Electronic ear tag monitoring method and system for livestock

Abstract

The application discloses a kind of livestock electronic ear tag monitoring method and system, it is related to intelligent breeding animal detection technical field, including installing electronic ear tag on the ear of animal to carry out unique identification, according to animal activity intensity automatically adjusting data sampling frequency to carry out data acquisition;Physiological index data collected are extracted features, and animal health condition is detected based on the extracted features;Response measures are executed according to detection result and individual animal health report is generated, data is stored and backed up.The application monitors animal physiological index data in real time by using electronic ear tag and automatically adjusts data sampling frequency, extracts effective features from data to intelligently evaluate animal health condition and generates detailed individual health report, reduces the burden of data storage, can adapt to the change of animal behavior and health state, significantly improves the accuracy and timeliness of animal health monitoring and the precision and efficiency of livestock management.

Description

Technical Field

[0001] This invention relates to the field of intelligent animal detection technology, and in particular to a method and system for monitoring livestock using electronic ear tags. Background Technology

[0002] In animal husbandry, the development of animal health monitoring technology is a key factor in improving breeding efficiency and animal welfare. Electronic ear tags, as a smart monitoring tool, have been widely used for real-time animal tracking and health monitoring since their introduction to the market. Traditional electronic ear tag technology mainly focuses on basic identification and location tracking functions. With the development of Internet of Things (IoT) technology, the functions of electronic ear tags have expanded to more complex health monitoring fields. However, existing technologies typically have a fixed data sampling frequency, which not only increases the burden of data storage but may also lead to the loss of important data at critical moments. Furthermore, they lack the ability to effectively extract and fuse data features, accurately detect data, and have automatic emergency response mechanisms for specific detection results. These technological shortcomings limit the effectiveness of electronic ear tag monitoring systems in practical applications and reduce the accuracy and efficiency of livestock management. Summary of the Invention

[0003] In view of the problems existing in the above-mentioned existing methods and systems for monitoring livestock electronic ear tags, this invention is proposed.

[0004] Therefore, the problem that this invention aims to solve is that the existing technology usually has a fixed data sampling frequency, which not only increases the burden of data storage, but may also lead to the loss of important data at critical moments, the inability to effectively extract data features for fusion, and the lack of accurate data detection and automatic emergency response mechanisms for specific detection results. These technical deficiencies limit the effectiveness of electronic ear tag monitoring systems in practical applications and reduce the accuracy and efficiency of livestock management.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for monitoring livestock using electronic ear tags, comprising: attaching electronic ear tags to the ears of animals for unique identification; automatically adjusting the data sampling frequency according to the animal's activity intensity for data collection; extracting features from the collected physiological indicator data; detecting the animal's health status based on the extracted features; implementing response measures according to the detection results and generating an individual animal health report; and storing and backing up the data.

[0006] As a preferred embodiment of the livestock electronic ear tag monitoring method of the present invention, wherein: the step of installing the electronic ear tag on the animal's ear for unique identification refers to selecting an electronic ear tag that includes multiple sensors and GPS positioning functions, and embedding a unique electronic ID in the electronic ear tag, binding the electronic ID with the animal's detailed information in the management system, and using the electronic ear tag to monitor the animal's physiological indicators in real time.

[0007] As a preferred embodiment of the livestock electronic ear tag monitoring method of the present invention, the step of automatically adjusting the data sampling frequency according to the animal activity intensity for data collection includes:

[0008] The animal's movement was monitored in real time using a triaxial accelerometer in the ear tag, and the animal's activity intensity I was calculated.

[0009]

[0010] In the formula, T is the length of the sampling window, k is a constant, and a x (t), a y (t), a z (t) is the acceleration of the animal along the x, y, z axes at time t;

[0011] Calculate the moving average θ and standard deviation δ of the activity intensity:

[0012]

[0013] In the formula, m is the number of sampling points within the time window, and I v This represents the animal activity intensity at the v-th sampling point;

[0014] Adjust the data sampling frequency f based on θ and δ:

[0015]

[0016] In the formula, f min and f max These are the minimum and maximum values ​​of the sampling frequency, respectively, and α is the adjustment coefficient;

[0017] Based on the current sampling frequency, sensors in the electronic ear tag are used to periodically collect physiological data of the animals, and the collected data is stored in a central database.

[0018] As a preferred embodiment of the livestock electronic ear tag monitoring method of the present invention, the step of feature extraction of the collected physiological index data includes:

[0019] The collected data is cleaned, filtered, and standardized. The collected animal physiological index data are then classified according to the animal's electronic ID to form an animal dataset.

[0020] Heart rate features H(t) were extracted from animal datasets using an autoregressive moving average model.

[0021]

[0022] In the formula, o is a constant term, and φ i It is the autoregressive coefficient, θj is the moving average coefficient, ∈(t) is the error term, p and q are the order of the model, l and j represent the index, and t is time;

[0023] Extracting body temperature features C from animal datasets:

[0024] C=∫e -2πwbt T(t)dt

[0025] In the formula, T(t) is the body temperature value at time t, b is the frequency variable, and w is the complex unit;

[0026] Extracting activity intensity feature A from the animal dataset:

[0027] A = [μ A ,σ A ,S A ]

[0028] In the formula, μ A It is the average value of the activity intensity, σ A It is the standard deviation, S A It is the entropy based on the distribution of activity intensity;

[0029] The S A The calculation formula is expressed as follows:

[0030]

[0031] In the formula, p(c) is the probability density function for estimating activity intensity, n is the total number of data points, and c is the number of numerical points in the activity intensity data. i It represents a single data point, h is the bandwidth, and K is the kernel function;

[0032] All extracted data features are fused to form a fused feature vector set Q:

[0033]

[0034] In the formula, Q is the final set of feature vectors after PCA processing.

[0035] As a preferred embodiment of the livestock electronic ear tag monitoring method of the present invention, the step of detecting animal health status based on extracted features includes:

[0036] An animal health status detection model is constructed based on a random forest model. The number of trees is determined and the maximum depth of the trees is set. The minimum sample split and the minimum number of leaf nodes in the sample are also set.

[0037] The animal health status detection model was trained using training set data, and k-fold cross-validation was implemented to evaluate the model performance. The model parameters were then optimized based on the cross-validation results.

[0038] After training, the extracted data features Q are input into the animal health status detection model to obtain the animal health status detection results: "healthy", "mildly unwell", and "severely ill".

[0039] As a preferred embodiment of the livestock electronic ear tag monitoring method of the present invention, the step of executing response measures based on the detection results and generating an individual animal health report includes:

[0040] If the test result is healthy, continue to collect physiological data regularly through electronic ear tags;

[0041] If the test result indicates mild discomfort, a notification will be sent to the administrator's mobile device and email, the animal will be observed more frequently, and changes in relevant health indicators will be recorded.

[0042] If the test result indicates a serious illness, an emergency protocol will be automatically triggered, automatically sending detailed health alerts and the animal's location to designated veterinarians and caregivers for further examination and treatment based on the animal's specific symptoms.

[0043] Detailed individual animal health reports are generated based on the test results for each animal and the resulting emergency measures, and these health reports are sent to veterinarians and animal handlers via email.

[0044] As a preferred embodiment of the electronic ear tag monitoring method for livestock described in this invention, the storage and backup of data refers to classifying and storing the collected and processed physiological indicator data, extracted data features, test results, emergency measures, and individual animal health reports into a central database, backing up the data, and controlling access to the data.

[0045] Another object of the present invention is to provide an electronic ear tag monitoring system for livestock, comprising,

[0046] The data acquisition module is used to attach electronic ear tags to identify animals and adjust the data sampling frequency according to the animal's activity level for data acquisition.

[0047] The feature extraction module is used to extract features from the collected data and fuse those features.

[0048] The health monitoring and response module is used to build an animal health status model to monitor animal health and generate response measures based on the monitoring results.

[0049] The data storage module is used to store data generated during the collection and processing process, and to back up and control the access of the data.

[0050] A computer device includes: a memory and a processor; the memory stores a computer program, and the processor executes the computer program to implement the steps of a livestock electronic ear tag monitoring method.

[0051] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of an electronic ear tag monitoring method for livestock.

[0052] The beneficial effects of this invention are as follows: By using electronic ear tags to monitor animal physiological indicators in real time and automatically adjust the data sampling frequency, this invention extracts effective features from the data to conduct intelligent animal health status assessment and generate detailed individual health reports, reducing the burden of data storage, adapting to changes in animal behavior and health status, and significantly improving the accuracy and timeliness of animal health monitoring as well as the precision and efficiency of livestock management. Attached Figure Description

[0053] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A flowchart illustrating the electronic ear tag monitoring method for livestock.

[0055] Figure 2 A schematic diagram illustrating the implementation of electronic ear tag monitoring methods for livestock.

[0056] Figure 3 This is a schematic diagram of an electronic ear tag monitoring system for livestock. Detailed Implementation

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0060] Example 1

[0061] Reference Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides a method for monitoring livestock using electronic ear tags. The method for monitoring livestock using electronic ear tags includes...

[0062] S1. The electronic ear tag is installed on the animal's ear for unique identification, and the data sampling frequency is automatically adjusted according to the animal's activity intensity for data collection;

[0063] Specifically, attaching electronic ear tags to an animal's ear for unique identification involves selecting an electronic ear tag that includes multiple sensors and GPS positioning functions, and embedding a unique electronic ID in the ear tag. This electronic ID is then linked to the animal's detailed information in the management system, allowing for real-time monitoring of the animal's physiological indicators.

[0064] Multiple sensors, including body temperature sensors, heart rate sensors, three-axis accelerometers, and gyroscopes, are used to attach electronic ear tags containing various sensors and GPS positioning functions to the animals' ears, enabling unique identification of each animal. The unique electronic ID embedded in the ear tag not only simplifies the animal identification process but also allows for real-time monitoring and accurate recording of each animal's health and location information. By binding these unique electronic IDs with the animal's detailed information in the livestock management system, animal management becomes more systematic and automated, improving the efficiency of animal monitoring, reducing the risk of data confusion and misidentification, and thus enhancing the overall management quality and response speed of the livestock business.

[0065] Furthermore, data collection includes automatically adjusting the data sampling frequency based on the intensity of animal activity.

[0066] The animal's movement was monitored in real time using a triaxial accelerometer in the ear tag, and the animal's activity intensity I was calculated.

[0067]

[0068] In the formula, T is the length of the sampling window, k is a constant, and a x (t), a y (t), a z (t) is the acceleration of the animal along the x, y, z axes at time t;

[0069] Calculate the moving average θ and standard deviation δ of the activity intensity:

[0070]

[0071] In the formula, m is the number of sampling points within the time window, and I v This represents the animal activity intensity at the v-th sampling point;

[0072] Adjust the data sampling frequency f based on θ and δ:

[0073]

[0074] In the formula, f min and f max These are the minimum and maximum values ​​of the sampling frequency, respectively, and α is an adjustment coefficient calculated using a genetic algorithm.

[0075] Based on the current sampling frequency, sensors in the electronic ear tag are used to periodically collect physiological data of the animals, and the collected data is stored in a central database.

[0076] Using a triaxial accelerometer in the ear tag to monitor animal movement in real time, the method of adjusting the data sampling frequency according to the intensity of animal activity allows the system to dynamically collect data as needed. By calculating the moving average and standard deviation of animal activity intensity and adjusting the data sampling frequency based on these calculations, the sampling frequency is increased when the animal is highly active to capture more health data, and decreased when the animal is at rest or less active to save resources. This not only optimizes the data collection process and reduces the cost of data storage and processing, but also ensures that high-quality data is obtained at critical moments, thereby improving the accuracy and timeliness of health monitoring.

[0077] S2. Extract features from the collected physiological indicator data and detect the animal's health status based on the extracted features;

[0078] Specifically, feature extraction from the collected physiological indicator data includes:

[0079] The collected data is cleaned, filtered, and standardized. The collected animal physiological index data are then classified according to the animal's electronic ID to form an animal dataset.

[0080] Heart rate features H(t) were extracted from animal datasets using an autoregressive moving average model.

[0081]

[0082] In the formula, o is a constant term, and φ i It is the autoregressive coefficient, θ j It is the moving average coefficient, φi and θ j The least squares method is used to determine ∈(t), where ∈(t) is the error term, p and q are the order of the model, determined based on the autocorrelation function (ACF) and partial autocorrelation function (PACF) of the data, l and j represent indices, and t is time.

[0083] Extracting body temperature features C from animal datasets:

[0084] C=∫e -2πwbt T(t)dt

[0085] In the formula, T(t) is the body temperature value at time t, b is the frequency variable used to analyze the periodic components of body temperature changes, and w is the complex unit.

[0086] Extracting activity intensity feature A from the animal dataset:

[0087] A = [μ A ,σ A ,S A ]

[0088] In the formula, μ A It is the average value of the activity intensity, σ A It is the standard deviation, S A It is the entropy based on the distribution of activity intensity;

[0089] The S A The calculation formula is expressed as follows:

[0090]

[0091] In the formula, p(c) is the probability density function for estimating activity intensity, n is the total number of data points, and c is the number of numerical points in the activity intensity data. i A is a single data point, h is the bandwidth, and K is the kernel function. Kernel functions include linear kernel functions, polynomial kernel functions, and Gaussian kernel functions, etc. In this embodiment, the preferred kernel function is the Gaussian kernel function.

[0092] All extracted data features are fused to form a fused feature vector set Q:

[0093]

[0094] In the formula, Q is the final set of feature vectors after PCA processing.

[0095] The Autoregressive Moving Average (ARMA) model is a commonly used method in time series analysis to describe patterns of change in time series data. It involves cleaning, filtering, and standardizing the collected data, then classifying it according to the animal's electronic ID, enabling efficient data analysis. By utilizing advanced statistical and machine learning models, such as ARMA and kernel density estimation, features of physiological indicators like heart rate, body temperature, and activity intensity can be extracted. This allows for the accurate extraction of useful information from large amounts of physiological data. Effectively fusing these features to form a fused feature vector set can then be used to accurately assess the animal's health status. This not only enhances the depth and breadth of data analysis but also makes the obtained health assessment results more scientific and accurate, providing a reliable basis for subsequent health management and emergency measures.

[0096] Furthermore, detecting animal health status based on extracted features includes,

[0097] An animal health status detection model is constructed based on a random forest model. The number of trees is determined and the maximum depth of the trees is set. The minimum sample split and the minimum number of leaf nodes in the sample are also set.

[0098] The animal health status detection model was trained using training set data, and k-fold cross-validation was implemented to evaluate the model performance. The model parameters were then optimized based on the cross-validation results.

[0099] After training, the extracted data features Q are input into the animal health status detection model to obtain the animal health status detection results: "healthy", "mildly unwell", and "severely ill".

[0100] By constructing an animal health status detection model using a random forest model, key features were extracted from animal physiological data and applied to the prediction model. Through precise adjustment of model parameters, high data utilization and prediction accuracy were ensured. Training with training set data and implementing k-fold cross-validation not only optimized model performance but also significantly improved the model's generalization ability through a data-driven approach. Through refined data processing and machine learning techniques, the monitoring of animal health status became more accurate and timely, thereby achieving the beneficial effects of early diagnosis and treatment, and reducing the long-term impact of animal diseases and treatment costs.

[0101] S3. Implement response measures based on the test results and generate individual animal health reports, and store and back up the data;

[0102] Specifically, implementing response measures based on test results and generating individual animal health reports includes:

[0103] If the test result is healthy, continue to collect physiological data regularly through electronic ear tags;

[0104] If the test result indicates mild discomfort, a notification will be sent to the administrator's mobile device and email, the animal will be observed more frequently, and changes in relevant health indicators will be recorded.

[0105] If the test result indicates a serious illness, an emergency protocol will be automatically triggered, automatically sending detailed health alerts and the animal's location to designated veterinarians and caregivers for further examination and treatment based on the animal's specific symptoms.

[0106] Detailed individual animal health reports are generated based on the test results for each animal and the resulting emergency measures, and these health reports are sent to veterinarians and animal handlers via email.

[0107] By taking corresponding response measures based on animal health status test results, customized management for different health conditions is achieved, improving the timeliness of treatment. This differentiated response mechanism enables more efficient allocation of resources, ensures rapid response to animals in high-risk states, and reduces interference with healthy or mildly unwell animals. All measures and health status assessment results are compiled into individual health reports, which are sent to veterinarians and managers via email, providing detailed data and decision support, and enhancing the professionalism and efficiency of livestock management.

[0108] Furthermore, storing and backing up the data refers to classifying and storing the collected and processed physiological indicator data, extracted data features, test results, emergency measures, and individual animal health reports into a central database, backing up the data, and controlling access to the data.

[0109] By classifying and storing all key data, including physiological indicators, extracted data features, test results, emergency measures, and individual health reports, in a central database and implementing backup and access control, the security and integrity of the data are ensured. This systematic data management strategy not only improves the reliability and security of the data but also facilitates historical data analysis and trend prediction, providing a scientific basis for the formulation of future health management strategies.

[0110] Example 2

[0111] Reference Figure 3 This is the second embodiment of the present invention, which differs from the previous embodiment. It provides an electronic ear tag monitoring system for livestock, comprising:

[0112] The data acquisition module is used to attach electronic ear tags to identify animals and adjust the data sampling frequency according to the animal's activity level for data acquisition.

[0113] The feature extraction module is used to extract features from the collected data and fuse those features.

[0114] The health monitoring and response module is used to build an animal health status model to monitor animal health and generate response measures based on the monitoring results.

[0115] The data storage module is used to store data generated during the collection and processing process, and to back up and control the access of the data.

[0116] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0118] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0119] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

Claims

1. A method for monitoring livestock using electronic ear tags, characterized in that: include, Electronic ear tags are installed on the ears of animals for unique identification, and the data sampling frequency is automatically adjusted according to the intensity of the animal's activity to collect data; Feature extraction is performed on the collected physiological indicator data, and the animal's health status is detected based on the extracted features; Implementation of response measures based on test results and generation of individual animal health reports; storage and backup of the data; The process of automatically adjusting the data sampling frequency based on animal activity intensity includes using a triaxial accelerometer in the ear tag to monitor the animal's movement in real time and calculating the animal's activity intensity. Calculate the moving average of activity intensity and standard deviation ,based on and Adjust data sampling frequency Based on the current sampling frequency, the sensors in the electronic ear tag are used to periodically collect physiological data of the animals and store the collected data in a central database. The feature extraction of the collected physiological index data includes, The collected data is cleaned, filtered, and standardized. The collected animal physiological index data are then classified according to the animal's electronic ID to form an animal dataset. Heart rate features were extracted from animal datasets using an autoregressive moving average model. : In the formula, o is a constant term. It is the autoregressive coefficient. It is the moving average coefficient. is the error term, p and q are the order of the model, l and j represent indices, and t is time; Extracting body temperature features from animal datasets : In the formula, is the body temperature value at time t, b is the frequency variable, and w is the complex unit; Extracting activity intensity features from animal datasets : In the formula, It is the average value of the activity intensity. It is the standard deviation. It is the entropy based on the distribution of activity intensity; The The calculation formula is expressed as follows: In the formula, p(c) is the probability density function for estimating activity intensity, n is the total number of data points, and c is the number of numerical points in the activity intensity data. It represents a single data point, h is the bandwidth, and K is the kernel function; All extracted data features are fused to form a fused feature vector set Q: In the formula, Q is the final set of feature vectors after PCA processing; The detection of animal health status based on extracted features includes... An animal health status detection model is constructed based on a random forest model. The number of trees is determined and the maximum depth of the trees is set. The minimum sample split and the minimum number of leaf nodes in the sample are also set. The animal health status detection model was trained using training set data, and k-fold cross-validation was implemented to evaluate the model performance. The model parameters were then optimized based on the cross-validation results. After training, the extracted data features Q are input into the animal health status detection model to obtain the animal health status detection results: "healthy", "mildly unwell", and "severely ill".

2. The method for monitoring livestock using electronic ear tags as described in claim 1, characterized in that: The process of attaching electronic ear tags to an animal's ear for unique identification involves selecting an electronic ear tag that includes multiple sensors and GPS positioning functions, embedding a unique electronic ID in the ear tag, binding the electronic ID with the animal's detailed information in the management system, and using the electronic ear tag to monitor the animal's physiological indicators in real time.

3. The method for monitoring livestock using electronic ear tags as described in claim 2, characterized in that: The calculation of animal activity intensity : In the formula, T is the length of the sampling window, and k is a constant. , , It is the animal's acceleration along the x, y, z axes at time t; Calculate the moving average of activity intensity and standard deviation : In the formula, m is the number of sampling points within the time window. This represents the animal activity intensity at the v-th sampling point; based on and Adjust data sampling frequency : In the formula, and These are the minimum and maximum values ​​of the sampling frequency, respectively. It is an adjustment factor.

4. The method for monitoring livestock electronic ear tags as described in claim 3, characterized in that: The step of implementing response measures based on the test results and generating individual animal health reports includes, If the test result is healthy, continue to collect physiological data regularly through electronic ear tags; If the test result indicates mild discomfort, a notification will be sent to the administrator's mobile device and email, the animal will be observed more frequently, and changes in relevant health indicators will be recorded. If the test result indicates a serious illness, an emergency protocol will be automatically triggered, automatically sending detailed health alerts and the animal's location to designated veterinarians and caregivers for further examination and treatment based on the animal's specific symptoms. Detailed individual animal health reports are generated based on the test results for each animal and the resulting emergency measures, and these health reports are sent to veterinarians and animal handlers via email.

5. The method for monitoring livestock electronic ear tags as described in claim 4, characterized in that: The storage and backup of data refers to classifying and storing the collected and processed physiological indicator data, extracted data features, test results, emergency measures, and individual animal health reports into a central database, backing up the data, and controlling access to the data.

6. A livestock electronic ear tag monitoring system based on the livestock electronic ear tag monitoring method according to any one of claims 1-5, characterized in that: include, The data acquisition module is used to attach electronic ear tags to identify animals and adjust the data sampling frequency according to the animal's activity level for data acquisition. The feature extraction module is used to extract features from the collected data and fuse those features. The health monitoring and response module is used to build an animal health status model to monitor animal health and generate response measures based on the monitoring results. The data storage module is used to store data generated during the collection and processing process, and to back up and control the access of the data.

7. A computer device, comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the livestock electronic ear tag monitoring method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the livestock electronic ear tag monitoring method according to any one of claims 1 to 5.

Images