A modern poultry farm environmental monitoring system and method

Abstract

The present invention discloses an environmental monitoring system and method for a modern poultry farm, and relates to the technical field of data processing. The environmental monitoring method for the modern poultry farm comprises: obtaining a temperature change sequence of each breeding area in the poultry farm, the temperature change sequence is used to characterize the temperature change of the breeding area within a preset time period; using each temperature change sequence, determining the clustering coefficient of the regional feature points in each breeding area at the current moment, the regional feature points are characteristic position points preset in the breeding area; clustering the regional feature points according to the clustering coefficient of each regional feature point at the current moment and the distance between each regional feature point, and obtaining at least one current cluster area; using the centroid position change information and regional range change information of the current cluster area, determining the poultry clustering rate of the current cluster area; according to the poultry clustering rate of the current cluster area, determining whether the environmental temperature of the poultry farm is abnormal.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an environmental monitoring system and method for a modern poultry farm. Background Art

[0002] Poultry is very sensitive to environmental conditions. Temperature, humidity, light and other factors directly affect their growth, health and production performance. Therefore, establishing a system that can monitor and intelligently control the farm environment in real time is the key to improving breeding efficiency and ensuring poultry health.

[0003] In the existing method, multiple temperature sensors are installed in the farm to monitor the temperature changes in the farm in real time and adjust the temperature in time.

[0004] However, with the expansion of the scale of breeding and the increase in the density of poultry breeding in farms, poultry tend to gather in the farms. In the case of poultry gathering, the sensor will detect false temperature anomalies, affecting the monitoring judgment of the monitoring system and reducing the accuracy of the monitoring system for actual temperature anomaly monitoring. Summary of the invention

[0005] The embodiments of the present invention provide a system and method for monitoring the environment of a modern poultry farm, which can improve the accuracy of monitoring actual temperature anomalies.

[0006] A first aspect of an embodiment of the present invention provides an environmental monitoring method for a modern poultry farm, comprising:

[0007] Obtaining a temperature change sequence of each breeding area in a poultry farm, where the temperature change sequence is used to characterize the temperature change of the breeding area within a preset time period;

[0008] Using each temperature change sequence, determine the clustering coefficient of the regional feature points in each breeding area at the current moment, where the regional feature points are preset feature position points in the breeding area;

[0009] Clustering the feature points of each region according to the clustering coefficient of the feature points of each region at the current moment and the distance between the feature points of each region to obtain at least one current cluster region;

[0010] Using the centroid position change information and area range change information of the current cluster area, determine the poultry gathering rate of the current cluster area, and the poultry gathering rate is used to characterize the possibility that the current cluster area belongs to the gathering area of ​​poultry animals;

[0011] Based on the poultry gathering rate in the current cluster area, determine whether the ambient temperature of the poultry farm is abnormal.

[0012] A second aspect of the embodiment of the present invention provides an environmental monitoring system for a modern poultry farm, comprising:

[0013] The temperature acquisition module is used to obtain the temperature change sequence of each breeding area in the poultry farm. The temperature change sequence is used to characterize the temperature change of the breeding area within a preset time period;

[0014] A coefficient calculation module is used to determine the clustering coefficient of the regional feature points in each breeding area at the current moment by using each temperature change sequence, where the regional feature points are preset feature position points in the breeding area;

[0015] A regional clustering module, used to cluster the regional feature points according to the clustering coefficient of each regional feature point at the current moment and the distance between the regional feature points to obtain at least one current cluster region;

[0016] A clustering rate determination module is used to determine the poultry clustering rate of the current cluster area by using the centroid position change information and area range change information of the current cluster area. The poultry clustering rate is used to characterize the possibility that the current cluster area belongs to the clustering area of ​​poultry animals;

[0017] The abnormality determination module is used to determine whether the ambient temperature of the poultry farm is abnormal based on the poultry aggregation rate in the current cluster area.

[0018] In the environmental monitoring method for a modern poultry farm provided by an embodiment of the present invention, a temperature change sequence reflecting the temperature change of each breeding area in a preset time period is first obtained in the poultry farm. According to the temperature change, a corresponding clustering coefficient is assigned to the regional feature points of each breeding area. And according to the clustering coefficient of the regional feature points of each breeding area at the current moment and the distance between the regional feature points, accurate clustering between each breeding area is achieved to obtain at least one current cluster area. Finally, according to the centroid position change information and the regional range change information of the current cluster area, the poultry clustering rate of the current cluster area is determined. According to the poultry clustering rate of the current cluster area, it can be determined whether the ambient temperature of the poultry farm is abnormal. In this way, according to the temperature change of each breeding area in the preset time period, the embodiment of the present invention comprehensively considers the significant temperature change caused by the poultry aggregation behavior, and realizes accurate clustering of the current cluster area. Then, according to the centroid position change information and the regional range change information of the current cluster area, the characteristics that the poultry aggregation behavior will continue to change are comprehensively considered, so as to accurately judge the poultry clustering phenomenon in the poultry farm. In this way, on the basis of accurately judging the poultry clustering phenomenon in the poultry farm, the influence of false temperature anomalies caused by the poultry clustering phenomenon can be overcome, thereby improving the accuracy of actual temperature anomaly monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic flow chart of a first environmental monitoring method for a modern poultry farm provided by an embodiment of the present invention;

[0021] Figure 2 A schematic flow chart of a second method for environmental monitoring of a modern poultry farm provided by an embodiment of the present invention;

[0022] Figure 3 A schematic flow chart of a third method for environmental monitoring of a modern poultry farm provided by an embodiment of the present invention;

[0023] Figure 4 A schematic structural diagram of an environmental monitoring system for a modern poultry farm provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the environmental monitoring system and method for a modern poultry farm proposed by the present invention, its specific implementation method, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0025] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0026] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of laws and regulations.

[0027] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0028] In the existing method, multiple temperature sensors are installed in the farm to monitor the temperature changes in the farm in real time and adjust the temperature in time. However, with the expansion of the breeding scale of the farm and the increase in the density of poultry breeding in the farm, poultry tends to gather in the farm. In the case of poultry gathering, the sensor will detect false temperature anomalies, affecting the monitoring judgment of the monitoring system, and reducing the accuracy of the monitoring system in monitoring the actual temperature anomaly.

[0029] The object of the present invention is to provide an environmental monitoring system and method for a modern poultry farm. In the environmental monitoring method for a modern poultry farm provided by an embodiment of the present invention, a temperature change sequence reflecting the temperature change of each breeding area in a preset time period in the poultry farm is first obtained. According to the temperature change, a corresponding clustering coefficient is assigned to the regional feature points of each breeding area. And according to the clustering coefficient of the regional feature points of each breeding area at the current moment and the distance between the regional feature points, accurate clustering between each breeding area is achieved to obtain at least one current cluster area. Finally, according to the centroid position change information and regional range change information of the current cluster area, the poultry clustering rate of the current cluster area is determined. According to the poultry clustering rate of the current cluster area, it can be determined whether the ambient temperature of the poultry farm is abnormal. In this way, according to the temperature change of each breeding area in the preset time period, the embodiment of the present invention comprehensively considers the significant temperature change caused by the poultry aggregation behavior, and achieves accurate clustering of the current cluster area. Then, based on the centroid position change information and regional range change information of the current cluster area, taking into account the characteristics of the continuous change of poultry aggregation behavior, the poultry clustering phenomenon in the poultry farm can be accurately determined. In this way, on the basis of accurately determining the poultry clustering phenomenon in the poultry farm, the influence of false temperature anomalies caused by the poultry clustering phenomenon can be overcome, thereby improving the accuracy of actual temperature anomaly monitoring.

[0030] The following describes a specific embodiment of an environmental monitoring method for a modern poultry farm provided by an embodiment of the present invention.

[0031] Figure 1 A flow chart of an environmental monitoring method for a modern poultry farm is provided. The environmental monitoring method for a modern poultry farm can be applied to a service end. The environmental monitoring method for a modern poultry farm can include the following S101 to S105.

[0032] S101, obtaining a temperature change sequence of each breeding area in a poultry farm, where the temperature change sequence is used to characterize the temperature change of the breeding area within a preset time period.

[0033] In this embodiment, a temperature sensor is installed in each breeding area of ​​the poultry farm, and the temperature sensor is used to record the temperature of the breeding area.

[0034] The temperature change sequence is used to reflect the temperature change of the breeding area within a preset time period. For example, the temperature change sequence can be {a-31, b-28, c-32, d-27}, which means that the temperature of the breeding area is 31 degrees at time a, then changes to 28 degrees at time b, changes to 32 degrees at time c, and finally changes to 27 degrees at time d.

[0035] As an example, the server records temperature data in real time through a temperature sensor, and constructs a temperature change sequence of each breeding area within the preset time period according to the temperature at each moment within the preset time period corresponding to each breeding area.

[0036] S102, using each temperature change sequence, determining the clustering coefficient of the regional feature points in each breeding area at the current moment, where the regional feature points are preset feature position points in the breeding area.

[0037] In this embodiment, the regional feature point is a key point or a representative point preset in the breeding area. For example, the regional feature point can be a point where a temperature sensor is located in the breeding area.

[0038] As an example, when the temperature of the breeding area where the regional feature point is located rises, the high temperature of the regional feature point may be caused by the gathering of poultry animals, or it may be caused by the fermentation of poultry feces. The temperature increase caused by the gathering of poultry animals is a false temperature anomaly, and there is no need to clean the farm environment at this time; the temperature increase caused by the fermentation of poultry feces is an actual temperature anomaly, and the poultry feces in the farm need to be cleaned.

[0039] When the temperature rise of the regional feature point is caused by the gathering of poultry, the temperature of the regional feature point rises faster because the gathering effect of poultry is rapid. When the temperature rise of the regional feature point is caused by the fermentation of poultry feces, the high temperature generated by the fermentation of poultry feces is mainly caused by the reproduction and heat dissipation of microorganisms in the accumulation of poultry feces, and the temperature change rate is slower. In other words, for regional feature points with faster temperature change rates, the greater the possibility that they belong to the gathering area of ​​poultry, so a larger clustering coefficient can be assigned to them.

[0040] Based on this, the server analyzes the temperature change sequence of each breeding area and calculates the average temperature change value of each breeding area in the same time period, such as the average temperature change value corresponding to each minute. According to the average temperature change value of each breeding area, the clustering coefficient of the current moment is set to match the regional feature points in each breeding area.

[0041] S103: Clustering the regional feature points according to the clustering coefficient of each regional feature point at the current moment and the distance between the regional feature points to obtain at least one current cluster region.

[0042] In this embodiment, the server calculates the distance between each regional feature point by using a measurement method such as Euclidean distance or Manhattan distance, and then uses a suitable clustering algorithm (such as K-means clustering algorithm, DBSCAN clustering algorithm, etc.) to perform clustering according to the clustering coefficient corresponding to each regional feature point and the distance between each regional feature point, so as to divide each regional feature point into multiple clusters.

[0043] Finally, the breeding areas described by the corresponding regional feature points in the same cluster are combined into a current cluster area, thereby obtaining multiple current cluster areas.

[0044] S104, using the centroid position change information and area range change information of the current cluster area, determining the poultry gathering rate of the current cluster area, where the poultry gathering rate is used to characterize the possibility that the current cluster area is a gathering area for poultry animals.

[0045] In this embodiment, the mass center position change information is used to characterize the movement of poultry animals, and the area range change information is used to characterize the aggregation or dispersion of poultry animals.

[0046] The poultry aggregation rate is an indicator of the degree of poultry aggregation in the current cluster area.

[0047] As an example, the server obtains multiple historical cluster areas corresponding to the poultry farm at the target historical moment according to the temperature change sequence of each breeding area, using the same method as that of obtaining the current cluster area. Then, the centroid position of the historical cluster area is compared with the centroid position of the corresponding current cluster area to obtain centroid position change information; at the same time, the area range of the historical cluster area is compared with the area range of the corresponding current cluster area to obtain area range change information.

[0048] Among them, the greater the centroid position change information, the more likely it is that poultry animals will move in the corresponding current cluster area; the area range change information indicates that the corresponding current cluster area is more likely to have poultry animals gather or disperse. Therefore, when the centroid position change information or the area range change information is greater, it means that the current cluster area is more likely to be a poultry animal gathering area, that is, the poultry gathering rate is greater.

[0049] Based on this, the server can directly multiply the centroid position change information with the area range change information and then perform normalization calculation to obtain the poultry clustering rate that matches the current cluster area.

[0050] S105, determining whether the ambient temperature of the poultry farm is abnormal based on the poultry aggregation rate in the current cluster area.

[0051] In this embodiment, the greater the poultry gathering rate, that is, the greater the possibility that the current cluster area belongs to the poultry gathering area, the temperature rise at this time is caused by the gathering of poultry, and the ambient temperature is not abnormal.

[0052] As an example, the server can pre-set a threshold. When the poultry gathering rate is greater than or equal to the set threshold, it means that the temperature rise is caused by the gathering of poultry, and the ambient temperature is not abnormal; when the poultry gathering rate is less than the set threshold, it means that the temperature rise is caused by the fermentation of poultry feces, and the ambient temperature is abnormal.

[0053] In the environmental monitoring method for a modern poultry farm provided by an embodiment of the present invention, a temperature change sequence reflecting the temperature change of each breeding area in a preset time period is first obtained in the poultry farm. According to the temperature change, a corresponding clustering coefficient is assigned to the regional feature points of each breeding area. And according to the clustering coefficient of the regional feature points of each breeding area at the current moment and the distance between the regional feature points, accurate clustering between each breeding area is achieved to obtain at least one current cluster area. Finally, according to the centroid position change information and the regional range change information of the current cluster area, the poultry clustering rate of the current cluster area is determined. According to the poultry clustering rate of the current cluster area, it can be determined whether the ambient temperature of the poultry farm is abnormal. In this way, according to the temperature change of each breeding area in the preset time period, the embodiment of the present application comprehensively considers the significant temperature change caused by the poultry aggregation behavior, and realizes accurate clustering of the current cluster area. Then, according to the centroid position change information and the regional range change information of the current cluster area, the characteristics that the poultry aggregation behavior will continue to change are comprehensively considered, so as to accurately judge the poultry clustering phenomenon in the poultry farm. In this way, on the basis of accurately judging the poultry clustering phenomenon in the poultry farm, the influence of false temperature anomalies caused by the poultry clustering phenomenon can be overcome, thereby improving the accuracy of actual temperature anomaly monitoring.

[0054] As an optional embodiment, S101 may specifically include:

[0055] According to the preset division strategy, the poultry farm is divided into multiple breeding areas;

[0056] The temperature sensors in the breeding area are used to collect temperature at a preset collection frequency to obtain the temperature at multiple times in the breeding area;

[0057] The temperatures at multiple moments are sorted in the order of collection time to obtain the temperature change sequence of the breeding area.

[0058] In this embodiment, the preset division strategy is used to characterize the strategy for dividing the poultry farm into regions. For example, the preset division strategy may include the size and shape of the breeding area.

[0059] The preset acquisition frequency is used to characterize the frequency of collecting the temperature of the breeding area. For example, the preset acquisition frequency may be 1 second each time.

[0060] As an example, the server divides the poultry farm into multiple breeding areas according to the preset division strategy using a virtual division method (such as an electronic fence based on a GIS system), and assigns a unique identifier to each breeding area so that it can be accurately identified in subsequent data collection and processing.

[0061] Then, for each breeding area: the server automatically collects the temperature through the temperature sensor according to the set collection frequency. At the same time, when collecting the temperature, the timestamp corresponding to each temperature is recorded to ensure the time sequence of the data. Finally, the collected temperatures are sorted in the order of the timestamps to form the temperature change sequence of the breeding area.

[0062] Through this embodiment, the temperature changes of poultry farms are monitored in real time, and a temperature change sequence of the breeding area is constructed, which helps to accurately determine the clustering coefficient of the regional feature points in each breeding area at the current moment according to the temperature change sequence, and can improve the accuracy of identifying poultry clustering areas.

[0063] As an optional embodiment, before S102, the environmental monitoring method of the modern poultry farm may further include:

[0064] According to each temperature change sequence, calculate the average temperature in the poultry farm at the current moment;

[0065] The breeding areas whose current temperature is greater than the average temperature are determined as areas to be identified;

[0066] S102 may specifically include:

[0067] The temperature variation sequence corresponding to each to-be-identified region is used to determine the clustering coefficient of the regional feature points in each to-be-identified region at the current moment.

[0068] In this embodiment, the area to be identified is used to characterize a breeding area to be identified as to whether there is a phenomenon of poultry gathering.

[0069] As an example, the server obtains the temperature value at the current moment in each temperature change sequence according to each temperature change sequence, and then summarizes the temperature values ​​of the temperature change sequences of all breeding areas at the current moment to obtain a list containing the current temperature values ​​of all areas. The mathematical mean calculation method is used to calculate the average value of all temperature values ​​in the above list, that is, the average temperature in the poultry farm at the current moment is obtained.

[0070] Then, the current temperature value of each breeding area is compared with the calculated average temperature. The breeding areas with a current temperature greater than the average temperature are identified as areas to be identified. These areas may have abnormal temperatures and require further monitoring and investigation.

[0071] Through this embodiment, the average temperature in the poultry farm at the current moment is calculated according to each temperature change sequence. Then, according to the average temperature in the poultry farm at the current moment, the area to be identified in each breeding area is screened. In this way, this embodiment obtains the area to be identified where poultry may gather by preliminary screening of the breeding area. Subsequently, only the area to be identified needs to be further processed, and all breeding areas do not need to be processed, thereby reducing the amount of data processing and improving monitoring efficiency.

[0072] As an optional embodiment, S102 may specifically include:

[0073] The temperature difference is obtained by calculating the difference between the temperature at the current moment in the temperature change sequence and the temperature at the historical moment, and then taking the absolute value. The historical moment is any moment in the temperature change sequence except the current moment.

[0074] Multiply the temperature difference by the instantaneous temperature change slope corresponding to the historical moment to obtain the local clustering coefficient corresponding to the historical moment;

[0075] The average value of each local clustering coefficient is calculated to obtain the clustering coefficient of the regional feature points in the breeding area corresponding to the temperature change sequence at the current moment.

[0076] In this embodiment, the local clustering coefficient is used to characterize the one-sided clustering coefficient of the regional feature points in the breeding area at the current moment, which is calculated based on the temperature at a single historical moment.

[0077] As an example, the clustering coefficient of the regional feature points in the breeding area at the current moment can be determined by the following formula 1:

[0078] Formula 1

[0079] In the formula, It is used to characterize the clustering coefficient of regional feature point z at time x. Used to characterize the temperature of the regional characteristic point z at time x, Used to characterize the temperature of the characteristic point z in the region at time c, It is used to characterize the instantaneous temperature change slope corresponding to moment c, and C is used to characterize the number of historical moments.

[0080] in, It is used to characterize the temperature difference between the temperature of the regional feature point z at time x and the temperature of the regional feature point z at time c. The larger the temperature difference or the larger the instantaneous temperature change slope, the faster the temperature change of the regional feature point z at time c, and the larger the local clustering coefficient corresponding to time c.

[0081] in, It is used to characterize the average value of the local clustering coefficient corresponding to each historical moment. The larger the local clustering coefficient corresponding to each historical moment, the faster the overall temperature change of the regional feature point z in the preset time period, and the larger the clustering coefficient corresponding to the current moment.

[0082] The larger the clustering coefficient of the regional feature point at the current moment, the greater the possibility that the corresponding breeding area belongs to the gathering area of ​​poultry animals, that is, the higher the importance of the regional feature point in the clustering.

[0083] Through this embodiment, the temperature change of the regional feature points is analyzed according to the temperature change sequence, so as to determine the clustering coefficient of the regional feature points at the current moment according to the temperature change. In this way, it is helpful to cluster the regional feature points according to the clustering coefficient of the regional feature points at the current moment, and the accuracy of clustering can be improved.

[0084] As an optional embodiment, Figure 2 As shown, S103 may specifically include the following S201-S202:

[0085] S201, correcting the distances between the feature points of each region according to the clustering coefficient of the feature points of each region at the current moment, to obtain a corrected clustering distance;

[0086] S202: Clustering the feature points of each region according to the corrected clustering distance between the feature points of each region to obtain at least one current cluster region.

[0087] In this embodiment, the server can set a weight factor corresponding to each regional feature point according to the clustering coefficient of each regional feature point at the current moment, and then obtain a modified clustering distance by multiplying the distance between each regional feature point by the corresponding weight factor.

[0088] Then, the server applies a preset clustering algorithm (K-means clustering algorithm or DBSCAN clustering algorithm) to cluster the feature points of each region, and divides the feature points of each region into multiple clusters according to the corrected clustering distance.

[0089] Finally, the breeding areas described by the corresponding regional feature points in the same cluster are combined into a current cluster area, thereby obtaining multiple current cluster areas.

[0090] Through this embodiment, according to the clustering coefficient of each regional feature point at the current moment, the distance between each regional feature point is corrected to obtain a more accurate corrected cluster distance. Then, each regional feature point is clustered by the corrected cluster distance, thereby improving the accuracy of regional feature point clustering.

[0091] As an optional embodiment, S201 may specifically include:

[0092] Calculate the straight-line distance between the first regional feature point and the second regional feature point according to the position of the first regional feature point and the position of the second regional feature point, wherein the first regional feature point and the second regional feature point are any one of the regional feature points;

[0093] The clustering coefficient of the first region feature point at the current moment, the clustering coefficient of the second region feature point at the current moment, and the inverse of the straight-line distance between the first region feature point and the second region feature point are multiplied to obtain a modified clustering distance between the first region feature point and the second region feature point.

[0094] In this embodiment, the modified cluster distance between the first region feature point and the second region feature point is specifically determined by the following formula 2:

[0095] Formula 2

[0096] In the formula, It is used to characterize the modified clustering distance between the regional feature point z and the regional feature point a at time x. It is used to characterize the clustering coefficient of regional feature point a at time x. It is used to characterize the clustering coefficient of regional feature point z at time x. Used to represent the straight-line distance between regional feature point z and regional feature point a.

[0097] The greater the clustering coefficient of the regional feature point z, or the greater the clustering coefficient of the regional feature point a, the greater the possibility that the regional feature point z and the regional feature point a are clustered into the same cluster. The greater the straight-line distance between the regional feature point z and the regional feature point a, the less likely the regional feature point z and the regional feature point a are clustered into the same cluster.

[0098] Corrected clustering distance between regional feature point z and regional feature point a at time x The larger it is, the greater the possibility that the regional feature point z and the regional feature point a are clustered into the same cluster at time x.

[0099] Through this embodiment, according to the clustering coefficient of each regional feature point at the current moment, the distance between each regional feature point is corrected to obtain a more accurate corrected cluster distance. Then, each regional feature point is clustered by the corrected cluster distance, thereby improving the accuracy of regional feature point clustering.

[0100] As an optional embodiment, Figure 3 As shown, S104 may specifically include the following S301-S303:

[0101] S301, determining the historical cluster areas corresponding to each historical moment according to the temperature change sequence of each breeding area in the poultry breeding farm;

[0102] S302, determining centroid position change information and area range change information of the current cluster area according to the current cluster area and each historical cluster area;

[0103] S303, using the centroid position change information and the area range change information, calculate the poultry aggregation rate in the current cluster area.

[0104] In this embodiment, the server uses the same method as that for obtaining the current cluster area to obtain the historical cluster area corresponding to the poultry farm at each historical moment.

[0105] Then, for the cluster areas corresponding to two adjacent moments, the following steps are performed respectively: the centroid positions of the two cluster areas are compared to obtain the difference in the centroid positions between the two adjacent moments, and the centroid position change information of the current cluster area is constituted based on the differences in the centroid positions between multiple adjacent moments; the area ranges of the two cluster areas are compared to obtain the difference in the area range between the two adjacent moments, and the area range change information of the current cluster area is constituted based on the differences in the area range between multiple adjacent moments.

[0106] Finally, the difference between the centroid position of two adjacent moments in the centroid position change information and the difference between the area range of two adjacent moments in the area range change information are multiplied and then normalized to obtain the corresponding calculation result. The average of multiple calculation results can be used to obtain the poultry gathering rate of the current cluster area.

[0107] Through this embodiment, the poultry clustering rate of the current cluster area is accurately calculated based on the centroid position change information and area range change information of the current cluster area. Therefore, the poultry clustering phenomenon in the poultry farm can be accurately judged based on the poultry clustering rate, thereby overcoming the influence of false temperature anomalies caused by the poultry clustering phenomenon and improving the accuracy of actual temperature anomaly monitoring.

[0108] As an optional embodiment, the centroid position change information includes a plurality of centroid movement values, where the centroid movement value is the distance between the centroids of the cluster regions corresponding to two adjacent moments;

[0109] The area range change information includes multiple range change values, where the range change value is the difference between the areas of the cluster areas corresponding to two adjacent moments;

[0110] S303 may specifically include:

[0111] The centroid movement value is multiplied by the corresponding range change value to obtain the local poultry gathering rate;

[0112] The local poultry aggregation rates are accumulated and normalized to obtain the poultry aggregation rate of the current cluster area.

[0113] In this embodiment, the centroid position change information includes a plurality of centroid movement values, and the centroid movement value is the difference in the centroid position in the cluster area between two adjacent moments.

[0114] The area range change information includes a plurality of range change values, and the range change value is the difference in the size of the cluster area between two adjacent moments.

[0115] The local poultry clustering rate is used to characterize the one-sided poultry clustering rate calculated based on the centroid movement value and range change value of the cluster area between two single adjacent moments.

[0116] As an example, the poultry gathering rate in the current cluster area is specifically determined by the following formula 3:

[0117] Formula 3

[0118] In the formula, It is used to characterize the flocking rate of birds in cluster area f at time x, It is used to represent the centroid movement value of the cluster area f corresponding to time x. It is used to represent the range change value of the cluster area f corresponding to time x, X is used to represent the number of historical moments, and Sigmoid is used to represent the normalization function.

[0119] in, It is used to characterize the product of the centroid movement value of the cluster area f corresponding to time x and the range change value of the cluster area f corresponding to time x, that is, the local poultry gathering rate corresponding to time x. The larger the centroid movement value, the more significant the movement of poultry animals, that is, the greater the possibility that the cluster area belongs to the gathering area of ​​poultry animals; the larger the range change value, the more significant the aggregation or dispersion of poultry animals, that is, the greater the possibility that the cluster area belongs to the gathering area of ​​poultry animals.

[0120] The poultry clustering rate is an indicator that represents the possibility that the current cluster area belongs to a clustering area of ​​poultry animals. The greater the poultry clustering rate, the greater the possibility that the current cluster area belongs to a clustering area of ​​poultry animals.

[0121] Through this embodiment, the poultry clustering rate of the current cluster area is accurately calculated according to the centroid movement value and range change value of the current cluster area. Therefore, the poultry clustering phenomenon in the poultry farm can be accurately judged according to the poultry clustering rate, thereby overcoming the influence of false temperature anomalies caused by the poultry clustering phenomenon and improving the accuracy of actual temperature anomaly monitoring.

[0122] As an optional embodiment, S105 may specifically include:

[0123] Comparing the poultry aggregation rate with a preset aggregation rate threshold to obtain a aggregation rate comparison result;

[0124] When the clustering rate comparison result indicates that the poultry clustering rate is less than the preset clustering rate threshold, an abnormal temperature warning is initiated. The abnormal temperature warning is used to indicate that the ambient temperature in the current cluster area of ​​the poultry farm is abnormal.

[0125] In this embodiment, the server pre-sets a preset crowding rate threshold, for example, the preset crowding rate threshold may be 0.6. Then the poultry crowding rate of the current cluster area is compared with 0.6. When the poultry crowding rate of the current cluster area is greater than or equal to 0.6, it is considered that the temperature rise in the current cluster area is caused by the gathering of poultry animals, which is a normal poultry crowding phenomenon, and there is no need to clean up the poultry farm.

[0126] When the poultry gathering rate in the current cluster area is less than 0.6, it is considered that the temperature rise in the current cluster area is caused by the fermentation of poultry feces, which is an abnormal feces accumulation phenomenon. In order to ensure the hygiene and cleanliness of the poultry farm, the server will initiate an abnormal temperature warning to remind relevant staff to clean up the poultry farm.

[0127] Based on the environmental monitoring method of modern poultry farms. Accordingly, the present invention also provides a specific embodiment of the environmental monitoring system of modern poultry farms.

[0128] Figure 4 A structural schematic diagram of an environmental monitoring system for a modern poultry farm provided in an embodiment of the present application is shown. The environmental monitoring system 400 for a modern poultry farm may include a temperature acquisition module 410, a coefficient calculation module 420, a regional clustering module 430, a clustering rate determination module 440, and an abnormality determination module 450.

[0129] The temperature acquisition module 410 is used to obtain the temperature change sequence of each breeding area in the poultry farm, and the temperature change sequence is used to characterize the temperature change of the breeding area within a preset time period;

[0130] The coefficient calculation module 420 is used to determine the clustering coefficient of the regional feature points in each breeding area at the current moment by using each temperature change sequence, where the regional feature points are feature position points preset in the breeding area;

[0131] The regional clustering module 430 is used to cluster the regional feature points according to the clustering coefficient of each regional feature point at the current moment and the distance between each regional feature point to obtain at least one current cluster region;

[0132] The clustering rate determination module 440 is used to determine the poultry clustering rate of the current clustering area by using the centroid position change information and area range change information of the current clustering area. The poultry clustering rate is used to indicate the possibility that the current clustering area belongs to the poultry clustering area;

[0133] The abnormality determination module 450 is used to determine whether the ambient temperature of the poultry farm is abnormal according to the poultry aggregation rate in the current cluster area.

[0134] In the environmental monitoring system of a modern poultry farm provided by an embodiment of the present invention, a temperature change sequence reflecting the temperature change of each breeding area in a preset time period is first obtained in the poultry farm. According to the temperature change, a corresponding clustering coefficient is assigned to the regional feature points of each breeding area. And according to the clustering coefficient of the regional feature points of each breeding area at the current moment and the distance between the regional feature points, accurate clustering between each breeding area is achieved to obtain at least one current cluster area. Finally, according to the centroid position change information and regional range change information of the current cluster area, the poultry clustering rate of the current cluster area is determined. According to the poultry clustering rate of the current cluster area, it can be determined whether the ambient temperature of the poultry farm is abnormal. In this way, according to the temperature change of each breeding area in the preset time period, the embodiment of the present invention comprehensively considers the significant temperature change caused by the poultry aggregation behavior, and realizes accurate clustering of the current cluster area. Then, according to the centroid position change information and regional range change information of the current cluster area, the characteristic that the poultry aggregation behavior will continue to change is comprehensively considered, so as to accurately judge the poultry clustering phenomenon in the poultry farm. In this way, on the basis of accurately judging the poultry clustering phenomenon in the poultry farm, the influence of false temperature anomalies caused by the poultry clustering phenomenon can be overcome, thereby improving the accuracy of actual temperature anomaly monitoring.

[0135] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0136] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0137] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A method for environmental monitoring of a modern poultry farm, characterized in that: The method comprises: Acquire a temperature change sequence of each breeding area in a poultry farm, wherein the temperature change sequence is used to characterize the temperature change of the breeding area within a preset time period; Using each of the temperature change sequences, determining a clustering coefficient of a regional feature point in each of the breeding areas at a current moment, wherein the regional feature point is a feature position point preset in the breeding area; Clustering the regional feature points according to the clustering coefficient of each regional feature point at the current moment and the distance between each regional feature point to obtain at least one current cluster region; Determine the poultry gathering rate of the current cluster area by using the centroid position change information and area range change information of the current cluster area, wherein the poultry gathering rate is used to characterize the possibility that the current cluster area belongs to the gathering area of ​​poultry animals; Determining whether the ambient temperature of the poultry farm is abnormal according to the poultry gathering rate in the current cluster area; Wherein, before determining the clustering coefficient of the regional feature points in each of the breeding areas at the current moment, it also includes: calculating the average temperature in the poultry farm at the current moment according to each of the temperature change sequences; determining each of the breeding areas whose temperature at the current moment is greater than the average temperature as the area to be identified; using each of the temperature change sequences to determine the clustering coefficient of the regional feature points in each of the breeding areas at the current moment, includes: using the temperature change sequence corresponding to each of the areas to be identified to determine the clustering coefficient of the regional feature points in each of the areas to be identified at the current moment; Among them, the method for obtaining the clustering coefficient of the regional characteristic points in the breeding area at the current moment is: calculate the difference between the temperature at the current moment in the temperature change sequence and the temperature at the historical moment and take the absolute value to obtain the temperature difference, and the historical moment is any moment in the temperature change sequence except the current moment; multiply the temperature difference by the instantaneous temperature change slope corresponding to the historical moment to obtain the local clustering coefficient corresponding to the historical moment; calculate the average value of each local clustering coefficient to obtain the clustering coefficient of the regional characteristic points in the breeding area corresponding to the temperature change sequence at the current moment; Among them, the method for obtaining the poultry clustering rate of the current cluster area is: according to the temperature change sequence of each breeding area in the poultry farm, determine the historical cluster areas corresponding to each historical moment; according to the current cluster area and each of the historical cluster areas, determine the centroid position change information and the area range change information of the current cluster area; use the centroid position change information and the area range change information to calculate the poultry clustering rate of the current cluster area.

2. The environmental monitoring method for a modern poultry farm according to claim 1, characterized in that: The step of obtaining the temperature change sequence of each breeding area in the poultry breeding farm comprises: Dividing the poultry farm into a plurality of breeding areas according to a preset division strategy; The temperature in the breeding area is collected by a temperature sensor in the breeding area at a preset collection frequency to obtain the temperature at multiple times in the breeding area; The temperatures at the multiple moments are sorted in the order of collection time to obtain a temperature change sequence of the breeding area.

3. The environmental monitoring method for a modern poultry farm according to claim 1, characterized in that: The step of clustering the regional feature points according to the clustering coefficients of the regional feature points at the current moment and the distances between the regional feature points to obtain at least one current cluster region includes: According to the clustering coefficient of each of the regional feature points at the current moment, the straight-line distances between the regional feature points are respectively corrected to obtain a corrected clustering distance; The regional feature points are clustered according to the modified clustering distances between the regional feature points to obtain at least one current cluster region.

4. The environmental monitoring method for a modern poultry farm according to claim 3, characterized in that: The step of respectively correcting the straight-line distances between the regional feature points according to the clustering coefficients of the regional feature points at the current moment to obtain the corrected clustering distances includes: Calculating a straight-line distance between the first regional feature point and the second regional feature point according to a position of the first regional feature point and a position of the second regional feature point, wherein the first regional feature point and the second regional feature point are any one of the regional feature points; The clustering coefficient of the first regional feature point at the current moment, the clustering coefficient of the second regional feature point at the current moment, and the inverse of the straight-line distance between the first regional feature point and the second regional feature point are multiplied to obtain a modified clustering distance between the first regional feature point and the second regional feature point.

5. The environmental monitoring method for a modern poultry farm according to claim 1, characterized in that: The centroid position change information includes a plurality of centroid movement values, where the centroid movement value is the distance between the centroids of cluster regions corresponding to two adjacent moments; The area range change information includes a plurality of range change values, where the range change value is the difference between the areas of the cluster areas corresponding to two adjacent moments; The calculating the poultry gathering rate of the current cluster area by using the mass center position change information and the area range change information includes: The mass center movement value is multiplied by the corresponding range change value to obtain the local poultry gathering rate; The local poultry clustering rates are accumulated and normalized to obtain the poultry clustering rate of the current cluster area.

6. The environmental monitoring method for a modern poultry farm according to any one of claims 1 to 5, characterized in that: The determining whether the ambient temperature of the poultry farm is abnormal according to the poultry gathering rate in the current cluster area includes: Comparing the poultry clustering rate with a preset clustering rate threshold to obtain a clustering rate comparison result; When the clustering rate comparison result indicates that the poultry clustering rate is less than the preset clustering rate threshold, a temperature abnormality warning is initiated, and the temperature abnormality warning is used to indicate that an abnormal ambient temperature occurs in the current cluster area of ​​the poultry farm.

7. An environmental monitoring system for a modern poultry farm, characterized in that: The system is used to implement an environmental monitoring method for a modern poultry farm as described in any one of claims 1 to 6, and the system comprises: A temperature acquisition module is used to obtain a temperature change sequence of each breeding area in a poultry farm, wherein the temperature change sequence is used to characterize the temperature change of the breeding area within a preset time period; A coefficient calculation module, used to determine the clustering coefficient of the regional feature points in each of the breeding areas at the current moment by using each of the temperature change sequences, wherein the regional feature points are feature position points preset in the breeding areas; A regional clustering module, used for clustering each of the regional feature points according to the clustering coefficient of each of the regional feature points at the current moment and the distance between each of the regional feature points, to obtain at least one current cluster region; A clustering rate determination module, used to determine the poultry clustering rate of the current clustering area by using the centroid position change information and area range change information of the current clustering area, wherein the poultry clustering rate is used to characterize the possibility that the current clustering area belongs to a clustering area of ​​poultry animals; The abnormality determination module is used to determine whether the ambient temperature of the poultry farm is abnormal according to the poultry aggregation rate in the current cluster area.

Images