Greening maintenance section intelligent division method based on geographic elements

Abstract

The invention provides a geographic element-based greening maintenance section intelligent division method, which comprises the following steps of: 1, acquiring geographic element data of a target area, including POI point data, water system sideline data and road sideline data, and 2, respectively generating corresponding kernel functions according to the POI point data, the water system sideline data and the road sideline data, generating a comprehensive weight distribution map covering the target area through a weight accumulation mode; step 3; selecting a corresponding number of seed points according to a preset section division number, and generating a weighted Voronoi graph based on the weights of the seed points; step 4, taking the variance of the weight accumulation sum of the subdivided grids in each Voronoi sub-region as a loss function to obtain an equalized weighted Voronoi graph; and 5, according to the optimized weighted Voronoi diagram, cutting and segmenting the target area, and outputting a final greening maintenance section division result. According to the intelligent division method, the division efficiency is improved, and section division is formed; and the method has good expansibility.

Description

Technical Field

[0001] The present invention belongs to the technical field of greening maintenance, and more specifically, relates to an intelligent division method for greening maintenance sections based on geographical elements. Background Art

[0002] With the rapid development of urbanization, the construction and widening of urban roads are also progressing rapidly, and the cause of road greening becomes particularly important. On the other hand, with the rapid development of urban transportation, people's requirements for the functions of road greening are becoming more comprehensive, and the quality requirements for various functions are also getting higher and higher. This requires scientific and reasonable planning of urban road green spaces based on the research of urban road greening.

[0003] In urban life, urban greening maintenance is an essential task. Therefore, the areas that need to be maintained in the urban area are usually divided into different sections as the basic units for bidding and construction management.

[0004] Currently, in the management of Party A, it is usually professional people in greening maintenance, engineering personnel and the person in charge of Party A who discuss, consider the geographical elements of the maintenance area and the density of population and business, measure within the specified quantity range, and then determine the scope of these sections. There are repeated discussions, adjustments, and reaching a consensus to draw a conclusion.

[0005] The existing technology has the following problems:

[0006] 1. Low efficiency: This method usually requires multiple meetings and repeated discussions, consuming a large amount of time, which may lead to a slow decision-making process;

[0007] 2. Difficult coordination: People with different roles may have different concerns and opinions. It takes a long time to reach an agreement and there will be challenges in coordination;

[0008] 3. High subjectivity: The decision-making process highly depends on the experience and judgment of participants, may be affected by personal preferences, and lacks objective data support;

[0009] 4. Information asymmetry: The degree of information mastery of all parties may be different, resulting in incomplete or deviated decisions;

[0010] 5. High communication cost: The participation of multiple parties and frequent interactions increase the communication cost and may lead to misunderstandings or omissions in information transmission. Summary of the Invention

[0011] Therefore, to solve the above technical problems, the present invention proposes an intelligent division method for greening maintenance sections based on geographical elements, including the following steps; Step 1, data preprocessing: Obtain the geographical element data of the target area, including POI point data, water system boundary line data, and road boundary line data, and classify, organize, and standardize the data; Step 2, weight distribution calculation: Generate corresponding kernel functions according to the POI point data, water system boundary line data, and road boundary line data, and generate a comprehensive weight distribution map covering the target area through weight accumulation, where the weights of the water area and the building area are set to 0; Step 3; Seed point selection and initial division: Select the corresponding number of seed points according to the preset number of section divisions, and generate a weighted Voronoi diagram based on the weights of the seed points; Step 4, iterative optimization: Use the variance of the sum of the weights of the subdivision grids in each Voronoi sub-region as the loss function, and iteratively adjust the positions of the seed points through an optimization algorithm until the variance is minimized to obtain a balanced weighted Voronoi diagram; Step 5, section division: Cut and divide the target area according to the optimized weighted Voronoi diagram, and output the final greening maintenance section division result. Through the intelligent division method of the present invention, the division efficiency is improved, geographical elements and other factors can be quickly considered to form the division of sections; moreover, the considered factors are verified according to certain rules, increasing objectivity, reducing disputes, and being easily recognized by all parties involved. At the same time, it has good scalability. If new factors are considered, they can participate in the form of weight data and immediately participate in the model operation to obtain corresponding results.

[0012] An intelligent division method for greening maintenance sections based on geographical elements, including the following steps;

[0013] Step 1, data preprocessing: Obtain the geographical element data of the target area, including POI point data, water system boundary line data, and road boundary line data, and classify, organize, and standardize the data;

[0014] Step 2, weight distribution calculation: Generate corresponding kernel functions according to the POI point data, water system boundary line data, and road boundary line data, and generate a comprehensive weight distribution map covering the target area through weight accumulation, where the weights of the water area and the building area are set to 0;

[0015] Step 3; Seed point selection and initial division: Select the corresponding number of seed points according to the preset number of section divisions, and generate a weighted Voronoi diagram based on the weights of the seed points;

[0016] Step 4, Iterative Optimization: Using the variance of the sum of weights of the subdivision grids within each Voronoi sub-region as the loss function, iteratively adjust the positions of the seed points through an optimization algorithm until the variance is minimized, obtaining an equalized weighted Voronoi diagram;

[0017] Step 5, Section Division: According to the optimized weighted Voronoi diagram, crop and divide the target area, and output the final result of the greening maintenance section division.

[0018] Furthermore, in Step 2, the weights of the POI point data are calculated using a Gaussian kernel function; the weights of the water system boundary line data and the road boundary line data are calculated based on their distances from each point in the target area, and the closer the distance, the higher the weight. The standard deviation of the Gaussian kernel function is adaptively determined based on the spatial scale of the target area, specifically 1 / 20 to 1 / 10 of the length of the regional diagonal; the distance calculation uses the Euclidean distance method, and the maximum influence radius is set to 500 meters, and the weights beyond this radius decay to 0.

[0019] Furthermore, in Step 3, the initial positions of the seed points are randomly selected based on the areas in the comprehensive weight distribution map where the weight values are higher than the preset threshold. The preset threshold is the 10%-20% weight quantile value in the comprehensive weight distribution map, and the random selection of the seed points needs to satisfy the minimum spacing constraint, and the spacing is not less than 1 / (number of sections × 2) of the length of the target area diagonal.

[0020] Furthermore, in Step 4, the optimization algorithm is the Adam optimizer. Update the positions of the seed points through the backpropagation algorithm to minimize the loss function. The learning rate of the Adam optimizer is set to 0.01 - 0.1, the momentum parameters β1 = 0.9, β2 = 0.999, the maximum number of iterations is 500 times, and when the change rate of the loss function for 10 consecutive iterations is less than 1%, the optimization is terminated in advance.

[0021] Furthermore, in Step 5, the crop and division are implemented based on a Geographic Information System (GIS) tool to ensure that the section boundaries coincide with natural or artificial geographical elements. The crop and division are based on the "Split Polygon" function module of ArcGIS in the Geographic Information System (GIS) tool, and the boundary is smoothed by combining buffer analysis. The buffer radius is 5 - 10 meters to ensure that the section boundaries are aligned with the road centerlines or water system shorelines.

[0022] Furthermore, Step 2 also includes dynamically adjusting the weight ratios of POIs, water systems, and roads to adapt to the greening maintenance requirements of different urban areas.

[0023] Further, in step four, the calculation of the weighted sum of the subdivision grids includes weight conversion of the Voronoi sub-region boundary grids according to the area ratio. The weight conversion is implemented through an interactive interface. The user can drag the slider to adjust the weight coefficients of POIs, water systems, and roads. The system recommends the optimal weight combination according to the historical maintenance efficiency data.

[0024] Further, the method is implemented through a software system, which supports the user to input the number of sections and weight parameters, and displays the optimized section division results in real time.

[0025] Further, in step one, the data preprocessing further includes outlier removal, coordinate system unification, and spatial interpolation processing of the geographical feature data to ensure the consistency and integrity of the data.

[0026] Further, in step two, the generation of the comprehensive weight distribution map also introduces terrain slope data, and the weights of areas with slopes greater than the preset threshold are reduced to adapt to the maintenance difficulty of complex terrain areas.

[0027] Beneficial effects of the present invention: The present invention proposes an intelligent method for dividing greening maintenance sections based on geographical features, including the following steps; Step one, data preprocessing: Obtain the geographical feature data of the target area, including POI point data, water system boundary line data, and road boundary line data, and classify, organize, and standardize the data; Step two, weight distribution calculation: According to the POI point data, water system boundary line data, and road boundary line data, generate corresponding kernel functions respectively, and generate a comprehensive weight distribution map covering the target area through weight accumulation, where the weights of water areas and building areas are set to 0; Step three; Seed point selection and initial division: According to the preset number of section divisions, select the corresponding number of seed points, and generate a weighted Voronoi diagram based on the weights of the seed points; Step four, iterative optimization: Use the variance of the weighted sum of the subdivision grids in each Voronoi sub-region as the loss function, and iteratively adjust the positions of the seed points through an optimization algorithm until the variance is minimized to obtain a balanced weighted Voronoi diagram; Step five, section division: According to the optimized weighted Voronoi diagram, cut and divide the target area, and output the final greening maintenance section division result. Through the intelligent division method of the present invention, the division efficiency is improved, geographical features and other factors can be quickly considered to form the section division; moreover, the considered factors are checked according to certain rules, increasing objectivity, reducing disputes, and being easily recognized by all parties involved. At the same time, it has good scalability. If new factors are considered, they can participate in the form of weight data and immediately participate in the model operation to obtain corresponding results. Description of the Drawings

[0028] Figure 1This is a flowchart of an intelligent division method for greening maintenance sections based on geographical elements of the present invention.

[0029] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. Specific Embodiments

[0030] The following embodiments are described to assist in understanding the present application, and the embodiments are not and should not be construed in any way as limiting the scope of protection of the present application.

[0031] In the following description, those skilled in the art will recognize that throughout this discussion, components may be described as separate functional units (which may include sub-units), but those skilled in the art will recognize that various components or portions thereof may be divided into separate components or integrated together (including integration within a single system or component).

[0032] At the same time, the connections between components or systems are not intended to be limited to direct connections. Instead, the data between these components may be modified, reformatted, or otherwise changed by intermediate components. Additionally, additional or fewer connections may be used. It should also be noted that the terms "coupled", "connected", or "input" should be understood to include direct connections, indirect connections through one or more intermediate devices, and wireless connections. Embodiment 1:

[0033] As Figure 1 shown, this is a flowchart of an intelligent division method for greening maintenance sections based on geographical elements of the present invention.

[0034] An intelligent division method for greening maintenance sections based on geographical elements includes the following steps; Step 1, data preprocessing: Obtain geographical element data of the target area, including POI point data, water system boundary line data, and road boundary line data, and classify, organize, and standardize the data; Step 2, weight distribution calculation: Generate corresponding kernel functions according to the POI point data, water system boundary line data, and road boundary line data, and generate a comprehensive weight distribution map covering the target area through weight accumulation, where the weights of the water area and building area are set to 0; Step 3; Seed point selection and initial division: Select the corresponding number of seed points according to the preset number of section divisions, and generate a weighted Voronoi diagram based on the weights of the seed points; Step 4, iterative optimization: Use the variance of the sum of the weights of the subdivision grids within each Voronoi sub-region as the loss function, and iteratively adjust the positions of the seed points through an optimization algorithm until the variance is minimized to obtain a balanced weighted Voronoi diagram; Step 5, section division: According to the optimized weighted Voronoi diagram, crop and divide the target area, and output the final greening maintenance section division result.

[0035] In Step 2, the POI point data calculates weights using a Gaussian kernel function; the weights of the water system boundary line data and the road boundary line data are calculated according to their distances from each point in the target area, and the closer the distance, the higher the weight. The standard deviation of the Gaussian kernel function is adaptively determined based on the spatial scale of the target area, specifically 1 / 20 to 1 / 10 of the length of the diagonal of the area; the distance calculation uses the Euclidean distance method, and a maximum influence radius of 500 meters is set, and the weights beyond this radius decay to 0.

[0036] In Step 3, the initial positions of the seed points are randomly selected based on the areas in the comprehensive weight distribution map where the weight values are higher than the preset threshold. The preset threshold is the weight percentile value of the top 10%-20% in the comprehensive weight distribution map, and the random selection of the seed points needs to meet the minimum spacing constraint, and the spacing is not less than 1 / (number of sections × 2) of the length of the diagonal of the target area.

[0037] In Step 4, the optimization algorithm is the Adam optimizer, and the positions of the seed points are updated through the backpropagation algorithm to minimize the loss function. The learning rate of the Adam optimizer is set to 0.01-0.1, the momentum parameters β1 = 0.9, β2 = 0.999, the maximum number of iterations is 500 times, and when the change rate of the loss function for 10 consecutive iterations is less than 1%, the optimization is terminated in advance.

[0038] In Step 5, the cropping and segmentation are implemented based on a Geographic Information System (GIS) tool to ensure that the section boundaries coincide with natural or artificial geographical elements. The cropping and segmentation are based on the "Split Face" function module of ArcGIS in the Geographic Information System (GIS) tool, and the boundary is smoothed by combining buffer analysis. The buffer radius is 5-10 meters to ensure that the section boundaries are aligned with the road center line or the water system shore line.

[0039] Step 2 also includes dynamically adjusting the weight ratios of POI, water system, and road to adapt to the greening maintenance needs of different urban areas.

[0040] In Step 4, the calculation of the cumulative sum of weights of the subdivision grids includes weight conversion for the boundary grids of Voronoi sub-regions according to the area ratio. The weight conversion is implemented through an interactive interface. The user can drag the slider to adjust the weight coefficients of POI, water system, and road, and the system recommends the optimal weight combination based on historical maintenance efficiency data.

[0041] The method is implemented through a software system, which supports users to input the number of sections and weight parameters, and displays the optimized section division results in real time.

[0042] In Step 1, the data preprocessing also includes removing outliers, unifying coordinate systems, and spatial interpolation processing for the geographical feature data to ensure the consistency and integrity of the data.

[0043] In step two, the generation of the comprehensive weight distribution map also introduces terrain slope data, and the weight of areas with a slope greater than a preset threshold is reduced to adapt to the maintenance difficulty of complex terrain areas.

[0044] Advantages of the present invention: The present invention provides an intelligent division method for greening maintenance sections based on geographical elements, including the following steps; Step one, data preprocessing: Obtain geographical element data of the target area, including POI point data, water system boundary line data, and road boundary line data, and classify, organize, and standardize the data; Step two, weight distribution calculation: Generate corresponding kernel functions according to the POI point data, water system boundary line data, and road boundary line data, and generate a comprehensive weight distribution map covering the target area through weight accumulation, where the weights of water areas and building areas are set to 0; Step three; Seed point selection and initial division: Select the corresponding number of seed points according to the preset number of section divisions, and generate a weighted Voronoi diagram based on the weights of the seed points; Step four, iterative optimization: Use the variance of the sum of weights of the sub-grids within each Voronoi sub-region as the loss function, and iteratively adjust the positions of the seed points through an optimization algorithm until the variance is minimized to obtain an equalized weighted Voronoi diagram; Step five, section division: According to the optimized weighted Voronoi diagram, crop and divide the target area, and output the final greening maintenance section division result. Through the intelligent division method of the present invention, the division efficiency is improved, geographical elements and other factors can be quickly considered to form the division of sections; moreover, the considered factors are verified according to certain rules, increasing objectivity, reducing disputes, and being easily recognized by all parties involved. At the same time, it has good scalability. If new factors are considered, they can participate in the form of weight data and immediately participate in the model operation to obtain corresponding results.

[0045] The above embodiments only represent several implementation manners of the present invention, and the description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent shall be subject to the appended claims.

Claims

1. An intelligent division method for greening maintenance sections based on geographical elements, characterized in that: Including the following steps; Step 1, data preprocessing: Obtain the geographical feature data of the target area, including POI point data, water system boundary line data, and road boundary line data, and classify, organize, and standardize the data; Step 2, weight distribution calculation: According to the POI point data, water system boundary line data, and road boundary line data, generate corresponding kernel functions respectively, and generate a comprehensive weight distribution map covering the target area through weight accumulation, where the weights of the water area and the building area are set to 0; Step 3; Seed point selection and initial division: According to the preset number of section divisions, select the corresponding number of seed points, and generate a weighted Voronoi diagram based on the weights of the seed points; Step 4, iterative optimization: Use the variance of the weighted sum of the weights of the subdivision grids in each Voronoi sub-region as the loss function, and iteratively adjust the positions of the seed points through an optimization algorithm until the variance is minimized to obtain an equalized weighted Voronoi diagram; Step 5, section division: According to the optimized weighted Voronoi diagram, crop and divide the target area, and output the final greening maintenance section division result.

2. The intelligent division method of greening maintenance sections based on geographical elements according to claim 1, characterized in that: In Step 2, the Gaussian kernel function is used to calculate the weights of the POI point data; the weights of the water system boundary line data and the road boundary line data are calculated according to their distances from each point in the target area, and the closer the distance, the higher the weight. The standard deviation of the Gaussian kernel function is adaptively determined based on the spatial scale of the target area, specifically 1 / 20 to 1 / 10 of the length of the diagonal of the area; the distance calculation uses the Euclidean distance method, and the maximum influence radius is set to 500 meters, and the weight beyond this radius decays to 0.

3. The intelligent division method for greening maintenance sections based on geographical elements according to claim 1, wherein: In Step 3, the initial positions of the seed points are randomly selected based on the areas in the comprehensive weight distribution map with weight values higher than the preset threshold. The preset threshold is the 10%-20% weight percentile in the comprehensive weight distribution map, and the random selection of the seed points needs to meet the minimum spacing constraint, and the spacing is not less than 1 / (number of sections × 2) of the length of the diagonal of the target area.

4. The intelligent division method of greening maintenance sections based on geographical elements according to claim 1, wherein: In Step 4, the optimization algorithm is the Adam optimizer, and the positions of the seed points are updated through the backpropagation algorithm to minimize the loss function. The learning rate of the Adam optimizer is set to 0.01-0.1, the momentum parameters β1 = 0.9, β2 = 0.999, the maximum number of iterations is 500 times, and when the change rate of the loss function for 10 consecutive iterations is less than 1%, the optimization is terminated in advance.

5. The intelligent division method of greening maintenance sections based on geographical elements according to claim 1, characterized in that: In Step 5, the crop and division are implemented based on a Geographic Information System (GIS) tool to ensure that the section boundaries coincide with natural or artificial geographical features. The crop and division are based on the "Split Raster" function module of ArcGIS in the Geographic Information System (GIS) tool, and the boundary is smoothed by combining buffer analysis. The buffer radius is 5-10 meters to ensure that the section boundary is aligned with the road center line or the water system shore line.

6. The intelligent division method for greening maintenance sections based on geographical elements according to claim 2, wherein: Step 2 also includes dynamically adjusting the weight ratios of POI, water system, and road to adapt to the greening maintenance needs of different urban areas.

7. The intelligent division method for greening maintenance sections based on geographical elements according to claim 4, characterized in that: In step 4, the calculation of the weighted sum of the subdivision grid includes weight conversion of the Voronoi sub-region boundary grid according to the area ratio. The weight conversion is implemented through an interactive interface. The user can drag the slider to adjust the weight coefficients of POIs, water systems, and roads, and the system recommends the optimal weight combination based on historical maintenance efficiency data.

8. The intelligent division method of greening maintenance sections based on geographical elements according to claim 1, characterized in that: The method is implemented through a software system, which supports users to input the number of sections and weight parameters, and displays the optimized section division results in real time.

9. The intelligent division method of greening maintenance sections based on geographical elements according to claim 1, characterized in that: In step 1, the data preprocessing further includes outlier removal, coordinate system unification, and spatial interpolation processing of geographic feature data to ensure the consistency and integrity of the data.

10. The intelligent division method for greening maintenance sections based on geographical elements according to claim 6, characterized in that: In step 2, the generation of the comprehensive weight distribution map also introduces terrain slope data, and the weight of areas with a slope greater than the preset threshold is reduced to adapt to the maintenance difficulty of complex terrain areas.

Images