Intelligent structure topology method for urban spatial form

Abstract

The invention discloses an intelligent structure topology method of an urban spatial form, which realizes digital reconstruction of the urban spatial form through a multi-dimensional spatial element intelligent recombination technology, and comprises the following steps: acquiring urban spatial big data, and establishing an urban spatial database; intelligently identifying urban space elements according to types, and generating a vector graph; carrying out geometric intelligent analysis on the urban space element vector graph, and carrying out preprocessing of cutting, merging and combining; performing vector-grid-vector double-loop graph optimization on the vector graph to generate various urban space element topological patterns; and superposing the urban space element topological patterns according to the class and sequence to form an intelligent structure topological graph of the urban space form, and outputting and displaying the intelligent structure topological graph.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of smart city and geographic information technology, in particular to an intelligent structure topology method of urban spatial form. BACKGROUND

[0002] With the accelerated development of smart city construction and the rapid development of artificial intelligence technology, the digital analysis of urban spatial form has become the core demand in the fields of urban planning, traffic management, ecological assessment, etc. Traditional urban spatial analysis methods rely on manual operation of GIS geographic information system tools and manual operation of GIS geographic information system tools, and there are significant deficiencies in dealing with large-scale dynamic updating data.

[0003] The "one map" of national space planning requires real-time topology analysis of ten million elements to meet the fine management needs of urban and rural space; the new urbanization strategy proposes to build more than 200 city information model (CIM) platforms, which urgently need efficient spatial structure analysis tools; traffic network optimization and landscape ecological assessment all need to integrate remote sensing images, social and economic data, spatial form data and other multi-dimensional urban spatial big data, and high-fidelity urban spatial topology structure is beneficial to enhancing the scientific nature of decision-making in multidisciplinary applications.

[0004] Due to the single machine architecture and manual operation of GIS geographic information system, the data processing efficiency is low, which cannot meet the data processing needs of large scale and high dynamic update; the traditional urban spatial topology structure relying on manual experience and manual drawing has the problems of insufficient element recognition accuracy, low recognition precision, extensive topology relationship construction and long time consumption. When using machine learning and deep learning technology to identify urban spatial form, the light model training requires million-level labeled data, which leads to high technical cost and is not conducive to wide application and promotion. SUMMARY

[0005] In view of the problems in the prior art, the present application provides an intelligent structure topology method of urban spatial form, which automatically generates the topology structure of urban spatial form through distributed computing, intelligent cognition, adaptive geometric processing, double-cycle iterative optimization and other operations.

[0006] The purpose of the present application is achieved by the following technical solutions.

[0007] An intelligent structure topology method of urban spatial form, comprising the following steps:

[0008] 1) Obtain urban spatial big data and establish a city spatial database;

[0009] Based on the Amap open platform, multi-dimensional urban spatial data is obtained in real time. The Spark distributed architecture is used for data cleaning and feature extraction to form urban spatial morphological vectorized data with dynamic update capabilities. The data is input into the ArcGIS geographic information system to establish an urban spatial database.

[0010] 2) Intelligently identify urban spatial elements by type and generate vector graphics;

[0011] According to the five types of urban spatial elements, namely base surface, cluster, depression, green wedge and corridor, the attention mechanism is used to automatically detect, identify and extract the five types of urban spatial elements to generate vector graphics.

[0012] 3) Geometric intelligent analysis of urban spatial element vector graphics, and pre-processing of cropping, merging, and combining;

[0013] Based on the geometric properties of urban spatial elements, vector graphics are intelligently analyzed and geospatially preprocessed to generate new vector graphics. For urban spatial elements with geometric surface features, such as base surfaces, clusters, depressions, and green wedges, the Delaunay triangulation algorithm is used for adaptive processing, including overlapping contours, clipping, and merging, to generate new vector graphics layers. For urban spatial elements with geometric line features, such as corridors, vector graphics are spatially processed as continuous line segments.

[0014] 4) Vector graphics are optimized through a double loop of “vector-raster-vector” to generate topological patterns of various urban spatial elements;

[0015] The vector graphics are first converted into raster images according to a certain grid accuracy, and then the generated raster images are converted back into vector graphics. In this way, the vector graphics of each urban spatial element are subjected to a "vector-raster-vector" double-loop iterative optimization, and then after smoothing, a set of urban spatial element topological patterns is further generated.

[0016] 5) Superimpose the topological patterns of urban space elements in order and by category to form an intelligent structural topological graph of the urban space form, and output it for display.

[0017] Furthermore, step 1) is specifically as follows:

[0018] 1.1) Use the AutoNavi Maps OpenAPI to obtain real-time multi-dimensional urban spatial data including road networks, building outlines, building storeys, block outlines, river systems, green spaces, and mountains;

[0019] 1.2) Use Spark to partition multi-dimensional urban spatial data into multiple partitions for distributed storage. Within the Spark distributed architecture, data inspection and geometry repair are used to remove useless, irrelevant, and out-of-range data.

[0020] 1.3) Import the processed multi-dimensional urban spatial data into the ArcGIS geographic information system to form an urban spatial morphology vector database with dynamic update capabilities.

[0021] Furthermore, step 2) is specifically as follows:

[0022] 2.1) Based on the database in 1.3) above, calculate the spatial intensity data and classify it into three intervals using the natural break point classification method. Use the attention mechanism to automatically detect the planar spatial regions corresponding to the three-level data intervals and derive the three-level base surface contour vector graphics;

[0023] 2.2) Within the three-level base surface interval described in 2.1), continue to automatically detect planar spatial regions corresponding to high spatial intensity values ​​through the attention mechanism (a single area should not be less than 1 square kilometer), and derive the three-level cluster contour surface vector graphics;

[0024] 2.3) Within the three-level base surface interval described in 2.1), continue to automatically detect planar spatial regions corresponding to low spatial intensity values ​​through the attention mechanism (a single area should not be less than 1 square kilometer), and derive the three-level depression contour surface vector graphics;

[0025] 2.4) At the outer edge of the third-level base surface contour in 2.1), the concave feature surface area is automatically detected through the attention mechanism, and the third-level green wedge contour surface vector graphics are derived;

[0026] 2.5) Based on the road network data in the database in 1.3), the attention mechanism is used to automatically detect primary and secondary trunk road networks, rail transit networks, and expressway networks, and derive three-level corridor line vector graphics. The primary and secondary trunk road networks include urban main roads, secondary roads, and branch roads, and are considered first-order corridors. The rail transit network includes subways, light rail, trams, and maglev trains, and is considered a second-order corridor. The expressway network includes highways, ring roads, urban expressways, and tunnels, and is considered a third-order corridor.

[0027] Furthermore, step 3) is specifically as follows:

[0028] 3.1) Based on the geometric surface attribute characteristics of the three-level base surface outlines in 2.1), a Delaunay triangulation algorithm is used to perform intelligent analysis and perform overlapping contour processing to ensure: (1) there is no overlap between the three-level base surfaces; (2) the contour lines of adjacent base surfaces completely overlap. Output a new three-level base surface contour vector graphic;

[0029] 3.2) In ArcGIS, run the "Clip" command under the Geoprocessing tab, using the new third-level base surface outline from 3.1) as the input element, the third-level cluster outline from 2.2) and the third-level depression outline from 2.3) as the clipping elements, and output the final third-level base surface outline vector graphic.

[0030] 3.3) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the three-level cluster outline surface from 2.2) as the input dataset, and output a new three-level cluster outline surface vector graphic.

[0031] 3.4) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the third-level depression contour surface from 2.3) as the input dataset, and output a new third-level depression contour surface vector graphic.

[0032] 3.5) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the third-level green wedge contour surface from 2.4) as the input dataset, and output a new third-level green wedge contour surface vector graphic.

[0033] 3.6) In ArcGIS, run the "Union" command under the Geoprocessing tab, using the continuous third-level corridor lines from 2.5) as the input dataset, and output a new third-level corridor line vector graphic.

[0034] Furthermore, step 4) is specifically as follows:

[0035] 4.1) Run the "Merge" command. On one hand, the vector graphics of all surface features are used as the input dataset, including the third-level base surface, third-level clusters, third-level depressions, and third-level green wedges, and the output is an integrated vector surface. On the other hand, the vector graphics of all line features are used as the input dataset, including the third-level corridors, and the output is an integrated vector line.

[0036] 4.2) During the "vector-to-raster" graphics optimization phase, run the "PolygonToRaster_conversion" command on the integrated vector surface from 4.1) above, set the "pixel size", and output a raster image of the surface features. Also, run the "PolylineToRaster_conversion" command on the integrated vector lines from 4.1) above, set the same "pixel size", and output a raster image of the line features.

[0037] 4.3) During the "Raster to Vector" graphics optimization phase, run the "RasterToPolygon_conversion" command on the area feature raster image from 4.2) above, select the "Simplify Polygon" option, and output an optimized vector surface. Also, run the "RasterToPolyline_conversion" command on the line feature raster image from 4.2) above, select the "Simplify Polyline" option, and output an optimized vector line.

[0038] 4.4) Run the "SimplifyPolygon_cartography" command on the optimized vector surface in 4.3) above to output a simplified vector surface;

[0039] 4.5) Run the "Simplify line (Simplifyline_cartography)" command on the optimized vector lines in 4.3) above to output simplified vector lines.

[0040] Furthermore, step 5) is specifically as follows:

[0041] 5.1) Extracting the three-level base surface topology pattern, three-level cluster topology pattern, three-level depression topology pattern, and three-level green wedge topology pattern from the simplified vector surface in 4.4) above, based on the base surface, cluster, depression, and green wedge types. Furthermore, extracting the three-level corridor topology pattern from the simplified vector line in 4.5) above.

[0042] 5.2) Display the top-down sequence of the following: third-level corridors, third-level depressions, third-level clusters, third-order base surface, second-order base surface, first-order base surface, and third-level green wedges. Set different symbol colors to display and output the intelligent structural topology of the urban spatial form. This can be output as an engineering drawing using a drawing device.

[0043] Compared with the prior art, the advantages of the present invention are:

[0044] 1. This invention uses Spark distributed architecture to increase the speed of data cleaning and feature extraction by dozens of times. Its operation method is portable and applicable to large-scale dynamically updated urban spaces, enabling rapid processing of massive data.

[0045] 2. This invention uses the attention mechanism to mimic the human cognitive process, achieving automatic recognition and extraction of various urban spatial elements, while improving work efficiency and enhancing the accuracy of recognition and extraction;

[0046] 3. The present invention uses the Delaunay triangulation algorithm to achieve adaptive merging of surface elements, construct high-quality spatial topological relationships, and has strong operability;

[0047] 4. The "vector-grid-vector" dual-loop optimization iteration of the present invention achieves dimensionality reduction of complex urban spatial morphological information without losing spatial structural feature information;

[0048] 5. The intelligent structural topology method of urban spatial morphology of the present invention has large-scale dynamic adaptability and fidelity, low technical threshold, strong operability and short time consumption. It has practical application significance in the fields of urban planning and design engineering practice, urban morphology identification, transportation network optimization, landscape ecological assessment, etc., and provides a supplement to the urban digital twin system, enhancing the intelligent level of urban spatial analysis and scientific decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of an intelligent structural topology method of urban space form according to the present invention;

[0050] Figure 2 It is a schematic diagram of the topological patterns of urban space elements superimposed in order of categories;

[0051] Figure 3 It is a schematic diagram of multi-dimensional spatial data of a city;

[0052] Figure 4 It is a schematic diagram of the third-level base surface contour of a city;

[0053] Figure 5 This is a schematic diagram of the outline of the third-level cluster of a city;

[0054] Figure 6 This is a schematic diagram of the contour surface of the third-level depression in a certain city;

[0055] Figure 7 This is a schematic diagram of the third-level green wedge contour surface of a city;

[0056] Figure 8 This is a schematic diagram of the third-level corridor outline of a city;

[0057] Figure 9 It is a vector graphic diagram of a city's spatial morphological elements;

[0058] Figure 10 It is a topological diagram of the final spatial morphological structure of a certain urban area. DETAILED DESCRIPTION

[0059] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] like Figure 1 As shown, an intelligent structural topology method for urban spatial morphology includes the following steps:

[0061] 1) Obtain the urban spatial big data and establish an urban spatial database.

[0062] 1.1) Obtain the city's multi-dimensional urban spatial data, including road network, building outlines, building storeys, block outlines, river systems, green spaces and mountains, in real time through the Amap open platform OpenAPI; Figure 3 shown.

[0063] 1.2) Spark is used to partition the city's multi-dimensional spatial data into multiple partitions for distributed storage. Within the Spark distributed architecture, data inspection and geometry repair are used to remove useless, irrelevant, and out-of-range data.

[0064] 1.3) Import the processed multi-dimensional spatial data of the city into the ArcGIS geographic information system to form an urban spatial morphology vector database with dynamic update capabilities.

[0065] 2) Intelligently identify urban spatial elements by type and generate vector graphics.

[0066] 2.1) Based on the database in 1.3) above, calculate the spatial intensity data of the city and divide the spatial intensity data into three levels according to the natural break point classification method. Use the attention mechanism to automatically detect the surface space area corresponding to the three-level data interval and derive the three-level base surface contour vector graphics of the city; Figure 4 shown.

[0067] 2.2) Within the three-level base surface interval in 2.1) above, continue to automatically detect the planar spatial area corresponding to the high spatial intensity value through the attention mechanism (the single area is set to be no less than 1 square kilometer), and derive the contour surface vector graphics of the three-level cluster of the city; Figure 5 shown.

[0068] 2.3) Within the three-level base surface interval in 2.1) above, continue to automatically detect the planar spatial area corresponding to the low spatial intensity value through the attention mechanism (the single area is set to be no less than 1 square kilometer), and derive the contour surface vector graphics of the three-level depression of the city; Figure 6 shown.

[0069] 2.4) At the outer edge of the third-level base surface contour in 2.1), the concave feature surface area is automatically detected through the attention mechanism, and the third-level green wedge contour surface vector graphics of the city are derived; Figure 7 shown.

[0070] 2.5) Based on the road network data in the database of 1.3) above, the attention mechanism is used to automatically detect the primary and secondary trunk road networks, rail transit network, and expressway network, and derive the three-level corridor line vector graphics of the city. Figure 8 shown.

[0071] 3) Geometric intelligent analysis of urban space element vector graphics, and pre-processing of cropping, merging and combining.

[0072] 3.1) Based on the geometric surface attribute characteristics of the third-level base surface outlines in 2.1), a Delaunay triangulation algorithm is used to perform intelligent analysis and process overlapping contour lines to ensure: (1) there is no overlap between the third-level base surfaces; and (2) the contour lines of adjacent base surfaces completely coincide. Output a new vector graphic of the third-level base surface outline of the city;

[0073] 3.2) In ArcGIS, run the "Clip" command under the Geoprocessing tab, using the new third-level base surface outline from 3.1) as the input element, the third-level cluster outline from 2.2) and the third-level depression outline from 2.3) as the clipping elements, and output the final third-level base surface outline vector graphic of the city.

[0074] 3.3) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the third-level cluster outlines from 2.2) as the input dataset, and output a new third-level cluster outline vector graphic for the city.

[0075] 3.4) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the third-level depression contour surface from 2.3) as the input dataset, and output a new third-level depression contour surface vector graphic for the city.

[0076] 3.5) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the third-level green wedge outline surface from 2.4) as the input dataset, and output a new third-level green wedge outline vector graphic for the city.

[0077] 3.6) In ArcGIS, run the "Union" command under the Geoprocessing tab, using the continuous third-level corridor lines in 2.5) as the input dataset, and output the new third-level corridor line vector graphics of the city. Integrate the newly processed vector data in 3.2), 3.3), 3.4), 3.5), and 3.6) to display the following. Figure 9 The vector graphics of the urban spatial morphological elements are shown.

[0078] 4) Vector graphics are optimized in a double loop of “vector-raster-vector” to generate topological patterns of various urban spatial elements.

[0079] 4.1) Run the "Merge" command. On one hand, the vector graphics of all surface features are used as the input dataset, including the third-level base surface, third-level clusters, third-level depressions, and third-level green wedges, and the output is an integrated vector surface. On the other hand, the vector graphics of all line features are used as the input dataset, including the third-level corridors, and the output is an integrated vector line.

[0080] 4.2) During the "vector-to-raster" graphics optimization phase, run the "PolygonToRaster_conversion" command on the integrated vector surface from 4.1) above, setting the "Pixel Size" to 1km, to output a raster image of the surface features. Also, run the "PolylineToRaster_conversion" command on the integrated vector lines from 4.1) above, setting the "Pixel Size" to 1km, to output a raster image of the line features.

[0081] 4.3) During the "Raster to Vector" graphics optimization phase, run the "RasterToPolygon_conversion" command on the area feature raster image from 4.2) above, select the "Simplify Polygon" option, and output an optimized vector surface. Also, run the "RasterToPolyline_conversion" command on the line feature raster image from 4.2) above, select the "Simplify Polyline" option, and output an optimized vector line.

[0082] 4.4) Run the "SimplifyPolygon_cartography" command on the optimized vector surface in 4.3) above to output a simplified vector surface;

[0083] 4.5) Run the "Simplify line (Simplifyline_cartography)" command on the optimized vector lines in 4.3) above to output simplified vector lines.

[0084] 5) Superimpose the topological patterns of all spatial elements of the city in order and by category to form the topological graph of the city’s spatial morphology and intelligent structure, and output it for display.

[0085] 5.1) Extracting the three-level base surface topology pattern, three-level cluster topology pattern, three-level depression topology pattern, and three-level green wedge topology pattern from the simplified vector surface in 4.4) above, based on the base surface, cluster, depression, and green wedge types. Furthermore, extracting the three-level corridor topology pattern from the simplified vector line in 4.5) above.

[0086] 5.2) Display in sequence, such as Figure 2As shown in the figure, from top to bottom, they are: third-level corridors, third-level depressions, third-level clusters, third-order base surface, second-order base surface, first-order base surface, and third-level green wedges. Set different symbol colors to display and output the intelligent structural topology of the urban spatial form (such as Figure 10 as shown), and output as engineering drawings through drawing equipment.

[0087] The present invention adopts Spark distributed architecture to increase the speed of data cleaning and feature extraction by dozens of times. Its operation method is portable and suitable for large-scale dynamically updated urban spaces, realizing rapid processing of massive data; the present invention imitates the human cognitive process through the attention mechanism to realize automatic recognition and extraction of various urban spatial elements, while improving work efficiency and enhancing the accuracy of recognition and extraction; the present invention adopts Delaunay triangulation algorithm to realize adaptive merging of surface elements, construct high-quality spatial topological relationships, and has strong operability; the "vector-grid-vector" dual-loop optimization iteration of the present invention realizes the dimensionality reduction of complex urban spatial morphological information without losing spatial structural feature information; the intelligent structural topology method of urban spatial morphology of the present invention has large-scale dynamic adaptability and fidelity, low technical threshold, strong operability, and short time consumption. It has practical application significance in urban planning and design engineering practice, urban morphology identification, transportation network optimization, landscape ecological assessment and other fields, provides a supplement to the urban digital twin system, and enhances the intelligent level of urban spatial analysis and scientific decision-making.

Claims

1. An intelligent structural topology method for urban spatial morphology, characterized in that: The digital reconstruction of urban spatial form is achieved through the intelligent reorganization technology of multi-dimensional spatial elements. The specific steps include: 1) Obtain urban spatial big data and establish an urban spatial database; 2) Intelligently identify urban spatial elements by type and generate vector graphics; 3) Geometric intelligent analysis of urban spatial element vector graphics, and pre-processing of cropping, merging, and combining; 4) Vector graphics are optimized through a "vector-raster-vector" double loop to generate topological patterns of various urban spatial elements; 5) Superimpose the topological patterns of urban space elements in order and by category to form an intelligent structural topological graph of the urban space form, and output it for display.

2. The intelligent structural topology method for urban spatial morphology according to claim 1, characterized in that: Step 1) includes: acquiring multi-dimensional urban spatial data in real time based on the map open platform, using the Spark distributed architecture for data cleaning and feature extraction, forming urban spatial morphology vectorized data with dynamic update capabilities, inputting it into the ArcGIS geographic information system, and establishing an urban spatial database.

3. The intelligent structural topology method for urban spatial morphology according to claim 1, characterized in that: Step 2) includes: automatically detecting and identifying the five types of urban spatial elements, namely base surface, cluster, depression, green wedge, and corridor, through the attention mechanism to extract and generate vector graphics.

4. The intelligent structural topology method for urban spatial morphology according to claim 1, characterized in that: Step 3) includes: intelligently analyzing the vector graphics according to the geometric attributes of the urban spatial elements, performing geospatial preprocessing on the vector graphics, and forming new urban spatial element vector graphics; for urban spatial elements with geometric surface features, using the Delaunay triangulation algorithm for adaptive processing to generate new vector graphics layers; for urban spatial elements with geometric line features, performing joint spatial processing on the vector graphics according to continuous line segments.

5. The intelligent structural topology method for urban spatial morphology according to claim 1, characterized in that: Step 4) includes: converting the vector graphics into raster images according to the set grid accuracy, and then converting the generated raster images back into vector graphics. In this way, the vector graphics of each urban spatial element are iteratively optimized in a "vector-raster-vector" double loop. After smoothing, a set of urban spatial element topological patterns is further generated.

6. The intelligent structural topology method for urban spatial morphology according to claim 2, characterized in that: Step 1) is specifically as follows: 1.1) Real-time access to multi-dimensional urban spatial data including road networks, building outlines, building storeys, block outlines, river systems, green spaces, and mountains through the OpenAPI map open platform; 1.2) Use Spark to partition multi-dimensional urban spatial data into multiple partitions for distributed storage. Within the Spark distributed architecture, use data inspection and geometry repair to remove useless, irrelevant, and out-of-range data. 1.3) Import the processed multi-dimensional urban spatial data into the ArcGIS geographic information system to form an urban spatial morphology vector database with dynamic update capabilities.

7. The automated method for generating urban morphological topological graphics based on urban spatial elements according to claim 6, characterized in that: Step 2) is specifically as follows: 2.1) Based on the database of step 1.3), calculate spatial intensity data, and divide the spatial intensity data into three levels according to the natural break point classification method; automatically detect the planar spatial regions corresponding to the three-level data intervals through an attention mechanism, and derive the three-level base surface contour vector graphics; 2.2) Within the three-level base surface interval in step 2.1), continue to automatically detect the planar spatial region corresponding to the high spatial intensity value through the attention mechanism, and derive the three-level cluster contour surface vector graphics; 2.3) Within the third-level base surface interval in step 2.1), continue to automatically detect the planar spatial region corresponding to the low spatial intensity value through the attention mechanism, and derive the third-level depression contour surface vector graphics; 2.4) At step 2.1), the outer edge of the third-level base surface contour is automatically detected using the attention mechanism to obtain the concave feature of the surface space region, and the third-level green wedge contour surface vector graphics are derived; 2.5) Based on the road network data in the database of step 1.3), automatically detect the primary and secondary trunk road networks, rail transit network, and expressway network through an attention mechanism, and derive three-level corridor line vector graphics; the primary and secondary trunk road networks include urban main roads, secondary roads, and branch roads, which are first-order corridors; the rail transit network includes subways, light rails, trams, and maglev tracks, which are second-order corridors; and the expressway network includes highways, ring roads, urban expressways, and tunnels, which are third-order corridors.

8. The automated method for generating urban morphological topological graphics based on urban spatial elements according to claim 7, characterized in that: Step 3) is specifically as follows: 3.1) Based on the geometric surface attribute features of the three-level base surface contours in step 2.1), a Delaunay triangulation algorithm is used to perform intelligent analysis and overlap contour processing to ensure that there are no overlapping surfaces between the three-level base surfaces and that the contour lines of adjacent base surfaces completely overlap, and a new three-level base surface contour vector graphic is output; 3.2) In ArcGIS, run the "Clip" command under the Geoprocessing tab, using the new third-level base surface contour surface from step 3.1) as the input element, the third-level cluster contour surface from step 2.2) and the third-level depression contour surface from step 2.3) as the clipping elements, and output the final third-level base surface contour surface vector graphic; 3.3) In ArcGIS software, run the "Merge" command under the Geoprocessing tab, using the three-level cluster outline surface from step 2.2) as the input dataset, and output a new three-level cluster outline surface vector graphic; 3.4) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the third-level depression contour surface from step 2.3) as the input dataset, and output a new third-level depression contour surface vector graphic; 3.5) In ArcGIS, run the "Merge" command under the Geoprocessing tab, using the three-level green wedge contour surface from step 2.4) as the input dataset, and output a new three-level green wedge contour surface vector graphic; 3.6) In ArcGIS, run the "Union" command under the Geoprocessing tab, using the continuous third-level corridor lines from step 2.5) as the input dataset, and output a new third-level corridor line vector graphic.

9. The automated method for generating urban morphological topological graphics based on urban spatial elements according to claim 8, characterized in that: Step 4) is specifically as follows: 4.1) Run the "Merge" command: Use the vector graphics of all surface features as the input dataset, including the third-level base surface, third-level clusters, third-level depressions, and third-level green wedges, and output them as an integrated vector surface; use the vector graphics of all line features as the input dataset, including the third-level corridors, and output them as an integrated vector line; 4.2) In the "Vector to Raster" graphics optimization stage: Run the "Surface to Raster" command on the integrated vector surface from step 4.1) and set the "Pixel Size" to output a surface feature raster image; run the "Polyline to Raster" command on the integrated vector line from step 4.1) and set the same "Pixel Size" to output a line feature raster image; 4.3) In the "Raster to Vector" graphics optimization stage: Run the "Raster to Polygon" command on the surface feature raster image from step 4.2) and select the "Simplify Polygon" option to output an optimized vector polygon. Run the "Raster to Polyline" command on the line feature raster image from step 4.2) and select the "Simplify Polyline" option to output an optimized vector line. 4.4) Run the "Simplify Surface" command on the optimized vector surface obtained in step 4.3) to output a simplified vector surface; 4.5) Run the "Simplify Line" command on the optimized vector line of step 4.3) to output the simplified vector line.

10. The automated method for generating urban morphological topological graphics based on urban spatial elements according to claim 9, characterized in that: Step 5) is specifically as follows: 5.1) Extracting a third-level base surface topological pattern, a third-level cluster topological pattern, a third-level depression topological pattern, and a third-level green wedge topological pattern from the simplified vector surface of step 4.4) according to the base surface, cluster, depression, and green wedge types, respectively; and then extracting a third-level corridor topological pattern from the simplified vector line of step 4.5); 5.2) Display the topology of the urban space in a sequentially stacked manner, from top to bottom: third-level corridors, third-level depressions, third-level clusters, third-order base surface, second-order base surface, first-order base surface, and third-level green wedges; set different symbol colors to display and output the intelligent structural topology of the urban spatial form, and output it as an engineering drawing through a drawing device.

Images