Data processing system and method for three-dimensional real estate surveying and mapping

Abstract

The invention discloses a data processing system and method for three-dimensional real estate surveying and mapping, and relates to the technical field of intelligent surveying and mapping, and the system comprises a multi-source data fusion module, a model generation module, a spatial relationship analysis module, an efficient rendering module and a data security module. The multi-source data fusion module converts the original surveying and mapping data in different formats into a unified three-dimensional point cloud data set; the model generation module generates a parameterized three-dimensional building model based on the point cloud data; the spatial relation analysis module constructs a relation graph of the building model and generates a surveying and mapping index report; the efficient rendering module processes large-scale three-dimensional data and generates an interactive three-dimensional scene; and the data security module controls the data access authority and generates an operation log. According to the method, the processing efficiency and precision of the three-dimensional real estate surveying and mapping data are improved, efficient analysis and visualization of large-scale three-dimensional data are realized, the security of sensitive data is ensured, and advanced technical support is provided for modern city planning, real estate management and real estate development.

Description

Technical Field

[0001] The present invention relates to the field of intelligent surveying and mapping technology, in particular to a data processing system and method for three-dimensional real estate surveying and mapping. Background Art

[0002] With the acceleration of urbanization and the rapid development of the real estate market, traditional two-dimensional real estate surveying and mapping technology can no longer meet the needs of modern urban planning, real estate management and real estate development. In recent years, with the application of technologies such as laser scanning and oblique photography, three-dimensional real estate surveying and mapping technology has gradually become the focus of the industry. The existing three-dimensional real estate surveying and mapping data processing system can realize basic three-dimensional data collection, storage and visualization, and support simple spatial analysis and measurement functions.

[0003] However, the current 3D real estate surveying and mapping data processing system still faces many challenges. The main problems include: low data collection efficiency and slow processing speed of large-scale 3D data; 3D data from different sources and formats are difficult to effectively integrate and have poor compatibility with existing 2D real estate databases; lack of professional analysis tools for real estate characteristics and limited spatial relationship analysis capabilities; insufficient 3D rendering performance for large scenes, making it difficult to smoothly display city-level real estate data; and lack of effective protection mechanisms for sensitive real estate information. Summary of the invention

[0004] In view of the problems existing in the existing three-dimensional real estate surveying and mapping data processing system, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to improve the processing efficiency, accuracy and security of three-dimensional real estate surveying and mapping data, while achieving efficient analysis, visualization and management of large-scale three-dimensional data.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a data processing system for three-dimensional real estate surveying and mapping, which includes: a multi-source data fusion module for converting raw data in real estate surveying and mapping into a three-dimensional point cloud data set in a unified format; a model generation module for generating a parameterized three-dimensional building model based on the three-dimensional point cloud data set; a spatial relationship analysis module for constructing a relationship diagram of the parameterized three-dimensional building model and generating a surveying and mapping indicator report; an efficient rendering module for processing large-scale three-dimensional real estate data and generating an interactive three-dimensional scene display; a data security module for controlling access to real estate surveying and mapping data according to user permissions and generating an operation log.

[0007] As a preferred solution of the data processing system for three-dimensional real estate surveying and mapping described in the present invention, the process of the multi-source data fusion module is as follows: importing original data; performing data preprocessing on the original data to obtain preprocessed data; converting the preprocessed data to a unified coordinate system to obtain multi-source data with consistent coordinates; performing spatial alignment on the multi-source data, and generating and fusing three-dimensional point cloud data based on the multi-source data after spatial alignment; processing the fused three-dimensional point cloud data to form a three-dimensional point cloud data set in a unified format.

[0008] As a preferred solution of the data processing system for three-dimensional real estate surveying and mapping described in the present invention, the process of the model generation module includes: classifying the three-dimensional point cloud data set to obtain building point cloud data; semantically segmenting the building point cloud data to identify the main components of the building; extracting key geometric features from the building point cloud data; based on the key geometric features, using parametric modeling technology to construct a model framework of the building; optimizing the model framework, adding building elements through a building rule library to obtain a parametric three-dimensional building model; and verifying the accuracy of the parametric three-dimensional building model to generate a model quality report.

[0009] As a preferred solution of the data processing system for three-dimensional real estate surveying and mapping described in the present invention, the parametric modeling technology is used to construct a model framework of a building, including: using a plane fitting algorithm to process key geometric features to determine the main plane of the building; based on the fitted plane features, calculating the contour lines and edge lines of the building to form the skeleton structure of the building; according to the skeleton structure, determining the main geometric parameters of the building; based on the main geometric parameters, constructing a parametric main structure model of the building; according to the semantic segmentation results, identifying the position and size of key building elements; adding the key building elements to the parametric main structure model to form a model framework of the building.

[0010] As a preferred solution of the data processing system for three-dimensional real estate surveying and mapping of the present invention, the specific process of the spatial relationship analysis module includes: receiving parameterized three-dimensional building model data; spatially decomposing the parameterized three-dimensional building model to identify independent building units; extracting the geometric features and semantic features of each building unit, and constructing a topological relationship matrix between building units; using the R-tree spatial indexing algorithm to analyze and determine the spatial relationship between building units and generate analysis results; based on the topological relationship matrix and the analysis results, generating a relationship diagram representing the spatial structure of the building complex, and using the relationship diagram to calculate key surveying and mapping indicators; associating the relationship diagram with the key surveying and mapping indicators to generate a comprehensive surveying and mapping indicator report.

[0011] As a preferred solution of the data processing system for three-dimensional real estate surveying and mapping described in the present invention, the R-tree spatial index algorithm is used to analyze and determine the spatial relationship between building units, including the following steps: constructing a minimum bounding rectangle MBR for each building unit; constructing an R-tree index structure based on the MBR of the building unit to organize the spatial data into a hierarchical tree structure; defining the spatial relationship type and formulating judgment criteria for each relationship type, wherein the spatial relationship types include adjacent, contained, intersecting and overlapping; for each building unit, using the R-tree index to perform spatial query to filter out other building units that may have spatial relationships; for each pair of filtered building units, determining the specific spatial relationship according to the formulated judgment criteria.

[0012] As a preferred solution of the data processing system for three-dimensional real estate surveying and mapping described in the present invention, the original data includes laser scanning point cloud data, oblique photography image data, total station measurement data, GNSS measurement data, drone aerial image data, existing two-dimensional cadastral map data and topographic map data.

[0013] In a second aspect, the present invention provides a data processing method based on three-dimensional real estate surveying and mapping, based on the data processing system based on three-dimensional real estate surveying and mapping provided in the first aspect above, the method includes importing original surveying and mapping data and converting it into a three-dimensional point cloud data set in a unified format; generating a parametric three-dimensional building model based on the three-dimensional point cloud data set; constructing a relationship diagram of the parametric three-dimensional building model, and generating a surveying and mapping indicator report; processing large-scale three-dimensional real estate data and generating an interactive three-dimensional scene display; controlling access to real estate surveying and mapping data according to user permissions, and generating an operation log.

[0014] The beneficial effects of the present invention are as follows: the three-dimensional real estate surveying and mapping data processing system provided by the present invention has multiple technical advantages. Its multi-source data fusion module can effectively integrate data of different formats and coordinate systems, improve data quality and processing efficiency, and provide a reliable foundation for subsequent modeling. The model generation module introduces deep learning and parametric modeling technology to achieve accurate identification and efficient modeling of buildings, and can better adapt to the modeling needs of complex building structures. The spatial relationship analysis module adopts the R-tree spatial indexing algorithm to improve the efficiency and accuracy of spatial relationship analysis between building units, and provide useful data support for urban planning and management. The efficient rendering module improves the visualization effect and interactive experience of large-scale three-dimensional data through dynamic level of detail technology and improved spatial indexing algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 Architectural diagram of a data processing system for three-dimensional real estate mapping.

[0017] Figure 2 Flowchart of the multi-source data fusion module of the data processing system for three-dimensional real estate surveying and mapping.

[0018] Figure 3 Flowchart of a model generation module for a data processing system for three-dimensional real estate mapping. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1, reference Figure 1~Figure 3 , which is the first embodiment of the present invention, and provides a data processing system for three-dimensional real estate surveying and mapping, and its architecture diagram is as follows Figure 1 As shown, it includes multi-source data fusion module, model generation module, spatial relationship analysis module, efficient rendering module and data security module, as follows: Multi-source data fusion module, used to convert raw data in real estate surveying and mapping into a 3D point cloud dataset in a unified format; A model generation module, used to generate a parameterized three-dimensional building model based on the three-dimensional point cloud data set; A spatial relationship analysis module, used to construct a relationship diagram of the parametric three-dimensional building model and generate a surveying and mapping indicator report; An efficient rendering module for processing large-scale 3D real estate data and generating interactive 3D scene displays; The data security module is used to control access to real estate surveying and mapping data based on user permissions and generate operation logs.

[0023] In traditional technologies, real estate surveying and mapping data usually comes from multiple channels, and the data formats and coordinate systems are often inconsistent, making data integration difficult. In addition, the quality of data from different sources varies, and direct fusion is prone to introduce errors. It can be seen that traditional data processing methods cannot fully meet the needs of high-precision 3D modeling.

[0024] In this regard, the present invention provides a multi-source data fusion module, which can efficiently integrate multi-source heterogeneous data while improving data quality, realize unified processing of data in different formats and coordinate systems, and significantly improve the accuracy and efficiency of data fusion. The specific process is as follows: import various types of original data, including laser scanning point cloud data, oblique photography image data, total station measurement data, GNSS measurement data, drone aerial image data, two-dimensional cadastral map data and topographic map data, and select the import according to project requirements, available data sources, accuracy requirements, budget and time constraints; perform data preprocessing on the original data, including but not limited to noise reduction, filtering and outlier removal, to obtain preprocessed data; convert the preprocessed data to a unified coordinate system, and use a high-precision coordinate transformation algorithm to obtain multi-source data with consistent coordinates; perform iterative nearest point spatial alignment on the multi-source data to establish a corresponding relationship between the multi-source data; generate three-dimensional point cloud data in a unified format based on the multi-source data after spatial alignment, and fuse the point cloud data from different sources to retain the advantage information of each data source; perform density equalization processing and spatial index construction on the fused three-dimensional point cloud data to form a three-dimensional point cloud data set in a unified format. Among them, the multi-source data fusion module flow chart is as follows Figure 2 shown.

[0025] Preferably, by intelligently integrating various types of raw data, the multi-source data fusion module effectively solves the problems of inconsistent data formats, differences in coordinate systems, and uneven data quality in traditional technologies. The application of high-precision coordinate transformation algorithms and iterative closest point space registration technology ensures the accuracy and efficiency of data fusion. At the same time, the extraction of key geometric features and the establishment of corresponding relationships between multi-source data greatly reduce manual intervention and improve processing efficiency.

[0026] Furthermore, the model generation module flow chart is as follows Figure 3As shown, it specifically includes: receiving a three-dimensional point cloud data set generated by a multi-source data fusion module; using a deep learning classification algorithm to classify the three-dimensional point cloud data set, separating the building point cloud from other element point clouds (such as vegetation, terrain), and obtaining building point cloud data; using a semantic segmentation network to process the building point cloud data, identifying the main components of the building, including walls, roofs, foundations, etc., and adding semantic labels to each element; extracting key geometric features from the building point cloud data, including building corners, edge lines and feature planes; based on the key geometric features, using parametric modeling technology to construct a model framework of a real estate building, including a main structure and key building elements; optimizing the model framework, automatically identifying and adding secondary building elements through a preset building rule library, and iteratively adjusting model parameters to obtain a parametric three-dimensional building model; verifying the accuracy of the generated parametric three-dimensional building model, calculating the geometric deviation by comparing it with the original point cloud data, and generating a model quality report.

[0027] Preferably, classifying the three-dimensional point cloud data set using a deep learning classification algorithm includes the following steps: dividing the preprocessed point cloud data into three-dimensional grids of a fixed size, extracting local features in each grid, including height distribution, normal vector distribution and geometric features; constructing a deep learning network model based on a multi-layer perceptron (MLP) for learning local and global features of point clouds; preparing a training data set, including manually annotated samples of building point clouds, terrain point clouds, vegetation point clouds, etc.; using the prepared training data set to train the deep learning network model, using a cross entropy loss function and a stochastic gradient descent (SGD) optimizer to iteratively optimize network parameters; inputting the three-dimensional point cloud data to be classified into the trained network model to obtain a category prediction result for each point; post-processing the classification results, including statistical filtering and connected domain analysis, to improve the spatial consistency of the classification; outputting the classified point cloud data, wherein the building point cloud is extracted separately for subsequent building modeling process.

[0028] In traditional 3D building model construction technology, fixed geometric shapes and predefined templates are usually used to create building models. This method has the following problems: first, it is difficult to accurately reflect the geometric characteristics of complex buildings, especially for non-standard or historical buildings; second, the model lacks flexibility and is difficult to quickly adjust according to actual measurement data; third, traditional methods often require a lot of manual intervention, which is time-consuming, labor-intensive and inefficient. In addition, traditional models are difficult to meet different accuracy requirements and cannot achieve multi-scale expression.

[0029] In this regard, the use of parametric modeling technology to construct a model framework of a building includes: using a plane fitting algorithm to process the plane features in the key geometric features to determine the main planes of the building, including the wall, ground and roof planes; based on the fitted plane features, calculating the contour lines and edge lines of the building to form the skeleton structure of the building; according to the skeleton structure, determining the main geometric parameters of the building, including length, width and height; based on the main geometric parameters, constructing a parametric main structure model of the building, including walls, floor slabs and roofs; according to the semantic segmentation results, identifying the positions and sizes of key building elements, wherein the key building elements include columns, beams and stairs; adding the key building elements to the parametric main structure model to form a real estate building model framework.

[0030] Furthermore, secondary building elements are automatically identified and added through a preset building rule library, wherein the secondary building elements include windows, doors and balconies; the actual measurement data and model parameters are compared with the least squares method to calculate the parameter deviation; the model parameters are iteratively adjusted according to the parameter deviation using a gradient descent algorithm; the three steps of comparison, calculation and adjustment are repeated until the parameter deviation is less than a predetermined threshold or the maximum number of iterations is reached; and a final parametric three-dimensional building model is generated based on the optimized model parameters.

[0031] Preferably, the model generation module of the present invention significantly improves the construction efficiency and accuracy of three-dimensional building models by introducing deep learning and parametric modeling technology. The application of deep learning classification algorithms and semantic segmentation networks realizes the precise extraction of building point clouds and the intelligent identification of main components, greatly reducing manual intervention. The introduction of parametric modeling technology enables the model to flexibly adapt to complex architectural geometric features, especially for non-standard or historical buildings, providing more accurate expression. The application of the building rule library further automates the process of adding secondary architectural elements and improves the integrity of the modeling. At the same time, the iterative optimization algorithm ensures a high degree of consistency between the model and the actual building. This method not only overcomes the limitations of traditional fixed geometric shapes and predefined templates, but also realizes the multi-scale expression of the model, meets different accuracy requirements, and lays the foundation for high-quality three-dimensional real estate surveying and mapping.

[0032] Furthermore, the specific process of the spatial relationship analysis module is as follows: receiving parameterized three-dimensional building model data; performing spatial decomposition on the parameterized three-dimensional building model to identify independent building units; extracting the geometric features and semantic features of each building unit, including position coordinates, outer contours, height, volume and functional attributes; constructing a topological relationship matrix between building units, wherein the matrix elements represent the spatial relationship types between building units; using the R-tree spatial indexing algorithm, analyzing and determining the spatial relationships between building units, including adjacency, inclusion, intersection and overlap, to generate analysis results; based on the topological relationship matrix and the analysis results, generating a relationship diagram representing the spatial structure of the building complex; using the relationship diagram to calculate key surveying and mapping indicators, including building density, volume ratio, green space ratio and building spacing; associating the relationship diagram with the calculated surveying and mapping indicators to generate a comprehensive surveying and mapping indicator report containing spatial distribution information; performing three-dimensional visualization processing on the relationship diagram and the comprehensive surveying and mapping indicator report to generate an interactive spatial relationship display interface; outputting the spatial relationship analysis results, including a visualized relationship diagram, a detailed surveying and mapping indicator report and digitized spatial relationship data.

[0033] Among them, using the R-tree spatial index algorithm to analyze and determine the spatial relationship between building units includes the following: constructing a minimum bounding rectangle (MBR) for each building unit, which contains all the geometric features of the building unit; constructing an R-tree index structure based on the MBR of the building unit to organize the spatial data into a hierarchical tree structure; pre-defining spatial relationship types, including but not limited to adjacent, contained, intersecting and overlapping, and formulating judgment criteria for each relationship type; for each building unit, using the R-tree index to perform spatial query to filter out other building units that may have spatial relationships; for each pair of filtered building units, determining their specific spatial relationship according to the predefined judgment criteria; for special cases, such as when the height difference of the building units is large, additional three-dimensional spatial relationships are considered, such as upper and lower overlaps; the analyzed spatial relationships are stored in a relationship matrix, and the matrix elements represent the spatial relationship types between the building unit pairs; Optimize the results of spatial relationship analysis, including merging duplicate relationships and resolving potential conflicting relationships; output the optimized spatial relationship matrix.

[0034] Furthermore, the efficient rendering module of the present invention is designed to solve the visualization and interaction problems of large-scale three-dimensional real estate data. The module first receives the parametric three-dimensional building model generated by the model generation module and the analysis results of the spatial relationship analysis module. In order to cope with the rendering pressure brought by massive data, the dynamic level of detail (LOD) technology is introduced to automatically adjust the detail level of the model according to the observation angle, effectively balancing the display effect and rendering performance. Considering the complexity of city-level real estate data, this module adopts an improved spatial indexing algorithm to greatly improve the scene loading speed and display efficiency. This enables users to smoothly browse a large range of three-dimensional urban environments, laying the foundation for subsequent analysis work.

[0035] In addition, in order to better display the results of spatial relationship analysis, this module innovatively links surveying and mapping indicators with three-dimensional scenes. For example, the distribution of building density or volume ratio can be intuitively presented through color coding.

[0036] Furthermore, the present invention fully considers the sensitivity and importance of real estate surveying and mapping data, and specially designs a data security module. This module can not only strictly control data access, but also record all operations in detail. Its core is a flexible permission management mechanism that can accurately allocate data access rights according to the user's role and responsibilities. The module also introduces encryption technology, such as the AES encryption algorithm, to ensure the security of data during storage and transmission.

[0037] Furthermore, the present embodiment also provides a data processing method for three-dimensional real estate surveying and mapping, including importing original surveying and mapping data and converting it into a three-dimensional point cloud data set in a unified format; generating a parametric three-dimensional building model based on the three-dimensional point cloud data set; constructing a relationship diagram of the parametric three-dimensional building model, and generating a surveying and mapping indicator report; processing large-scale three-dimensional real estate data and generating an interactive three-dimensional scene display; controlling access to real estate surveying and mapping data according to user permissions, and generating an operation log.

[0038] In summary, the three-dimensional real estate surveying and mapping data processing system provided by the present invention has multiple technical advantages. Its multi-source data fusion module can effectively integrate data in different formats and coordinate systems, improve data quality and processing efficiency, and provide a reliable foundation for subsequent modeling. The model generation module introduces deep learning and parametric modeling technology to achieve accurate identification and efficient modeling of buildings, and can better adapt to the modeling needs of complex building structures. The spatial relationship analysis module adopts the R-tree spatial indexing algorithm to improve the efficiency and accuracy of spatial relationship analysis between building units, and provides useful data support for urban planning and management. The efficient rendering module improves the visualization effect and interactive experience of large-scale three-dimensional data through dynamic level of detail technology and improved spatial indexing algorithm.

[0039] Example 2, reference Figure 1~Figure 3 , which is the second embodiment of the present invention, provides a data processing system for three-dimensional real estate surveying and mapping. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0040] To verify the effectiveness of the invention, the researchers conducted field tests in the core business district of a provincial capital city. The test area covers about 3 square kilometers and contains 187 buildings, including high-rise office buildings, commercial complexes, and residential buildings. The experiment used a DJI Matrice 300 RTK drone equipped with a Zenmuse P1 camera for oblique photogrammetry, a Leica RTC360 laser scanner to obtain ground point cloud data, and combined RTK-GNSS measurement to obtain control point data.

[0041] During the data processing phase, the multi-source data fusion module successfully integrated approximately 50 million laser point clouds and 800GB of oblique photography image data. Through high-precision coordinate transformation and iterative closest point registration algorithm, a registration accuracy of 1.5 cm was achieved. The model generation module uses an improved PointNet++ deep learning network for point cloud classification, with a classification accuracy of 95.7%. During the parametric modeling process, the reconstruction accuracy of complex buildings was improved by 22%, and the modeling time was reduced by 45% compared with traditional methods.

[0042] The spatial relationship analysis module constructed a building relationship diagram containing 187 nodes and calculated key indicators such as the average building density (32%), volume ratio (3.8) and green area ratio (18%) in the area. When processing 3D scenes within a 3 square kilometer range, the efficient rendering module increased the average frame rate from the original 18fps to a stable 45fps through dynamic LOD technology, and shortened the scene loading time from the original 35 seconds to 12 seconds. The data security module successfully blocked 18 unauthorized access attempts and generated more than 7,000 detailed operation logs.

[0043] In order to more intuitively demonstrate the advantages of the present invention, the researchers compared the performance of the traditional method and the present invention in various key indicators, as shown in Table 1.

[0044] Table 1 Comparison of the present invention and the prior art in key performance indicators Performance Indicators The present invention Prior art Modeling efficiency 3.3 hours / building 6 hours / building Modeling accuracy (complex buildings) 95% 88% Spatial analysis time 1 hour 2.5 hours Scene rendering frame rate 45fps 18fps Scene loading time 12s 35s Unauthorized access interception rate 98% 85% As can be seen from Table 1, the present invention has achieved significant improvements in various key indicators. Especially in terms of modeling accuracy and modeling efficiency, the improvement is relatively large. These advances not only improve the work efficiency of three-dimensional real estate surveying and mapping, but also significantly improve the accuracy and visualization quality of data processing. In terms of scene rendering performance, improvements in frame rate and loading time provide users with a smoother interactive experience. At the same time, the enhancement of data security also provides more reliable protection for sensitive real estate information. These improvements jointly promote the development of three-dimensional real estate surveying and mapping technology in a more efficient, more accurate and safer direction, and provide more powerful technical support for urban planning and real estate management.

[0045] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A data processing system for three-dimensional real estate surveying and mapping, characterized in that: include: Multi-source data fusion module, used to convert raw data in real estate surveying and mapping into a 3D point cloud dataset in a unified format; A model generation module, used to generate a parameterized three-dimensional building model based on the three-dimensional point cloud data set; A spatial relationship analysis module, used to construct a relationship diagram of the parametric three-dimensional building model and generate a surveying and mapping indicator report; An efficient rendering module for processing large-scale 3D real estate data and generating interactive 3D scene displays; The data security module is used to control access to real estate surveying and mapping data based on user permissions and generate operation logs.

2. The data processing system for three-dimensional real estate surveying and mapping according to claim 1, characterized in that: The process of the multi-source data fusion module is as follows: Import raw data; Performing data preprocessing on the original data to obtain preprocessed data; Converting the preprocessed data into a unified coordinate system to obtain multi-source data with consistent coordinates; Performing spatial registration on the multi-source data, and generating and fusing three-dimensional point cloud data based on the multi-source data after spatial registration; The fused 3D point cloud data is processed to form a 3D point cloud data set in a unified format.

3. The data processing system for three-dimensional real estate surveying and mapping according to claim 1, characterized in that: The process of the model generation module includes: Classify the three-dimensional point cloud data set to obtain building point cloud data; Performing semantic segmentation on the building point cloud data to identify the main components of the building; extracting key geometric features from the building point cloud data; Based on the key geometric features, a model framework of the building is constructed using parametric modeling technology; Optimizing the model framework, adding architectural elements through an architectural rule library, and obtaining a parametric three-dimensional architectural model; The accuracy of the parametric three-dimensional building model is verified and a model quality report is generated.

4. The data processing system for three-dimensional real estate surveying and mapping according to claim 3, characterized in that: The model framework of the building constructed by using parametric modeling technology includes: Use plane fitting algorithms to process key geometric features and determine the main planes of the building; Based on the fitted plane features, the building's contour lines and edge lines are calculated to form the building's skeleton structure; Determine the main geometric parameters of the building according to the skeleton structure; Based on the main geometric parameters, construct a parametric main structure model of the building; Based on the semantic segmentation results, identify the location and size of key building elements; The key building elements are added to the parametric main structure model to form a model framework of the building.

5. The data processing system for three-dimensional real estate surveying and mapping according to claim 1, characterized in that: The specific process of the spatial relationship analysis module includes: Receiving parametric three-dimensional building model data; Performing spatial decomposition on the parameterized three-dimensional building model to identify independent building units; Extract the geometric and semantic features of each building unit and construct the topological relationship matrix between building units; Use the R-tree spatial index algorithm to analyze and determine the spatial relationship between building units and generate analysis results; Based on the topological relationship matrix and the analysis results, a relationship diagram representing the spatial structure of the building complex is generated, and key surveying and mapping indicators are calculated using the relationship diagram; The relationship diagram is associated with the key surveying and mapping indicators to generate a comprehensive surveying and mapping indicator report.

6. The data processing system for three-dimensional real estate surveying and mapping according to claim 5, characterized in that: The method of analyzing and determining the spatial relationship between building units using the R-tree spatial index algorithm comprises the following steps: Construct a minimum bounding rectangle MBR for each building unit; An R-tree index structure is constructed based on the MBR of building units to organize spatial data into a hierarchical tree structure; Defining spatial relationship types and establishing judgment criteria for each relationship type, wherein the spatial relationship types include adjacent, contained, intersecting and overlapping; For each building unit, the R-tree index is used to perform spatial query to filter out other building units that may have spatial relationships; For each pair of building units selected, the specific spatial relationship is determined according to the established judgment criteria.

7. The data processing system for three-dimensional real estate surveying and mapping according to claim 1, characterized in that: The original data includes laser scanning point cloud data, oblique photography image data, total station measurement data, GNSS measurement data, drone aerial image data, existing two-dimensional cadastral map data and topographic map data.

8. A data processing method for three-dimensional real estate surveying and mapping, based on the data processing system for three-dimensional real estate surveying and mapping according to any one of claims 1 to 7, characterized in that: include: Import original surveying and mapping data and convert it into a 3D point cloud dataset in a unified format; generating a parametric three-dimensional building model based on the three-dimensional point cloud data set; Constructing a relationship diagram of the parametric three-dimensional building model and generating a surveying and mapping indicator report; Process large-scale 3D real estate data and generate interactive 3D scene displays; Control access to real estate surveying and mapping data based on user permissions and generate operation logs.

Images