Crop planting area abnormity identification method and device and electronic equipment

Abstract

The invention discloses a crop planting area abnormity identification method and device and electronic equipment, and belongs to the technical field of computers. The method comprises the following steps: respectively acquiring planting area data of target crops in a target administrative region, a first administrative region and a second administrative region; the first administrative region is an upper-level administrative region of the target administrative region, and the second administrative region is an adjacent administrative region of the same level as the target administrative region; obtaining a first anomaly recognition result based on the planting area data of the target administrative region, the first administrative region and the second administrative region, and obtaining a second anomaly recognition result based on the planting area data of the target administrative region and the second administrative region; and when both the first anomaly recognition result and the second anomaly recognition result are abnormal, determining that the planting area data of the target administrative region is abnormal data. According to the crop planting area anomaly identification method disclosed by the invention, the accuracy of crop planting area anomaly identification is improved.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and particularly relates to a method, device, and electronic device for identifying abnormal crop planting areas. Background Art

[0002] As an important staple food crop, the planting area of crops is of great significance for ensuring food security. Generally, based on statistical detection methods, by detecting indicators such as the change rate between data, it can be judged whether the crop planting area is abnormal.

[0003] However, due to the frequent changes in the crop planting plans of each administrative region, the change trend of the crop planting area is not stable. And it is difficult for statistical detection methods to identify whether the change in the crop planting area is due to abnormal data statistics or just because of the changes in the planting plans of administrative regions. Therefore, the accuracy of identifying abnormal crop planting areas is not high. Summary of the Invention

[0004] This application aims to at least solve one of the technical problems existing in the prior art. For this purpose, this application provides a method, device, and electronic device for identifying abnormal crop planting areas to improve the accuracy of identifying abnormal crop planting areas.

[0005] In a first aspect, this application provides a method for identifying abnormal crop planting areas, which includes: Obtain the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region respectively; the first administrative region is the upper-level administrative region of the target administrative region, and the second administrative region is the adjacent administrative region at the same level as the target administrative region; Based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtain a first abnormal identification result, and based on the planting area data of the target administrative region and the second administrative region, obtain a second abnormal identification result; In the case where both the first abnormal identification result and the second abnormal identification result are abnormal, determine that the planting area data of the target administrative region is abnormal data.

[0006] According to the method for identifying abnormal crop planting areas of the present application, by respectively obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region); based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtaining a first abnormal identification result, and based on the planting area data of the target administrative region and the second administrative region, obtaining a second abnormal identification result; in the case where both the first abnormal identification result and the second abnormal identification result are abnormal, determining that the planting area data of the target administrative region is abnormal data, so as to identify the abnormality of the planting area data of the target crop in the target administrative region from the dimension of considering the planting plan of the administrative region, thereby improving the accuracy of identifying abnormal crop planting areas.

[0007] According to an embodiment of the present application, obtaining the first abnormal identification result based on the planting area data of the target administrative region, the first administrative region, and the second administrative region includes: Through a vertical hierarchical anomaly discrimination model, based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtaining the first random error and random effect of the target administrative region; the first random error represents the time error of the planting area in the current year, and the random effect represents the objective contribution rate of the target administrative region to the first administrative region in the current year; Determining whether there is an abnormality in the first random error and random effect of the target administrative region; In the case where at least one of the first random error and random effect of the target administrative region is abnormal, obtaining a first abnormal identification result indicating an abnormality.

[0008] According to an embodiment of the present application, determining whether there is an abnormality in the first random error and random effect of the target administrative region includes: Based on the first random error of the historical years of the target administrative region, obtaining a first normal distribution; the first normal distribution is the distribution of the first random error corresponding to each historical year with respect to the historical year; Based on the first normal distribution, determining whether there is an abnormality in the first random error of the target administrative region.

[0009] According to an embodiment of the present application, determining whether there is an abnormality in the first random error and random effect of the target administrative region includes: Based on the random effect of the second administrative region, obtaining a second normal distribution; the second normal distribution is the distribution of each random effect with respect to each administrative region in the second administrative region; Determine whether the random effect of the target administrative region is abnormal based on the second normal distribution.

[0010] According to an embodiment of the present application, based on the planting area data of the target administrative region and the second administrative region, obtain a second anomaly recognition result, including: Through a horizontal spatio-temporal anomaly discrimination model, based on the planting area data of the target administrative region and the second administrative region, obtain the second random error of the target administrative region; the second random error represents the planting area of the current year with respect to the spatial error; Determine whether there is an anomaly in the second random error of the target administrative region; In the case where the second random error is abnormal, obtain a second anomaly recognition result indicating the anomaly.

[0011] According to an embodiment of the present application, in the case where both the first anomaly recognition result and the second anomaly recognition result are abnormal, after determining that the planting area data of the target administrative region is abnormal data, the method further includes: Through a pre-established posterior distribution model, based on the planting area data of the target administrative region, fixed effects and random effects, and the planting area data of the first administrative region, perform correction processing on the planting area data of the target administrative region.

[0012] According to an embodiment of the present application, through a pre-established posterior distribution model, based on the planting area data of the target administrative region, fixed effects and random effects, and the planting area data of the first administrative region, perform correction processing on the planting area data of the target administrative region, including: In the case where the fixed effects of the current year and multiple adjacent historical years in the target administrative region are all abnormal, update the fixed effect of the current year based on the normal fixed effect of the target administrative region; the normal fixed effect is determined according to the normal fixed effects of the historical years in the target administrative region; Based on the planting area data of the target administrative region, the updated fixed effect and random effect, and the planting area data of the first administrative region, perform correction processing on the planting area data of the target administrative region.

[0013] In a second aspect, the present application provides a device for identifying abnormal planting areas of crops, including: A first acquisition module, configured to respectively acquire the planting area data of the target crops in the target administrative region, the first administrative region, and the second administrative region; the first administrative region is the upper-level administrative region of the target administrative region, and the second administrative region is an adjacent administrative region at the same level as the target administrative region; A second acquisition module, configured to obtain a first anomaly recognition result based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, and obtain a second anomaly recognition result based on the planting area data of the target administrative region and the second administrative region; A determination module, configured to determine that the planting area data of the target administrative region is abnormal data when both the first anomaly recognition result and the second anomaly recognition result are abnormal.

[0014] According to the crop planting area anomaly recognition device of the present application, by separately obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative region at the same level as the target administrative region (i.e., the second administrative region); based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtain a first anomaly recognition result, and based on the planting area data of the target administrative region and the second administrative region, obtain a second anomaly recognition result; when both the first anomaly recognition result and the second anomaly recognition result are abnormal, determine that the planting area data of the target administrative region is abnormal data, so as to consider the dimension of the planting plan of the administrative region based on the planting area data of the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative region at the same level as the target administrative region (i.e., the second administrative region), and perform anomaly recognition on the planting area data of the target crop in the target administrative region to improve the accuracy of crop planting area anomaly recognition.

[0015] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the steps of the crop planting area anomaly recognition method in the first aspect above.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the crop planting area anomaly recognition method in the first aspect above are implemented.

[0017] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the crop planting area anomaly recognition method in the first aspect above are implemented.

[0018] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. Description of the Drawings

[0019] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, where: Figure 1 It is one of the schematic flowcharts of the method for identifying abnormal crop planting areas provided by the embodiments of the present application; Figure 2 It is the second of the schematic flowcharts of the method for identifying abnormal crop planting areas provided by the embodiments of the present application; Figure 3 It is the schematic structural diagram of the device for identifying abnormal crop planting areas provided by the embodiments of the present application; Figure 4 It is the schematic structural diagram of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0020] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, rather than all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0021] The terms "first", "second", etc. in the description and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the description and claims means at least one of the connected objects, and the character " / " generally means an "or" relationship between the associated objects before and after.

[0022] Next, in conjunction with the accompanying drawings, the method, device, and electronic device for identifying abnormal crop planting areas provided by the embodiments of the present application will be described in detail through specific embodiments and their application scenarios.

[0023] Among them, the method for identifying abnormal crop planting areas can be applied to a terminal, and specifically can be executed by hardware or software in the terminal.

[0024] The terminal includes, but is not limited to, portable communication devices such as mobile phones or tablet computers having a touch-sensitive surface (for example, a touch screen display and / or a touchpad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer having a touch-sensitive surface (for example, a touch screen display and / or a touchpad).

[0025] In each of the following embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse, and a joystick.

[0026] The method for identifying abnormal crop planting areas provided in the embodiments of this application may be executed by an electronic device or a functional module or entity in the electronic device that can implement the method for identifying abnormal crop planting areas. The electronic devices mentioned in the embodiments of this application include, but are not limited to, mobile phones, tablet computers, computers, cameras, and wearable devices, etc. Hereinafter, taking the electronic device as the execution subject, the method for identifying abnormal crop planting areas provided in the embodiments of this application will be described.

[0027] As Figure 1 shown, the method for identifying abnormal crop planting areas includes: step 110, step 120, and step 130.

[0028] Step 110: Obtain the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region respectively; the first administrative region is the upper-level administrative region of the target administrative region, and the second administrative region is the adjacent administrative region at the same level as the target administrative region.

[0029] In actual execution, the target administrative region can be any administrative region, and the target administrative region can be the administrative region to be judged whether the planting area data of the target crop is abnormal.

[0030] In actual execution, the target crop can be any crop, such as any theoretically feasible crop like rice, wheat, potato, etc.

[0031] In actual execution, the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region may include the planting area data of the target crop in the current year in the target administrative region, the first administrative region, and the second administrative region, or may include the planting area data of the target crop in historical years in the target administrative region, the first administrative region, and the second administrative region.

[0032] Step 120: Obtain a first abnormal identification result based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, and obtain a second abnormal identification result based on the planting area data of the target administrative region and the second administrative region.

[0033] In some embodiments, a first abnormal identification result may be obtained based on the planting area data of the target administrative region, the first administrative region, and the second administrative region through a vertical hierarchical anomaly discrimination model.

[0034] In actual execution, the vertical hierarchical anomaly discrimination model can be used to identify the planting area data of the target crop in the target administrative region from the upper-level administrative region to the current-level administrative region in terms of the vertical hierarchical dimension.

[0035] In some embodiments, the horizontal spatio-temporal anomaly discrimination model can be used to obtain a second anomaly recognition result based on the planting area data of the target administrative region and the second administrative region.

[0036] In actual execution, the horizontal spatio-temporal anomaly discrimination model can be used to identify the planting area data of the target crop in the target administrative region in the horizontal dimension of adjacent administrative regions at the same level.

[0037] Step 130: When both the first anomaly recognition result and the second anomaly recognition result are anomalies, determine that the planting area data of the target administrative region is abnormal data.

[0038] In some embodiments, when either the first anomaly recognition result or the second anomaly recognition result is normal, determine that the planting area data of the target crop in the target administrative region is normal data.

[0039] In actual execution, when both the first anomaly recognition result and the second anomaly recognition result are anomalies, it can be confirmed that the planting area data of the target crop in the target administrative region is abnormal in terms of both the vertical hierarchical dimension and the horizontal dimension, that is, the planting area data of the target crop in the target administrative region is abnormal data.

[0040] In some embodiments, after obtaining the first anomaly recognition result and the second anomaly recognition result for the target administrative region, the anomaly recognition can also be performed on the planting area data of the target crop in the second administrative region to obtain the anomaly type of the planting area data of the target crop in the target administrative region. In some embodiments, when the planting area data of the target crop in the target administrative region is abnormal data and the planting area data of the target crop in the second administrative region is normal data, the anomaly type of the planting area data of the target crop in the target administrative region is individual anomaly. When the planting area data of the target crop in both the target administrative region and the second administrative region is abnormal data, the anomaly type of the planting area data of the target crop in the target administrative region is regional anomaly.

[0041] In some embodiments, after obtaining the first abnormal recognition result and the second abnormal recognition result for the target administrative region, the abnormal type of the planting area data of the target crop in the target administrative region can also be obtained based on the planting area data of the target crop in the historical years of the target administrative region. For example, when the planting area data of the target crop in the historical years of the target administrative region is abnormal, it is determined that the abnormal type of the planting area data of the target crop in the target administrative region is a systematic abnormality.

[0042] In some embodiments, after determining that the planting area data of the target crop in the target administrative region is abnormal data, the planting area data of the target crop in the target administrative region can be corrected.

[0043] According to the crop planting area abnormal recognition method of the present application, by separately obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region); based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtaining the first abnormal recognition result, and based on the planting area data of the target administrative region and the second administrative region, obtaining the second abnormal recognition result; when both the first abnormal recognition result and the second abnormal recognition result are abnormal, determining that the planting area data of the target administrative region is abnormal data, so as to, considering the dimension of the planting plan of the administrative region, based on the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region), perform abnormal recognition on the planting area data of the target crop in the target administrative region to improve the accuracy of crop planting area abnormal recognition.

[0044] In some embodiments, through a vertical hierarchical abnormal discrimination model, based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, the first random error and random effect of the target administrative region can be obtained; the first random error represents the time error of the planting area in the current year, and the random effect represents the objective contribution rate of the target administrative region to the first administrative region in the current year; determine whether there is an abnormality in the first random error and random effect of the target administrative region; when at least one of the first random error and random effect of the target administrative region is abnormal, obtain the first abnormal recognition result indicating that the planting area data of the target administrative region is abnormal.

[0045] In actual implementation, the vertical hierarchical anomaly discrimination model can be a hierarchical Bayesian model or any other theoretically feasible model. The first random error can represent the error of the planting area of the target administrative region in the current year with respect to the planting area in historical years. The random effect represents the contribution rate of the objective factors (such as natural disasters, policy impacts, etc.) in the current year of the target administrative region to the first administrative region.

[0046] In actual implementation, the planting area data of the target administrative region, the first administrative region, and the second administrative region can be input into the vertical hierarchical anomaly discrimination model to obtain the first random error and random effect of the target administrative region, and determine whether there are anomalies in the first random error and random effect of the target administrative region.

[0047] In actual implementation, based on the vertical hierarchical anomaly discrimination model, through the planting area data of the target administrative region, the first administrative region, and several second administrative regions, the first random error and random effect of the target administrative region and each second administrative region can be obtained. Based on the first random errors of all second administrative regions, it is determined whether there is an anomaly in the first random error of the target administrative region, and based on the random effects of all second administrative regions, it is determined whether there is an anomaly in the random effect of the target administrative region.

[0048] In some embodiments, after obtaining the first random error of the target administrative region and each second administrative region, based on any theoretically feasible mathematical processing method, it is determined whether there is an anomaly in the first random error of the target administrative region based on the first random errors of all second administrative regions. For example, at least one of the average value, variance, and standard deviation can be obtained based on the first random errors of all second administrative regions, and it is determined whether there is an anomaly in the first random error of the target administrative region based on at least one of the average value, variance, and standard deviation.

[0049] In some embodiments, after obtaining the random effect of the target administrative region and each second administrative region, based on any theoretically feasible mathematical processing method, it is determined whether there is an anomaly in the random effect of the target administrative region based on the random effects of all second administrative regions. For example, at least one of the average value, variance, and standard deviation can be obtained based on the random effects of all second administrative regions, and it is determined whether there is an anomaly in the random effect of the target administrative region based on at least one of the average value, variance, and standard deviation.

[0050] According to the method for identifying abnormal crop planting areas of the present application, by respectively obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region); through the vertical hierarchical anomaly discrimination model, based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtain the first random error and random effect of the target administrative region; determine whether there is an anomaly in the first random error and random effect of the target administrative region; in the case where at least one of the first random error and random effect of the target administrative region is abnormal, obtain a first anomaly recognition result indicating that the planting area data of the target administrative region is abnormal, and based on the planting area data of the target administrative region and the second administrative region, obtain a second anomaly recognition result; in the case where both the first anomaly recognition result and the second anomaly recognition result are abnormal, determine that the planting area data of the target administrative region is abnormal data, so as to consider the dimension of the planting plan of the administrative region based on the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region), and perform anomaly recognition on the planting area data of the target crop in the target administrative region to improve the accuracy of abnormal crop planting area recognition.

[0051] In some embodiments, a first normal distribution may be obtained based on the first random error of the target administrative region in historical years; the first normal distribution is the distribution of the first random error corresponding to each historical year with respect to the historical year; based on the first normal distribution, determine whether there is an anomaly in the first random error of the target administrative region.

[0052] In actual execution, the vertical hierarchical anomaly discrimination model may obtain the first random error and the first normal distribution of the historical years of the target administrative region based on the planting area data of the target crop in the current year of the target administrative region, the first administrative region, and the second administrative region.

[0053] In some embodiments, the vertical hierarchical anomaly discrimination model may interpolate to obtain the first random error of the target administrative region and the historical years of the target administrative region based on the following formula:

[0054] where ɑ represents the contribution rate of the target administrative region or the i-th second administrative region; y B,t represents the planting area data of the first administrative region in the t-th year, and x i,t represents the planting area data of the target administrative region or the i-th second administrative region in the t-th year; β i represents the solid effect of the target administrative region or the i-th second administrative region; u irepresents the random effect of the target administrative region or the i-th second administrative region, and ; represents the first random error of the target administrative region or the i-th second administrative region, and .

[0055] In some embodiments, when the first random error of the target administrative region deviates from the first normal distribution, it can be determined that the first random error of the target administrative region is abnormal.

[0056] In some embodiments, when the absolute value of the first random error of the target administrative region is greater than the first standard deviation, it can be determined that the first random error of the target administrative region deviates from the first normal distribution, and it can be determined that the first random error of the target administrative region is abnormal. The first standard deviation can be three times the standard deviation of the first normal distribution.

[0057] According to the method for identifying abnormal crop planting areas of the present application, by respectively obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region); through the vertical hierarchical anomaly discrimination model, based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtain the first random error and random effect of the target administrative region; determine whether the first random error and random effect of the target administrative region are abnormal; when at least one of the first random error and random effect of the target administrative region is abnormal, obtain the first anomaly identification result indicating that the planting area data of the target administrative region is abnormal, and based on the planting area data of the target administrative region and the second administrative region, obtain the second anomaly identification result; when both the first anomaly identification result and the second anomaly identification result are abnormal, determine that the planting area data of the target administrative region is abnormal data, so as to consider the dimension of the planting plan of the administrative region, identify the abnormality of the planting area data of the target crop in the target administrative region based on the planting area data of the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region), so as to improve the accuracy of identifying abnormal crop planting areas.

[0058] In some embodiments, the second normal distribution can be obtained based on the random effect of the second administrative region; the second normal distribution is the distribution of each random effect with respect to each administrative region in the second administrative region; based on the second normal distribution, determine whether the random effect of the target administrative region is abnormal.

[0059] In actual implementation, the vertical hierarchical anomaly discrimination model can obtain the random effects and the second normal distribution of all second administrative regions based on the planting area data of the target crop in the current year in the target administrative region, the first administrative region, and the second administrative regions.

[0060] In some embodiments, the vertical hierarchical anomaly discrimination model can interpolate to obtain the random effects of the target administrative region and all second administrative regions based on the following formula:

[0061] where ɑ represents the contribution rate of the target administrative region or the i-th second administrative region; y B,t represents the planting area data of the first administrative region in the t-th year, and x i,t represents the planting area data of the target administrative region or the i-th second administrative region in the t-th year; β i represents the fixed effect of the target administrative region or the i-th second administrative region; u i represents the random effect of the target administrative region or the i-th second administrative region, and ; represents the first random error of the target administrative region or the i-th second administrative region, and .

[0062] In some embodiments, when the random effect of the target administrative region deviates from the second normal distribution, it can be determined that there is an anomaly in the random effect of the target administrative region.

[0063] In some embodiments, when the absolute value of the random effect of the target administrative region is greater than the second standard deviation, it can be determined that the random effect of the target administrative region deviates from the second normal distribution, and it can be determined that there is an anomaly in the random effect of the target administrative region. The second standard deviation can be three times the standard deviation of the second normal distribution, i.e., ±3 .

[0064] According to the method for identifying abnormal crop planting areas of the present application, by separately obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative regions); through a vertical hierarchical anomaly discrimination model, based on the planting area data of the target administrative region, the first administrative region, and the second administrative regions, obtain the first random error and random effect of the target administrative region; determine whether there are anomalies in the first random error and random effect of the target administrative region; in the case where at least one of the first random error and random effect of the target administrative region is abnormal, obtain a first anomaly identification result indicating that the planting area data of the target administrative region is abnormal, and based on the planting area data of the target administrative region and the second administrative regions, obtain a second anomaly identification result; in the case where both the first anomaly identification result and the second anomaly identification result are abnormal, determine that the planting area data of the target administrative region is abnormal data, so as to identify anomalies in the planting area data of the target crop in the target administrative region in consideration of the dimension of the planting plan of the administrative region, in order to improve the accuracy of identifying abnormal crop planting areas.

[0065] In some embodiments, a second random error of the target administrative region may be obtained through a horizontal spatio-temporal anomaly discrimination model based on the planting area data of the target administrative region and the second administrative regions; determine whether there is an anomaly in the second random error of the target administrative region; in the case where the second random error is abnormal, obtain a second anomaly identification result indicating the anomaly.

[0066] In actual implementation, the horizontal spatio-temporal anomaly discrimination model may be a hierarchical Bayesian model or any other theoretically feasible model. The second random error represents the error of the planting area of the target administrative region in the current year with respect to the planting area of the second administrative regions.

[0067] In actual implementation, the planting area data of the target administrative region and the second administrative regions may be input into the horizontal spatio-temporal anomaly discrimination model to obtain the second random error of the target administrative region, and determine whether there is an anomaly in the second random error of the target administrative region.

[0068] In actual implementation, based on the horizontal spatio-temporal anomaly discrimination model, through the planting area data of the target administrative region and several second administrative regions, the second random error of the target administrative region and each second administrative region may be obtained, and based on the second random errors of all second administrative regions, determine whether there is an anomaly in the second random error of the target administrative region.

[0069] In some embodiments, after obtaining the second random errors of the target administrative region and each second administrative region, based on any theoretically feasible mathematical processing method, it can be determined whether there is an abnormality in the second random error of the target administrative region based on the second random errors of all second administrative regions. For example, at least one of the mean, variance, and standard deviation can be obtained based on the second random errors of all second administrative regions, and it can be determined whether there is an abnormality in the second random error of the target administrative region based on at least one of the mean, variance, and standard deviation.

[0070] In some embodiments, a third normal distribution can be obtained based on the second random error of the second administrative region; it can be determined whether the second random error of the target administrative region is abnormal based on the third normal distribution.

[0071] In actual execution, the horizontal spatio-temporal anomaly discrimination model can obtain the second random error and the third normal distribution of the target administrative region based on the planting area data of the target crop in the current year of the second administrative region and the planting area data of the target administrative region in historical years.

[0072] In some embodiments, the horizontal spatio-temporal anomaly discrimination model can interpolate to obtain the second random error of the target administrative region based on the following formula:

[0073] where represents the spatial autoregressive coefficient, reflecting the influence intensity of the second administrative region; represents the planting area data of the j-th second administrative region in the t-th year; represents the spatial weight matrix (each second administrative region takes 1 / n, indicating an equal influence on the target administrative region. In the case where the second administrative region is a non-adjacent administrative region of the target administrative region, this second administrative region is 0); represents the temporal autoregressive coefficient, reflecting the historical trend of the target administrative region; represents the second random error of the target administrative region in the t-th year, ; represents the target administrative region at the -th year of the target crop planting area data; represents the target administrative region at the -th year of the target crop planting area data.

[0074] In some embodiments, it can be determined that there is an abnormality in the second random error of the target administrative region when the second random error of the target administrative region deviates from the third normal distribution.

[0075] In some embodiments, when the absolute value of the random effect of the target administrative region is greater than three standard deviations, it can be determined that the random difference of the target administrative region deviates from the third normal distribution, and it is determined that there is an abnormality in the second random error of the target administrative region. The third standard deviation can be three times the standard deviation of the third normal distribution.

[0076] According to the method for identifying abnormal crop planting areas of the present application, by separately obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region); based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtaining a first abnormal identification result, and through a horizontal spatio-temporal abnormality discrimination model, based on the planting area data of the target administrative region and the second administrative region, obtaining the second random error of the target administrative region; determining whether there is an abnormality in the second random error of the target administrative region; in the case where the second random error is abnormal, obtaining a second abnormal identification result indicating the abnormality; in the case where both the first abnormal identification result and the second abnormal identification result are abnormal, determining that the planting area data of the target administrative region is abnormal data, so as to identify the abnormality of the planting area data of the target crop in the target administrative region in consideration of the dimension of the planting plan of the administrative region, based on the planting area data of the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region), so as to improve the accuracy of identifying abnormal crop planting areas.

[0077] In some embodiments, when it is determined that the abnormal identification result indicates that the planting area data of the target administrative region is abnormal, the abnormal identification of the planting area data of the target crop in the second administrative region can be performed. When only the planting area data of the target crop in the target administrative region is abnormal, it is determined that the abnormal type of the target administrative region is an isolated abnormality. When both the target administrative region and the second administrative region are abnormal, it is determined that the abnormal type of the target administrative region is a regional abnormality.

[0078] In some embodiments, the abnormal type of the target administrative region can be determined based on the solid-state effects of the target administrative region in historical years and the current year. When the solid-state effects of each year t and the previous year t-1 in three consecutive years of the target administrative region satisfy >0.15, it is determined that the abnormal type of the target administrative region is a systematic deviation.

[0079] In some embodiments, when both the first abnormal recognition result and the second abnormal recognition result are abnormal, after determining the abnormal recognition result that the planting area data of the target administrative region is abnormal, when the abnormal recognition result indicates that the planting area data of the target administrative region is abnormal, through a pre-established posterior distribution model, based on the planting area data, fixed effects and random effects of the target administrative region, and the planting area data of the first administrative region, the planting area data of the target administrative region is corrected.

[0080] In actual implementation, the posterior distribution model can be trained based on a hierarchical Bayesian model.

[0081] In some embodiments, when the fixed effects of the current year and multiple adjacent historical years of the target administrative region are all abnormal, through a pre-established posterior distribution model, based on the conditional interpolation strategy of the posterior predictive distribution, the planting area data of the target administrative region can be corrected.

[0082] In some embodiments, when the abnormal recognition result indicates that the planting area data of the target administrative region is abnormal, the first random error abnormality, random effect abnormality or second random error abnormality that causes the abnormal planting area data can be corrected, and the planting area data of the target administrative region can be corrected based on the correction result.

[0083] In some embodiments, the planting area data, fixed effects and random effects of the target administrative region, and the planting area data of the first administrative region can be input into the posterior distribution model, and the planting area data of the target administrative region can be corrected through the posterior distribution model to obtain the corrected planting area data of the target administrative region.

[0084] According to the method for abnormal recognition of crop planting area of the present application, by separately obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region); based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtaining the first abnormal recognition result, and based on the planting area data of the target administrative region and the second administrative region, obtaining the second abnormal recognition result; when both the first abnormal recognition result and the second abnormal recognition result are abnormal, determining that the planting area data of the target administrative region is abnormal data, so as to consider the dimension of the planting plan of the administrative region based on the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region), and perform abnormal recognition on the planting area data of the target crop in the target administrative region to improve the accuracy of abnormal recognition of crop planting area.

[0085] In some embodiments, when the solid state effects in the current year and multiple adjacent historical years of the target administrative region are all abnormal, the solid state effect in the current year is updated based on the normal solid state effect of the target administrative region; the normal solid state effect is determined according to the normal solid state effects in the historical years of the target administrative region; the planting area data of the target administrative region is corrected based on the planting area data of the target administrative region, the updated solid state effect, the random effect, and the planting area data of the first administrative region.

[0086] In some embodiments, in the current year of the target administrative region and each year t among multiple adjacent historical years satisfies > 0.15, it is determined that the solid state effects in the current year and multiple adjacent historical years of the target administrative region are all abnormal.

[0087] In an actual execution, the normal solid state effect can be determined according to the planting area data of the target crop in the target administrative region and the solid state effects in the historical years with normal solid state effects. For example, it can be the average value of the planting area data of the target crop in the target administrative region and the solid state effects in the historical years with normal solid state effects.

[0088] In some embodiments, the solid state effect in the current year can be updated based on the normal solid state effect of the target administrative region according to the following formula: ; where represents the updated solid state effect in the current year; represents the solid state effect with abnormal planting area data of the target crop in the target administrative region; represents the normal solid state effect.

[0089] In some embodiments, the planting area data of the target administrative region can be corrected according to the following formula:

[0090] where represents the planting area data of the target administrative region after the correction process; represents the planting area data of the first administrative region; represents the planting area data of the target administrative region before the correction process; represents the solid state effect of the target administrative region; represents the random effect of the target administrative region.

[0091] According to the method for identifying abnormal crop planting areas of the present application, the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region) are respectively obtained; based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, a first abnormal identification result is obtained, and based on the planting area data of the target administrative region and the second administrative region, a second abnormal identification result is obtained; in the case where both the first abnormal identification result and the second abnormal identification result are abnormal, it is determined that the planting area data of the target administrative region is abnormal data, so as to identify the abnormality of the planting area data of the target crop in the target administrative region from the dimension of considering the planting plan of the administrative region based on the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region), thereby improving the accuracy of identifying abnormal crop planting areas.

[0092] To better understand the method for identifying abnormal crop planting areas provided by the embodiments of the present application, the following further elaboration is provided. It should be understood that the following discussion is only exemplary.

[0093] The present application provides a method for identifying abnormal crop planting areas, and the specific steps can be as Figure 2 shown: Step 210: Respectively obtain the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region; the first administrative region is the upper-level administrative region of the target administrative region, and the second administrative region is the adjacent administrative region at the same level as the target administrative region.

[0094] In actual execution, the target administrative region can be any administrative region, and the target administrative region can be the administrative region to be judged whether the planting area of the target crop is abnormal.

[0095] In actual execution, the target crop can be any crop, such as any theoretically feasible crops like rice, wheat, potatoes, etc.

[0096] In actual execution, the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region can include the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region in the current year, or can include the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region in historical years.

[0097] In some embodiments, after obtaining the planting area data of the target crops in the target administrative region, the first administrative region, and the second administrative region, the planting area data of the target crops in the target administrative region, the first administrative region, and the second administrative region can be standardized. For example, the planting area data of the target crops in the target administrative region, the first administrative region, and the second administrative region can be standardized by Z-score.

[0098] In some embodiments, based on the spatial relationship between the target administrative region and each second administrative region, spatial topology can be performed on the target administrative region and the second administrative regions.

[0099] Step 220: Through the longitudinal hierarchical anomaly discrimination model, based on the planting area data of the target administrative region, the first administrative region, and the second administrative regions, obtain the first random error and random effect of the target administrative region, and determine whether there are anomalies in the first random error and random effect of the target administrative region.

[0100] In actual execution, the longitudinal hierarchical anomaly discrimination model can be a hierarchical Bayesian model or any other theoretically feasible model.

[0101] In actual execution, the planting area data of the target administrative region, the first administrative region, and the second administrative regions can be input into the longitudinal hierarchical anomaly discrimination model to obtain the first random error and random effect of the target administrative region, and determine whether there are anomalies in the first random error and random effect of the target administrative region.

[0102] In actual execution, based on the longitudinal hierarchical anomaly discrimination model, through the planting area data of the target administrative region, the first administrative region, and several second administrative regions, obtain the first random error and random effect of the target administrative region and each second administrative region. Based on the first random errors of all second administrative regions, determine whether there is an anomaly in the first random error of the target administrative region, and based on the random effects of all second administrative regions, determine whether there is an anomaly in the random effect of the target administrative region.

[0103] In some embodiments, after obtaining the first random error of the target administrative region and each second administrative region, based on any theoretically feasible mathematical processing method, determine whether there is an anomaly in the first random error of the target administrative region based on the first random errors of all second administrative regions. For example, at least one of the average value, variance, and standard deviation can be obtained based on the first random errors of all second administrative regions, and whether there is an anomaly in the first random error of the target administrative region can be determined based on at least one of the average value, variance, and standard deviation.

[0104] In some embodiments, after obtaining the random effects of the target administrative region and each second administrative region, based on any theoretically feasible mathematical processing method, it is possible to determine whether there is an abnormality in the random effect of the target administrative region based on the random effects of all second administrative regions. For example, it is possible to obtain at least one of the mean, variance, and standard deviation based on the random effects of all second administrative regions, and determine whether there is an abnormality in the random effect of the target administrative region based on at least one of the mean, variance, and standard deviation.

[0105] In some embodiments, based on the first random error of the target administrative region in historical years, a first normal distribution can be obtained; the first normal distribution is the distribution of the first random error corresponding to each historical year with respect to the historical years; based on the first normal distribution, it is determined whether there is an abnormality in the first random error of the target administrative region.

[0106] In actual execution, the vertical hierarchical anomaly discrimination model can obtain the first random error and the first normal distribution of the target administrative region in historical years based on the planting area data of the target crops in the current year of the target administrative region, the first administrative region, and the second administrative regions.

[0107] In some embodiments, the vertical hierarchical anomaly discrimination model can obtain the first random error and the first normal distribution of the target administrative region in historical years based on the following formula:

[0108] where ɑ represents the contribution rate of the target administrative region or the i-th second administrative region; y B,t represents the planting area data of the first administrative region in the t-th year, and x i,t represents the planting area data of the target administrative region or the i-th second administrative region in the t-th year; β i represents the fixed effect of the target administrative region or the i-th second administrative region; u i represents the random effect of the target administrative region or the i-th second administrative region, and ; represents the first random error of the target administrative region or the i-th second administrative region, and .

[0109] In some embodiments, based on the random effects of the second administrative regions, a second normal distribution can be obtained; the second normal distribution is the distribution of each random effect with respect to each administrative region in the second administrative regions; based on the second normal distribution, it is determined whether the random effect of the target administrative region is abnormal.

[0110] In actual execution, the vertical - level anomaly discrimination model can obtain the random effects of all second - level administrative regions and the second normal distribution based on the planting area data of the target crop in the current year in the target administrative region, the first administrative region, and the second administrative regions.

[0111] In some embodiments, the vertical - level anomaly discrimination model can obtain the random effects of the target administrative region and all second - level administrative regions based on the following formula:

[0112] where ɑ represents the contribution rate of the target administrative region or the i - th second - level administrative region; y B,t represents the planting area data of the first administrative region in the t - th year, and x i,t represents the planting area data of the target administrative region or the i - th second - level administrative region in the t - th year; β i represents the fixed effect of the target administrative region or the i - th second - level administrative region; u i represents the random effect of the target administrative region or the i - th second - level administrative region, and ; represents the first random error of the target administrative region or the i - th second - level administrative region, and .

[0113] Step 230: In the case where at least one of the first random error and the random effect in the target administrative region is abnormal, obtain a first anomaly recognition result indicating the anomaly.

[0114] In some embodiments, it can be determined that the first random error of the target administrative region is abnormal when the first random error of the target administrative region deviates from the first normal distribution.

[0115] In some embodiments, it can be determined that the first random error of the target administrative region deviates from the first normal distribution and the first random error of the target administrative region is abnormal when the absolute value of the first random error of the target administrative region is greater than the first standard deviation. The first standard deviation can be three times the standard deviation of the first normal distribution.

[0116] In some embodiments, it can be determined that the random effect of the target administrative region is abnormal when the random effect of the target administrative region deviates from the second normal distribution.

[0117] In some embodiments, it can be determined that the random effect of the target administrative region deviates from the second normal distribution and the random effect of the target administrative region is abnormal when the absolute value of the random effect of the target administrative region is greater than the second standard deviation. The second standard deviation can be three times the standard deviation of the second normal distribution, that is, ±3 .

[0118] Step 240: Based on the planting area data of the target administrative region and the second administrative region, obtain the second random error of the target administrative region through the horizontal spatio-temporal anomaly discrimination model; determine whether there is an anomaly in the second random error of the target administrative region.

[0119] In actual implementation, the horizontal spatio-temporal anomaly discrimination model can be a hierarchical Bayesian model or any other theoretically feasible model.

[0120] In actual implementation, the planting area data of the target administrative region and the second administrative region can be input into the horizontal spatio-temporal anomaly discrimination model to obtain the second random error of the target administrative region, and determine whether there is an anomaly in the second random error of the target administrative region.

[0121] In actual implementation, based on the horizontal spatio-temporal anomaly discrimination model, through the planting area data of the target administrative region and several second administrative regions, obtain the second random error of the target administrative region and each second administrative region, and determine whether there is an anomaly in the second random error of the target administrative region based on the second random errors of all second administrative regions.

[0122] In some embodiments, after obtaining the second random error of the target administrative region and each second administrative region, based on any theoretically feasible mathematical processing method, determine whether there is an anomaly in the second random error of the target administrative region based on the second random errors of all second administrative regions. For example, at least one of the mean, variance, and standard deviation can be obtained based on the second random errors of all second administrative regions, and it can be determined whether there is an anomaly in the second random error of the target administrative region based on at least one of the mean, variance, and standard deviation.

[0123] In some embodiments, a third normal distribution can be obtained based on the second random error of the second administrative region; determine whether the second random error of the target administrative region is abnormal based on the third normal distribution.

[0124] In actual implementation, the horizontal spatio-temporal anomaly discrimination model can obtain the second random error and the third normal distribution of the target administrative region based on the planting area data of the target crop in the current year of the second administrative region and the planting area data of the target administrative region in historical years.

[0125] In some embodiments, the horizontal spatio-temporal anomaly discrimination model can obtain the second random error of the target administrative region based on the following formula:

[0126] where represents the spatial autoregressive coefficient, reflects the influence intensity of the second administrative region; represents the planting area data of the j-th second administrative region in the t-th year; represents the spatial weight matrix (each second administrative region takes 1 / n, indicating an equal impact on the target administrative region. In the case where the second administrative region is a non-adjacent administrative region of the target administrative region, this second administrative region is 0); represents the time autoregressive coefficient, reflecting the historical trend of the target administrative region; represents the second random error of the target administrative region in the t-th year, ; represents the target administrative region at the t-th year planting area data of the target crop; represents the target administrative region at the t-th year planting area data of the target crop.

[0127] Step 250, in the case where the second random error is abnormal, obtain a second anomaly recognition result indicating the anomaly.

[0128] In some embodiments, it is possible to determine that the second random error of the target administrative region is abnormal when the second random error of the target administrative region deviates from the third normal distribution.

[0129] In some embodiments, it is possible to determine that the random difference of the target administrative region deviates from the third normal distribution and determine that the second random error of the target administrative region is abnormal when the absolute value of the random effect of the target administrative region is greater than three times the third standard deviation. The third standard deviation can be three times the standard deviation of the third normal distribution.

[0130] Step 260, in the case where both the first anomaly recognition result and the second anomaly recognition result are abnormal, determine that the planting area data of the target administrative region is abnormal data.

[0131] In some embodiments, in the case where any one of the first anomaly recognition result and the second anomaly recognition result is normal, determine that the planting area data of the target crop in the target administrative region is normal data.

[0132] In actual execution, it is possible to confirm that the planting area data of the target crop in the target administrative region is abnormal in both the vertical hierarchical dimension and the horizontal dimension when both the first anomaly recognition result and the second anomaly recognition result are abnormal, that is, the planting area data of the target crop in the target administrative region is abnormal data.

[0133] When it is determined that the abnormal recognition result indicates that the planted area data of the target administrative region is abnormal, the abnormal recognition is performed on the planted area data of the target crop in the second administrative region. When only the planted area data of the target crop in the target administrative region is abnormal, it is determined that the abnormal type of the target administrative region is an isolated abnormality. When both the target administrative region and the second administrative region are abnormal, it is determined that the abnormal type of the target administrative region is a regional abnormality.

[0134] In some embodiments, the abnormal type of the target administrative region can be determined based on the solid-state effect of the target administrative region in historical years and the current year. When the solid-state effect of each year t and the previous year t-1 in three consecutive years of the target administrative region satisfies >0.15, it is determined that the abnormal type of the target administrative region is a systematic deviation.

[0135] Step 270: Based on the planted area data, solid-state effect and random effect of the target administrative region, and the planted area data of the first administrative region, the planted area data of the target administrative region is corrected through a pre-established posterior distribution model.

[0136] In actual execution, the posterior distribution model can be trained based on a hierarchical Bayesian model.

[0137] In some embodiments, when the abnormal recognition result indicates that the planted area data of the target administrative region is abnormal, the first random error abnormality, random effect abnormality or second random error abnormality that causes the abnormal planted area data can be corrected, and the planted area data of the target administrative region is corrected based on the correction result.

[0138] In some embodiments, the planted area data, first random error, random effect of the target administrative region, and the planted area data of the first administrative region can be input into the posterior distribution model, and the planted area data of the target administrative region is corrected through the posterior distribution model to obtain the corrected planted area data of the target administrative region.

[0139] In some embodiments, when the solid-state effects of the current year and multiple adjacent historical years of the target administrative region are all abnormal, the solid-state effect of the current year is updated based on the normal solid-state effect of the target administrative region; the normal solid-state effect is determined according to the normal solid-state effect of the historical years of the target administrative region; based on the planted area data, updated solid-state effect and random effect of the target administrative region, and the planted area data of the first administrative region, the planted area data of the target administrative region is corrected.

[0140] In some embodiments, when each year t in the current year and multiple adjacent historical years of the target administrative region satisfies When it is >0.15, it is determined that the solid state effects in the current year and multiple adjacent historical years of the target administrative region are all abnormal.

[0141] In an actual implementation, the normal solid state effect can be determined based on the planting area data of the target crop in the target administrative region and the solid state effects in historical years with normal solid state effects. For example, it can be the average of the planting area data of the target crop in the target administrative region and the solid state effects in historical years with normal solid state effects.

[0142] In some embodiments, the solid state effect of the current year can be updated based on the following formula, based on the normal solid state effect of the target administrative region: ; where, represents the updated solid state effect of the current year; represents the solid state effect with abnormal planting area data of the target crop in the target administrative region; represents the normal solid state effect.

[0143] In some embodiments, the planting area data of the target administrative region can be corrected based on the following formula:

[0144] where, represents the planting area data of the target administrative region after correction processing; represents the planting area data of the first administrative region; represents the planting area data of the target administrative region before correction processing; represents the solid state effect of the target administrative region; represents the random effect of the target administrative region.

[0145] According to the method for identifying abnormal crop planting areas of the present application, through a multi-dimensional joint anomaly detection mechanism, the vertical hierarchical correlation (the first administrative region) and the horizontal spatio-temporal proximity (the second administrative region) are fused to construct a dual detection framework of a hierarchical Bayesian model and a spatio-temporal autoregressive model. The vertical model analyzes the contribution heterogeneity of the target administrative region to the first administrative region, and identifies the first random error offset and random residual anomaly; the horizontal model quantifies the spatial weights of neighboring regions and the historical trend inertia, and captures local spatio-temporal deviations. The collaborative decision-making of the two models significantly reduces the misjudgment risk of traditional single-dimensional analysis, especially for anomalies in hidden areas (such as synchronous fluctuations in multiple neighboring regions) with high sensitivity. Moreover, by adopting adaptive anomaly classification and dynamic correction, based on the posterior confidence interval, residual distribution offset, and parameter persistence analysis, the model can autonomously distinguish isolated anomalies, regional anomalies, and systematic deviation types without manual presetting of thresholds. For systematic deviations, a dynamic parameter adaptive mechanism is introduced: when the annual change rate of the first random error exceeds 15% for three consecutive years, the historical benchmark parameters and the current posterior mean are automatically fused for resetting to avoid calibration distortion caused by model lag. In addition, data-driven lossless local correction is adopted, abandoning the global smoothing filtering algorithm, and a conditional interpolation strategy based on the posterior predictive distribution is adopted. Only for the planting area data determined to be abnormal, the correction value is generated by integrating the posterior distribution of the hierarchical model parameters, and the original information of the non-abnormal data is retained. This method not only suppresses the over-smoothing of normal data by traditional filtering methods, but also reduces the uncertainty of the correction results in small sample regions through the Bayesian shrinkage effect.

[0146] An embodiment of the present application further provides a device for identifying abnormal crop planting areas.

[0147] As Figure 3 shown in, the device 300 for identifying abnormal crop planting areas includes: a first acquisition module 310, a second acquisition module 320, and a determination module 330.

[0148] The first acquisition module 310 is configured to respectively acquire the planting area data of the target crop in the target administrative region, the first administrative region, and the second administrative region; the first administrative region is the upper-level administrative region of the target administrative region, and the second administrative region is the adjacent administrative region at the same level as the target administrative region; The second acquisition module 320 is configured to obtain a first anomaly recognition result based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, and obtain a second anomaly recognition result based on the planting area data of the target administrative region and the second administrative region; The determination module 330 is configured to determine that the planting area data of the target administrative region is abnormal data when both the first anomaly recognition result and the second anomaly recognition result are abnormal.

[0149] According to the crop planting area anomaly recognition device of the present application, by respectively obtaining the planting area data of the target crop in the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region); based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtaining a first anomaly recognition result, and based on the planting area data of the target administrative region and the second administrative region, obtaining a second anomaly recognition result; in the case where both the first anomaly recognition result and the second anomaly recognition result are anomalies, determining the planting area data of the target administrative region as abnormal data, so as to consider the dimension of the planting plan of the administrative region, and perform anomaly recognition on the planting area data of the target crop in the target administrative region based on the planting area data of the target administrative region, the upper-level administrative region of the target administrative region (i.e., the first administrative region), and the adjacent administrative regions at the same level as the target administrative region (i.e., the second administrative region), so as to improve the accuracy of crop planting area anomaly recognition.

[0150] In some embodiments, the second acquisition module 320 includes: A first acquisition unit, configured to obtain a first random error and a random effect of the target administrative region based on the planting area data of the target administrative region, the first administrative region, and the second administrative region through a vertical hierarchical anomaly discrimination model; the first random error represents the planting area of the current year with respect to the time error, and the random effect represents the objective contribution rate of the target administrative region to the first administrative region in the current year; A first determination unit, configured to determine whether there is an anomaly in the first random error and the random effect of the target administrative region; A second acquisition unit, configured to obtain a first anomaly recognition result indicating an anomaly in the case where at least one of the first random error and the random effect of the target administrative region is abnormal.

[0151] In some embodiments, the first determination unit is configured to obtain a first normal distribution based on the first random error of the target administrative region in historical years; the first normal distribution is the distribution of the first random error corresponding to each historical year with respect to the historical year; based on the first normal distribution, determine whether there is an anomaly in the first random error of the target administrative region.

[0152] In some embodiments, the first determination unit is further configured to obtain a second normal distribution based on the random effect of the second administrative region; the second normal distribution is the distribution of each random effect with respect to each administrative region in the second administrative region; based on the second normal distribution, determine whether the random effect of the target administrative region is abnormal.

[0153] In some embodiments, the second acquisition module 320 further includes: A third acquisition unit, configured to obtain a second random error of the target administrative region based on the planting area data of the target administrative region and the second administrative region through a horizontal spatio-temporal anomaly discrimination model; A second determination unit, configured to determine whether there is an anomaly in the second random error of the target administrative region; A fourth acquisition unit, configured to obtain a second anomaly recognition result indicating an anomaly when the second random error is abnormal.

[0154] In some embodiments, the crop planting area anomaly recognition device 300 further includes: A correction module, configured to perform a correction process on the planting area data of the target administrative region based on the planting area data of the target administrative region, the fixed effect and the random effect, and the planting area data of the first administrative region through a pre-established posterior distribution model when the anomaly recognition result indicates that the planting area data of the target administrative region is abnormal.

[0155] In some embodiments, the correction module is configured to update the fixed effect of the current year based on the normal fixed effect of the target administrative region when the fixed effects of the current year and multiple adjacent historical years of the target administrative region are both abnormal; the normal fixed effect is determined according to the normal fixed effects of the historical years of the target administrative region; and perform a correction process on the planting area data of the target administrative region based on the planting area data of the target administrative region, the updated fixed effect and the random effect, and the planting area data of the first administrative region.

[0156] The crop planting area anomaly recognition device in the embodiments of the present application may be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other devices other than the terminal. Exemplarily, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and may also be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0157] The crop planting area anomaly recognition device in the embodiments of this application can be a device with an operating system. This operating system can be the Microsoft (Windows) operating system, can be the Android operating system, can be the IOS operating system, or can also be other possible operating systems, which are not specifically limited in the embodiments of this application.

[0158] The crop planting area anomaly recognition device 300 provided in the embodiments of this application can implement Figures 1 to 2 each process implemented by the method embodiments. To avoid repetition, it will not be elaborated here.

[0159] In some embodiments, as Figure 4 shown, the embodiments of this application also provide an electronic device 400, including a processor 401, a memory 402, and a computer program stored on the memory 402 and executable on the processor 401. When this program is executed by the processor 401, it implements each process of the above-mentioned crop planting area anomaly recognition method embodiments and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0160] It should be noted that the electronic devices in the embodiments of this application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0161] The embodiments of this application also provide a non-transitory computer-readable storage medium. A computer program is stored on this non-transitory computer-readable storage medium. When this computer program is executed by a processor, it implements each process of the above-mentioned crop planting area anomaly recognition method embodiments and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0162] Among them, the processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disks, or optical discs, etc.

[0163] The embodiments of this application also provide a computer program product, including a computer program. When this computer program is executed by a processor, it implements the above-mentioned crop planting area anomaly recognition method.

[0164] The embodiments of this application further provide a chip. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above-mentioned crop planting area anomaly recognition method embodiments and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0165] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-a-chip, etc.

[0166] It should be noted that in this document, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the presence of additional identical elements in the process, method, article, or device including such element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0167] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0168] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

[0169] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0170] Although the embodiments of this application have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and purposes of this application, and the scope of this application is defined by the claims and their equivalents.

Claims

1. A method for abnormally identifying the planting area of crops, characterized in that, Including: Respectively obtain the planting area data of the target crops in the target administrative region, the first administrative region, and the second administrative region; The first administrative region is the upper-level administrative region of the target administrative region, and the second administrative region is an adjacent administrative region at the same level as the target administrative region; Based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtain a first anomaly recognition result, and based on the planting area data of the target administrative region and the second administrative region, obtain a second anomaly recognition result; When both the first anomaly recognition result and the second anomaly recognition result are anomalies, determine that the planting area data of the target administrative region is abnormal data.

2. The method for abnormally identifying the crop planting area according to claim 1, wherein, The obtaining of the first anomaly recognition result based on the planting area data of the target administrative region, the first administrative region, and the second administrative region includes: Through a vertical hierarchical anomaly discrimination model, based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, obtain the first random error and random effect of the target administrative region; the first random error represents the error of the planting area in the current year with respect to time, and the random effect represents the objective contribution rate of the target administrative region to the first administrative region in the current year; Determine whether there are anomalies in the first random error and the random effect of the target administrative region; When at least one of the first random error and the random effect of the target administrative region is abnormal, obtain a first anomaly recognition result indicating an anomaly.

3. The method for abnormally identifying the crop planting area according to claim 2, wherein, The determination of whether there are anomalies in the first random error and the random effect of the target administrative region includes: Based on the first random error of the target administrative region in historical years, obtain a first normal distribution; the first normal distribution is the distribution of the first random error corresponding to each historical year with respect to the historical year; Based on the first normal distribution, determine whether there is an anomaly in the first random error of the target administrative region.

4. The method for abnormally identifying the crop planting area according to claim 2, wherein, The determination of whether there are anomalies in the first random error and the random effect of the target administrative region includes: Based on the random effect of the second administrative region, obtain a second normal distribution; the second normal distribution is the distribution of each random effect with respect to each administrative region in the second administrative region; Based on the second normal distribution, determine whether the random effect of the target administrative region is abnormal.

5. The method for abnormally identifying the crop planting area according to claim 1, wherein The obtaining of the second anomaly recognition result based on the planting area data of the target administrative region and the second administrative region includes: Through a horizontal spatio-temporal anomaly discrimination model, based on the planting area data of the target administrative region and the second administrative region, obtain the second random error of the target administrative region; the second random error represents the error of the planting area in the current year with respect to space; Determine whether there is an anomaly in the second random error of the target administrative region; When the second random error is abnormal, obtain a second anomaly recognition result indicating an anomaly.

6. The method for abnormally identifying the crop planting area according to any one of claims 1-5, characterized in that, After determining that the planting area data of the target administrative region is abnormal data when both the first abnormal recognition result and the second abnormal recognition result are abnormal, the method further includes: Based on the planting area data, fixed effects, and random effects of the target administrative region and the planting area data of the first administrative region, correcting the planting area data of the target administrative region through a pre-established posterior distribution model.

7. The method for abnormally identifying the crop planting area according to claim 6, wherein, The correcting the planting area data of the target administrative region through a pre-established posterior distribution model based on the planting area data, fixed effects, and random effects of the target administrative region and the planting area data of the first administrative region includes: When the fixed effects of the current year and multiple adjacent historical years of the target administrative region are all abnormal, updating the fixed effect of the current year based on the normal fixed effect of the target administrative region; the normal fixed effect is determined according to the normal fixed effects of the historical years of the target administrative region; Based on the planting area data of the target administrative region, the updated fixed effect, random effects, and the planting area data of the first administrative region, correcting the planting area data of the target administrative region.

8. An abnormal recognition device for crop planting area, characterized in that including: A first acquisition module, configured to respectively acquire the planting area data of the target crops in the target administrative region, the first administrative region, and the second administrative region; The first administrative region is the upper-level administrative region of the target administrative region, and the second administrative region is an adjacent administrative region at the same level as the target administrative region; A second acquisition module, configured to obtain a first abnormal recognition result based on the planting area data of the target administrative region, the first administrative region, and the second administrative region, and obtain a second abnormal recognition result based on the planting area data of the target administrative region and the second administrative region; A determination module, configured to determine that the planting area data of the target administrative region is abnormal data when both the first abnormal recognition result and the second abnormal recognition result are abnormal.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the crop planting area abnormal recognition method according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the crop planting area abnormal recognition method according to any one of claims 1-7.

Images