A method, device and medium for obtaining the degree of governance of a geographical area
Through feature extraction and weighted calculation of remote sensing image data set, the degree of governance to be managed by non-grain farming plots is accurately evaluated, which solves the problems of unreasonable governance strategies and difficult cost control, and improves the quality of governance and cost control effect.
Patent Information
- Application Number
- CN202411903349.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-23
- Publication Date
- 2025-04-04
AI Technical Summary
Before managing non-grain farming plots, it is difficult to accurately understand the actual situation and degree of governance required for land, which leads to unreasonable governance strategies and difficult to control governance costs.
By obtaining the remote sensing image data set of the geographical area to be managed, extracting feature vectors, calculating feature weights, weighting and calculations to obtain the score to be managed, and the degree to be managed is obtained through normalization processing.
A reasonable and accurate assessment of the degree to be managed in geographical areas is achieved, providing a basis for determining applicable governance strategies, and improving the effectiveness of governance quality and cost control.
Smart Images
Figure CN119762730A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and medium for acquiring the degree of governance of a geographical area. Background Art
[0002] At present, in order to promote the "non-grain" remediation work, it is necessary to manage non-grain cultivated land and increase the area of grain fields. Grain fields refer to relatively concentrated and contiguous plots based on permanent basic farmland, with good water and soil resources, relatively complete infrastructure, and crops planted can be wheat, corn, etc., while the current non-grain cultivated land is mainly perennial economic crop plots, such as plots for planting seedlings, flowers, fruits, etc. Therefore, it is necessary to carry out remediation work on non-grain cultivated land. Before remediating this type of plot, it is necessary to understand the actual situation of the plot and the degree of remediation required to find a suitable remediation strategy, which is meaningful for improving the quality of remediation and controlling the cost of remediation.
[0003] Therefore, the present invention proposes a method for obtaining the degree of governance in a geographical area. Summary of the invention
[0004] In response to the above technical problems, the present invention provides a method, device and medium for obtaining the degree of governance of a geographical area, which can obtain a reasonable and accurate degree of governance of a geographical area and provide a basis for determining a governance strategy suitable for the geographical area.
[0005] According to a first aspect of the present invention, a method for obtaining the degree of governance to be achieved in a geographical area is provided, comprising the following steps:
[0006] S100, obtaining a first image data set of the geographical area to be governed; the first image data set is a collection of a number of images obtained by taking remote sensing images of the geographical area to be governed according to a time period within a preset time period.
[0007] S200, perform feature extraction on the first image data set to obtain a first feature vector corresponding to the geographic area to be governed; the first feature vector corresponds to several target feature dimensions including the area corresponding to the geographic area to be governed, the crop growth cycle, the difference between the maximum NDVI value and the average NDVI value within the crop growth cycle, the average change rate of the NDVI value, and the NDVI value distribution ratio.
[0008] S300: Calculate the feature weight corresponding to each target feature dimension in the first feature vector.
[0009] S400, calculating a weighted sum according to the feature value and feature weight corresponding to each target feature dimension to obtain a score for the geographical area to be governed.
[0010] S500, normalizing the governance score corresponding to the governance geographical area to be governed to obtain the governance degree corresponding to the governance geographical area to be governed.
[0011] According to a second aspect of the present invention, there is provided a non-transitory computer-readable storage medium, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the above-mentioned method for obtaining the degree of governance of a geographical area.
[0012] According to a third aspect of the present invention, there is provided an electronic device comprising a processor and the above-mentioned non-transitory computer-readable storage medium.
[0013] The present invention has at least the following beneficial effects:
[0014] The present invention provides a method for obtaining the degree of governance of a geographical area. First, a first image data set of the geographical area to be governed is obtained, and features are extracted from the first image data set to obtain a first feature vector corresponding to the geographical area to be governed. The feature weight corresponding to each target feature dimension in the first feature vector is calculated to obtain the influence of each target feature dimension on the degree to be governed, and the positive or negative influence of the target feature dimension on the degree to be governed is also considered. Then, according to the feature value and feature weight corresponding to each target feature dimension, a weighted sum is calculated to obtain a score to be governed corresponding to the geographical area to be governed. Finally, the score to be governed corresponding to the geographical area to be governed is normalized to obtain the degree to be governed corresponding to the geographical area to be governed, so that the obtained degree to be governed is more reasonable and accurate, so that the target personnel can grasp the land situation of the geographical area to be governed, and provide a basis for determining the governance strategy suitable for the geographical area. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0016] Figure 1 A flowchart of a method for obtaining the degree of governance of a geographical area provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0018] The embodiment of the present invention provides a method for obtaining the degree of governance of a geographical area. Figure 1 As shown, the method comprises the following steps:
[0019] S100, obtaining a first image data set of the geographical area to be governed; the first image data set is a collection of a plurality of images obtained by taking remote sensing images of the geographical area to be governed according to a time period within a preset time period. The preset time period is longer than the crop growth cycle corresponding to the geographical area to be governed. In a specific implementation, the time period may be 1 day.
[0020] Specifically, the geographical area to be governed may be a plot of land where perennial cash crops are planted, for example, fruits, flowers, trees, and the like.
[0021] S200, extract features from the first image data set to obtain a first feature vector corresponding to the geographic area to be managed; the first feature vector corresponds to several target feature dimensions including the area corresponding to the geographic area to be managed, the crop growth cycle, the difference between the maximum NDVI value and the average NDVI value within the crop growth cycle, the average change rate of the NDVI value, and the NDVI value distribution ratio. For example, the area of the geographic area to be managed is the average value of the area obtained from each first image data, wherein obtaining the area size of the physical object in the image based on the image data is a prior art and will not be described in detail here.
[0022] Furthermore, the crop growth cycle corresponding to the geographical area to be governed is a number of days. Since crops have a pattern of changing from small to large and then to small in the process of growth, the crop growth cycle can be obtained according to the change cycle of the NDVI value.
[0023] Specifically, the average change rate of the NDVI value is the ratio of the difference between the maximum NDVI value and the average NDVI value during the crop growth cycle to the crop growth cycle.
[0024] Furthermore, the NDVI value distribution ratio is the ratio of the difference between the maximum NDVI value and the average NDVI value during the crop growth cycle to the area of the geographical area to be managed.
[0025] As mentioned above, due to the different crops planted in the geographical areas to be governed and the grain-cultivating geographical areas, the two types of plots will have significantly different characteristics. When considering the degree of governance of the geographical areas to be governed, since the crop growth cycles of the two types of geographical areas are quite different, and the NDVI of the crops in the geographical areas to be governed varies greatly, while the NDVI of the crops in the grain-cultivating geographical areas fluctuates less, extracting the above-mentioned target characteristic dimensions will help to grasp the gap between the geographical areas to be governed and the grain-cultivating geographical areas, and thus help to obtain the degree of governance of the geographical areas to be governed.
[0026] S300: Calculate the feature weight corresponding to each target feature dimension in the first feature vector.
[0027] In a specific embodiment, step S300 includes the following steps:
[0028] S301, obtaining a number of geographic area samples to be governed and a target feature data set corresponding to each of the geographic area samples to be governed; the target feature data set includes data corresponding to each target feature dimension.
[0029] S302, standardizing the data in the target feature data set corresponding to each sample of the geographic area to be governed, so that the data corresponding to different target feature dimensions are converted into the same dimension.
[0030] S303: Calculate the feature information entropy corresponding to each target feature dimension based on the standardized data.
[0031] Among them, the feature information entropy corresponding to the target feature dimension meets the following conditions:
[0032] H j =-(1 / lnm)∑ m i＝1 (P ij oeLh ij ), where H j is the characteristic information entropy corresponding to the jth target characteristic dimension, m is the number of samples in the geographical area to be governed, P ij is the proportion of the i-th sample of the geographical area to be governed under the j-th target characteristic dimension.
[0033] S304, calculating the feature weight corresponding to each target feature dimension according to the feature information entropy corresponding to each target feature dimension.
[0034] Among them, the feature weights corresponding to the target feature dimensions meet the following conditions:
[0035] W j =(1-H j ) / ∑ nj＝1 (1-H j ), where W j is the feature weight corresponding to the jth target feature dimension, and n is the number of target feature dimensions.
[0036] As mentioned above, since the introduced multiple target feature dimensions can play an effective role in distinguishing the geographical areas to be governed and the geographical areas to be grain cultivated, but the degree of influence of each target feature dimension is different, by obtaining the above-mentioned feature weights, it is possible to know the influence of each target feature dimension on the score to be governed, thereby improving the accuracy of the score to be governed.
[0037] S400, calculating a weighted sum according to the feature value and feature weight corresponding to each target feature dimension to obtain a score for the geographical area to be governed.
[0038] Specifically, the governance score corresponding to the to-be-governed geographical area meets the following conditions:
[0039] S=∑ D d＝1 (±a d (2 / π×abs(arctg(x d ), where S represents the governance score corresponding to the geographical area to be governed, D is the number of target feature dimensions, and a d is the feature weight corresponding to the dth target feature dimension, x d is the eigenvalue corresponding to the dth target feature dimension. ± indicates that when the target feature dimension is the regional area or the crop growth cycle, it takes a positive sign, otherwise it takes a negative sign.
[0040] It should be noted that since the growth cycle of grain crops is short and the NDVI values vary greatly from planting to harvesting, while the growth cycle of perennial cash crops is long and the perennial vegetation index always maintains a high value with only a small fluctuation, the longer the crop growth cycle, the more the crop tends to be a perennial cash crop and the more it needs governance. On this basis, the larger the regional area, the greater the degree of governance, and the smaller the change in NDVI value, the more it tends to be a perennial cash crop. Therefore, the regional area and crop growth cycle have a positive impact on the governance score, while other characteristic dimensions have a negative impact on the governance score.
[0041] S500, normalizing the governance score corresponding to the governance geographical area to be governed to obtain the governance degree corresponding to the governance geographical area to be governed.
[0042] Specifically, the degree of governance F corresponding to the geographical area to be governed meets the following conditions:
[0043] F = 100 × 1 / (1 + e -S ).
[0044] As mentioned above, by obtaining the feature weight corresponding to each target feature dimension, it is possible to know the degree of influence of each target feature dimension on the degree of governance of the geographical area to be governed, and consider the positive or negative influence of the target feature dimension on the degree of governance, so that the calculated score to be governed is more reasonable and reliable. By normalizing the score to be governed, when there are multiple geographical areas to be governed, the degree to be governed corresponding to each geographical area to be governed is limited to the same range based on the same standard, so that the obtained degree to be governed is more reasonable, thereby improving the accuracy of the obtained governance policy text and making the obtained governance policy text more in line with the needs.
[0045] In a specific embodiment, the method further comprises the following steps:
[0046] S10, when the degree of governance corresponding to the geographical area to be governed is greater than a preset degree threshold, a second feature vector corresponding to each geographical area under governance is obtained based on a second image data set of each geographical area under governance obtained in advance, and based on the similarity between the first feature vector and each second feature vector, the geographical area under governance corresponding to the geographical area to be governed is determined, and the determined geographical area under governance is used as the key geographical area.
[0047] Specifically, the geographical area under governance refers to an area that is under governance and does not belong to a grain farming geographical area; for example, the entire geographical area originally planted with cash crops is governed to plant grain crops in part of the area.
[0048] Furthermore, crops in the grain-growing geographical area include rice, wheat and corn.
[0049] Specifically, the method for acquiring the second image data set is consistent with the method for acquiring the first image data set.
[0050] Furthermore, the method for obtaining the second feature vector is consistent with the method for obtaining the first feature vector, that is, the target feature dimensions corresponding to the second feature vector include the regional area corresponding to the geographical area under governance, the crop growth cycle, the difference between the maximum NDVI value and the average NDVI value within the crop growth cycle, the average change rate of the NDVI value, and the NDVI value distribution ratio; among which, the crop growth cycle is the average growth cycle of all crops in the geographical area under governance.
[0051] In a specific embodiment, the following steps are used to determine the geographical area under governance corresponding to the geographical area to be governed:
[0052] S11, for any target feature dimension, calculate the feature similarity between the feature value of the target feature dimension in the first feature vector and the feature value of the target feature dimension in each second feature vector. For example, the feature similarity between the two feature values is obtained by calculating the cosine similarity of the two feature values.
[0053] S12, based on the feature similarity between the feature value of the target feature dimension in the first feature vector and the feature value of the target feature dimension in each second feature vector and the feature weight corresponding to each target feature dimension, a weighted sum is calculated to obtain the first similarity of the first feature vector and each second feature vector.
[0054] S13, determining the managed geographical area corresponding to the largest first similarity as the managed geographical area corresponding to the to-be-managed geographical area.
[0055] As mentioned above, when the degree of governance corresponding to the geographical area to be governed is large, it indicates that the difference between the geographical area to be governed and the grain-cultivating geographical area is large. Therefore, in the governance process, it is necessary to first transition to the geographical area under governance. By comparing the similarity between the characteristic vectors of the two geographical areas, the geographical area under governance that is similar to the geographical area to be governed can be determined, and its governance situation is closer to and suitable for the geographical area to be governed. Therefore, the found governance policy text is more in line with the actual governance needs of the geographical area to be governed.
[0056] S20, when the degree of governance corresponding to the geographical area to be governed is not greater than the preset degree threshold, the third feature vector corresponding to each grain-growing geographical area is obtained according to the third image data set of each grain-growing geographical area obtained in advance, and the grain-growing geographical area corresponding to the geographical area to be governed is determined according to the similarity between the first feature vector and each third feature vector, and the determined grain-growing geographical area is used as the key geographical area.
[0057] Specifically, the method for acquiring the third image data set is consistent with the method for acquiring the first image data set.
[0058] Furthermore, the method for obtaining the third eigenvector is consistent with the method for obtaining the first eigenvector, that is, the target feature dimensions corresponding to the third eigenvector include the regional area corresponding to the grain farming geographical area, the crop growth cycle, the difference between the maximum NDVI value and the average NDVI value during the crop growth cycle, the average change rate of the NDVI value, and the NDVI value distribution ratio.
[0059] In a specific embodiment, the food farming geographical area corresponding to the geographical area to be governed is determined by the following steps:
[0060] S21, for any target feature dimension, calculate the feature similarity between the feature value of the target feature dimension in the first feature vector and the feature value of the target feature dimension in each third feature vector. For example, the feature similarity between the two feature values is obtained by calculating the cosine similarity of the two feature values.
[0061] S22, based on the feature similarity between the feature value of the target feature dimension in the first feature vector and the feature value of the target feature dimension in each third feature vector and the feature weight corresponding to each target feature dimension, a weighted sum is calculated to obtain the second similarity of the first feature vector and each third feature vector.
[0062] S23, determining the grain-growing geographical area corresponding to the largest second similarity as the grain-growing geographical area corresponding to the geographical area to be governed.
[0063] As mentioned above, when the degree of governance corresponding to the geographical area to be governed is small, it indicates that the difference between the geographical area to be governed and the grain-cultivating geographical area is small. Therefore, the grain-cultivating geographical area can be directly used as the governance direction of the geographical area to be governed. By comparing the similarity between the characteristic vectors of the two geographical areas, the grain-cultivating geographical area close to the geographical area to be governed can be determined, and its governance situation is closer to and suitable for the geographical area to be governed. Therefore, the found governance strategy text is more in line with the actual governance needs of the geographical area to be governed.
[0064] S30, based on the key geographical area, determining the target governance policy text corresponding to the geographical area to be governed from a preset governance policy text library.
[0065] Specifically, step S30 also includes the following steps:
[0066] S31, when the key geographical area is a food-growing geographical area, determining a first target plot of land to be governed from the geographical area to be governed.
[0067] Specifically, the geographical area to be managed is divided into a number of regional grids, and according to the change of the NDVI value of each regional grid, the regional grids determined with non-food crops are merged as the first target plot to be managed.
[0068] S32, obtaining the attribute characteristics of the first target land parcel to be governed, and obtaining the corresponding first governance policy text from the first governance policy text set in the preset governance policy text library according to the attribute characteristics of the first target land parcel to be governed; it can be understood as: using the attribute characteristics as keywords, searching the first governance policy text set for the first governance policy text with the highest similarity to the attribute characteristics.
[0069] Specifically, the attribute characteristics of the first target land parcel to be managed include the area of the first target land parcel to be managed and the types of crops planted in the first target land parcel to be managed.
[0070] S33, when the key geographical area is a geographical area under governance, obtaining attribute characteristics of the key geographical area, and obtaining a corresponding second governance policy text from a second governance policy text set in a preset governance policy text library according to the attribute characteristics of the key geographical area.
[0071] Specifically, the attribute characteristics of the key geographical area include the area of the key geographical area and the types of crops grown in the key geographical area.
[0072] Furthermore, the method for acquiring the second governance policy text is consistent with the method for acquiring the first governance policy text.
[0073] As mentioned above, the degree of treatment of the geographical area to be treated can reflect the gap between cultivated crops and food crops. For different cultivated crops, when treating them to make them tend to food plots, factors such as the impact of the crops to be treated on the growth of food crops, soil nutrition and treatment costs should be considered. Therefore, different treatment methods should be adopted for plots with different degrees of treatment. For example, when the degree of treatment is large, it is necessary to first transition to the geographical area under treatment, which is conducive to improving the rationality of plot treatment and promoting the balance of local food revenue and expenditure and economic revenue and expenditure.
[0074] In summary, the present invention provides a method for obtaining the degree of governance of a geographical area, firstly, a first image data set of the geographical area to be governed is obtained, and features are extracted from the first image data set to obtain a first feature vector corresponding to the geographical area to be governed, and the feature weight corresponding to each target feature dimension in the first feature vector is calculated to obtain the influence of each target feature dimension on the degree to be governed, and the positive or negative influence of the target feature dimension on the degree to be governed is also considered, and then a weighted sum is calculated according to the feature value and feature weight corresponding to each target feature dimension to obtain a score to be governed corresponding to the geographical area to be governed, and finally the score to be governed corresponding to the geographical area to be governed is normalized to obtain the degree to be governed corresponding to the geographical area to be governed, so that the obtained degree to be governed is more reasonable and accurate, so that the target personnel can grasp the land situation of the geographical area to be governed, and provide a basis for determining the governance strategy suitable for the geographical area.
[0075] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method for obtaining the degree of governance of a geographical area provided in the above embodiment.
[0076] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.
[0077] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.
Claims
1. A method for obtaining the degree of governance of a geographical area, characterized in that: The method comprises the following steps: S100, obtaining a first image data set of the geographical area to be governed; the first image data set is a collection of a plurality of images obtained by taking remote sensing images of the geographical area to be governed according to a time period within a preset time period; S200, extracting features from the first image data set to obtain a first feature vector corresponding to the geographical area to be governed; the first feature vector corresponds to a number of target feature dimensions including the area corresponding to the geographical area to be governed, the crop growth cycle, the difference between the maximum NDVI value and the average NDVI value within the crop growth cycle, the average change rate of the NDVI value, and the NDVI value distribution ratio; S300, calculating a feature weight corresponding to each target feature dimension in the first feature vector; S400, calculating a weighted sum according to the characteristic value and characteristic weight corresponding to each target characteristic dimension to obtain a score corresponding to the geographical area to be governed; S500, normalizing the governance score corresponding to the governance geographical area to be governed to obtain the governance degree corresponding to the governance geographical area to be governed.
2. The method for obtaining the degree of governance of a geographical area according to claim 1, characterized in that: The average change rate of the NDVI value is the ratio of the difference between the maximum NDVI value and the average NDVI value during the crop growth cycle to the crop growth cycle; The NDVI value distribution ratio is the ratio of the difference between the maximum NDVI value and the average NDVI value during the crop growth cycle to the area of the geographical area to be managed.
3. The method for obtaining the degree of governance of a geographical area according to claim 1, characterized in that: Step S300 includes the following steps: S301, obtaining a number of samples of geographic areas to be governed and a target feature data set corresponding to each sample of geographic areas to be governed; the target feature data set includes data corresponding to each target feature dimension; S302, standardizing the data in the target feature data set corresponding to each sample of the geographic area to be governed, so that the data corresponding to different target feature dimensions are converted into the same dimension; S303, calculating the feature information entropy corresponding to each target feature dimension according to the standardized data; Among them, the feature information entropy corresponding to the target feature dimension meets the following conditions: H j =-(1 / lnm)∑ m i＝1 (P ij LqCy ij ), where H j is the characteristic information entropy corresponding to the jth target characteristic dimension, m is the number of samples in the geographical area to be governed, P ij is the proportion of the i-th sample of the geographical area to be governed under the j-th target characteristic dimension; S304, calculating a feature weight corresponding to each target feature dimension according to the feature information entropy corresponding to each target feature dimension; Among them, the feature weights corresponding to the target feature dimensions meet the following conditions: W j =(1-H j ) / ∑ n j＝1 (1-H j ), where W j is the feature weight corresponding to the jth target feature dimension, and n is the number of target feature dimensions.
4. The method for obtaining the degree of governance of a geographical area according to claim 1, characterized in that: The governance score corresponding to the geographical area to be governed meets the following conditions: S=∑ D d＝1 (±a d (2 / π×abs(arctg(x d ), where S represents the governance score corresponding to the geographical area to be governed, D is the number of target feature dimensions, and a d is the feature weight corresponding to the dth target feature dimension, x d is the eigenvalue corresponding to the dth target feature dimension. ± indicates that when the target feature dimension is the regional area or the crop growth cycle, it takes a positive sign, otherwise it takes a negative sign.
5. The method for obtaining the degree of governance of a geographical area according to claim 1, characterized in that: The method further comprises the steps of: S10, when the degree of governance corresponding to the to-be-governed geographical area is greater than a preset degree threshold, a second feature vector corresponding to each of the to-be-governed geographical areas is obtained according to a second image data set of each of the to-be-governed geographical areas in advance, and a to-be-governed geographical area corresponding to the to-be-governed geographical area is determined according to the similarity between the first feature vector and each of the second feature vectors, and the determined to-be-governed geographical area is used as a key geographical area; S20, when the degree of governance corresponding to the to-be-governed geographical area is not greater than a preset degree threshold, obtaining a third feature vector corresponding to each grain-growing geographical area according to a third image data set of each grain-growing geographical area obtained in advance, and determining the grain-growing geographical area corresponding to the to-be-governed geographical area according to the similarity between the first feature vector and each third feature vector, and using the determined grain-growing geographical area as the key geographical area; S30, based on the key geographical area, determining the target governance policy text corresponding to the geographical area to be governed from a preset governance policy text library.
6. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the method for obtaining the degree of governance of a geographical area as described in any one of claims 1-5.
7. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 6.