Data processing method and device based on smart city

Abstract

The invention provides a data processing method and device based on a smart city, and relates to the technical field of data processing.The method comprises the steps that a city-level spatial data base is constructed through oblique photography of an unmanned aerial vehicle, and a unified and real spatial foundation is formed by generating a live-action three-dimensional model, a digital orthoimage and a digital elevation model; on this basis, a building base and a building white model are extracted, spatial logic verification is carried out on multi-source business basic data, a standard address system stably associated with a building three-dimensional entity is further constructed, precise spatial anchoring of governance objects such as population, houses and units is achieved, and the method is suitable for mass production. And finally, the associated data is uniformly converged to a city information model platform, and reliable and updatable spatial data support is provided for smart city application. According to the invention, the timeliness of smart city data processing in a dynamic earth surface deformation scene can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a data processing method and device based on a smart city. BACKGROUND

[0002] The existing smart city data processing usually takes multi-department business systems and industry platforms as data sources, collects business data such as population, housing, units, roads, and pipe networks in a decentralized manner, and completes preliminary sorting and application within each system. Overall, it relies more on business attribute association rather than unified spatial constraints. Data is often aggregated through interface connection or manual comparison. There is a lack of unified constraints on coordinate systems, address standards, coding rules, and update mechanisms, resulting in inconsistent locations, inconsistent semantics, or repeated expressions of the same object in different systems. At the same time, the association between spatial data and business data is mostly limited to two-dimensional layer superimposition or text address matching, lacking a stable anchoring mechanism centered on three-dimensional spatial entities. This makes the data fusion result highly sensitive to scene changes and data updates, making it difficult to support fine governance, cross-department collaboration, and rapid response in complex emergency scenarios. Overall, it still mainly relies on "data aggregation and display", and has not yet formed a data-driven smart city processing system centered on unified spatial foundation and systematic data governance.

[0003] In addition, in the prior art, when geological disasters or extreme weather cause ground deformation and change the road traffic boundaries and water body river shorelines in a short period of time, the existing smart city data processing system usually relies on pre-constructed static road traffic data, water body river data, and standard address data. These data have a long update cycle after generation, and lack real-time or quasi-real-time linkage verification mechanisms with digital elevation models and digital orthophotos, resulting in new digital elevation models and digital orthophotos generated or updated after a disaster reflecting the true topographic changes, while existing road traffic data and water body river data still maintain their pre-disaster spatial positions, thus forming systematic misplacement in space. In this case, the prior art mostly uses simple layer superimposition or manual verification to identify abnormalities, making it difficult to timely and automatically transmit topographic changes to road traffic relationships, water body boundaries, and standard address spatial anchors. This in turn causes standard address units to remain anchored at the original road centerline or building base position, even if this position has been submerged by water, collapsed or become an inaccessible area. The system still cannot identify and correct this spatial distortion in a short period of time, resulting in serious risks such as positioning errors, path planning failures, and resource delivery biases in emergency command, personnel evacuation, and rescue dispatch operations based on distorted address spatial carriers at critical moments. This is a major deficiency of the prior art in dynamic ground change scenarios.

[0004] Therefore, there is a need for a method to improve the timeliness of smart city data processing in dynamic ground deformation scenarios. Summary of the Invention

[0005] This invention provides a data processing method and apparatus based on smart cities, which can improve the timeliness of smart city data processing in dynamic surface deformation scenarios.

[0006] A first aspect of the present invention provides a data processing method based on smart cities, the method comprising: Basic data collection was carried out around the city-level spatial data base, and raw image data under the preset coordinate system was obtained by UAV oblique photogrammetry. Point cloud data of a real-world 3D model is generated based on the original image data through aerial triangulation and dense matching. Digital orthophotos and digital elevation models are generated synchronously under the constraints of the point cloud data. Using the real-world 3D model as a reference, the building outline is extracted to form building base data, and building white model data is generated based on the building base data; To meet the needs of urban digital public infrastructure construction, the preset coordinate system is introduced into the multi-source business basic data, and the spatial logical relationship between the multi-source business basic data, the building base data, and the terrain data is verified based on the digital orthophoto and the digital elevation model. Based on the aforementioned spatial logical relationship, standard address units are generated on the basis of road spatial entities around a unified standard address system. Spatial association is established between the standard address units and the building white model data to form an address space carrier. The actual population, actual housing, and actual units are associated with the address space carrier to form associated data; The associated data is processed according to a unified data format specification and data slicing rules, aggregated into the city information model platform, and output to smart city applications.

[0007] In a second aspect of the invention, a data processing apparatus based on a smart city is provided. The apparatus is used to execute a data processing method based on a smart city as described in any of the preceding embodiments. The apparatus includes an acquisition module, a processing module, and an output module, wherein: The acquisition module is used to collect basic data around the city-level spatial data base and acquire raw image data under a preset coordinate system through UAV oblique photogrammetry. The processing module is used to generate point cloud data of a real-world 3D model based on the original image data through aerial triangulation and dense matching. The processing module is used to synchronously generate digital orthophotos and digital elevation models under the constraints of the point cloud data. The processing module is used to extract the building outline to form building base data based on the real scene 3D model, and generate building white model data based on the building base data; The processing module is used to introduce multi-source business basic data into the preset coordinate system based on the construction needs of urban digital public infrastructure, and to verify the spatial logical relationship between the multi-source business basic data and the building base data and terrain data based on the digital orthophoto and the digital elevation model. The processing module is used to generate standard address units on the basis of road spatial entities based on the spatial logical relationship and around the unified standard address system, and to establish a spatial association relationship between the standard address units and the building white model data to form an address space carrier. The processing module is used to associate the actual population, actual housing, and actual units with the address space carrier to form associated data; The output module is used to process the associated data according to a unified data format specification and data slicing rules, aggregate it to the city information model platform, and output it to smart city applications.

[0008] In a third aspect of the invention, an electronic device is provided, including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any of the preceding embodiments.

[0009] In a fourth aspect of the invention, a non-transitory computer-readable storage medium is provided, the computer-readable storage medium storing instructions that, when executed, perform the method as described in any of the preceding claims.

[0010] In summary, one or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages: 1. This invention constructs a city-level spatial data foundation starting with UAV oblique photography, enabling original images, real-world 3D models, digital orthophotos, and digital elevation models to form a highly consistent spatial representation under the same preset coordinate system. Based on this, multi-source business foundation data, building base data, and building white model data are uniformly incorporated into a spatial logic verification framework. This ensures that key spatial elements such as roads, waterways, buildings, and standard addresses no longer rely on static attribute associations but are constrained by the latest landform reflected in digital orthophotos and digital elevation models. When dynamic landform deformation occurs, new images and point cloud data can quickly generate updated digital orthophotos and digital elevation models, instantly triggering automatic verification and correction of the planar position, elevation relationship, and spatial topology of multi-source business foundation data. This synchronously adjusts the spatial anchoring relationships of road spatial entities, standard address units, and address spatial carriers, ensuring that the spatial relationships of actual population, actual buildings, and actual units are updated promptly with landform changes, avoiding reliance on manual verification or periodic update mechanisms. This significantly improves the timeliness of data processing and business response capabilities of smart cities in dynamic landform deformation scenarios such as geological disasters and extreme weather.

[0011] 2. By uniformly constraining outliers, mismatched points, and point cloud density at the point cloud data level, a stable and reliable spatial benchmark is formed. Under this spatial benchmark, digital orthophotos and digital elevation models are generated simultaneously, ensuring that the planar position representation of the image and the elevation representation of the terrain are consistent in origin and mutually verified. This avoids the spatial deviation problem caused by the separate generation of orthophotos and elevation models, and provides consistent two-dimensional and three-dimensional basic data support for subsequent spatial logic verification.

[0012] 3. By introducing a combined processing method of aerial triangulation and dense matching, the exterior orientation elements of the image are accurately calculated under the joint constraints of image control points and image connectivity. Based on this, spatially continuous and density-controlled point cloud data is formed, so that the real-scene 3D model not only has the accuracy of real spatial position and attitude, but also reflects the continuous structural characteristics of urban space, providing a high-precision 3D geometric foundation for subsequent orthorectification, terrain modeling and building modeling.

[0013] 4. By extracting the building outline and generating white model data of the building using the real-world 3D model as a reference, the building's planar footprint, elevation benchmark, and 3D volume are all derived from the constraints of real spatial data. Furthermore, through outline consistency verification and spatial consistency callback correction mechanisms, systematic deviations between the building model and the real scene are avoided, thereby constructing a building spatial entity that can stably support address anchoring and the association of governance objects.

[0014] 5. By uniformly introducing multi-source business basic data into a preset coordinate system and performing spatial logic verification on it from multiple dimensions such as planar location, elevation relationship, spatial topology and terrain constraints, the multi-source business basic data no longer depends solely on the consistency of business attributes, but is subject to the joint constraints of digital orthophotos, digital elevation models and building base data, thereby significantly reducing the risk of spatial misalignment and semantic conflict caused by historical data lag or departmental differences.

[0015] 6. By generating standard address units based on road spatial entities after completing spatial logic verification, and spatially associating the standard address units with building base data and building white model data, the address is upgraded from a traditional road text description to a spatial carrier that can be accurately located in three-dimensional space. This improves the stability and traceability of the address in dynamic scenarios and provides a reliable spatial anchor for emergency command and refined management. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a data processing method based on smart cities disclosed in an embodiment of the present invention; Figure 2 This is a schematic diagram of a data processing device based on a smart city disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention.

[0017] Explanation of reference numerals in the attached drawings: 201, acquisition module; 202, processing module; 203, output module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Implementation

[0018] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0019] In the description of the embodiments of the present invention, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0020] In the description of the embodiments of the present invention, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0021] Existing smart city data processing technologies generally rely on multi-departmental business systems and industry platforms as data sources, focusing on business attribute associations and interface-based aggregation. They lack a unified spatial foundation, leading to inconsistent coordinate systems, address standards, and coding rules. This results in inconsistencies in the spatial location and semantic expression of the same object across different systems. Furthermore, data fusion often remains at the level of two-dimensional overlay or text matching, lacking a stable anchoring mechanism centered on three-dimensional spatial entities. In dynamic scenarios involving geological disasters or extreme weather-induced surface deformation, existing data such as roads, waterways, and standard addresses are prone to systematic misalignment with the actual post-disaster terrain due to delayed updates and lack of linkage verification with digital elevation models and digital orthophotos. Current technologies primarily rely on manual verification or static layer comparisons, making it difficult to promptly transmit terrain changes to road traffic relationships and address spatial anchors. Consequently, emergency command and rescue dispatch operate based on distorted address spatial carriers, exposing the significant deficiencies of the current smart city data processing system in terms of unified spatial constraints and dynamic change response capabilities.

[0022] This embodiment discloses a data processing method based on smart cities, referring to... Figure 1 This includes the following steps S110-S180: S110 conducts basic data collection around a city-level spatial data base, acquiring raw image data under a preset coordinate system through UAV oblique photogrammetry.

[0023] This invention discloses a data processing method based on smart cities, which is applied to a server. The server includes, but is not limited to, electronic devices such as mobile phones, tablets, wearable devices, and PCs (Personal Computers), and can also be a backend server running a data processing method based on smart cities. The server can be implemented using a standalone server or a server cluster composed of multiple servers.

[0024] When collecting basic data around the city-level spatial data base, the spatial boundary of the target area is first determined based on the construction scope of the city's digital public infrastructure. Under the constraints of the spatial boundary, a pre-set coordinate system and elevation benchmark are uniformly selected so that all subsequent collected spatial data have a consistent spatial reference basis in terms of planar position and elevation expression, thereby avoiding the inherent inconsistency problem of coordinate benchmarks between multiple sources of data.

[0025] After determining the target area and the preset coordinate system, an aerial photography scheme is designed for the UAV oblique photogrammetry task. By combining the terrain undulation characteristics, building density distribution and urban spatial complexity of the target area, the combination of UAV flight altitude, forward overlap, lateral overlap and oblique photography angle is determined so that the aerial photography parameters can meet the requirements of image resolution and geometric stability for subsequent 3D reconstruction and spatial analysis while ensuring coverage integrity.

[0026] After completing the aerial photography scheme design, image control points are set up around the preset coordinate system. High-precision spatial coordinates of the image control points are obtained by using global satellite navigation positioning measurement. The distribution rationality of the image control points is verified, so that the image control points form a control network with uniform coverage and sufficient spatial constraint in the target area, thereby providing reliable external constraint conditions for the spatial positioning of the original image data.

[0027] After completing the layout and measurement of image control points, the UAV is controlled to perform oblique photogrammetry according to the aerial photography plan. By simultaneously acquiring oblique images covering the target area from multiple perspectives, the same ground object is imaged multiple times under different perspective conditions, thereby obtaining a set of original image data with unified temporal characteristics. During the acquisition process, the attitude parameters and time information corresponding to the images are recorded to support the subsequent calculation of image geometric relationships.

[0028] After completing the UAV oblique photogrammetry operation, the acquired raw image data is subjected to quality checks and screening. By verifying the image sharpness, exposure consistency, viewpoint integrity, and image coverage continuity, abnormal image frames with blurriness, occlusion, or insufficient overlap are removed to ensure that the raw image data participating in subsequent processing are consistent in imaging quality and temporal conditions.

[0029] After the raw image data quality screening is completed, the raw image data and the image control point measurement results are jointly organized, and the initial spatial position of the image is constrained based on the preset coordinate system. This ensures that the raw image data has a unified spatial benchmark and clear geometric constraints before entering the subsequent aerial triangulation and 3D reconstruction processing, thus forming basic image data results that can directly support the construction of a city-level spatial data base.

[0030] S120 generates point cloud data for a real-world 3D model based on raw image data through aerial triangulation and dense matching.

[0031] In one possible implementation, point cloud data for a real-world 3D model is generated based on the original image data through aerial triangulation and dense matching. Specifically, this includes: removing anomalous images from the original image data that are blurred, occluded, or have temporal shifts to obtain image control results; performing aerial triangulation on the original image data based on a preset coordinate system and the image control results, extracting corresponding feature points between images and establishing image connectivity, and combining image control points to perform joint adjustment of the image exterior orientation elements, thereby determining the spatial position and attitude parameters of each image in the preset coordinate system, and obtaining image exterior orientation elements; and performing dense matching preparation processing on the original image data based on the image exterior orientation elements. By analyzing and filtering image perspective differences, overlapping area ranges, and baseline lengths, image combination relationships that meet the dense matching conditions are determined. Based on the image combination relationships, dense matching processing is performed on the original image data. By performing point-by-point matching on corresponding areas of multi-view images at the pixel scale, a set of matching points with spatial correspondence is obtained. Combining the image exterior orientation elements, the matching points of the matching point set are back-calculated to their three-dimensional spatial positions in a preset coordinate system, thus forming an initial three-dimensional point set. Point cloud consistency constraint processing is performed on the initial three-dimensional point set. By identifying and eliminating abnormal points caused by occlusion, reflection, or matching errors, and correcting the point cloud density distribution and spatial continuity, point cloud data is generated.

[0032] Specifically, when performing abnormal image removal on the original image data, an image quality assessment record is established for each image frame. This record includes at least a sharpness evaluation value, an occlusion ratio evaluation value, and a time offset evaluation value. Image frames with sharpness evaluation values ​​below a sharpness threshold, occlusion ratio evaluation values ​​above an occlusion threshold, or time offset evaluation values ​​above a time offset threshold are identified as abnormal images and removed, thus forming a valid image set for subsequent aerial triangulation. The sharpness evaluation value characterizes the recognizable detail and texture of the image; the occlusion ratio evaluation value characterizes the proportion of the image area covered by clouds, strong shadows, or foreground objects; the time offset evaluation value characterizes the deviation of the image capture time from a unified temporal reference; and the image control results characterize the spatial coordinates of image control points in a preset coordinate system and their correspondence with image frames. Image control points are ground control points deployed within the target area and whose precise coordinates are obtained through global satellite navigation positioning measurements. The result after removing abnormal images is defined as the valid image set, while the image control results are limited to the set of control point coordinates and their correspondences.

[0033] When performing aerial triangulation based on a preset coordinate system and image control results, corresponding feature points are extracted within the overlapping areas of the effective image set, and image connectivity is established. Corresponding feature points refer to image feature points that correspond to the same ground feature in different images. Image connectivity is used to characterize the overlap and matching constraints between images. Based on this, image control points are introduced as absolute spatial constraints into the joint adjustment solution. The joint adjustment solution is used to simultaneously solve the spatial position parameters and attitude parameters of each image, as well as the three-dimensional spatial position corresponding to the corresponding feature points, under the meaning of minimizing the reprojection residual. This ensures that the image exterior orientation elements have a unified spatial reference under the preset coordinate system. The spatial position parameters characterize the three-dimensional coordinates of the image's photographic center under the preset coordinate system, and the attitude parameters characterize the rotation relationship of the image camera coordinate system relative to the preset coordinate system. The image exterior orientation elements are the set composed of the spatial position parameters and attitude parameters. To quantify the constraint objective of the joint adjustment, let the observed pixel coordinates of the corresponding feature points in the i-th image be... The three-dimensional points are determined by the exterior orientation elements of the image and the interior orientation parameters of the camera. The predicted pixel coordinates are obtained by projecting them onto the image plane. The sum of squared reprojection residuals is used as the optimization objective to minimize the overall error. The calculation formula is as follows:

[0034] in, This indicates the values ​​of the objective function in the joint adjustment. This indicates the number of corresponding feature points that participated in the adjustment. This represents the set of image indices where the k-th feature point with the same name is visible. This represents the observed pixel coordinates of the k-th feature point in the i-th image. This represents the predicted pixel coordinates obtained by projecting the image's exterior orientation elements. This represents a coefficient indicating the constraint weights of the control points on the control image, and its value is non-negative. Indicates the number of control points on the image. This represents the three-dimensional coordinates of the j-th image control point obtained from the adjustment solution. This represents the three-dimensional coordinates of the j-th image control point obtained by global satellite navigation positioning measurement. The formula minimizes the pixel residual between image observation and projection prediction simultaneously and incorporates the image control point coordinate deviation into the penalty term, so that the solution results satisfy both image geometric consistency and absolute spatial consistency, thereby obtaining stable image exterior orientation elements.

[0035] When performing dense matching preparation based on image exterior orientation elements, image pairs in the effective image set are geometrically matched. The selection criteria include image viewpoint difference, overlap area range, and baseline length. Image viewpoint difference is used to characterize the angle between the observation directions of two images to avoid insensitivity due to too small a viewpoint difference or severe occlusion due to too large a viewpoint difference. Overlap area range is used to characterize the common coverage ratio of the two images on the ground projection to ensure sufficient matching area. Baseline length is used to characterize the spatial distance between the photographic centers of the two images to provide sufficient stereo intersection geometry. In practice, the image viewpoint difference is obtained by first calculating the line vector connecting the photographic centers of the image pair and the line-of-sight vector based on the image exterior orientation elements. The overlap area range is obtained by intersecting the ground coverage polygons of the two images in a preset coordinate system. At the same time, the baseline length is calculated from the coordinates of the photographic centers of the two images. Then, image pairs that do not meet the conditions are filtered out according to a preset threshold range. The set of retained image pairs is the image combination relationship. The image combination relationship is used to limit the candidate image set for subsequent dense matching, so that dense matching is carried out under controllable geometric conditions, thereby reducing the probability of mismatch and improving the spatial uniformity of point cloud density.

[0036] When performing dense matching based on image combination relationships, point-by-point matching is performed on each image pair or multi-view image group in the image combination relationship at the pixel scale. Dense matching is used to establish cross-image correspondences for as many pixels as possible in the overlapping area, so that the 3D reconstruction is expanded from sparse points to high-density points. In practice, for each reference image, pixels are traversed in its overlapping area at a preset step size or pixel blocks are traversed by superpixel blocks, and matching positions that satisfy similarity constraints are searched in the corresponding target image. Similarity constraints can be jointly limited by grayscale consistency, gradient consistency, or local texture consistency. At the same time, epipolar constraints are introduced to narrow the search range. Epipolar constraints are determined by the image exterior orientation elements and are used to reduce the matching search from a two-dimensional region to a one-dimensional line segment. The matching point set is obtained through the above matching process. The matching point set refers to the pixel pair or pixel group that has established a correspondence between at least two images. It contains the pixel coordinates of the reference image, the pixel coordinates of the target image, and the matching confidence value. The matching confidence value is used to characterize the reliability of the matching result and is used for subsequent outlier removal.

[0037] When converting the set of matching points into an initial 3D point set by combining the exterior orientation elements of the images, a spatial intersection solution is performed on each matching record in the set. This spatial intersection solution is used to determine the 3D spatial position of ground features in a preset coordinate system using the line-of-sight intersection points of multi-view images. Specifically, the matching pixel coordinates are converted into a normalized line-of-sight direction in the camera coordinate system based on the exterior orientation elements of the images. This line-of-sight direction is then transformed into a spatial ray in the preset coordinate system using attitude parameters. Ideally, the spatial rays corresponding to two or more images intersect at a single point. In the presence of noise and errors, the 3D point closest to each ray is obtained using least squares as the intersection result, thus yielding the initial 3D point set. This initial 3D point set consists of a large number of 3D points, each corresponding to a matching record in the set and possessing 3D coordinates and a confidence attribute. The confidence attribute can be determined by the matching confidence value and the intersection residual. To clarify the intersection process, two spatial rays can be represented as... and ,in The coordinates of the center of the two images are given. Given a unit vector corresponding to the line-of-sight direction, the parameters that minimize the distance between the two rays are solved. The midpoint is taken as the three-dimensional point coordinate, thereby transforming the two-dimensional matching relationship into a three-dimensional spatial expression, ensuring that the initial three-dimensional point set maintains the same geometric constraint relationship with the image exterior orientation elements under the preset coordinate system.

[0038] When performing point cloud consistency constraint processing on the initial 3D point set, outliers are first identified based on spatial statistical features. By calculating the distance distribution, local density, and local normal consistency between each 3D point and its neighboring 3D points, 3D points that significantly deviate from the neighborhood structure are identified as outliers and removed. Sources of outliers include incorrect correspondences caused by occlusion, texture confusion caused by reflection, and intersection deviations caused by matching errors. Subsequently, point cloud density distribution correction is performed on the retained points. This is done by constructing a voxel mesh or a 2D mesh in a preset coordinate system and counting the number of points in each mesh. Downsampling is performed on areas with excessively high point counts to avoid redundancy, while matching backfilling or interpolation is triggered on areas with excessively low point counts. To avoid voids, the spatial uniformity of point cloud density is improved. Simultaneously, spatial continuity of the point cloud is corrected by detecting faults caused by occlusion or weak texture features and smoothing the boundaries of these faults, ensuring a continuous representation of the point cloud on building and ground surfaces. After outlier removal, density distribution correction, and spatial continuity correction, the output is point cloud data that meets a unified spatial benchmark, stable geometry, and can be used for subsequent orthorectification and elevation inversion. The point cloud data refers to a set of three-dimensional points obtained through consistency constraints, containing three-dimensional coordinates, point density identifiers, and quality identifiers, used to characterize the reliability and usability of each three-dimensional point in spatial representation.

[0039] S130 generates digital orthophotos and digital elevation models simultaneously under point cloud data constraints.

[0040] In one possible implementation, digital orthophotos and digital elevation models are generated simultaneously under point cloud data constraints. Specifically, this includes: obtaining a unified spatial constraint benchmark by identifying and removing outliers, correcting mismatched points in occluded areas, and unifying the point cloud density distribution; under this unified spatial constraint benchmark, based on the geometric correspondence between the point cloud data and the original image data, using surface elevation and feature height information from the point cloud data to perform pixel-level correction of tilt distortion in the original image data, thereby generating a digital orthophoto in a preset coordinate system; based on the elevation distribution characteristics in the point cloud data, performing feature point and ground point separation processing on the point cloud data, identifying building points and vegetation points and retaining the ground point set to form ground point cloud data for terrain representation; and performing spatial interpolation and gridding processing on the ground point cloud data to generate a digital elevation model.

[0041] Specifically, before applying spatial constraints to the point cloud data, quality shaping processing is performed to ensure the spatial reliability of the point cloud data. By statistically analyzing the spatial distribution characteristics of each 3D point in the point cloud data, outliers that deviate significantly from their neighboring points in terms of spatial location and height are identified and removed from the point cloud data. Simultaneously, for mismatched points caused by multi-view matching occlusion relationships or reflection interference, 3D points with abrupt height changes and lacking neighborhood support within the occluded area are corrected or deleted, taking into account the height continuity and surface normal consistency of the point cloud data in the local area. After completing the outlier processing, density distribution unification processing is performed on the point cloud data. By constructing a spatial grid under a preset coordinate system and adjusting the point density of the point cloud in each grid cell, the point cloud data forms a uniform, continuous, and stable spatial reference that can constrain subsequent image correction and terrain inversion within the overall spatial range. This allows the processed point cloud data to serve as a unified spatial constraint source for the generation of subsequent digital orthophotos and digital elevation models.

[0042] When generating digital orthophotos under unified spatial constraints, orthorectification is performed on the original image data based on the established geometric correspondence between point cloud data and original image data. By utilizing the real surface elevation information and the height information of buildings and other features reflected in the point cloud data, the tilt distortion caused by terrain undulations and feature heights in the original image is corrected pixel by pixel. Specifically, each pixel in the original image is projected along its corresponding imaging line of sight to the three-dimensional surface position expressed by the point cloud data, and the pixel is spatially repositioned according to the real spatial coordinates of the three-dimensional surface position in the preset coordinate system. This eliminates the displacement error caused by oblique photography, so that the corrected image corresponds one-to-one with the real surface in planar position, and finally forms a digital orthophoto that can truly reflect the distribution of surface texture in the preset coordinate system.

[0043] Before generating the digital elevation model, feature points and ground points are separated based on the elevation distribution characteristics in the point cloud data. By analyzing the height differences, slope changes, and surface roughness characteristics of the point cloud data in the local neighborhood, non-ground points belonging to features such as buildings and vegetation are identified and removed from the point cloud data, retaining only the set of ground points that can continuously express the topographic relief characteristics. Ground points are used to represent the spatial location of exposed or close to the ground surface, and their elevation changes should meet the topographic continuity constraints. Building points and vegetation points, on the other hand, exhibit abrupt changes in height relative to the surrounding ground points. Stable distinction is achieved through the above feature differences, thereby obtaining ground point cloud data for subsequent topographic modeling.

[0044] Spatial interpolation and gridding are performed on ground point cloud data. The ground point cloud data is projected onto a regular grid structure in a preset coordinate system, and interpolation calculations are performed in each grid cell based on the elevation values ​​of neighboring ground points to generate an elevation raster that continuously covers the target area. Spatial interpolation is used to complete the elevation information in sparse or unevenly distributed areas of ground points, so that the elevation expression remains continuous in space. Gridding is used to transform discrete ground point cloud data into a set of regularly arranged elevation cells, thereby forming a digital elevation model that can systematically express the topographic relief characteristics.

[0045] S140 uses a real-world 3D model as a reference to extract the building outline to form the building base data, and generates white model data of the building based on the building base data.

[0046] In one possible implementation, building silhouettes are extracted using a real-world 3D model as a reference to form building base data. Building white model data is then generated based on this base data. Specifically, this includes: performing building separation enhancement processing on the real-world 3D model to identify height abrupt changes, normal vector differences, and slope differences between the building and the ground surface to form a set of candidate building regions; performing building silhouette extraction processing based on the candidate region set, generating a set of building silhouette lines through planar projection, boundary recognition, and topology verification, and performing silhouette consistency verification in conjunction with digital orthophotos; constructing building base data based on the building silhouette line set, forming a set of building base surfaces through closed surface construction and planar topology verification, and completing ground elevation fitting in conjunction with a digital elevation model; performing building height analysis processing based on the building base data and the real-world 3D model, calculating the building height value through the height difference between the roof point set and the ground point set; performing 3D extrusion based on the building base data and the building height value to generate building white model data; performing spatial consistency verification on the building white model data and the real-world 3D model, and correcting the building silhouette and building height when deviations exceed limits, thereby outputting building base data and building white model data consistent with the real-world 3D model.

[0047] Specifically, when performing building separation enhancement processing on the real-scene 3D model, joint discrimination is performed based on the distinguishable features of the surface of ground features and the surface of the ground in the spatial structure of the real-scene 3D model. Local height gradients are calculated on the point cloud or mesh surface of the real-scene 3D model to identify height change zones. The local height gradient is used to characterize the rate of elevation change of adjacent locations and to characterize the abrupt boundary at the junction of the building's exterior wall and the ground surface. At the same time, local normal vectors are calculated on the surface of the real-scene 3D model and the angle between adjacent normal vectors is compared. The normal vector is used to characterize the local surface orientation, and the difference in normal vectors is used to characterize the significant change in orientation between the building's exterior wall and the ground surface. Local slopes are calculated in the terrain undulation area and the slope change amplitude is compared. The slope difference is used to characterize the geometric difference between the ground slope and the building's roof or platform surface. Spatial segments that meet the height change, normal vector difference, and slope difference are aggregated into connected regions, and hole completion and boundary smoothing are performed on the connected regions to form a set of candidate building regions that can be used for contour extraction. The set of candidate building regions is used to limit the possible area occupied by the building and reduce the probability of subsequent false detections.

[0048] When performing building contour extraction based on a set of candidate building regions, the set of candidate building regions is first projected onto a horizontal plane in a preset coordinate system. The planar projection is used to convert the three-dimensional candidate regions into a two-dimensional footprint representation for boundary extraction. Then, the outer boundary is identified in the projection result to form an initial boundary line. Boundary identification is used to extract the outer envelope of the point or surface set. Topological verification is performed on the initial boundary line. Topological verification is used to check the closure, self-intersection, and overlap with adjacent boundaries of the boundary line, thereby eliminating geometric anomalies caused by breaks, burrs, and self-intersections and forming a set of building contour lines. After obtaining the set of building contour lines, contour consistency verification is performed in conjunction with digital orthophotos. By superimposing the set of building contour lines onto the digital orthophotos and detecting the gradient distribution of roof texture boundaries and shadow boundaries near the contour lines, the position of the contour lines is kept consistent with the roof texture boundaries, and false boundaries caused by tree canopy occlusion or strong shadows are eliminated, thereby improving the consistency between the set of building contour lines and the actual building footprint.

[0049] When constructing building base data based on a set of building outlines, each closed outline in the set is converted into a closed planar feature to form a set of building base surfaces. This closed planar feature construction transforms linear boundaries into planar geometry that can represent the building's footprint. Planar topology checks are then performed on the set of building base surfaces to verify for overlaps, gaps, holes, and boundary inconsistencies, ensuring that the set of building base surfaces is mutually exclusive and complete in spatial representation. After completing the planar topology check, ground elevation fitting is performed using a digital elevation model (DEM). By sampling the ground elevation within the coverage area of ​​the building base surface set in the DEM and statistically fitting the sampling results, the set of building base surfaces obtains a ground elevation benchmark that conforms to the ground surface. Ground elevation fitting prevents the building base from appearing to float or sink in the 3D scene and provides a consistent ground reference surface for building height analysis.

[0050] When performing building height analysis based on building base data and a real-world 3D model, a subset of point clouds covering the coverage area of ​​each building base surface is extracted from the real-world 3D model. Within this subset, a roof point set and a ground point set are identified. The roof point set represents the point cloud on the upper surface of the building, while the ground point set represents the ground point cloud around the building or within its base area. The building height is obtained by calculating the difference between the representative elevations of the roof point set and the ground point set. The representative elevations can be calculated using quantile statistics to reduce the impact of local structures or noise. The building height can be calculated using the height difference formula:

[0051] Where H represents the building height. This represents the representative elevation value of the rooftop point set. The representative elevation can be determined by the median elevation or the upper quantile elevation of the rooftop point set to suppress the influence of rooftop equipment and noise points. The representative elevation value represents the set of ground points. The representative elevation can be determined by the median elevation of the set of ground points to suppress the influence of local undulations and outliers. The formula obtains the effective height of the building relative to the ground by subtracting the overall elevation level of the set of ground points from the overall elevation level of the set of roof points, so that the building height value can be stably used for subsequent three-dimensional stretching.

[0052] When generating white model data of a building by performing 3D extrusion based on the building's base data and height value, each building base surface is stretched along a direction perpendicular to the horizontal plane, with the stretching distance corresponding to the building's height value, thus forming a white model body. The white model body is used to represent the three-dimensional volume of the building with regular geometry. During the extrusion process, geometric constraints are applied to the white model body, and the geometric structure of the white model body is stabilized by keeping the sides perpendicular and unifying the normal direction of the surfaces. At the same time, consistency processing is performed on the contact boundaries between adjacent white model bodies to avoid block intersections or gaps. When the building exhibits obvious height segmentation characteristics in the real-world 3D model, the building base surface is split according to the height segmentation boundaries and stretched separately so that the white model body can represent the complex volume structure such as towers and podiums, thereby obtaining white model data of the building that can be used for spatial association and scene support.

[0053] When performing spatial consistency verification on the building white model data and the actual 3D model, a quantitative assessment is conducted on the spatial deviation between the outer surface of the building white model and the corresponding point cloud subset in the actual 3D model. The deviation statistic is obtained by calculating the distance distribution from the point cloud subset to the outer surface of the building white model, and then compared with a deviation threshold to determine if the deviation exceeds the limit. When the deviation exceeds the limit, a callback correction is triggered. The callback correction includes local adjustments to the boundary positions of the building outline set and a re-estimation of the building height value, so that the building base surface set more closely matches the building footprint representation of the actual 3D model on the planar boundary, and the building white model body more closely matches the true elevation level of the roof point set in terms of height. The deviation statistic used in the spatial consistency verification can use the root mean square distance to take into account both the overall deviation level and the impact of abnormal deviations. The calculation formula is as follows:

[0054] in, Let N represent the root mean square distance, and let N be the number of 3D points in the subset of the point cloud participating in the verification, with a positive integer value. This represents the shortest distance from the i-th 3D point to the outer surface of the white model of the building. The shortest distance is calculated from the distance from the point to the surface and can be a non-negative value. This formula obtains a quantitative index of the overall fit by averaging and square-taking the square roots of the squared distances from all points to the outer surface of the white model. When the deviation threshold is exceeded, it indicates that there is a systematic inconsistency between the white model and the real 3D model, thereby triggering a callback correction of the outline and height and outputting building base data and building white model data consistent with the real 3D model.

[0055] S150 introduces a preset coordinate system for multi-source business basic data in response to the needs of urban digital public infrastructure construction, and verifies the spatial logical relationship between multi-source business basic data, building base data, and terrain data based on digital orthophotos and digital elevation models.

[0056] In one possible implementation, a preset coordinate system is introduced into the multi-source business foundation data to meet the needs of urban digital public infrastructure construction. Based on digital orthophotos and digital elevation models, the spatial logical relationship between the multi-source business foundation data and building foundation data and terrain data is verified. Specifically, this includes: performing coordinate system unification processing on the multi-source business foundation data to form a unified spatial reference under the preset coordinate system; performing planar position consistency verification on the multi-source business foundation data based on digital orthophotos to identify the planar offset relationship between the multi-source business foundation data and the actual surface texture; and performing planar position consistency verification on the multi-source business foundation data based on the digital elevation model. The system performs elevation logic relationship verification to determine the rationality of the vertical representation of multi-source business basic data; it also performs spatial inclusion and spatial adjacency relationship verification on the multi-source business basic data based on building base data to identify abnormal relationships that do not conform to the urban spatial organization logic; it performs terrain adaptability verification on the multi-source business basic data based on terrain data to verify the rationality of the spatial distribution of the multi-source business basic data under terrain constraints; and it classifies and marks various spatial logic anomalies identified by verification and determines correction or constraint strategies, thereby enabling the multi-source business basic data to form spatial logic relationships with digital orthophotos, digital elevation models, building base data, and terrain data.

[0057] Specifically, when performing coordinate system unification processing on multi-source business basic data, the coordinate reference information and data acquisition method information of the multi-source business basic data are sorted out respectively. The coordinate reference information includes at least the original coordinate system type, projection parameters, ellipsoid parameters, and elevation reference type. When the coordinate reference information is missing, the coordinate deviation parameters are inversely calculated by spatial fitting with a known set of control points. Subsequently, for each type of multi-source business basic data, the coordinate transformation parameters from the original coordinate system to the preset coordinate system are solved, so that the geometric objects of the multi-source business basic data can be uniformly expressed under the preset coordinate system. The benchmark consistency check is performed on the transformation results to eliminate systematic translation, rotation, and scale distortion. Among them, coordinate system unification processing is used to solve the spatial misalignment problem caused by inconsistent historical surveying benchmarks of different data sources. The preset coordinate system is used as a unified spatial reference benchmark for the entire domain. The unified spatial benchmark is used to characterize the spatial state of multi-source business basic data that can be directly superimposed and compared under the same coordinate reference. When a set of control points exists, the plane transformation relationship can be estimated through a similarity transformation model to minimize the residuals of the control points before and after the transformation. The calculation formula is:

[0058] in, This represents the planar coordinates of a geometric object in the original coordinate system. This represents the planar coordinates of the geometric object within a preset coordinate system, where 's' represents the scale factor and is a positive number. Indicates the rotation angle value and can be used Variation within the range, The formula represents the translation value and is used to compensate for differences in the origin. It maps geometric objects in the original coordinate system to the preset coordinate system through a combination of scaling, rotation and translation, thereby achieving planar unification of multi-source business basic data. Subsequently, the conversion quality is constrained by the control point residual statistics, so that the unified spatial benchmark has verifiable accuracy assurance.

[0059] When performing planar position consistency verification on multi-source operational basic data based on digital orthophotos, the geometric boundaries of the multi-source operational basic data are superimposed onto the corresponding surface texture representation of the digital orthophoto. Alignment constraints are constructed around stably identifiable texture structure elements, which at least include road boundary textures, waterfront textures, and building roof texture boundaries. Planar offset distribution is obtained by extracting the edge lines of texture structure elements from the digital orthophoto and measuring their distance from the corresponding boundaries of the multi-source operational basic data. Planar offset anomalies are determined when the plane offset distribution exceeds an offset threshold. The planar position consistency verification is used to determine whether the planar geometry of the multi-source operational basic data is consistent with the actual surface texture, and the planar offset relationship is used to characterize the systematic displacement direction and magnitude of geometric objects relative to texture boundaries. To quantify the degree of offset, the average offset distance can be used as an indicator, calculated using the following formula:

[0060] in, This represents the average offset distance, where M is the number of sampling points participating in the alignment evaluation and is a positive integer. This represents the shortest planar distance between the i-th sampling point and the boundary of the multi-source service basic data and the boundary of the digital orthophoto texture, and it is non-negative. This formula forms a stable assessment of the overall offset level by averaging the boundary distances of multiple sampling points. It is used to quickly identify systematic misalignments in a large area and serve as the basis for subsequent correction strategies.

[0061] When performing elevation logic relationship verification on multi-source business basic data based on the digital elevation model (DEM), the geometric objects of the multi-source business basic data are projected onto the raster space corresponding to the DEM, and the elevation sequence of the DEM is extracted within the coverage area of ​​the geometric objects to construct elevation logic constraints. For road traffic data, the continuity of the elevation sequence is used to determine whether there are unreasonable abrupt changes or reverse slope sections in the longitudinal profile of the road. For water and river data, the decreasing trend of the elevation sequence is used to determine whether the shoreline and the centerline of the river meet the elevation constraints of the natural flow direction. For building foundation data associated with real estate registration data, the elevation sequence is used to determine whether the ground elevation within the building foundation area is consistent with the fitting result of the ground elevation of the building foundation. Among these, the elevation logic relationship verification is used to determine whether the vertical expression conforms to the basic laws of topographic relief and hydrological flow direction. The vertical expression is used to characterize the consistency and rationality of the multi-source business basic data in the elevation dimension. The slope change rate can be used to assess the degree of elevation abrupt change of the road, and the calculation formula is as follows:

[0062] in, This represents the slope value of the k-th segment. This represents the k-th elevation value obtained by sampling along the road. This represents the (k+1)th elevation value. The value of the plane distance corresponding to the k-th segment is positive. This formula obtains the local slope by the ratio of the elevation difference between adjacent sampling points to the distance. It is used to identify abrupt changes in slope, abnormal slope signs, or abnormal slope amplitudes, thereby forming a calculable basis for judging the vertical rationality of road traffic data.

[0063] When performing spatial inclusion and spatial adjacency checks on multi-source business foundation data based on building foundation data, a spatial relationship verification domain centered on the building foundation data is constructed, and the consistency of the topological relationships of the multi-source business foundation data within the spatial relationship verification domain is judged. Spatial inclusion is used to determine whether a geometric object is located inside or within the coverage of another geometric object, and spatial adjacency is used to determine whether geometric objects form a reasonable adjacency relationship under boundary or distance constraints. For road traffic data, the checks verify whether the minimum distance required for accessibility is maintained between the road boundary and the building foundation boundary and whether the road crosses the building foundation. For water and river data, the checks verify whether the water shoreline and the building foundation meet the avoidance constraints and whether the water body covers the building foundation. For administrative division data, the checks verify whether the administrative division surface completely covers the building foundation and whether there are breaks caused by cross-surface drift of the building foundation. The minimum distance can be used to determine the adjacency rationality, and the calculation formula is as follows:

[0064] in, This represents the minimum non-negative distance between the boundaries of geometric object A and geometric object B. Represents the set of boundary points of geometric object A. Let p represent the set of boundary points of geometric object B, where p represents the boundary points from... The selected boundary point, q represents the boundary point from which the boundary point is located. The selected boundary points, The Euclidean distance between two points is represented by the formula. This formula quantifies the degree of adjacency by finding the minimum distance between two boundary point pairs of objects and comparing it with an accessibility threshold or avoidance threshold to identify topological anomalies such as interpenetration, coverage, or spacing abnormalities that do not conform to the logic of urban spatial organization.

[0065] When performing terrain adaptability verification on multi-source business foundation data based on terrain data, the slope distribution, aspect distribution, and terrain confluence paths derived from the digital elevation model are used as terrain constraint features. The slope distribution characterizes changes in terrain steepness, the aspect distribution characterizes the surface inclination direction, and the terrain confluence paths characterize the spatial channels through which surface water may converge and flow. For road traffic data, the verification examines whether the relationship between road orientation and slope distribution avoids large-scale reverse slope crossings or unreasonable steep inclines. For water and river data, the verification examines whether the water body shoreline and terrain confluence paths are consistent and avoids long-term overlap between water body boundaries and elevation ridges. For administrative division data, the verification examines whether the natural boundary characteristics of administrative divisions near ridgelines or valley lines conform to the spatial distribution patterns under terrain constraints. Terrain adaptability verification is used to identify hidden anomalies where geometric objects satisfy planar superposition but do not conform to terrain control laws, thereby improving the interpretability and reliability of spatial logical relationships. The terrain confluence consistency index can be used to assess the degree of fit between water body boundaries and confluence paths; the calculation formula is as follows:

[0066] Where C represents the value of the consistency index and can be used... Variation within the range, This represents the number of sampling points along the water boundary and is a positive integer. The value of represents the shortest distance from the i-th sampling point to the nearest topographic confluence path and is non-negative. r represents the distance attenuation coefficient and is positive, used to control the attenuation rate of the distance's contribution to consistency. This formula exponentially attenuates the distance from the sampling point to the confluence path and averages it, so that the smaller the distance, the greater the contribution to consistency. This quantifies the overall fit between the water boundary and the topographic control path and is used to identify abnormal areas where the water boundary deviates from the confluence path.

[0067] When classifying and labeling spatial logical anomalies identified through verification and determining correction or constraint strategies, a spatial logical anomaly labeling system is constructed based on the residual characteristics output by the unified processing of the coordinate system, the distribution of plane offsets output by the plane position consistency verification, the slope anomalies and trend anomalies output by the elevation logical relationship verification, the topological conflict types output by the spatial inclusion relationship and spatial adjacency relationship verification, and the terrain consistency index output by the terrain adaptability verification. Each anomaly object is assigned a corresponding label. The anomaly labels include at least plane offset anomalies, elevation anomalies, topological conflict anomalies, and terrain incompatibility anomalies. A correction strategy or constraint strategy is associated with each anomaly label. The correction strategy is used to perform position callback, boundary reconstruction, or attribute correction on geometric objects under the condition of meeting the accuracy threshold and consistency threshold. The constraint strategy is used to set risk shielding conditions for the subsequent standard address unit generation and association with governance objects when immediate correction is not possible or when there is uncertainty. By writing the anomaly labels and strategy results into the quality attribute fields of multi-source business basic data, the multi-source business basic data has traceable verification basis and executable correction path when overlaid with digital orthophotos, digital elevation models, building base data, and terrain data.

[0068] S160, based on spatial logical relationships, generates standard address units on the basis of road spatial entities around a unified standard address system, establishes spatial association between standard address units and building white model data, and forms an address space carrier.

[0069] In one possible implementation, based on spatial logical relationships, standard address units are generated on the basis of road spatial entities around a unified standard address system. Spatial associations are established between these standard address units and building white model data to form an address space carrier. Specifically, this includes: performing topological normalization confirmation processing on the road spatial entities after spatial logical relationship verification to form a valid set of road spatial entities; performing road attribution determination based on the spatial adjacency relationship between the valid road spatial entity set and building base data to determine the road spatial entity corresponding to the building base data; generating standard address units on the basis of the road spatial entities, so that the standard address units reflect the relationship between road attributes and building spatial location; generating a unique identification code for each standard address unit according to unified identification code encoding rules; establishing spatial associations between the standard address units and the corresponding building base data and building white model data; and performing consistency verification on the spatial associations, thereby forming the address space carrier.

[0070] Specifically, when performing topological normalization verification on road spatial entities after spatial logical relationship verification, a systematic check is conducted on the integrity and usability of road spatial entities in terms of geometric structure and topological relationships. By checking the continuity of road centerlines, segmental connection relationships, and connectivity relationships between road nodes, abnormal road segments with broken, overlapping, self-intersecting, or suspended nodes are identified and eliminated. At the same time, the consistency of road grade attributes, road name attributes, and road code attributes is checked to eliminate logically incomplete road spatial entities caused by missing or conflicting attributes. This ensures that the retained road spatial entities meet the stability requirements for address generation benchmarks in terms of geometric shape and semantic attributes, thus forming a valid set of road spatial entities that can be used for subsequent address anchoring. Among them, road spatial entities are used to represent the continuous geometric expression of urban roads in space, and topological normalization is used to represent the state of road spatial entities in terms of connection and structural relationships that conform to the organization rules of urban road networks.

[0071] When determining road attribution based on the spatial adjacency relationship between the effective set of road spatial entities and building base data, a road influence range is constructed around the road spatial entities. Within the road influence range, the minimum distance relationship, orientation relationship, and accessibility relationship between the building base data and the road spatial entities are analyzed to determine which road spatial entity the building base data has the most direct service relationship with in space. The spatial adjacency relationship is used to characterize the degree of proximity and accessibility between the building base data and the road spatial entities in spatial location. By comparing the distance from the building base boundary to the boundaries of multiple road spatial entities and combining the road level and road direction, the unique road spatial entity corresponding to each building base data is determined, thereby establishing a clear road attribution basis for the subsequent generation of standard address units.

[0072] After determining the road spatial entities corresponding to the building base data, standard address units are generated based on the road spatial entities according to the unified standard address system. By combining the standardized name of the road spatial entity, road attribute information, and the relative ordering relationship of the building base data in the road direction, address representations are constructed for the building base data according to unified address arrangement rules. This ensures that the generated standard address units can semantically reflect the road name, road attributes, and spatial location relationship of the building simultaneously. The standard address units serve as the smallest granular address representation units with clear spatial orientation in the city. The unified standard address system is used to constrain the consistency of address generation rules and address representation structure, thereby ensuring the comparability of standard addresses generated in different regions and at different times in terms of structure and meaning.

[0073] After generating standard address units, an identification code generation process is performed on each standard address unit according to the unified identification code encoding rules. By combining administrative division identifiers, road spatial entity identifiers, and address sequence information according to the preset encoding structure, an identification code that can uniquely identify the standard address unit is generated, so that the standard address unit has uniqueness, stability, and traceability at the system level. The identification code is used as a unique index in cross-system data exchange and subsequent governance object association processes to avoid ambiguity and conflicts caused by relying solely on text address descriptions.

[0074] After obtaining a standard address unit with a unique identification code, a spatial association is established between the standard address unit and the corresponding building base data and building white model data. By mapping the position of the standard address unit in two-dimensional space to its corresponding building base surface, and further extending this mapping relationship to the building white model data that corresponds one-to-one with the building base data, the standard address unit can be accurately anchored to the specific building white model entity in three-dimensional space. Among them, the building white model data is used to express the three-dimensional volume structure of the building, and the spatial association relationship is used to characterize the binding relationship between the address and the building in spatial location, thereby transforming the address from a two-dimensional road reference into a spatial carrier with a three-dimensional building entity as the core.

[0075] After completing the spatial association between standard address units and building base data and building white model data, a consistency check is performed on the spatial association relationship. This check is conducted by verifying whether the standard address unit is uniquely associated with a single building white model data, whether its road affiliation is logically consistent, and whether its three-dimensional spatial location falls within a reasonable range of the building white model data. This identifies anomalies such as multiple entities at one address, multiple addresses in one entity, or misaligned order. When anomalies are found, the corresponding road affiliation determination or address arrangement rules are backtracked for correction, ensuring that the final address space carrier remains consistent in spatial orientation, semantic expression, and system identification. This results in an address space carrier that is locatable, traceable, and usable for association of governance object data.

[0076] S170 links the actual population, actual housing, and actual units with the address space carrier to form linked data.

[0077] In one possible implementation, the actual population, actual housing, and actual units are associated with address space carriers to form associated data. Specifically, this includes: performing governance object standardization processing on the actual population data, actual housing data, and actual unit data to form a governance object set; performing initial matching processing on the governance object set based on the unique identification code of the address space carrier to form candidate associations between governance objects and standard address units; performing spatial consistency verification on the candidate associations based on the building white model data associated with the address space carrier to eliminate abnormal associations lacking spatial rationality, thus obtaining processed associations; performing spatial hierarchy relationship parsing processing around the building white model data to refine and bind the actual housing data, establishing hierarchical associations between the actual population data, actual unit data, and actual housing data; and based on the processed associations and hierarchical associations, associating the verified governance objects with their corresponding address space carriers and outputting the associated data.

[0078] Specifically, when performing standardization processing on actual population data, actual housing data, and actual unit data, the system addresses the issues of field heterogeneity, coding heterogeneity, and status heterogeneity that exist in cross-departmental aggregation scenarios. It unifies and verifies the identifier field, address field, business attribute field, and source field of various governance objects to ensure that governance objects from different sources structurally meet the requirements of comparability and connectivity. The identifier field carries the unique or unique identifier of the governance object; the address field carries the address description and house number information; the business attribute field carries population, housing, or unit attributes; and the source field carries metadata such as data source and update time. For governance objects with missing identifier fields or conflicting identifier fields, a supplementary identifier is generated using multi-field joint uniqueness rules. The address field is also standardized and cleaned to eliminate inconsistencies caused by synonyms, abbreviations, misspellings, and order differences, thus forming a set of governance objects that can directly participate in subsequent matching and verification.

[0079] When performing initial matching processing on the governance object set based on the unique identification code of the address space carrier, the address field of each governance object record in the governance object set is parsed into a comparable address element sequence. The address element sequence is then jointly compared with the unique identification code and address semantic elements corresponding to the standard address unit. Candidate associations between governance objects and standard address units are established through a combination of priority coding matching and supplementary semantic matching. Coding matching is used to directly establish a deterministic association when the governance object record already carries a unique identification code or can be mapped to a unique identification code. Semantic matching is used to determine the similarity between the governance object record and the standard address unit based on address elements such as road name, house number, and building number when the governance object record lacks a unique identification code. During semantic matching, address similarity is calculated between the address element sequence and the standard address element sequence, and candidate pairs with address similarity exceeding the matching threshold are included in the candidate association. The calculation formula is as follows:

[0080] Where S represents the address similarity value and can be used... Variation within the range, Indicates the number of address element categories and is a positive integer. Indicates the first The weight values ​​of class address elements and satisfy the following conditions: , Indicates the first The similarity value of class address elements can be obtained and can be... Within the range of variations, the address element categories include at least administrative division elements, road elements, house number elements, and building elements. The similarity value can be obtained by complete consistency judgment or edit distance normalization judgment. This formula makes the key elements contribute more to the overall matching by weighted fusion of the similarity of multiple types of address elements, so that even when the unique identification code is missing, it can still form candidate association relationships that can be used for subsequent spatial verification.

[0081] When performing spatial consistency verification on candidate associations based on the building white model data associated with the address space carrier, the standard address units in the candidate associations are mapped to their corresponding building white model data, and the spatial clues available in the governance object records are verified for consistency. The spatial clues include at least the building number, floor number, unit number, and spatial range description related to the house or unit registered in the governance object record. Spatial consistency verification is used to determine whether the candidate associations are valid in three-dimensional spatial orientation. By checking whether the spatial clues indicated by the governance object fall into the spatial range corresponding to the building white model data, abnormal associations that are similar only at the address text level but contradict each other in spatial orientation are identified. For governance object records that cannot provide spatial clues, indirect verification is performed using their business association clues with actual house data or actual unit data. When the verification fails, the candidate association is marked as an abnormal association and removed, thereby outputting the processed associations that do not contain abnormal associations.

[0082] When performing spatial hierarchy analysis on building white model data, the geometric and attribute structures of the building white model data are used to analyze the building structure, floor structure, and unit structure. The actual housing data is then refined and bound according to the hierarchical elements of building number, floor number, and unit number, ensuring that each piece of actual housing data can be uniquely located within the building white model data. Spatial hierarchy analysis refines the building white model data from an overall volumetric representation into hierarchical representations of housing units and individual units. Hierarchical relationships characterize the attribution and mapping paths between actual population data, actual unit data, and actual housing data. After refinement and binding, actual population data is associated with corresponding actual housing data based on residential or usage relationships, and actual unit data is associated with corresponding actual housing data based on operational or office relationships. This allows actual population data and actual unit data to indirectly obtain their hierarchical positions within the building white model data through the actual housing data, thus forming a complete hierarchical relationship.

[0083] When outputting associated data based on the processing of relational and hierarchical relationships, a consistency check is first performed on the processed relational and hierarchical relationships. This is done by verifying whether the same governance object is associated with multiple address space carriers, whether the same actual housing data corresponds to multiple standard address units, and whether the same actual population data falls into mutually exclusive housing hierarchical positions. Inconsistencies such as multi-address integration, integration with multiple addresses, or hierarchical conflicts are identified and eliminated. Subsequently, the governance objects that have passed the check are finally associated with their corresponding address space carriers, and the association results are written into the associated data. This ensures that the associated data simultaneously includes the governance object identifier, unique identification code, standard address unit identifier, building white model identifier, and hierarchical elements corresponding to the building structure, floor structure, and unit structure. This gives the associated data a traceable spatial pointing chain and allows it to be directly used for subsequent aggregation on the urban information model platform and smart city business calls.

[0084] S180 processes the associated data according to a unified data format specification and data slicing rules, aggregates it into the city information model platform, and outputs it to smart city applications.

[0085] Before aggregating the associated data, the associated data is first processed to standardize its structure in accordance with the unified data carrying requirements of the city information model platform. This is achieved by performing field validation, type unification, and constraint completion on the governance object identifiers, standard address unit identifiers, unique identification codes, building white model identifiers, and spatial hierarchy elements contained in the associated data. This ensures that the associated data meets the unified data format specifications in terms of field structure, naming rules, and associated semantics, thereby guaranteeing that associated data generated from different sources and at different times has a consistent data organization form before entering the city information model platform, and avoiding data parsing ambiguity caused by structural differences.

[0086] After completing the data structure standardization process, spatial indexing is performed on the associated data according to the unified data format specifications. By configuring spatial index parameters consistent with the preset coordinate system for spatial objects in the associated data, each piece of associated data can be quickly located to the corresponding spatial range. At the same time, attribute indexes are built for non-spatial attribute fields to support subsequent rapid retrieval according to governance object type, address type, or business attribute. This ensures that the associated data is adapted to the efficient scheduling requirements of the urban information model platform in both logical and spatial structures.

[0087] After the index is built, data slicing is performed on the associated data to meet the needs of large-scale city-level data carrying and distributed scheduling. The associated data is divided into blocks according to spatial range, building white model data range, or administrative division range, so that each data slice covers a clear and continuous spatial area. Data slicing rules are used to control the data size of a single data unit and to keep the data slices seamlessly connected at the spatial boundaries. This supports the city information model platform to load and update associated data on demand at different spatial scales, avoiding the performance pressure caused by overall loading.

[0088] After the data slicing process is completed, the processed related data is aggregated according to the data access specifications of the city information model platform. By writing each data slice into the data storage unit corresponding to its spatial range and registering the metadata information of the related data on the platform side, the city information model platform can identify the spatial coverage, data version status and update time of the related data. The metadata information is used to support the platform's unified management, version control and incremental updates of the data, so that the related data has maintainability and evolvability within the platform.

[0089] After data aggregation is completed, the associated data is encapsulated as a service to meet the needs of smart city applications. By publishing the associated data to the outside world in the form of standardized data service interfaces, smart city applications can obtain information on governance objects, address space carriers, and building white model association information within a specified spatial range on demand based on a unified interface. The data service interface maintains the same spatial index and data slicing rules as the city information model platform, enabling smart city applications to directly utilize the platform's spatial scheduling capabilities when calling associated data, thereby achieving real-time loading and updating in conjunction with the 3D scene.

[0090] Ultimately, through the continuous processing of data format standardization, data slicing, data aggregation, and service-oriented output, the related data are transformed into data results that can be uniformly carried, dynamically scheduled, and stably output in the urban information model platform. This enables smart city applications to operate under the same spatial data foundation and unified standard data system, thereby supporting refined urban governance, cross-departmental collaboration, and business linkage in complex scenarios.

[0091] This embodiment also discloses a data processing device based on a smart city, referring to... Figure 2 The device includes an acquisition module 201, a processing module 202, and an output module 203. It is used to execute any of the above-described data processing methods based on smart cities, wherein: The acquisition module 201 is used to carry out basic data collection around the city-level spatial data base and acquire raw image data under the preset coordinate system through UAV oblique photogrammetry. Processing module 202 is used to generate point cloud data of a real-world 3D model based on the original image data through aerial triangulation and dense matching. Processing module 202 is used to simultaneously generate digital orthophotos and digital elevation models under point cloud data constraints; Processing module 202 is used to extract the building outline to form building base data based on the real scene 3D model, and generate building white model data based on the building base data; The processing module 202 is used to introduce a preset coordinate system into the multi-source business basic data according to the needs of urban digital public infrastructure construction, and to verify the spatial logical relationship between the multi-source business basic data, building base data and terrain data based on digital orthophotos and digital elevation models. Processing module 202 is used to generate standard address units based on road spatial entities according to spatial logical relationships and around a unified standard address system, and to establish spatial association between standard address units and building white model data to form an address space carrier; Processing module 202 is used to associate the actual population, actual housing and actual units with the address space carrier to form associated data; The output module 203 is used to process the associated data according to the unified data format specifications and data slicing rules, aggregate it to the city information model platform, and output it to smart city applications.

[0092] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0093] This embodiment also discloses an electronic device, as shown in the reference. Figure 3 The electronic device may include: at least one processor 301, at least one communication bus 302, user interface 303, network interface 304, and at least one memory 305.

[0094] The communication bus 302 is used to enable communication between these components.

[0095] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0096] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0097] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0098] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. As a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface 303 module, and an application program for a data processing method based on smart cities.

[0099] exist Figure 3In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 301 can be used to call an application program stored in the memory 305 that is a data processing method based on smart cities. When executed by one or more processors 301, the electronic device executes one or more methods as described in the above embodiments.

[0100] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, as some steps can be performed in other orders or simultaneously according to the present invention. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0101] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0102] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical 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] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0105] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 305 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 of the various embodiments of this invention. The aforementioned memory 305 includes various media capable of storing program code, such as a USB flash drive, external hard drive, magnetic disk, or optical disk.

[0106] The present invention also discloses a non-transitory computer-readable storage medium storing instructions. When executed by one or more processors 301, these instructions cause an electronic device to perform one or more methods as described in the above embodiments.

[0107] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truths. This invention is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A data processing method based on a smart city, characterized in that, The method comprises: Carrying out basic data collection around a city-level spatial data base, obtaining original image data under a preset coordinate system through unmanned aerial vehicle oblique photogrammetry; Generating point cloud data of a real three-dimensional model based on the original image data through aerial triangulation and dense matching; Synchronously generating a digital orthographic image and a digital elevation model under the constraint of the point cloud data; Extracting a building contour to form building base data with reference to the real three-dimensional model, and generating building white model data based on the building base data; Introducing a plurality of source business basic data into the preset coordinate system around the city digital public infrastructure construction demand, and verifying the spatial logical relationship between the plurality of source business basic data and the building base data and terrain data based on the digital orthographic image and the digital elevation model; Based on the spatial logical relationship, generating a standard address unit on the basis of a road space entity around a unified standard address system, establishing a spatial correlation relationship between the standard address unit and the building white model data, and forming an address space carrier; Data correlation is performed between real population, real housing and real units and the address space carrier to form associated data; The associated data is processed according to a unified data format specification and data slicing rule and converged to a city information model platform, and output to a smart city application. 2.The data processing method based on smart city according to claim 1, wherein, The sychronously generating a digital orthographic image and a digital elevation model under the constraint of the point cloud data specifically comprises: The point cloud data is processed by identifying and removing outliers, correcting mismatched points in the occlusion area, and unifying the point cloud density distribution, thereby obtaining a unified spatial constraint reference; Under the unified spatial constraint reference, based on the geometric correspondence relationship between the point cloud data and the original image data, the pixel correction of the tilt distortion of the original image data is performed by using the ground elevation information and the ground object height information in the point cloud data, thereby generating a digital orthographic image under the preset coordinate system; Based on the elevation distribution characteristics in the point cloud data, the ground point and ground point separation processing is performed on the point cloud data, the building points and vegetation points are identified and the ground point set is retained, and the ground point cloud data for terrain expression is formed; The spatial interpolation and gridding processing is performed based on the ground point cloud data, and the digital elevation model is generated. 3.The data processing method based on smart city according to claim 1, characterized in that, The generating point cloud data of a real three-dimensional model based on the original image data through aerial triangulation and dense matching specifically comprises: The original image data is processed to remove abnormal images with blur, occlusion or time offset, and image control results are obtained; Based on the preset coordinate system and the image control results, the aerial triangulation processing is performed on the original image data, the homonymous feature points between images are extracted and the image connection relationship is established, the image exterior orientation elements are jointly adjusted and solved in combination with the image control points, thereby determining the spatial position parameters and attitude parameters of each image in the preset coordinate system, and obtaining the image exterior orientation elements; Perform dense matching preparation processing on the original image data based on the image exterior orientation elements, determine the image combination relationship that meets the dense matching condition by analyzing and screening the image view angle difference, overlapping area range and baseline length; Perform dense matching processing on the original image data based on the image combination relationship, obtain the matching point set with spatial correspondence relationship by point-by-point matching of the corresponding regions of multi-view images at the pixel scale; Inverse calculate the matching points of the matching point set to the three-dimensional space position under the preset coordinate system combined with the image exterior orientation elements, thereby forming the initial three-dimensional point set; Perform point cloud consistency constraint processing on the initial three-dimensional point set, identify and eliminate abnormal points caused by occlusion, reflection or matching error, and correct the point cloud density distribution and spatial continuity, thereby generating the point cloud data. 4.The data processing method based on smart city according to claim 1, characterized in that, The building contour is extracted based on the real three-dimensional model to form building base data, and the building white model data is generated based on the building base data, specifically including: Perform building separation enhancement processing on the real three-dimensional model to identify the height mutation, normal vector difference and slope difference between the building and the ground surface to form a building candidate region set; Perform building contour extraction processing based on the building candidate region set, generate a building contour line set through plane projection, boundary identification and topological review, and perform contour consistency review combined with the digital orthophoto; Construct the building base data based on the building contour line set, form a building base surface set through closed surface construction and planar topological review, and complete ground elevation fitting combined with the digital elevation model; Perform building height analysis processing based on the building base data and the real three-dimensional model, obtain the building height value through the height difference calculation of the roof point set and the ground point set; Perform three-dimensional stretching based on the building base data and the building height value to generate the building white model data; Perform spatial consistency review on the building white model data and the real three-dimensional model, and call back and correct the building contour and building height when the deviation is out of limit, thereby outputting the building base data and the building white model data consistent with the real three-dimensional model. 5.The data processing method based on smart city according to claim 1, characterized in that, Introduce the preset coordinate system to the multi-source business basic data based on the demand of urban digital public infrastructure construction, and verify the spatial logical relationship between the multi-source business basic data and the building base data and terrain data based on the digital orthophoto and the digital elevation model, specifically including: Perform coordinate system processing on the multi-source business basic data to form a unified spatial reference under the preset coordinate system; Perform plane position consistency check on the multi-source business basic data based on the digital orthophoto to identify the plane offset relationship between the multi-source business basic data and the real ground texture; Perform elevation logical relationship check on the multi-source business basic data based on the digital elevation model to determine the reasonableness of the multi-source business basic data in vertical expression; Performing spatial inclusion relationship and spatial adjacency relationship verification on the multi-source business basic data around the building base data to identify abnormal relationships that do not conform to the urban spatial organization logic; Performing terrain adaptability verification on the multi-source business basic data based on the terrain data to verify the spatial distribution rationality of the multi-source business basic data under terrain constraints; Classifying and marking various spatial logic abnormalities identified through verification and determining correction or constraint strategies, so that the multi-source business basic data forms the spatial logic relationship with the digital orthophoto, the digital elevation model, the building base data and the terrain data. 6.The data processing method based on smart city according to claim 1, characterized in that, Based on the spatial logic relationship, generating a standard address unit based on a road space entity around a unified standard address system, establishing a spatial correlation relationship between the standard address unit and the building white model data, and forming an address space carrier, specifically including: Performing topological specification confirmation processing on the road space entity after the spatial logic relationship verification to form an effective road space entity set; Performing road attribution determination based on the spatial adjacency relationship between the effective road space entity set and the building base data to determine the road space entity corresponding to the building base data; Generating the standard address unit based on the road space entity, so that the standard address unit reflects the relationship between road attributes and building spatial positions; Generating a unique identification code for each standard address unit according to a unified identification code coding rule; Establishing a spatial correlation relationship between the standard address unit and the corresponding building base data and building white model data; Performing consistency checking on the spatial correlation relationship, thereby forming the address space carrier. 7.The data processing method based on smart city according to claim 1, characterized in that, The real population, real housing and real unit are data correlated with the address space carrier to form correlation data, specifically including: Performing governance object standardization processing on real population data, real housing data and real unit data to form a governance object set; Based on the unique identification code of the address space carrier, performing initial matching processing on the governance object set to form a candidate correlation relationship between the governance object and the standard address unit; Based on the building white model data associated with the address space carrier, performing spatial consistency verification on the candidate correlation relationship to eliminate abnormal correlations that do not have spatial rationality, obtaining a processing correlation relationship; Performing spatial hierarchical relationship analysis processing around the building white model data to refine and bind the real housing data, and establishing hierarchical correlation relationships between the real population data, the real unit data and the real housing data; Based on the processing correlation relationship and the hierarchical correlation relationship, correlating the governance object that passes the verification with the corresponding address space carrier and outputting correlation data. 8.A data processing apparatus based on a smart city, characterized in that, The device is used to perform a data processing method based on a smart city according to any one of claims 1-7, and the device includes an acquisition module, a processing module and an output module, wherein: The acquisition module is configured to collect basic data around a city-level spatial data base, and acquire original image data under a preset coordinate system through unmanned aerial vehicle oblique photogrammetry; The processing module is configured to generate point cloud data of a real three-dimensional model through aerial triangulation and dense matching based on the original image data; The processing module is configured to generate a digital orthographic image and a digital elevation model synchronously under the constraint of the point cloud data; The processing module is configured to extract a building contour to form building base data with reference to the real three-dimensional model, and generate building white model data based on the building base data; The processing module is configured to introduce multi-source business basic data into the preset coordinate system around the demand for city digital public infrastructure construction, and verify a spatial logical relationship between the multi-source business basic data and the building base data and terrain data based on the digital orthographic image and the digital elevation model; The processing module is configured to generate a standard address unit based on a road space entity around a unified standard address system based on the spatial logical relationship, establish a spatial correlation relationship between the standard address unit and the building white model data, and form an address space carrier; The processing module is configured to associate real population, real housing and real units with the address space carrier to form associated data; The output module is configured to process and converge the associated data to a city information model platform according to a unified data format specification and data slicing rule, and output to a smart city application.

9. An electronic device, comprising: The electronic device includes a processor, a communication bus, a user interface, a network interface and a memory, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, the communication bus is configured to realize connection and communication between components in the electronic device, and the processor is configured to execute the instructions stored in the memory, so that the electronic device executes the method in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, comprising: The computer readable storage medium stores instructions, when the instructions are executed, the method in any one of claims 1-7 is executed.

Images