An urban renewal area generation method, device, equipment and medium

Abstract

The application provides a city renewal area generation method and device, equipment and medium, relates to the technical field of city planning, and comprises the following steps: acquiring a plurality of source heterogeneous spatial data sets in a to-be-updated area labeled with city renewal requirements, and a plurality of reference spatial units constructed in advance; mapping the spatial data in the plurality of source heterogeneous spatial data sets to the reference spatial units, coupling the reference spatial units with multiple factors, and obtaining attribute tables of the reference spatial units; setting weights of the attribute values in the attribute tables by using a multi-attribute decision weighting model, determining comprehensive renewal potential scores corresponding to the reference spatial units, and performing screening to obtain target spatial units; and spatially aggregating the target spatial units that are adjacent but discrete, and reconstructing the target spatial units into continuous planning blocks as city renewal areas. The technical scheme of the embodiment of the application can improve the accuracy, adaptability and efficiency of city renewal area determination.

Description

Technical Field

[0001] This invention relates to the field of urban planning technology, and in particular to a method, apparatus, equipment and medium for generating urban renewal areas. Background Technology

[0002] As my country's urban development enters a new stage focused on optimizing existing resources, urban renewal has gradually become one of the core methods. In urban renewal, identifying and delineating areas with renewal value is a crucial technical link connecting macro-policy objectives with the implementation of micro-projects.

[0003] Currently, mainstream methods for identifying urban renewal areas can be categorized into three types: static indicator screening based on a single layer, multi-source indicator weighted overlay method (comprehensive scoring method), and patch identification method based on remote sensing and image processing. However, these methods still have the following technical limitations in key aspects such as data organization structure, indicator evaluation methods, and area boundary generation: different data types (plots, buildings, pipelines, POIs, etc.) are analyzed independently in their respective original layers, making data alignment and coupling difficult. Multi-source data are only visually overlaid or simply weighted and averaged, making it difficult to directly associate linear and point features with area units, resulting in the discarding of a large amount of deep spatial information. The use of fixed indicator sets and static weights makes it difficult to quickly respond to changes in urban policy orientation. The identification results are mostly discrete unit sets, requiring a large amount of manual outlining and integration, and are prone to "cutting houses and cutting land," lacking legal operability. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method, apparatus, device and medium for generating urban renewal areas. By using a heterogeneous data fusion mechanism with a reference spatial unit as the carrier, it solves the fundamental problem that multi-source data cannot be collaboratively calculated in the same dimension. By using a multi-attribute decision weighting model, it can flexibly adjust weights according to policy guidance and has strong scenario adaptability. By automatically and reasonably aggregating discrete target spatial units into continuous and regular area regions, it conforms to the business logic of contiguous development and improves feasibility.

[0005] In a first aspect, embodiments of the present invention provide a method for generating urban renewal areas, including: Obtain a multi-source heterogeneous spatial dataset labeled with urban renewal needs within the area to be updated, as well as multiple pre-constructed benchmark spatial units; The spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units, and multi-factor attribute coupling is performed on each of the reference spatial units to obtain the attribute table of each reference spatial unit. The multi-attribute decision weighting model is used to set the weights of the attribute values ​​in each attribute table to determine the comprehensive update potential score corresponding to each benchmark spatial unit; The comprehensive update potential score corresponding to each of the benchmark spatial units is compared with a preset score threshold, and the benchmark spatial units are filtered to obtain the target spatial units. Spatially adjacent but discrete target spatial units are spatially aggregated and reconstructed into continuous planning areas, serving as urban renewal zones.

[0006] In a preferred embodiment of the present invention, the above-described mapping of spatial data in the multi-source heterogeneous spatial dataset to each of the reference spatial units, and the coupling of multi-factor attributes of each of the reference spatial units to obtain an attribute table for each of the reference spatial units, includes: Using a geometric topology algorithm, the spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units to obtain the initial attribute table corresponding to each of the reference spatial units; The attribute values ​​in each of the initial attribute tables are subjected to extreme value normalization processing to obtain the attribute table of each of the reference space units.

[0007] In a preferred embodiment of the present invention, the above-described method of using a geometric topology algorithm to map spatial data in the multi-source heterogeneous spatial dataset to each of the reference spatial units, thereby obtaining an initial attribute table corresponding to each of the reference spatial units, includes: The spatial data corresponding to each label in the multi-source heterogeneous spatial dataset are standardized to obtain a standardized spatial dataset. Based on the geometric type corresponding to each spatial data in the standardized spatial dataset, each spatial data is mapped to each reference spatial unit to obtain an initial attribute table corresponding to each reference spatial unit.

[0008] In a preferred embodiment of the present invention, the above-mentioned use of a multi-attribute decision weighting model to set weights for the attribute values ​​in each attribute table and determine the comprehensive update potential score corresponding to each benchmark spatial unit includes: Construct a judgment matrix based on the urban renewal needs; The judgment matrix is ​​normalized in columns and the average row value is calculated to obtain the weight vector corresponding to each label; Consistency verification is performed on each of the weight vectors to obtain the verification results; When the verification result is successful, the attribute values ​​in each attribute table are weighted and summed using the weight vector to obtain the comprehensive update potential score corresponding to each benchmark spatial unit.

[0009] In a preferred embodiment of the present invention, the above-described consistency verification of the weight vector to obtain the verification result includes: The maximum eigenvalue is determined based on the judgment matrix and the weight vector. Based on the largest eigenvalue, determine the consistency index of the weight vector; The consistency ratio of the weight vector is determined based on the consistency index and the preset random consistency index. When the consistency ratio is less than a preset ratio threshold, the verification result is determined to be a successful verification.

[0010] In a preferred embodiment of the present invention, the above-mentioned spatial aggregation of spatially adjacent but discrete target spatial units, reconstructing them into continuous planning areas as urban renewal areas, includes: Obtain the aggregation distance threshold; Based on the aggregation distance threshold, each of the target spatial units is aggregated to obtain multiple aggregated regions; The urban renewal areas are obtained by filling holes and optimizing the shape of each aggregated area.

[0011] In a preferred embodiment of the present invention, the above-mentioned aggregation processing of each target spatial unit according to the aggregation distance threshold to obtain multiple aggregation regions includes: The buffer radius is determined based on the aggregation distance threshold. Based on the buffer radius, a positive buffering operation is performed on each of the target spatial units to obtain multiple bridging regions. Based on the buffer radius, a reverse buffering operation is performed on each of the bridging regions to obtain multiple aggregated regions.

[0012] Secondly, embodiments of the present invention also provide an urban renewal area generation device, comprising: The data acquisition module is used to acquire multi-source heterogeneous spatial datasets labeled with urban renewal needs within the area to be updated, as well as multiple pre-built benchmark spatial units; The mapping module is used to map the multi-source heterogeneous spatial dataset to each of the reference spatial units, and to perform multi-factor attribute coupling on each of the reference spatial units to obtain the attribute table of each of the reference spatial units. The scoring module is used to set weights for the attribute values ​​in each attribute table using a multi-attribute decision weighting model, and to determine the comprehensive update potential score corresponding to each benchmark spatial unit. The filtering module is used to compare the comprehensive update potential score corresponding to each of the benchmark spatial units with a preset scoring threshold, and to filter each of the benchmark spatial units to obtain the target spatial units. The reconstruction module is used to spatially aggregate spatially adjacent but discrete target spatial units and reconstruct them into continuous planning areas as urban renewal areas.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the urban renewal area generation method of the first aspect described above.

[0014] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the urban renewal area generation method of the first aspect described above.

[0015] The embodiments of the present invention bring the following beneficial effects: This invention provides a method for generating urban renewal areas. By constructing a unified benchmark spatial unit, it maps and couples multi-source heterogeneous data into an attribute table, breaking down barriers between different types of data and achieving multi-dimensional comprehensive quantitative evaluation. Simultaneously, it employs a multi-attribute decision model with configurable weights, enabling flexible adaptation to different policy orientations and rapid generation of targeted comprehensive renewal potential scores. Based on this, it spatially aggregates discrete target spatial units to generate planning areas with continuously closed boundaries, avoiding the "cutting houses and land" problem in traditional methods. This significantly improves the objectivity, automation, and operability of urban renewal area identification, effectively supporting large-scale, routine urban renewal planning decisions.

[0016] Other features and advantages of the invention will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for generating urban renewal areas provided in an embodiment of the present invention; Figure 2 A flowchart illustrating another method for generating urban renewal areas provided in an embodiment of the present invention; Figure 3 A flowchart illustrating another method for generating urban renewal areas provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an urban renewal area generation device provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] As my country's urban development enters a new stage focused on optimizing existing infrastructure, urban renewal is gradually becoming a core means of enhancing urban functions and quality. In urban renewal planning, identifying and delineating areas with renewal value is a crucial technical link connecting macro-policy objectives with the implementation of micro-projects.

[0022] Currently, the mainstream methods for identifying urban renewal areas can be summarized into three categories: static index screening based on a single layer, multi-source index weighted overlay method (comprehensive scoring method), and patch identification method based on remote sensing and image processing.

[0023] However, static index screening methods based on a single layer typically rely on a single type of data layer for evaluation, such as building construction year, density, or floor area ratio, and perform basic spatial analysis on a GIS platform. The identification logic usually involves setting thresholds for a certain type of static indicator to screen high-density, older areas as candidate areas for redevelopment. For example, if the building density in a certain area exceeds a specific value and the buildings are over 30 years old, it can be identified as a potential redevelopment area. This method is logically intuitive and computationally inexpensive, but it heavily relies on a single type of data and cannot cover other potential dimensions (such as municipal facilities, resident demands, and resource availability), resulting in extremely limited identification results and applicability. Furthermore, it lacks a unified spatial evaluation benchmark: different data types (plots, buildings, pipelines, POIs, etc.) are analyzed independently in their respective original layers, making data alignment and coupling difficult.

[0024] To improve the comprehensiveness of area identification, the multi-source indicator weighted superposition method (comprehensive scoring method) introduces statistical data and POI (Point of Interest) information to construct an evaluation system that includes multiple factors such as population density, tax revenue, land use intensity, and transportation accessibility. It employs subjective weighting, the Analytic Hierarchy Process (AHP), and entropy weighting to calculate the comprehensive score. The high-scoring areas are then identified as candidates for updated areas. While this method theoretically achieves "multi-factor comprehensive judgment," the multi-source data often comes from layers of different formats, scales, and semantic categories. In practice, the fusion process mainly relies on visual overlay or independent weighted calculations, lacking true coupling in spatial structure. Especially at the spatial object level, it is difficult to form a unified evaluation dimension among point, line, and surface data, resulting in information fragmentation and isolated indicators.

[0025] In recent years, some methods have attempted to directly extract urban area texture, green coverage, and building density from remote sensing images, and then use image processing methods such as convolutional neural networks (CNNs) and clustering algorithms to classify and identify patches, thereby determining the boundaries of old areas. This patch identification method based on remote sensing and image processing has a certain ability to automatically extract spatial features, making it suitable for rapid large-scale scanning and identification. However, it lacks support from multi-source attribute information, and the evaluation results are often superficially similar but not truly relevant. For example, an area with poor green coverage may appear as "low-vitality" in a remote sensing image, but it may actually be a planned development area or industrial land with low renewal priority. Therefore, identification methods based solely on image texture lack attribute-level support, resulting in a high misjudgment rate.

[0026] Based on this, the urban renewal area generation method provided by this embodiment of the invention realizes multi-dimensional comprehensive quantitative evaluation by constructing a unified benchmark spatial unit. It can flexibly adapt to different policy orientations and quickly generate targeted comprehensive renewal potential scores, avoiding the problem of "cutting houses and land" in traditional methods. It significantly improves the objectivity, automation and operability of urban renewal area identification, and effectively supports large-scale and normalized urban renewal planning decisions.

[0027] To facilitate understanding of this embodiment, a method for generating urban renewal areas disclosed in this embodiment of the invention will first be described in detail.

[0028] Example 1 This invention provides a method for generating urban renewal areas. Figure 1 This is a flowchart illustrating a method for generating urban renewal areas, as provided in an embodiment of the present invention. Figure 1 As shown, the method for generating urban renewal areas may include the following steps: Step S101: Obtain a multi-source heterogeneous spatial dataset labeled with urban renewal needs within the area to be updated, as well as multiple pre-built benchmark spatial units.

[0029] Areas awaiting renewal refer to existing spaces within a city that may require functional upgrades, infrastructure improvements, or environmental remediation. Examples include an administrative district, street, or specific planning study area. Urban renewal needs refer to the factors that need to be considered in urban renewal projects. Examples include risk hazards, resident demands, idle resources, and value enhancement. Furthermore, during the collection process, multi-source heterogeneous spatial datasets can be collected based on urban renewal needs, including at least: problem-oriented data to help identify areas with current risks and hazards in the city (such as data on aging pipelines and the distribution of dilapidated buildings), with corresponding risk and hazard labels; demand-oriented data to help identify renewal needs from the perspective of citizens or the market (such as data on resident complaints or concentrated locations of renewal intentions), with corresponding resident demand labels; resource-oriented data to help identify usable but not yet effectively utilized spatial resources (such as data on approved but not supplied land and data on inefficient and idle resources), with corresponding idle resource labels; and value-oriented data to help identify areas with potential for value enhancement (such as land value data, population and economic level data), with corresponding value enhancement labels, forming spatial data that reflects four dimensions: risks and hazards, resident demands, idle resources, and value enhancement. Spatial data in multi-source heterogeneous spatial datasets can originate from different collection channels (housing and construction, planning, petitions, statistics, etc.). Therefore, spatial data with different labels can have different formats (Shapefile, GeoJSON, Excel, raster) and different geometric types (points, lines, polygons, raster). Each spatial data can correspond to a spatial coordinate, used to indicate the collection location of that spatial data within the area to be updated. A baseline spatial unit refers to a polygonal feature consisting of the smallest independent land use units (such as parcels, plots, ownership units), covering the entire area to be updated, and possessing a unique code and closed geometric boundary.

[0030] Specifically, the first step is to delineate the urban area to be assessed (the area to be updated), and construct a unified evaluation framework. This involves selecting the smallest independent land use unit covering the area as the baseline spatial unit based on the actual business situation of the area to be updated. Each baseline spatial unit must have a closed geometric boundary and a unique identifier, and the combination of all baseline spatial units must cover the entire area to be updated without overlap. Then, based on urban renewal needs, spatial data reflecting four aspects of urban renewal—risks and hazards, resident demands, idle resources, and value enhancement—is collected. This spatial data varies in format, source, and geometric type, forming a multi-source heterogeneous dataset.

[0031] Step S102: Map the spatial data in the multi-source heterogeneous spatial dataset to each of the reference spatial units, and perform multi-factor attribute coupling on each of the reference spatial units to obtain the attribute table of each of the reference spatial units.

[0032] Spatial data from a multi-source heterogeneous spatial dataset is used as attribute values ​​for reference spatial units to achieve spatial data mapping. Specifically, for each piece of spatial data in the multi-source heterogeneous spatial dataset, its corresponding reference spatial unit is queried based on its spatial coordinates in the spatial coordinate system, and this spatial data is used as the attribute value of the corresponding reference spatial unit. Each reference spatial unit can correspond to at least one piece of spatial data, and the at least one piece of spatial data corresponding to the reference spatial unit is used as the attribute table corresponding to that reference spatial unit. Specifically, since the reference spatial unit is a planar feature, when the spatial coordinates of spatial data fall within the area of ​​a reference spatial unit, the reference spatial unit that the data falls into is used as the reference spatial unit corresponding to that spatial data.

[0033] Step S103: Use a multi-attribute decision weighting model to set weights for the attribute values ​​in each attribute table, and determine the comprehensive update potential score corresponding to each benchmark spatial unit.

[0034] The multi-attribute decision-weighted model assigns weights to each attribute value in the corresponding attribute table for each spatial baseline unit, obtaining a weight value for each attribute value. By setting the weight values, the importance of each attribute value is determined. For each baseline spatial unit, the weighted sum of each attribute value is calculated to obtain the comprehensive update potential score corresponding to the baseline spatial unit. In this embodiment of the invention, the multi-attribute decision-weighted model can use analytic hierarchy process (AHP) to assign weights to the attribute values ​​in the attribute table, or it can use pre-set weight values ​​to query the weight values ​​corresponding to attribute values.

[0035] Specifically, a multi-attribute decision weighted model is used to set weights for the attribute values ​​in each attribute table to determine the comprehensive renewal potential score corresponding to each benchmark spatial unit. This includes: constructing a judgment matrix based on the urban renewal needs; performing column normalization and row average calculation on the judgment matrix to obtain the weight vector corresponding to each label; performing consistency verification on each weight vector to obtain the verification result; and when the verification result is successful, using the weight vector to perform a weighted summation of the attribute values ​​in each attribute table to obtain the comprehensive renewal potential score corresponding to each benchmark spatial unit.

[0036] For example, the tags for urban renewal needs include potential risks, resident demands, idle resources, and value enhancement. A pairwise comparison judgment matrix is ​​constructed based on these tags. For instance, if there are four tags for urban renewal needs, a matrix can be constructed... The judgment matrix is ​​further constructed by comparing each label with multiple data types. For example, the "risk / hazard" label corresponds to data on aging pipelines and dilapidated housing distribution; the "resident demands" label corresponds to resident complaints; the "idle resources" label corresponds to data on approved but unsupplied land and inefficient idle resources; and the "value enhancement" label corresponds to land value data, population, and economic level data. The resulting judgment matrix can be... The judgment matrix can be constructed using a 1-9 basic scaling method to quantify expert experience. Specifically, a value of 1 is assigned when two labels are considered equally important; a value of 5 is assigned when two labels are clearly important; a value of 9 is assigned when two labels are extremely important, and so on. Then, the judgment matrix is ​​normalized column-wise, and the average value is calculated for each row to obtain the weight vector for each label. As the objective weighting coefficient for each label, the detailed formula is as follows:

[0037] in, To determine the value assigned to the i-th row and j-th column of the matrix, To determine the value assigned to the k-th row and j-th column of the matrix, Let be the weight vector of the i-th label.

[0038] At the same time, for the weight vector The calculation results need to calculate the consistency ratio (CR). Consistency verification is passed only if the CR is less than a preset threshold, meaning the verification result is successful. At this point, it is confirmed that the weight allocation of each label has logical consistency; otherwise, the judgment matrix needs to be corrected.

[0039] When the verification result is successful, the attribute values ​​in each attribute table are weighted and summed using a linear weighted summation formula and a weight vector to obtain a comprehensive renewal potential score for each baseline spatial unit. This score quantitatively characterizes the suitability of the unit for urban renewal.

[0040] Furthermore, the consistency verification of the weight vector is performed to obtain the verification result, including: determining the largest eigenvalue based on the judgment matrix and the weight vector; determining the consistency index of the weight vector based on the largest eigenvalue; determining the consistency ratio of the weight vector based on the consistency index and a preset random consistency index; and determining the verification result as passed when the consistency ratio is less than a preset ratio threshold.

[0041] Specifically, the largest eigenvalue can be calculated using the following formula. :

[0042] in, for The judgment matrix, Representation matrix with vector The product of the first Each component, vector This refers to the weight vector of all labels. , forming a vector.

[0043] The consistency index can be calculated using the following formula. :

[0044] The consistency ratio can be calculated using the following formula. :

[0045] RI stands for Random Index, which is obtained by querying the RI standard value table.

[0046] If the consistency ratio is less than a preset threshold (e.g., 0.1), the verification result is determined to be successful. If the consistency ratio is greater than or equal to the preset threshold (e.g., 0.1), the verification result is determined to be unsuccessful, and the judgment matrix needs to be redefined.

[0047] Step S104: Compare the comprehensive update potential score corresponding to each of the benchmark spatial units with the preset score threshold, and filter each of the benchmark spatial units to obtain the target spatial units.

[0048] Specifically, the comprehensive update potential score corresponding to each baseline spatial unit can be compared with a preset scoring threshold. When the comprehensive update potential score is greater than or equal to the preset scoring threshold, the baseline spatial unit is used as the target spatial unit. The preset scoring threshold can be determined according to the actual situation.

[0049] Step S105: Spatially aggregate spatially adjacent but discrete target spatial units and reconstruct them into continuous planning areas as urban renewal areas.

[0050] Specifically, a buffer bridging algorithm can be used to aggregate discrete target spatial units, merging nearby units to form continuous planning areas, which serve as urban renewal regions. It's understood that there can be multiple urban renewal regions. Furthermore, the center points of the target spatial units can be used as input, and the DBSCAN algorithm can be used to cluster them based on density reachability, forming multiple target spatial unit clusters. For each cluster, a bounding box or convex hull is generated, forming continuous planning areas, which also serve as urban renewal regions.

[0051] This invention provides a method for generating urban renewal areas. By constructing a unified benchmark spatial unit, it maps and couples multi-source heterogeneous data into an attribute table, breaking down barriers between different types of data and achieving multi-dimensional comprehensive quantitative evaluation. Simultaneously, it employs a multi-attribute decision model with configurable weights, enabling flexible adaptation to different policy orientations and rapid generation of targeted comprehensive renewal potential scores. Based on this, it spatially aggregates discrete target spatial units to generate planning areas with continuously closed boundaries, avoiding the "cutting houses and land" problem in traditional methods. This significantly improves the objectivity, automation, and operability of urban renewal area identification, effectively supporting large-scale, routine urban renewal planning decisions.

[0052] Example 2 This invention also provides another method for generating urban renewal areas; this method is implemented based on the method in the above embodiments; the method focuses on describing the specific implementation of mapping spatial data in the multi-source heterogeneous spatial dataset to each of the benchmark spatial units, and coupling multi-factor attributes of each of the benchmark spatial units to obtain the attribute table of each of the benchmark spatial units.

[0053] Figure 2 A flowchart of another urban renewal area generation method provided by an embodiment of the present invention is shown below. Figure 2 As shown, the method for generating urban renewal areas may include the following steps: Step S201: Obtain a multi-source heterogeneous spatial dataset labeled with urban renewal needs within the area to be updated, as well as multiple pre-built benchmark spatial units.

[0054] For example, taking the old city area of ​​a certain city (approximately 5 square kilometers) as an example, the multi-source heterogeneous spatial dataset covers spatial data oriented towards four directions: risk, demand, resources, and value. Risk-oriented data includes linear data (Shapefile format) showing the distribution of old gas pipelines, and point data (GeoJSON format) showing the locations of dilapidated building surveys. Demand-oriented data includes point data (CSV format, including coordinates) showing 12345 complaint work orders, originally in Excel address text format, which needs to be converted into point data with coordinates through geocoding, and point data (CSV format, including coordinates) showing urban health check satisfaction surveys. Resource-oriented data includes areal data (GeoPackage format) showing inefficient industrial land, and areal data (Shapefile format) showing approved but not yet supplied land. Value-oriented data includes point data (Excel spreadsheet containing latitude and longitude coordinates) showing property appraisal prices. These data cover various file types such as .shp, .geojson, .gpkg, .xlsx, and .tif in terms of format, and simultaneously include points (dangerous buildings, complaints, assessment prices), lines (gas pipeline networks), and areas (inefficient industrial land) in terms of geometric types. In terms of coordinate reference, they include both WGS84 latitude and longitude and CGCS2000 projected coordinate systems, fully reflecting the dual characteristics of "multi-source" (cross-departmental and cross-system) and "heterogeneous" (different formats, different structures, and different dimensions). The embodiments of this invention, through the construction of reference spatial units and geometric topological mapping, unify and collect these diverse spatial data into the attribute table of 620 reference spatial units.

[0055] Step S202: Using a geometric topology algorithm, the spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units to obtain the initial attribute table corresponding to each of the reference spatial units.

[0056] For isal data, both isal data (such as inefficient industrial land, approved but not yet supplied land, ecological protection zones, etc.) and the reference spatial unit are isal geometry. The relationship between the two is not a simple "containment" or "being contained"; more often, it is "partial overlap." That is, a large isal data may span multiple reference spatial units, and a reference spatial unit may contain multiple isal data. Therefore, the most accurate mapping method is face-to-face overlay intersection operation: the two isal layers are geometrically intersected (Intersect), generating a series of overlapping faces, and then the proportion of the area of ​​each overlapping face to the total area of ​​its corresponding reference spatial unit is calculated. This proportion is used as a weight to assign the specified attribute value of the isal data to the reference spatial unit proportionally, as the attribute value corresponding to the isal data. For example, if an inefficient industrial patch has an area of ​​100 hectares, and its overlapping area with the reference unit U-0105 is 20 hectares, then the proportion of inefficient industry in U-0105 is 20%, and the unit receives 20% of the attribute value of that patch.

[0057] Linear data (such as gas pipelines, roads, water systems, and power lines) typically interact with baseline spatial units by "passing through" or "following the boundary." The key to mapping linear features is line-to-surface clipping: first, the linear data is clipped from the surface boundary of the baseline spatial unit, extracting the line segment that falls within each baseline spatial unit; then, the geometric length of this segment is calculated (for multiple line segments, all segments are summed). In this way, each baseline unit obtains a "total length of a certain type of linear feature" index as the attribute value corresponding to that current data. In another possible implementation, the length or density of the pipeline network within the baseline spatial unit can be calculated to account for the influence of the surrounding environment.

[0058] The relationship between point data (such as locations of dilapidated buildings, complaint work orders, POIs, sampling points, etc.) and reference cells is relatively simple and direct: a point either falls inside a reference cell or outside it (if it happens to fall on the boundary, it needs to be assigned to an adjacent cell according to the agreement). The core operation is to determine whether a point is inside a polygon. A commonly used algorithm is the ray casting algorithm: a ray is emitted from the target point in any direction, and the number of intersections between the ray and the polygon boundary is counted. An odd number of intersections are inside, and an even number are outside. After the determination is completed, a "counting statistics" is performed on all reference cells, that is, the number of points falling into each reference cell is counted, which is used as the attribute value corresponding to the point data. In another possible implementation, for point data, instead of directly counting the number of points falling into each cell, kernel density analysis or inverse distance weighted interpolation is used to generate a continuous surface, and then the raster value or raster average value of the center point of the reference spatial cell is extracted as the index.

[0059] For spatial data in a multi-source heterogeneous spatial dataset, each spatial data point can be mapped using one of the three methods mentioned above to determine its corresponding reference spatial unit and obtain the attribute values ​​of that reference spatial unit. These attribute values ​​are then organized using the unique code of the reference spatial unit as the row index and the name of each spatial data point as the column index, thus forming the initial attribute table. At this point, the values ​​in the table still carry their respective physical dimensions; for example, the proportion of inefficient industry is a dimensionless ratio between 0 and 1, pipeline density is meters per hectare, dilapidated building density is units per hectare, and GDP per unit area is 10,000 yuan per km², etc.

[0060] Furthermore, using a geometric topology algorithm, the spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units to obtain an initial attribute table corresponding to each of the reference spatial units. This includes: standardizing the spatial data corresponding to each label in the multi-source heterogeneous spatial dataset to obtain a standardized spatial dataset; and mapping each of the spatial data to each of the reference spatial units according to the geometric type corresponding to each of the spatial data in the standardized spatial dataset to obtain an initial attribute table corresponding to each of the reference spatial units.

[0061] Furthermore, for the collected multi-source heterogeneous spatial datasets, spatial reference unification can be performed on the spatial data of each label, that is, the spatial coordinates of the spatial data of each label can be uniformly transformed to the same spatial coordinate system. Then, data cleaning is performed, and topology checks and outlier removal are carried out on the spatial data of each label. That is, the geometric integrity of the spatial data is verified, common geometric errors are checked and corrected, such as self-intersection of line segments, unclosed polygon loops, duplicate nodes, gaps or overlaps, etc., to ensure the mathematical validity and spatial logical consistency of the geometry, and to identify and deal with obvious erroneous records in the data, such as coordinates exceeding the range of the area to be updated, and geometric types not matching attribute semantics. Finally, the spatial data after coordinate unification, topology repair and outlier removal are reorganized according to a unified attribute field structure and data format to construct a standardized spatial dataset with accurate spatial location and unified attribute structure. For example, all areal data uniformly use the same field name "AREA" to store area and "CODE" to store feature code; all point data uniformly add a "SOURCE" field to indicate the data source; and all linear data uniformly add a "LENGTH" field to store feature length. Through this operation, the spatial data, which were originally of varying formats and with disorganized fields, were integrated into a standardized spatial dataset with a clear structure and standardized fields. For each spatial data point in the standardized dataset, it can be mapped using one of three mapping methods: point data, area data, or line data, to determine the corresponding reference spatial unit and obtain the attribute value of that reference spatial unit. These attribute values ​​are then organized using the unique code of the reference spatial unit as the row index and the name of each spatial data point as the column index, thus forming the initial attribute table.

[0062] Coordinate unification ensures spatial correspondence accuracy across different layers during overlay analysis. Topology repair prevents computational crashes or result distortions caused by geometric errors, enabling subsequent geometric operations such as overlay intersection, line-to-surface clipping, and point containment checks to be performed stably and accurately. Outlier removal eliminates invalid data caused by collection errors or data entry mistakes, avoiding the "garbage in, garbage out" problem and ensuring the credibility of the evaluation results. The well-structured, standardized spatial dataset simplifies the mapping logic, eliminating the need to write separate processing branches for each data format, thus improving the algorithm's versatility and maintainability.

[0063] Step S203: Perform extreme value normalization processing on the attribute values ​​in each of the initial attribute tables to obtain the attribute table of each reference space unit.

[0064] Extreme value normalization is performed on the attribute values ​​in the initial attribute table, linearly mapping the attribute values ​​with different physical dimensions to the standard interval [0, 100]. Specifically, for the attribute value of each data name, the normalization process usually adopts the following formula:

[0065] in, For the first The attribute values ​​of each reference spatial unit are normalized standard scores; For the first The attribute values ​​of each reference spatial unit; This is the minimum value among all attribute values ​​of the reference space units. These are the maximum attribute values ​​among all reference space units. Among them, [the following can be defined]: Corrections are made, such as using the 95th or 97.5th percentile of the attribute values ​​of all reference spatial units as a replacement, and assigning a score of 100 to any unit exceeding this upper limit. For example, taking the attribute value named "pipeline density" as an example, the attribute value range of the 620 reference spatial units across the entire region is 0~23.5 m / ha. The attribute value of reference spatial unit U-0105 is 8.0 m / ha, and its standard score is:

[0066] Step S204: Use a multi-attribute decision weighting model to set weights for the attribute values ​​in each attribute table, and determine the comprehensive update potential score corresponding to each benchmark spatial unit.

[0067] Step S205: Compare the comprehensive update potential score corresponding to each of the benchmark spatial units with the preset score threshold, and filter each of the benchmark spatial units to obtain the target spatial units.

[0068] Step S206: Spatially aggregate spatially adjacent but discrete target spatial units and reconstruct them into continuous planning areas as urban renewal areas.

[0069] The urban renewal area generation method provided in this invention constructs a benchmark spatial unit and, based on computational geometry and spatial topology algorithms (including planar element overlay analysis, line-plane clipping, polygon interior point judgment, etc.), maps spatial data originally distributed across multiple layers (one layer corresponds to one data name) and possessing different spatial morphologies to a unified benchmark spatial unit. This achieves structured aggregation of spatial attributes, breaks down spatial barriers between data from different vertical domains, and enables data from different sources and with different spatial morphologies to be weighted and calculated within a single mathematical model. This provides a more comprehensive and objective reflection of the complex needs of urban renewal, solves the technical challenge of multi-source heterogeneous spatial data being unable to be collaboratively calculated in the same dimension, and realizes a comprehensive quantitative evaluation of urban characteristics. By using the extreme value normalization method, urban indicators of different dimensions (such as the degree of infrastructure aging, density of residents' demands, intensity of resource utilization, land value, etc.) are uniformly mapped to a fixed interval. The attribute values ​​are weighted through a multi-attribute decision weighting model, which allows users to freely configure factor weights according to policy guidance and generate a comprehensive update potential score. This allows for rapid response to changes in urban governance guidance without modifying the underlying data and algorithm, thereby improving the model's adaptability, reusability, and interpretability of evaluation results.

[0070] Example 3 This invention also provides another method for generating urban renewal areas; this method is implemented based on the method in the above embodiments; this method focuses on spatially aggregating spatially adjacent but discrete target spatial units and reconstructing them into continuous planning areas, as a specific implementation method for urban renewal areas.

[0071] Figure 3 A flowchart of another urban renewal area generation method provided by an embodiment of the present invention is shown below. Figure 3 As shown, the method for generating urban renewal areas may include the following steps: Step S301: Obtain a multi-source heterogeneous spatial dataset labeled with urban renewal needs within the area to be updated, as well as multiple pre-built benchmark spatial units.

[0072] Step S302: Map the spatial data in the multi-source heterogeneous spatial dataset to each of the reference spatial units, and perform multi-factor attribute coupling on each of the reference spatial units to obtain the attribute table of each of the reference spatial units.

[0073] Step S303: Use a multi-attribute decision weighting model to set weights for the attribute values ​​in each attribute table, and determine the comprehensive update potential score corresponding to each benchmark spatial unit.

[0074] Step S304: Compare the comprehensive update potential score corresponding to each of the benchmark spatial units with the preset score threshold, and filter each of the benchmark spatial units to obtain the target spatial units. Step S305: Obtain the aggregation distance threshold.

[0075] The setting of the aggregation distance threshold should adhere to the principles of urban road fabric and spatial connectivity. It can be based on physical constraints related to road width levels, referencing the hierarchical width standards of the urban road network within the area to be updated. The aggregation distance threshold D should be set to satisfy... ,in The average width of urban branch roads in the area to be updated (usually about 15 meters). This refers to the average width of the main urban roads or expressways in the area to be updated (typically greater than 40 meters). This setting ensures that the buffer algorithm can "cross" and stitch together plots separated by smaller gaps such as internal alleys and side roads, forming contiguous spaces. At the same time, when encountering wide physical barriers such as main urban roads and rivers, the aggregation is naturally blocked because the distance exceeds the threshold, thus ensuring that the generated area boundaries strictly conform to the urban macro road network framework, forming a reasonable boundary range that is easy to manage in a coordinated manner.

[0076] Step S306: Based on the aggregation distance threshold, aggregate each of the target spatial units to obtain multiple aggregate regions.

[0077] Specifically, according to the aggregation distance threshold, each target spatial unit may be classified using a graph theory-based connectivity clustering or density clustering algorithm. When the distance between any two target spatial units (the distance between the boundaries of the two target spatial units or the distance between the centers of the two target spatial units) is less than or equal to the aggregation distance threshold, the two target spatial units are classified into the same category. Further, the graph theory-based connectivity clustering takes all target spatial units as nodes, and establishes an empty graph structure. For any two target spatial units, it is determined whether they should be connected according to a preset spatial adjacency rule. The adjacency rule may be that the distance between the geometric centers or boundaries of two target spatial units is less than the set aggregation distance threshold D. An undirected edge is established between two target spatial units that satisfy the adjacency rule, and is recorded in the graph structure. After this stage, a complete adjacency graph is formed. Breadth-First Search (BFS) or Depth-First Search (DFS) is selected for connected component search according to the structural characteristics of the adjacency graph. Each connected component corresponds to at least one target spatial unit that should be aggregated into one aggregation region. For all target spatial units in each connected component, their geometric shapes are merged into a complete areal feature. The merging method is to perform a geometric Union operation on all units, eliminate internal boundaries, and form a continuous aggregation region. Further, the density clustering algorithm (DBSCAN algorithm) may extract the geometric center point coordinates of each target spatial unit, and convert the unit set into a point set. Two core parameters of DBSCAN are set: Eps (neighborhood radius) and MinPts (minimum number of points). In the urban renewal scenario, the value of Eps is consistent with the aggregation distance threshold D (that is, when the distance between the center points of the units is less than D, it is regarded as density-connected), and MinPts is usually 1 or 2 — a value of 1 means that even a single isolated unit can form its own area, and a value of 2 means that at least two units are close to each other to form an area (isolated noise units can be filtered out). Traverse all points of the target spatial unit: if the number of points in the Eps neighborhood of a certain point is ≥ MinPts, the point is marked as a core point, and with this point as the starting point, all points density-reachable therefrom are recursively found through breadth-first search to form a cluster; if the number of points in the Eps neighborhood of a certain point is < MinPts, but the point is located in the neighborhood of a certain core point, the point is marked as a boundary point and classified into the cluster where the core point is located; if a point is neither a core point nor a boundary point, it is marked as a noise point (that is, an isolated unit, which does not form an area). For each cluster, it is necessary to convert the discrete point set into a continuous areal region by means of a bounding box or a convex hull, that is, to form an aggregation region.

[0078] Furthermore, based on the aggregation distance threshold, each of the target spatial units is aggregated to obtain multiple aggregated regions, including: determining a buffer radius based on the aggregation distance threshold; performing a forward buffering operation on each of the target spatial units based on the buffer radius to obtain multiple bridging regions; and performing a reverse buffering operation on each of the bridging regions based on the buffer radius to obtain multiple aggregated regions.

[0079] A buffer zone is generated for each target spatial cell, using half the aggregation distance threshold (D / 2) as the buffer radius. These buffer zones not only cover the target spatial cell itself but also extend outwards by a distance of D / 2. When the spatial interval between two target cells is less than D / 2, the outwardly expanding buffer zones of the two cells geometrically overlap in the middle region. This overlapping region is the "bridging zone"—it acts like a virtual bridge, physically connecting the two originally separate cells geometrically.

[0080] The buffers of all target spatial units are treated as a whole, and a geometric merging operation is performed. All overlapping buffers are merged into a connected large polygon, and the common boundaries of the overlapping parts are eliminated. At this point, the previously independent target spatial units and the spaces between them are all integrated into a complete large geometry, forming a bridging region.

[0081] For the merged large polygon and the bridging region, a reverse buffer is performed with the same buffer radius of D / 2, i.e., shrinking inwards towards the interior of the large polygon to obtain the aggregated region. This operation "retraces" the boundary of the large polygon from its expanded position to a position close to the edge of the target spatial unit, essentially stripping away the extra expanded portion. However, the key point is that because the width of the bridging region is at least D / 2 (composed of two D / 2 buffers superimposed), after reverse buffering D / 2, the bridging region is not completely eliminated, leaving a sufficiently wide connection channel. This restores the boundary's fit to the target spatial unit contour while preserving the connections established by the forward buffer.

[0082] The aggregation technology based on the buffer bridging principle solves the problem of discrete assessment units being difficult to form large-scale implementation areas, improving the feasibility of planning results. It can automatically integrate spatially adjacent but physically discontinuous scattered plots into "areas" with closed boundaries, continuous forms, and a certain scale effect. This allows the subsequently output urban renewal areas to directly correspond to the scope of implementable planning projects, significantly reducing the workload of manually delineating area boundaries. At the same time, the reverse buffering operation ensures that the boundaries of the special areas fit the outline of the target spatial units, guaranteeing that the boundaries of the generated urban renewal areas strictly extend along the land ownership boundaries, avoiding "cutting houses" or "cutting land," and ensuring that the identified urban renewal areas have direct operability in terms of land ownership and law, reducing the difficulty of confirming rights in the subsequent implementation process.

[0083] Step S307: Fill the holes and optimize the shape of each aggregated area to obtain the urban renewal area.

[0084] Calculate the area of ​​all enclosed blank areas (i.e., spaces not covered by any target spatial units but completely surrounded by the outer contour of the aggregation area) within the aggregation region. For each blank area, compare its area with a preset "minimum hole area threshold": if the area is less than the threshold (e.g., 500㎡), it is considered an "internal defect"—it could be a small green space, a power distribution room site, or a small plot of land that was not selected due to a low score. These enclosed blank areas do not need to be retained separately within the framework of the overall contiguous development of the area and should be filled into the area to maintain its integrity and avoid the awkward situation of "a useless little hole embedded in a complete area." If the area is greater than the threshold, it is considered a true "external gap"—it may correspond to external roads, rivers, or other functional zones and should be retained as the natural boundary of the area. The boundary of the aggregation region is formed by piecing together the boundaries of each reference spatial unit, and there may be some small jagged edges (such as protrusions or indentations of individual reference units). Without altering the main area and ownership boundaries of the region, boundary simplification algorithms (such as Douglas-Peucker polyline simplification) or mathematical morphology opening operations can be used to eliminate excessively small bumps and depressions, making the region boundaries smoother and more regular, thus improving the aesthetics of the map and the visualization of the planning text.

[0085] The urban renewal area generation method provided in this invention introduces an aggregation distance threshold setting mechanism based on urban road level width constraints. This allows the aggregation scale to adaptively match the urban spatial texture, ensuring that large physical barriers such as main roads and rivers naturally block aggregation, while small intervals such as side roads and alleys are reasonably crossed. This generates aggregation areas whose boundaries highly match the urban road network framework. Furthermore, a buffer bridging algorithm based on forward buffering, fusion, and reverse buffering is used to generate aggregation areas. This transforms the tedious traditional task of manually tracing and merging each block into fully automated geometric calculations. This not only reduces the workload from several days to minutes, but more importantly, ensures that the aggregated boundary strictly follows the reference spatial unit. The meta-extension fundamentally avoids the "cutting buildings and cutting land" problem of traditional methods, which involves dividing buildings or mixing different ownership plots, making the output directly operable in terms of law and property rights. The hole filling and morphological optimization steps further eliminate micro-blank areas caused by low-scoring units or small public spaces within the area, making the final output of the urban renewal area continuous and complete with regular and clear boundaries. It can directly meet the data requirements of actual planning business such as project establishment, land acquisition and demolition plan preparation, and land reserve plan formulation, significantly reducing the coordination costs in the later confirmation of rights and implementation process, and truly realizing high-quality automated transformation from discrete evaluation results to implementable planning scope.

[0086] Example 4 Corresponding to the above method embodiments, this invention provides an urban renewal area generation device. Figure 4 This is a schematic diagram of the structure of an urban renewal area generation device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the urban renewal area generation device may include: The data acquisition module 401 is used to acquire a multi-source heterogeneous spatial dataset labeled with urban renewal needs within the area to be updated, as well as multiple pre-built benchmark spatial units. The mapping module 402 is used to map the multi-source heterogeneous spatial dataset to each of the reference spatial units, and to perform multi-factor attribute coupling on each of the reference spatial units to obtain the attribute table of each of the reference spatial units. The scoring module 403 is used to set the weights of the attribute values ​​in each attribute table using a multi-attribute decision weighting model, and to determine the comprehensive update potential score corresponding to each benchmark spatial unit. The filtering module 404 is used to compare the comprehensive update potential score corresponding to each of the benchmark spatial units with a preset scoring threshold, and to filter each of the benchmark spatial units to obtain the target spatial units. Reconstruction module 405 is used to spatially aggregate spatially adjacent but discrete target spatial units and reconstruct them into continuous planning areas as urban renewal areas.

[0087] This invention provides an urban renewal area generation device that, by constructing a unified benchmark spatial unit, maps and couples multi-source heterogeneous data into an attribute table, breaking down barriers between different types of data and achieving multi-dimensional comprehensive quantitative evaluation. Simultaneously, it employs a multi-attribute decision model with configurable weights, enabling flexible adaptation to different policy orientations and rapid generation of targeted comprehensive renewal potential scores. Based on this, it spatially aggregates discrete target spatial units to generate planning areas with continuously closed boundaries, avoiding the "cutting houses and cutting land" problem in traditional methods. This significantly improves the objectivity, automation, and operability of urban renewal area identification, effectively supporting large-scale, routine urban renewal planning decisions.

[0088] In some embodiments, the mapping module 402 is further configured to: Using a geometric topology algorithm, the spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units to obtain the initial attribute table corresponding to each of the reference spatial units; The attribute values ​​in each of the initial attribute tables are subjected to extreme value normalization processing to obtain the attribute table of each of the reference space units.

[0089] In some embodiments, the mapping module 402 is further configured to: The spatial data corresponding to each label in the multi-source heterogeneous spatial dataset are standardized to obtain a standardized spatial dataset. Based on the geometric type corresponding to each spatial data in the standardized spatial dataset, each spatial data is mapped to each reference spatial unit to obtain an initial attribute table corresponding to each reference spatial unit.

[0090] In some embodiments, the scoring module 403 is further configured to: Construct a judgment matrix based on the urban renewal needs; The judgment matrix is ​​normalized in columns and the average row value is calculated to obtain the weight vector corresponding to each label; Consistency verification is performed on each of the weight vectors to obtain the verification results; When the verification result is successful, the attribute values ​​in each attribute table are weighted and summed using the weight vector to obtain the comprehensive update potential score corresponding to each benchmark spatial unit.

[0091] In some embodiments, the scoring module 403 is further configured to: The maximum eigenvalue is determined based on the judgment matrix and the weight vector. Based on the largest eigenvalue, determine the consistency index of the weight vector; The consistency ratio of the weight vector is determined based on the consistency index and the preset random consistency index. When the consistency ratio is less than a preset ratio threshold, the verification result is determined to be a successful verification.

[0092] In some embodiments, the reconstruction module 405 is further configured to: Obtain the aggregation distance threshold; Based on the aggregation distance threshold, each of the target spatial units is aggregated to obtain multiple aggregated regions; The urban renewal areas are obtained by filling holes and optimizing the shape of each aggregated area.

[0093] In some embodiments, the reconstruction module 405 is further configured to: The buffer radius is determined based on the aggregation distance threshold. Based on the buffer radius, a positive buffering operation is performed on each of the target spatial units to obtain multiple bridging regions. Based on the buffer radius, a reverse buffering operation is performed on each of the bridging regions to obtain multiple aggregated regions.

[0094] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0095] Example 5 This invention also provides an electronic device for running the above-described urban renewal area generation method; see [link to related documentation]. Figure 5 The diagram shows the structure of an electronic device, which includes a memory 500 and a processor 501. The memory 500 is used to store one or more computer instructions, which are executed by the processor 501 to implement the above-mentioned urban renewal area generation method.

[0096] Furthermore, Figure 5 The electronic device shown also includes a bus 502 and a communication interface 503. The processor 501, the communication interface 503 and the memory 500 are connected via the bus 502.

[0097] The memory 500 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 503 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 502 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0098] Processor 501 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 501 or by instructions in software form. Processor 501 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 500, and processor 501 reads information from memory 500 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0099] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the above-described urban renewal area generation method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0100] The computer program product for the method of generating urban renewal areas provided in this embodiment of the invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0101] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0102] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0103] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0104] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0105] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for generating urban renewal areas, characterized in that, include: Obtain a multi-source heterogeneous spatial dataset labeled with urban renewal needs within the area to be updated, as well as multiple pre-constructed benchmark spatial units; The spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units, and multi-factor attribute coupling is performed on each of the reference spatial units to obtain the attribute table of each reference spatial unit. The multi-attribute decision weighting model is used to set the weights of the attribute values ​​in each attribute table to determine the comprehensive update potential score corresponding to each benchmark spatial unit; The comprehensive update potential score corresponding to each of the benchmark spatial units is compared with a preset score threshold, and the benchmark spatial units are filtered to obtain the target spatial units. Spatially adjacent but discrete target spatial units are spatially aggregated and reconstructed into continuous planning areas, serving as urban renewal zones.

2. The method according to claim 1, characterized in that, The spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the aforementioned benchmark spatial units. Multi-factor attribute coupling is then performed on each of the benchmark spatial units to obtain an attribute table for each benchmark spatial unit, including: Using a geometric topology algorithm, the spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units to obtain the initial attribute table corresponding to each of the reference spatial units; The attribute values ​​in each of the initial attribute tables are subjected to extreme value normalization processing to obtain the attribute table of each of the reference space units.

3. The method according to claim 2, characterized in that, Using a geometric topology algorithm, spatial data in the multi-source heterogeneous spatial dataset is mapped to each of the reference spatial units, resulting in an initial attribute table corresponding to each reference spatial unit, including: The spatial data corresponding to each label in the multi-source heterogeneous spatial dataset are standardized to obtain a standardized spatial dataset. Based on the geometric type corresponding to each spatial data in the standardized spatial dataset, each spatial data is mapped to each reference spatial unit to obtain an initial attribute table corresponding to each reference spatial unit.

4. The method according to claim 1, characterized in that, A multi-attribute decision weighting model is used to assign weights to the attribute values ​​in each attribute table to determine the comprehensive update potential score corresponding to each baseline spatial unit, including: Construct a judgment matrix based on the urban renewal needs; The judgment matrix is ​​normalized in columns and the average row value is calculated to obtain the weight vector corresponding to each label; Consistency verification is performed on each of the weight vectors to obtain the verification results; When the verification result is successful, the attribute values ​​in each attribute table are weighted and summed using the weight vector to obtain the comprehensive update potential score corresponding to each benchmark spatial unit.

5. The method according to claim 4, characterized in that, The consistency of the weight vector is verified to obtain the verification result, including: The maximum eigenvalue is determined based on the judgment matrix and the weight vector. Based on the largest eigenvalue, determine the consistency index of the weight vector; The consistency ratio of the weight vector is determined based on the consistency index and the preset random consistency index. When the consistency ratio is less than a preset ratio threshold, the verification result is determined to be a successful verification.

6. The method according to claim 1, characterized in that, Spatially adjacent but discrete target spatial units are spatially aggregated and reconstructed into continuous planning areas as urban renewal zones, including: Obtain the aggregation distance threshold; Based on the aggregation distance threshold, each of the target spatial units is aggregated to obtain multiple aggregated regions; The urban renewal areas are obtained by filling holes and optimizing the shape of each aggregated area.

7. The method according to claim 6, characterized in that, Based on the aggregation distance threshold, each of the target spatial units is aggregated to obtain multiple aggregated regions, including: The buffer radius is determined based on the aggregation distance threshold. Based on the buffer radius, a positive buffering operation is performed on each of the target spatial units to obtain multiple bridging regions. Based on the buffer radius, a reverse buffering operation is performed on each of the bridging regions to obtain multiple aggregated regions.

8. A device for generating urban renewal areas, characterized in that, include: The data acquisition module is used to acquire multi-source heterogeneous spatial datasets labeled with urban renewal needs within the area to be updated, as well as multiple pre-built benchmark spatial units; The mapping module is used to map the multi-source heterogeneous spatial dataset to each of the reference spatial units, and to perform multi-factor attribute coupling on each of the reference spatial units to obtain the attribute table of each of the reference spatial units. The scoring module is used to set weights for the attribute values ​​in each attribute table using a multi-attribute decision weighting model, and to determine the comprehensive update potential score corresponding to each benchmark spatial unit. The filtering module is used to compare the comprehensive update potential score corresponding to each of the benchmark spatial units with a preset scoring threshold, and to filter each of the benchmark spatial units to obtain the target spatial units. The reconstruction module is used to spatially aggregate spatially adjacent but discrete target spatial units and reconstruct them into continuous planning areas as urban renewal areas.

9. An electronic device, characterized in that, The method includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the urban renewal area generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the urban renewal area generation method according to any one of claims 1 to 7.

Images