" is a method or device that presents specific prevention measures and countermeasures to the user based on the risk score.

[1177] "Means for collecting feedback data from users" refers to a method or device for incorporating response results and status reports from users into the system.

[1178] "Means for updating artificial intelligence models" refers to methods or devices that improve the accuracy of analytical algorithms or learn new models based on collected feedback data.

[1179] The "means for analyzing emotions and customizing notification content" refers to a method or device that determines emotions from user input and behavioral data and adjusts notification messages to match that emotional state.

[1180] The present invention provides a system for detecting abnormalities in manufacturing facilities and proposing countermeasures based on a system for early detection of avian influenza and implementing preventive measures in real time. This system is implemented in the following manner and configuration.

[1181] First, temperature, humidity, and vibration sensors, as well as cameras, are installed within the manufacturing facility to periodically measure environmental data and the operating status of the equipment and send the data to a server.

[1182] The server receives temperature, humidity, vibration, and image data and preprocesses them. This includes noise removal, data normalization, and frame-by-frame image labeling. The preprocessed data is then analyzed by an artificial intelligence algorithm to quantify abnormal behavior and equipment operating conditions as a risk score.

[1183] If the risk score exceeds a certain threshold, the server generates an alert and sends it to the administrator's smartphone or head-mounted display. The alert suggests specific preventive and countermeasure measures, such as, "The temperature of the refrigerator has exceeded the set range. Please immediately check the site and request repairs."

[1184] The server collects feedback data from users and updates the AI ​​model based on this data. This feedback includes the results of countermeasure implementation and status reports, and also analyzes the user's emotional data. By customizing the notification content according to the user's emotions, the system helps users implement countermeasures without feeling stressed.

[1185] For example, if it determines that a user is in a high stress state, it will send an encouraging message such as, "It is important to take action immediately. Please do not rush and follow the instructions." This function is realized by analyzing the user's input and behavioral patterns using an emotion engine.

[1186] A specific scenario is shown below.

[1187] If the temperature in a freezer warehouse at a manufacturing facility becomes abnormally high, a temperature sensor collects data and sends it to a server. The server removes noise from this data, and an AI model analyzes it. If the risk score exceeds a threshold, the server generates an alert and sends a message to the manager's smartphone saying, "The freezer temperature has exceeded the set range. Please check the site immediately and request repairs." The manager receives this notification and immediately takes action. Feedback is then sent to the server, stating, "Repair work completed, temperature has returned to normal range," along with the user's emotional data. The server updates the AI ​​model based on this data.

[1188] An example of a prompt to use for the generative AI model is as follows:

[1189] "Analyze the following data set and predict the anomaly risk score for this production line.

[1190] Datasets: Temperature data, humidity data, vibration data, image data

[1191] Time range: 30 minutes

[1192] Output: Anomaly risk score, specific explanation of the anomaly cause

[1193] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1194] Step 1:

[1195] Sensors collect data such as temperature, humidity, vibration, and images.

[1196] Specifically, the temperature sensor acquires temperature data every 10 minutes, the humidity sensor acquires humidity data every 15 minutes, the vibration sensor acquires vibration data every 5 seconds, and the camera captures images every second. These data are periodically sent to the server.

[1197] Input: Environmental and image data from sensors.

[1198] Output: The raw data sent to the server.

[1199] Step 2:

[1200] The server receives the data sent from the sensor.

[1201] Specifically, the server periodically monitors data from each sensor and receives the data via HTTP requests.

[1202] Input: Raw data sent from the sensor.

[1203] Output: Raw data stored on the server.

[1204] Step 3:

[1205] The server preprocesses the data received.

[1206] Specifically, the process involves noise removal, normalization, and then dividing and labeling the image data by frame.

[1207] Input: Raw data stored in the server.

[1208] Output: Preprocessed data.

[1209] Step 4:

[1210] The server uses the pre-processed data to perform analysis using an AI model.

[1211] Specifically, an artificial intelligence algorithm analyzes pre-processed data, detects abnormal behavior, body temperature, and changes in equipment operating status, and scores the risk.

[1212] Input: Preprocessed data.

[1213] Output: Risk score and analysis results.

[1214] Step 5:

[1215] If the risk score exceeds a certain threshold, the server generates an alert and notifies you.

[1216] Specifically, the system monitors the risk score and, if it exceeds a threshold, sends an alert notification to the administrator's smartphone or head-mounted display.

[1217] Input: Risk score.

[1218] Output: Alert notification.

[1219] Step 6:

[1220] The server suggests prevention and countermeasures based on the risk score.

[1221] Specifically, the system refers to past response examples in a database, selects appropriate preventive measures and countermeasures, and includes them in the notification.

[1222] Inputs: Risk score and past case data.

[1223] Output: Notification of specific preventive measures and countermeasures.

[1224] Step 7:

[1225] The user receives the notification and sends the feedback data to the server.

[1226] Specifically, the user checks the notification via a smartphone or head-mounted display, enters the response results, and sends them.

[1227] Input: Countermeasure execution results and user feedback data.

[1228] Output: Feedback data sent to the server.

[1229] Step 8:

[1230] The server updates the artificial intelligence model based on the feedback data.

[1231] Specifically, the feedback data is analyzed, input into the AI ​​model as new data, and the model is retrained.

[1232] Input: Feedback data.

[1233] Output: The updated AI model.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] [Fourth embodiment]

[1238] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1239] 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.

[1240] 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).

[1241] 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.

[1242] 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.

[1243] 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).

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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."

[1251] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time. This system involves a series of processes that collect data from sensors installed in aquaculture farms, analyze the data, calculate a risk score, and issue an alert. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[1252] Data Collection and Transmission

[1253] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[1254] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[1255] Data Preprocessing and Analysis

[1256] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[1257] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[1258] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[1259] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1260] Alert notifications and countermeasure suggestions

[1261] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[1262] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1263] 5. Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[1264] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[1265] Feedback Collection and Machine Learning

[1266] 6. User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[1267] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[1268] 7. Server: The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[1269] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[1270] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[1271] The processing flow will be explained below.

[1272] Step 1:

[1273] Terminal: Various sensors (temperature sensors, humidity sensors, motion sensors) and cameras installed in the farm collect data.

[1274] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[1275] Step 2:

[1276] Terminal: Sends collected data to the server at regular intervals.

[1277] Specific operation: Temperature data, humidity data, and behavior data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[1278] Step 3:

[1279] Server: Checks the received data and stores it in a database.

[1280] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, a receipt confirmation response is sent to the terminal.

[1281] Step 4:

[1282] Server: Preprocesses the received data.

[1283] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[1284] Step 5:

[1285] Server: Analyzes the pre-processed data and calculates the risk score.

[1286] How it works: Using an AI algorithm, abnormal behavior (e.g., a chicken not moving) and abnormal body temperature are analyzed. This is compared with past learning data and a risk score is calculated, for example, as 80.

[1287] Step 6:

[1288] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[1289] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1290] Step 7:

[1291] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[1292] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[1293] Step 8:

[1294] Users: Receive notifications and take action.

[1295] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[1296] Step 9:

[1297] User: Feedback the results and status of countermeasures to the server via the terminal.

[1298] Specific operation: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application.

[1299] Step 10:

[1300] Server: Stores the received feedback data in a database.

[1301] Specific operation: The feedback data is analyzed and added to the database. It is stored as new data and used to update the analytical model.

[1302] Step 11:

[1303] Server: Updates the artificial intelligence model based on the feedback data.

[1304] What happens: The AI ​​algorithm is retrained using the new data collected to improve analysis accuracy, and the new model is deployed and applied to the next data analysis.

[1305] This system will enable early detection of avian influenza and preventative measures in real time.

[1306] Example 1

[1307] 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."

[1308] Conventional early detection and prevention measures for avian influenza at aquaculture farms rely on manual observation and incomplete data collection, making it difficult to make quick and accurate judgments. Furthermore, when abnormalities are discovered, response measures are often limited and inconsistent. This results in delayed detection of abnormalities and a high risk of infection spreading. Furthermore, the inability to effectively utilize collected data also delays improvements in the accuracy of future preventive measures.

[1309] 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.

[1310] In this invention, the server includes: means for periodically receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score; means for generating an alert and notifying the user when the risk score exceeds a set threshold; means for issuing the alert and suggesting specific prevention and countermeasures; and means for collecting feedback data from users and updating the AI ​​model to improve the accuracy of the analysis. This enables early detection of avian influenza and effective preventive measures, enables rapid response when abnormalities are discovered, and enables improved accuracy of future preventive measures.

[1311] A "farm" is a specially established environment for raising useful organisms such as livestock and fish.

[1312] A "sensor" is a device that detects changes in physical or chemical quantities and outputs them as an electrical signal.

[1313] "Data" refers to a record of information detected by the sensor, and specifically includes information such as temperature, humidity, movement, and video.

[1314] "Receiving" is the act of acquiring data transmitted from a remote location.

[1315] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis. Specifically, this includes data normalization and filtering of outliers.

[1316] "Artificial intelligence" refers to technologies and systems that learn from large amounts of data to solve specific tasks or problems.

[1317] "Abnormal behavior" refers to a behavioral pattern that deviates from normal, such as a sudden decrease in physical activity.

[1318] "Temperature changes" are when a chicken's body temperature rises or falls outside of its normal range.

[1319] A "risk score" is a numerical representation of the risk of an abnormality occurring, calculated from sensor data.

[1320] The "threshold" is the boundary value at which the risk score is judged to be abnormal from a normal state.

[1321] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[1322] "Prevention and control" refers to measures taken before or immediately after an abnormality occurs, and specifically includes quarantining chickens and antiviral treatment.

[1323] "Feedback data" is data that reports the results and status of a user's implementation of a measure.

[1324] "Model updating" means using feedback data to retrain the artificial intelligence algorithm and improve the accuracy of the analysis.

[1325] This invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing alerts. It also collects feedback data from users and updates the artificial intelligence model to improve the accuracy of the analysis.

[1326] First, we will explain the overall configuration of this system. The system consists of terminals installed in the farm, which consist of temperature sensors, humidity sensors, motion sensors, and cameras, and a server that processes and analyzes the received data. These devices communicate via the Internet to collect and analyze data.

[1327] Data collection

[1328] Terminal: Temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and sends the data to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second. The data is then sent to the server every minute.

[1329] Data Transfer

[1330] Terminal: Sends collected data to a server via a network. Data transfer can be real-time or periodically, allowing for rapid analysis. For example, data can be transferred to the server every minute via the farm's Wi-Fi network.

[1331] Data Preprocessing

[1332] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. It also removes noise from the obtained temperature data and divides and labels the behavioral data by frame.

[1333] Data analysis

[1334] Server: Using the preprocessed data, an AI algorithm analyzes abnormal behavior and changes in body temperature and generates a risk score. Abnormal behavior is judged by comparing it with past data and a risk score is calculated. As a specific example, the AI ​​model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1335] Alerting and Notification

[1336] Server: If the risk score exceeds a set threshold, an alert is generated and notified to the appropriate user. At this time, a message proposing specific prevention and countermeasures is also sent. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." In addition, a notification is sent suggesting countermeasures such as, "Isolate the chickens and begin antiviral treatment."

[1337] Gathering feedback and updating AI models

[1338] User: Implements countermeasures and reports the results and situation to the server as feedback via the device. For example, an administrator quarantines chickens and then reports through the app that their body temperature has returned to normal.

[1339] Server: The AI ​​model is updated using the collected feedback data. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. For example, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[1340] Prompt Sentence Examples

[1341] Examples of prompts to be input to a generative AI model include:

[1342] This question concerns the design of a system for early detection of abnormalities in chickens on a farm. The system uses temperature, humidity, and motion sensors, and cameras to collect data, which is then analyzed on a server. Please explain the names of the specific hardware and software, the data preprocessing method, the anomaly detection algorithm, the alert notification method, and the feedback collection process.

[1343] In this way, the present invention makes it possible to build a system that realizes early detection and preventive measures for avian influenza through the analysis of real-time data.

[1344] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1345] Step 1: Data collection

[1346] Terminal: Temperature, humidity, and motion sensors, as well as cameras, collect data on the chickens' body temperature, environment, and behavior. Each sensor periodically records data.

[1347] Specific operation: The temperature sensor measures the chicken's body temperature every 10 minutes, the humidity sensor measures the environmental humidity every 5 minutes, the movement sensor checks the chicken's movements every minute, and the camera records the chicken's behavior every second.

[1348] Input: Chicken body temperature, humidity, movement, behavioral video

[1349] Output: Collected data (body temperature data, humidity data, exercise data, video data)

[1350] Step 2: Data Transfer

[1351] Terminal: Sends collected data to the server in real time or periodically.

[1352] Specific operation: The collected data is transferred to the server every minute via the Wi-Fi network.

[1353] Input: Collected data (body temperature data, humidity data, exercise data, video data)

[1354] Output: Data sent to the server

[1355] Step 3: Data Preprocessing

[1356] Server: Preprocesses the received sensor data and converts it into a format suitable for analysis.

[1357] Specific operation: The server performs noise removal and outlier filtering on the received data. The video data is also divided into frames, and each frame is assigned an action label.

[1358] Input: Data sent to the server (body temperature data, humidity data, exercise data, video data)

[1359] Output: Preprocessed data (normalized data, filtered data, labeled video data)

[1360] Step 4: Data analysis

[1361] Server: Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature and calculates a risk score.

[1362] Specific operation: The AI ​​model compares data with past data, detects abnormal behavior and changes in body temperature, and calculates a risk score. For example, if the temperature data is 38.2°C and the person is "immobile," the model calculates a risk score of 80.

[1363] Input: Preprocessed data (normalized data, filtered data, labeled video data)

[1364] Output: Risk score

[1365] Step 5: Alerting and Notification

[1366] Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[1367] Specific operation: If the risk score exceeds 50, the server will send an alert message to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1368] Input: Risk Score

[1369] Output: Alert message

[1370] Step 6: Propose a solution

[1371] Server: Sends notifications with alerts and specific prevention and countermeasure suggestions.

[1372] Specific action: Along with the alert notification, a message containing a countermeasure suggestion to "quarantine the chickens and start antiviral treatment" will be sent to the administrator.

[1373] Input: Risk score, Alert message

[1374] Output: Measures proposed message

[1375] Step 7: Gather feedback

[1376] User: Implements countermeasures and reports the results and status to the server as feedback via the terminal.

[1377] Specific operations: After implementing the measures, the administrator uses a smartphone app to enter and send information such as "The chickens were isolated and their body temperatures subsequently returned to normal."

[1378] Input: Countermeasure results, status information

[1379] Output: Feedback data

[1380] Step 8: Update the AI ​​model

[1381] Server: Updates the artificial intelligence model using collected feedback data.

[1382] Specific operation: The server retrains the AI ​​model based on the newly acquired feedback data, further improving the accuracy of analysis.

[1383] Input: Feedback data

[1384] Output: Updated AI model

[1385] (Application example 1)

[1386] 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."

[1387] Conventional methods for early detection and prevention of avian influenza at aquaculture farms rely on data collection and analysis using sensors, but these methods pose challenges in terms of real-time monitoring and prompt notification to managers. Furthermore, there is a lack of a mechanism for updating the AI ​​model based on feedback, resulting in insufficient analysis accuracy. Therefore, a system that enables early detection of abnormal behavior and prompt countermeasures is needed.

[1388] 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.

[1389] In this invention, the server includes means for receiving data collected from sensors installed in the farm, means for preprocessing the received sensor data and converting it into a format suitable for analysis, means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and generate a risk score, means for generating and notifying an alert when the risk score exceeds a certain threshold, means for proposing prevention and countermeasures based on the risk score, means for collecting feedback data from users and updating the AI ​​model, and means for the farm manager to monitor the status of the chickens in real time. This enables real-time status monitoring and prompt notification, as well as improved analysis accuracy based on feedback.

[1390] An "aquaculture farm" is a facility for raising and managing animals such as livestock and farmed fish.

[1391] A "sensor" is a device for measuring variables in the external environment and collecting that data.

[1392] The "data receiving means" is a function for acquiring data transmitted from a sensor.

[1393] "Preprocessing" is the process of converting received data into a form suitable for analysis.

[1394] "Artificial intelligence" is a program that allows a computer to analyze data and detect abnormal behavior or changes in body temperature.

[1395] The "risk score" is an indicator of danger calculated based on abnormal behavior and changes in body temperature.

[1396] The "alert generation means" is a function for issuing a warning when the risk score exceeds a certain threshold.

[1397] "Notification means" is the process by which an administrator is notified of an alert.

[1398] "Preventive measures" are methods for suggesting disease prevention based on risk scores.

[1399] The "measure proposal means" is a function that proposes appropriate measures for problems that may occur.

[1400] A "feedback collection means" is a method for collecting behavioral results from users.

[1401] "Model updating" is the process of improving an artificial intelligence model based on collected feedback data.

[1402] "Real-time monitoring means" is a function that allows farm managers to instantly grasp the status of chickens.

[1403] This invention describes a system for early detection of avian influenza and real-time implementation of preventive measures. This system includes a function to collect and analyze data from sensors installed in aquaculture farms, calculate a risk score, and notify managers of appropriate alerts. In addition, the accuracy of the analysis can be improved by collecting feedback data from users and updating the generative AI model.

[1404] System configuration

[1405] Data Collection and Transmission

[1406] Device:

[1407] Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data from the chickens. Each sensor periodically records the data and transmits it to a server at regular intervals.

[1408] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[1409] Data Preprocessing and Analysis

[1410] server:

[1411] Preprocessing of received sensor data and conversion to a format suitable for analysis, specifically normalizing the data and filtering outliers.

[1412] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[1413] Using pre-processed data, an artificial intelligence algorithm analyzes abnormal behavior and changes in body temperature to generate a risk score. Abnormal behavior is judged by comparing it with past data and calculating a risk score.

[1414] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1415] Alert notifications and countermeasure suggestions

[1416] server:

[1417] If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[1418] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1419] Send notifications with alerts and specific prevention and action suggestions.

[1420] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[1421] Feedback Collection and Machine Learning

[1422] User:

[1423] Countermeasures are implemented and the results and status are reported as feedback to the server via the device.

[1424] Example: A manager isolates a chicken and then reports through the app that its temperature has returned to normal.

[1425] server:

[1426] The collected feedback data is used to update the AI ​​model, which further improves the accuracy of the analysis and makes the next anomaly detection more accurate.

[1427] Example: Retraining the AI ​​model based on newly acquired feedback data to improve the accuracy of risk scores.

[1428] Hardware and software used

[1429] Hardware: temperature sensor, humidity sensor, motion sensor, camera, smartphone

[1430] Software: denoising algorithms for data preprocessing, labeling algorithms, and AI models (e.g., models using machine learning libraries TensorFlow or PyTorch)

[1431] Prompt Sentence Examples

[1432] "Given the temperature readings and activity levels of the chickens, determine the risk score for bird flu infection. Consider higher temperatures and inactivity as higher risk."

[1433] This system allows farm managers to monitor for abnormal signs of avian influenza in real time and take prompt action, significantly reducing the risk of infection spreading.

[1434] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1435] Step 1: Data collection

[1436] The terminal collects data from temperature, humidity, and motion sensors and cameras installed in the farm. The input is raw data obtained from the sensors, which typically includes temperature, humidity, movement, and video data. This data is collected at regular intervals and prepared for transmission. The output is a dataset of various environmental conditions and behavioral data.

[1437] Step 2: Send data

[1438] The terminal sends the collected data to the server at regular intervals. The input is the data collected in the previous step. The data is sent to the server via the network. The output is the data received by the server.

[1439] Step 3: Data Preprocessing

[1440] The server converts the received data into a format suitable for analysis. Specifically, it performs noise removal and outlier filtering. The input is the transmitted sensor data, and the output is preprocessed and normalized data. For example, temperature data is normalized, and behavioral data is split into frames and labeled.

[1441] Step 4: Anomaly detection and risk scoring

[1442] The server uses the preprocessed data to analyze abnormal behavior and changes in body temperature using a generative AI model. It calculates a risk score and compares it with past data to determine abnormal behavior. The input is the preprocessed data, and the output is the calculated risk score. Specifically, it detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1443] Step 5: Alerting and Notification

[1444] The server generates an alert when the risk score exceeds a set threshold and notifies the appropriate user. The input is the risk score and a preset threshold, and the output is a notification message. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the individual immediately and take quarantine measures."

[1445] Step 6: Propose a solution

[1446] The server will then provide alerts and suggest specific preventive and countermeasure measures. The input is the risk score and past countermeasure data, and the output is a message proposing countermeasures. For example, the server might suggest countermeasures such as "Isolate the chickens and start antiviral treatment."

[1447] Step 7: Gather feedback

[1448] The user implements the measures and reports the results and situation as feedback to the server via their device. The input is data on the measures actually taken and their results, and the output is sent to the server as feedback data. Specifically, the manager quarantines the chickens and then reports through the app that their body temperature has returned to normal.

[1449] Step 8: Update the model

[1450] The server updates the generative AI model using the collected feedback data. The input is the feedback data, and the output is the updated AI model. This further improves the accuracy of the analysis and makes the next anomaly detection more accurate. Specifically, the AI ​​model is retrained based on the newly acquired feedback data to improve the accuracy of risk score calculation.

[1451] 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.

[1452] The present invention is a system for early detection of avian influenza and implementing preventive measures in real time, and includes an emotion engine that recognizes user emotions. This system involves a series of processes: collecting data from sensors installed in aquaculture farms, analyzing the data, calculating a risk score, and issuing an alert. Furthermore, emotion data based on user feedback is collected and the artificial intelligence model is updated to improve the accuracy of the analysis. A specific embodiment of this system is described below.

[1453] Data Collection and Transmission

[1454] 1. Terminal: Temperature, humidity, and motion sensors, as well as cameras, are installed in the farm to collect chicken body temperature, environmental data, and behavioral data. Each sensor records data periodically and transmits the data to the server at regular intervals.

[1455] Example: A temperature sensor measures the chicken's body temperature every 10 minutes, a camera records the chicken's behavior every second, and sends the data to a server every minute.

[1456] Data Preprocessing and Analysis

[1457] 2. Server: Preprocesses the received sensor data and converts it into a format suitable for analysis, specifically normalizing the data and filtering outliers.

[1458] Example: Noise is removed from the obtained temperature data, and behavioral data is divided into frames and labeled.

[1459] 3. Server: Using the pre-processed data, an AI algorithm analyzes abnormal behavior and changes in body temperature, and generates a risk score. Abnormal behavior is judged by comparing it with past data, and a risk score is calculated.

[1460] Example: An AI model detects temperature data of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1461] Alert notifications and countermeasure suggestions

[1462] 4. Server: If the risk score exceeds a set threshold, an alert is generated and notifies the appropriate users.

[1463] Example: If the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1464] 5. Server: Sends notifications along with alerts and suggests specific preventive and countermeasure measures.

[1465] Example: Suggested measures include "Isolate the chickens and start antiviral treatment."

[1466] 6. Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[1467] Example: If the user's input and behavioral patterns are analyzed and it is determined that they are under high stress, an encouraging message such as "It is important to take immediate action. Please do not rush and follow the instructions" will be sent.

[1468] Feedback Collection and Machine Learning

[1469] 7. User: Receive notification and take action.

[1470] Example: Following the notification, promptly isolate the chickens and implement the specified antiviral measures. After implementing the measures, observe the results.

[1471] 8. User: Feedback the results and status of countermeasures to the server via the terminal.

[1472] Example: Feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is input and sent through the application. The user's emotions are also recorded when giving feedback.

[1473] 9. Server: Stores the received feedback data in a database.

[1474] Example: Analyze user emotion data along with feedback data and add it to the database. Store it as new data and use it to update the analysis model.

[1475] 10. Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[1476] Example: Retraining artificial intelligence algorithms and sentiment engines with new data collected to improve analysis accuracy. Deploying new models to reflect the next data analysis.

[1477] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[1478] The processing flow will be explained below.

[1479] Step 1:

[1480] Terminals: Temperature, humidity, and motion sensors, as well as cameras installed in the farm, collect body temperature, environmental, and behavioral data of the chickens.

[1481] How it works: Temperature sensors measure the chickens' body temperatures every 10 minutes, humidity sensors continuously monitor the humidity of the environment, and motion sensors and cameras monitor the chickens' behavior, collecting data every second.

[1482] Step 2:

[1483] Terminal: Sends collected data to the server at regular intervals.

[1484] Specific operation: Temperature data, humidity data, and behavior data are uploaded to the server in batches every minute. The data is sent over the network, enabling real-time analysis on the server.

[1485] Step 3:

[1486] Server: Checks the received data and stores it in a database.

[1487] Specific operation: Analyzes data received in JSON format, splits it into appropriate fields, and stores it in the database. To maintain data integrity, a receipt confirmation response is sent to the terminal.

[1488] Step 4:

[1489] Server: Preprocesses the received data.

[1490] Specific operations: Perform data cleansing such as noise removal and data smoothing. For example, filter spikes in temperature data and label behavioral data frame by frame.

[1491] Step 5:

[1492] Server: Analyzes the pre-processed data and calculates the risk score.

[1493] How it works: Using an AI algorithm, abnormal behavior (e.g., a chicken not moving) and abnormal body temperature are analyzed. This is compared with past learning data and a risk score is calculated, for example, as 80.

[1494] Step 6:

[1495] Server: Generates an alert when the risk score exceeds the set threshold and notifies the appropriate user device.

[1496] Specific operation: If the risk score exceeds 50, an alert is generated and a notification is pushed to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures."

[1497] Step 7:

[1498] Server: Sends notification messages along with alerts, suggesting preventative and countermeasure measures.

[1499] Specific action: Send a message to the user's device containing specific instructions for preventive measures, such as "Isolate the chickens and start antiviral treatment."

[1500] Step 8:

[1501] Server: The emotion engine analyzes the user's emotions and customizes the notification content based on the results.

[1502] Specific actions: Analyze the user's input and behavioral patterns, and if it determines that the user is under high stress, send an encouraging message such as, "It is important to take immediate action. Don't rush, just follow the instructions."

[1503] Step 9:

[1504] Users: Receive notifications and take action.

[1505] Specific actions: Promptly quarantine the chickens in accordance with the notice, implement the designated antiviral measures, and observe the results after implementing the measures.

[1506] Step 10:

[1507] User: Feedback the results and status of countermeasures to the server via the terminal.

[1508] Specific operation: The user inputs and sends feedback data through the application, such as "Isolation work completed, body temperature has returned to the normal range of 39°C." The user's emotions are also recorded when providing feedback.

[1509] Step 11:

[1510] Server: Stores the received feedback data in a database.

[1511] Specific operation: The user's emotional data is analyzed along with the feedback data and added to the database. The data is stored as new data and used to update the analysis model.

[1512] Step 12:

[1513] Server: Updates the artificial intelligence model and emotion engine based on feedback data and emotion data.

[1514] What happens: Retrain the AI ​​algorithms and sentiment engine with the new data collected to improve analysis accuracy. Deploy the new model and apply it to the next data analysis.

[1515] In this way, this system enables early detection and prevention of avian influenza in real time, and by providing notifications based on the user's emotions, it supports the implementation of more effective countermeasures.

[1516] Example 2

[1517] 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."

[1518] When an infectious disease such as avian influenza breaks out at an aquaculture farm, early detection and rapid countermeasures are required. While existing systems can detect some anomalies, they only notify users uniformly and are unable to respond to the individual circumstances and emotions of each user. This can lead to stress for users and delays in taking appropriate countermeasures. Furthermore, the system lacks a mechanism for utilizing feedback data to improve the accuracy of analysis.

[1519] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an AI to analyze abnormal behavior and changes in body temperature using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for analyzing user emotions and customizing the notification content; and means for collecting feedback data and emotion data from users and updating the AI ​​model. This enables early detection and rapid countermeasures for avian influenza, realizes notifications that take user emotions into consideration, and improves analysis accuracy by utilizing feedback data.

[1520] A "sensor" is a device that detects a specific physical quantity of an object and outputs it as an electrical signal.

[1521] "Data receiving means" refers to the function of the equipment or software that acquires and incorporates data transmitted from the sensor.

[1522] "Data preprocessing means" refers to a function that performs processing to convert raw data into a format that is easy to analyze, and specifically includes data normalization and filtering of outliers.

[1523] "Artificial intelligence" is a technology that allows computer systems to learn, reason, and recognize by imitating human intelligence, and is used in this invention to detect abnormal behavior and calculate risk scores.

[1524] The "abnormal behavior analysis means" is a function that uses preprocessed data to enable artificial intelligence to analyze abnormal behavior and changes in body temperature of chickens.

[1525] The "risk scoring means" is a function that quantifies the risk of abnormality based on the analysis results.

[1526] The "alert generation means" is a function that issues an alert and notifies the user when the risk score exceeds a set threshold.

[1527] The "prevention and countermeasure suggestion means" is a function that suggests specific countermeasures to the user against infectious diseases such as avian influenza based on the analysis results.

[1528] "Emotion analysis means" is a function that analyzes the user's emotions and generates and customizes appropriate notification content based on that information.

[1529] "Feedback collection means" is a function that acquires the results and status of measures implemented by users and incorporates them into the system.

[1530] "Model updating means" is a function that uses collected feedback data to improve and update the artificial intelligence model.

[1531] The present invention is a system for early detection of avian influenza and for implementing preventive measures in real time. This system involves a series of processes for collecting and analyzing data from multiple sensors installed in aquaculture farms, calculating a risk score, and issuing alerts as necessary. Furthermore, the system is equipped with a function for improving the accuracy of the analysis based on user feedback and emotion data. A specific embodiment of this system is described below.

[1532] Data Collection and Transmission

[1533] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. These sensors record data periodically and send it to the server at regular intervals. For example, the temperature sensor measures the chicken's body temperature every 10 minutes, and the camera records the chicken's behavior every second and sends the data to the server every minute.

[1534] Data Preprocessing

[1535] The server preprocesses the received sensor data and converts it into a format suitable for analysis. Specifically, it normalizes the data and filters out outliers. For example, it removes noise from the acquired temperature data and divides and labels the behavioral data into frames.

[1536] Data analysis

[1537] The server uses pre-processed data and an artificial intelligence algorithm to analyze abnormal behavior and changes in body temperature and calculate a risk score. Abnormal behavior is determined by comparing it with past data. For example, if the AI ​​model detects a temperature of 38.2°C and abnormal behavior (immobility), it will calculate a risk score of 80.

[1538] Alert notifications and countermeasure suggestions

[1539] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It also sends a notification suggesting specific preventative measures along with the alert. For example, if the risk score exceeds 50, an alert message is sent to the administrator's smartphone stating, "Abnormal behavior and high body temperature have been observed. Isolate the chickens immediately and take quarantine measures." At the same time, the system suggests measures such as "Isolate the chickens and begin antiviral treatment."

[1540] Sentiment analysis and notification customization

[1541] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. For example, if the server analyzes the user's input and behavioral patterns and determines that they are under high stress, it will send an encouraging message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[1542] Gathering feedback and updating machine learning models

[1543] The user receives the notification, takes action, and then sends feedback about the results and situation to the server via their device. For example, the user may quickly quarantine the chickens in accordance with the notification and implement the specified antiviral measures. As a result, feedback data such as "Isolation completed, body temperature has returned to the normal range of 39°C" is sent. The user's emotions are also recorded when providing feedback.

[1544] The server updates the AI ​​model and emotion engine based on the received feedback data and emotion data, for example, by retraining the AI ​​algorithm and emotion engine using the new data collected to improve the accuracy of the analysis, and then deploys the new model to be reflected in the next data analysis.

[1545] Prompt Sentence Examples

[1546] Here are some example prompts to input to a generative AI model:

[1547] "The system uses various sensors installed in the farm to monitor the health of chickens in real time, detects abnormalities early and calculates a risk score. It then sends appropriate alerts and measures. It also analyzes user sentiment and customizes the notification content. Feedback data is used to update the model and improve the accuracy of the analysis."

[1548] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1549] Step 1: Data collection

[1550] The terminal collects chicken body temperature, environmental data, and behavioral data using temperature sensors, humidity sensors, motion sensors, and cameras installed in the farm. As input, it takes raw data from each sensor and records it at regular intervals. For example, the temperature sensor measures chicken body temperature every 10 minutes, and the camera records chicken behavior every second. As output, it buffers the collected data and prepares it to be sent to the server.

[1551] Step 2: Send data

[1552] The device sends the collected data to the server at a specified interval. As input, it uses the sensor data buffered on the device and uploads this data to the server as output. For example, the collected temperature data or video data can be sent to the server every minute.

[1553] Step 3: Data Preprocessing

[1554] The server preprocesses the received sensor data. It receives raw data sent from the device as input and generates preprocessed data suitable for analysis as output. This preprocessing includes data normalization, outlier filtering, and noise removal. For example, it removes noise from the obtained temperature data and segments and labels the behavioral data by frame.

[1555] Step 4: Data analysis

[1556] The server uses an artificial intelligence algorithm to analyze the preprocessed data. It uses the preprocessed data as input and analyzes abnormal behavior and changes in body temperature as output to calculate a risk score. For example, an AI model detects a temperature of 38.2°C and abnormal behavior (immobility) and calculates a risk score of 80.

[1557] Step 5: Alert Generation

[1558] If the risk score exceeds a set threshold, the server generates an alert and notifies the appropriate user. It uses the risk score as input and generates an alert message as output. For example, if the risk score exceeds 50, an alert message stating "Abnormal behavior and high body temperature have been observed. Isolate the person immediately and take quarantine measures" is sent to the administrator's smartphone.

[1559] Step 6: Propose a solution

[1560] The server sends a notification to the user along with the alert, suggesting specific prevention and countermeasures. It uses the risk score and analysis results as input and generates a message suggesting countermeasures as output. For example, it suggests countermeasures such as "Isolate the chickens and start antiviral treatment."

[1561] Step 7: Sentiment Analysis and Notification Customization

[1562] The server's emotion engine analyzes the user's emotions and customizes the notification content based on the results. It uses the user's feedback and operation history as input and generates a customized notification message as output. For example, if it determines that the user is under high stress, it sends a message such as, "It is important to take immediate action. Please do not rush and follow the instructions."

[1563] Step 8: Gather feedback

[1564] The user implements the measures and sends the results and status as feedback to the server. The user inputs the results of their actions as input, and this data is sent to the server as output. For example, feedback data such as "Isolation work completed, body temperature has returned to the normal range of 39°C" is sent.

[1565] Step 9: Update the model

[1566] The server uses the received feedback data and emotion data to update the artificial intelligence model and emotion engine. It uses the newly collected data as input and generates an updated model as output. For example, it uses the collected new data to retrain the AI ​​algorithm and emotion engine to improve the accuracy of analysis. It then deploys the new model and applies it to the next data analysis.

[1567] In this way, the system will enable early detection of avian influenza and rapid countermeasures, providing effective support to users.

[1568] (Application example 2)

[1569] 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."

[1570] Conventional systems have been unable to detect abnormalities early or implement sufficient preventative measures at aquaculture farms and manufacturing facilities, making it difficult to respond quickly when an abnormality occurs. Furthermore, conventional anomaly detection systems do not customize notification content based on feedback or user sentiment, and therefore do not provide sufficient support for implementing optimal measures.

[1571] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving data collected from sensors installed in the aquaculture farm or manufacturing facility; means for preprocessing the received sensor data and converting it into a format suitable for analysis; means for an artificial intelligence (AI) to analyze abnormal behavior and changes in body temperature and equipment operating status using the preprocessed data and score the risk; means for generating and notifying an alert when the risk score exceeds a certain threshold; means for proposing prevention and countermeasures based on the risk score; means for collecting feedback data from users and updating the AI ​​model; and means for the AI ​​to analyze the user's emotions and customize the content of the notification. This enables early detection of abnormalities and rapid response, and can propose optimal countermeasures based on the user's emotions.

[1572] An "aquaculture farm" is a facility for raising and managing living organisms such as poultry and fish.

[1573] A "manufacturing facility" is a location such as a factory or workshop where products are produced or assembled.

[1574] A "sensor" is a device that detects environmental data such as temperature, humidity, vibration, and images, as well as operational data, and outputs it as a signal.

[1575] The "means for receiving data" refers to a method or device for inputting data transmitted from a sensor into a server or computer.

[1576] "Means for preprocessing data and converting it into a format suitable for analysis" refers to a method or device that processes received data into an analyzable state by removing noise, normalizing, labeling, etc.

[1577] "Artificial intelligence" refers to algorithms and software that analyze received data and evaluate abnormal behavior, changes in body temperature, and the operating status of equipment.

[1578] A "means for scoring risk" is a method or device that expresses the degree of abnormality or risk as a number based on the results of analysis using artificial intelligence.

[1579] "Means for generating and notifying alerts" refers to a method or device for generating and notifying a user of a warning based on a risk score that exceeds a set threshold.

[1580] The "means for proposing prevention and countermeasures" is a method or device that presents specific prevention measures and countermeasures to the user based on the risk score.

[1581] "Means for collecting feedback data from users" refers to a method or device for incorporating response results and status reports from users into the system.

[1582] "Means for updating artificial intelligence models" refers to methods or devices that improve the accuracy of analytical algorithms or learn new models based on collected feedback data.

[1583] The "means for analyzing emotions and customizing notification content" refers to a method or device that determines emotions from user input and behavioral data and adjusts notification messages to match that emotional state.

[1584] The present invention provides a system for detecting abnormalities in manufacturing facilities and proposing countermeasures based on a system for early detection of avian influenza and implementing preventive measures in real time. This system is implemented in the following manner and configuration.

[1585] First, temperature, humidity, and vibration sensors, as well as cameras, are installed within the manufacturing facility to periodically measure environmental data and the operating status of the equipment and send the data to a server.

[1586] The server receives temperature, humidity, vibration, and image data and preprocesses them. This includes noise removal, data normalization, and frame-by-frame image labeling. The preprocessed data is then analyzed by an artificial intelligence algorithm to quantify abnormal behavior and equipment operating conditions as a risk score.

[1587] If the risk score exceeds a certain threshold, the server generates an alert and sends it to the administrator's smartphone or head-mounted display. The alert suggests specific preventive and countermeasure measures, such as, "The temperature of the refrigerator has exceeded the set range. Please immediately check the site and request repairs."

[1588] The server collects feedback data from users and updates the AI ​​model based on this data. This feedback includes the results of countermeasure implementation and status reports, and also analyzes the user's emotional data. By customizing the notification content according to the user's emotions, the system helps users implement countermeasures without feeling stressed.

[1589] For example, if it determines that a user is in a high stress state, it will send an encouraging message such as, "It is important to take action immediately. Please do not rush and follow the instructions." This function is realized by analyzing the user's input and behavioral patterns using an emotion engine.

[1590] A specific scenario is shown below.

[1591] If the temperature in a freezer warehouse at a manufacturing facility becomes abnormally high, a temperature sensor collects data and sends it to a server. The server removes noise from this data, and an AI model analyzes it. If the risk score exceeds a threshold, the server generates an alert and sends a message to the manager's smartphone saying, "The freezer temperature has exceeded the set range. Please check the site immediately and request repairs." The manager receives this notification and immediately takes action. Feedback is then sent to the server, stating, "Repair work completed, temperature has returned to normal range," along with the user's emotional data. The server updates the AI ​​model based on this data.

[1592] An example of a prompt to use for the generative AI model is as follows:

[1593] "Analyze the following data set and predict the anomaly risk score for this production line.

[1594] Datasets: Temperature data, humidity data, vibration data, image data

[1595] Time range: 30 minutes

[1596] Output: Anomaly risk score, specific explanation of the anomaly cause

[1597] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1598] Step 1:

[1599] Sensors collect data such as temperature, humidity, vibration, and images.

[1600] Specifically, the temperature sensor acquires temperature data every 10 minutes, the humidity sensor acquires humidity data every 15 minutes, the vibration sensor acquires vibration data every 5 seconds, and the camera captures images every second. These data are periodically sent to the server.

[1601] Input: Environmental and image data from sensors.

[1602] Output: The raw data sent to the server.

[1603] Step 2:

[1604] The server receives the data sent from the sensor.

[1605] Specifically, the server periodically monitors data from each sensor and receives the data via HTTP requests.

[1606] Input: Raw data sent from the sensor.

[1607] Output: Raw data stored on the server.

[1608] Step 3:

[1609] The server preprocesses the data received.

[1610] Specifically, the process involves noise removal, normalization, and then dividing and labeling the image data by frame.

[1611] Input: Raw data stored in the server.

[1612] Output: Preprocessed data.

[1613] Step 4:

[1614] The server uses the pre-processed data to perform analysis using an AI model.

[1615] Specifically, an artificial intelligence algorithm analyzes pre-processed data, detects abnormal behavior, body temperature, and changes in equipment operating status, and scores the risk.

[1616] Input: Preprocessed data.

[1617] Output: Risk score and analysis results.

[1618] Step 5:

[1619] If the risk score exceeds a certain threshold, the server generates an alert and notifies you.

[1620] Specifically, the system monitors the risk score and, if it exceeds a threshold, sends an alert notification to the administrator's smartphone or head-mounted display.

[1621] Input: Risk score.

[1622] Output: Alert notification.

[1623] Step 6:

[1624] The server suggests prevention and countermeasures based on the risk score.

[1625] Specifically, the system refers to past response examples in a database, selects appropriate preventive measures and countermeasures, and includes them in the notification.

[1626] Inputs: Risk score and past case data.

[1627] Output: Notification of specific preventive measures and countermeasures.

[1628] Step 7:

[1629] The user receives the notification and sends the feedback data to the server.

[1630] Specifically, the user checks the notification via a smartphone or head-mounted display, enters the response results, and sends them.

[1631] Input: Countermeasure execution results and user feedback data.

[1632] Output: Feedback data sent to the server.

[1633] Step 8:

[1634] The server updates the artificial intelligence model based on the feedback data.

[1635] Specifically, the feedback data is analyzed, input into the AI ​​model as new data, and the model is retrained.

[1636] Input: Feedback data.

[1637] Output: The updated AI model.

[1638] 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.

[1639] 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.

[1640] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1641] 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.

[1642] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1643] 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.

[1644] 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).

[1645] 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.

[1646] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1647] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1648] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1649] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1650] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1651] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1652] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1653] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1654] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1655] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1656] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1657] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1658] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1659] The following is further disclosed regarding the above embodiment.

[1660] (Claim 1)

[1661] means for receiving data collected from sensors installed in the aquaculture facility;

[1662] A means of preprocessing the received sensor data and converting it into a format suitable for analysis;

[1663] Using the pre-processed data, an artificial intelligence analyzes abnormal behavior and changes in body temperature and scores the risk;

[1664] A means for generating and notifying alerts when the risk score exceeds a certain threshold;

[1665] A means of suggesting prevention and countermeasures based on risk scores;

[1666] a means for collecting feedback data from users and updating the artificial intelligence model;

[1667] A system including:

[1668] (Claim 2)

[1669] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalous behavior.

[1670] (Claim 3)

[1671] 10. The system of claim 1, further comprising means for aggregating data collected from multiple farms and analyzing and predicting the overall situation.

[1672] "Example 1"

[1673] (Claim 1)

[1674] a means for periodically receiving data collected from sensors installed in the farm;

[1675] A means of preprocessing the received sensor data and converting it into a format suitable for analysis;

[1676] Using the pre-processed data, an artificial intelligence analyzes abnormal behavior and changes in body temperature and scores the risk;

[1677] A means for generating an alert and notifying a user when the risk score exceeds a set threshold;

[1678] A means of suggesting specific prevention and countermeasures along with alerts;

[1679] A means for collecting feedback data from users and updating the AI ​​model to improve the accuracy of the analysis;

[1680] A system including:

[1681] (Claim 2)

[1682] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect abnormal behavior and changes in body temperature.

[1683] (Claim 3)

[1684] 10. The system of claim 1, further comprising means for aggregating data collected from multiple farms and analyzing and predicting the overall situation.

[1685] "Application Example 1"

[1686] (Claim 1)

[1687] means for receiving data collected from sensors installed in the aquaculture facility;

[1688] A means of preprocessing the received sensor data and converting it into a format suitable for analysis;

[1689] Using the pre-processed data, an artificial intelligence analyzes abnormal behavior and changes in body temperature and scores the risk;

[1690] A means for generating and notifying alerts when the risk score exceeds a certain threshold;

[1691] A means of suggesting prevention and countermeasures based on risk scores;

[1692] a means for collecting feedback data from users and updating the artificial intelligence model;

[1693] A means for farm managers to monitor the status of their chickens in real time, and

[1694] A system including:

[1695] (Claim 2)

[1696] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalous behavior.

[1697] (Claim 3)

[1698] 10. The system of claim 1, further comprising means for aggregating data collected from multiple farms and analyzing and predicting the overall situation.

[1699] "Example 2: Combining Emotion Engines"

[1700] (Claim 1)

[1701] means for receiving data collected from sensors installed in the aquaculture facility;

[1702] A means of preprocessing the received sensor data and converting it into a format suitable for analysis;

[1703] Using the pre-processed data, an artificial intelligence analyzes abnormal behavior and changes in body temperature and scores the risk;

[1704] A means for generating and notifying alerts when the risk score exceeds a certain threshold;

[1705] A means of suggesting prevention and countermeasures based on risk scores;

[1706] A means to analyze user sentiment and customize notification content;

[1707] a means for collecting feedback data and emotion data from users and updating an artificial intelligence model;

[1708] A system including:

[1709] (Claim 2)

[1710] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalous behavior.

[1711] (Claim 3)

[1712] 10. The system of claim 1, further comprising means for aggregating data collected from multiple farms and analyzing and predicting the overall situation.

[1713] "Application example 2 when combining emotion engines"

[1714] The claims have been revised as follows:

[1715] (Claim 1)

[1716] means for receiving data collected from sensors installed at the farm or manufacturing facility;

[1717] A means of preprocessing the received sensor data and converting it into a format suitable for analysis;

[1718] Using pre-processed data, artificial intelligence analyzes abnormal behavior and changes in body temperature and equipment operating status, and scores the risk.

[1719] A means for generating and notifying alerts when the risk score exceeds a certain threshold;

[1720] A means of suggesting prevention and countermeasures based on risk scores;

[1721] a means for collecting feedback data from users and updating the artificial intelligence model;

[1722] AI will analyze user emotions and customize notification content.

[1723] A system including:

[1724] (Claim 2)

[1725] 10. The system of claim 1, further comprising means for analyzing the preprocessed data in real time to detect anomalous behavior or equipment anomalies.

[1726] (Claim 3)

[1727] 10. The system of claim 1, further comprising means for aggregating data collected from multiple farms or manufacturing facilities and analyzing and predicting the overall situation. [Explanation of symbols]

[1728] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving data collected from sensors installed in the aquaculture facility; A means of preprocessing the received sensor data and converting it into a format suitable for analysis; Using the pre-processed data, an artificial intelligence analyzes abnormal behavior and changes in body temperature and scores the risk; A means for generating and notifying alerts when the risk score exceeds a certain threshold; A means of suggesting prevention and countermeasures based on risk scores; a means for collecting feedback data from users and updating the artificial intelligence model; A system including:

2. The system of claim 1 , further comprising means for analyzing the pre-processed data in real time to detect anomalous behavior.

3. The system of claim 1 further comprising means for aggregating data collected from multiple farms and analyzing and predicting the overall situation.

Images