Multidimensional Data Comprehensive Processing Method and System for Real Estate Surveying and Mapping

Abstract

The present invention discloses a multi-dimensional data comprehensive processing method and system for real estate surveying and mapping, which relates to the technical field of real estate surveying and mapping and evaluation, and includes: comprehensively scanning the real estate area through lidar equipment, collecting multi-dimensional data including topographic data, spatial data, and attribute data, and preprocessing the data; using a data segmentation algorithm to identify and extract the elements of the real estate area, and then deeply analyzing the spatial distribution features, attribute features, and environmental correlation features through an adaptive convolutional neural network and a graph convolutional network; calculating the spatial distribution feature index, attribute feature index, and environmental correlation feature index to comprehensively evaluate the real estate area, finally generating a comprehensive score for each area, and dividing the real estate area into important areas and ordinary areas according to the score; combining real-time surveying and mapping and a dynamic adjustment mechanism to optimize the data collection frequency and processing parameters of different areas, and realizing intelligent data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of real estate surveying and mapping and evaluation, and specifically relates to a multi-dimensional data comprehensive processing method and system for real estate surveying and mapping. Background Art

[0002] With the continuous advancement of the urbanization process, the planning, evaluation, and management of real estate play an increasingly important role in urban development. Traditional real estate evaluation methods mostly rely on manual surveys and manual measurements, and cannot fully utilize the advantages of modern technologies, resulting in low efficiency and accuracy of data collection. With the development of lidar (LiDAR), remote sensing technology, and computer vision technology, it has become possible to obtain multi-dimensional data of real estate areas, which include not only terrain and building shapes, but also attribute information of real estate such as area, volume, and use. However, how to accurately and comprehensively analyze these multi-dimensional data and effectively extract features related to real estate evaluation is still a major challenge faced by current technologies.

[0003] The existing technologies have the following deficiencies:

[0004] Most existing real estate evaluation methods use single data sources or traditional spatial analysis technologies, and there are many deficiencies in the feature extraction and analysis processes. First of all, many traditional methods rely on static models when extracting spatial distribution features and cannot effectively handle the precise analysis of irregular shapes and complex regions, resulting in low accuracy when dealing with complex regions. Secondly, existing attribute feature extraction methods usually ignore the high-frequency changes in the data, resulting in inaccurate prediction results, especially when dealing with large-scale data, the decline in accuracy is particularly obvious. Moreover, the analysis of environmental factors often stays on static models and cannot reflect the impact of dynamic changes such as traffic flow and facility usage on real estate in real time. Generally speaking, existing technologies cannot fully integrate different features of multi-dimensional data, resulting in the lack of comprehensiveness and timeliness in the evaluation and decision-making support for real estate areas. Therefore, there is an urgent need for an innovative method that can effectively integrate multi-dimensional data, improve the accuracy of feature extraction, and have dynamic adaptability to cope with the complex challenges in modern urban real estate evaluation. Summary of the Invention

[0005] The purpose of the present invention is to provide a multi-dimensional data comprehensive processing method and system for real estate surveying and mapping to solve the problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A multi-dimensional data comprehensive processing method for real estate surveying and mapping includes the following steps:

[0008] Use lidar to collect multi-dimensional data of real estate, including terrain data, spatial data, and attribute data, and preprocess the collected data to reduce noise and optimize the integrity and accuracy of the data;

[0009] Identify and separate the feature areas in real estate through a data segmentation algorithm, including: boundary lines, building outlines, and terrain features, analyze the feature areas, and extract the spatial distribution features, attribute features, and environmental correlation features of the feature areas;

[0010] Analyze the spatial distribution features, attribute features, and environmental correlation features of each feature area respectively. According to the analysis results, calculate the spatial distribution feature index, attribute feature index, and environmental correlation feature index within each feature area;

[0011] Among them, the spatial distribution features include: position coordinates and shape, the attribute features include: area, volume, and use, and the environmental correlation features include: surrounding facilities and road networks;

[0012] Conduct a comprehensive analysis of the spatial distribution feature index, attribute feature index, and environmental correlation feature index. According to the analysis results, generate a comprehensive score for each real estate feature area;

[0013] According to the comprehensive score, divide the real estate feature areas into important areas and ordinary areas;

[0014] Combine real-time mapping and dynamic adjustment mechanisms to optimize the data collection frequency and processing parameters of different categories of real estate feature areas, and achieve intelligent data processing for different mapping targets.

[0015] Preferably, the identifying and separating the feature areas in real estate through a data segmentation algorithm specifically includes:

[0016] Perform multi-scale segmentation on the real estate data collected by lidar. The data includes terrain data, spatial data, and attribute data, and use the local area feature coefficient for data preprocessing and optimization;

[0017] Among them, the calculation expression of the local area feature coefficient is:

[0018] ;

[0019] In the formula, represents the attribute value of the th data point, represents the collected data point, represents the average attribute value of the area, is the total number of data points, is the local area feature coefficient, represents the area position coordinates;

[0020] The region is segmented using geometric analysis methods, and the normal vector and local curvature of each data point are calculated;

[0021] Among them, the calculation expression of the normal vector is:

[0022] ;

[0023] Among them, the calculation expression of the local curvature is:

[0024] ;

[0025] In the formula, represents the normal vector of the data point, represents the Laplace operator of the data point, represents the gradient of the data point, represents the local curvature of the data point;

[0026] According to the normal vector and local curvature of each data point, the region score of each region is calculated for identifying the feature region, and the calculation expression is:

[0027] ;

[0028] In the formula, represents the region score, and represent preset proportionality coefficients, and and are both greater than 0;

[0029] Judge whether the region score of each region is greater than or equal to the preset threshold. If so, it is identified as a feature region; if not, it is identified as a non-feature region.

[0030] Preferably, the feature region is analyzed to extract the spatial distribution characteristics, attribute characteristics and environmental association characteristics of the feature region, specifically including:

[0031] The spatial distribution characteristics of the real estate region are extracted through multiple convolutional layers and pooling layers of the convolutional neural network, including geometric characteristics of position, shape, boundary and contour, specifically including:

[0032] The convolution operation is performed on the real estate region data using a convolution kernel to extract the boundary line of the building, terrain features and building contour;

[0033] Through the adaptive pooling operation, the pooling factor and the convolution kernel size are dynamically adjusted, so that the convolutional neural network can effectively extract the spatial features at different scales;

[0034] Through the joint learning network, fuse the spatial data and attribute data of real estate, and extract the attribute features of the real estate area, including:

[0035] While using the convolutional layer to extract spatial features, use the fully connected layer to map the spatial features and attribute data to predict the attributes of the building;

[0036] Adopt the regression analysis method to predict the physical attributes of the real estate area;

[0037] Through the combination of graph theory and graph convolutional network with convolutional neural network, extract the correlation features between the real estate area and its surrounding environment, including:

[0038] Model the real estate area and its surrounding environment as graphic data, use the graph convolutional network to extract the correlation features between the real estate and its surrounding environment, and calculate the shortest path and accessibility environmental factors between the real estate and surrounding facilities;

[0039] Through the joint learning of environmental data and the spatial features output by the convolutional neural network, extract the environmental impact features of the real estate area.

[0040] Preferably, the acquisition process of the spatial distribution feature index is as follows:

[0041] Extract the spatial distribution features of the feature area, including the geometric features of position, shape, boundary and contour, and generate a spatial data point set , where each point represents the spatial coordinates of an element in the real estate area, represents the number of acquisition points, represents the th position coordinate of the acquisition point, represents the total number of acquisition points;

[0042] Apply the density clustering algorithm to the extracted spatial data point set , preset the neighborhood radius as , and set the density threshold, and divide the spatial data points into multiple clustering regions according to their density relationship , where each clustering region contains element points ;

[0043] Calculate the spatial distribution feature parameters of each clustering region;

[0044] Calculate the area of the region, and the calculation expression is:

[0045] ;

[0046] Among them, represents the clustering region The area, representing the convex hull boundary points of the area;

[0047] Calculate the area density, and the calculation expression is:

[0048] ;

[0049] In the formula, represents the area density of the th acquisition point, represents the number of points within the clustering area ;

[0050] Calculate the morphological complexity, and the calculation expression is:

[0051] ;

[0052] In the formula, represents the fractal dimension of the area;

[0053] Based on the comprehensive calculation of the area, area density, and morphological complexity of each clustering area, calculate the spatial distribution characteristic index of the area, and the calculation expression is:

[0054] ;

[0055] In the formula, represents the value of the largest area among all clustering areas, represents the maximum density value among all clustering areas, represents the spatial distribution characteristic index of the clustering area.

[0056] Preferably, the process of obtaining the attribute characteristic index is:

[0057] Extract the attribute characteristics of the feature area, including: area, volume, and usage;

[0058] Construct the attribute characteristics into an attribute vector ;

[0059] Perform Haar wavelet transform on the attribute vector to decompose the attribute characteristics into low-frequency components and high-frequency components, represents the area corresponding to the th acquisition point, specifically including:

[0060] Perform recursive Haar wavelet transform on the attribute data to decompose the data vector into low-frequency and high-frequency components at multiple levels, and the calculation expression is:

[0061] ;

[0062] In the formula, and are two adjacent attribute data, and are the low-frequency and high-frequency components of the first layer respectively;

[0063] Repeat the decomposition process, decompose the low-frequency component continuously to obtain the low-frequency and high-frequency components of a higher level, and the calculation expression is:

[0064] ;

[0065] In the formula, represents the low-frequency component of the th layer, represents the high-frequency component of the th layer, represents the number of layers;

[0066] According to the low-frequency and high-frequency components obtained by Haar wavelet transform, calculate the attribute characteristic index of the real estate element area, and the calculation expression is:

[0067] ;

[0068] In the formula, represents the attribute characteristic index within the real estate element area, and are preset weight coefficients, and and sum to 1.

[0069] Preferably, the process of obtaining the environmental correlation characteristic index is:

[0070] Extract the environmental correlation characteristics of the real estate element area, and the environmental correlation characteristics include: surrounding facilities and road network;

[0071] Construct an environmental characteristic vector , represents the area corresponding to the th collection point;

[0072] Perform Fourier transform on the environmental characteristic vector to convert the time-domain signal into a frequency-domain signal, and the calculation expression is:

[0073] ;

[0074] Among them, represents the value of the frequency-domain signal at the th frequency point, represents the frequency point, represents the number of environmental characteristic data, represents the total number of environmental characteristic data, represents the imaginary unit, represents the th environmental characteristic data in the time-domain signal;

[0075] Calculate the amplitude of the frequency components after Fourier transform. The calculation expression is:

[0076] ;

[0077] where is the amplitude of the th frequency component;

[0078] Use the mean calculation expression to calculate the average frequency of all frequency components, and use the difference between the maximum frequency value and the minimum frequency value to calculate the frequency range value;

[0079] Calculate the environmental correlation characteristic index. The calculation expression is:

[0080] ;

[0081] In the formula, represents the average frequency of all frequency components, represents the frequency range value, represents the environmental correlation characteristic index.

[0082] Preferably, comprehensively analyze the spatial distribution characteristic index, the attribute characteristic index, and the environmental correlation characteristic index, and generate a comprehensive score for each real estate element area according to the analysis results. Specifically, it includes:

[0083] Obtain the spatial distribution characteristic index, the attribute characteristic index, and the environmental correlation characteristic index of the real estate element area, and perform normalization calculation processing on the spatial distribution characteristic index, the attribute characteristic index, and the environmental correlation characteristic index to obtain the comprehensive score of the real estate element area.

[0084] Preferably, divide the real estate element area into important areas and ordinary areas according to the comprehensive score. Specifically, it includes:

[0085] Judge whether the comprehensive score of each real estate element area is greater than or equal to the preset threshold. If so, it means that the corresponding area is an important area and is marked as an important area. If not, it means that the corresponding area is an ordinary area and is marked as an ordinary area.

[0086] Preferably, combine real-time surveying and mapping and a dynamic adjustment mechanism to optimize the data collection frequency and processing parameters of different categories of real estate element areas, and realize intelligent data processing for different surveying and mapping targets. Specifically, it includes:

[0087] According to the spatial distribution characteristics, attribute characteristics, and environmental association characteristics of different real estate element regions, a classification model is established to classify real estate element regions into multiple categories. The classification basis includes, but is not limited to, the type, area, shape, and surrounding environment of the real estate;

[0088] According to the classification results of each real estate element region, dynamically adjust the data collection frequency;

[0089] According to the classification results of each real estate element region and real-time surveying and mapping data, optimize the data processing parameters;

[0090] According to the feedback data of real-time surveying and mapping, continuously optimize the data collection frequency and processing parameters of different category regions through machine learning algorithms;

[0091] Based on historical data and surveying and mapping accuracy feedback, adjust the parameters of the model;

[0092] Through an adaptive mechanism, evaluate the characteristic change trend of different regions and dynamically adjust the computational complexity;

[0093] For the dynamically adjusted data collection frequency and processing parameters, optimize the computational performance of the entire system;

[0094] Generate a real-time feedback mechanism, and automatically update the characteristic classification of the real estate region according to the new collected data and processing results.

[0095] A multi-dimensional data comprehensive processing system for real estate surveying and mapping, including:

[0096] A data collection module, which uses lidar to collect multi-dimensional data of real estate, including terrain data, spatial data, and attribute data, and preprocesses the collected data to reduce noise and optimize the integrity and accuracy of the data;

[0097] An element region identification module, which identifies and separates the element regions in the real estate through a data segmentation algorithm, including: boundary lines, building outlines, and terrain features,

[0098] A feature extraction module, which analyzes the element regions and extracts the spatial distribution characteristics, attribute characteristics, and environmental association characteristics of the element regions;

[0099] A feature index calculation module, which analyzes the spatial distribution characteristics, attribute characteristics, and environmental association characteristics of each element region respectively, and calculates the spatial distribution feature index, attribute feature index, and environmental association feature index within each element region according to the analysis results;

[0100] A comprehensive analysis module that comprehensively analyzes the spatial distribution feature index, attribute feature index, and environmental association feature index, and generates a comprehensive score for each real estate element area according to the analysis results;

[0101] A regional division module that divides the real estate element area into important areas and ordinary areas according to the comprehensive score;

[0102] A dynamic adjustment module that combines real-time surveying and mapping and a dynamic adjustment mechanism to optimize the data collection frequency and processing parameters of different categories of real estate element areas, and realizes intelligent data processing for different surveying and mapping objectives.

[0103] The beneficial effects of the present invention:

[0104] (1) The present invention accurately collects multi-dimensional data of real estate through lidar technology, covering terrain data, spatial data, and attribute data, and combines advanced deep learning algorithms such as adaptive convolutional neural networks and graph convolutional networks to improve the extraction accuracy of spatial distribution, attribute features, and environmental association features of real estate areas. When facing buildings and areas with complex and irregular shapes, the present invention uses a dynamic adjustment mechanism to automatically optimize the size of the convolutional kernel and the selection of pooling factors according to the feature complexity of the area, and can more accurately capture subtle spatial and geometric changes, improving the flexibility and adaptability of feature extraction. Traditional methods usually use fixed convolutional kernels and pooling factors, which are difficult to adapt to the huge changes in the shape and structure of real estate areas. The present invention overcomes this problem through a dynamic mechanism, ensuring that accurate feature extraction can be obtained for buildings and areas of different scales and shapes.

[0105] Furthermore, the present invention uses a multi-level joint learning network to deeply fuse the spatial data and attribute data of real estate, breaking through the limitation of separate processing of spatial features and attribute features in traditional methods, and enhancing the collaborative ability of the model in multi-modal data analysis. The convolutional layer first extracts the spatial features of the real estate area, such as geometric features such as building shape, contour, and boundary line, and then through the fully connected layer, these spatial features are deeply mapped with the physical attributes of the real estate for attribute prediction. Through the regression analysis method, the network weights are adaptively adjusted during the training process, improving the accuracy of the model for predicting the attributes of known and unknown areas.

[0106] (2) By comprehensively analyzing the spatial distribution feature index, attribute feature index, and environmental correlation feature index of the real estate area, the present invention deeply excavates the inherent characteristics of the real estate area from multiple dimensions, improving the scientificity and accuracy of evaluation and decision-making. First, the calculation of the spatial distribution feature index not only considers the area, density, and morphological complexity of the area, but also comprehensively quantifies the geometric morphology of the real estate area through density clustering algorithms and normal vector calculations, achieving precise modeling of complex-shaped and different-scale areas. This method can automatically identify and extract the spatial distribution patterns of different regions, providing a solid foundation for subsequent analysis. Second, the construction of the attribute feature index uses Haar wavelet transform technology to perform multi-level decomposition on the physical attribute data of the real estate, finely capturing low-frequency and high-frequency changes, breaking through the limitation of ignoring details in traditional methods, ensuring accurate prediction of attributes such as building area, volume, and use, and improving the flexibility and accuracy of data processing. Finally, the design of the environmental correlation feature index combines Fourier transform to perform frequency-domain analysis on the dynamic changes in the surrounding environment, effectively capturing the impact of time-varying factors such as traffic flow and public facility usage on the real estate area. This real-time and dynamic analysis method enhances the accuracy of environmental features, especially suitable for the ever-changing urban environment, helps to optimize regional evaluation in real time, and provides support for intelligent decision-making. Through the highly integrated and precise analysis of these three feature indexes, the present invention provides a more scientific, timely, and accurate solution for real estate evaluation, planning, and decision-making. Especially when facing complex and dynamically changing regions, it can significantly improve the depth and breadth of data analysis and promote the intelligent development of the real estate industry. Description of the Drawings

[0107] Figure 1 is the specific step flowchart of the multi-dimensional data comprehensive processing method for real estate mapping of the present invention;

[0108] Figure 2 is the flowchart of the multi-dimensional data comprehensive processing system for real estate mapping in the present invention. Detailed Embodiments

[0109] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0110] Please refer to Figure 1 as shown, the present invention is a multi-dimensional data comprehensive processing method for real estate mapping, including the following steps:

[0111] Use lidar to collect multi-dimensional data of the real estate, including terrain data, spatial data, and attribute data, and preprocess the collected data to reduce noise and optimize the integrity and accuracy of the data;

[0112] Identify and separate the feature areas in the real estate through a data segmentation algorithm, including: boundary lines, building outlines, and terrain features. Analyze the feature areas to extract the spatial distribution features, attribute features, and environmental association features of the feature areas;

[0113] Analyze the spatial distribution features, attribute features, and environmental association features of each feature area respectively. According to the analysis results, calculate the spatial distribution feature index, attribute feature index, and environmental association feature index within each feature area;

[0114] Among them, the spatial distribution features include: position coordinates and shape, the attribute features include: area, volume, and use, and the environmental association features include: surrounding facilities and road network;

[0115] Conduct a comprehensive analysis of the spatial distribution feature index, attribute feature index, and environmental association feature index. According to the analysis results, generate a comprehensive score for each real estate feature area;

[0116] According to the comprehensive score, divide the real estate feature areas into important areas and ordinary areas;

[0117] Combine real-time surveying and mapping and a dynamic adjustment mechanism to optimize the data collection frequency and processing parameters for different categories of real estate feature areas, and achieve intelligent data processing for different surveying and mapping objectives.

[0118] Among them, use lidar to collect multi-dimensional data of real estate, including terrain data, spatial data, and attribute data. Preprocess the collected data to reduce noise and optimize the integrity and accuracy of the data. Specifically, it includes:

[0119] First, conduct a comprehensive scan of the real estate area through a lidar (LiDAR) device to obtain multi-dimensional data including terrain data, spatial data, and attribute data. The specific steps include: using the lidar to emit laser beams and measure the time of the reflected laser pulses, thereby calculating the distance and depth information to obtain high-precision three-dimensional point cloud data. Synchronize the positioning by carrying a GPS and an inertial measurement unit (IMU) to ensure the accuracy of the spatial data, and record spatial information such as terrain features, building outlines, and road networks in real time through laser scanning; at the same time, use sensors to obtain the attribute data of the ground objects, such as building height, area, use, and materials.

[0120] The collected multi-dimensional data will be preprocessed to reduce noise and optimize the integrity and accuracy of the data. The preprocessing steps include: removing outliers and extreme points, eliminating noise points in lidar data through filtering algorithms to improve the quality of point cloud data. Then, interpolation and data fusion techniques are used to complete the spatial data and attribute data to ensure the continuity and consistency of the data in different regions. Finally, for different surveying and mapping targets (such as terrain, buildings, roads, etc.), different processing strategies are adopted to optimize the data to ensure that the data accuracy meets the requirements of subsequent analysis and processing.

[0121] Identify and separate the feature regions in the real estate through data segmentation algorithms, including: boundary lines, building outlines, terrain features, analyze the feature regions, and extract the spatial distribution features, attribute features and environmental correlation features of the feature regions, specifically including:

[0122] Perform multi-scale segmentation on the real estate data collected by lidar, the data includes terrain data, spatial data and attribute data, and use the local region feature coefficient Perform preprocessing and optimization of the data;

[0123] Among them, the calculation expression of the local region feature coefficient is:

[0124] ;

[0125] In the formula, represents the attribute value of the th data point, represents the collected data point, represents the average attribute value of the region, is the total number of data points, is the local region feature coefficient, represents the region position coordinates;

[0126] Use geometric analysis methods to segment the region and calculate the normal vector and local curvature of each data point;

[0127] Among them, the calculation expression of the normal vector is:

[0128] ;

[0129] Among them, the calculation expression of the local curvature is:

[0130] ;

[0131] In the formula, represents the normal vector of the data point, represents the Laplacian operator of the data point, represents the gradient of the data point, Represents the local curvature of the data point;

[0132] According to the normal vector and local curvature of each data point, calculate the regional score of each region for identifying the feature region. The calculation formula is:

[0133] ;

[0134] In the formula, represents the regional score, and represent preset proportionality coefficients, and and are both greater than 0;

[0135] Judge whether the regional score of each region is greater than or equal to the preset threshold. If so, identify it as a feature region; if not, identify it as a non-feature region.

[0136] When extracting the spatial distribution characteristics of the real estate area, it is processed through an adaptive convolutional neural network architecture. Different from the static convolutional kernel and pooling factor of the existing technology, a dynamic adjustment mechanism is introduced to automatically adjust the convolutional kernel size and pooling factor according to the feature complexity of different regions. When facing buildings and regions with irregular shapes and large size variations, the network can dynamically optimize the convolutional operation according to local details, enhancing the flexibility of feature extraction. For example, geometric features such as the boundary lines of buildings, terrain undulations, and building outlines will be automatically adjusted by the convolutional kernel, so as to accurately extract the spatial features at different scales. In addition, the convolutional neural network not only extracts the overall geometric shape of the building, but also can distinguish subtle structural differences, solving the problem of insufficient extraction accuracy of traditional methods in complex regions.

[0137] In terms of attribute feature extraction, through a multi-level joint learning network, the spatial data and attribute data of real estate are fused, breaking through the limitation of separate processing of spatial features and attribute features in traditional methods. First, the convolutional layer extracts the spatial distribution characteristics of the real estate area, such as the shape and outline of the building; then, through the fully connected layer, the extracted spatial features are deeply mapped with the attribute data of the real estate (such as building area, floor height, functional use, etc.) for attribute prediction. In order to enhance the prediction accuracy, the present invention further adopts a regression analysis method to accurately predict the physical attributes of each region by adaptively adjusting the weights during the training process. This method can not only effectively predict the attributes of known regions, but also infer the attributes of unknown regions based on the surrounding environment, with high flexibility and adaptability.

[0138] The extraction of environment-related features adopts a method that combines a graph convolutional network (GCN) and a convolutional neural network (CNN) to simultaneously process the complex relationships of spatial data and environmental data. By modeling the real estate area and its surrounding environment (such as roads, public facilities, traffic flow) as a graph structure, the present invention uses a graph convolutional network to process environmental data and combines the spatial distribution features extracted by the CNN to jointly learn the correlation between the real estate and its surrounding environment. The innovation lies in not only considering the static graph structure but also introducing time series data, such as the dynamic changes in traffic flow and facility usage, enabling the model to update and accurately evaluate the relationship between the real estate and its surrounding facilities in real time. Through this dynamic graph convolutional network, a more comprehensive understanding of the environmental impact of the real estate area can be achieved, including the shortest path, accessibility, and the influence of surrounding facilities, providing higher-precision environmental features for regional assessment.

[0139] Analyze the spatial distribution feature attributes and environment-related features of each element area. According to the analysis results, calculate the spatial distribution feature index, attribute feature index, and environment-related feature index within each element area, specifically including:

[0140] The process of obtaining the spatial distribution feature index is as follows:

[0141] Extract the spatial distribution features of the element area, including position, shape, boundary, and contour geometric features, to generate a spatial data point set , where each point represents the spatial coordinates of an element in the real estate area, represents the number of collection points, represents the th collection point's position coordinates, represents the total number of collection points;

[0142] Apply the density clustering algorithm to the extracted spatial data point set , with a preset neighborhood radius of , and set the density threshold to divide the spatial data points into multiple clustering regions according to their density relationships , where each clustering region contains element points ;

[0143] Calculate the spatial distribution feature parameters for each clustering region;

[0144] Calculate the area of the region, and the calculation expression is:

[0145] ;

[0146] Among them, represents the clustering region The area, represent the convex hull boundary points of the region;

[0147] Calculate the regional density, and the calculation expression is:

[0148] ;

[0149] In the formula, represents the regional density of the th acquisition point, represents the number of points within the clustering region ;

[0150] Calculate the morphological complexity, and the calculation expression is:

[0151] ;

[0152] In the formula, represents the fractal dimension of the region;

[0153] Based on the comprehensive calculation of the regional area, regional density, and morphological complexity of each clustering region, calculate the spatial distribution characteristic index of the region, and the calculation expression is:

[0154] ;

[0155] In the formula, represents the value of the largest area among all clustering regions, represents the maximum density value among all clustering regions, represents the spatial distribution characteristic index of the clustering region;

[0156] The process of obtaining the attribute characteristic index is as follows:

[0157] Extract the attribute characteristics of the feature region, including: area, volume, and usage;

[0158] Construct the attribute characteristics into an attribute vector ;

[0159] Perform Haar wavelet transform on the attribute vector to decompose the attribute characteristics into low-frequency components and high-frequency components, represents the region corresponding to the th acquisition point, specifically including:

[0160] Perform recursive Haar wavelet transform on the attribute data to decompose the data vector into low-frequency and high-frequency components at multiple levels, and the calculation expression is:

[0161] ;

[0162] In the formula, and are two adjacent attribute data and are the low-frequency and high-frequency components of the first layer respectively;

[0163] Repeat the decomposition process, decompose the low-frequency component continuously to obtain the low-frequency and high-frequency components of a higher level. The calculation expression is:

[0164] ;

[0165] In the formula, represents the low-frequency component of the th layer, represents the high-frequency component of the th layer, represents the layer number;

[0166] According to the low-frequency and high-frequency components obtained by Haar wavelet transform, calculate the attribute characteristic index of the real estate element area. The calculation expression is:

[0167] ;

[0168] In the formula, represents the attribute characteristic index within the real estate element area, and are preset weight coefficients, and and sum to 1;

[0169] The acquisition process of the environmental correlation characteristic index is as follows:

[0170] Extract the environmental correlation characteristics of the real estate element area. The environmental correlation characteristics include: surrounding facilities and road network;

[0171] Construct an environmental feature vector , represents the area corresponding to the th collection point;

[0172] Perform Fourier transform on the environmental feature vector to convert the time-domain signal into a frequency-domain signal. The calculation expression is:

[0173] ;

[0174] Among them, represents the value of the frequency-domain signal at the th frequency point, represents the frequency point, represents the number of environmental feature data, represents the total number of environmental feature data, represents the imaginary unit, representing the th environmental characteristic data in the time-domain signal;

[0175] Calculate the amplitude of the frequency components after Fourier transform, and the calculation expression is:

[0176] ;

[0177] where is the amplitude of the th frequency component;

[0178] Use the mean calculation expression to calculate the average frequency of all frequency components, and use the difference between the maximum frequency value and the minimum frequency value to calculate the frequency extreme difference;

[0179] Calculate the environmental correlation characteristic index, and the calculation expression is:

[0180] ;

[0181] In the formula, represents the average frequency of all frequency components, represents the frequency extreme difference, represents the environmental correlation characteristic index.

[0182] Conduct a comprehensive analysis of the spatial distribution characteristic index, attribute characteristic index, and environmental correlation characteristic index. According to the analysis results, generate a comprehensive score for each real estate element area, specifically including:

[0183] Obtain the spatial distribution characteristic index, attribute characteristic index, and environmental correlation characteristic index of the real estate element area, conduct normalization calculation processing on the spatial distribution characteristic index, attribute characteristic index, and environmental correlation characteristic index, and obtain the comprehensive score of the real estate element area. The calculation expression is:

[0184] ;

[0185] In the formula, represents the comprehensive score of the real estate element area, represents the attribute characteristic index of the real estate element area, represents the spatial distribution characteristic index of the real estate element area, represents the environmental correlation characteristic index of the real estate element area, , and are preset proportionality coefficients, and , and are all greater than 0.

[0186] According to the comprehensive score, the real estate element areas are divided into important areas and ordinary areas, specifically including:

[0187] Judge whether the comprehensive score of each real estate element area is greater than or equal to the preset threshold. If so, it means the corresponding area is an important area and is marked as an important area. If not, it means the corresponding area is an ordinary area and is marked as an ordinary area.

[0188] Combined with real-time surveying and mapping and dynamic adjustment mechanisms, optimize the data collection frequency and processing parameters for different categories of real estate element areas to achieve intelligent data processing for different surveying and mapping objectives, specifically including:

[0189] Based on the spatial distribution characteristics, attribute characteristics, and environmental correlation characteristics of different real estate element areas, establish a classification model to divide the real estate element areas into multiple categories. The classification basis includes but is not limited to the type, area, shape, and surrounding environment of the real estate;

[0190] According to the classification results of each real estate element area, dynamically adjust the data collection frequency. Specifically, for important areas (such as large commercial areas, high-risk areas), increase the data collection frequency and improve the collection accuracy; for ordinary areas (such as residential areas or open areas), reduce the collection frequency and minimize unnecessary redundant data collection;

[0191] According to the classification results of each real estate element area and real-time surveying and mapping data, optimize the data processing parameters. For example, for key areas (such as areas with complex buildings or dense traffic), adjust the granularity of spatial distribution feature analysis and use more convolutional layers and pooling layers; for the attribute analysis part, adjust the hierarchical depth of Haar wavelet transform according to the physical attributes of the area; for the environmental correlation feature analysis, adjust the calculation range of Fourier transform according to the complexity of surrounding facilities;

[0192] According to the feedback data of real-time surveying and mapping, continuously optimize the data collection frequency and processing parameters for different categories of areas through machine learning algorithms; specifically including: using an adaptive learning rate to optimize the feature extraction strategy for each area;

[0193] Based on historical data and surveying and mapping accuracy feedback, adjust the parameters of the model to improve the balance between processing accuracy and real-time performance;

[0194] Through an adaptive mechanism, evaluate the feature change trends of different areas and dynamically adjust the computational complexity to ensure the efficiency and accuracy of real-time data processing;

[0195] For the dynamically adjusted data collection frequency and processing parameters, optimize the computational performance of the entire system to ensure that there are no data bottlenecks in the real-time data analysis and feedback process for different areas, and ensure that the system can process large-scale real estate data and respond in a timely manner;

[0196] Generate a real-time feedback mechanism. According to the new collected data and processing results, automatically update the feature classification of the real estate area, and gradually improve the mapping efficiency and accuracy.

[0197] Please refer to Figure 2 as shown, a multi-dimensional data comprehensive processing system for real estate mapping, including:

[0198] A data acquisition module. The data acquisition module uses lidar to collect multi-dimensional data of real estate, including terrain data, spatial data, and attribute data, and preprocesses the collected data to reduce noise and optimize the integrity and accuracy of the data;

[0199] An element area recognition module. The element area recognition module identifies and separates the element areas in real estate through a data segmentation algorithm, including: boundary lines, building outlines, and terrain features.

[0200] A feature extraction module. The feature extraction module analyzes the element areas and extracts the spatial distribution features, attribute features, and environmental correlation features of the element areas.

[0201] A feature index calculation module. The feature index calculation module analyzes the spatial distribution features, attribute features, and environmental correlation features of each element area respectively, and calculates the spatial distribution feature index, attribute feature index, and environmental correlation feature index within each element area according to the analysis results.

[0202] A comprehensive analysis module. The comprehensive analysis module comprehensively analyzes the spatial distribution feature index, attribute feature index, and environmental correlation feature index, and generates a comprehensive score for each real estate element area according to the analysis results.

[0203] A region division module. The region division module divides the real estate element areas into important areas and ordinary areas according to the comprehensive score.

[0204] A dynamic adjustment module. The dynamic adjustment module combines real-time mapping and a dynamic adjustment mechanism to optimize the data acquisition frequency and processing parameters of different categories of real estate element areas, and realizes intelligent data processing for different mapping objectives.

[0205] Working principle of the present invention: By using lidar technology to collect topographic data, spatial data, and attribute data of real estate, combined with innovative data processing and analysis methods, comprehensive evaluation of real estate areas with high precision is achieved. Specifically, first, a lidar device is used to collect three-dimensional point cloud data of the real estate area, and noise is removed and data quality is optimized through preprocessing steps. Then, a data segmentation algorithm is used to identify regions in the data, separate the feature regions in the real estate, and extract the spatial distribution features, attribute features, and environmental correlation features of each region. In terms of spatial feature extraction, the present invention adopts an adaptive convolutional neural network, which dynamically adjusts the convolution kernel and pooling factor according to the feature complexity of the region to accurately extract geometric information such as building outlines and topographic features; in terms of attribute feature analysis, a multi-level joint learning network is adopted, and through combining spatial features with attribute data such as building area and floor height, deep mapping and regression analysis are performed to improve the prediction accuracy; in terms of environmental feature extraction, the present invention introduces the combination of a graph convolutional network and a convolutional neural network to process the complex relationship between the real estate and the surrounding environment, and by dynamically adjusting the analysis range of environmental data, the relevance of the real estate area is updated in real time. Finally, by calculating the spatial distribution feature index, attribute feature index, and environmental correlation feature index, the comprehensive scores of each real estate area are normalized, and the data collection frequency and processing parameters of different regions are dynamically adjusted in combination with real-time surveying and mapping data to achieve intelligent data processing. This technical solution not only improves the surveying and mapping accuracy but also can efficiently meet the surveying and mapping requirements of different types of real estate, ensuring the real-time performance and efficiency of the system.

[0206] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0207] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-dimensional data comprehensive processing method for real estate surveying and mapping, characterized in that, It includes the following steps: Collect multi-dimensional data of real estate using lidar, including terrain data, spatial data, and attribute data, and preprocess the collected data to reduce noise and optimize data integrity and accuracy; Identify and separate the feature areas in the real estate through a data segmentation algorithm, including: boundary lines, building outlines, and terrain features, analyze the feature areas, and extract the spatial distribution features, attribute features, and environmental association features of the feature areas; Analyze the spatial distribution features, attribute features, and environmental association features of each feature area respectively, and calculate the spatial distribution feature index, attribute feature index, and environmental association feature index within each feature area according to the analysis results; Among them, the spatial distribution features include: position coordinates and shape, the attribute features include: area, volume, and use, and the environmental association features include: surrounding facilities and road networks; Conduct a comprehensive analysis of the spatial distribution feature index, attribute feature index, and environmental association feature index, and generate a comprehensive score for each real estate feature area according to the analysis results; Divide the real estate feature areas into important areas and ordinary areas according to the comprehensive scores; Combine real-time surveying and mapping and a dynamic adjustment mechanism to optimize the data collection frequency and processing parameters of different categories of real estate feature areas, and achieve intelligent data processing for different surveying and mapping objectives.

2. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, characterized in that The identifying and separating the feature areas in the real estate through the data segmentation algorithm specifically includes: Perform multi-scale segmentation on the real estate data collected by lidar, where the data includes terrain data, spatial data, and attribute data, and use the local area feature coefficient to perform preprocessing and optimization of the data; Among them, the calculation expression of the local area feature coefficient is: ; In the formula, represents the attribute value of the th data point, represents the data point collected, represents the average attribute value of the region, is the total number of data points, is the local region feature coefficient, represents the region position coordinate; Use geometric analysis methods to segment the area, and calculate the normal vector and local curvature of each data point; Among them, the calculation expression of the normal vector is: ; Among them, the calculation expression of the local curvature is: ; In the formula, represents the normal vector of the data point, represents the Laplacian operator of the data point, represents the gradient of the data point, represents the local curvature of the data point; According to the normal vector and local curvature of each data point, calculate the area score of each area for identifying feature areas, and the calculation expression is: ; In the formula, represents the regional score, and represent the preset proportionality coefficient, and and are both greater than 0; Judge whether the area score of each area is greater than or equal to the preset threshold. If so, identify it as a feature area; if not, identify it as a non-feature area.

3. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, characterized in that The analyzing the feature areas and extracting the spatial distribution features, attribute features, and environmental association features of the feature areas specifically includes: Extract the spatial distribution features of the real estate area through multiple convolutional layers and pooling layers of the convolutional neural network, including the geometric features of position, shape, boundary, and contour, specifically including: Use convolutional kernels to perform convolutional operations on the real estate area data to extract the boundary lines, terrain features, and building outlines of the buildings; Through adaptive pooling operations, dynamically adjust the pooling factor and convolutional kernel size so that the convolutional neural network can effectively extract spatial features at different scales; Through a joint learning network, fuse the spatial data and attribute data of the real estate to extract the attribute features of the real estate area, including: While using convolutional layers to extract spatial features, use fully connected layers to map the spatial features and attribute data to predict the attributes of the buildings; Adopt a regression analysis method to predict the physical attributes of the real estate area; Extract the association features between the real estate area and its surrounding environment through the combination of graph theory and graph convolutional network and the convolutional neural network, including: Model the real estate area and its surrounding environment as graphic data, use a graph convolutional network to extract the correlation features between the real estate and the surrounding environment, and calculate the shortest path and accessibility environmental factors between the real estate and the surrounding facilities; Through the joint learning of environmental data and the spatial features output by the convolutional neural network, extract the environmental impact features of the real estate area.

4. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, wherein The process of obtaining the spatial distribution feature index is as follows: Extract the spatial distribution characteristics of the feature area, including position, shape, boundary, and contour geometric features, and generate a set of spatial data points , where each point represents the spatial coordinates of a feature in the real estate area, represents the number of collection points, represents the position coordinates of the th collection point; For the extracted set of spatial data points Apply the density clustering algorithm with a preset neighborhood radius of , and set the density threshold to divide the spatial data points into multiple clustering regions according to their density relationships , where each clustering region contains feature points ; Calculate the spatial distribution feature parameters for each clustering area; Calculate the area of the area, and the calculation expression is: ; Among them, represents the area of the clustering region , and represents the convex hull boundary points of the region; Calculate the area density, and the calculation expression is: ; In the formula, represents the regional density of the th acquisition point, represents the number of points within the clustering region ; Calculate the morphological complexity, and the calculation expression is: ; In the formula, represents the fractal dimension of the area; Based on the comprehensive calculation of the area, area density, and morphological complexity of each clustering area, calculate the spatial distribution feature index of the area, and the calculation expression is: ; In the formula, represents the value of the largest area among all clustering regions, represents the maximum density value among all clustering regions, represents the spatial distribution characteristic index of the clustering region.

5. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, characterized in that The process of obtaining the attribute feature index is as follows: Extract the attribute features of the feature area, including: area, volume, and usage; Construct the attribute features into an attribute vector ; Perform Haar wavelet transform on the attribute vector to decompose the attribute features into low-frequency components and high-frequency components. Denote the area corresponding to the th acquisition point, specifically including: Perform a recursive Haar wavelet transform on the attribute data to decompose the data vector into low-frequency and high-frequency components at multiple levels. The calculation expression is as follows: ; In the formula, and are two adjacent attribute data, and are the low-frequency and high-frequency components of the first layer respectively; Repeat the decomposition process for the low-frequency components Continue the decomposition to obtain low-frequency and high-frequency components at a higher level. The calculation formula is as follows: ; In the formula, represents the low-frequency component of the th layer, represents the high-frequency component of the th layer, represents the number of layers; According to the low-frequency and high-frequency components obtained after Haar wavelet transform, calculate the attribute feature index of the real estate feature area, and the calculation expression is: ; In the formula, represents the attribute characteristic index within the real estate element area, and are preset weight coefficients, and and The sum of is 1.

6. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, characterized in that, The process of obtaining the environmental correlation feature index is as follows: Extract the environmental correlation features of the real estate feature area, and the environmental correlation features include: surrounding facilities and road network; Construct environmental feature vectors , denote the area corresponding to the th collection point; Perform a Fourier transform on the environmental feature vector to convert the time-domain signal into a frequency-domain signal, and the calculation expression is: ; Among them, represents the value of the frequency-domain signal at the th frequency point, represents the frequency point, represents the number of environmental characteristic data, represents the total number of environmental characteristic data, represents the imaginary unit, represents the th environmental characteristic data in the time-domain signal; Calculate the amplitude of the frequency components after the Fourier transform, and the calculation expression is: ; Among them, is the amplitude of the th frequency component; Use the mean calculation expression to calculate the average frequency of all frequency components, and use the difference between the maximum frequency value and the minimum frequency value to calculate the frequency extreme difference; Calculate the environmental correlation feature index, and the calculation expression is: ; In the formula, represents the average frequency of all frequency components, represents the frequency extreme difference, represents the environmental correlation feature index.

7. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, wherein The comprehensive analysis of the spatial distribution feature index, attribute feature index, and environmental correlation feature index, and according to the analysis results, generate a comprehensive score for each real estate feature area, specifically including: Obtain the spatial distribution feature index, attribute feature index, and environmental correlation feature index of the real estate feature area, perform normalization calculation and processing on the spatial distribution feature index, attribute feature index, and environmental correlation feature index, and obtain the comprehensive score of the real estate feature area.

8. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, characterized in that According to the comprehensive score, divide the real estate feature area into important areas and ordinary areas, specifically including: Judge whether the comprehensive score of each real estate feature area is greater than or equal to the preset threshold. If so, it means that the corresponding area is an important area and is marked as an important area. If not, it means that the corresponding area is an ordinary area and is marked as an ordinary area.

9. The multi-dimensional data comprehensive processing method for real estate surveying and mapping according to claim 1, characterized in that Combine real-time surveying and mapping and a dynamic adjustment mechanism to optimize the data collection frequency and processing parameters for different categories of real estate feature areas, and achieve intelligent data processing for different surveying and mapping objectives, specifically including: According to the spatial distribution features, attribute features, and environmental correlation features of different real estate feature areas, establish a classification model to divide the real estate feature areas into multiple categories, and the classification basis includes but is not limited to the type, area, morphology, and surrounding environment of the real estate; Dynamically adjust the data collection frequency according to the classification results of each real estate feature area; Optimize the data processing parameters according to the classification results of each real estate feature area and the real-time surveying and mapping data; Based on the feedback data from real-time surveying and mapping, continuously optimize the data acquisition frequency and processing parameters for different categories of regions through machine learning algorithms; Adjust the parameters of the model based on historical data and mapping accuracy feedback; Through an adaptive mechanism, evaluate the trend of feature changes in different regions and dynamically adjust the computational complexity; Optimize the computational performance of the entire system for the dynamically adjusted data acquisition frequency and processing parameters; Generate a real-time feedback mechanism to automatically update the feature classification of the real estate area according to the new acquisition data and processing results.

10. A multi-dimensional data comprehensive processing system for real estate surveying and mapping, characterized in that, For the multi-dimensional data comprehensive processing method for real estate surveying and mapping as described in any one of claims 1-9, including: A data acquisition module, which uses lidar to acquire multi-dimensional data of real estate, including topographic data, spatial data, and attribute data, and preprocesses the acquired data to reduce noise and optimize the integrity and accuracy of the data; A feature area identification module, which identifies and separates feature areas in real estate through a data segmentation algorithm, including: boundary lines, building outlines, and topographic features; A feature extraction module, which analyzes the feature areas and extracts the spatial distribution features, attribute features, and environmental association features of the feature areas; A feature index calculation module, which analyzes the spatial distribution features, attribute features, and environmental association features of each feature area respectively, and calculates the spatial distribution feature index, attribute feature index, and environmental association feature index within each feature area according to the analysis results; A comprehensive analysis module, which comprehensively analyzes the spatial distribution feature index, attribute feature index, and environmental association feature index, and generates a comprehensive score for each real estate feature area according to the analysis results; A regional division module, which divides the real estate feature areas into important areas and ordinary areas according to the comprehensive score; A dynamic adjustment module, which combines real-time surveying and mapping with a dynamic adjustment mechanism to optimize the data acquisition frequency and processing parameters for different categories of real estate feature areas, and achieve intelligent data processing for different surveying and mapping objectives.

Images