Land space planning optimization method and system based on three-dimensional modeling

Abstract

The invention discloses a territorial space planning optimization method and system based on three-dimensional modeling, and relates to the technical field of three-dimensional modeling, and the method comprises the steps: obtaining multi-source territorial space data, constructing a three-dimensional space data set, carrying out the three-dimensional geometric modeling, and generating a territorial space three-dimensional model; carrying out multi-dimensional space analysis on the land space three-dimensional model, obtaining a space conflict feature set, carrying out planning constraint, and formulating a space optimization suggestion; executing the space optimization suggestion to perform three-dimensional dynamic modeling, generating a multi-time sequence planning simulation result to perform space planning evaluation, generating a land space planning score, performing planning compensation based on the backtracking space optimization suggestion, updating the space optimization suggestion, and obtaining a space planning optimization scheme. The technical problem that in the prior art, land space planning depends on two-dimensional data, the space conflict and the dynamic evolution process are difficult to comprehensively recognize, and the planning scheme is insufficient in scientificity is solved, and the technical effect of improving the space conflict recognition precision and the planning decision scientificity is achieved.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional modeling technology, and in particular to a land space planning optimization method and system based on three-dimensional modeling. Background Art

[0002] National land space planning typically utilizes analytical methods based on two-dimensional geographic information systems (GIS), relying primarily on topographic maps, land use maps, and other planar data for planning, design, and assessment. Due to the lack of comprehensive representation of terrain elevation, three-dimensional structure, and multi-level spatial relationships, it is difficult to fully reflect key spatial characteristics such as actual topography, building density, and ecological capacity. This primarily two-dimensional analytical approach has limitations in addressing spatial overlap, functional conflicts, and three-dimensional visualization and decision-making. In particular, it cannot effectively support multi-dimensional planning coordination and dynamic simulation analysis in complex scenarios such as urban renewal, ecological protection, and infrastructure layout. Summary of the Invention

[0003] This application provides a land space planning optimization method and system based on three-dimensional modeling, which is used to solve the technical problem that the existing land space planning relies on two-dimensional data, making it difficult to fully identify spatial conflicts and dynamic evolution processes, resulting in insufficient scientificity of planning schemes.

[0004] In view of the above problems, this application provides a land space planning optimization method and system based on three-dimensional modeling.

[0005] In a first aspect, the present application provides a land space planning optimization method based on three-dimensional modeling, the method comprising: Acquire multi-source land space data to construct a three-dimensional spatial data set for three-dimensional geometric modeling and generate a three-dimensional model of land space; perform multi-dimensional spatial analysis on the three-dimensional model of land space, obtain a spatial conflict feature set for planning constraints, and formulate spatial optimization suggestions; execute the spatial optimization suggestions for three-dimensional dynamic modeling, generate multi-time series planning simulation results for spatial planning evaluation, and generate a land space planning score; based on the land space planning score, backtrack the spatial optimization suggestions for planning compensation, update the spatial optimization suggestions, and obtain a spatial planning optimization plan.

[0006] The second aspect of the present application provides a national land space planning optimization system based on three-dimensional modeling, the system comprising: A three-dimensional geometric modeling module is used to obtain multi-source land and space data to construct a three-dimensional spatial data set for three-dimensional geometric modeling and generate a three-dimensional model of the land and space; a multi-dimensional spatial analysis module is used to perform multi-dimensional spatial analysis on the three-dimensional model of the land and space, obtain a spatial conflict feature set for planning constraints, and formulate spatial optimization suggestions; a planning scoring module is used to execute the spatial optimization suggestions for three-dimensional dynamic modeling, generate multi-time series planning simulation results for spatial planning evaluation, and generate a land and space planning score; a planning compensation module is used to backtrack the spatial optimization suggestions based on the land and space planning score to perform planning compensation, update the spatial optimization suggestions, and obtain a spatial planning optimization plan.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application obtains multi-source land and space data to construct a three-dimensional spatial data set for three-dimensional geometric modeling, and generates a three-dimensional model of land and space; performs multi-dimensional spatial analysis on the three-dimensional model of land and space, obtains a spatial conflict feature set for planning constraints, and formulates spatial optimization suggestions; executes the spatial optimization suggestions for three-dimensional dynamic modeling, generates multi-series planning simulation results for spatial planning evaluation, and generates a land and space planning score; based on the land and space planning score, backtracks the spatial optimization suggestions for planning compensation, updates the spatial optimization suggestions, and obtains a spatial planning optimization solution. The present invention solves the technical problem that the existing land and space planning relies on two-dimensional data, making it difficult to fully identify spatial conflicts and dynamic evolution processes, resulting in insufficient scientificity of planning solutions. By introducing multi-source data to construct a three-dimensional spatial model and performing multi-dimensional spatial analysis and dynamic modeling optimization, the technical effect of improving the accuracy of spatial conflict identification and the scientificity of planning decisions is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of the process flow of a land space planning optimization method based on three-dimensional modeling provided in an embodiment of the present application; Figure 2 Schematic diagram of the structure of the national land space planning optimization system based on three-dimensional modeling provided in the embodiment of the present application.

[0010] Explanation of the accompanying drawings: three-dimensional geometric modeling module 11, multi-dimensional space analysis module 12, planning scoring module 13, planning compensation module 14. DETAILED DESCRIPTION

[0011] This application provides a land space planning optimization method and system based on three-dimensional modeling, aiming to solve the technical problem that the existing land space planning relies on two-dimensional data, making it difficult to fully identify spatial conflicts and dynamic evolution processes, resulting in insufficient scientificity of planning schemes. By introducing multi-source data to construct a three-dimensional spatial model and conducting multi-dimensional spatial analysis and dynamic modeling optimization, the application achieves the technical effect of improving the accuracy of spatial conflict identification and the scientificity of planning decisions.

[0012] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0013] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0014] Example 1, as Figure 1 As shown, the present application provides a land space planning optimization method based on three-dimensional modeling, the method comprising: Step S100: Acquire multi-source land space data to construct a three-dimensional space data set for three-dimensional geometric modeling to generate a three-dimensional land space model.

[0015] In an embodiment of the present application, multi-source national land space data is first obtained, including lidar point clouds, remote sensing images and geographic reference data, and spatial geometric features and semantic attribute information are extracted through analysis. Based on the geographic reference data, the spatial coordinates of all data sources are normalized to establish a unified geographic coding system. Subsequently, the lidar point cloud data is denoised and classified, and ground and non-ground point clouds are extracted. The remote sensing images are combined for feature matching and registration, and high-precision three-dimensional terrain surface data is generated through fusion. At the same time, semantic segmentation is carried out based on remote sensing images, and spatial elements such as buildings, roads, and green spaces are extracted to construct a three-dimensional spatial attribute database. On this basis, the three-dimensional terrain surface data and the three-dimensional spatial attribute database are fused and compensated to complete a three-dimensional spatial data set with a complete structure and rich semantics.

[0016] Next, 3D geometric modeling was carried out based on the constructed 3D spatial dataset. First, surface modeling was performed by analyzing contour lines and sudden changes in terrain to form a terrain geometry sub-model. Building structure modeling was then performed based on the extracted building parameters to generate a 3D solid sub-model. Mesh subdivision and point cloud density analysis were performed on the vegetation cover area to divide it into different density zones and construct a vegetation cover sub-model. Finally, these sub-models were superimposed and fused under a unified spatial reference to generate a 3D national spatial model with solid geometric structure and spatial topological relationships.

[0017] Furthermore, in the method provided in the embodiment of the application, obtaining multi-source land space data to construct a three-dimensional spatial dataset also includes: Based on the multi-source land and space data, analysis is performed to obtain lidar point cloud data, remote sensing image data, and geographic reference data; the multi-source land and space data are normalized in terms of spatial coordinates according to the geographic reference data, and a unified geographic coding rule is constructed; based on the lidar point cloud data, denoising is performed to extract ground point cloud data and non-ground point cloud data; according to the unified geographic coding rule, feature matching is performed on the ground point cloud data, the non-ground point cloud data, and the remote sensing image data, respectively, to construct an initial registration matrix for data fusion, and to construct three-dimensional terrain surface data; semantic segmentation is performed based on the remote sensing image data to construct a three-dimensional spatial attribute database; mapping missing compensation is performed on the three-dimensional terrain surface data and the three-dimensional spatial attribute database to construct the three-dimensional spatial dataset.

[0018] In the present embodiment, during the construction of a three-dimensional spatial dataset, multi-source national land spatial data is first parsed to extract lidar point cloud data, remote sensing image data, and georeferenced data. To achieve unified alignment of the multi-source data, an affine transformation method is used to normalize the spatial coordinates of the various spatial data types based on the control points in the georeferenced data. This ensures that all data is expressed in the same geographic coordinate system (e.g., WGS84), and a unified geocoding rule is established to provide a unified identifier for subsequent spatial indexing.

[0019] During the point cloud data processing phase, the LiDAR point cloud data is first denoised. A statistical outlier removal algorithm is used to remove isolated points with unusual spatial distribution by calculating the average distance between a point and its surroundings, improving the cleanliness of the data and the stability of subsequent processing. Next, a progressive morphological filtering algorithm is used to classify the denoised point cloud. This algorithm uses a set initial structuring element radius and multiple rounds of morphological opening operations to iteratively extract a highly continuous surface trend surface, thereby identifying ground point cloud data. Points above this trend surface are marked as non-ground point cloud data, including buildings, vegetation, and other protruding objects.

[0020] After point cloud classification, the Scale-Invariant Feature Transform (SIFT) algorithm is used to perform spatial feature matching between the ground and non-ground point clouds, using texture and edge features extracted from remote sensing imagery, according to unified geocoding rules. Based on these matching results, an iterative closest point registration algorithm is used to construct an initial registration matrix. The ground and non-ground point cloud data are then rigidly transformed and fused to generate continuous, high-precision 3D terrain surface data.

[0021] During the semantic information extraction process, a U-Net deep semantic segmentation network is used to perform pixel-level classification of remote sensing imagery, identifying semantic regions such as buildings, roads, and green spaces. During the training phase, the U-Net model constructs a training set based on labeled, high-resolution remote sensing images. It uses forward convolution to encode features and reverse upsampling to restore spatial resolution. The training loss function uses cross-entropy to improve the accuracy of classification boundaries. After training, the model can perform full-image semantic segmentation on new images, generating a 3D spatial attribute database containing feature categories.

[0022] Finally, the generated 3D terrain surface data is fused with the 3D spatial attribute database, and spatial association mapping is used to map semantic information to specific geometric objects. For areas with missing attributes or geometric holes, Kriging spatial interpolation is used to compensate for the missing attributes, and spatial variograms are constructed to predict and fill in the attributes of adjacent areas. This completes the process, resulting in a structurally continuous and semantically complete 3D spatial dataset.

[0023] Furthermore, in the method provided in the embodiment of the application, constructing a three-dimensional spatial data set for three-dimensional geometric modeling to generate a three-dimensional model of national land space also includes: The three-dimensional terrain surface data is traversed to determine characteristic contour lines, terrain characteristic analysis is performed based on the characteristic contour lines, and terrain mutation characteristics are determined; surface modeling is performed based on the terrain mutation characteristics to construct a three-dimensional geometric sub-model; the three-dimensional spatial attribute database is traversed to perform standard analysis to obtain a building parameter set, modeling is performed based on the building parameter set, and a three-dimensional entity sub-model is constructed; three-dimensional grid subdivision is performed based on the vegetation coverage area, multiple vegetation coverage grids are traversed to perform point cloud density analysis, high-density vegetation areas and sparse vegetation areas are divided, and a vegetation coverage three-dimensional sub-model is constructed; the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the vegetation coverage three-dimensional sub-model are spatially superimposed to construct the national land space three-dimensional model.

[0024] In this embodiment, the three-dimensional terrain surface data is first traversed region by region. A contour extraction algorithm is then used to identify characteristic contour lines at different elevation levels, forming elevation profiles that reflect the terrain's undulations. Based on the extracted contour data, a curvature analysis method is used to calculate the elevation gradient and spatial curvature between them. This allows the identification of areas with steep slope changes and sudden changes in terrain, such as cliffs, steps, and sharp slope breaks.

[0025] Based on the identified abrupt terrain changes, the elevation data was spatially fitted using a triangulated irregular network (TIN) modeling approach. Delaunay triangulation was then used to construct a patch mesh, achieving a surface representation of the abrupt terrain. This process transformed terrain points into a 3D surface model with spatial topology, generating a continuous and spatially realistic 3D geometric sub-model that effectively reproduced the complex structure and elevation fluctuations of the landform.

[0026] During the building modeling phase, the system traverses the 3D spatial attribute database and performs structured parsing using the CityGML standard to extract basic building parameter information, including location coordinates, height, massing, and roof form, to construct a building parameter set. Subsequently, a procedural modeling method is used to drive the modeling engine based on the parameter set to automatically generate a 3D solid model containing components such as the base, walls, and roof. Ultimately, a 3D solid sub-model with topological structure and semantic annotation is formed, enabling the three-dimensional reconstruction of the urban building complex.

[0027] Vegetation areas annotated in the spatial attribute database were divided into multi-level 3D grid cells using the octree voxel subdivision method, and density statistics were performed on the point cloud data within each grid. A fixed-radius search method was used to estimate the point density per unit volume, and high-density vegetation areas and sparse vegetation areas were demarcated based on a set threshold. Based on the density classification results, voxel modeling was applied to generate 3D vegetation models of varying degrees of detail, constructing 3D sub-models of vegetation cover with distribution hierarchies and ecological semantics.

[0028] Finally, the 3D geometric sub-model, 3D entity sub-model, and 3D vegetation cover sub-model are spatially superimposed. This process first establishes a unified geographic coordinate system based on unified geographic coding rules. The 3D geometric sub-model, 3D entity sub-model, and 3D vegetation cover sub-model undergo unified spatial alignment and topological analysis to identify the spatial relationships between the models. Verification operations extract abnormal topological parameters between the models, correcting spatial overlaps, gaps, and interlacing relationships to form an optimized topological relationship network. Based on this topological optimization results, the model is spatially partitioned, and a multi-level spatial index structure is established. Based on this spatial index, the sub-models are vertically projected and fused, ultimately constructing a 3D national spatial model with a unified spatial benchmark, complete topological structure, and multi-factor representation.

[0029] Furthermore, in the method provided in the embodiment of the application, the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation cover sub-model are spatially superimposed to construct the three-dimensional land space model, further comprising: A unified geographic coordinate system is constructed based on the unified geographic coding rules, and a topological analysis is performed on the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model according to the unified geographic coordinate system to obtain the model space topological relationship; the model space topological relationship is verified based on the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model to obtain the model abnormal topological parameters; the model space topological relationship is corrected according to the model abnormal topological parameters to obtain the model space topological optimization relationship network; the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model are spatially divided based on the model space topological optimization relationship network to construct a hierarchical spatial index; the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model are vertically projected according to the hierarchical spatial index to construct the national land space three-dimensional model.

[0030] In the embodiment of this application, a unified geographic coordinate conversion method is first used to construct a unified geographic coordinate system. Based on the unified geographic coding rules generated in the early stage, the local coordinate system of each sub-model is uniformly converted using the WGS-84 coordinate conversion method. The 3D geometric sub-model, 3D entity sub-model, and 3D vegetation cover sub-model are all normalized to the globally used WGS-84 coordinate reference frame to establish a unified geographic coordinate system to ensure spatial registration consistency.

[0031] Next, we use the 3D-BRep topology construction method to perform model space topology analysis. Using boundary representation, we construct and encode the geometric boundaries of each sub-model. By analyzing the face-to-face, face-to-edge, and point-to-face spatial relationships between models, we form model space topology relationships that describe the connections, contacts, and adjacencies between models.

[0032] The established topological relationships are then checked for consistency using a 3D Boolean conflict detection algorithm. Based on a 3D Boolean computation framework, this method traverses the intersections between submodels pair by pair, detecting any unreasonable spatial relationships between them. It focuses on identifying penetration anomalies (e.g., the base of a building protruding through the terrain) and overhang anomalies (e.g., a building not touching the ground or vegetation suspended in the air). The corresponding spatial positions and geometric deviations are then extracted to generate model anomaly topology parameters.

[0033] Boolean operations are then used to repair topological anomalies discovered in the previous step. For penetration anomalies, Boolean subtraction is performed to trim and remove overlapping portions of the model. For overhanging anomalies, Boolean unions are performed or bottom faces are extended to fill contact. This process ensures geometric closure and structural logical consistency, ultimately forming a spatial topology network for the repaired model.

[0034] After topology optimization is complete, the modified three sub-models are spatially partitioned using an octree spatial indexing algorithm. This method recursively divides the three-dimensional space into equal parts, called voxel nodes, and records the geometric information contained in each node. This hierarchical spatial indexing enables efficient location, management, and regional processing of model data, providing a data scheduling foundation for model fusion.

[0035] Finally, a vertical projection fusion method was applied to vertically fuse and overlay the 3D geometric sub-models, 3D solid sub-models, and 3D vegetation cover sub-models according to the spatial positional relationships in the hierarchical spatial index. This process maintained the spatial hierarchy of each sub-model, and projection mapping techniques were used to ensure boundary continuity and overlap alignment, consolidating all data structures into a unified data unit. The result was a 3D national spatial model that exhibited topological consistency, spatial accuracy, and complete representation.

[0036] Step S200: Perform multi-dimensional spatial analysis on the three-dimensional model of the national land space, obtain a spatial conflict feature set for planning constraints, and formulate spatial optimization suggestions.

[0037] In an embodiment of the present application, in the process of performing a multi-dimensional spatial analysis on the three-dimensional model of the national land space to obtain a spatial conflict feature set, first, based on the three-dimensional spatial buffer analysis method, a spatial buffer zone is set for a specific control line, boundary or planning red line, and spatial objects that violate the boundary control requirements are identified to generate a first type of spatial conflict area. Subsequently, the spatial visibility features are extracted through three-dimensional visual field analysis, and a sight corridor conflict analysis is carried out to identify visual interference such as obstruction of public landscapes and line of sight blocking, and a second type of spatial conflict area is generated. Then, combined with the traffic accessibility analysis method, the traffic network structure in the model is identified, and the road connectivity and facility accessibility are analyzed to form a third type of spatial conflict area. By fusing the above three types of conflict areas, feature fusion calculation is performed to construct a spatial conflict feature set containing three-dimensional vector boundaries and conflict weights.

[0038] Based on this, the team extracted 3D vector boundary data and conflict intensity values ​​from the spatial conflict feature set. Using the vector boundary as the target variable and the conflict intensity as the constraint, they introduced a multi-objective spatial optimization method to reconstruct the spatial structure, outputting an adjusted 3D spatial element layout diagram. A 3D scenario planning model was then constructed based on this layout diagram. A multi-view spatial comparison array was generated to aid decision-making, showcasing the differences in spatial performance before and after optimization from different perspectives. This comparison array was ultimately integrated into the spatial optimization recommendations.

[0039] Furthermore, in the method provided in the embodiment of the application, a multi-dimensional spatial analysis is performed on the three-dimensional model of the national land space to obtain a spatial conflict feature set, which also includes: A three-dimensional spatial buffer analysis is performed based on the three-dimensional model of the national land space to generate a first type of spatial conflict area; a visual domain analysis is performed based on the three-dimensional model of the national land space to obtain three-dimensional spatial visibility characteristics, and a visual corridor conflict analysis is performed according to the three-dimensional spatial visibility characteristics to generate a second type of spatial conflict area; a traffic accessibility analysis is performed by traversing the three-dimensional model of the national land space to identify and determine the traffic road network, and a conflict analysis is performed according to the traffic road network to generate a third type of spatial conflict area; the first type of spatial conflict area, the second type of spatial conflict area, and the third type of spatial conflict area are subjected to a fusion feature analysis to construct the spatial conflict feature set.

[0040] In an embodiment of the present application, in the process of performing a three-dimensional spatial buffer zone analysis based on a three-dimensional model of national land space, the three-dimensional vector boundary data of the ecological protection red line is first extracted as the spatial benchmark of the ecological control area. Subsequently, a dynamic buffer radius calculation rule is set based on the boundary data, and an ecological sensitivity assessment is carried out in combination with the slope data extracted from the three-dimensional terrain model to construct an ecological sensitivity classification weight matrix. By superimposing the buffer radius rule and the sensitivity weight matrix, the response intensity of different regions to ecological interference is identified, and a conflict intensity value is generated accordingly. Finally, the spatial conflict boundary between the ecological protection red line and the construction land is delineated according to the conflict intensity value to form a first type of spatial conflict area.

[0041] Next, a visual domain analysis is performed on the three-dimensional model of the national land space to identify architectural conflicts that disrupt urban visual corridors. Specifically, a three-dimensional visual domain analysis method is used to set typical viewpoints (such as landscape corridors, squares in front of cultural relics protection units, and mountain viewpoints). The visible area of ​​each viewpoint in three-dimensional space is calculated based on the ray projection method, and the three-dimensional spatial visibility characteristics around the observation point are extracted, that is, the visibility status between each viewpoint and each object on the model surface. Based on these visibility results, a visual corridor conflict analysis is then carried out to determine whether the buildings in the model block, oppress, or visually interfere with the core visual range. Based on information such as the occlusion position and the degree of visibility loss, the spatial outlines corresponding to the conflicting buildings are extracted, and finally a second type of spatial conflict area is generated, which is used to reflect areas where urban visual accessibility is damaged or important visual corridors are restricted.

[0042] A transportation accessibility analysis was then conducted on the three-dimensional model of the national land space to identify areas where connectivity barriers exist between the transportation network structure and building land. Using the shortest path analysis method, the three-dimensional model of the national land space was first traversed to extract road centerlines, node connectivity, and building entrance and exit locations, thereby constructing a three-dimensional transportation map structure model. Subsequently, based on the Dijkstra algorithm, the shortest path from each building unit to the transportation hub was calculated, starting with the building unit and ending at the main road or service node. This determined whether there were path breaks or substandard accessibility. For buildings without effective access to the transportation network, their spatial boundaries were extracted and marked as areas with transportation accessibility issues. Finally, a third type of spatial conflict area was generated to identify areas where the transportation system and spatial layout were incompatible.

[0043] Finally, the three types of spatial conflict areas were uniformly processed and subjected to fusion feature analysis to construct the final spatial conflict representation. Using a spatial feature fusion analysis method, the spatial boundaries of the first, second, and third types of spatial conflict areas were merged and their attributes integrated within the same three-dimensional coordinate system. Attribute fields such as conflict type, conflict location, and conflict intensity were fused. Through unified coding standards, spatial overlay processing, and conflict type integration, a complete set of spatial conflict features was generated.

[0044] Furthermore, in the method provided in the embodiment of the application, a three-dimensional spatial buffer zone analysis is performed based on the three-dimensional national land space model to generate a first type of spatial conflict area, and the method further includes: Based on the three-dimensional model of the national land space, three-dimensional vector boundary data of the ecological protection red line is extracted, a buffer assessment is performed based on the three-dimensional vector boundary data, and a dynamic buffer radius calculation rule is set; based on the three-dimensional model of the national land space, three-dimensional terrain surface slope data is extracted to perform an ecological sensitivity assessment, and an ecological sensitivity grading weight matrix is ​​constructed; according to the dynamic buffer radius calculation rule and the ecological sensitivity grading weight matrix, an overlapping analysis is performed to generate a conflict intensity value, and the first type of spatial conflict area is delineated according to the conflict intensity value.

[0045] In this embodiment, during the 3D spatial buffer zone analysis based on the 3D national land model, 3D vector boundary data for the ecological protection redline is first extracted based on the 3D national land model. This step uses 3D spatial data processing methods to spatially analyze the ecological protection redline defined in the model, identify its boundary contours, extract the 3D coordinate points and boundary structure that constitute the redline, and generate 3D vector boundary data for the ecological protection redline, including its geographic location, elevation information, and topological relationships.

[0046] Subsequently, a buffer assessment was performed based on the three-dimensional vector boundary data, and dynamic buffer radius calculation rules were set. The method of zoning assignment and rule matching was adopted. First, the basic buffer distance was set according to the control level of the ecological protection red line (such as core protection area, key ecological area, and general control area), such as 50 meters, 30 meters, and 20 meters respectively; then the slope data of the area around the ecological protection red line boundary was extracted, and the buffer radius was corrected according to the slope level. When the slope was greater than 15°, the buffer distance was increased by 20% on the basic value; the slope was between 5° and 15° and increased by 10%; the slope was less than 5° and remained unchanged.

[0047] Based on a three-dimensional model of national land space, three-dimensional terrain surface slope data was extracted for ecological sensitivity assessment. Using terrain unit traversal and slope calculation methods, the elevation changes between terrain units in the three-dimensional model were analyzed to obtain a complete slope distribution map. Based on ecological response characteristics, slopes were classified using a sensitivity grading method: slopes less than 5° were considered low sensitivity, 5°-15° were considered medium sensitivity, and above 15° were considered high sensitivity. These slopes were assigned weights of 1, 2, and 3, forming a standardized sensitivity grading indicator system. This weighted matrix for ecological sensitivity grading was then constructed to quantify the susceptibility of different terrain regions to ecological disturbances.

[0048] Next, an overlap analysis is performed using dynamic buffer radius calculation rules combined with the ecological sensitivity grading weight matrix. Using a spatial overlap calculation method, the buffer zone layer and the sensitivity matrix layer are spatially superimposed. Within the overlapping area, the buffer level and sensitivity level are read for each spatial unit, and a combined judgment is made based on the preset conflict intensity scoring rules. For example, a unit with a high buffer level (3 points) and a high sensitivity (3 points) is assigned a conflict intensity of 6, a unit with a medium buffer level (2 points) and a medium sensitivity (2 points) is assigned a value of 4, and so on. This generates a conflict intensity value layer. This layer, based on spatial units, indicates the level of construction interference risk to each location within the ecological protection red line and serves as the core intermediate result of ecological conflict identification.

[0049] Finally, the first category of spatial conflict areas is delineated based on conflict intensity values. Extraction criteria are set within the conflict intensity layer, such as using areas with conflict intensity values ​​greater than or equal to 5 as the delineation criteria. Spatial filtering is then performed to extract high-conflict areas. The extracted results are then merged into adjacent cells, their boundaries smoothed, and subjected to 3D geometry reconstruction to generate closed spatial surface objects. These are then converted into 3D vector boundary data with spatial attribute identifiers, ultimately forming the first category of spatial conflict areas.

[0050] Furthermore, in the method provided in the embodiment of the application, obtaining a spatial conflict feature set for planning constraints and formulating spatial optimization suggestions also includes: Based on the three-dimensional vector boundary data and the conflict intensity value of the spatial conflict feature set; multi-objective optimization is performed using the three-dimensional vector boundary data as the target variable and the conflict intensity value as the constraint condition to determine a three-dimensional spatial element layout diagram; three-dimensional scene planning is performed according to the three-dimensional spatial element layout diagram to generate a multi-perspective spatial comparison array; and the multi-perspective spatial comparison array is added to the spatial optimization suggestion.

[0051] In the embodiment of the present application, optimization boundary identification and parameter reading operations are first carried out based on the three-dimensional vector boundary data and conflict intensity values ​​of the spatial conflict feature set. The first type of spatial conflict area in the spatial conflict feature set is extracted through a spatial traversal method, and the corresponding three-dimensional vector boundary data is loaded to limit the target area range of this round of optimization. At the same time, the conflict intensity value bound to the boundary data is extracted as a restrictive condition in the spatial use configuration, and an association relationship between the conflict intensity value and the optimization parameters is established.

[0052] Next, a multi-objective optimization operation was conducted using the three-dimensional vector boundary data as the target variable and the conflict intensity value as the constraint condition. During the execution process, a set of spatial units was constructed based on the optimized control area delineated by the three-dimensional vector boundary data, and the spatial elements to be configured within the area were identified and partitioned. Construction feasibility levels were set based on the conflict intensity values ​​corresponding to different spatial units. Restrictions were imposed on areas with high conflict intensity values, reducing their priority in spatial element allocation. On this basis, combined with existing data on construction land, ecological reserves, and corridors, the site selection, layout, and spatial compliance of various spatial elements were carried out, ultimately forming a structurally complete three-dimensional spatial element layout map that met the control boundary constraints.

[0053] 3D scene planning was then carried out according to the 3D spatial element layout diagram. Automated modeling and entity assembly methods were used to reconstruct the various functional units in the layout diagram in 3D. Model templates were set for different element types, such as construction land, ecological green space, and public facilities. After entity generation, these templates were superimposed on the real terrain model to form a complete 3D planning scene. Multiple typical viewing angles were then set to extract 3D views from top, horizontal, perspective, and cross-sectional perspectives. This generated a multi-perspective spatial comparison array with contrasting properties, facilitating the intuitive visualization of the spatial distribution changes in conflict areas before and after optimization, the effects of mitigating ecological pressure, and the resulting improvements in land use form.

[0054] Finally, spatial optimization recommendations are generated based on the multi-perspective spatial comparison array. This process compares three-dimensional scene images from different perspectives to observe the changes in the spatial relationships between conflicting areas, planned areas, and adjusted areas. First, the scene changes displayed in the comparison array are classified and identified. Areas that appear repeatedly from multiple perspectives and still have high conflict values ​​but are planned to be retained are considered important areas. Areas that still have space waste or duplicate construction after adjustment are considered compressible or replaceable areas. Then, based on the location, type, and layout of each functional element in the three-dimensional spatial element layout diagram, the above areas are prioritized and their usage is optimized. Finally, a preliminary spatial optimization recommendation is generated, including which areas need to be retained, which areas should be replanned, and which areas can be integrated or reduced, and the multi-perspective spatial comparison array is embedded as part of the recommendation.

[0055] Step S300: Execute the spatial optimization suggestions to perform three-dimensional dynamic modeling, generate multi-time sequence planning simulation results for spatial planning evaluation, and generate a national land space planning score.

[0056] In an embodiment of the present application, when executing spatial optimization suggestions for three-dimensional dynamic modeling, first, a temporal dynamic three-dimensional model framework is constructed, the overall planning cycle is divided into multiple time nodes, and corresponding spatial optimization targets are set for each time node. On this basis, the national land space is continuously evolved in three dimensions according to the optimization suggestions, an initial multi-time sequence planning simulation result is generated, and the simulation result is dynamically calibrated through multi-source real-time data streams to form a complete multi-time sequence planning simulation result. Based on the result, a three-dimensional space performance evaluation index is constructed, and it is mapped to each time node for quantification, the index change rate is calculated, and the index time series evolution curve is constructed. Risk analysis is carried out according to the indicator change trend, and a risk probability distribution map is generated. Finally, the national land space is comprehensively evaluated in combination with the three-dimensional space indicator change rate and the risk probability distribution map, and a national land space planning score with a complete structure and dynamic response is output.

[0057] Furthermore, in the method provided in the embodiment of the application, executing the spatial optimization suggestion to perform three-dimensional dynamic modeling and generate multi-sequence planning simulation results also includes: Construct a time-series dynamic three-dimensional model framework, divide the planning cycle into multiple time nodes, set multiple spatial optimization targets for the multiple time nodes based on the spatial optimization suggestions, and there is a correspondence between the multiple spatial optimization targets and the multiple time nodes; execute the spatial optimization suggestions on the national land space to perform three-dimensional spatial evolution, and generate initial multi-series planning simulation results; integrate multi-source real-time data streams, and perform real-time calibration on the initial multi-series planning simulation results based on the multi-source real-time data streams to generate the multi-series planning simulation results.

[0058] In the embodiment of the present application, a temporal dynamic three-dimensional model framework is first constructed, which is divided into multiple time nodes according to the planning cycle. This step adopts a three-dimensional modeling method based on time dimension segmentation, and divides multiple time nodes with practical decision-making significance (such as 2030, 2040, and 2050) with reference to the control period, medium-term, and long-term period set by the spatial master plan. In the modeling system, a layer time marking mechanism is used to create an independent three-dimensional spatial model layer for each time node, forming a temporal dynamic three-dimensional model framework with phased expression capabilities. Each layer has data structures such as spatial geometric attributes, land use types, and elevation information, and is bound to time node attribute fields to ensure that the spatial state of each time period can be separated and evolved.

[0059] Subsequently, multiple spatial optimization targets are set for multiple time nodes based on the spatial optimization suggestions, and there is a corresponding relationship between the multiple spatial optimization targets and the multiple time nodes. In the specific operation, the three-dimensional spatial element layout map and the multi-perspective spatial comparison array are first extracted from the spatial optimization suggestions, and the spatial units that need to be retained, adjusted or compressed at different time nodes are identified through the spatial overlap analysis method. Taking the 2030 time node as an example, the functional land distribution of the corresponding year in the layout map is extracted, and the areas with conflict intensity values ​​higher than the set threshold are identified. Combined with the mitigation solutions presented in the comparison array, phased spatial optimization targets are formed, such as compressing and adjusting redundant facility land in the first type of spatial conflict area, expanding the green space boundary setback range, etc. All spatial optimization targets are numbered and corresponded to each time node one by one, and are embedded in the model framework as spatial modeling input parameters to establish a corresponding relationship between multiple spatial optimization targets and multiple time nodes.

[0060] Then, the spatial optimization suggestions for the national land space are implemented and three-dimensional spatial evolution is carried out to generate the initial multi-temporal planning simulation results. Using a method based on layer replacement and spatial entity reconstruction, the spatial optimization target set in the previous step is called at each time node, and the corresponding layer status is updated in the three-dimensional modeling system. Each evolution includes replacing the land use type in the target spatial unit with the new functional type set by the optimization suggestion; performing vector topological correction on the boundary between construction land and ecological land; and updating the building elevation and density parameters of the area involving building blocks. Through phased update operations, the spatial state sequence under multiple time nodes is gradually constructed. The final output result is the initial multi-temporal planning simulation result, which records the planning evolution path of the space from the current situation to the long-term in the form of a structured layer sequence.

[0061] Finally, the initial multi-series planning simulation results are calibrated in real time based on the integration of multiple real-time data streams to generate the multi-series planning simulation results. This step utilizes a method based on discrepancy identification and spatial correction. This method incorporates multiple real-time data streams, including remote sensing change detection data from a remote sensing system to identify areas of deviation between the model's land cover boundaries and actual land feature changes. Population migration data from a spatial population database is analyzed through heat map mapping to determine whether the model's residential spaces align with actual population distribution trends. For areas of deviation, a spatial offset vector calculation method is used to automatically correct the functional types or boundaries in the model layers. For example, at the "2040 node," if remote sensing change detection data indicates that an ecological control area has actually been developed, the corresponding model layer is updated to restricted land use and the use description field is redefined. Through time-by-time node discrepancy correction, the final multi-series planning simulation results are output, adjusted based on real-time data feedback.

[0062] Furthermore, in the method provided in the embodiment of the application, generating multi-time sequence planning simulation results for spatial planning evaluation and generating a national land space planning score also includes: Based on the multi-time planning simulation results, a three-dimensional space efficiency evaluation index is constructed; the three-dimensional space efficiency evaluation index is mapped to the multiple time nodes for spatial measurement, and the three-dimensional space index change rate of the multiple time nodes is calculated; based on the three-dimensional space index change rate of the multiple time nodes, an indicator time series evolution curve is constructed, and a risk analysis is performed according to the indicator time series evolution curve to generate a risk probability distribution map; a comprehensive spatial planning evaluation of the national land space is performed according to the three-dimensional space index change rate and the risk probability distribution map to obtain a national land space planning score.

[0063] In this embodiment, a three-dimensional spatial performance evaluation index is first constructed based on the results of a multi-temporal planning simulation. Using an element-oriented index extraction method, the multi-period three-dimensional spatial elements in the simulation results are quantitatively structured. Specifically, representative evaluation dimensions, such as green space ratio per unit land area, three-dimensional building density, road accessibility, and ecological space connectivity, are extracted using data such as functional land use classification, spatial boundaries, and elevation attributes from the three-dimensional model layer to form the three-dimensional spatial performance evaluation index.

[0064] The three-dimensional spatial performance evaluation indicators are then mapped to multiple time nodes for spatial measurement. Using an attribute-time layer overlay method, the three-dimensional spatial performance evaluation indicators extracted at each time node are mapped to the corresponding multi-time series model layer. The specific steps include traversing the spatial units of the three-dimensional model at each time node, injecting the evaluation indicator values ​​into the attribute table according to the spatial unit number, and visualizing the rendering using vector-to-raster conversion technology. This completes the temporal positioning of the three-dimensional spatial indicators on the model layers at different time periods, forming a multi-time node three-dimensional spatial indicator layer sequence.

[0065] Next, we calculated the rate of change of the three-dimensional spatial indicator at multiple time points. Using the temporal difference method, we calculated the rate of change for the indicator values ​​of the same spatial unit in the layer sequence at different time periods. For example, if the unit green space ratio of a unit is 0.25 in 2030 and 0.35 in 2040, the average annual rate of change is calculated as (0.35-0.25) / 10 = 0.01 / year. This calculation is performed for all indicators at each spatial unit, generating a three-dimensional spatial indicator change rate that includes the indicator name, rate of change, spatial location, and time span.

[0066] Then, based on the rate of change of three-dimensional spatial indicators at multiple time nodes, a time-series evolution curve is constructed. Using B-spline fitting, the temporal trend of each indicator is smoothly modeled, generating a continuous time series curve. This curve effectively reveals the direction and trend of indicator fluctuations at different planning stages, such as the continuous upward trend of building density. The curve model is used for subsequent anomaly identification and risk analysis.

[0067] Subsequently, risk analysis was conducted based on the time-series evolution curves of the indicators, generating a risk probability distribution map. This approach employed indicator anomaly detection and spatial weighting. First, a normal range of variation was set for each assessment indicator (e.g., an annual rate of change of ±0.02 was considered acceptable). When the indicator's rate of change or evolution curve exceeded this range in a given spatial unit, an anomaly was recorded. The number of anomalies for all indicators within the same unit was then counted. Risk weights were then assigned based on indicator importance (e.g., a weight of 0.4 for ecological indicators, 0.3 for transportation indicators, 0.2 for construction indicators, and 0.1 for greening indicators, with the total weight being 1). This weighting was derived from an expert scoring method. A panel of experts, comprised of professionals in urban planning, ecology, transportation, and land management, rated the importance of each indicator to the rationality of the national land space. The scores were normalized and tested for consistency using the Analytic Hierarchy Process (AHP) to determine the relative weight of each indicator category. The risk value for each spatial unit was then calculated using the following formula: Risk value = ∑(number of indicator anomalies × indicator weight) / maximum weighted total anomaly value. The results are then normalized to between 0 and 1, rendered as a color layer, and output as a risk probability distribution map.

[0068] Finally, a comprehensive spatial planning assessment of the national land space is conducted based on the rate of change of three-dimensional spatial indicators and the risk probability distribution map, resulting in a national land space planning score. This score is calculated using a multi-indicator weighted comprehensive method. Specifically, the rate of change of each indicator is first normalized (min-max normalization). This is then multiplied by the internal weight of the indicator within its category, as determined by the expert method (for example, in the "Ecology" category, connectivity accounts for 0.6 and green space ratio accounts for 0.4). This is then multiplied by the external weight of the category within all major categories (for example, the Ecology category is 0.4). The total score of all indicators is then multiplied by (1 - risk value) to form the final planning score. The formula is score = {∑[normalized indicator value × internal weight × external weight]} × (1 - risk value). This process ultimately yields the national land space planning score.

[0069] Step S400: Based on the national land space planning score, the spatial optimization suggestion is back-traced to perform planning compensation, the spatial optimization suggestion is updated, and a spatial planning optimization solution is obtained.

[0070] In an embodiment of the present application, planning compensation is performed based on the spatial optimization suggestions based on the national land space planning score. A reverse analysis method based on score feedback is adopted to match the national land space planning score results with the key decision-making areas in the spatial optimization suggestions one by one, and identify spatial units with low scores or high risk values. In this process, the scoring results are first spatially deconstructed, and the low-scoring areas are associated with their corresponding spatial optimization targets to determine whether they are due to poor performance of indicators such as excessive construction intensity, decreased ecological connectivity, or insufficient traffic accessibility. Subsequently, combined with the risk probability distribution map, the functional configuration, land use boundaries, development sequence, etc. of the above-mentioned areas are strategically revised to form a planning compensation logic. For example, for units with low scores but belonging to ecologically sensitive areas, their use is adjusted to ecological preservation or restricted development areas; for areas with substandard accessibility, road network access is optimized or public service nodes are added. Finally, the three-dimensional spatial element layout map and multi-perspective spatial comparison array involved in the original spatial optimization suggestions are updated, and the spatial optimization suggestions after structural adjustment are output to form a new spatial planning optimization plan.

[0071] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: This application obtains multi-source land and space data to construct a three-dimensional spatial data set for three-dimensional geometric modeling, and generates a three-dimensional model of land and space; performs multi-dimensional spatial analysis on the three-dimensional model of land and space, obtains a spatial conflict feature set for planning constraints, and formulates spatial optimization suggestions; executes the spatial optimization suggestions for three-dimensional dynamic modeling, generates multi-series planning simulation results for spatial planning evaluation, and generates a land and space planning score; based on the land and space planning score, backtracks the spatial optimization suggestions for planning compensation, updates the spatial optimization suggestions, and obtains a spatial planning optimization solution. The present invention solves the technical problem that the existing land and space planning relies on two-dimensional data, making it difficult to fully identify spatial conflicts and dynamic evolution processes, resulting in insufficient scientificity of planning solutions. By introducing multi-source data to construct a three-dimensional spatial model and performing multi-dimensional spatial analysis and dynamic modeling optimization, the technical effect of improving the accuracy of spatial conflict identification and the scientificity of planning decisions is achieved.

[0072] Example 2 is based on the same inventive concept as the land space planning optimization method based on three-dimensional modeling in the above embodiment. Figure 2 As shown, the present application provides a national land space planning optimization system based on three-dimensional modeling. The system and method embodiments in the present application are based on the same inventive concept. The system includes: The three-dimensional geometric modeling module 11 is used to obtain multi-source national land space data to construct a three-dimensional spatial data set for three-dimensional geometric modeling and generate a three-dimensional model of the national land space; the multi-dimensional spatial analysis module 12 is used to perform multi-dimensional spatial analysis on the three-dimensional model of the national land space, obtain a spatial conflict feature set for planning constraints, and formulate spatial optimization suggestions; the planning scoring module 13 is used to execute the spatial optimization suggestions for three-dimensional dynamic modeling, generate multi-time series planning simulation results for spatial planning evaluation, and generate a national land space planning score; the planning compensation module 14 is used to backtrack the spatial optimization suggestions based on the national land space planning score for planning compensation, update the spatial optimization suggestions, and obtain a spatial planning optimization plan.

[0073] Furthermore, the system is also used to implement the following functions: Based on the multi-source land and space data, analysis is performed to obtain lidar point cloud data, remote sensing image data, and geographic reference data; the multi-source land and space data are normalized in terms of spatial coordinates according to the geographic reference data, and a unified geographic coding rule is constructed; based on the lidar point cloud data, denoising is performed to extract ground point cloud data and non-ground point cloud data; according to the unified geographic coding rule, feature matching is performed on the ground point cloud data, the non-ground point cloud data, and the remote sensing image data, respectively, to construct an initial registration matrix for data fusion, and to construct three-dimensional terrain surface data; semantic segmentation is performed based on the remote sensing image data to construct a three-dimensional spatial attribute database; mapping missing compensation is performed on the three-dimensional terrain surface data and the three-dimensional spatial attribute database to construct the three-dimensional spatial dataset.

[0074] Furthermore, the system is also used to implement the following functions: The three-dimensional terrain surface data is traversed to determine characteristic contour lines, terrain characteristic analysis is performed based on the characteristic contour lines, and terrain mutation characteristics are determined; surface modeling is performed based on the terrain mutation characteristics to construct a three-dimensional geometric sub-model; the three-dimensional spatial attribute database is traversed to perform standard analysis to obtain a building parameter set, modeling is performed based on the building parameter set, and a three-dimensional entity sub-model is constructed; three-dimensional grid subdivision is performed based on the vegetation coverage area, multiple vegetation coverage grids are traversed to perform point cloud density analysis, high-density vegetation areas and sparse vegetation areas are divided, and a vegetation coverage three-dimensional sub-model is constructed; the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the vegetation coverage three-dimensional sub-model are spatially superimposed to construct the national land space three-dimensional model.

[0075] Furthermore, the system is also used to implement the following functions: A unified geographic coordinate system is constructed based on the unified geographic coding rules, and a topological analysis is performed on the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model according to the unified geographic coordinate system to obtain the model space topological relationship; the model space topological relationship is verified based on the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model to obtain the model abnormal topological parameters; the model space topological relationship is corrected according to the model abnormal topological parameters to obtain the model space topological optimization relationship network; the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model are spatially divided based on the model space topological optimization relationship network to construct a hierarchical spatial index; the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model are vertically projected according to the hierarchical spatial index to construct the national land space three-dimensional model.

[0076] Furthermore, the system is also used to implement the following functions: A three-dimensional spatial buffer analysis is performed based on the three-dimensional model of the national land space to generate a first type of spatial conflict area; a visual domain analysis is performed based on the three-dimensional model of the national land space to obtain three-dimensional spatial visibility characteristics, and a visual corridor conflict analysis is performed according to the three-dimensional spatial visibility characteristics to generate a second type of spatial conflict area; a traffic accessibility analysis is performed by traversing the three-dimensional model of the national land space to identify and determine the traffic road network, and a conflict analysis is performed according to the traffic road network to generate a third type of spatial conflict area; the first type of spatial conflict area, the second type of spatial conflict area, and the third type of spatial conflict area are subjected to a fusion feature analysis to construct the spatial conflict feature set.

[0077] Furthermore, the system is also used to implement the following functions: Based on the three-dimensional model of the national land space, three-dimensional vector boundary data of the ecological protection red line is extracted, a buffer assessment is performed based on the three-dimensional vector boundary data, and a dynamic buffer radius calculation rule is set; based on the three-dimensional model of the national land space, three-dimensional terrain surface slope data is extracted to perform an ecological sensitivity assessment, and an ecological sensitivity grading weight matrix is ​​constructed; according to the dynamic buffer radius calculation rule and the ecological sensitivity grading weight matrix, an overlapping analysis is performed to generate a conflict intensity value, and the first type of spatial conflict area is delineated according to the conflict intensity value.

[0078] Furthermore, the system is also used to implement the following functions: Based on the three-dimensional vector boundary data and the conflict intensity value of the spatial conflict feature set; multi-objective optimization is performed using the three-dimensional vector boundary data as the target variable and the conflict intensity value as the constraint condition to determine a three-dimensional spatial element layout diagram; three-dimensional scene planning is performed according to the three-dimensional spatial element layout diagram to generate a multi-perspective spatial comparison array; and the multi-perspective spatial comparison array is added to the spatial optimization suggestion.

[0079] Furthermore, the system is also used to implement the following functions: Construct a time-series dynamic three-dimensional model framework, divide the planning cycle into multiple time nodes, set multiple spatial optimization targets for the multiple time nodes based on the spatial optimization suggestions, and there is a corresponding relationship between the multiple spatial optimization targets and the multiple time nodes; execute the spatial optimization suggestions on the national land space to perform three-dimensional spatial evolution, and generate initial multi-time-series planning simulation results; integrate multi-source real-time data streams, and perform real-time calibration on the initial multi-time-series planning simulation results based on the multi-source real-time data streams to generate the multi-time-series planning simulation results.

[0080] Furthermore, the system is also used to implement the following functions: Based on the multi-time planning simulation results, a three-dimensional space efficiency evaluation index is constructed; the three-dimensional space efficiency evaluation index is mapped to the multiple time nodes for spatial measurement, and the three-dimensional space index change rate of the multiple time nodes is calculated; based on the three-dimensional space index change rate of the multiple time nodes, an indicator time series evolution curve is constructed, and a risk analysis is performed according to the indicator time series evolution curve to generate a risk probability distribution map; a comprehensive spatial planning evaluation of the national land space is performed according to the three-dimensional space index change rate and the risk probability distribution map to obtain a national land space planning score.

[0081] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0083] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A land space planning optimization method based on three-dimensional modeling, characterized by: The method comprises: Acquire multi-source land and space data to construct a three-dimensional spatial data set for three-dimensional geometric modeling and generate a three-dimensional land and space model; Conduct multi-dimensional spatial analysis on the three-dimensional model of the national land space, obtain a set of spatial conflict characteristics for planning constraints, and formulate spatial optimization suggestions; Execute the spatial optimization suggestions to conduct three-dimensional dynamic modeling, generate multi-sequence planning simulation results for spatial planning evaluation, and generate national land space planning scores; Based on the national land space planning score, the spatial optimization suggestion is traced back to perform planning compensation, the spatial optimization suggestion is updated, and a spatial planning optimization plan is obtained.

2. The land space planning optimization method based on three-dimensional modeling according to claim 1 is characterized in that: Acquire multi-source land space data to construct a three-dimensional spatial dataset. The methods include: Analyze the multi-source land and space data to obtain lidar point cloud data, remote sensing image data, and geographic reference data; Normalizing the spatial coordinates of the multi-source land space data according to the geographic reference data to construct a unified geographic coding rule; Performing denoising processing based on the laser radar point cloud data to extract ground point cloud data and non-ground point cloud data; According to the unified geocoding rules, the ground point cloud data, the non-ground point cloud data and the remote sensing image data are respectively feature matched, an initial registration matrix is ​​constructed for data fusion, and three-dimensional terrain surface data is constructed; Perform semantic segmentation based on the remote sensing image data to build a three-dimensional spatial attribute database; The three-dimensional terrain surface data and the three-dimensional space attribute database are mapped and compensated for missing information to construct the three-dimensional space data set.

3. The land space planning optimization method based on three-dimensional modeling according to claim 2 is characterized in that: Construct a 3D spatial dataset for 3D geometric modeling and generate a 3D model of national land space. The methods include: Traversing the three-dimensional terrain surface data to determine characteristic contour lines, performing terrain feature analysis based on the characteristic contour lines, and determining terrain mutation features; Performing surface modeling based on the sudden change characteristics of the terrain to construct a three-dimensional geometric sub-model; Traversing the three-dimensional spatial attribute database to perform standard analysis, obtain a building parameter set, perform modeling according to the building parameter set, and construct a three-dimensional entity sub-model; Based on the vegetation coverage area, three-dimensional grid subdivision is performed, multiple vegetation coverage grids are traversed to perform point cloud density analysis, high-density vegetation areas are divided into sparse vegetation areas, and a three-dimensional vegetation coverage sub-model is constructed; The three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation cover sub-model are spatially superimposed to construct the three-dimensional model of the national land space.

4. The land space planning optimization method based on three-dimensional modeling according to claim 3 is characterized in that: The three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation cover sub-model are spatially superimposed to construct the three-dimensional land space model, and the method includes: Constructing a unified geographic coordinate system based on the unified geographic coding rules, performing topological analysis on the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation cover sub-model according to the unified geographic coordinate system to obtain a model space topological relationship; Verifying the model spatial topological relationship based on the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation cover sub-model to obtain model abnormal topological parameters; Correcting the model space topology relationship according to the model abnormal topology parameters to obtain a model space topology optimization relationship network; Based on the model space topology optimization relationship network, the three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation cover sub-model are spatially divided to construct a hierarchical spatial index; The three-dimensional geometric sub-model, the three-dimensional entity sub-model, and the three-dimensional vegetation coverage sub-model are vertically projected according to the hierarchical spatial index to construct the three-dimensional model of the national land space.

5. The land space planning optimization method based on three-dimensional modeling according to claim 1 is characterized in that: Performing a multi-dimensional spatial analysis on the three-dimensional model of the national land space to obtain a spatial conflict feature set, the method comprising: Performing a three-dimensional spatial buffer zone analysis based on the three-dimensional national land space model to generate a first type of spatial conflict area; Performing a visual domain analysis based on the three-dimensional model of the national land space to obtain three-dimensional spatial visibility characteristics, performing a visual corridor conflict analysis based on the three-dimensional spatial visibility characteristics, and generating a second type of spatial conflict area; Traversing the three-dimensional model of the national land space to perform traffic accessibility analysis, identify and determine the traffic road network, perform conflict analysis according to the traffic road network, and generate a third type of spatial conflict area; The first type of spatial conflict area, the second type of spatial conflict area, and the third type of spatial conflict area are subjected to fusion feature analysis to construct the spatial conflict feature set.

6. The land space planning optimization method based on three-dimensional modeling according to claim 5 is characterized in that: A three-dimensional spatial buffer zone analysis is performed based on the three-dimensional national land space model to generate a first type of spatial conflict area, the method comprising: Extracting three-dimensional vector boundary data of the ecological protection red line based on the three-dimensional land space model, performing a buffer assessment based on the three-dimensional vector boundary data, and setting a dynamic buffer radius calculation rule; Based on the three-dimensional land space model, three-dimensional terrain surface slope data is extracted to conduct ecological sensitivity assessment, and an ecological sensitivity classification weight matrix is ​​constructed; An overlapping analysis is performed according to the dynamic buffer radius calculation rule and the ecological sensitivity grading weight matrix to generate a conflict intensity value, and the first type of spatial conflict area is delineated according to the conflict intensity value.

7. The land space planning optimization method based on three-dimensional modeling according to claim 6 is characterized in that: Obtain spatial conflict feature sets for planning constraints and formulate spatial optimization recommendations. The methods include: The three-dimensional vector boundary data and the conflict intensity value based on the spatial conflict feature set; Perform multi-objective optimization using the three-dimensional vector boundary data as a target variable and the conflict intensity value as a constraint condition to determine a three-dimensional spatial element layout diagram; Performing three-dimensional scene planning according to the three-dimensional spatial element layout diagram to generate a multi-view spatial comparison array; The multi-view spatial comparison array is added to the spatial optimization suggestion.

8. The land space planning optimization method based on three-dimensional modeling according to claim 1 is characterized in that: Executing the spatial optimization suggestion to perform three-dimensional dynamic modeling and generate multi-sequence planning simulation results, the method includes: Constructing a time-series dynamic three-dimensional model framework, dividing the planning period into multiple time nodes, and setting multiple spatial optimization targets for the multiple time nodes based on the spatial optimization suggestions, wherein the multiple spatial optimization targets correspond to the multiple time nodes; Performing three-dimensional spatial evolution on the national land space by implementing the spatial optimization suggestions, and generating initial multi-temporal planning simulation results; Integrate multi-source real-time data streams, perform real-time calibration on the initial multi-sequence planning simulation results based on the multi-source real-time data streams, and generate the multi-sequence planning simulation results.

9. The land space planning optimization method based on three-dimensional modeling according to claim 8, characterized in that: Generate multi-time planning simulation results for spatial planning assessment and generate national land space planning scores. The methods include: Constructing a three-dimensional spatial performance evaluation index based on the multi-time sequence planning simulation results; Mapping the three-dimensional spatial performance evaluation index to the multiple time nodes for spatial measurement, and calculating the change rate of the three-dimensional spatial index at the multiple time nodes; Constructing an indicator time series evolution curve based on the three-dimensional spatial indicator change rates of the multiple time nodes, performing risk analysis based on the indicator time series evolution curve, and generating a risk probability distribution diagram; A comprehensive spatial planning assessment of the national land space is conducted based on the change rate of the three-dimensional spatial indicators and the risk probability distribution map to obtain a national land space planning score.

10. The national land space planning optimization system based on three-dimensional modeling is characterized by: The system is used to execute the land space planning optimization method based on three-dimensional modeling as described in any one of claims 1 to 9, and the system includes: The 3D geometric modeling module is used to obtain multi-source land space data to construct a 3D spatial data set for 3D geometric modeling and generate a 3D land space model; A multi-dimensional spatial analysis module is used to perform multi-dimensional spatial analysis on the three-dimensional model of the national land space, obtain a set of spatial conflict characteristics for planning constraints, and formulate spatial optimization suggestions; A planning scoring module is used to execute the spatial optimization suggestions to perform three-dimensional dynamic modeling, generate multi-sequence planning simulation results for spatial planning evaluation, and generate a national land space planning score; The planning compensation module is used to perform planning compensation based on the national land space planning score by backtracking the spatial optimization suggestions, updating the spatial optimization suggestions, and obtaining a spatial planning optimization plan.

Images