Animal epidemic disease prevention and control monitoring management system

Abstract

The invention provides an animal epidemic disease prevention and control monitoring management system. The animal epidemic disease prevention and control monitoring management system comprises a multi-dimensional data acquisition module, a data management module and a risk early warning module, the multi-dimensional data acquisition module acquires animal living data and animal living environment data in real time, and uploads the animal living data and the animal living environment data to the data management module; the data management module preprocesses the animal living data and the animal living environment data collected in real time, stores and manages the preprocessed animal living data and animal living environment data, and sends the preprocessed animal living data and animal living environment data to the risk early warning module; meanwhile, the data acquisition frequency of the multi-dimensional data acquisition module is dynamically regulated and controlled according to the fluctuation condition of the animal living data and the animal living environment data; and the risk early warning module predicts the animal epidemic disease risk according to the animal living data and the animal living environment data, and carries out early warning according to the prediction result.

Description

Technical Field

[0001] This invention proposes an animal disease prevention and control monitoring and management system, which belongs to the field of animal disease monitoring technology. Background Technology

[0002] With the development of large-scale and intensive animal husbandry, the density of animal farming is constantly increasing, significantly raising the risk of animal disease transmission. Animal diseases not only cause mass mortality of farmed animals and serious economic losses, but can also endanger human health and trigger public health emergencies through food chain and contact transmission. Therefore, effective prevention and monitoring of animal diseases has become a key link in the development of animal husbandry and the protection of public health security.

[0003] Currently, existing animal disease prevention and control monitoring methods mostly rely on traditional approaches such as manual inspections and periodic sampling and testing, which have significant limitations. In terms of data collection, traditional methods struggle to achieve real-time and comprehensive collection and management of animal living data and environmental data. They often only obtain discrete and partial data, failing to reflect the dynamic processes of animal growth and environmental changes, resulting in insufficient timeliness and completeness of data collection. Summary of the Invention

[0004] This invention provides an animal disease prevention and control monitoring and management system to solve the technical problems existing in the prior art. The technical solution adopted is as follows: An animal disease prevention and control monitoring and management system, comprising: The multi-dimensional data acquisition module is used to collect animal living data and animal living environment data corresponding to each animal monitoring area in real time, and upload the animal living data and animal living environment data corresponding to the animal monitoring area to the data management module. The data management module is used to preprocess and store the real-time collected animal living data and animal living environment data, and dynamically adjust the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area according to the fluctuation of the animal living data and animal living environment data corresponding to the animal monitoring area. The disease prevention and control prediction module is used to conduct a safety assessment of each animal monitoring area based on animal living data and animal living environment data, and to confirm the epidemic prevention safety level based on the analysis of the safety assessment results. The safety level includes high, medium and low levels. The risk warning module provides a first warning for animal monitoring areas with low safety levels, and a second warning for the overall animal disease prevention risk within the current monitoring range based on the corresponding disease prevention safety level of each biological monitoring area.

[0005] Furthermore, the multidimensional data acquisition module includes: The data acquisition and control module is used to collect animal living data and animal living environment data corresponding to the animal monitoring area according to a preset data acquisition frequency after the multi-dimensional data acquisition module is activated. The animal living data includes movement trajectory and activity period; the environmental data includes temperature data, humidity data and ammonia concentration. The instruction judgment module is used to determine in real time whether a data acquisition frequency update instruction has been received from the data management module; The data acquisition and adjustment module is used to collect animal life data and animal living environment data according to the updated data acquisition frequency after the multidimensional data acquisition module receives the data acquisition frequency update instruction sent by the data management module. The data upload module is used to upload animal living data and animal living environment data corresponding to the animal monitoring area to the data management module.

[0006] Furthermore, the animal living data and animal living environment data corresponding to the animal monitoring area are uploaded to the data management module, including: Real-time retrieval of temperature and humidity data from the current data acquisition frequency and environmental data; The temperature and humidity data are compared with preset temperature and humidity reference values, respectively, and the data upload frequency is set according to the comparison results of the temperature and humidity data with the preset temperature and humidity reference values, respectively. According to the set data upload frequency, the animal living data and animal living environment data corresponding to the animal monitoring area are uploaded to the data management module.

[0007] Furthermore, the data upload frequency is set based on the comparison results of temperature data and humidity data with preset temperature reference values ​​and humidity reference values, respectively, including: When the temperature data does not exceed the temperature reference value and the humidity data does not exceed the humidity reference value, the data upload frequency is set to the same frequency according to the current data acquisition frequency. When either the temperature data or the humidity data exceeds its corresponding temperature reference value or humidity reference value, the data upload frequency is set using the first data upload frequency setting strategy. The first data upload frequency setting strategy is as follows: Retrieve the first percentage parameter P that indicates the current temperature and humidity data exceeds their corresponding temperature and humidity reference values. 01 ; Using the first percentage parameter P 01 Set the first data upload frequency F 01 =[1+(P 01 *P 01x )0.5 / exp(T / T) g )]*F0; where, P 01x This represents the first percentage parameter corresponding to the time when either the previous temperature or humidity data exceeded its corresponding temperature or humidity reference value; T represents the time interval between the time when either the current temperature or humidity data exceeded its corresponding temperature or humidity reference value and the time when either the previous temperature or humidity data exceeded its corresponding temperature or humidity reference value; F0 represents the current data acquisition frequency; T g This indicates the length of time corresponding to the data upload cycle; When both the temperature data and humidity data exceed their corresponding temperature reference values ​​and humidity reference values, the data upload frequency is set using the second data upload frequency setting strategy. The second data upload frequency setting strategy is as follows: The second temperature percentage parameter P is used to retrieve temperature data that exceeds the temperature reference value. 02t And, retrieve the second humidity percentage parameter P that exceeds the humidity reference value. 02w ; Using the second temperature percentage parameter P 02t Second humidity percentage parameter P 02w Set the first data upload frequency F 02 =[1+(P 02t *P 02w ) 0.5 ]*F0.

[0008] Furthermore, the data management module includes: The data preprocessing module is used to preprocess the animal living data and animal living environment data collected in real time, wherein the preprocessing includes, but is not limited to, data noise reduction and data cleaning. The data storage and transmission module is used to treat each animal monitoring area as a data storage node, store the pre-processed animal living data and animal living environment data corresponding to the animal monitoring area to its corresponding storage node, and send the pre-processed animal living data and animal living environment data corresponding to each animal monitoring area to the risk warning module. The data acquisition frequency control module is used to dynamically adjust the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area based on the fluctuations in animal living data and animal living environment data corresponding to the animal monitoring area.

[0009] Furthermore, the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area is dynamically adjusted based on fluctuations in animal living data and animal living environment data within the monitoring area, including: The multidimensional data acquisition module retrieves the current data upload frequency setting parameters for each animal monitoring area, wherein the setting parameters include the data upload frequency setting strategy used for the current data upload frequency and the current data upload frequency; When the current data upload frequency of the animal monitoring area is the same as the data acquisition frequency of the animal monitoring area, the data acquisition frequency of the multidimensional data acquisition module will not be adjusted. When the current data upload frequency of the animal monitoring area is set using the first data upload frequency setting strategy, the movement trajectory and activity time period in the current animal life data are retrieved. The trajectory density of an animal within its current habitat area is obtained by utilizing the movement trajectories in current animal life data. The strategy utilizes the trajectory density and activity time periods from the current animal living data in the animal monitoring area, combined with the first data upload frequency, to set the first percentage parameter P. 01 The control multidimensional data acquisition module regulates the data acquisition frequency corresponding to the animal monitoring area; When the current data upload frequency of the animal monitoring area is set using the second data upload frequency setting strategy, retrieve the movement trajectory and activity time period from the current animal life data, as well as the ammonia concentration from the environmental data; The current animal trajectory density within its habitat area is obtained by utilizing the movement trajectories in the current animal living data of the animal monitoring area. Using the current animal life data, including trajectory density, activity period, and ammonia concentration, combined with the second data upload frequency setting strategy, the second temperature percentage parameter P is employed. 02t Second humidity percentage parameter P 02w The control multidimensional data acquisition module regulates the data acquisition frequency corresponding to the animal monitoring area.

[0010] Furthermore, the disease prevention and control prediction module is used to conduct safety assessments of each animal monitoring area based on animal living data and animal living environment data, and to confirm the epidemic prevention safety level based on the analysis of the safety assessment results, including: The data retrieval module is used to retrieve preprocessed animal living data and animal living environment data corresponding to each current animal monitoring area; The epidemic prevention and safety level determination module is used to conduct a safety assessment of each current biological monitoring area based on the pre-processed animal living data and animal living environment data corresponding to each current animal monitoring area. Based on the analysis of the safety assessment results, the corresponding epidemic prevention safety levels are divided, and the epidemic prevention safety level corresponding to each biological monitoring area is determined.

[0011] Furthermore, based on the preprocessed animal living data and animal living environment data corresponding to each current animal monitoring area, a safety assessment is conducted for each current biological monitoring area. Based on the analysis of the safety assessment results, the corresponding epidemic prevention safety level is classified, determining the epidemic prevention safety level corresponding to each biological monitoring area, including: The trajectory density of animal activity within each unit of time is obtained from the movement trajectory in the preprocessed animal life data corresponding to each animal monitoring area; the value of the unit time length ranges from 24h to 72h. The percentage of animal activity time per unit time is obtained from the activity periods of each unit time in the preprocessed animal life data corresponding to each animal monitoring area. Using the trajectory density and animal activity time percentage for each unit of time corresponding to each animal monitoring area, the first monitoring vector A=[a] for each unit of time corresponding to each animal monitoring area is generated. 01 a 02 ], where a 01 This represents the trajectory density corresponding to animal activity per unit time; a 02 This indicates the percentage of time the animal spends in each unit of time. Based on the temperature data, humidity data, and ammonia concentration for each unit of time in each animal monitoring area, the standard deviation of temperature, standard deviation of humidity, and standard deviation of ammonia concentration for each unit of time are obtained. Using the standard deviations of temperature, humidity, and ammonia concentration within each unit of time, the second monitoring vector B=[b] for each animal monitoring area within each unit of time is obtained. 01 b 02 b 03 ], where b 01 b represents the standard deviation of temperature per unit time. 02 This represents the standard deviation of humidity per unit time; b 03 This indicates the ammonia concentration per unit time. Using the first monitoring vector A=[a] corresponding to each unit of time that has been experienced in each animal monitoring area 01 a 02 ] and the second monitoring vector B=[b 01 b 02 b 03 Determine the corresponding epidemic prevention and safety level for each biological monitoring area.

[0012] Furthermore, using the first monitoring vector A=[a] corresponding to each unit of time already experienced in each animal monitoring area... 01 a 02 ] and the second monitoring vector B=[b 01 b 02 b 03 Determine the corresponding epidemic prevention and control safety level for each biomonitoring area, including: Based on the first monitoring vector A=[a] for each unit of time 01 a 02 Get the first monitoring vector A=[a 01 a 02 The corresponding L1 norm ║A║ L1 ; Based on the second monitoring vector B=[b] for each unit of time 01 b 02 b 03 Obtain the second monitoring vector B=[b 01 b 02 b 03 The corresponding L1 norm ║B║ L1 ; Using the norm ║A║ corresponding to each unit of time already experienced in each animal monitoring area L1 Sum of norms ║B║ L1 Generate safety assessment coefficients for each animal monitoring area; The safety level of an animal monitoring area is determined based on the quantitative relationship between the safety assessment coefficient of the animal monitoring area and the first safety assessment coefficient threshold and the second safety assessment coefficient threshold.

[0013] Furthermore, based on the current disease prevention and control safety level corresponding to each biological monitoring area, a second early warning is issued for the overall animal disease prevention and control risk within the current monitoring scope, including: Retrieve animal monitoring areas with a current security level of medium and low. The total number of animal monitoring areas with a current security level of medium and low is compared with a preset number threshold. When the total number of animal monitoring areas with a current security level of medium and the total number of animal monitoring areas with a current security level of low does not exceed the preset number threshold, the security assessment coefficients corresponding to each animal monitoring area with a security level of medium and the security assessment coefficients corresponding to each animal monitoring area with a security level of low are retrieved. The overall safety coefficient of the animal disease prevention scope is obtained by using the safety assessment coefficients corresponding to each animal monitoring area with a medium safety level and the safety assessment coefficients corresponding to each animal monitoring area with a low safety level. When the overall safety factor of the overall animal disease prevention scope is lower than the preset overall safety factor threshold, it is determined that the overall animal disease prevention risk is high, and an overall animal disease prevention risk warning is issued.

[0014] Beneficial effects of this invention: This invention proposes an animal disease prevention and control monitoring and management system. Compared to traditional manual inspections and periodic sampling, its multi-dimensional data acquisition module enables real-time collection of animal living data and environmental data, overcoming the limitations of discrete data acquisition and ensuring the timeliness of data acquisition. This allows for dynamic reflection of animal growth status and environmental changes. Simultaneously, the data management module dynamically adjusts the acquisition frequency based on data fluctuations. When data fluctuations are small, the frequency is reduced to minimize unnecessary data collection, lowering system energy consumption and data storage pressure. When data fluctuations are large, the frequency is increased to ensure comprehensive capture of critical data, achieving an optimal balance between acquisition efficiency and resource consumption. The data management module's preprocessing function effectively solves the problems of inconsistent data formats and redundant errors. Through cleaning, filtering, and integration operations, data quality is improved, providing a reliable data foundation for subsequent risk warning analysis. Its storage management mechanism breaks free from the limitations of traditional fixed storage models, flexibly adjusting storage strategies according to data importance and usage frequency. This avoids waste of storage resources while ensuring the secure storage of important data, improving the effectiveness and security of data management. The risk warning module abandons the traditional method of warning based on single data or experience. It predicts disease risks through comprehensive analysis of animal living data and living environment data, fully considering the multi-factor correlation of disease occurrence and significantly improving the accuracy of risk prediction. At the same time, based on real-time data collection and efficient processing, the warning mechanism can respond quickly to changes in risk and trigger warnings in a timely manner when the disease risk reaches the warning threshold. This gives farmers more time for prevention and control, effectively reduces the risk of disease transmission and spread, and provides scientific and timely decision support for animal disease prevention and control. Attached Figure Description

[0015] Figure 1 This is a system block diagram of the system described in this invention. Detailed Implementation

[0016] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0017] Embodiments of the present invention propose an animal disease prevention and control monitoring and management system, such as... Figure 1 As shown, the animal disease prevention and control monitoring and management system includes a multi-dimensional data acquisition module, a data management module, a disease prevention and control prediction module, and a risk early warning module; The multi-dimensional data acquisition module is used to collect animal living data and animal living environment data corresponding to each animal monitoring area in real time, and upload the animal living data and animal living environment data corresponding to the animal monitoring area to the data management module. The data management module is used to preprocess and store the real-time collected animal living data and animal living environment data, and dynamically adjust the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area according to the fluctuation of the animal living data and animal living environment data corresponding to the animal monitoring area. The disease prevention and control prediction module is used to predict the risk of animal diseases based on animal living data and animal living environment data, obtain prediction results, and confirm the epidemic prevention safety level based on the prediction results. The safety level includes high, medium and low levels. The risk warning module provides a first warning for animal monitoring areas with low safety levels, and a second warning for the overall animal disease prevention risk within the current monitoring range based on the corresponding disease prevention safety level of each biological monitoring area.

[0018] The multidimensional data acquisition module includes: The data acquisition and control module is used to collect animal living data and animal living environment data corresponding to the animal monitoring area according to a preset data acquisition frequency after the multi-dimensional data acquisition module is activated. The animal living data includes movement trajectory and activity period; the environmental data includes temperature data, humidity data and ammonia concentration. The instruction judgment module is used to determine in real time whether a data acquisition frequency update instruction has been received from the data management module; The data acquisition and adjustment module is used to collect animal life data and animal living environment data according to the updated data acquisition frequency after the multidimensional data acquisition module receives the data acquisition frequency update instruction sent by the data management module. The data upload module is used to upload animal living data and animal living environment data corresponding to the animal monitoring area to the data management module.

[0019] The working principle of the above technical solution is as follows: This animal disease prevention and control monitoring and management system achieves full-process prevention and control monitoring and management of animal diseases through the coordinated operation of a multi-dimensional data acquisition module, a data management module, and a risk early warning module. First, the multi-dimensional data acquisition module collects animal living data and animal living environment data in real time for each animal monitoring area and uploads the two types of data to the data management module in real time. Next, after receiving the data, the data management module performs preprocessing operations such as cleaning, filtering, and integration to remove data redundancy and errors. Then, it stores and manages the processed effective data, while simultaneously analyzing the fluctuations of the two types of data in real time. Based on the fluctuation amplitude, the data acquisition frequency of the corresponding multi-dimensional data acquisition module is dynamically adjusted; the acquisition frequency is appropriately reduced when the data fluctuation is small, and increased when the fluctuation is large. Finally, the risk early warning module retrieves the preprocessed animal living data and animal living environment data from the data management module, performs comprehensive analysis of the data using a preset disease risk prediction algorithm, and determines the risk level of animal disease occurrence. If the risk level reaches the early warning threshold, the corresponding early warning mechanism is triggered.

[0020] The above technical solution achieves the following results: Compared to traditional manual inspections and periodic sampling, the multidimensional data acquisition module enables real-time collection of animal life and environmental data, overcoming the limitations of discrete data acquisition and ensuring the timeliness of data acquisition. It dynamically reflects animal growth status and environmental changes. Simultaneously, the data management module dynamically adjusts the acquisition frequency based on data fluctuations. When data fluctuations are small, the frequency is reduced to minimize unnecessary data collection, lowering system energy consumption and data storage pressure. When data fluctuations are large, the frequency is increased to ensure comprehensive capture of critical data, achieving an optimized balance between acquisition efficiency and resource consumption. The data management module's preprocessing function effectively solves the problems of inconsistent data formats and redundant errors. Through cleaning, filtering, and integration operations, it improves data quality, providing a reliable data foundation for subsequent risk warning analysis. Its storage management mechanism breaks free from the limitations of traditional fixed storage models, flexibly adjusting storage strategies according to data importance and usage frequency. This avoids wasting storage resources and ensures the secure storage of important data, improving the effectiveness and security of data management. The risk warning module abandons the traditional method of warning based on single data or experience. It predicts disease risks through comprehensive analysis of animal living data and living environment data, fully considering the multi-factor correlation of disease occurrence and significantly improving the accuracy of risk prediction. At the same time, based on real-time data collection and efficient processing, the warning mechanism can respond quickly to changes in risk and trigger warnings in a timely manner when the disease risk reaches the warning threshold. This gives farmers more time for prevention and control, effectively reduces the risk of disease transmission and spread, and provides scientific and timely decision support for animal disease prevention and control.

[0021] In one embodiment of the present invention, uploading animal living data and animal living environment data corresponding to the animal monitoring area to the data management module includes: Real-time retrieval of temperature and humidity data from the current data acquisition frequency and environmental data; The temperature and humidity data are compared with preset temperature and humidity reference values, respectively, and the data upload frequency is set according to the comparison results of the temperature and humidity data with the preset temperature and humidity reference values, respectively. According to the set data upload frequency, the animal living data and animal living environment data corresponding to the animal monitoring area are uploaded to the data management module.

[0022] The data upload frequency is set based on the comparison results of temperature data and humidity data with preset temperature reference values ​​and humidity reference values, respectively, including: When the temperature data does not exceed the temperature reference value and the humidity data does not exceed the humidity reference value, the data upload frequency is set to the same frequency according to the current data acquisition frequency. When either the temperature data or the humidity data exceeds its corresponding temperature reference value or humidity reference value, the data upload frequency is set using the first data upload frequency setting strategy. The first data upload frequency setting strategy is as follows: Retrieve the first percentage parameter P that indicates the current temperature and humidity data exceeds their corresponding temperature and humidity reference values. 01 ; Using the first percentage parameter P 01 Set the first data upload frequency F 01 =[1+(P 01 *P 01x ) 0.5 / exp(T / T) g )]*F0; where, P 01x This represents the first percentage parameter corresponding to the condition where either the previous temperature or humidity data exceeded its corresponding temperature or humidity reference value. If no previous temperature or humidity data exceeded its corresponding temperature or humidity reference value, then let P... 01x =1; T represents the time interval between the moment when any data point in the current temperature and humidity data exceeds its corresponding temperature and humidity reference values ​​and the moment when any data point in the previous temperature and humidity data exceeded its corresponding temperature and humidity reference values. If there is no previous instance where any data point in the previous temperature and humidity data exceeded its corresponding temperature and humidity reference values, then let T / T. g =1; F0 indicates the current data acquisition frequency; When both the temperature data and humidity data exceed their corresponding temperature reference values ​​and humidity reference values, the data upload frequency is set using the second data upload frequency setting strategy. The second data upload frequency setting strategy is as follows: The second temperature percentage parameter P is used to retrieve temperature data that exceeds the temperature reference value. 02t And, retrieve the second humidity percentage parameter P that exceeds the humidity reference value. 02w ; Using the second temperature percentage parameter P 02t Second humidity percentage parameter P 02w Set the second data upload frequency F 02 =[1+(P 02t *P 02w ) 0.5 ]*F0.

[0023] The working principle of the above technical solution is as follows: First, before data upload, the system retrieves the current data acquisition frequency in real time and extracts temperature and humidity data from the animal living environment data. Next, the extracted temperature and humidity data are compared with preset temperature and humidity reference values, respectively. Based on different combinations of whether the two types of data exceed the threshold, the corresponding strategy is used to set the data upload frequency. Finally, according to the set data upload frequency, the animal living data and animal living environment data corresponding to the animal monitoring area are uploaded to the data management module.

[0024] The data upload frequency setting follows a three-level judgment logic: First, if both temperature and humidity data do not exceed the temperature reference value and humidity reference value, the current data acquisition frequency is directly used as the data upload frequency. Second, if either the temperature or humidity data exceeds the corresponding reference value, the first data upload frequency setting strategy is activated—first, the first percentage parameter P corresponding to the data exceeding the threshold is retrieved. 01 Combined with the first percentage parameter P when the threshold was exceeded last time 01x (P when there is no historical data) 01x =1) The ratio of the time interval between the current threshold and the previous threshold exceedance, T / T g (When there is no historical data, T / Tg=1) and the current data acquisition frequency F0, using the formula F 01 =[1+(P 01 *P 01x ) 0.5 / exp(T / T) g The first data upload frequency F is calculated using the formula F0. 01The third level involves activating a second data upload frequency setting strategy if both temperature and humidity data exceed their corresponding reference values. This strategy first retrieves the second temperature percentage parameter P, indicating that the temperature exceeds the threshold. 02t The second humidity percentage parameter P that exceeds the humidity threshold 02w Then, combined with the current data acquisition frequency F0, the formula F 02 =[1+(P 02t *P 02w ) 0.5 The second data upload frequency F is calculated using F*F0. 02 .

[0025] The above technical solution achieves the following results: Compared to a fixed upload frequency, this solution uses temperature and humidity—two key environmental data points affecting animal health—as the core judgment criteria, dynamically adjusting the upload frequency by comparing them with preset reference values. When environmental data is normal, the upload frequency is maintained consistent with the collection frequency, ensuring stable transmission of basic data. When a single environmental data point exceeds a threshold, the upload frequency is calculated by combining historical threshold parameters and time intervals, avoiding excessive upload pressure due to occasional fluctuations while strengthening data capture for continuous anomalies. When both environmental data points exceed thresholds, the upload frequency is increased through dual-parameter coupling calculation, accurately focusing on high-risk scenarios, achieving "stable transmission in normal scenarios and strong capture in abnormal scenarios," significantly improving the accuracy of data uploads and the timeliness in high-risk scenarios. This embodiment avoids the resource waste problem of using high-frequency uploads regardless of the environmental data status by setting tiered frequencies. In low-risk scenarios where environmental data is normal, uploads are made at a basic frequency to reduce data transmission volume and instantaneous pressure on storage modules, thereby reducing server computing power consumption and energy consumption. Only when environmental data is abnormal, the upload frequency is dynamically increased according to the degree of abnormality, realizing an "on-demand allocation" resource scheduling mode, significantly optimizing the overall system resource utilization, extending the service life of hardware equipment, and reducing the system operation and maintenance costs of aquaculture enterprises.

[0026] On the other hand, for scenarios where single-environment data exceeds the threshold, the introduction of historical parameters and time intervals into the formula effectively distinguishes between "occasional anomalies" and "continuous anomalies"—if the threshold is exceeded multiple times within a short period and the magnitude of the anomaly increases, the calculated upload frequency will gradually increase, rapidly accumulating abnormal data. For high-risk scenarios where dual-environment data exceeds the threshold, the calculation method of multiplying and taking the square root of the product of the two parameters allows the upload frequency to increase in a stepwise manner with the degree of anomaly, transmitting key data to the data management module faster and more intensively. Both of these strategies provide richer and more timely abnormal data support for the risk warning module, enabling the warning algorithm to capture potential disease risk signals earlier, significantly improving risk response sensitivity, and gaining a time window for the rapid implementation of subsequent prevention and control measures. The percentage parameter (P) introduced in this embodiment... 01 P 02t P02w ), historical parameters (P) 01x ) and time interval parameters (T / T) g These are all dynamic parameters that can be adjusted according to different animal species and farming scenarios (such as poultry, livestock, greenhouse farming, and open-air farming). Farming enterprises can flexibly modify the preset reference values ​​and parameter weights according to the environmental adaptability characteristics of their own farmed animals, so that the data upload strategy can adapt to the monitoring needs of different scenarios, enhancing the system's adaptability in diverse farming scenarios. At the same time, this parameterized design also reserves space for the subsequent introduction of more environmental influencing factors (such as ammonia concentration and ventilation volume) to expand the dimensions of upload frequency judgment, improving the scalability of the solution.

[0027] In one embodiment of the present invention, the data management module includes: The data preprocessing module is used to preprocess the animal living data and animal living environment data collected in real time, wherein the preprocessing includes, but is not limited to, data noise reduction and data cleaning. The data storage and transmission module is used to treat each animal monitoring area as a data storage node, store the pre-processed animal living data and animal living environment data corresponding to the animal monitoring area to its corresponding storage node, and send the pre-processed animal living data and animal living environment data corresponding to each animal monitoring area to the risk warning module. The data acquisition frequency control module is used to dynamically adjust the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area based on the fluctuations in animal living data and animal living environment data corresponding to the animal monitoring area.

[0028] Specifically, the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area is dynamically adjusted based on fluctuations in animal living data and animal living environment data within the monitoring area. This includes: The multidimensional data acquisition module retrieves the current data upload frequency setting parameters for each animal monitoring area, wherein the setting parameters include the data upload frequency setting strategy used for the current data upload frequency and the current data upload frequency; When the current data upload frequency of the animal monitoring area is the same as the data acquisition frequency of the animal monitoring area, the data acquisition frequency of the multidimensional data acquisition module will not be adjusted. When the current data upload frequency of the animal monitoring area is set using the first data upload frequency setting strategy, the movement trajectory and activity time period in the current animal life data are retrieved. The trajectory density of an animal within its current habitat area is obtained by utilizing the movement trajectories in current animal life data. The strategy utilizes the trajectory density and activity time periods from the current animal living data in the animal monitoring area, combined with the first data upload frequency, to set the first percentage parameter P. 01 The control multidimensional data acquisition module regulates the data acquisition frequency corresponding to the animal monitoring area; The data collection frequency for the adjusted animal monitoring area is obtained using the following formula: Among them, F t This indicates the data collection frequency corresponding to the adjusted animal monitoring area; F x This indicates the data collection frequency for the animal monitoring area before the adjustment; a 01d T represents the normalized trajectory density of the current animal within its habitat area; h T represents the activity duration corresponding to the activity period in the current animal life data; d Indicates the length of a unit of time; When the current data upload frequency of the animal monitoring area is set using the second data upload frequency setting strategy, retrieve the movement trajectory and activity time period from the current animal life data, as well as the ammonia concentration from the environmental data; The current animal trajectory density within its habitat area is obtained by utilizing the movement trajectories in the current animal living data of the animal monitoring area. Using the current animal life data, including trajectory density, activity period, and ammonia concentration, combined with the second data upload frequency setting strategy, the second temperature percentage parameter P is employed. 02t Second humidity percentage parameter P 02w The control multidimensional data acquisition module regulates the data acquisition frequency corresponding to the animal monitoring area.

[0029] The data collection frequency for the adjusted animal monitoring area is obtained using the following formula: Among them, F t This indicates the data collection frequency corresponding to the adjusted animal monitoring area; F x This indicates the data collection frequency for the animal monitoring area before the adjustment; a 01d T represents the normalized trajectory density of the current animal within its habitat area; h T represents the activity duration corresponding to the activity period in the current animal life data; d The unit time length is represented by C; C represents the ammonia concentration after normalization.

[0030] The working principle of the above technical solution is as follows: The data management module, through the coordinated operation of the data preprocessing module, data storage and transmission module, and data acquisition frequency control module, completes data processing, storage, transmission, and dynamic optimization of acquisition frequency. First, the data preprocessing module receives animal life data and animal living environment data uploaded by the multidimensional data acquisition module, performs preprocessing operations such as data noise reduction (filtering invalid signals such as environmental interference and equipment errors) and data cleaning (removing duplicate, missing, and abnormal data), and outputs high-quality standardized data. Next, the data storage and transmission module uses each animal monitoring area as an independent data storage node, stores the preprocessed corresponding area data to the dedicated node, and simultaneously sends this data to the risk warning module to provide data support for early warning analysis. Finally, the data acquisition frequency control module initiates a dynamic control process: first, it retrieves the current data upload frequency setting parameters (including the upload frequency strategy used and the current upload frequency) from the multidimensional data acquisition module, and then adjusts the acquisition frequency according to the parameter type and scenario.

[0031] The effects of the above technical solution are as follows: the noise reduction and cleaning operations of the data preprocessing module effectively filter out interference signals and invalid data during data transmission and acquisition, reduce data redundancy and errors, and enable the data stored and analyzed subsequently to have higher accuracy and completeness; at the same time, the mode of using the monitoring area as an independent storage node realizes the precise binding of data and area, avoids cross-regional data confusion, greatly improves the availability of data, and lays a solid data foundation for the accurate analysis of the risk warning module.

[0032] The data acquisition frequency control module dynamically adjusts the acquisition frequency based on the upload frequency strategy. When the upload frequency matches the acquisition frequency (low-risk scenario), the status quo is maintained to reduce unnecessary frequency adjustment costs; when the first strategy (single environmental anomaly) is adopted, it combines animal trajectory density, activity time, and other living data with P 01 The first strategy increases the sampling frequency only when animal activity or environmental abnormalities worsen. The second strategy (dual environmental abnormalities) introduces an additional ammonia concentration parameter, increasing the sampling frequency only in high-risk scenarios. This "on-demand control" mode significantly reduces invalid data collection, decreases energy and computing power consumption of hardware (sensors, servers), optimizes storage resource usage, extends equipment lifespan, and lowers system maintenance costs for livestock farms. The differentiated design for different control scenarios allows the sampling frequency to accurately match the risk level. For a single environmental abnormality (first strategy), the focus is on the animal's own activity status (trajectory density, activity duration) and the degree of environmental abnormality (P...). 01 To avoid excessively increasing the sampling frequency due to occasional environmental fluctuations; for dual-environmental anomalies (second strategy), ammonia concentration, a key hazardous gas indicator, is additionally included, combined with dual-environmental anomaly parameters (P... 02t P 02wIn high-risk scenarios, the system rapidly increases the collection frequency of data on animal activity, capturing data changes more intensively to ensure no high-risk signals are missed. This layered adaptation mechanism allows data collection to cover risk scenarios without wasting resources, significantly enhancing the system's adaptability to different risk levels. The data storage and transmission modules synchronously complete data storage and transmission to the early warning module, achieving seamless integration of "preprocessing-storage-transmission," reducing data latency, and ensuring the early warning module can acquire high-quality data in real time. Simultaneously, the data collection frequency control module adjusts the collection frequency based on the upload frequency strategy (linked with the previous data upload logic), forming a closed-loop collaboration of "data upload strategy - collection frequency control," avoiding data redundancy or loss caused by a disconnect between upload and collection frequencies, ensuring a high degree of matching between data transmission rhythm and collection rhythm, and further improving the overall collaborative operation efficiency of the system. The normalized trajectory density, activity duration ratio, various percentage parameters, and ammonia concentration coefficient introduced in this embodiment are all dynamically adjustable parameters. Farming enterprises can flexibly modify parameter thresholds and weights according to different animal species (such as poultry and livestock with different environmental sensitivities) and farming scenarios (such as the different ammonia concentration thresholds in enclosed sheds and open-air farming), so that the data management module can adapt to diverse farming needs and greatly improve the system's flexibility and applicability.

[0033] In one embodiment of the present invention, a disease prevention and control prediction module is used to perform a safety assessment on each animal monitoring area based on animal living data and animal living environment data, and to confirm the epidemic prevention safety level based on the analysis of the safety assessment results, including: The data retrieval module is used to retrieve preprocessed animal living data and animal living environment data corresponding to each current animal monitoring area; The epidemic prevention and safety level determination module is used to conduct a safety assessment of each current biological monitoring area based on the pre-processed animal living data and animal living environment data corresponding to each current animal monitoring area. Based on the analysis of the safety assessment results, the corresponding epidemic prevention safety levels are divided, and the epidemic prevention safety level corresponding to each biological monitoring area is determined.

[0034] Specifically, based on the pre-processed animal living data and animal living environment data corresponding to each current animal monitoring area, the epidemic prevention and control safety level of each biological monitoring area is divided, and the epidemic prevention and control safety level of each biological monitoring area is determined, including: The trajectory density of animal activity within each unit of time is obtained from the movement trajectory in the preprocessed animal life data corresponding to each animal monitoring area; the value of the unit time length ranges from 24h to 72h. The percentage of animal activity time per unit time is obtained from the activity periods of each unit time in the preprocessed animal life data corresponding to each animal monitoring area. Using the trajectory density and animal activity time percentage for each unit of time corresponding to each animal monitoring area, the first monitoring vector A=[a] for each unit of time corresponding to each animal monitoring area is generated. 01 a 02 ], where a 01 This represents the trajectory density corresponding to animal activity per unit time; a 02 This indicates the percentage of time the animal spends in each unit of time. Based on the temperature data, humidity data, and ammonia concentration for each unit of time in each animal monitoring area, the standard deviation of temperature, standard deviation of humidity, and standard deviation of ammonia concentration for each unit of time are obtained. Using the standard deviations of temperature, humidity, and ammonia concentration within each unit of time, the second monitoring vector B=[b] for each animal monitoring area within each unit of time is obtained. 01 b 02 b 03 ], where b 01 b represents the standard deviation of temperature per unit time. 02 This represents the standard deviation of humidity per unit time; b 03 This indicates the ammonia concentration per unit time. Using the first monitoring vector A=[a] corresponding to each unit of time that has been experienced in each animal monitoring area 01 a 02 ] and the second monitoring vector B=[b 01 b 02 b 03 Determine the corresponding epidemic prevention and safety level for each biological monitoring area.

[0035] The working principle of the above technical solution is as follows: the risk warning module achieves accurate early warning of animal disease risks through the collaborative operation of the data retrieval module, the epidemic prevention and safety level determination module, the first early warning module, and the second early warning module. First, the data retrieval module retrieves pre-processed animal living data and animal living environment data from the data management module, providing a high-quality data source for subsequent analysis. Next, the epidemic prevention and safety level determination module initiates the level classification process: First, based on the animal living data, it extracts animal movement trajectories within each unit of time (24h-72h) to calculate trajectory density, extracts the animal activity periods during the same period to calculate the proportion of activity time, and combines the two to construct the first monitoring vector A=[a] for each unit of time. 01 (Trajectory density), a 02(Activity time percentage)]; Second, based on animal living environment data, calculate the standard deviation of temperature, humidity, and ammonia concentration for each unit of time, and construct the second monitoring vector B=[b 01 (Standard deviation of temperature), b 02 (Standard deviation of humidity), b 03 (Standard deviation of ammonia concentration)]; The third step is to integrate the first monitoring vector A and the second monitoring vector B that have been used for each unit of time in the animal monitoring area, and determine the epidemic prevention safety level corresponding to each animal monitoring area through a preset level classification algorithm (such as vector similarity matching, risk threshold comparison, etc.); Finally, the first early warning module triggers a special early warning for animal monitoring areas with a low epidemic prevention safety level, while the second early warning module combines the epidemic prevention safety levels of all current animal monitoring areas, analyzes the distribution and severity of animal epidemic prevention risks within the overall monitoring range, and triggers the corresponding overall risk early warning.

[0036] The above technical solution achieves the following effects: The epidemic prevention and safety level determination module constructs dual monitoring vectors to achieve multi-dimensional data fusion analysis. The first monitoring vector focuses on the animal's own activity status (trajectory density, activity time ratio), reflecting direct changes in the animal's health status. The second monitoring vector focuses on environmental stability (temperature, humidity, ammonia concentration standard deviation), reflecting environmental factors that induce disease growth. The combination of the two avoids the limitations of single-dimensional data analysis. Simultaneously, data statistics are performed in 24-72 hour time units, avoiding misjudgments caused by short-term data fluctuations and timely capturing medium- and long-term data trend changes. This makes the epidemic prevention and safety level classification more closely aligned with the actual risk status, providing accurate basis for subsequent early warnings and significantly reducing the probability of false and missed warnings. The module adopts a dual early warning mode of "zonal early warning + overall early warning". The first early warning module provides precise early warning for individual low-security-level monitoring areas, ensuring that local risks are not overlooked and facilitating the rapid implementation of targeted prevention and control measures such as isolation and disinfection in specific areas. The second early warning module conducts an overall risk assessment based on the security levels of all areas, which can identify cross-regional risk spread trends (such as multiple adjacent areas being at low security levels at the same time) or the impact of local high-risk areas on the overall prevention and control system, achieving full-range risk coverage from "point" to "area" and avoiding overlooking overall risks due to focusing only on local areas.

[0037] The construction of dual monitoring vectors enables risk analysis to have clear data traceability. If an area is classified as having a low epidemic prevention safety level, the first monitoring vector can be used to determine whether it is caused by abnormal animal activity (such as a sudden drop in track density or a sharp reduction in the proportion of activity time), or the second monitoring vector can be used to determine whether it is caused by environmental anomalies (such as a sudden increase in the standard deviation of temperature and humidity or excessive ammonia concentration), providing clear guidance for farmers to locate the root cause of the risk. At the same time, accurate zoning safety levels and overall risk assessment results can provide scientific decision-making support for the allocation of prevention and control resources (such as prioritizing the deployment of epidemic prevention materials to low-safety-level areas) and the formulation of prevention and control measures (such as adjusting ventilation and temperature control equipment for areas with abnormal environments), thereby improving prevention and control efficiency. This embodiment uses high-quality pre-processed data as the basis for analysis, reducing the impact of data redundancy and errors on analysis efficiency; at the same time, the unit time is set in the range of 24h-72h, which ensures the effectiveness of data accumulation and avoids early warning delays caused by excessively long periods. When abnormal trends appear in animal or environmental data, the dual monitoring vector can quickly capture these changes and reflect them in the safety level classification results. This allows the first and second early warning modules to trigger warnings promptly, providing farmers with ample time to prepare for prevention and control, and reducing the risk of disease transmission and spread. The parameter design of the dual monitoring vector is flexible. Farmers can adjust the weights of various environmental parameters in the second monitoring vector according to different animal species (e.g., poultry are more sensitive to ammonia concentration, and livestock are more sensitive to temperature fluctuations), or adjust the unit time length according to the farming scenario (e.g., the difference in environmental stability between enclosed sheds and open-air farming), making the safety level classification more suitable for specific farming needs.

[0038] In one embodiment of the present invention, the first monitoring vector A=[a] corresponding to each unit of time already experienced by each animal monitoring area is utilized. 01 a 02 ] and the second monitoring vector B=[b 01 b 02 b 03 Determine the corresponding epidemic prevention and control safety level for each biomonitoring area, including: Based on the first monitoring vector A=[a] for each unit of time 01 a 02 Get the first monitoring vector A=[a 01 a 02 The corresponding L1 norm ║A║ L1 ; Based on the second monitoring vector B=[b] for each unit of time 01 b 02 b 03 Obtain the second monitoring vector B=[b 01 b 02 b 03 The corresponding L1 norm ║B║ L1 ; Using the norm ║A║ corresponding to each unit of time already experienced in each animal monitoring area L1 Sum of norms ║B║ L1 Generate safety assessment coefficients for each animal monitoring area; The safety assessment coefficient for each animal monitoring area is obtained using the following formula: Where Q represents the safety assessment coefficient corresponding to each animal monitoring area; n represents the number of times each animal monitoring area has experienced each unit of time; ║A║ L1i and ║B║ L1i Let A and B represent the norms corresponding to the i-th unit of time, respectively. L1 and ║B║ L1 ;║A║ L1b and ║B║ L1b Let A represent the norms corresponding to n units of time. L1 Standard deviation and ║B║ L1 Standard deviation; The safety level of an animal monitoring area is determined based on the quantitative relationship between the safety assessment coefficient of the animal monitoring area and the first safety assessment coefficient threshold and the second safety assessment coefficient threshold, wherein the safety level includes high, medium and low.

[0039] The safety level of an animal monitoring area is determined based on the quantitative relationship between its safety assessment coefficient and a first safety assessment coefficient threshold, as well as a second safety assessment coefficient threshold. The security assessment coefficient is compared with a preset first security assessment coefficient threshold and a second security assessment coefficient threshold; When the safety assessment coefficient is not lower than the preset first safety assessment coefficient threshold, the safety level of the animal monitoring area is determined to be high. When the safety assessment coefficient is lower than the preset first safety assessment coefficient threshold, but not lower than the second safety assessment coefficient threshold, the safety level of the animal monitoring area is determined to be medium. If the safety assessment coefficient is lower than the preset second safety assessment coefficient threshold, the safety level of the animal monitoring area is determined to be low.

[0040] The working principle of the above technical solution is as follows: This technical solution is the core detailed process of the epidemic prevention safety level determination module in the risk warning module, focusing on the quantitative determination of the epidemic prevention safety level through vector norm and safety assessment coefficient. First, for each unit of time that has passed in each animal monitoring area, the first monitoring vector A=[a 01 a 02 The L1 norm of ] ║A║ L1, and the second monitoring vector B=[b 01 b 02 b 03 The L1 norm of ] ║B║ L1 The process involves transforming the multi-dimensional information of a vector into a single-dimensional quantitative indicator; then, counting the number of time units (n) that have been recorded in the monitored area, and extracting the corresponding ║A║ for each time unit. L1i and ║B║ L1i (i=1 to n), calculate n ║A║ L1i Standard deviation ║A║ L1b and n ║B║ L1i Standard deviation ║B║ L1b Then substitute it into the preset formula (combining ║A║ of n units of time). L1i 、║B║ L1i The safety assessment coefficient Q of the monitored area is calculated using the standard deviation of the coefficient. Finally, the safety assessment coefficient Q is compared with the preset first safety assessment coefficient threshold and the second safety assessment coefficient threshold: if Q ≥ the first threshold, the safety level is determined to be high; if the second threshold ≤ Q < the first threshold, the safety level is determined to be medium; if Q < the second threshold, the safety level is determined to be low, thus completing the determination of the epidemic prevention safety level of a single animal monitoring area.

[0041] The above technical solution achieves the following results: by using the L1 norm to transform multi-dimensional monitoring vectors into single-dimensional quantified values, it effectively integrates information from various parameters within the vector (such as the trajectory density and activity ratio of the first vector, and the temperature, humidity, and ammonia concentration standard deviation of the second vector), avoiding the one-sidedness of single-parameter analysis; simultaneously, by introducing the norm standard deviation to calculate the safety assessment coefficient, it fully considers the fluctuation trend of historical data—if the L1 norm standard deviation is used to calculate the safety assessment coefficient for a certain monitoring area, it will be more accurate to say that the L1 norm standard deviation is the standard deviation of the monitoring vector. L1i Or ║B║ L1i Short-term fluctuations can lead to a larger standard deviation, which in turn affects the value of the safety assessment coefficient Q, allowing Q to more accurately reflect the dynamic changes in risk. This quantitative calculation and threshold comparison method eliminates the subjectivity of traditional experience-based judgments, making safety level classification more objective and significantly reducing the probability of misjudgment due to human bias.

[0042] This solution establishes a standardized risk assessment process through explicit mathematical calculations (L1 norm calculation, standard deviation calculation, and safety assessment coefficient formula) and fixed threshold comparison rules. Regardless of the operator's experience, as long as the same monitoring vector data is input, a consistent safety assessment coefficient and risk level result can be obtained through a unified process. This avoids inconsistencies in assessment results caused by differences in operating habits and experience, significantly improving the repeatability and consistency of risk assessment across different monitoring areas and time points. This facilitates unified risk management and horizontal comparison for aquaculture enterprises across different regions.

[0043] The calculation of the safety assessment coefficient Q incorporates historical norm data and its standard deviation over a given unit of time, thus reflecting both the static characteristics of the current data (such as the ║A║ of a certain unit of time) and the ║A║ of the current data. L1i It can capture both the size and the dynamic fluctuations of data (such as multiple consecutive units of time ║B║). L1i The standard deviation of the animal activity (e.g., track density) or environmental conditions (e.g., temperature and humidity standard deviation) changes slightly but persistently. These changes are directly reflected in the Q-value, allowing the system to detect potential risks earlier. Before the risk escalates, a decrease in the Q-value can trigger a level adjustment. Compared to the traditional "black and white" judgment method, this significantly improves sensitivity to risk trends, providing a longer window for early prevention and control. The first and second safety assessment coefficient thresholds preset in the scheme are not fixed values. Farming enterprises can flexibly adjust the thresholds based on the disease susceptibility of different animal breeds (e.g., young animals are more sensitive than adults, so a higher first threshold can be set), the risk tolerance at different stages of farming (e.g., the threshold can be appropriately lowered before slaughter to strictly control risk), and the prevalence of diseases in different regions (e.g., the threshold can be increased in high-incidence areas to strengthen early warning). This flexible threshold setting mechanism allows the safety level determination to accurately adapt to diverse farming scenarios and prevention and control needs, enhancing the system's practical value. By using a quantified safety assessment coefficient Q to classify levels, a quantitative overall risk assessment can be conducted based on the distribution of Q values ​​in each region (such as the proportion of low-level regions and the average value of Q values), rather than simply relying on the number of levels. This makes the overall early warning results more in line with the actual severity of risks and further optimizes the collaborative operation efficiency of the risk early warning module.

[0044] In one embodiment of the present invention, a risk warning module provides a first warning for animal monitoring areas with a low safety level, and a second warning for the overall animal disease prevention risk within the current monitoring range based on the corresponding disease prevention safety level of each biological monitoring area. Specifically, the risk warning module includes a first warning module and a second warning module, wherein the first warning module is used to provide a first warning for biological monitoring areas with a low disease prevention safety level; and the second warning module is used to provide a warning for the overall animal disease prevention risk within the current monitoring range based on the corresponding disease prevention safety level of each biological monitoring area.

[0045] This includes issuing early warnings about the overall animal disease prevention risk within the current monitoring area based on the corresponding disease prevention safety level of each biological monitoring area, including: Retrieve animal monitoring areas with a current security level of medium and low. The total number of animal monitoring areas with a current security level of medium and low is compared with a preset number threshold. When the total number of animal monitoring areas with a current security level of medium and the total number of animal monitoring areas with a current security level of low does not exceed the preset number threshold, the security assessment coefficients corresponding to each animal monitoring area with a security level of medium and the security assessment coefficients corresponding to each animal monitoring area with a security level of low are retrieved. The overall safety coefficient of the animal disease prevention scope is obtained by using the safety assessment coefficients corresponding to each animal monitoring area with a medium safety level and the safety assessment coefficients corresponding to each animal monitoring area with a low safety level. The overall safety factor of the entire animal disease prevention scope is obtained by the following formula: Where Z represents the overall safety coefficient of the entire animal disease prevention and control area; N represents the number of animal monitoring areas with a medium safety level; M represents the number of animal monitoring areas with a low safety level; Q zi Q represents the safety assessment coefficient corresponding to the i-th intermediate-level animal monitoring area; di Let Q represent the safety assessment coefficient corresponding to the i-th low-level animal monitoring area; 02 Indicates the threshold for the second security assessment coefficient; ║A║ L1bx The norms ║A║ represent the N animal monitoring areas with a medium security level, respectively. L1 Standard deviation; ║A║ L1by The norms ║A║ represent the M animal monitoring areas with a low security level, respectively. L1 Standard deviation; When the overall safety factor of the overall animal disease prevention scope is lower than the preset overall safety factor threshold, it is determined that the overall animal disease prevention risk is high, and an overall animal disease prevention risk warning is issued.

[0046] The working principle of the above technical solution is as follows: After realizing the safety level division of animal monitoring areas, the first early warning module (for low-level areas) and the second early warning module (overall risk early warning) can trigger the early warning mechanism more accurately. When the Q value is lower than the second threshold, the first early warning module can directly lock the corresponding area and start a special early warning. When the second early warning module is calculating the overall risk, it can perform a quantitative overall risk assessment based on the distribution of Q values ​​in each area (such as the proportion of low-level areas and the average Q value), rather than simply relying on the number of levels. This makes the overall early warning result more in line with the actual severity of the risk and further optimizes the collaborative operation efficiency of the risk early warning module.

[0047] The technical solution in this embodiment is the core process of the second early warning module in the risk warning module to realize overall animal disease prevention risk warning. It completes the overall risk warning through four steps: "regional screening - quantity comparison - coefficient calculation - early warning judgment". First, the second early warning module retrieves areas with medium and low safety levels from the disease prevention safety level determination module, excluding areas with high safety levels and focusing on potentially risky areas. Next, it counts the total number of medium and low-level areas and compares it with a preset quantity threshold. If the total number does not exceed the threshold, it further retrieves the safety assessment coefficient Q corresponding to each medium-level area. zi And the security assessment coefficient Q corresponding to each lower-level area di Then, substitute the values ​​into the preset formula (Number of intermediate regions N, number of low-level regions M, Q). zi Q di Second security assessment coefficient threshold Q 02 Intermediate regional norm ║A║ L1 Standard deviation ║A║ L1bx Low-level regional norm ║A║ L1 Standard deviation ║A║ L1by Calculate the overall safety coefficient Z for the entire animal disease prevention scope; finally, compare the overall safety coefficient Z with the preset overall safety coefficient threshold. If Z is lower than the threshold, the overall animal disease prevention risk is determined to be high, triggering an overall risk warning.

[0048] The effect of the above technical solution is as follows: This embodiment first filters out two types of risk areas, medium and low, avoiding the problem of focusing only on low-risk areas while ignoring the potential risks of medium-risk areas, thus achieving comprehensive coverage of all non-high-risk areas; then, it combines the number of the two types of areas with the safety assessment coefficient to comprehensively calculate the overall risk, taking into account both the scale of the number of areas and the risk level of individual areas (through Q). zi Q di This approach reflects the overall risk coverage by incorporating the fluctuation characteristics of animal activity data within the region and integrating risk information from multiple dimensions. This avoids misjudgments of overall risk caused by single-dimensional analysis.

[0049] On the one hand, a preliminary screening is conducted using a quantity threshold. If the total number of intermediate and low-risk areas exceeds the threshold, the overall risk can be quickly determined to be high, reducing unnecessary complex calculations. If the total number does not exceed the threshold, a more refined assessment is performed using a comprehensive safety factor, avoiding over-warning due to a small number of risky areas. On the other hand, a second safety assessment threshold Q is introduced into the calculation of the comprehensive safety factor. 02 As a reference benchmark, the differences in safety assessment coefficients between intermediate and low-level areas are taken into account, and the norms of both types of areas (║A║) are also incorporated. L1The standard deviation reflects the consistency of animal activity patterns within a risk area. A large standard deviation for a certain type of area indicates that there are significant differences in animal activity patterns within that area and that the risk distribution is uneven. This characteristic can be reflected through coefficient calculation, making the overall risk assessment more consistent with the actual risk distribution and significantly enhancing accuracy.

[0050] This embodiment achieves tiered risk warning response through a hierarchical judgment logic of "quantity comparison - coefficient calculation". When the total quantity in intermediate and low-level areas exceeds the threshold, a warning can be quickly triggered, suitable for emergency scenarios with concentrated risk outbreaks, giving prevention and control personnel time to intervene quickly. When the total quantity does not exceed the threshold, a comprehensive safety coefficient is used for further judgment, avoiding a "one-size-fits-all" warning mode. Even when the risk scale is small but the risk level is high, the risk can still be accurately identified through coefficient calculation, ensuring that the warning is neither delayed nor excessive, thus optimizing the response efficiency under different risk scenarios. The calculation result of the comprehensive safety coefficient can not only determine the overall risk level, but also indirectly reflect the main source of risk—if the Q of the intermediate and low-level areas is calculated... di A high weighting indicates that the overall risk is mainly driven by low-risk areas, and prevention and control resources can be prioritized for these areas; if the weighting of medium-risk areas is high, the risk is low. L1bx A large number indicates significant variations in animal activity within the intermediate-level region, necessitating differentiated investigations for such areas. This early warning result, encompassing both the source and distribution characteristics of risk, provides control personnel with a clearer direction for resource allocation, preventing resource waste and enhancing the targeting and effectiveness of control measures. The plan directly utilizes the safety level, safety assessment coefficient, and norm derived from the previous epidemic prevention safety level determination module. L1 Data such as standard deviation can be reused without re-collection or calculation, reducing system computing power consumption. At the same time, the calculation logic of the comprehensive safety factor is consistent with that of the previous safety assessment factor, both incorporating data fluctuation characteristics and threshold references. This ensures the logical consistency between overall risk warning and individual area level determination, avoiding contradictions in risk judgment caused by differences in data dimensions or calculation logic. It also deepens the collaborative operation between modules and improves the stability and reliability of the entire risk warning module.

[0051] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An animal disease prevention and control monitoring and management system, characterized in that, include; The multi-dimensional data acquisition module is used to collect animal living data and animal living environment data corresponding to each animal monitoring area in real time, and upload the animal living data and animal living environment data corresponding to the animal monitoring area to the data management module. The data management module is used to preprocess and store the real-time collected animal living data and animal living environment data, and dynamically adjust the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area according to the fluctuation of the animal living data and animal living environment data corresponding to the animal monitoring area. The disease prevention and control prediction module is used to conduct a safety assessment of each animal monitoring area based on animal living data and animal living environment data, and to confirm the epidemic prevention safety level based on the analysis of the safety assessment results. The safety level includes high, medium and low levels. The risk warning module provides a first warning for animal monitoring areas with low safety levels, and a second warning for the overall animal disease prevention risk within the current monitoring range based on the corresponding disease prevention safety level of each biological monitoring area.

2. The animal disease prevention and control monitoring management system according to claim 1, characterized in that, The multidimensional data acquisition module includes: The data acquisition and control module is used to collect animal living data and animal living environment data corresponding to the animal monitoring area according to a preset data acquisition frequency after the multi-dimensional data acquisition module is activated. The animal living data includes movement trajectory and activity period; the environmental data includes temperature data, humidity data and ammonia concentration. The instruction judgment module is used to determine in real time whether a data acquisition frequency update instruction has been received from the data management module; The data acquisition and adjustment module is used to collect animal life data and animal living environment data according to the updated data acquisition frequency after the multidimensional data acquisition module receives the data acquisition frequency update instruction sent by the data management module. The data upload module is used to upload animal living data and animal living environment data corresponding to the animal monitoring area to the data management module.

3. The animal disease prevention and control monitoring management system according to claim 1 or 2, characterized in that, Upload animal living data and animal living environment data corresponding to the animal monitoring area to the data management module, including: Real-time retrieval of temperature and humidity data from the current data acquisition frequency and environmental data; The temperature and humidity data are compared with preset temperature and humidity reference values, respectively, and the data upload frequency is set according to the comparison results of the temperature and humidity data with the preset temperature and humidity reference values, respectively. According to the set data upload frequency, the animal living data and animal living environment data corresponding to the animal monitoring area are uploaded to the data management module.

4. The animal disease prevention and control monitoring management system according to claim 3, characterized in that, The data upload frequency is set based on the comparison results of temperature data and humidity data with preset temperature reference values ​​and humidity reference values, respectively, including: When the temperature data does not exceed the temperature reference value and the humidity data does not exceed the humidity reference value, the data upload frequency is set to the same frequency according to the current data acquisition frequency. When either the temperature data or the humidity data exceeds its corresponding temperature reference value or humidity reference value, the data upload frequency is set using the first data upload frequency setting strategy. When both the temperature and humidity data exceed their corresponding temperature and humidity reference values, the data upload frequency is set using the second data upload frequency setting strategy.

5. The animal disease prevention and control monitoring management system according to claim 1, characterized in that, The data management module includes: The data preprocessing module is used to preprocess the animal living data and animal living environment data collected in real time, wherein the preprocessing includes, but is not limited to, data noise reduction and data cleaning. The data storage and transmission module is used to treat each animal monitoring area as a data storage node, store the pre-processed animal living data and animal living environment data corresponding to the animal monitoring area to its corresponding storage node, and send the pre-processed animal living data and animal living environment data corresponding to each animal monitoring area to the risk warning module. The data acquisition frequency control module is used to dynamically adjust the data acquisition frequency of the multi-dimensional data acquisition module corresponding to the animal monitoring area based on the fluctuations in animal living data and animal living environment data corresponding to the animal monitoring area.

6. The animal disease prevention and control monitoring management system according to claim 1 or 5, characterized in that, The data acquisition frequency of the multi-dimensional data acquisition module in the animal monitoring area is dynamically adjusted based on fluctuations in animal living data and animal living environment data corresponding to the monitoring area, including: The multidimensional data acquisition module retrieves the current data upload frequency setting parameters for each animal monitoring area, wherein the setting parameters include the data upload frequency setting strategy used for the current data upload frequency and the current data upload frequency; When the current data upload frequency of the animal monitoring area is the same as the data acquisition frequency of the animal monitoring area, the data acquisition frequency of the multidimensional data acquisition module will not be adjusted. When the current data upload frequency of the animal monitoring area is set using the first data upload frequency setting strategy, the movement trajectory and activity time period in the current animal life data are retrieved. The trajectory density of an animal within its current habitat area is obtained by utilizing the movement trajectories in current animal life data. The strategy utilizes the trajectory density and activity time periods from the current animal living data in the animal monitoring area, combined with the first data upload frequency, to set the first percentage parameter P. 01 The control multidimensional data acquisition module regulates the data acquisition frequency corresponding to the animal monitoring area; When the current data upload frequency of the animal monitoring area is set using the second data upload frequency setting strategy, retrieve the movement trajectory and activity time period from the current animal life data, as well as the ammonia concentration from the environmental data; The current animal trajectory density within its habitat area is obtained by utilizing the movement trajectories in the current animal living data of the animal monitoring area. Using the current animal life data, including trajectory density, activity period, and ammonia concentration, combined with the second data upload frequency setting strategy, the second temperature percentage parameter P is employed. 02t Second humidity percentage parameter P 02w The control multidimensional data acquisition module regulates the data acquisition frequency corresponding to the animal monitoring area.

7. The animal disease prevention and control monitoring management system according to claim 1, characterized in that, The disease prevention and control prediction module is used to conduct safety assessments of each animal monitoring area based on animal living data and animal living environment data, and to confirm the epidemic prevention safety level based on the analysis of the safety assessment results, including: The data retrieval module is used to retrieve preprocessed animal living data and animal living environment data corresponding to each current animal monitoring area; The epidemic prevention and safety level determination module is used to conduct a safety assessment of each current biological monitoring area based on the pre-processed animal living data and animal living environment data corresponding to each current animal monitoring area. Based on the analysis of the safety assessment results, the corresponding epidemic prevention safety levels are divided, and the epidemic prevention safety level corresponding to each biological monitoring area is determined.

8. The animal disease prevention and control monitoring management system according to claim 7, characterized in that, Based on the preprocessed animal living data and animal living environment data corresponding to each current animal monitoring area, a safety assessment is conducted for each biological monitoring area. Based on the analysis of the safety assessment results, the corresponding epidemic prevention safety level is classified, determining the epidemic prevention safety level corresponding to each biological monitoring area, including: The trajectory density of animal activity within each unit of time is obtained from the movement trajectory in the preprocessed animal life data corresponding to each animal monitoring area; the value of the unit time length ranges from 24h to 72h. The percentage of animal activity time per unit time is obtained from the activity periods of each unit time in the preprocessed animal life data corresponding to each animal monitoring area. Using the trajectory density and animal activity time percentage for each unit of time corresponding to each animal monitoring area, the first monitoring vector A=[a] for each unit of time corresponding to each animal monitoring area is generated. 01 a 02 ], where a 01 This represents the trajectory density corresponding to animal activity per unit time; a 02 This indicates the percentage of time the animal spends in each unit of time. Based on the temperature data, humidity data, and ammonia concentration for each unit of time in each animal monitoring area, the standard deviation of temperature, standard deviation of humidity, and standard deviation of ammonia concentration for each unit of time are obtained. Using the standard deviations of temperature, humidity, and ammonia concentration within each unit of time, the second monitoring vector B=[b] for each animal monitoring area within each unit of time is obtained. 01 b 02 b 03 ], where b 01 b represents the standard deviation of temperature per unit time. 02 This represents the standard deviation of humidity per unit time; b 03 This indicates the ammonia concentration per unit time. Using the first monitoring vector A=[a] corresponding to each unit of time that has been experienced in each animal monitoring area 01 a 02 ] and the second monitoring vector B=[b 01 b 02 b 03 Determine the corresponding epidemic prevention and safety level for each biological monitoring area.

9. The animal disease prevention and control monitoring management system according to claim 8, characterized in that, Using the first monitoring vector A=[a] corresponding to each unit of time that has been experienced in each animal monitoring area 01 a 02 ] and the second monitoring vector B=[b 01 b 02 b 03 Determine the corresponding epidemic prevention and control safety level for each biomonitoring area, including: Based on the first monitoring vector A=[a] for each unit of time 01 a 02 Get the first monitoring vector A=[a 01 a 02 The corresponding L1 norm ║A║ L1 ; Based on the second monitoring vector B=[b] for each unit of time 01 b 02 b 03 Obtain the second monitoring vector B=[b 01 b 02 b 03 The corresponding L1 norm ║B║ L1 ; Using the norm ║A║ corresponding to each unit of time already experienced in each animal monitoring area L1 Sum of norms ║B║ L1 Generate safety assessment coefficients for each animal monitoring area; The safety level of an animal monitoring area is determined based on the quantitative relationship between the safety assessment coefficient of the animal monitoring area and the first safety assessment coefficient threshold and the second safety assessment coefficient threshold.

10. The animal disease prevention and control monitoring management system according to claim 1, characterized in that, Based on the current disease prevention and control safety level of each biological monitoring area, a second early warning is issued for the overall animal disease prevention and control risk within the current monitoring scope, including: Retrieve animal monitoring areas with a current security level of medium and low. The total number of animal monitoring areas with a current security level of medium and low is compared with a preset number threshold. When the total number of animal monitoring areas with a current security level of medium and the total number of animal monitoring areas with a current security level of low does not exceed the preset number threshold, the security assessment coefficients corresponding to each animal monitoring area with a security level of medium and the security assessment coefficients corresponding to each animal monitoring area with a security level of low are retrieved. The overall safety coefficient of the animal disease prevention scope is obtained by using the safety assessment coefficients corresponding to each animal monitoring area with a medium safety level and the safety assessment coefficients corresponding to each animal monitoring area with a low safety level. When the overall safety factor of the overall animal disease prevention scope is lower than the preset overall safety factor threshold, it is determined that the overall animal disease prevention risk is high, and an overall animal disease prevention risk warning is issued.

Images