An intelligent epidemic prevention system for animal husbandry and veterinary medicine

Abstract

The present invention relates to the technical field of data processing, and particularly relates to an intelligent epidemic prevention system for livestock veterinarians, including a pathogen survival probability acquisition module, a cold and heat stress acquisition module, an epidemic risk occurrence probability acquisition module, a health status acquisition module, and an epidemic outbreak risk acquisition module. First, determine the pathogen survival probability of the livestock environment, and obtain the cold and heat stress of animals in the livestock environment based on the fluctuation of the temperature data in the livestock environment, so as to combine the air quality of the livestock environment to obtain the epidemic risk occurrence probability of animals in the livestock environment. Then, analyze the epidemic risk occurrence probability and animal physiological parameters to obtain the health status of animals. Finally, obtain each aggregation area from the aggregation situation of animals in the livestock environment, and thus obtain the epidemic outbreak risk of the livestock environment based on the health status of animals in each aggregation area. The present invention can improve the accuracy of the monitoring results of the epidemic outbreak risk.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to an intelligent epidemic prevention system for animal husbandry and veterinary medicine. Background Art

[0002] During the process of veterinarians monitoring animal diseases in animal husbandry, the animal husbandry environment (i.e., the farm) is the habitat for the breeding and reproduction of viruses, and the poor state of the environment will exacerbate the reproduction of viruses, resulting in a relatively high epidemic risk among the animal husbandry groups. Therefore, it is crucial to monitor the outbreak risk of animal diseases in the animal husbandry environment. Currently, the outbreak risk is mainly obtained by monitoring the temperature and humidity data in the animal husbandry environment. This monitoring method considers fewer factors, and the monitoring results of the outbreak risk are somewhat one-sided, thus reducing the accuracy of the monitoring results of the outbreak risk. Summary of the Invention

[0003] In order to solve the technical problem of the low accuracy of the existing monitoring results of the outbreak risk in the farm, the purpose of the present invention is to provide an intelligent epidemic prevention system for animal husbandry and veterinary medicine, and the specific technical solution adopted is as follows:

[0004] In the first aspect of the present invention, there is provided an intelligent epidemic prevention system for animal husbandry and veterinary medicine, including:

[0005] A pathogen survival probability acquisition module, configured to determine the pathogen survival probability of the animal husbandry environment, where the pathogen survival probability is obtained from the ventilation efficiency and temperature and humidity data of the animal husbandry environment;

[0006] A heat and cold stress acquisition module, configured to obtain the heat and cold stress of animals in the animal husbandry environment based on the fluctuation of the temperature data in the animal husbandry environment;

[0007] An epidemic risk occurrence probability acquisition module, configured to obtain the epidemic risk occurrence probability of animals in the animal husbandry environment according to the pathogen survival probability, heat and cold stress, and air quality of the animal husbandry environment; the epidemic risk occurrence probability is directly proportional to the pathogen survival probability and heat and cold stress, and inversely proportional to the air quality;

[0008] A health status acquisition module, configured to analyze the epidemic risk occurrence probability and animal physiological parameters to obtain the health status of animals;

[0009] An epidemic outbreak risk acquisition module, configured to obtain the epidemic outbreak risk of the animal husbandry environment based on the health status of animals in each aggregation area; each aggregation area is obtained from the aggregation situation of animals in the animal husbandry environment.

[0010] In an exemplary embodiment, the process of obtaining the pathogen survival probability includes:

[0011] Obtain the mean value of the first data within the monitoring time period, and the proportion of the amount of data in the first data that is higher than the mean value; the first data is one of the temperature data and the humidity data;

[0012] Based on the mean value and the proportion of the amount of data, obtain an influence index of the first data on the pathogen survival probability; the influence index is directly proportional to the mean value and the proportion of the amount of data;

[0013] Based on the ventilation efficiency and the influence indexes of the temperature data and the humidity data, obtain the pathogen survival probability, which is inversely proportional to the ventilation efficiency and directly proportional to the influence indexes of the temperature data and the humidity data.

[0014] In an exemplary embodiment, the process of obtaining the ventilation efficiency includes:

[0015] Obtain the maximum value of the harmful gas concentration in the livestock environment within the monitoring time period;

[0016] Respectively obtain the concentration rising data segment and the concentration falling data segment adjacent to the maximum value of the harmful gas concentration;

[0017] Based on the concentration rising rate and the concentration falling rate of each maximum value of the harmful gas concentration, obtain a ventilation efficiency reference index corresponding to each maximum value of the harmful gas concentration; the ventilation efficiency reference index is inversely proportional to the concentration rising rate and the value of the maximum value of the harmful gas concentration, and directly proportional to the concentration falling rate; the concentration rising rate is the data change rate of the concentration rising data segment, and the concentration falling rate is the data change rate of the concentration falling data segment;

[0018] Fuse all the ventilation efficiency reference indexes corresponding to the maximum values of the harmful gas concentration to obtain the ventilation efficiency.

[0019] In an exemplary embodiment, the process of obtaining the heat and cold stress includes:

[0020] Obtain the temperature difference and the time interval between each temperature maximum value and the adjacent temperature minimum value in the temperature data within the monitoring time period;

[0021] Based on the temperature difference and the time interval, obtain the degree of temperature change between heat and cold corresponding to each temperature maximum value; the degree of temperature change between heat and cold is directly proportional to the temperature difference and inversely proportional to the time interval;

[0022] Fuse the degrees of temperature change between heat and cold corresponding to all the temperature maximum values to obtain the heat and cold stress.

[0023] In an exemplary embodiment, the animal physiological parameters include the amount of exercise and body temperature of the animal;

[0024] The process of obtaining the health status includes:

[0025] Obtain the correlation between the exercise amount and body temperature of an animal, as well as the degree of fever of the animal's body temperature;

[0026] Based on the probability of the occurrence of the epidemic risk, the correlation, and the degree of fever of the body temperature, obtain the health status of the animal; the health status is inversely proportional to the probability of the occurrence of the epidemic risk and the degree of fever of the body temperature, and is directly proportional to the correlation.

[0027] In an exemplary embodiment, the process of obtaining the correlation between the exercise amount and the body temperature includes:

[0028] Obtain the exercise amount curve and body temperature curve of the animal within the monitoring time period;

[0029] Obtain the similarity between the exercise amount curve and the body temperature curve as the correlation between the exercise amount and the body temperature.

[0030] In an exemplary embodiment, the process of obtaining the degree of fever of the body temperature includes: obtaining the proportion of the amount of body temperature data higher than the upper limit of the normal body temperature in the body temperature data of the animal within the monitoring time period as the degree of fever of the body temperature.

[0031] In an exemplary embodiment, the process of obtaining the risk of epidemic outbreak includes:

[0032] Obtain the number of abnormal animals with a health status lower than the preset health status threshold in each gathering area;

[0033] Based on the total number of animals, the number of abnormal animals, and the average health status of the animals in each gathering area, obtain the epidemic area outbreak risk of each gathering area; the epidemic area outbreak risk is directly proportional to the total number of animals and the number of abnormal animals, and is inversely proportional to the average health status;

[0034] Fuse the epidemic area outbreak risks of each gathering area to obtain the epidemic outbreak risk of the livestock environment.

[0035] In an exemplary embodiment, the intelligent epidemic prevention system further includes a ventilation adjustment module for increasing the ventilation power of the livestock environment when the epidemic outbreak risk of the livestock environment is greater than the preset epidemic outbreak risk threshold.

[0036] In an exemplary embodiment, the process of obtaining the air quality includes: obtaining the average concentration of harmful gases in the livestock environment within the monitoring time period and performing negative correlation on the average concentration of harmful gases to obtain the air quality.

[0037] The present invention has the following beneficial effects: Compared with the existing method of obtaining the risk of epidemic outbreak only based on the temperature and humidity data in the livestock environment, in addition to considering the temperature and humidity in the livestock environment, the present invention also considers the influence of the temperature change in the livestock environment on the cold and heat stress of animals, and the influence of the air quality in the livestock environment on the probability of the occurrence of the epidemic risk. More importantly, it also combines the influence of animal physiological parameters and the aggregation situation of animals in the livestock environment on the risk of epidemic outbreak. The factors considered are more comprehensive, thereby improving the comprehensiveness of the factors considered in the monitoring of the risk of epidemic outbreak, and further improving the accuracy of the monitoring results of the risk of epidemic outbreak. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 FIG. 6 is a schematic structural diagram of an intelligent epidemic prevention system for livestock veterinarians provided by an embodiment of the present invention;

[0039] Figure 2 FIG. 10 is a flowchart of steps corresponding to each module of an intelligent epidemic prevention system for livestock veterinarians provided by an embodiment of the present invention;

[0040] Figure 3 FIG. 14 is a flowchart for obtaining the ventilation efficiency provided by an embodiment of the present invention;

[0041] Figure 4 FIG. 18 is a flowchart for obtaining the survival probability of pathogens provided by an embodiment of the present invention;

[0042] Figure 5 FIG. 22 is a flowchart for obtaining the cold and heat stress provided by an embodiment of the present invention;

[0043] Figure 6 FIG. 26 is a flowchart for obtaining the health status provided by an embodiment of the present invention;

[0044] Figure 7 FIG. 30 is a flowchart for obtaining the risk of epidemic outbreak provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific embodiments, structures, features and their effects of the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this invention belongs. All the data information collected in this application is obtained with full consent and authorization, and the collection, use, and processing of relevant information need to comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0047] This embodiment provides an intelligent epidemic prevention system for animal husbandry and veterinary medicine. As Figure 1 shown, it includes a pathogen survival probability acquisition module, a cold and heat stress acquisition module, an epidemic risk occurrence probability acquisition module, a health status acquisition module, and an epidemic outbreak risk acquisition module. Each module can be a software module, which is essentially the corresponding method step; it can also be a hardware module, and the executed method step is configured in the hardware module so that the hardware module realizes the corresponding function. Correspondingly, the intelligent epidemic prevention system can be a software system, configured in relevant processors, computer hosts, and relevant veterinary supervision platforms; it can also be a hardware system, such as servers, computer hosts, etc. This embodiment does not limit the specific configuration methods of each module and the intelligent epidemic prevention system.

[0048] As Figure 2 shown, the method steps corresponding to each module are as follows:

[0049] The pathogen survival probability acquisition module is used to determine the pathogen survival probability of the animal husbandry environment, and the pathogen survival probability is obtained from the ventilation efficiency and temperature and humidity data of the animal husbandry environment;

[0050] The cold and heat stress acquisition module is used to obtain the cold and heat stress of animals in the animal husbandry environment based on the fluctuation of the temperature data of the animal husbandry environment;

[0051] The epidemic risk occurrence probability acquisition module is used to obtain the epidemic risk occurrence probability of animals in the animal husbandry environment according to the pathogen survival probability, cold and heat stress, and air quality of the animal husbandry environment; the epidemic risk occurrence probability is directly proportional to the pathogen survival probability and cold and heat stress, and inversely proportional to the air quality;

[0052] The health status acquisition module is used to analyze the epidemic risk occurrence probability and animal physiological parameters to obtain the health status of animals;

[0053] The epidemic outbreak risk acquisition module is used to obtain the epidemic outbreak risk of the animal husbandry environment based on the health status of animals in each gathering area; each gathering area is obtained from the gathering situation of animals in the animal husbandry environment.

[0054] The specific implementation processes of each module will be described below in conjunction with the accompanying drawings.

[0055] A pathogen survival probability acquisition module, which is used to determine the pathogen survival probability of the livestock environment, and the pathogen survival probability is obtained from the ventilation efficiency and temperature and humidity data of the livestock environment.

[0056] In this embodiment, the livestock environment is the breeding environment of the animals being raised, specifically a farm, and further an indoor farm. The animals raised in the farm are of the same kind. Taking the most common pigs as an example. When the situation in the farm deteriorates, it may cause diseases in the pig herd. Therefore, it is necessary to analyze various environmental parameters in the farm in real time to judge the risk of an epidemic outbreak.

[0057] Temperature sensors and humidity sensors are arranged in the farm to detect the temperature data and humidity data of the farm. A ventilation system, such as a ventilation fan and other equipment, is also arranged in the farm to achieve ventilation of the farm. A harmful gas concentration sensor is also arranged in the farm to detect the harmful gas concentration in the farm. Since the most common harmful gas in the farm that causes relatively great damage to the animals' bodies is ammonia, then, the harmful gas concentration sensor in this embodiment is an ammonia concentration sensor, and the obtained harmful gas concentration is the ammonia concentration.

[0058] Preset a monitoring time period, and the time length of this monitoring time period is set according to actual needs, such as 20 minutes. Moreover, the end time of this monitoring time period can be the current time to achieve real-time epidemic outbreak risk monitoring based on the data information within the monitoring time period. The sampling frequency of each sensor in this embodiment is set according to the actual situation, such as once per second. Then, there are multiple sampling moments within the monitoring time period. In addition, the sampling frequencies of each sensor are the same and the data is collected synchronously.

[0059] Taking pigs as an example, when the farm is in a high-temperature and high-humidity state, it will accelerate the survival state of various pathogens (such as foot-and-mouth disease virus and erysipelothrix rhusiopathiae) in the livestock environment. And when the ventilation situation of the farm is poor, it will cause various harmful gases and dust to stay, thus increasing the spread of various pathogens. Therefore, first obtain the ventilation efficiency of the livestock environment during the monitoring time period. The ventilation efficiency is essentially the ventilation condition of the farm. The better the ventilation condition, the lower the pathogen survival probability in the farm. In an exemplary embodiment, as Figure 3 shown, the following gives a specific acquisition process of the ventilation efficiency:

[0060] Step 1-1: Obtain the maximum value of the harmful gas concentration in the harmful gas concentration of the livestock environment during the monitoring time period.

[0061] The harmful gas concentration sensor collects the harmful gas concentration in the farm according to the sampling frequency, obtains the harmful gas concentration at each sampling moment, and obtains the time series sequence of the harmful gas concentration in the farm during the monitoring period according to the time sequence. The curve fitting can also be performed on the time series sequence of the harmful gas concentration to obtain the change curve of the harmful gas concentration. Then, each maximum value of the harmful gas concentration in the time series sequence of the harmful gas concentration is obtained.

[0062] Step 1-2: Respectively obtain the concentration rising data segment and the concentration falling data segment adjacent to the maximum value of the harmful gas concentration.

[0063] It should be understood that in the time series sequence of the harmful gas concentration, the maximum value of the harmful gas concentration is larger than the values of the harmful gas concentration data on both sides. For any maximum value of the harmful gas concentration, obtain the concentration rising data segment and the concentration falling data segment adjacent to the maximum value of the harmful gas concentration. Since the data change situation of the data segment before the maximum value of the harmful gas concentration in the time series sequence of the harmful gas concentration is that the harmful gas concentration gradually rises, then, obtain the data segment before the maximum value of the harmful gas concentration and adjacent to the maximum value of the harmful gas concentration as the concentration rising data segment; and obtain the data segment after the maximum value of the harmful gas concentration and adjacent to the maximum value of the harmful gas concentration as the concentration falling data segment. In this embodiment, the amount of data included in the concentration rising data segment and the concentration falling data segment is set according to actual needs, and the amount of data included needs to satisfy that both the concentration rising data segment and the concentration falling data segment are monotonically changing data segments, such as 5 data. In addition, for the maximum value of the harmful gas concentration close to the edge of the time series sequence of the harmful gas concentration, the amount of data included in the corresponding concentration rising data segment and concentration falling data segment may not meet the requirements, then these maximum values of the harmful gas concentration can be discarded and not participate in the subsequent acquisition of the ventilation efficiency.

[0064] Step 1-3: Obtain the ventilation efficiency reference index corresponding to each maximum value of the harmful gas concentration according to the concentration rising rate and the concentration falling rate of each maximum value of the harmful gas concentration.

[0065] For any maximum value of the harmful gas concentration, obtain the data change rate of the concentration rising data segment of the maximum value of the harmful gas concentration as the concentration rising rate. In an exemplary embodiment, obtain the slope of each data point in the curve segment corresponding to the concentration rising data segment, and then calculate the average slope as the concentration rising rate. Similarly, obtain the data change rate of the concentration falling data segment of the maximum value of the harmful gas concentration as the concentration falling rate. In an exemplary embodiment, obtain the slope of each data point in the curve segment corresponding to the concentration falling data segment, and then calculate the absolute value of the average slope as the concentration falling rate.

[0066] When the ventilation condition in the farm is good, the concentration of harmful gases cannot rise to a high level, and even if it rises, it will quickly decline due to good ventilation. Therefore, the better the ventilation efficiency in the farm, the smaller the concentration rise rate in the concentration rise data segment before the maximum value of the harmful gas concentration, and the greater the concentration decline rate in the concentration decline data segment after the maximum value of the harmful gas concentration. Moreover, the better the ventilation efficiency in the farm, the less likely there is a large concentration of harmful gases. Then, the better the ventilation efficiency in the farm, the smaller the value of the maximum harmful gas concentration. Therefore, the ventilation efficiency reference index of the maximum harmful gas concentration is inversely proportional to the concentration rise rate and the value of the maximum harmful gas concentration, and is directly proportional to the concentration decline rate.

[0067] In an exemplary embodiment, a specific quantification method for the ventilation efficiency reference index of the maximum harmful gas concentration is given as follows:

[0068] ;

[0069] Among them, is the ventilation efficiency reference index of the j-th maximum harmful gas concentration, is the value of the j-th maximum harmful gas concentration, is the concentration decline rate corresponding to the j-th maximum harmful gas concentration, is the concentration rise rate corresponding to the j-th maximum harmful gas concentration.

[0070] represents a normalization function. The normalization method here can be: obtain the maximum and minimum values in all corresponding to the maximum harmful gas concentrations, and then use the maximum-minimum normalization method to normalize the of the j-th maximum harmful gas concentration so that its value range is in [0, 1], which is convenient for subsequent ventilation efficiency calculation.

[0071] Step 1-4: Integrate the ventilation efficiency reference indexes corresponding to all the maximum harmful gas concentrations to obtain the ventilation efficiency.

[0072] Integrate the ventilation efficiency reference indexes corresponding to all the maximum harmful gas concentrations. In an exemplary embodiment, calculate the average value of the ventilation efficiency reference indexes corresponding to all the maximum harmful gas concentrations as the ventilation efficiency.

[0073] Since the ventilation efficiency of the farm and the temperature and humidity data of the farm determine the survival probability of pathogens in the farm. Therefore, obtain the survival probability of pathogens in the farm according to the ventilation efficiency of the farm and the temperature and humidity data of the farm. In an exemplary embodiment, as Figure 4As shown, a specific process for obtaining the survival probability of pathogens is given:

[0074] Steps 1-5: Obtain the mean of the first data during the monitoring period and the proportion of the data volume in the first data that is higher than the mean.

[0075] Based on the temperature sensor, humidity sensor, and the preset sensor sampling frequency, during the monitoring period, the time series of temperature data and the time series of humidity data of the farm can be obtained.

[0076] For the sake of convenience in explanation, it is assumed that the first data is one of the temperature data and the humidity data. Obtain the mean of the first data during the monitoring period and the proportion of the data volume in the first data that is higher than the mean.

[0077] Specifically: For the temperature data, obtain the temperature mean of the time series of temperature data during the monitoring period. Then, the magnitude relationship between each temperature data in the time series of temperature data and the temperature mean can be obtained, so as to obtain the temperature data higher than the temperature mean. Furthermore, obtain the data volume of the temperature data higher than the temperature mean, and then obtain the ratio of this data volume to the total number of temperature data in the time series of temperature data as the proportion of the data volume of the temperature data higher than the temperature mean; similarly, for the humidity data, obtain the humidity mean of the time series of humidity data during the monitoring period. Then, the magnitude relationship between each humidity data in the time series of humidity data and the humidity mean can be obtained, so as to obtain the humidity data higher than the humidity mean. Furthermore, obtain the data volume of the humidity data higher than the humidity mean, and then obtain the ratio of this data volume to the total number of humidity data in the time series of humidity data as the proportion of the data volume of the humidity data higher than the humidity mean.

[0078] Steps 1-6: Obtain the influence index of the first data on the survival probability of pathogens according to the mean and the proportion of the data volume.

[0079] Since the higher the temperature, the higher the survival probability of pathogens, and the higher the humidity, the higher the survival probability of pathogens. Also, since the mean of the first data and the proportion of the data volume in the first data that is higher than the mean represent the data levels of the temperature data and the humidity data, the higher the mean of the first data and the proportion of the data volume in the first data that is higher than the mean, the higher the data levels of the temperature data and the humidity data, and the higher the survival probability of pathogens. Then, the influence index of the first data on the survival probability of pathogens is proportional to the mean of the first data and the proportion of the data volume in the first data that is higher than the mean. Moreover, the higher the influence index on the survival probability of pathogens, the higher the survival probability of pathogens.

[0080] Correspondingly, the influence index of the temperature data is obtained from the temperature mean and the proportion of the data volume of the temperature data higher than the temperature mean; the influence index of the humidity data is obtained from the humidity mean and the proportion of the data volume of the humidity data higher than the humidity mean.

[0081] In an exemplary embodiment, a specific quantification formula for the influence index of the first data on the pathogen survival probability is given as follows:

[0082] ;

[0083] Wherein, represents the influence index of the i-th data on the pathogen survival probability, where i is equal to 1 or 2. When i is equal to 1, the i-th data is temperature data; when i is equal to 2, the i-th data is humidity data; is the proportion of the amount of data higher than the mean value of the i-th data in the i-th data, is the total amount of the i-th data, represents the proportion of the amount of data higher than the mean value in the i-th data; is the mean value of the i-th data, represents the maximum allowable value of the i-th data. When the i-th data is temperature data, the maximum allowable value is the upper limit value of the temperature that may occur in the farm; when the i-th data is humidity data, the maximum allowable value is the upper limit value of the humidity that may occur in the farm.

[0084] Step 1-7: Obtain the pathogen survival probability according to the influence indexes of ventilation efficiency, temperature data, and humidity data.

[0085] Comprehensively analyze the pathogen survival probability from two aspects: ventilation efficiency and the influence indexes of temperature data and humidity data to obtain the pathogen survival probability. Since the higher the ventilation efficiency, the lower the pathogen survival probability; the higher the influence indexes of temperature data and humidity data, it means that the temperature and humidity in the farm are at a relatively high level, and the pathogen survival probability in the farm is higher. Therefore, the pathogen survival probability is inversely proportional to the ventilation efficiency and directly proportional to the influence indexes of temperature data and humidity data.

[0086] In an exemplary embodiment, a specific quantification method for the pathogen survival probability is given as follows:

[0087] ;

[0088] Wherein, represents the pathogen survival probability, represents the ventilation efficiency.

[0089] The cold and heat stress acquisition module is used to obtain the cold and heat stress of animals in the livestock environment based on the fluctuation of temperature data in the livestock environment.

[0090] The increased probability of pathogens surviving in farms increases the risk of epidemics. Furthermore, poor farm environments can affect the animals themselves, increasing the likelihood of epidemics. Therefore, it is important to analyze the impact of the farm environment on the animals themselves. When some farm environmental parameters are unsuitable for animal life, this can affect the animals themselves, increasing the risk of epidemics.

[0091] When the temperature on a farm fluctuates too rapidly, animals may experience heat or cold stress, which can lead to elevated cortisol levels, inhibiting lymphocyte activity and causing a 20% to 30% decrease in the antibody titer of the plague vaccine, increasing the risk of epidemics on the farm. This is because temperature fluctuations on the farm are crucial for determining whether heat or cold stress is present.

[0092] In an exemplary embodiment, Figure 5 As shown, a specific process of obtaining cold and heat stress sensitivity is given as follows:

[0093] Step 2-1: Obtain the temperature difference between each temperature maximum value and the adjacent temperature minimum value in the temperature data within the monitoring period, as well as the time interval.

[0094] Each temperature maximum value in the temperature data (i.e., the temperature data time series) within the monitoring time period is obtained. Next, the temperature minimum value adjacent to each temperature maximum value is obtained. In this embodiment, the temperature minimum value adjacent to each temperature maximum value is specifically the temperature minimum value immediately following each temperature maximum value. For temperature maximum values that do not have an immediately following temperature minimum value, subsequent heat stress calculations are not performed.

[0095] The temperature difference between each temperature maximum value and the next adjacent temperature minimum value, as well as the time interval between each temperature maximum value and the next adjacent temperature minimum value are obtained.

[0096] Step 2-2: Based on the temperature difference and time interval, obtain the degree of temperature change corresponding to each temperature maximum value.

[0097] The greater the difference between each temperature maximum and the next temperature minimum, the greater the temperature difference and the more dramatic the temperature fluctuations. Consequently, the more severe the heat and cold stresses that temperature fluctuations may cause to animals. The shorter the time interval between each temperature maximum and the next temperature minimum, the more rapid the temperature drop from high to low, the more dramatic the temperature fluctuations, and the more severe the heat and cold stresses that temperature fluctuations may cause to animals.

[0098] Based on the temperature difference and time interval, the degree of temperature change corresponding to each temperature maximum is obtained. The degree of temperature change is proportional to the temperature difference and inversely proportional to the time interval.

[0099] In an exemplary embodiment, a specific quantification method for the degree of temperature change between hot and cold is given as follows:

[0100] ;

[0101] where is the degree of temperature change corresponding to the th temperature maximum value, is the time interval between the th temperature maximum value and the adjacent minimum value point thereafter, is the temperature difference between the th temperature maximum value and the adjacent minimum value point thereafter.

[0102] The normalization method here can be: obtain the maximum and minimum values of corresponding to all temperature maximum values, and then use the maximum-minimum normalization method to normalize of the th temperature maximum value, so that its numerical range is in [0, 1], which is convenient for subsequent calculation of cold and heat stress.

[0103] Step 2-3: Combine the degrees of temperature change between hot and cold corresponding to all temperature maximum values to obtain the cold and heat stress.

[0104] Combine the degrees of temperature change between hot and cold corresponding to all temperature maximum values. In an exemplary embodiment, here calculate the average value of the degrees of temperature change between hot and cold corresponding to all temperature maximum values as the required cold and heat stress.

[0105] The epidemic risk occurrence probability acquisition module is used to obtain the epidemic risk occurrence probability of animals in the livestock environment according to the pathogen survival probability, cold and heat stress, and the air quality of the livestock environment.

[0106] When the ammonia concentration is relatively high, it may damage the cilia of the animal respiratory tract, reduce the mucosal immune barrier function, and cause animals to be more likely to have epidemic risks. Therefore, obtain the air quality according to the harmful gas concentration. Specifically: obtain the average value of the harmful gas concentration in the farm during the monitoring period, and perform negative correlation on the obtained average value of the harmful gas concentration to obtain the air quality. In an exemplary embodiment, the negative correlation here is specifically negative correlation normalization, and the method of negative correlation normalization adopted can be: exp(-y), where y is the data that needs to be negatively correlated normalized, and exp is the exponential function with the natural constant e as the base.

[0107] The higher the survival probability of the pathogen, the higher the probability of the occurrence of the epidemic risk of animals in the farm; the stronger the cold and heat stress, the higher the probability of the occurrence of the epidemic risk of animals in the farm; the worse the air quality in the farm, the higher the probability of the occurrence of the epidemic risk of animals in the farm. Therefore, the probability of the occurrence of the epidemic risk is directly proportional to the survival probability of the pathogen and the cold and heat stress, and inversely proportional to the air quality. According to the survival probability of the pathogen, the cold and heat stress, and the air quality of the livestock environment, the probability of the occurrence of the epidemic risk can be obtained.

[0108] In an exemplary embodiment, a specific quantification method for the probability of the occurrence of the epidemic risk is given as follows:

[0109] ;

[0110] Among them, represents the probability of the occurrence of the epidemic risk, represents the cold and heat stress, represents the air quality. Here, the method of averaging the three indicators is adopted, that is, the method of weighted summation with equal weights, to fuse these three indicators to obtain the probability of the occurrence of the epidemic risk.

[0111] The health status acquisition module is used to analyze the probability of the occurrence of the epidemic risk and the animal physiological parameters to obtain the health status of the animal.

[0112] When there is a probability of the epidemic risk for an animal, if there are also some adverse reactions in the physical state of the animal, it will affect the health status of the animal. Therefore, it is necessary to monitor the physiological parameters of the animal. The animal physiological parameters include the exercise amount and body temperature of the animal. Correspondingly, a motion sensor and a body temperature sensor need to be set on the animal body.

[0113] Since there are multiple animals in the farm, any one animal is taken as an example for illustration below. In an exemplary embodiment, a smart ear tag is installed on the animal's ear. The smart ear tag is built-in with a body temperature sensor and a heart rate sensor, which can obtain the body temperature and heart rate data of the animal in real time. Moreover, a locator is also built-in in the smart ear tag, which is used to obtain the position information of the animal in real time, so as to obtain the motion state and exercise amount data of the animal. It should be understood that the acquisition frequency of each sensor built-in in the smart ear tag can be the same as and synchronized with the acquisition frequency of each environmental sensor in the above text.

[0114] When there is an epidemic risk in a farm, animals in better physical condition usually have better resistance and can better resist the epidemic, while weaker animals may have physical abnormalities due to the poor environment. Moreover, when animals are relatively healthy, their physiological and exercise states will be relatively normal, their body temperatures will be within the normal range and they will appear more excited, and their exercise amounts will be in a relatively high normal state. When animals do not engage in strenuous exercise, the body temperatures of healthy animals will be within the normal range and relatively low. If an animal's body temperature is also high when it is not exercising, the animal may be in a state of persistent fever, which will inhibit the activity of lymphocytes and reduce the antibody effect, and the animal's health condition will be poor. Therefore, the health condition of animals is related to the probability of the epidemic risk in the farm and the physiological parameters of the animals. In an exemplary embodiment, as Figure 6 shown, a specific process for obtaining the health condition is given as follows:

[0115] Step 4-1: Obtain the correlation between the exercise amount and body temperature of the animal, and the degree of body temperature fever of the animal.

[0116] The health condition is related to the correlation between the exercise amount and body temperature of the animal, and the degree of body temperature fever of the animal. Therefore, it is necessary to obtain the correlation between the exercise amount and body temperature of the animal, and the degree of body temperature fever of the animal.

[0117] Among them, the process for obtaining the correlation between the exercise amount and body temperature of the animal is specifically as follows: Based on the intelligent ear tag, obtain the exercise amount curve and body temperature curve of the animal within the monitoring time period. Among them, the process for obtaining the exercise amount curve is: Obtain the moving distance of the animal at each sampling moment in the intelligent ear tag, and use the moving distance to represent the exercise amount. The greater the moving distance, the greater the exercise amount. The moving distance is the distance between the position of the animal at each sampling moment and the position of the animal at the previous sampling moment (the distance at the first sampling moment is 0). Fit the moving distances of the animal at each sampling moment within the monitoring time period into an exercise amount curve. The process for obtaining the body temperature curve is: Obtain the body temperature data of the animal at each sampling moment within the monitoring time period, and fit it into a body temperature curve.

[0118] Obtain the similarity between the exercise amount curve and the body temperature curve as the correlation between the exercise amount and body temperature. Among them, the similarity can be the Pearson correlation coefficient, cosine similarity, etc. In this embodiment, the Pearson correlation coefficient is taken as an example, that is, obtain the Pearson correlation coefficient between the exercise amount curve and the body temperature curve, and then normalize the Pearson correlation coefficient. The result obtained is the correlation between the exercise amount and body temperature. Since the numerical range of the Pearson correlation coefficient is [-1, 1], the method for normalizing the Pearson correlation coefficient can be: Calculate the sum value of the Pearson correlation coefficient being the numerical value 1, and then divide the sum value by 2.

[0119] Under normal circumstances, there is a relatively high correlation between the amount of exercise of an animal and its body temperature. Within a certain range, the greater the amount of exercise, the greater the increase in body temperature. Correspondingly, the worse the health condition of the animal, the lower the correlation between the amount of exercise and the body temperature.

[0120] The degree of body temperature fever characterizes the severity of the animal's body temperature fever. In an exemplary embodiment, the process of obtaining the degree of body temperature fever is as follows: First, determine the upper limit value of the normal body temperature of the animal. Under normal circumstances, for pigs, the upper limit value of the normal body temperature can be set to 39.0 °C. Compare the body temperature data of each sampling moment of the animal during the monitoring period with the upper limit value of the normal body temperature, obtain the amount of body temperature data higher than the upper limit value of the normal body temperature in the body temperature data of the animal during the monitoring period, and then perform a division operation with the total number of the body temperature data of the animal during the monitoring period. The result obtained is the proportion of the body temperature data higher than the upper limit value of the normal body temperature in the body temperature data of the animal during the monitoring period. Take this proportion of the body temperature data as the degree of body temperature fever. Therefore, the higher the proportion of the body temperature data, the more body temperature data with too high body temperature appears during the monitoring period, and the more severe the degree of body temperature fever.

[0121] Step 4-2: Obtain the health condition of the animal based on the probability of the occurrence of the epidemic risk, the correlation, and the degree of body temperature fever.

[0122] Comprehensively analyze the health condition of the animal from three aspects: the probability of the occurrence of the epidemic risk, the correlation between the amount of exercise and the body temperature, and the degree of body temperature fever. Among them, the higher the probability of the occurrence of the epidemic risk, the more serious the impact of the epidemic on the health condition of the animal, and the worse the health condition of the animal; the higher the correlation between the amount of exercise and the body temperature, the better the health condition of the animal; the higher the degree of body temperature fever, the worse the health condition of the animal. Therefore, the health condition is inversely proportional to the probability of the occurrence of the epidemic risk and the degree of body temperature fever, and directly proportional to the correlation between the amount of exercise and the body temperature.

[0123] In an exemplary embodiment, a specific quantification method for the health condition is given as follows:

[0124] ;

[0125] Among them, is the health condition of the s-th animal, is the correlation between the amount of exercise and the body temperature of the s-th animal, is the degree of body temperature fever of the s-th pig. Here, the method of averaging the three indicators, that is, the method of weighted summation with equal weights, is used to fuse these three indicators to obtain the health condition.

[0126] The above operations obtain the health status of each animal in the farm, where there may be a part of the animals in good health and another part in poor health. However, when the animals in poor health gather together, there may be a certain risk of epidemic outbreak at this time.

[0127] An epidemic outbreak risk acquisition module, which is used to obtain the epidemic outbreak risk of the livestock environment based on the health status of the animals in each aggregation area; each aggregation area is obtained from the aggregation situation of the animals in the livestock environment.

[0128] Animals will gather in the farm. Then, the intelligent ear tags are used to obtain the position information of each animal in the farm, so as to obtain multiple aggregation areas according to the aggregation situation of the animals in the farm. In an exemplary embodiment, the aggregation situation of the animals in the farm can be clustered based on the existing clustering algorithm to obtain multiple clusters, and each cluster represents each aggregation area. For example: clustering is performed using the K-means clustering algorithm based on the distance between any two animals. Among them, the value of K needs to be determined in advance, and the value of K is set according to the clustering requirements.

[0129] Then, based on the health status of the animals in each aggregation area, the epidemic outbreak risk of the farm is obtained. In an exemplary embodiment, as Figure 7 shown, the following gives a specific acquisition process of the epidemic outbreak risk:

[0130] Step 5-1: Obtain the number of abnormal animals whose health status in each aggregation area is lower than the preset health status threshold.

[0131] Taking any one aggregation area for analysis, this aggregation area includes multiple animals. Preset a health status threshold, and the numerical range of this preset health status threshold is 0-1, and the specific value of this preset health status threshold is set according to the actual situation. This preset health status threshold is used to distinguish between low or high health status. Then, if a safer health status judgment logic is required, this preset health status threshold can be set slightly larger, so that the health status of more animals meets the judgment logic. In this embodiment, the preset health status threshold is taken as 0.6 as an example.

[0132] Compare the health status of each animal in this aggregation area with the preset health status threshold, and obtain the animals corresponding to the health status lower than the preset health status threshold. These animals are defined as abnormal animals, so as to obtain the number of abnormal animals. At the same time, obtain the total number of animals in this aggregation area.

[0133] Step 5-2: Obtain the epidemic area outbreak risk of each aggregation area according to the total number of animals, the number of abnormal animals and the average health status of the animals in each aggregation area.

[0134] Calculate the average health status of each animal in the aggregation area to obtain the average health status of the aggregation area.

[0135] The outbreak risk of the epidemic area in the aggregation area is affected by the total number of animals, the number of abnormal animals, and the average health status in the aggregation area. Among them, the more the total number of animals in the aggregation area, the higher the risk of epidemic outbreak in the aggregation area; the more the number of abnormal animals in the aggregation area, it means that there are more animals with poor health status in the aggregation area, then the higher the risk of epidemic outbreak in the aggregation area. Moreover, when the total number of animals and the number of abnormal animals in the aggregation area are more, it indicates that the animals with lower health status in the aggregation area will affect each other and spread outward continuously, so the higher the risk of epidemic outbreak. The better the average health status of the aggregation area, the better the overall health status of the animals in the aggregation area, and the lower the risk of epidemic outbreak in the aggregation area. Therefore, the outbreak risk of the epidemic area is directly proportional to the total number of animals and the number of abnormal animals, and inversely proportional to the average health status.

[0136] In an exemplary embodiment, in order to facilitate the specific quantification of the outbreak risk of the epidemic area, it is necessary to normalize the total number of animals and the number of abnormal animals in the aggregation area. The normalization method here can be: calculate the sum value of the total number of animals and the number of abnormal animals in each aggregation area, determine the maximum value and the minimum value from the sum values corresponding to each aggregation area, and then use the maximum-minimum normalization method to normalize the sum value of the total number of animals and the number of abnormal animals in the aggregation area.

[0137] The following gives a specific quantification process of the outbreak risk of the epidemic area in the aggregation area:

[0138] ;

[0139] Among them, is the outbreak risk of the epidemic area in the c-th aggregation area, is the average health status of the c-th aggregation area, is the result after normalizing the sum value of the total number of animals and the number of abnormal animals in the c-th aggregation area. It should be noted that according to the calculation method of the health status of each animal, the value of the average health status can be undoubtedly determined as a normalized value.

[0140] Using the above method, the outbreak risk of the epidemic area in each aggregation area is obtained.

[0141] Step 5-3: Integrate the outbreak risks of the epidemic areas in each aggregation area to obtain the outbreak risk of the livestock environment.

[0142] Integrate the epidemic area outbreak risks of each aggregation area. In an exemplary embodiment, calculate the average value of the epidemic area outbreak risks of all aggregation areas, and the obtained result is the epidemic outbreak risk of the farm.

[0143] When the ventilation condition in the farm is poor, various pathogens will breed, which will in turn lead to problems in the health of animals. And when the animals have health problems, it will continuously affect the health of other surrounding animals, resulting in the aggregation of unhealthy animals, and thus the farm has a relatively high risk of epidemic outbreak.

[0144] After obtaining the epidemic outbreak risk of the farm, the veterinarian can monitor the epidemic outbreak risk of the farm in real time and take relevant solutions.

[0145] In an exemplary embodiment, after obtaining the epidemic outbreak risk of the farm, the intelligent epidemic prevention system further includes a ventilation adjustment module.

[0146] In this embodiment, a preset epidemic outbreak risk threshold is set. The numerical range of the preset epidemic outbreak risk threshold is 0 - 1, and the specific value of the preset epidemic outbreak risk threshold is set according to the actual situation. The preset epidemic outbreak risk threshold is used to determine whether the epidemic outbreak risk of the farm is at a high or low level. Then, if a safer monitoring logic is required, the preset epidemic outbreak risk threshold can be set slightly smaller. In this embodiment, the preset epidemic outbreak risk threshold is taken as an example of 0.5.

[0147] The ventilation adjustment module is used to: compare the obtained epidemic outbreak risk of the farm with the preset epidemic outbreak risk threshold. When the epidemic outbreak risk is greater than the preset epidemic outbreak risk threshold, it means that the epidemic outbreak risk of the farm is relatively high and the ventilation situation of the farm needs to be improved. Then, on the basis of the existing ventilation power, increase the ventilation power of the farm, so as to improve the ventilation situation of the farm, optimize the air circulation in the farm, and further reduce the accumulation of pathogens. It should be understood that the increase range of the ventilation power of the farm is set according to the actual situation. For example: increase by a fixed value (such as increasing by 30% on the basis of the original ventilation power), or increase linearly. For example, the greater the epidemic outbreak risk, the greater the increase range of the ventilation power.

[0148] In addition, during the process of increasing the ventilation power, isolation and control measures can also be taken for the animals with health problems to prevent the further spread of the disease, so as to achieve the purpose of epidemic prevention and control.

[0149] It should be noted that: the above order of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0150] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An intelligent epidemic prevention system for animal husbandry and veterinary medicine, characterized in that, Including: A pathogen survival probability acquisition module, configured to determine the pathogen survival probability of the livestock environment, where the pathogen survival probability is obtained from the ventilation efficiency of the livestock environment and the temperature and humidity data; The acquisition process of the pathogen survival probability includes: Obtaining the mean value of the first data within the monitoring time period, and the proportion of the data volume in the first data that is higher than the mean value; the first data is one of the temperature data and the humidity data; According to the mean value and the data volume proportion, obtaining an influence index of the first data on the pathogen survival probability; the influence index is directly proportional to the mean value and the data volume proportion; According to the influence indexes of the ventilation efficiency, the temperature data, and the humidity data, obtaining the pathogen survival probability, where the pathogen survival probability is inversely proportional to the ventilation efficiency and directly proportional to the influence indexes of the temperature data and the humidity data; A cold and heat stress acquisition module, configured to obtain the cold and heat stress of animals in the livestock environment based on the fluctuation of the temperature data in the livestock environment; An epidemic risk occurrence probability acquisition module, configured to obtain the epidemic risk occurrence probability of animals in the livestock environment according to the pathogen survival probability, the cold and heat stress, and the air quality of the livestock environment; the epidemic risk occurrence probability is directly proportional to the pathogen survival probability and the cold and heat stress, and inversely proportional to the air quality; A health status acquisition module, configured to analyze the epidemic risk occurrence probability and the animal physiological parameters to obtain the health status of the animals; An epidemic outbreak risk acquisition module, configured to obtain the epidemic outbreak risk of the livestock environment based on the health status of animals in each aggregation area; each aggregation area is obtained from the aggregation situation of animals in the livestock environment.

2. The intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 1, characterized in that, The acquisition process of the ventilation efficiency includes: Obtaining the maximum value of the harmful gas concentration in the harmful gas concentration of the livestock environment within the monitoring time period; Respectively obtaining the concentration rising data segment and the concentration falling data segment adjacent to the maximum value of the harmful gas concentration; According to the concentration rising rate and the concentration falling rate of each maximum value of the harmful gas concentration, obtaining a ventilation efficiency reference index corresponding to each maximum value of the harmful gas concentration; the ventilation efficiency reference index is inversely proportional to the concentration rising rate and the value of the maximum value of the harmful gas concentration, and directly proportional to the concentration falling rate; the concentration rising rate is the data change rate of the concentration rising data segment, and the concentration falling rate is the data change rate of the concentration falling data segment; Fusing the ventilation efficiency reference indexes corresponding to all the maximum values of the harmful gas concentration to obtain the ventilation efficiency.

3. The intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 1, characterized in that, The acquisition process of the cold and heat stress includes: Obtaining the temperature difference and the time interval between each temperature maximum value and the adjacent temperature minimum value in the temperature data within the monitoring time period; Based on the temperature difference and the time interval, obtaining the temperature cold and heat change degree corresponding to each temperature maximum value; the temperature cold and heat change degree is directly proportional to the temperature difference and inversely proportional to the time interval; Fusing the temperature cold and heat change degrees corresponding to all the temperature maximum values to obtain the cold and heat stress.

4. The intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 1, characterized in that, The animal physiological parameters include the exercise amount and body temperature of the animals; The acquisition process of the health status includes: Obtaining the correlation between the exercise amount and body temperature of the animals, and the degree of body temperature fever of the animals; Based on the probability of the occurrence of the epidemic risk, the correlation, and the degree of body temperature fever, the health status of the animal is obtained; the health status is inversely proportional to the probability of the occurrence of the epidemic risk and the degree of body temperature fever, and directly proportional to the correlation.

5. The intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 4, characterized in that, The process of obtaining the correlation between the amount of exercise and body temperature includes: Obtaining the exercise amount curve and body temperature curve of the animal within the monitoring time period; Obtaining the similarity between the exercise amount curve and the body temperature curve as the correlation between the amount of exercise and body temperature.

6. The intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 4, characterized in that, The process of obtaining the degree of body temperature fever includes: obtaining the proportion of the amount of body temperature data higher than the upper limit of the normal body temperature in the body temperature data of the animal within the monitoring time period as the degree of body temperature fever.

7. An intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 1, characterized in that, The process of obtaining the risk of epidemic outbreak includes: Obtaining the number of abnormal animals with a health status lower than the preset health status threshold in each aggregation area; Based on the total number of animals, the number of abnormal animals, and the average health status of the animals in each aggregation area, the epidemic area outbreak risk of each aggregation area is obtained; the epidemic area outbreak risk is directly proportional to the total number of animals and the number of abnormal animals, and inversely proportional to the average health status; Fusing the epidemic area outbreak risks of each aggregation area to obtain the epidemic outbreak risk of the livestock environment.

8. An intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 1, characterized in that, The intelligent epidemic prevention system further includes a ventilation adjustment module for increasing the ventilation power of the livestock environment when the epidemic outbreak risk of the livestock environment is greater than the preset epidemic outbreak risk threshold.

9. The intelligent epidemic prevention system for animal husbandry and veterinary medicine according to claim 1, characterized in that, The process of obtaining the air quality includes: obtaining the average value of the harmful gas concentration in the livestock environment within the monitoring time period and performing negative correlation on the average value of the harmful gas concentration to obtain the air quality.

Images