Road landscape planning method and device, electronic equipment and storage medium

Abstract

The present application relates to the technical field of road landscape planning, and particularly relates to a road landscape planning method and device, an electronic device and a storage medium. The method comprises the following steps: firstly, a plurality of first node vectors are obtained; then, the plurality of first node vectors are classified with the minimum intra-class difference and the maximum inter-class difference as the target, and a road is divided into a plurality of first ecological sensitive sections according to the classification result; then, for each first ecological sensitive section, a view analysis is performed by a geographic information system to obtain a road landscape planning range, and a plant diversity analysis is performed according to the road planning range to obtain a plurality of ecological plots; finally, for each ecological plot, a landscape planning is performed according to ecological base data and sensitive characteristic classification. The present application defines the planning range based on GIS view analysis, combines plant diversity clustering and plot adaptation, preferentially retains original vegetation, avoids invasion of alien species, and maximally protects the integrity of the ecological system around the road.

Description

Technical Field

[0001] This invention relates to the field of road landscape planning technology, and in particular to a road landscape planning method, apparatus, electronic device and storage medium. Background Technology

[0002] As road construction continues to expand, the disturbance to the surrounding ecological environment during construction and operation is becoming increasingly prominent, and the conflict between protecting ecologically sensitive areas and road landscape planning is becoming more and more acute. The ecosystems surrounding roads are complex and diverse, and the degree of ecological sensitivity varies significantly across different road sections. Accurately delineating ecologically sensitive sections and carrying out targeted landscape planning is key to achieving coordinated development between road construction and ecological protection.

[0003] Currently, existing methods for delineating ecologically sensitive road sections largely rely on manual experience or single environmental factor analysis, lacking systematic and quantitative analytical tools. This results in insufficient accuracy in the delineation of sensitive sections, failing to accurately reflect the true differences in the ecological environment along the road. Problems arise such as excessively large differences in ecological characteristics within a category and unclear distinctions between ecological characteristics between categories, failing to provide a scientific and precise basis for subsequent landscape planning. Furthermore, existing delineation methods do not incorporate iterative optimization mechanisms, leading to poor stability and rationality of the classification results, and limited adaptability to different ecological scenarios.

[0004] In the road landscape planning stage, existing technologies often neglect systematic analysis of plant diversity around roads, failing to combine site ecological baseline data and sensitive characteristic classifications to develop differentiated planning schemes. This leads to either an excessive pursuit of aesthetic appeal at the expense of ecological protection, blindly introducing alien species and damaging the integrity of native ecosystems, or a sole emphasis on ecological protection without considering landscape functions, resulting in a disconnect between landscape planning and ecological needs. Furthermore, existing plant diversity classifications often use fixed standards without dynamic clustering optimization based on actual ecological samples, making it difficult to adapt to different ecological scenarios around roads, further reducing the scientific rigor and operability of landscape planning.

[0005] In summary, existing methods for delineating ecologically sensitive road sections and for landscape planning suffer from technical deficiencies such as low delineation accuracy, poor ecological relevance, insufficient scientific rigor in planning, and limited adaptability. These methods fail to effectively balance the relationship between road construction, landscape enhancement, and ecological protection. There is an urgent need for a technical solution that can accurately delineate ecologically sensitive sections, scientifically conduct landscape planning, and achieve coordinated development of ecology and landscape.

[0006] Therefore, it is necessary to develop a road landscape planning method. Summary of the Invention

[0007] The present invention provides a road landscape planning method, apparatus, electronic device and storage medium to solve the problem in the prior art that it is difficult to balance the relationship between landscape enhancement and ecological protection in road landscape planning.

[0008] In a first aspect, embodiments of the present invention provide a road landscape planning method, comprising: Multiple first node vectors are obtained, where each first node vector corresponds to a road node. The first node vectors are obtained based on environmental factors that affect the ecology around the road. With the goal of minimizing intra-class differences and maximizing inter-class differences, the multiple first node vectors are classified, and the road is divided into multiple first ecological sensitive segments based on the classification results. Each first ecological sensitive segment corresponds to a sensitive characteristic classification. For each first ecologically sensitive section, a view analysis is performed using a geographic information system to obtain the road landscape planning scope, and a plant diversity analysis is performed based on the road planning scope to obtain multiple ecological plots; For each ecological plot, landscape planning is carried out based on ecological base data and classification of sensitive characteristics.

[0009] In one possible implementation, the first node vector is constructed based on the elevation, slope, aspect, sunshine duration, and hydrological data of the road nodes. The multiple first node vectors are classified with the goal of minimizing intra-class differences and maximizing inter-class differences. Based on the classification results, the road is divided into multiple first ecologically sensitive segments, including: Get the number of items in the first category; Calculate the squared difference of the plurality of first node vectors, and use it as the global squared difference; Based on the first classification number, the multiple first node vectors are initially classified according to the corresponding road segments to obtain multiple initial classes, wherein each initial class corresponds to a road segment; For each initial class, calculate the within-class squared difference; The variance goodness of fit is determined based on multiple intra-class squared differences and the global squared difference; If the variance fit goodness does not reach the goodness threshold, then the multiple initial classes are iteratively optimized with the goal of maximizing the variance fit goodness. Otherwise, the multiple initial classes obtained through optimization are used as multiple process classes, and the variance goodness-of-fit value obtained through optimization is used as the first historical goodness-of-fit value; If the number of the first category does not reach the threshold, the number of the first category is incremented or decremented, and the process jumps to the step of performing initial classification on the multiple first node vectors according to the corresponding road segments based on the number of the first category to obtain multiple initial classes. Otherwise, a first curve is plotted to show the relationship between the number of categories and the goodness of fit of variance, with the first category number as the horizontal axis and the first historical goodness value as the vertical axis. The category number corresponding to the inflection point of the first curve is taken as the target number. Based on the multiple process classes corresponding to the target number, the road is divided into multiple first ecologically sensitive sections.

[0010] In one possible implementation, the iterative optimization of the plurality of initial classes with the objective of maximizing the variance fit includes: Obtain multiple first-class node positions, where each initial class is obtained based on two adjacent first-class node positions; Based on the first formula, the variance goodness of fit, the historical variance goodness of fit, the positions of the plurality of first classification nodes, and the positions of the plurality of historical classification nodes, the positions of the plurality of first nodes are adjusted, wherein the first formula is:

[0011] In the formula, For the first The adjusted [number]th Each category node position For the first The adjusted [number]th Each category node position, For the first The adjusted [number]th Each category node position For the first Goodness of fit of the adjusted variance. For the first Goodness of fit of the adjusted variance. For adjustment rate, This is a rounding function. This is the disturbance compensation amount; Based on the adjusted positions of the multiple first nodes, the multiple first node vectors are classified to obtain multiple initial classes; Jump to the step of calculating the within-class squared difference for each initial class.

[0012] In one possible implementation, determining the variance goodness of fit based on multiple within-class squared differences and the global squared difference includes: The variance goodness of fit is determined based on the second formula, multiple intra-class squared differences, and the global squared difference, wherein the second formula is:

[0013] In the formula, For variance, goodness of fit For global squared difference, The sum of the squared differences within the class. For the first The first class A vector, For the first The class center of each class, The total number of classes.

[0014] In one possible implementation, the plant diversity analysis based on the road planning area yields multiple ecological plots, including: Multiple first plots are extracted from the road planning area based on plot characteristics, wherein the plot characteristics include at least one of the following: forest land, wasteland, and land converted from farmland to forest; For each first plot, select multiple plot sample squares; For each first plot, plant diversity statistics are performed based on multiple plot quadrats of the first plot, and the obtained plant diversity data are used to construct a plot plant diversity vector, where the plant diversity vector represents the characteristics of the plot plant species and the overall proportion of plants. For each plot's plant diversity vector, vectors with a distance less than a distance threshold are selected from multiple plant diversity classes and used as the plot's reference vector. Each plant diversity class corresponds to an ecological characteristic. For each first plot, the plant diversity class with the most reference vectors is taken as the plot's class, and the plot is constructed as an ecological plot based on the plant diversity of the plot's class.

[0015] In one possible implementation, the plant diversity class is obtained based on clustering multiple ecological sample vectors, including: The cluster density and multiple ecological sample vectors are obtained. The ecological sample vectors are constructed based on the plant diversity statistics of the plots, and each ecological sample vector corresponds to a plot ecology. Cluster the multiple ecological sample vectors according to the clustering density to obtain multiple natural classes; For each natural class, the ecology of the natural class is determined based on the ecology of the plot corresponding to the vector, and the ratio of the number of vectors of the ecology of the corresponding natural class to the number of vectors in the natural class is used as the consistency reference value of the natural class. If multiple consistency reference values ​​are all higher than the reference threshold, then multiple natural classes will be used as the plant diversity classes. Otherwise, increase the clustering density and proceed to the step of clustering the multiple ecological sample vectors according to the clustering density to obtain multiple natural classes.

[0016] In one possible implementation, the ecological base data includes existing plant varieties, and for each ecological plot, landscape planning based on the ecological base data and sensitive characteristics includes: For each ecological plot, perform the following steps: Based on the ecological base data, landscape plant varieties are adapted to obtain multiple target landscape plants; The scale of each target landscape plant is determined based on its sensitivity characteristics. Landscape planning is carried out based on the multiple target landscape plants and the scale of each target landscape plant.

[0017] Secondly, embodiments of the present invention provide a road landscape planning apparatus for implementing the road landscape planning method as described in the first aspect or any possible implementation thereof, the road landscape planning apparatus comprising: The road environment acquisition module is used to acquire multiple first node vectors, where each first node vector corresponds to a road node. The first node vectors are acquired based on environmental factors that affect the ecology around the road. The ecological sensitivity analysis module is used to classify the multiple first node vectors with the goal of minimizing intra-class differences and maximizing inter-class differences, and divide the road into multiple first ecological sensitivity segments based on the classification results, wherein each first ecological sensitivity segment corresponds to a sensitivity characteristic classification. The ecological analysis module is used to perform a field analysis through a geographic information system for each first ecologically sensitive section to obtain the road landscape planning scope, and to perform plant diversity analysis based on the road planning scope to obtain multiple ecological plots. as well as, The landscape planning module is used to conduct landscape planning for each ecological plot based on ecological baseline data and sensitive characteristics.

[0018] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the computer program to implement the steps of the method as described in the first aspect or any possible implementation of the first aspect.

[0019] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect or any possible implementation thereof.

[0020] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: This invention discloses a road landscape planning method. First, multiple first node vectors are obtained, each corresponding to a road node. These first node vectors are obtained based on environmental factors affecting the surrounding ecology of the road. Then, the multiple first node vectors are classified with the goal of minimizing intra-class differences and maximizing inter-class differences. Based on the classification results, the road is divided into multiple first ecologically sensitive segments, each corresponding to a sensitive characteristic classification. Next, for each first ecologically sensitive segment, a viewpoint analysis is performed using a geographic information system to obtain the road landscape planning scope. Based on the road planning scope, plant diversity analysis is conducted to obtain multiple ecological plots. Finally, for each ecological plot, landscape planning is performed based on ecological base data and the sensitive characteristic classification.

[0021] This invention constructs node vectors by using multiple environmental factors, combines intra- and inter-class differences to optimize objectives and iterative optimization algorithms, accurately delineates ecologically sensitive segments, and balances classification accuracy and efficiency, providing a scientific basis for subsequent planning.

[0022] This invention defines the planning scope based on GIS field analysis, combines plant diversity clustering and plot adaptation, prioritizes the preservation of native vegetation, avoids the invasion of alien species, and maximizes the protection of the integrity of the ecosystem around the road.

[0023] This invention combines ecological base data with sensitive characteristic classification to formulate differentiated landscape planning schemes that not only meet ecological protection requirements but also take into account landscape functions. Furthermore, the accompanying formulas and examples enhance the feasibility of the schemes.

[0024] This invention, through cluster density adjustment and disturbance compensation, adapts to different ecological scenarios around roads, improving the stability and versatility of the solution. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of the road landscape planning method provided by an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the principle of plant diversity analysis within a road planning area provided by an embodiment of the present invention; Figure 3 This is a functional block diagram of the road landscape planning device provided in the embodiments of the present invention; Figure 4This is a functional block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0028] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0029] The embodiments of the present invention will be described in detail below. This example is implemented based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes. However, the protection scope of the present invention is not limited to the following embodiments.

[0030] Figure 1 A flowchart of a road landscape planning method provided for an embodiment of the present invention.

[0031] like Figure 1 As shown, a flowchart illustrating the implementation of the road landscape planning method provided by an embodiment of the present invention is presented, and is described in detail below: In step 101, multiple first node vectors are obtained, where each first node vector corresponds to a road node, and the first node vectors are obtained based on environmental factors that affect the ecology around the road.

[0032] In step 102, the multiple first node vectors are classified with the goal of minimizing intra-class differences and maximizing inter-class differences, and the road is divided into multiple first ecological sensitive segments according to the classification results, wherein each first ecological sensitive segment corresponds to a sensitive characteristic classification.

[0033] In some implementations, the first node vector is constructed based on the elevation, slope, aspect, sunshine duration, and hydrological data of the road node. The multiple first node vectors are classified with the goal of minimizing intra-class differences and maximizing inter-class differences. Based on the classification results, the road is divided into multiple first ecologically sensitive segments, including: Get the number of items in the first category; Calculate the squared difference of the plurality of first node vectors, and use it as the global squared difference; Based on the first classification number, the multiple first node vectors are initially classified according to the corresponding road segments to obtain multiple initial classes, wherein each initial class corresponds to a road segment; For each initial class, calculate the within-class squared difference; The variance goodness of fit is determined based on multiple intra-class squared differences and the global squared difference; If the variance fit goodness does not reach the goodness threshold, then the multiple initial classes are iteratively optimized with the goal of maximizing the variance fit goodness. Otherwise, the multiple initial classes obtained through optimization are used as multiple process classes, and the variance goodness-of-fit value obtained through optimization is used as the first historical goodness-of-fit value; If the number of the first category does not reach the threshold, the number of the first category is incremented or decremented, and the process jumps to the step of performing initial classification on the multiple first node vectors according to the corresponding road segments based on the number of the first category to obtain multiple initial classes. Otherwise, a first curve is plotted to show the relationship between the number of categories and the goodness of fit of variance, with the first category number as the horizontal axis and the first historical goodness value as the vertical axis. The category number corresponding to the inflection point of the first curve is taken as the target number. Based on the multiple process classes corresponding to the target number, the road is divided into multiple first ecologically sensitive sections.

[0034] In some implementations, the iterative optimization of the plurality of initial classes with the objective of maximizing the variance fit includes: Obtain multiple first-class node positions, where each initial class is obtained based on two adjacent first-class node positions; Based on the first formula, the variance goodness of fit, the historical variance goodness of fit, the positions of the plurality of first classification nodes, and the positions of the plurality of historical classification nodes, the positions of the plurality of first nodes are adjusted, wherein the first formula is:

[0035] In the formula, For the first The adjusted [number]th Each category node position For the first The adjusted [number]th Each category node position For the first The adjusted [number]th Each category node position For the first Goodness of fit of the adjusted variance. For the first Goodness of fit of the adjusted variance. For adjustment rate, This is a rounding function. This is the disturbance compensation amount; Based on the adjusted positions of the multiple first nodes, the multiple first node vectors are classified to obtain multiple initial classes; Jump to the step of calculating the within-class squared difference for each initial class.

[0036] In some implementations, determining the goodness of fit of variance based on multiple intra-class squared differences and the global squared difference includes: The variance goodness of fit is determined based on the second formula, multiple intra-class squared differences, and the global squared difference, wherein the second formula is:

[0037] In the formula, For variance, goodness of fit For global squared difference, The sum of the squared differences within the class. For the first The first class A vector, For the first The class center of each class, The total number of classes.

[0038] For example, this invention acquires multiple first node vectors based on a GIS (Geographic Information System). Each first node vector corresponds one-to-one with a road node along the road, and each road node serves as the basic unit for ecological sensitivity analysis. The core of constructing the first node vectors revolves around various environmental factors affecting the stability and integrity of the roadside ecosystem. Through the quantitative collection and standardized processing of these environmental factors, abstract ecological and environmental characteristics are transformed into calculable and analyzable vector data, providing data support for the subsequent precise delineation of ecologically sensitive sections.

[0039] In some scenarios, the construction of the first node vector is based on key environmental factors such as the elevation, slope, aspect, sunshine, and hydrological data of the road node. These factors are core elements that directly affect the growth of vegetation, soil environment, hydrological cycle, and biological habitat around the road. By accurately collecting and standardizing these data, a first node vector that can comprehensively characterize the ecological environment of the road node is constructed.

[0040] This invention aims to minimize intra-class differences and maximize inter-class differences. The multiple first-node vectors obtained in the preceding steps are systematically classified. The core significance of this classification objective is to ensure that road nodes within the same category have similar ecological sensitivity characteristics, while road nodes between different categories exhibit significant differences in ecological sensitivity. Based on the final classification results, the entire road is divided into multiple first-level ecologically sensitive segments, each corresponding to a unique sensitivity characteristic classification. This clarifies the ecological sensitivity type and level of each road segment, providing a basis for subsequent targeted landscape planning.

[0041] In some implementations, the specific process of classifying multiple first node vectors with the goal of minimizing intra-class differences and maximizing inter-class differences, and dividing the road into multiple first ecologically sensitive segments based on the classification results, is as follows: First, based on the total length of the road, the complexity of the surrounding ecological environment, and the requirements for planning accuracy, the number of first categories is reasonably determined. This number serves as the initial reference value for node vector classification. At the same time, it is necessary to calculate the global squared difference of multiple first node vectors. The global squared difference is used to characterize the overall dispersion of all first node vectors and reflect the overall difference level of the ecological environment along the road.

[0042] Then, based on the determined number of first categories, and according to the spatial continuity of roads, multiple first node vectors are initially classified according to their corresponding road segments to obtain multiple initial classes. Each initial class corresponds to a continuous road segment, ensuring that the initial classification is consistent with the spatial distribution of roads.

[0043] Next, for each initial class, its intra-class squared difference is calculated. The intra-class squared difference characterizes the dispersion of all first node vectors within that class. The smaller the intra-class squared difference, the more consistent the ecological characteristics of the nodes within that class. Combining the intra-class squared differences of multiple initial classes with the calculated global squared difference, the variance goodness of fit is determined using a specific calculation method. The variance goodness of fit evaluates the degree to which the current classification result fits the objective of "minimum intra-class variation and maximum inter-class variation." The higher the goodness of fit, the more reasonable the classification result. If the calculated goodness of fit of variance does not reach the preset goodness threshold, it means that the current classification result does not meet the requirements for dividing ecologically sensitive sections. It is necessary to maximize the goodness of fit of variance and iteratively optimize multiple initial classes until the goodness of fit reaches the threshold or tends to stabilize. If the goodness of fit of variance has reached the goodness threshold, the multiple initial classes obtained after optimization are used as multiple process classes, and the corresponding goodness of fit of variance at this time is recorded as the first historical goodness value for subsequent optimization and adjustment of the number of classifications.

[0044] If the current number of first categories does not reach the preset threshold, the number of first categories needs to be increased or decreased (the adjustment range is determined according to the actual planning needs), and the steps of "based on the number of first categories, perform initial classification of the multiple first node vectors according to the corresponding road segments to obtain multiple initial classes" are repeated, and the classification and optimization process is carried out again.

[0045] If the number of categories in the first category has reached the preset threshold, the adjustment of the number of categories is stopped. The first relationship curve between the number of categories and the variance fit is plotted with the number of categories in the first category as the horizontal axis and the first historical goodness value as the vertical axis. By analyzing the trend of the curve, the number of categories corresponding to the inflection point of the curve is determined as the target number of categories. The number of categories at the inflection point can achieve the optimal balance between classification accuracy and efficiency. Finally, based on the multiple process classes corresponding to the target number, the road is divided into multiple first ecologically sensitive sections.

[0046] In some implementations, the specific process of iteratively optimizing multiple initial classes with the goal of maximizing the variance fit is as follows: First, obtain the positions of multiple first-class nodes. The positions of the first-class nodes are the dividing points on the road used to divide different initial classes. Each initial class is defined by two adjacent first-class node positions.

[0047] Then, based on the first formula, the variance goodness of fit of the current iteration, the historical variance goodness of fit of the previous iteration, the positions of multiple first-class nodes, and the positions of multiple historical first-class nodes from the previous iteration, the positions of the current multiple first-class nodes are dynamically adjusted. The first formula is:

[0048] In the formula, For the first The adjusted [number]th Each category node position For the first The adjusted [number]th Each category node position For the first The adjusted [number]th Each category node position For the first Goodness of fit of the adjusted variance. For the first Goodness of fit of the adjusted variance. The adjustment rate is used to control the adjustment range of the classification node positions, and is set according to the actual optimization needs. This is a rounding function. This is the perturbation compensation amount (used to avoid getting trapped in local optima during the iteration process and improve the stability of the optimization results).

[0049] Next, based on the adjusted positions of the multiple first classification nodes, the multiple first node vectors are reclassified to obtain multiple initial classes. Finally, the process jumps to the step of "for each initial class, calculate the intra-class squared difference of the class" to continue the variance fit calculation and iterative optimization until the preset conditions are met.

[0050] In some implementations, the variance goodness of fit is determined by quantification based on the second formula, the intra-class squared differences of multiple initial classes, and the calculated global squared difference. The second formula is:

[0051] In the formula, The variance goodness of fit is denoted as A, with a value range of [0,1]. The closer A is to 1, the better the classification result matches the objective of "minimum within-class differences and maximum between-class differences". The global squared difference characterizes the overall dispersion of all first-node vectors. This is the sum of the within-class squared differences, i.e., the sum of the within-class squared differences of all initial classes, representing the sum of the dispersion of node vectors within all classes. For the first The first class A vector, For the first The class center of each class (i.e., the average value of all first node vectors within that class). This represents the total number of classes in the current category.

[0052] For example, suppose a certain road obtains 1000 first node vectors, and calculates the global squared difference. Given a value of 1200, and setting the number of elements in the first category to 5, resulting in 5 initial categories, the within-class squared differences for each initial category are calculated to be 80, 95, 78, 102, and 85 respectively. The total within-class squared differences are then calculated. The variance goodness of fit is 80 + 95 + 78 + 102 + 85 = 440. Calculate the variance goodness of fit using the second formula. =(1200-440) / 1200≈0.63. If the preset excellence threshold is 0.7, then the initial class needs to be iteratively optimized until A≥0.7.

[0053] In step 103, for each first ecologically sensitive section, a view analysis is performed using a geographic information system to obtain the road landscape planning scope, and a plant diversity analysis is performed based on the road planning scope to obtain multiple ecological plots.

[0054] In some implementations, the step of conducting plant diversity analysis based on the road planning area to obtain multiple ecological plots includes: Multiple first plots are extracted from the road planning area based on plot characteristics, wherein the plot characteristics include at least one of the following: forest land, wasteland, and land converted from farmland to forest; For each first plot, select multiple plot sample squares; For each first plot, plant diversity statistics are performed based on multiple plot quadrats of the first plot, and the obtained plant diversity data are used to construct a plot plant diversity vector, where the plant diversity vector represents the characteristics of the plot plant species and the overall proportion of plants. For each plot's plant diversity vector, vectors with a distance less than a distance threshold are selected from multiple plant diversity classes and used as the plot's reference vector. Each plant diversity class corresponds to an ecological characteristic. For each first plot, the plant diversity class with the most reference vectors is taken as the plot's class, and the plot is constructed as an ecological plot based on the plant diversity of the plot's class.

[0055] In some implementations, the plant diversity class is obtained based on clustering multiple ecological sample vectors, including: The cluster density and multiple ecological sample vectors are obtained. The ecological sample vectors are constructed based on the plant diversity statistics of the plots, and each ecological sample vector corresponds to a plot ecology. Cluster the multiple ecological sample vectors according to the clustering density to obtain multiple natural classes; For each natural class, the ecology of the natural class is determined based on the ecology of the plot corresponding to the vector, and the ratio of the number of vectors of the ecology of the corresponding natural class to the number of vectors in the natural class is used as the consistency reference value of the natural class. If multiple consistency reference values ​​are all higher than the reference threshold, then multiple natural classes will be used as the plant diversity classes. Otherwise, increase the clustering density and proceed to the step of clustering the multiple ecological sample vectors according to the clustering density to obtain multiple natural classes.

[0056] For example, in step 103, for each of the first ecologically sensitive sections, a field-of-view analysis is conducted using the spatial analysis function of a Geographic Information System (GIS). By simulating the field of view along the road and combining factors such as surrounding ecological protection boundaries and land use types, the scope of the road landscape planning is scientifically defined. This ensures that the planning scope covers the ecologically sensitive areas around the road while avoiding over-planning that could disturb the natural ecosystem. After determining the scope of the road landscape planning, a plant diversity system analysis is performed on the area within this scope. Through field surveys, sample collection, and data statistics, the plant composition characteristics of different areas are identified, thereby dividing the area into multiple ecological plots. Each ecological plot has unique plant diversity characteristics and ecological functions.

[0057] like Figure 2 As shown, in some implementation methods, the specific implementation process for obtaining multiple ecological plots by conducting plant diversity analysis based on the road planning area is as follows: First, based on the core ecological characteristics of the plots, multiple primary plots were extracted from the road landscape planning area. These plots mainly included types with clear ecological functions, such as woodland, wasteland, and land converted from farmland to forest. Plots with high ecological sensitivity and good plant growth conditions were prioritized for extraction, while non-ecological plots such as building land and paved roads were excluded. Second, for each primary plot, multiple plot quadrats were selected according to scientific sampling principles. The size, number, and distribution of the quadrats were determined based on the plot area, topographic complexity, and uniformity of plant distribution to ensure that the quadrats could comprehensively and objectively reflect the plant diversity characteristics of the plot.

[0058] Then, plant diversity statistics were performed on multiple plots of each first plot. The statistics included core indicators such as plant species, number of each plant species, coverage, and dominance. After standardizing the obtained plant diversity data, a plot plant diversity vector 201 was constructed. This vector can accurately represent the plant species composition, the overall proportion of each plant species, and the distribution characteristics of the corresponding plot, providing data support for subsequent plot ecological classification.

[0059] Next, multiple plant diversity classes 202 are preset, each corresponding to a specific ecological characteristic (such as deciduous forest ecology, shrub ecology, herbaceous ecology, etc.). For each plot's plant diversity vector 201, the distance (such as Euclidean distance, Manhattan distance, etc.) between it and the standard vector in each plant diversity class 202 is calculated. The standard vector with a distance less than a preset distance threshold is selected as the reference vector for that plot. The more reference vectors there are, the higher the fit between the plot and the corresponding plant diversity class 202.

[0060] Finally, for each first plot, the number of reference vectors for each plant diversity class 202 is counted, and the plant diversity class 202 with the most reference vectors is determined as the class to which the plot belongs. Based on the ecological characteristics 203 of the class to which it belongs: plant diversity characteristics and ecological requirements, the first plot is constructed as an ecological plot with clear ecological characteristics 203, ensuring that the ecological characteristics of each ecological plot are clear and traceable.

[0061] In some implementations, plant diversity classes are obtained by clustering multiple ecological sample vectors. The specific implementation process is as follows: First, the cluster density is determined (to control the fineness of the clustering results; the higher the cluster density, the finer the clustering results and the more categories). Multiple ecological sample vectors are collected, which are constructed based on plant diversity statistics of different typical plots. Each ecological sample vector corresponds to a specific plot ecological type, covering various common roadside ecological scenarios. Second, according to the preset cluster density, a suitable clustering algorithm (such as K-means clustering, hierarchical clustering, etc.) is used to cluster the multiple ecological sample vectors to obtain multiple natural classes. The ecological sample vectors within each natural class have highly similar plant diversity characteristics.

[0062] Then, for each natural class, the core ecological characteristics of the natural class are identified by combining the ecological types of all ecological sample vectors in the class. At the same time, the ratio of the number of vectors corresponding to the core ecological characteristics in the natural class to the total number of vectors in the natural class is calculated. This ratio is used as the consistency reference value of the natural class. The consistency reference value is used to evaluate the uniformity of the ecological characteristics of the natural class. The higher the ratio, the more concentrated and uniform the ecological characteristics of the natural class are.

[0063] If the consistency reference value of all natural classes is higher than the preset reference threshold, it means that the current clustering result can meet the requirements for classifying plant diversity classes, and multiple natural classes are directly used as the plant diversity classes; if the consistency reference value of some natural classes is lower than the reference threshold, it means that the current clustering density is insufficient, resulting in the ecological characteristics of some natural classes not being uniform enough, and the clustering density needs to be appropriately increased, and the process jumps to the step of "clustering the multiple ecological sample vectors according to the clustering density to obtain multiple natural classes", and the clustering analysis is carried out again until the consistency reference value of all natural classes reaches the reference threshold.

[0064] For example, suppose 50 ecological sample vectors are collected, covering three core ecological types: woodland, shrubland, and herbaceous land. The initial clustering density is set to 0.3, and after clustering, three natural classes are obtained. The consistency reference values ​​for each natural class are calculated to be 0.85, 0.78, and 0.82, respectively. If the preset reference threshold is 0.8, the consistency reference value of the second natural class does not meet the requirements, and the clustering density needs to be adjusted to 0.4. After re-clustering, four natural classes are obtained, and the consistency reference values ​​are calculated again to be higher than 0.8. At this time, these four natural classes are regarded as plant diversity classes.

[0065] In step 104, landscape planning is carried out for each ecological plot based on ecological base data and sensitive characteristics classification.

[0066] In some implementations, the ecological base data includes existing plant varieties, and the landscape planning for each ecological plot, based on the ecological base data and sensitive characteristics classification, includes: For each ecological plot, perform the following steps: Based on the ecological base data, landscape plant varieties are adapted to obtain multiple target landscape plants; The scale of each target landscape plant is determined based on its sensitivity characteristics. Landscape planning is carried out based on the multiple target landscape plants and the scale of each target landscape plant.

[0067] For example, step 104 involves conducting targeted landscape planning for each ecologically defined plot, combining the plot's ecological baseline data with the sensitivity characteristics classification of its corresponding first ecologically sensitive section. The core principle is to achieve a synergistic unity between landscape and ecological functions while protecting the integrity and stability of the ecosystem. This means satisfying both the aesthetics and practicality of the road landscape, while maximizing the protection of the surrounding ecological environment and minimizing the impact of road construction and operation on ecologically sensitive areas.

[0068] In some implementations, ecological base data mainly includes core information such as the species, growth status, and distribution range of existing plants within the site. Existing plants form the foundation of landscape planning, prioritizing the preservation of native vegetation and minimizing human interference with the natural ecosystem. Based on this, the specific implementation process for landscape planning for each ecological site, categorized according to ecological base data and sensitive characteristics, is as follows: For each ecological plot, the following steps are performed: First, based on the ecological base data of the plot, combined with the local climate conditions, soil characteristics, hydrological environment and sensitive characteristic classification requirements, the selection of suitable landscape plant varieties is carried out. Several target landscape plants with strong adaptability, high ecological value and good compatibility with native vegetation are selected. Native tree species and native herbaceous plants are given priority to avoid the introduction of alien invasive species and ensure that the target landscape plants can grow stably in the plot for a long time. Then, based on the sensitivity characteristics of the first ecologically sensitive section to which the ecological plot belongs, the planting scale (including planting quantity, planting density, planting range, etc.) of each target landscape plant is determined. For highly sensitive sections, the planting density of landscape plants needs to be controlled, native vegetation should be preserved first, and only moderate replanting should be carried out in degraded areas. For medium and low sensitive sections, the planting scale can be reasonably adjusted under the premise of meeting the ecological protection requirements, taking into account both landscape effect and ecological function. Finally, based on the selected target landscape plants and the planting scale of each target landscape plant, and taking into account factors such as the topography and spatial layout of the site, a detailed landscape planning scheme was formulated, which clarified the planting location, matching method, and maintenance measures of the plants, so as to ensure that the landscape planning not only meets the requirements of ecological protection, but also improves the landscape quality around the road, and achieves the coordinated development of ecology and landscape.

[0069] For example, suppose a certain ecological plot belongs to a highly sensitive area. The ecological base data shows that the native vegetation of the plot is mainly deciduous forest, including species such as birch and aspen. The sensitivity characteristic is classified as "hydrologically sensitive". In the landscape planning, the existing birch and aspen vegetation should be preserved first. Suitable native herbaceous plants with strong moisture resistance and soil stabilization ability should be selected as replanting varieties. The replanting density should be controlled at 20 plants / m². The planting range should be concentrated in the hydrologically sensitive area at the edge of the plot to avoid excessive planting and interference with the groundwater environment. At the same time, a small number of ornamental shrubs should be added to achieve a balance between ecological protection and landscape aesthetics.

[0070] The implementation method of the road landscape planning method of the present invention first obtains multiple first node vectors, wherein each first node vector corresponds to a road node, and the first node vectors are obtained based on environmental factors affecting the ecology around the road; then, with the goal of minimizing intra-class differences and maximizing inter-class differences, the multiple first node vectors are classified, and the road is divided into multiple first ecologically sensitive segments according to the classification results, wherein each first ecologically sensitive segment corresponds to a sensitive characteristic classification; next, for each first ecologically sensitive segment, a view analysis is performed through a geographic information system to obtain the road landscape planning scope, and plant diversity analysis is performed based on the road planning scope to obtain multiple ecological plots; finally, for each ecological plot, landscape planning is carried out based on ecological base data and sensitive characteristic classification.

[0071] This invention constructs node vectors by using multiple environmental factors, combines intra- and inter-class differences to optimize objectives and iterative optimization algorithms, accurately delineates ecologically sensitive segments, and balances classification accuracy and efficiency, providing a scientific basis for subsequent planning.

[0072] This invention defines the planning scope based on GIS field analysis, combines plant diversity clustering and plot adaptation, prioritizes the preservation of native vegetation, avoids the invasion of alien species, and maximizes the protection of the integrity of the ecosystem around the road.

[0073] This invention combines ecological base data with sensitive characteristic classification to formulate differentiated landscape planning schemes that not only meet ecological protection requirements but also take into account landscape functions. Furthermore, the accompanying formulas and examples enhance the feasibility of the schemes.

[0074] This invention adapts to different ecological scenarios around roads through cluster density adjustment and disturbance compensation, avoiding local optima in the classification and planning process, and improving the stability and versatility of the solution.

[0075] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0076] The following are embodiments of the apparatus of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0077] Figure 3 This is a functional block diagram of the road landscape planning device provided in an embodiment of the present invention, with reference to... Figure 3 The road landscape planning device includes: a road environment acquisition module 301, an ecological sensitivity analysis module 302, an ecological analysis module 303, and a landscape planning module 304, wherein: The road environment acquisition module 301 is used to acquire multiple first node vectors, wherein each first node vector corresponds to a road node, and the first node vectors are acquired based on environmental factors that affect the ecology around the road. The ecological sensitivity analysis module 302 is used to classify the multiple first node vectors with the goal of minimizing intra-class differences and maximizing inter-class differences, and to divide the road into multiple first ecological sensitivity segments according to the classification results, wherein each first ecological sensitivity segment corresponds to a sensitivity characteristic classification. The ecological analysis module 303 is used to perform a field analysis through a geographic information system for each first ecologically sensitive section to obtain the road landscape planning range, and to perform plant diversity analysis based on the road planning range to obtain multiple ecological plots. Landscape planning module 304 is used to conduct landscape planning for each ecological plot based on ecological base data and sensitive characteristics.

[0078] Figure 4 This is a functional block diagram of the electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, the electronic device 4 in this embodiment includes a processor 400 and a memory 401, wherein the memory 401 stores a computer program 402 that can run on the processor 400. When the processor 400 executes the computer program 402, it implements the steps of the various road landscape planning methods and embodiments described above, for example... Figure 1 Steps 101 to 104 are shown.

[0079] For example, the computer program 402 may be divided into one or more modules / units, which are stored in the memory 401 and executed by the processor 400 to complete the present invention.

[0080] The electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The electronic device 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will understand that... Figure 4This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 4 may also include input / output devices, network access devices, buses, etc.

[0081] The processor 400 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0082] The memory 401 can be an internal storage unit of the electronic device 4, such as a hard disk or memory. The memory 401 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 401 can include both internal and external storage units of the electronic device 4. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 can also be used to temporarily store data that has been output or will be output.

[0083] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here.

[0084] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0085] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0086] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0087] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0088] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0089] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods and apparatus embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0090] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A road landscape planning method, characterized in that, include: Multiple first node vectors are obtained, where each first node vector corresponds to a road node. The first node vectors are obtained based on environmental factors that affect the ecology around the road. With the goal of minimizing intra-class differences and maximizing inter-class differences, the multiple first node vectors are classified, and the road is divided into multiple first ecologically sensitive segments based on the classification results, including: Get the number of items in the first category; The squared difference of the plurality of first node vectors is calculated as the global squared difference, wherein the first node vectors are constructed based on the elevation, slope, aspect, sunshine and hydrological data of the road nodes; Based on the first classification number, the multiple first node vectors are initially classified according to the corresponding road segments to obtain multiple initial classes, wherein each initial class corresponds to a road segment; For each initial class, calculate the within-class squared difference; The variance goodness of fit is determined based on multiple intra-class squared differences and the global squared difference; If the variance fit goodness does not reach the goodness threshold, then the multiple initial classes are iteratively optimized with the goal of maximizing the variance fit goodness. Otherwise, the multiple initial classes obtained through optimization are used as multiple process classes, and the variance goodness-of-fit value obtained through optimization is used as the first historical goodness-of-fit value; If the number of the first category does not reach the threshold, the number of the first category is incremented or decremented, and the process jumps to the step of performing initial classification on the multiple first node vectors according to the corresponding road segments based on the number of the first category to obtain multiple initial classes. Otherwise, a first curve is plotted based on the relationship between the number of categories and the goodness of fit of variance, with the first category number as the horizontal axis and the first historical goodness value as the vertical axis. The category number corresponding to the inflection point of the first curve is taken as the target number. Based on the multiple process classes corresponding to the target number, the road is divided into multiple first ecological sensitive sections, where each first ecological sensitive section corresponds to a sensitive characteristic category. For each first ecologically sensitive section, a view analysis is performed using a geographic information system to obtain the road landscape planning scope, and a plant diversity analysis is performed based on the road landscape planning scope to obtain multiple ecological plots; For each ecological plot, landscape planning is carried out based on ecological base data and sensitive characteristics.

2. The road landscape planning method according to claim 1, characterized in that, The step of iteratively optimizing the multiple initial classes with the objective of maximizing the goodness of fit of variance includes: Obtain multiple first-class node positions, where each initial class is obtained based on two adjacent first-class node positions; Based on the first formula, the variance goodness of fit, the historical variance goodness of fit, the positions of the multiple first classification nodes, and the positions of the multiple historical classification nodes, the positions of the multiple first nodes are adjusted, wherein the first formula is: In the formula, For the first The adjusted number Each category node position, For the first The adjusted number Each category node position, For the first The adjusted number Each category node position, For the first Goodness of fit of the adjusted variance. For the first Goodness of fit of the adjusted variance. For adjustment rate, This is a rounding function. This is the amount of disturbance compensation; Based on the adjusted positions of the multiple first nodes, the multiple first node vectors are classified to obtain multiple initial classes; Jump to the step of calculating the within-class squared difference for each initial class.

3. The road landscape planning method according to claim 1, characterized in that, The step of determining the variance goodness of fit based on multiple intra-class squared differences and the global squared difference includes: The goodness of fit of variance is determined based on the second formula, multiple intra-class squared differences, and the global squared difference, wherein the second formula is: In the formula, For variance, goodness of fit For global squared difference, The sum of the squared differences within the class. For the first The first class A vector, For the first The class center of each class, The total number of classes.

4. The road landscape planning method according to claim 1, characterized in that, The plant diversity analysis conducted based on the road landscape planning area yielded multiple ecological plots, including: Multiple first plots are extracted from the road landscape planning area based on plot characteristics, wherein the plot characteristics include at least one of the following: woodland, wasteland, and land converted from farmland to forest; For each first plot, select multiple plot sample squares; For each first plot, plant diversity statistics are performed based on multiple plot quadrats of the first plot, and the obtained plant diversity data are used to construct a plot plant diversity vector, where the plant diversity vector represents the characteristics of the plot plant species and the overall proportion of plants. For each plot's plant diversity vector, vectors with a distance less than a distance threshold are selected from multiple plant diversity classes and used as the plot's reference vector. Each plant diversity class corresponds to an ecological characteristic. For each first plot, the plant diversity class with the most reference vectors is taken as the plot's class, and the plot is constructed as an ecological plot based on the plant diversity of the plot's class.

5. The road landscape planning method according to claim 4, characterized in that, The plant diversity class is obtained based on clustering of multiple ecological sample vectors, including: The cluster density and multiple ecological sample vectors are obtained. The ecological sample vectors are constructed based on the plant diversity statistics of the plots, and each ecological sample vector corresponds to a plot ecology. Cluster the multiple ecological sample vectors according to the clustering density to obtain multiple natural classes; For each natural class, the ecology of the natural class is determined based on the ecology of the plot corresponding to the vector, and the ratio of the number of vectors of the ecology of the corresponding natural class to the number of vectors in the natural class is used as the consistency reference value of the natural class. If multiple consistency reference values ​​are all higher than the reference threshold, then multiple natural classes will be used as the plant diversity classes. Otherwise, increase the clustering density and proceed to the step of clustering the multiple ecological sample vectors according to the clustering density to obtain multiple natural classes.

6. The road landscape planning method according to any one of claims 1-5, characterized in that, The ecological base data includes existing plant varieties. For each ecological plot, landscape planning is conducted based on the ecological base data and sensitive characteristics, including: For each ecological plot, perform the following steps: Based on the ecological base data, landscape plant varieties are adapted to obtain multiple target landscape plants; The scale of each target landscape plant is determined based on its sensitivity characteristics. Landscape planning is carried out based on the multiple target landscape plants and the scale of each target landscape plant.

7. A road landscape planning device, characterized in that, For implementing the road landscape planning method as described in any one of claims 1-6, the road landscape planning device comprises: The road environment acquisition module is used to acquire multiple first node vectors, where each first node vector corresponds to a road node. The first node vectors are acquired based on environmental factors that affect the ecology around the road. The ecological sensitivity analysis module is used to classify the multiple first node vectors with the goal of minimizing intra-class differences and maximizing inter-class differences, and to divide the road into multiple first ecological sensitivity segments based on the classification results, wherein each first ecological sensitivity segment corresponds to a sensitivity characteristic classification. The ecological analysis module is used to perform a field analysis through a geographic information system for each first ecologically sensitive section to obtain the road landscape planning scope, and to perform plant diversity analysis based on the road landscape planning scope to obtain multiple ecological plots. as well as, The landscape planning module is used to conduct landscape planning for each ecological plot based on ecological baseline data and sensitive characteristics.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6 above.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6 above.

Images