A Multi-Dimensional Simulation Method and System for Territorial Spatial Planning Data

Abstract

This invention belongs to the field of land spatial planning technology. It discloses a multi-dimensional simulation method and system for land spatial planning data. The method includes the following steps: S1, acquiring multi-dimensional feature data of the main urban area and pre-setting regional categories, then dividing the area into several unit regions; S2, constructing several unit regions based on the multi-dimensional feature data to obtain several unit simulation models; S3, combining the several unit simulation models to obtain a three-dimensional simulation model. This invention enables seamless integration of two unit simulation models. By setting fitness functions and deficient regions, it helps decision-makers accurately locate the new urban area and select the optimal coordinate distribution combination of each regional category within the new urban area to achieve a balance between the new urban area and the main urban area.

Description

Technical Field

[0001] This invention relates to the field of land and space planning technology, and more specifically, to a multi-dimensional simulation method and system for land and space planning data. Background Technology

[0002] Territorial spatial planning is a comprehensive planning method that involves the overall planning and long-term development of a country or region's land use, natural resource management, ecological environment protection, and economic and social development. With the advent of the information age and the rapid development of technologies such as big data, 3D GIS, and spatial data mining and analysis, the field of territorial spatial planning has brought unprecedented opportunities and challenges. As an important foundational work for national development, the scientific nature and accuracy of territorial spatial planning are directly related to the rational allocation of national resources, the protection of the ecological environment, and the sustainable development of regional economies.

[0003] However, in the existing land use planning process, the workload of relevant planners is quite cumbersome, and it is also inconvenient to help decision-makers determine the location of new urban areas and the optimal distribution of various regional categories within the new urban areas.

[0004] In view of this, the present invention proposes a multi-dimensional simulation method and system for land spatial planning data to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution: a multi-dimensional simulation method and system for land spatial planning data, comprising the following steps:

[0006] S1. Obtain multi-dimensional feature data of the main urban area and preset the regional categories, and combine the two to divide into several unit regions;

[0007] S2. Construct several unit regions based on multi-dimensional feature data to obtain several unit simulation models;

[0008] S3. Combine several unit simulation models to obtain a three-dimensional simulation model;

[0009] S4. Based on the planning needs of the new urban area, several extension areas are pre-defined. The optimal extension area and its corresponding optimal coordinate distribution combination are determined from these extension areas by improving the genetic algorithm.

[0010] S5. Construct the optimal extension region to obtain the final three-dimensional simulation model.

[0011] Furthermore, the steps for obtaining the multi-dimensional feature data of the main urban area are as follows:

[0012] The administrative scope of the main urban area is determined by combining GIS and satellite remote sensing data to obtain geographic information within the administrative scope of the main urban area, including topography, ground slope and geological type.

[0013] Building information within the main urban area's administrative region is obtained by combining high-definition images captured by drones with GIS. The building information includes building specifications, building structure, and building texture.

[0014] Road information within the main urban area is obtained by combining GIS and satellite remote sensing data. The road information includes road routes and their corresponding road specifications, transportation hubs and transportation facilities.

[0015] Natural environmental information within the main urban area is obtained by combining GIS and satellite remote sensing data. This natural environmental information includes plant species, vegetation density, plant area, and water area.

[0016] Geographic information, building information, road information, and natural environment information are linked according to geographic coordinates to form multi-dimensional feature data of the main urban area.

[0017] Furthermore, the steps for obtaining the plurality of unit regions are as follows:

[0018] The main urban area is predefined into regional categories, namely residential area, commercial area, industrial area and green area;

[0019] The main urban area is divided into regions based on regional categories and multi-dimensional feature data;

[0020] For each region category, the center coordinates of the region category are determined by geographic information and road information, and the nearest road route is found to form a closed loop with the nearest road route, thus obtaining a unit region.

[0021] Following the steps above, the remaining cell regions are obtained sequentially, resulting in several cell regions.

[0022] Furthermore, the step of obtaining several unit simulation models is as follows:

[0023] A virtual space is constructed, and the multi-dimensional feature data of the main urban area is allocated to several unit areas through the division of geographic coordinates and unit areas, so as to obtain the multi-dimensional feature data corresponding to several unit areas.

[0024] The multi-dimensional feature data corresponding to several unit regions are standardized sequentially and mapped into the virtual space to obtain several unit simulation models.

[0025] The unit simulation model is constructed as follows:

[0026] A geographic 3D model is obtained by mapping the geographic information corresponding to the unit area in virtual space; a building 3D model is obtained by mapping the building information corresponding to the unit area in virtual space; a road 3D model is obtained by mapping the road information corresponding to the unit area in virtual space; a natural environment 3D model is obtained by mapping the natural environment information corresponding to the unit area in virtual space; and the geographic 3D model, building 3D model, road 3D model, and natural environment 3D model corresponding to the unit area are aligned and merged in virtual space from bottom to top according to geographic coordinates to obtain the unit simulation model.

[0027] Furthermore, the step of obtaining the three-dimensional simulation model is as follows:

[0028] Obtain and compare the edge lines of each unit simulation model, identify the common coordinate points, and then adjust the relative positions of adjacent unit simulation models based on the common coordinate points.

[0029] Prioritize splicing the unit simulation model with the most common coordinate points. When splicing, first splice the road routes with common coordinate points in the two unit simulation models, and then align the road surfaces at the height.

[0030] The remaining unit simulation models are then assembled in the same manner until all unit simulation models are combined to obtain the three-dimensional simulation model.

[0031] Furthermore, the step of determining the optimal extension region and its corresponding optimal coordinate distribution combination from several extension regions using an improved genetic algorithm is as follows:

[0032] Obtain the areas surrounding the main urban area that meet the planning requirements, resulting in m extended areas;

[0033] For each extended region, h coordinate distribution combinations are randomly generated, resulting in m×h coordinate distribution combinations. The m×h coordinate distribution combinations are used as the initial population, where each coordinate distribution combination represents the relative distribution position of the four region categories in the same extended region.

[0034] Each coordinate distribution is combined into an individual, and each individual is encoded by the coordinates of the region category in a preset order. The coordinates of each region category are used as the individual's genes.

[0035] Define a fitness function to calculate the fitness value of each individual in the initial population;

[0036] Based on the fitness value, select elite individuals from the initial population as parent individuals, and perform crossover and mutation operations on the parent individuals;

[0037] Repeat the selection, crossover, and mutation operations to generate a new population and calculate the fitness value of the new population until the preset stopping condition or the maximum number of iterations is reached.

[0038] The individual with the highest fitness value in the final population is selected as the optimal coordinate distribution combination in all extended regions, and the extended region where the optimal coordinate distribution combination is located is taken as the optimal extended region.

[0039] Furthermore, the processes of selection, crossover, and mutation operations are as follows:

[0040] At the start of the current population evolution, calculate the fitness value of each individual in the current population and sort them in descending order;

[0041] An elite selection strategy is adopted, with a preset elite ratio of k%, and individuals with fitness values ​​in the top k% of the current population are selected as elite individuals and directly retained into the next generation of the population.

[0042] In the crossover operation, only the genes of individuals in the current population that are in adjacent extended regions are crossed, and new individuals are generated by exchanging some genes.

[0043] In the mutation operation, the genes of individuals in the current population are mutated by exchanging coordinates, thereby generating new individuals.

[0044] Furthermore, the fitness function is:

[0045] ;

[0046] In the formula, For fitness value, This refers to the distance between the residential areas and the green areas of the new urban area. This refers to the distance between the residential area and the industrial area of ​​the new urban area. This refers to the distance between the residential area and the commercial area of ​​the new urban area. This refers to the distance between the deficient areas in the main urban area and the supplementary areas in the new urban area. The supplementary areas are unit areas within the new urban area that belong to the same area category as the deficient areas. The distance between the residential areas of the main urban area and the industrial areas of the new urban area. It is a small positive number;

[0047] The steps for obtaining the missing region are as follows:

[0048] The Simpson Index for the main urban area is calculated based on the actual number of unit areas corresponding to each area category in the main urban area.

[0049] A reference Simpson index is preset for the main urban area. Based on the reference Simpson index, the reference number of unit areas corresponding to each area category in the main urban area is obtained. The reference number of unit areas corresponding to each area category in the main urban area is compared with the actual number of unit areas corresponding to each area category in the main urban area. The area category corresponding to the unit area with the largest difference in the comparison number is taken as the area category of the area with the deficiency.

[0050] Obtain the coordinates of the center point of the main urban area and use it as the first coordinate point;

[0051] Using the first coordinate point as the center, and taking the center point of the unit region of the same category as the missing region as the second coordinate point, draw a circle that includes all the second coordinate points;

[0052] Draw a line between the first and second coordinate points, and calculate the angle between adjacent lines. The area between the two adjacent lines with the largest angle is considered the missing area.

[0053] Obtain the second coordinate points on the two adjacent lines that constitute the missing area, and calculate the midpoint coordinates between the two second coordinate points. Use these midpoint coordinates as the position coordinates of the missing area.

[0054] Furthermore, the step of obtaining the final three-dimensional simulation model is as follows:

[0055] Based on the planning requirements of the new urban area, the area requirements for each area category are calculated, and the area requirements are matched with the optimal coordinate distribution combination to obtain the area corresponding to each area category.

[0056] Based on the area corresponding to each region category, select the unit simulation models with the same region category and the closest area for splicing and combination.

[0057] The road routes of the assembled unit simulation models are adjusted to connect with the road routes of the main urban area, thus obtaining the final three-dimensional simulation model.

[0058] A multi-dimensional simulation system for land spatial planning data includes:

[0059] The segmentation module is used to acquire multi-dimensional feature data of the main urban area and preset the area categories, and combine the two to divide the area into several unit areas;

[0060] The construction module is used to construct several unit regions based on multi-dimensional feature data, thereby obtaining several unit simulation models;

[0061] The combination module is used to combine several unit simulation models to obtain a three-dimensional simulation model;

[0062] The extension module is used to pre-determine several extension areas based on the planning needs of the new urban area, and to determine the optimal extension area and its corresponding optimal coordinate distribution combination from several extension areas through an improved genetic algorithm.

[0063] The final construction module is used to construct the optimal extension region, thereby obtaining the final three-dimensional simulation model.

[0064] The technical effects and advantages of the multi-dimensional simulation method and system for land spatial planning data of this invention are as follows:

[0065] 1. By dividing the unit area and constructing the unit simulation model, the functionality and integrity of each unit simulation model can be ensured. By splicing and aligning the unit simulation models based on common coordinate points and the centerline of the road route during the combination process, it is helpful to achieve seamless connection between two unit simulation models, which can make the splicing and combination effect of the three-dimensional simulation model realistic and continuous.

[0066] 2. Under the combined effect of the fitness function and the lack of areas, it can not only ensure that the new urban area is accurately connected to the lack of areas in the main urban area, and achieve effective filling and balance of various regional categories, but also enhance the unity and coordination between the new urban area and the main urban area through simulation. It is conducive to helping decision-makers accurately locate the new urban area and select the optimal coordinate distribution combination of various regional categories in the new urban area to achieve a balance between the new urban area and the main urban area, thus providing decision-makers with a scientific and reasonable planning scheme. Attached Figure Description

[0067] Figure 1 This is a flowchart illustrating a multi-dimensional simulation method for land spatial planning data according to the present invention.

[0068] Figure 2 This is a schematic diagram of the structure of a multi-dimensional simulation system for land spatial planning data according to the present invention;

[0069] Figure 3 This is a schematic diagram showing the combination of the location coordinates of the main urban area and the missing area in this invention. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example 1

[0071] Please see Figure 1 and Figure 2As shown in this embodiment, a multi-dimensional simulation method for land spatial planning data includes the following steps:

[0072] S1. Obtain multi-dimensional feature data of the main urban area and preset the regional categories, and combine the two to divide into several unit regions;

[0073] S2. Construct several unit regions based on multi-dimensional feature data to obtain several unit simulation models;

[0074] S3. Combine several unit simulation models to obtain a three-dimensional simulation model.

[0075] The steps for obtaining multi-dimensional feature data of the main urban area are as follows:

[0076] The administrative scope of the main urban area is determined by combining GIS (Geographic Information System) and satellite remote sensing data to obtain geographic information within the administrative scope of the main urban area, including topography, ground slope and geological type.

[0077] Building information within the main urban area's administrative region is obtained by combining high-definition images captured by drones with GIS. The building information includes building specifications, building structure, and building texture.

[0078] Road information within the main urban area is obtained by combining GIS and satellite remote sensing data. The road information includes road routes and their corresponding road specifications, transportation hubs and transportation facilities.

[0079] Natural environmental information within the main urban area is obtained by combining GIS and satellite remote sensing data. This natural environmental information includes plant species, vegetation density, plant area, and water area.

[0080] Geographic information, building information, road information, and natural environment information are linked according to geographic coordinates to form multi-dimensional feature data of the main urban area.

[0081] Among them, GIS provides a spatial analysis framework, while satellite remote sensing data provides detailed information on land cover and physical characteristics. By processing this remote sensing data through GIS software, a digital elevation model can be constructed, and geographic information, road information, and natural environment information can be obtained through the digital elevation model. By importing high-definition image data taken by drones into the GIS system and using the geographic registration function of GIS to match the image data with known geographic coordinate systems, building information can be obtained.

[0082] Specifically, by combining GIS and satellite remote sensing data with high-definition images taken by drones, it is possible to comprehensively and accurately acquire multi-dimensional feature data of the main urban area, including geographic information, building information, road information, and natural environment information. This not only improves the efficiency and accuracy of acquiring multi-dimensional feature data, but also ensures the quality of the basic data for subsequent simulation model construction.

[0083] The steps for obtaining several unit regions are as follows:

[0084] The main urban area is predefined into regional categories, namely residential areas (residential areas, residential communities, etc.), commercial areas (commercial streets, shopping centers, markets, etc.), industrial areas (factories, etc.) and green areas (parks, lawns, rivers, etc.).

[0085] The main urban area is divided into regions based on regional categories and multi-dimensional feature data;

[0086] For each region category, the center coordinates of the region category are determined by geographic information and road information, and the nearest road route is found to form a closed loop with the nearest road route, thus obtaining a unit region.

[0087] Following the steps above, the remaining unit regions are obtained sequentially, ensuring that each unit region is larger than the preset minimum area and that the regions do not overlap, thus obtaining several unit regions.

[0088] When dividing areas, the division is based on the centerline of the nearest road route.

[0089] Specifically, the main urban area is divided according to the preset area categories, and closed-loop unit areas are formed using the surrounding road routes. This ensures the functionality and integrity of each unit area. At the same time, it ensures that each unit area is larger than the preset minimum area and does not overlap, effectively avoiding the problem of increased complexity and computational cost of unit simulation models caused by overly detailed or overlapping divisions.

[0090] The steps to obtain several unit simulation models are as follows:

[0091] A virtual space is constructed, and the multi-dimensional feature data of the main urban area is allocated to several unit areas through the division of geographic coordinates and unit areas, so as to obtain the multi-dimensional feature data corresponding to several unit areas.

[0092] The multi-dimensional feature data corresponding to several unit regions are standardized sequentially and mapped into the virtual space to obtain several unit simulation models.

[0093] The unit simulation model is constructed as follows:

[0094] A geographic 3D model is obtained by mapping the geographic information corresponding to the unit area in virtual space; a building 3D model is obtained by mapping the building information corresponding to the unit area in virtual space; a road 3D model is obtained by mapping the road information corresponding to the unit area in virtual space; a natural environment 3D model is obtained by mapping the natural environment information corresponding to the unit area in virtual space; and the geographic 3D model, building 3D model, road 3D model, and natural environment 3D model corresponding to the unit area are aligned and merged in virtual space from bottom to top according to geographic coordinates to obtain the unit simulation model.

[0095] This includes defining quantifiable data with multi-dimensional features, such as ground slope, quantified codes for geological categories, building specifications (e.g., height, area), road specifications (e.g., width, number of lanes), quantifiable values ​​for vegetation density, vegetation area, and water area. These quantifiable data are standardized using Min-Max or Z-score standardization methods. Before constructing the virtual space, it is necessary to ensure that all geospatial data is based on geographic coordinates. This includes spatial location data from geographic information, building information, road information, and natural environment information.

[0096] Specifically, by standardizing multi-dimensional feature data, the efficiency and accuracy of subsequent unit simulation model construction can be improved. In the virtual space, three-dimensional models of geography, buildings, roads and natural environment are mapped respectively. Through precise vertical alignment and merging, a realistic and accurate unit simulation model can be obtained, which helps to shorten the construction time of the unit simulation model and improve the usability of the unit simulation model.

[0097] The steps to obtain a 3D simulation model are as follows:

[0098] Obtain and compare the edge lines of each unit simulation model, identify the common coordinate points, and then adjust the relative positions of adjacent unit simulation models based on the common coordinate points.

[0099] Prioritize splicing the unit simulation model with the most common coordinate points. When splicing, first splice the road routes with common coordinate points in the two unit simulation models, and then align the road surfaces at the height.

[0100] The remaining unit simulation models are then assembled in the same manner until all unit simulation models are combined to obtain the three-dimensional simulation model.

[0101] Among them, the edge line refers to a closed loop line formed by setting several coordinate points at the boundary of the unit simulation model and connecting several coordinate points in sequence. The selection principle of the coordinate points is to ensure that the overall shape or local curvature of the edge line changes after deleting any coordinate point. The common coordinate points are the coordinate points of two unit simulation models that have the same coordinates, and the coordinate points are the specific locations of the geographic coordinates.

[0102] Specifically, combining unit simulation models based on shared coordinate points ensures the accuracy and automation of the combination process. Furthermore, when combining road routes, aligning the road surface after combining the road first makes the combination of unit simulation models more precise, further improving the continuity of the combination. Moreover, using the centerline of the road route for combination simplifies the combination process and effectively avoids problems such as discontinuity and misalignment of joints that may occur when combining unit simulation models, ensuring the integrity and aesthetics of the 3D simulation model.

[0103] In this embodiment, by dividing the unit area and constructing the unit simulation model, the functionality and integrity of each unit simulation model can be ensured. By aligning the unit simulation models based on common coordinate points and the centerline of the road route during the combination process, it is helpful to achieve seamless connection between the two unit simulation models, making the effect of splicing and combining the three-dimensional simulation models realistic and continuous. Example 2

[0104] Please see Figure 1 , Figure 2 and Figure 3 As shown in this embodiment, a multi-dimensional simulation method for land spatial planning data includes the following steps:

[0105] S4. Based on the planning needs of the new urban area, several extension areas are pre-defined. The optimal extension area and its corresponding optimal coordinate distribution combination are determined from these extension areas by improving the genetic algorithm.

[0106] S5. Construct the optimal extension region to obtain the final three-dimensional simulation model.

[0107] The steps for determining the optimal extension region and its corresponding optimal coordinate distribution combination from several extension regions using an improved genetic algorithm are as follows:

[0108] Obtain areas around the main urban area that meet planning requirements. The planning requirements are minimum land area, being within the same administrative region as the main urban area, and having no unsuitable areas such as mountains and rocks. This will result in m extended areas, each of which includes four area categories: residential area, commercial area, industrial area, and green area.

[0109] For each extended region, h coordinate distribution combinations are randomly generated, resulting in m×h coordinate distribution combinations. The m×h coordinate distribution combinations are used as the initial population, where each coordinate distribution combination represents the relative distribution position of the four region categories in the same extended region.

[0110] Each coordinate distribution is combined into an individual, and each individual is encoded by the coordinates of the region category in a preset order, from left to right and then from top to bottom. The coordinates of each region category are used as the individual's genes.

[0111] Define a fitness function to calculate the fitness value of each individual in the initial population;

[0112] Based on the fitness value, select elite individuals from the initial population as parent individuals, and perform crossover and mutation operations on the parent individuals;

[0113] Repeatedly perform selection, crossover, and mutation operations to generate a new population and calculate the fitness value of the new population until a preset stopping condition or a maximum number of iterations is reached. The maximum number of iterations is then set to 500 or 1000. The preset stopping condition is reaching a preset fitness threshold or the distribution of individual fitness values ​​in the population tends to stabilize.

[0114] The individual with the highest fitness value is selected from the final population as the optimal coordinate distribution combination among all extended regions. The extended region where the optimal coordinate distribution combination is located is taken as the optimal extended region, and the location of the optimal extended region is taken as the location of the new urban area.

[0115] Specifically, by pre-setting several extended areas and using an improved genetic algorithm to search for the optimal coordinate distribution combination, the specific distribution of residential, commercial, industrial, and green areas within each extended area can be accurately determined. The relative positional relationship between the areas can be considered, and by setting the fitness function, the functional complementarity and spatial coordination between the new urban area and the main urban area can be ensured, thereby realizing the scientificity and rationality of the overall land space planning between the new urban area and the main urban area.

[0116] The processes of selection, crossover, and mutation are as follows:

[0117] At the start of the current population evolution, calculate the fitness value of each individual in the current population and sort them in descending order;

[0118] An elite selection strategy is adopted, with a preset elite ratio of k%, and individuals with fitness values ​​in the top k% of the current population are selected as elite individuals and directly retained into the next generation of the population.

[0119] In the crossover operation, only the genes of individuals in the current population that are in adjacent extension regions are crossed. New individuals are generated by exchanging some genes, and the number of some genes is greater than 0 and less than or equal to 3.

[0120] In the mutation operation, the genes of individuals in the current population are mutated by exchanging coordinates, thereby generating new individuals.

[0121] Specifically, by improving the application of genetic algorithms, the time to find the optimal solution (i.e., the optimal combination of coordinate distributions) is greatly shortened, and the efficiency of land spatial planning is improved. Through elite selection, crossover, and mutation operations in genetic algorithms, the convergence to the optimal solution is accelerated while ensuring population diversity. This helps decision-makers quickly obtain high-quality planning schemes and provides strong support for the development and construction of new urban areas.

[0122] The fitness function is:

[0123] ;

[0124] In the formula, For fitness value, This refers to the distance between the residential areas and the green areas of the new urban area. This refers to the distance between the residential area and the industrial area of ​​the new urban area. This refers to the distance between the residential area and the commercial area of ​​the new urban area. This refers to the distance between the deficient areas in the main urban area and the supplementary areas in the new urban area. The supplementary areas are unit areas within the new urban area that belong to the same area category as the deficient areas. The distance between the residential areas of the main urban area and the industrial areas of the new urban area. It is a small positive number;

[0125] Among them, with For example, the distance is calculated as follows:

[0126] Obtain the area corresponding to the planning requirements of the new urban area (optimal extension area), divide it according to the optimal distribution combination and the corresponding planning area of ​​each area in the new urban area, and calculate the distance between the center point of the residential area and the center point of the green area in the new urban area, thus obtaining... ;

[0127] by For example, the distance is calculated as follows:

[0128] Calculate the distance between the center point of the residential area in the main urban area and the center point of the industrial area in the new urban area, and you will get... ;

[0129] Specifically, the larger the sum of the above distances, the lower the fitness value; conversely, the smaller the sum of the above distances, the higher the fitness value. This allows us to select the coordinate distribution combination corresponding to the minimum sum of distances as the optimal coordinate distribution combination. This enables the rational distribution of different regional categories, which is conducive to improving the efficiency of land resource utilization, enhancing the interaction and communication between residents and industrial, commercial, and green areas within the residential area, and improving the overall vitality of the main urban area and the new urban area.

[0130] The steps to obtain the missing region are as follows:

[0131] The Simpson Index for the main urban area is calculated based on the actual number of unit areas corresponding to each area category in the main urban area.

[0132] The formula for calculating the Simpson index is as follows: In the formula, The Simpson Index corresponding to the main urban area. Indicates the first The actual number of class unit regions, Index for region categories, This represents the total number of all unit areas within the main urban area.

[0133] A reference Simpson index is preset for the main urban area. Based on the reference Simpson index, the reference number of unit areas corresponding to each area category in the main urban area is obtained (an initial weight is assigned to each area category, and the reference number of each area category is calculated by substituting the initial weight of each area category, the reference Simpson index, and the total number of all unit areas into the calculation formula of the Simpson index). The reference number of unit areas corresponding to each area category in the main urban area is compared with the actual number of unit areas corresponding to each area category in the main urban area. The area category corresponding to the unit area with the largest difference in the compared number is taken as the area category of the area with the deficiency.

[0134] Obtain the coordinates of the center point of the main urban area and use it as the first coordinate point;

[0135] Using the first coordinate point as the center, and taking the center point of the unit region of the same category as the missing region as the second coordinate point, draw a circle that includes all the second coordinate points;

[0136] Draw a line between the first and second coordinate points, and calculate the angle between adjacent lines. The area between the two adjacent lines with the largest angle is considered the missing area.

[0137] Obtain the second coordinate points on the two adjacent lines that constitute the missing area, and calculate the midpoint coordinates between the two second coordinate points. Use these midpoint coordinates as the position coordinates of the missing area.

[0138] Specifically, by calculating the Simpson Index of the main urban area and comparing it with the preset reference Simpson Index, the regional categories of deficient areas can be accurately identified. Thus, in the planning process of the new urban area, the relative positions of supplementary areas can be set in a targeted manner, achieving seamless integration of functions between the main urban area and the new urban area. By obtaining the deficient areas and determining their location coordinates, the integrity and coordination of urban functions can be effectively improved.

[0139] The steps to obtain the final 3D simulation model are as follows:

[0140] Based on the planning requirements of the new urban area, the area requirements for each area category are calculated, and the area requirements are matched with the optimal coordinate distribution combination to obtain the area corresponding to each area category.

[0141] Based on the area corresponding to each region category, select the unit simulation models with the same region category and the closest area for splicing and combination. The closest unit simulation model is obtained by the minimum difference between the area corresponding to the region category and the area of ​​the unit simulation model.

[0142] The road routes of each unit simulation model are adjusted to connect with the road routes of the main urban area to obtain the final three-dimensional simulation model. Among them, the widest road route is selected first for alignment and splicing.

[0143] Specifically, the final 3D simulation model can intuitively demonstrate the planning effect of the new urban area, ensuring the scientific nature of the functional connections and spatial layout between various unit areas. At the same time, through steps such as splicing and road alignment, the simulation model is seamlessly connected with the road system of the main urban area, providing strong support for subsequent planning implementation and urban management.

[0144] In this embodiment, under the combined effect of the fitness function and the lacking area, it is not only possible to ensure that the new urban area is accurately connected to the lacking area of ​​the main urban area, and to achieve effective filling and balance of each area category, but also to enhance the unity and coordination between the new urban area and the main urban area through simulation. This helps decision-makers to accurately locate the new urban area and select the optimal coordinate distribution combination of each area category in the new urban area to achieve a balance between the new urban area and the main urban area, thus providing decision-makers with a scientific and reasonable planning scheme. Example 3

[0145] Please see Figure 1 and Figure 2 As shown in this embodiment, a multi-dimensional simulation system for land spatial planning data includes:

[0146] The segmentation module is used to acquire multi-dimensional feature data of the main urban area and preset the area categories, and combine the two to divide the area into several unit areas;

[0147] The construction module is used to construct several unit regions based on multi-dimensional feature data, thereby obtaining several unit simulation models;

[0148] The combination module is used to combine several unit simulation models to obtain a three-dimensional simulation model;

[0149] The extension module is used to pre-determine several extension areas based on the planning needs of the new urban area, and to determine the optimal extension area and its corresponding optimal coordinate distribution combination from several extension areas through an improved genetic algorithm.

[0150] The final construction module is used to construct the optimal extension region, thereby obtaining the final three-dimensional simulation model.

[0151] In this embodiment, by dividing the unit area and constructing the unit simulation model, the functionality and integrity of each unit simulation model can be ensured, which helps to achieve seamless connection between two unit simulation models and makes the effect of splicing and combining the three-dimensional simulation models realistic and continuous. By setting the fitness function and the missing area, the effective filling and balance of each area category can be achieved, which helps decision-makers to accurately locate the new urban area and select the optimal coordinate distribution combination of each area category in the new urban area to achieve a balance between the new urban area and the main urban area, providing decision-makers with a scientific and reasonable planning scheme.

[0152] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention 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.

[0153] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, 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 coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0154] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

[0155] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-dimensional simulation method for land spatial planning data, characterized in that, Includes the following steps: S1. Obtain multi-dimensional feature data of the main urban area and preset the regional categories, and combine the two to divide into several unit regions; S2. Construct several unit regions based on multi-dimensional feature data to obtain several unit simulation models; S3. Combine several unit simulation models to obtain a three-dimensional simulation model; S4. Based on the planning needs of the new urban area, several extension areas are pre-defined. The optimal extension area and its corresponding optimal coordinate distribution combination are determined from these extension areas by improving the genetic algorithm. The steps for determining the optimal extension region and its corresponding optimal coordinate distribution combination from several extension regions using an improved genetic algorithm are as follows: Obtain the areas surrounding the main urban area that meet the planning requirements, resulting in m extended areas; For each extended region, h coordinate distribution combinations are randomly generated, resulting in m×h coordinate distribution combinations. The m×h coordinate distribution combinations are used as the initial population, where each coordinate distribution combination represents the relative distribution position of the four region categories in the same extended region. Each coordinate distribution is combined into an individual, and each individual is encoded by the coordinates of the region category in a preset order. The coordinates of each region category are used as the individual's genes. Define a fitness function and calculate the fitness value of each individual in the initial population; Based on the fitness value, select elite individuals from the initial population as parent individuals, and perform crossover and mutation operations on the parent individuals; Repeat the selection, crossover, and mutation operations to generate a new population and calculate the fitness value of the new population until the preset stopping condition or the maximum number of iterations is reached. From the final population, select the individual with the highest fitness value as the optimal coordinate distribution combination in all extended regions, and take the extended region where the optimal coordinate distribution combination is located as the optimal extended region. The fitness function is: ; In the formula, For fitness value, This refers to the distance between the residential areas and the green areas of the new urban area. This refers to the distance between the residential area and the industrial area of ​​the new urban area. This refers to the distance between the residential area and the commercial area of ​​the new urban area. This refers to the distance between the deficient areas in the main urban area and the supplementary areas in the new urban area. The supplementary areas are unit areas within the new urban area that belong to the same area category as the deficient areas. The distance between the residential areas of the main urban area and the industrial areas of the new urban area. It is a small positive number; The steps for obtaining the missing region are as follows: The Simpson Index for the main urban area is calculated based on the actual number of unit areas corresponding to each area category in the main urban area. A reference Simpson index is preset for the main urban area. Based on the reference Simpson index, the reference number of unit areas corresponding to each area category in the main urban area is obtained. The reference number of unit areas corresponding to each area category in the main urban area is compared with the actual number of unit areas corresponding to each area category in the main urban area. The area category corresponding to the unit area with the largest difference in the comparison number is taken as the area category of the area with the deficiency. Obtain the coordinates of the center point of the main urban area and use it as the first coordinate point; Using the first coordinate point as the center, and taking the center point of the unit region of the same category as the missing region as the second coordinate point, draw a circle that includes all the second coordinate points; Draw a line between the first and second coordinate points, and calculate the angle between adjacent lines. The area between the two adjacent lines with the largest angle is considered the missing area. Obtain the second coordinate points on the two adjacent lines that constitute the missing area, and calculate the midpoint coordinates between the two second coordinate points. Use these midpoint coordinates as the position coordinates of the missing area. S5. Construct the optimal extension region to obtain the final three-dimensional simulation model.

2. The multi-dimensional simulation method for land spatial planning data according to claim 1, characterized in that, The steps for obtaining the multi-dimensional feature data of the main urban area are as follows: The administrative scope of the main urban area is determined by combining GIS and satellite remote sensing data to obtain geographic information within the administrative scope of the main urban area, including topography, ground slope and geological type. Building information within the main urban area's administrative region is obtained by combining high-definition images captured by drones with GIS. The building information includes building specifications, building structure, and building texture. Road information within the main urban area is obtained by combining GIS and satellite remote sensing data. The road information includes road routes and their corresponding road specifications, transportation hubs and transportation facilities. Natural environmental information within the main urban area is obtained by combining GIS and satellite remote sensing data. This natural environmental information includes plant species, vegetation density, plant area, and water area. Geographic information, building information, road information, and natural environment information are linked according to geographic coordinates to form multi-dimensional feature data of the main urban area.

3. The multi-dimensional simulation method for land spatial planning data according to claim 2, characterized in that, The steps for obtaining the plurality of unit regions are as follows: The main urban area is predefined into regional categories, namely residential area, commercial area, industrial area and green area; The main urban area is divided into regions based on regional categories and multi-dimensional feature data; For each region category, the center coordinates of the region category are determined by geographic information and road information, and the nearest road route is found to form a closed loop with the nearest road route, thus obtaining a unit region. Following the steps above, the remaining cell regions are obtained sequentially, resulting in several cell regions.

4. The multi-dimensional simulation method for land spatial planning data according to claim 3, characterized in that, The steps to obtain several unit simulation models are as follows: A virtual space is constructed, and the multi-dimensional feature data of the main urban area is allocated to several unit areas through the division of geographic coordinates and unit areas, so as to obtain the multi-dimensional feature data corresponding to several unit areas. The multi-dimensional feature data corresponding to several unit regions are standardized sequentially and mapped into the virtual space to obtain several unit simulation models. The unit simulation model is constructed as follows: A geographic 3D model is obtained by mapping the geographic information corresponding to the unit area in virtual space; a building 3D model is obtained by mapping the building information corresponding to the unit area in virtual space; a road 3D model is obtained by mapping the road information corresponding to the unit area in virtual space; a natural environment 3D model is obtained by mapping the natural environment information corresponding to the unit area in virtual space; and the geographic 3D model, building 3D model, road 3D model, and natural environment 3D model corresponding to the unit area are aligned and merged in virtual space from bottom to top according to geographic coordinates to obtain the unit simulation model.

5. The multi-dimensional simulation method for land spatial planning data according to claim 4, characterized in that, The steps to obtain the three-dimensional simulation model are as follows: Obtain and compare the edge lines of each unit simulation model, identify the common coordinate points, and then adjust the relative positions of adjacent unit simulation models based on the common coordinate points. Prioritize splicing the unit simulation model with the most common coordinate points. When splicing, first splice the road routes with common coordinate points in the two unit simulation models, and then align the road surfaces at the height. The remaining unit simulation models are then assembled in the same manner until all unit simulation models are combined to obtain the three-dimensional simulation model.

6. The multi-dimensional simulation method for land spatial planning data according to claim 5, characterized in that, The selection, crossover, and mutation operations are performed as follows: At the start of the current population evolution, calculate the fitness value of each individual in the current population and sort them in descending order; An elite selection strategy is adopted, with a preset elite ratio of k%, and individuals with fitness values ​​in the top k% of the current population are selected as elite individuals and directly retained into the next generation of the population. In the crossover operation, only the genes of individuals in the current population that are in adjacent extended regions are crossed, and new individuals are generated by exchanging some genes. In the mutation operation, the genes of individuals in the current population are mutated by exchanging coordinates, thereby generating new individuals.

7. The multi-dimensional simulation method for land spatial planning data according to claim 6, characterized in that, The steps to obtain the final three-dimensional simulation model are as follows: Based on the planning requirements of the new urban area, the area requirements for each area category are calculated, and the area requirements are matched with the optimal coordinate distribution combination to obtain the area corresponding to each area category. Based on the area corresponding to each region category, select the unit simulation models with the same region category and the closest area for splicing and combination. The road routes of the assembled unit simulation models are adjusted to connect with the road routes of the main urban area, thus obtaining the final three-dimensional simulation model.

8. A multi-dimensional simulation system for land spatial planning data, used to implement the multi-dimensional simulation method for land spatial planning data as described in any one of claims 1 to 7, characterized in that, include: The segmentation module is used to acquire multi-dimensional feature data of the main urban area and preset the area categories, and combine the two to divide the area into several unit areas; The construction module is used to construct several unit regions based on multi-dimensional feature data, thereby obtaining several unit simulation models; The combination module is used to combine several unit simulation models to obtain a three-dimensional simulation model; The extension module is used to pre-determine several extension areas based on the planning needs of the new urban area, and to determine the optimal extension area and its corresponding optimal coordinate distribution combination from several extension areas through an improved genetic algorithm. The final construction module is used to construct the optimal extension region, thereby obtaining the final three-dimensional simulation model.

Images