Real estate surveying and mapping data processing method and system based on intelligent data

Abstract

The invention relates to the technical field of data processing, in particular to a real estate surveying and mapping data processing method and system based on intelligent data. The method comprises the following steps: acquiring multi-source real estate surveying and mapping data; performing space-time synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping space alignment data; real estate space feature extraction is carried out on the multi-source real estate surveying and mapping space alignment data to obtain real estate space feature data; performing cross-domain feature fusion on the multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data; public surveying and mapping point confirmation is carried out on the multi-source real estate surveying and mapping data through the real estate surveying and mapping fusion spatial feature data, and real estate surveying and mapping public surveying and mapping point data are obtained. Through multi-source data space-time synchronization, feature fusion, distortion correction, high-dimensional space reconstruction, semantic tag association and chain storage, the efficiency and accuracy of real estate surveying and mapping data processing are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a real estate surveying and mapping data processing method and system based on intelligent data. Background Art

[0002] With the rapid development of big data, cloud computing and artificial intelligence (AI) technology, real estate surveying and mapping has begun to transform into intelligent technology. Big data technology makes data collection more comprehensive, cloud platforms provide powerful data storage and computing capabilities, and AI shows great potential in data analysis and pattern recognition. Sensor-based data collection methods, such as unmanned aerial vehicles (UAVs) and laser scanning technology, can efficiently obtain high-precision three-dimensional terrain and building information, further improving the accuracy and timeliness of surveying and mapping data. However, existing technologies often fail to fully utilize the complementarity of multi-source data, resulting in the potential value of the data not being fully explored. At the same time, traditional surveying and mapping methods are prone to local surveying and mapping distortion and accuracy problems when dealing with large-scale areas, resulting in low efficiency and accuracy in real estate surveying and mapping data processing. Summary of the invention

[0003] Based on this, it is necessary to provide a real estate surveying and mapping data processing method and system based on intelligent data to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a real estate surveying and mapping data processing method based on intelligent data comprises the following steps:

[0005] Step S1: acquiring multi-source real estate surveying and mapping data; performing spatiotemporal synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping spatial alignment data; performing real estate spatial feature extraction on the multi-source real estate surveying and mapping spatial alignment data to obtain real estate spatial feature data; performing cross-domain feature fusion on the multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data;

[0006] Step S2: confirming the public surveying and mapping points of multi-source real estate surveying and mapping data by integrating the spatial feature data of real estate surveying and mapping to obtain the public surveying and mapping point data of real estate surveying and mapping; using the public surveying and mapping point data of real estate surveying and mapping to perform local surveying and mapping distortion correction to generate structural surveying and mapping correction data; reconstructing the real estate surveying and mapping high-dimensional space on the structural surveying and mapping correction data to generate three-dimensional real estate model data; and identifying the real estate use pattern on the three-dimensional real estate model data to generate real estate use pattern data;

[0007] Step S3: performing multi-layer semantic label association on the three-dimensional real estate model data according to the real estate use pattern data to generate multi-layer semantic label data; performing rule mining on the real estate semantic label data to generate real estate association rule mining data; constructing graph nodes and edges on the multi-layer semantic label data based on the real estate association rule mining data to generate a real estate surveying and mapping semantic association map;

[0008] Step S4: The semantic label data of the real estate surveying and mapping semantic association map is stored on the chain to generate the real estate surveying and mapping semantic chain storage data; the data stored on the real estate surveying and mapping semantic chain is collaboratively shared to generate real-time shared surveying and mapping data to execute the real estate surveying and mapping data processing sharing operation.

[0009] The present invention improves the accuracy of data integration by ensuring that surveying and mapping data from different sources can be matched consistently in time and space. By extracting spatial features, the spatial structure and characteristics of real estate can be fully reflected, and the analysis depth of data can be enhanced. By integrating feature data from different fields, the comprehensiveness of data is improved, ensuring that real estate surveying and mapping data can provide insights in more dimensions, which is conducive to the solution of complex problems. Through the confirmation of public surveying and mapping points and the correction of local distortion, the accuracy and consistency of data are significantly improved, and surveying and mapping errors are reduced. The three-dimensional real estate model is generated by high-dimensional space reconstruction technology, which can more realistically reflect the spatial structure of real estate and support more accurate planning and evaluation. Identifying the use pattern of real estate can provide a basis for subsequent resource allocation, management and optimization, and improve the intelligent level of data application. By associating three-dimensional real estate models with multi-level semantic tags, the data is made more structured, which is convenient for in-depth analysis and subsequent processing. By mining association rules, potential laws in real estate data can be discovered, providing data support for decision-making, and improving the intelligent analysis capability of surveying and mapping data. By constructing a semantic association map for real estate surveying and mapping, a more systematic and visual structure is provided, making the relevance of real estate data clearer and supporting more efficient information retrieval and decision-making. By storing real estate surveying and mapping semantic data on the blockchain, the immutability and transparency of the data are ensured, and the security and credibility of the data are improved. By achieving real-time sharing, all parties can synchronously obtain the latest surveying and mapping data, improve collaboration efficiency, promote multi-party participation and sharing of real estate data, and enhance the timeliness and accuracy of decision-making. Therefore, the present invention improves the efficiency and accuracy of real estate surveying and mapping data processing through multi-source data spatiotemporal synchronization, feature fusion, distortion correction, high-dimensional space reconstruction, semantic label association and on-chain storage.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire multi-source real estate surveying and mapping data;

[0012] Step S12: performing time synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping synchronization data; performing spatial coordinate alignment on the multi-source real estate surveying and mapping synchronization data to generate multi-source real estate surveying and mapping spatial alignment data;

[0013] Step S13: performing data preprocessing on the multi-source real estate surveying and mapping spatial alignment data to generate standard real estate surveying and mapping data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0014] Step S14: extracting real estate spatial features from the standard real estate surveying and mapping data to obtain real estate spatial feature data; and performing cross-domain feature fusion on the standard real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data.

[0015] The present invention aligns real estate surveying and mapping data from different sources in the time dimension to ensure that the data has the same time reference standard and eliminate the impact of time errors on the analysis. By unifying the spatial coordinate system, data from different surveying and mapping sources are spatially aligned to avoid data deviation problems caused by inconsistent coordinate systems. Data preprocessing includes operations such as data cleaning, denoising, missing value filling and standardization to ensure data integrity, accuracy and standardization, laying a high-quality data foundation for subsequent analysis. By mining the spatial characteristics in the data, the key attributes of real estate (such as geographical location, morphological characteristics, etc.) are revealed, providing an important basis for real estate-related analysis. Based on the characteristics of multi-source data, surveying and mapping information from different domains (such as geographic, architectural and environmental data) are integrated to generate real estate surveying and mapping fusion spatial feature data with comprehensive value, providing support for the comprehensive evaluation of complex real estate issues.

[0016] Preferably, cross-domain feature fusion of standard real estate surveying and mapping data based on real estate spatial feature data includes:

[0017] Perform high-level spatial feature decomposition on real estate spatial feature data to generate real estate high-level spatial feature decomposition data; perform low-level spatial feature decomposition on standard real estate surveying and mapping data to generate real estate low-level spatial feature decomposition data;

[0018] Perform feature distribution difference analysis on real estate low-level spatial feature decomposition data and real estate high-level spatial feature decomposition data to generate spatial feature distribution difference data; perform spatial cross-domain feature comparison on real estate low-level spatial feature decomposition data and real estate high-level spatial feature decomposition data based on spatial feature distribution difference data to generate real estate surveying and mapping spatial feature alignment data;

[0019] The real estate surveying and mapping spatial feature alignment data is used to perform multi-dimensional feature fusion on the standard real estate surveying and mapping data to generate real estate surveying and mapping fused spatial feature data.

[0020] By decomposing the real estate spatial feature data into high-level features and low-level features, the system can accurately capture subtle spatial characteristics while retaining global characteristics. High-level features reflect macroscopic spatial relationships, while low-level features capture microscopic details. The combination of the two significantly improves the accuracy of surveying and mapping data. Through feature distribution difference analysis and alignment, the deviation between different surveying and mapping data sources is eliminated to ensure the consistency and accuracy of data in multi-domain space. Feature distribution difference analysis can identify the differences in resolution, accuracy and spatial distribution between different data sources, providing a basis for feature fusion. By unifying the difference data, the fused spatial feature data finally generated is more adaptable to multi-scenario application requirements. After cross-domain feature comparison and alignment data, standard surveying and mapping data can better match the actual spatial features and adapt to the data standards of different regions or systems. By fusing the aligned spatial features in multiple dimensions, surveying and mapping data with higher information density can be generated.

[0021] Preferably, step S2 comprises the following steps:

[0022] Step S21: performing real estate structural analysis on multi-source real estate surveying and mapping data by integrating spatial feature data with real estate surveying and mapping to generate real estate surveying and mapping structural data; confirming public surveying and mapping points on multi-source real estate surveying and mapping data based on the real estate surveying and mapping structural data to obtain real estate surveying and mapping public surveying and mapping point data;

[0023] Step S22: using the real estate surveying and mapping public surveying and mapping point data to perform local surveying and mapping distortion analysis on the real estate surveying and mapping structure data to generate real estate local surveying and mapping distortion data; performing surveying and mapping data correction on the real estate surveying and mapping structure data using the real estate local surveying and mapping distortion data to generate structure surveying and mapping correction data;

[0024] Step S23: reconstructing the real estate surveying and mapping high-dimensional space on the structural surveying and mapping correction data to generate three-dimensional real estate model data; performing dynamic spatiotemporal grid analysis on the three-dimensional real estate model data to generate three-dimensional real estate dynamic spatiotemporal grid data;

[0025] Step S24: Based on the three-dimensional real estate dynamic spatiotemporal grid data, real estate use pattern recognition is performed on the three-dimensional real estate model data to generate real estate use pattern data.

[0026] The present invention ensures consistency between different data sources by analyzing multi-source data, especially in the identification and confirmation of key surveying and mapping points. This can eliminate deviations caused by differences in surveying and mapping tools or different data sources, and provide a more reliable structural data foundation. Identifying and correcting local distortions ensures that the final data is more accurate and avoids errors caused by data distortion, especially in the surveying and mapping of complex terrain or irregular building structures. Through high-dimensional space reconstruction, an accurate three-dimensional model is generated, which provides a three-dimensional and visual spatial foundation for subsequent analysis and decision-making, making the overall picture of the real estate clearer and easier to manage and optimize. Using a dynamic space-time grid to perform space-time analysis on the real estate model can effectively capture and analyze the changes and dynamic characteristics of the real estate, support dynamic data updates and precise monitoring, and is of great significance for surveying and mapping tasks that require real-time updates and tracking.

[0027] Preferably, step S22 includes the following steps:

[0028] Step S221: extract key geometric information from real estate surveying and mapping structure data using real estate surveying and mapping public surveying and mapping point data to obtain real estate key geometric information data; perform spatial topological characteristic analysis on real estate surveying and mapping structure data using real estate key geometric information data to generate real estate spatial topological characteristic data;

[0029] Step S222: Perform dynamic offset calculation on the real estate space topology characteristic data to obtain real estate space topology dynamic offset data; wherein the formula for dynamic offset calculation is as follows:

[0030]

[0031] Where D(x, y, z) is the offset distance, x is the horizontal coordinate of the survey point offset, y is the vertical coordinate of the survey point offset, and z is the vertical coordinate of the survey point offset. t Expressed as the horizontal position of the theoretical survey point, y t Expressed as the vertical position of the theoretical survey point, z t Expressed as the vertical coordinate of the theoretical survey point, x s Represented as the actual horizontal coordinate of the surveying point, y s Expressed as the actual ordinate of the surveying point, z s It is expressed as the actual vertical coordinate of the surveying point;

[0032] Step S223: converting the real estate spatial topology dynamic offset data into an offset curve to generate a surveying and mapping offset curve; calculating the offset curvature of the surveying and mapping offset curve to obtain offset curvature data; and performing distortion space mapping on the real estate surveying and mapping structure data through the offset curvature data to generate real estate local surveying and mapping distortion data;

[0033] Step S224: performing surveying and mapping data correction on the real estate surveying and mapping structure data using the real estate local surveying and mapping distortion data to generate structure surveying and mapping correction data.

[0034] The present invention can accurately identify the geometric structure and spatial relationship of real estate by extracting key geometric information from real estate surveying and mapping data and performing spatial topological characteristic analysis. This helps to more accurately understand the composition and spatial layout of real estate structures, especially in complex environments, and can improve the spatial consistency and accuracy of surveying and mapping data. By calculating the dynamic offset of surveying and mapping points, the gap between actual surveying and mapping points and theoretical surveying and mapping points can be accurately identified. The offset calculation formula (D(x, y, z)) of this step provides a reliable mathematical basis for the accuracy of surveying and mapping data, and helps to identify and correct small deviations in the data. The conversion and curvature calculation of the offset curve help analyze the trend and pattern of spatial offset, thereby further correcting distortion. This process ensures higher data accuracy, especially in the surveying and mapping of complex structures or special-shaped areas of buildings, and can effectively correct measurement errors and optimize the quality of surveying and mapping data. Correcting surveying and mapping data through distortion space mapping can effectively eliminate spatial distortion in the surveying and mapping process, improve the stability and reliability of data, and ensure the consistency of real estate surveying and mapping data in different applications. Correcting real estate surveying and mapping data through local distortion data can improve the surveying and mapping accuracy of local areas, especially for areas with complex terrain or difficult measurements. Local correction enhances the local accuracy and practicality of surveying and mapping data, providing a more reliable data basis for subsequent analysis.

[0035] Preferably, step S224 specifically includes:

[0036] Extracting regional error distribution features of real estate surveying and mapping structure data through real estate local surveying and mapping distortion data to obtain regional error distribution feature data, wherein the regional error distribution feature data includes an offset vector, a distortion radius, and an error intensity;

[0037] Perform Gaussian error correction calculation on the local real estate surveying and mapping distortion data according to the offset vector, distortion radius and error intensity to generate local correction parameter data;

[0038] Based on the local correction parameter data, correction matrices are generated for the offset vector, distortion radius and error intensity respectively to obtain preliminary correction matrix data; the real estate surveying and mapping structure data is globally corrected and optimized through the preliminary correction matrix data to generate global optimized correction data;

[0039] The global optimization correction data is used to perform multi-scale correction on the real estate surveying and mapping structural data to generate structural surveying and mapping correction data, wherein the multi-scale correction application includes macro correction, meso correction and micro correction.

[0040] The present invention can more accurately identify the error characteristics of each area in the surveying and mapping data by extracting the regional error distribution characteristics of the local real estate surveying and mapping distortion data, especially under the analysis of the offset vector, distortion radius and error intensity, which areas have large deviations. This regional error analysis helps to locate specific surveying and mapping error points and provides a clear target for subsequent corrections. By performing Gaussian error correction on the offset vector, distortion radius and error intensity, the error can be effectively corrected in a systematic manner. This correction method can adjust the error based on the probability distribution, making the correction process more precise and scientific, thereby improving the overall accuracy of the data. By generating a preliminary correction matrix and performing global consistency correction optimization, the global deviation in the real estate surveying and mapping data can be effectively eliminated. Global optimization correction data can ensure the uniformity and consistency of surveying and mapping data between different regions, especially in large-scale surveying and mapping projects, and can effectively ensure the global accuracy of the data. Through the multi-scale correction application of macro correction, meso correction and micro correction, the surveying and mapping data can be corrected according to different scales, making the entire data correction process more flexible and accurate. This strategy can optimize data at different levels, thereby improving local and global accuracy and ensuring that measurement results at different levels meet standards. Macro-level correction helps adjust overall errors in a large range, and is suitable for global consistency optimization of real estate surveying and mapping data to ensure the accuracy and consistency of data in large-scale areas. Meso-level correction mainly optimizes medium-scale areas, while micro-level correction focuses on precise adjustment of details. Through the comprehensive correction of these three different scales, data errors can be eliminated at different levels, and the overall accuracy of data can be improved, which is suitable for more complex surveying and mapping environments and scenarios with higher accuracy requirements. Through multi-level and multi-scale correction applications, the adaptability of real estate surveying and mapping data at different levels is ensured. Whether it is the overall structure of the building at the macro level or the detailed features at the micro level, it can be accurately adjusted at different scales to meet different application requirements, such as real estate development, urban planning, architectural design, etc.

[0041] Preferably, reconstructing the real estate surveying and mapping high-dimensional space of the structural surveying and mapping correction data includes:

[0042] Perform point cloud conversion on the structural surveying and mapping correction data to generate structural surveying and mapping point cloud data; perform point cloud downsampling on the structural surveying and mapping point cloud data to generate structural surveying and mapping downsampling point cloud data;

[0043] Perform regional point cloud segmentation on the downsampled point cloud data of structural surveying and mapping to generate regional point cloud segmentation data; perform structural angle feature key point extraction on the regional point cloud segmentation data to obtain structural angle feature key point data; perform Euclidean distance calculation on the regional point cloud segmentation data based on the structural angle feature key point data to obtain the real estate structure point cloud adjacency graph;

[0044] Perform point cloud triangulation on the adjacency graph of the real estate structure point cloud to generate point cloud triangulated mesh data; perform surface fitting on the point cloud triangulated mesh data to generate real estate point cloud surface fitting data;

[0045] The three-dimensional real estate model data is generated by performing three-dimensional model texture mapping on the point cloud triangular mesh data through real estate point cloud surface fitting data.

[0046] The present invention can significantly reduce the redundancy of data while maintaining the main features of the data by converting the structural surveying and mapping correction data into point cloud data and performing downsampling. This process not only optimizes the computing resources, but also improves the efficiency of subsequent analysis. The downsampled point cloud data can better adapt to the storage and processing requirements while ensuring that the accuracy will not be greatly reduced. By performing regional block division on the point cloud data and extracting the key points of the structural angle features, the important areas and structural features in the point cloud can be accurately identified. The extraction of angle features helps to highlight the main structural characteristics in the surveying and mapping area, reduce the interference of irrelevant data, and make the subsequent modeling and analysis more centralized and accurate. By calculating the Euclidean distance of the key points of the structural angle features, the adjacency graph of the real estate structure point cloud can be established, thereby reflecting the mutual relationship and spatial position relationship between the point cloud data. This adjacency graph can provide effective spatial constraints for subsequent triangulation and surface fitting, and improve the accuracy and rationality of spatial modeling. Triangulation and surface fitting of the point cloud data can convert discrete point cloud data into a continuous surface model, thereby laying the foundation for subsequent three-dimensional reconstruction. By performing 3D texture mapping on the point cloud triangulated mesh data, the 3D real estate model can be given a more realistic and detailed appearance. Texture mapping not only improves the visual effect of the model, but also enhances the practicality of the model, especially in applications such as virtual reality (VR) or augmented reality (AR). This technology can improve the user experience and facilitate virtual display and interaction of real estate. The resulting 3D real estate model data has high accuracy and details, and can fully display the external structure, size ratio and spatial layout of the real estate.

[0047] Preferably, step S3 comprises the following steps:

[0048] Step S31: assigning semantic labels to the real estate use pattern data to generate real estate semantic label data;

[0049] Step S32: semantically associating the three-dimensional real estate model data according to the real estate semantic label data to generate real estate semantic label associated data;

[0050] Step S33: performing multi-layer label nesting on the real estate semantic label data through the real estate semantic label association data to generate multi-layer semantic label data;

[0051] Step S34: perform association rule mining on the multi-layer semantic label data to generate real estate association rule mining data; construct graph nodes and edges on the multi-layer semantic label data based on the real estate association rule mining data to generate a real estate surveying and mapping semantic association graph.

[0052] The present invention can convert the originally abstract or complex surveying and mapping data into label data with clear meaning by assigning semantic labels to the real estate use pattern data and semantically associating the three-dimensional real estate model data. This makes the expression of data clearer and more orderly, and can make more intelligent analysis and decision-making based on semantic information. This process not only helps to understand the spatial structure of real estate, but also provides accurate information support for subsequent functional analysis, use pattern evaluation, etc. By nesting multiple layers of labels for semantic label data, the different feature levels of real estate can be finely divided to form a deeper semantic network. This multi-level label system helps to identify the multi-dimensional characteristics of real estate (for example: structural characteristics, functional uses, spatial distribution, etc.), making the data more refined and adapting to more complex analysis needs. Through association rule mining, not only can the hidden associations in the data be discovered, but also the potential laws between the real estate use pattern and the spatial layout can be revealed. Based on the association rule mining data, by constructing graph nodes and edges, a semantic association map of real estate surveying and mapping can be generated. This data presentation in the form of a map can not only intuitively present the relationship between the various elements of real estate, but also achieve more efficient spatial data retrieval, query and visualization. The map can reveal the mutual influence between different real estate characteristics, provide an intuitive interface for data interaction and information transfer, and facilitate professionals to conduct in-depth analysis in different fields. Through semantic labeling and association rule mining, we can deeply understand the functional distribution and usage patterns of real estate. Each label represents a certain characteristic of real estate (for example, residential, commercial use, parking lot, etc.), and multi-level label nesting can accurately describe the multi-dimensional attributes of real estate functions. This multi-dimensional functional analysis can help the real estate industry optimize spatial design, improve resource utilization, and meet the needs of different groups. Based on the semantic association map of real estate surveying and mapping, we can clearly understand the spatial connection and layout of various areas or functions of real estate, so as to effectively optimize space.

[0053] Preferably, step S4 comprises the following steps:

[0054] Step S41: storing the semantic label data chain of the real estate surveying and mapping semantic association map to generate real estate surveying and mapping semantic chain storage data;

[0055] Step S42: constructing a distributed data access strategy for the data stored on the real estate surveying and mapping semantic chain to generate a distributed data access strategy; using the distributed data access strategy to collaboratively analyze the data stored on the real estate surveying and mapping semantic chain to generate real estate surveying and mapping semantic collaborative analysis data;

[0056] Step S43: compress and share the real estate surveying and mapping semantic collaborative analysis data, thereby generating real-time shared surveying and mapping data to execute real estate surveying and mapping data processing and sharing operations.

[0057] The present invention can use blockchain technology to ensure the immutability and high security of data by storing the data of the real estate surveying and mapping semantic association map on the chain. This method can prevent data from being improperly modified during transmission and storage, and improve the credibility of the data. In addition, the transparency of the blockchain can provide a complete operation history, which is convenient for subsequent tracking and auditing of the data. By storing the real estate surveying and mapping semantic association map data on the chain, not only can the single point failure risk brought by centralized storage be avoided, but also a more flexible and decentralized data management method can be achieved. This decentralized storage method improves the redundancy and fault tolerance of the data and ensures the reliability of the system. By constructing a distributed data access strategy, efficient access and collaborative analysis of data stored on the real estate surveying and mapping semantic chain can be achieved. The distributed access strategy allows users in different locations to perform data reading and writing operations efficiently and in parallel at different times, thereby improving the speed and efficiency of data access. This method is particularly suitable for large-scale real estate surveying and mapping projects, ensuring that multiple teams and departments can efficiently share and collaborate on data processing. Collaborative analysis of the data stored on the real estate surveying and mapping semantic chain through a distributed data access strategy can achieve joint analysis and decision-making of data by multiple parties. This not only improves the accuracy of data analysis, but also ensures that all relevant parties can obtain the latest analysis results in real time, thereby improving the efficiency of the entire workflow. By compressing and sharing the real estate surveying and mapping semantic collaborative analysis data, the processed data can be shared with relevant parties in real time. This method not only improves the timeliness of data processing, but also ensures that all required data is delivered to all relevant personnel or systems in the shortest time, promoting rapid decision-making. By sharing compressed data and performing real estate surveying and mapping data processing sharing operations, the pressure of data transmission and storage can be effectively reduced, data redundancy can be reduced, and resources can be saved. Efficient data sharing operations can also reduce transmission delays between systems, improve the speed and accuracy of data circulation, and ensure that all parties can perform real estate surveying and mapping related work simultaneously.

[0058] In this specification, a real estate surveying and mapping data processing system based on intelligent data is provided, which is used to execute the real estate surveying and mapping data processing method based on intelligent data. The real estate surveying and mapping data processing system based on intelligent data includes:

[0059] A feature fusion module is used to obtain multi-source real estate surveying and mapping data; perform spatiotemporal synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping spatial alignment data; perform real estate spatial feature extraction on the multi-source real estate surveying and mapping spatial alignment data to obtain real estate spatial feature data; perform cross-domain feature fusion on the multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data;

[0060] The distortion correction module is used to confirm the public surveying and mapping points of multi-source real estate surveying and mapping data by integrating the spatial feature data of real estate surveying and mapping, and obtain the public surveying and mapping point data of real estate surveying and mapping; use the public surveying and mapping point data of real estate surveying and mapping to perform local surveying and mapping distortion correction, and generate structural surveying and mapping correction data; reconstruct the real estate surveying and mapping high-dimensional space of the structural surveying and mapping correction data, and generate three-dimensional real estate model data; perform real estate use pattern recognition on the three-dimensional real estate model data, and generate real estate use pattern data;

[0061] The association graph construction module is used to associate multi-layer semantic labels with three-dimensional real estate model data according to real estate use pattern data to generate multi-layer semantic label data; to perform rule mining on real estate semantic label data to generate real estate association rule mining data; to construct graph nodes and edges on multi-layer semantic label data based on real estate association rule mining data to generate real estate surveying and mapping semantic association graph;

[0062] The storage sharing module is used to store the semantic label data of the real estate surveying and mapping semantic association map on the chain, generate the real estate surveying and mapping semantic chain storage data; perform data collaborative sharing on the real estate surveying and mapping semantic chain storage data, generate real-time shared surveying and mapping data, and execute the real estate surveying and mapping data processing sharing operation.

[0063] The beneficial effect of the present invention is that by performing spatiotemporal synchronization and spatial alignment of multi-source real estate surveying and mapping data, the consistency of data from different sources in time and space can be ensured. This process avoids surveying and mapping deviations caused by data mismatch, improves the overall accuracy of the data, and provides a reliable basis for subsequent analysis. By correcting local distortion through public surveying and mapping point data for real estate surveying and mapping, local distortion caused by measurement errors, equipment problems or environmental factors can be eliminated. In this way, real estate surveying and mapping data will be more accurate, which will help reduce errors in later data processing and improve overall data quality. By performing usage pattern recognition on three-dimensional real estate model data, the usage characteristics of real estate (such as residential, commercial, public, etc.) can be automatically identified. This recognition provides data support for subsequent spatial planning, resource allocation and demand analysis, and improves the intelligence level of real estate management. By storing the semantic association map of real estate surveying and mapping on the chain, the security and immutability of the data are guaranteed by blockchain technology, and real-time surveying and mapping data sharing is realized through data collaborative sharing. Staff from different departments and regions can access the latest data efficiently and instantly, avoiding decision delays caused by information lag. Therefore, the present invention improves the efficiency and accuracy of real estate surveying and mapping data processing through multi-source data spatiotemporal synchronization, feature fusion, distortion correction, high-dimensional space reconstruction, semantic label association and on-chain storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic diagram of the steps of a method for processing real estate surveying and mapping data based on intelligent data;

[0065] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0066] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0067] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0068] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0069] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0070] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0071] To achieve this, please refer to Figures 1 to 3 , a real estate surveying and mapping data processing method based on intelligent data, the method comprising the following steps:

[0072] Step S1: acquiring multi-source real estate surveying and mapping data; performing spatiotemporal synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping spatial alignment data; performing real estate spatial feature extraction on the multi-source real estate surveying and mapping spatial alignment data to obtain real estate spatial feature data; performing cross-domain feature fusion on the multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data;

[0073] Step S2: confirming the public surveying and mapping points of multi-source real estate surveying and mapping data by integrating the spatial feature data of real estate surveying and mapping to obtain the public surveying and mapping point data of real estate surveying and mapping; using the public surveying and mapping point data of real estate surveying and mapping to perform local surveying and mapping distortion correction to generate structural surveying and mapping correction data; reconstructing the real estate surveying and mapping high-dimensional space on the structural surveying and mapping correction data to generate three-dimensional real estate model data; and identifying the real estate use pattern on the three-dimensional real estate model data to generate real estate use pattern data;

[0074] Step S3: performing multi-layer semantic label association on the three-dimensional real estate model data according to the real estate use pattern data to generate multi-layer semantic label data; performing rule mining on the real estate semantic label data to generate real estate association rule mining data; constructing graph nodes and edges on the multi-layer semantic label data based on the real estate association rule mining data to generate a real estate surveying and mapping semantic association map;

[0075] Step S4: The semantic label data of the real estate surveying and mapping semantic association map is stored on the chain to generate the real estate surveying and mapping semantic chain storage data; the data stored on the real estate surveying and mapping semantic chain is collaboratively shared to generate real-time shared surveying and mapping data to execute the real estate surveying and mapping data processing sharing operation.

[0076] The present invention improves the accuracy of data integration by ensuring that surveying and mapping data from different sources can be matched consistently in time and space. By extracting spatial features, the spatial structure and characteristics of real estate can be fully reflected, and the analysis depth of data can be enhanced. By integrating feature data from different fields, the comprehensiveness of data is improved, ensuring that real estate surveying and mapping data can provide insights in more dimensions, which is conducive to the solution of complex problems. Through the confirmation of public surveying and mapping points and the correction of local distortion, the accuracy and consistency of data are significantly improved, and surveying and mapping errors are reduced. The three-dimensional real estate model is generated by high-dimensional space reconstruction technology, which can more realistically reflect the spatial structure of real estate and support more accurate planning and evaluation. Identifying the use pattern of real estate can provide a basis for subsequent resource allocation, management and optimization, and improve the intelligent level of data application. By associating three-dimensional real estate models with multi-level semantic tags, the data is made more structured, which is convenient for in-depth analysis and subsequent processing. By mining association rules, potential laws in real estate data can be discovered, providing data support for decision-making, and improving the intelligent analysis capability of surveying and mapping data. By constructing a semantic association map for real estate surveying and mapping, a more systematic and visual structure is provided, making the relevance of real estate data clearer and supporting more efficient information retrieval and decision-making. By storing real estate surveying and mapping semantic data on the blockchain, the immutability and transparency of the data are ensured, and the security and credibility of the data are improved. By achieving real-time sharing, all parties can synchronously obtain the latest surveying and mapping data, improve collaboration efficiency, promote multi-party participation and sharing of real estate data, and enhance the timeliness and accuracy of decision-making. Therefore, the present invention improves the efficiency and accuracy of real estate surveying and mapping data processing through multi-source data spatiotemporal synchronization, feature fusion, distortion correction, high-dimensional space reconstruction, semantic label association and on-chain storage.

[0077] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for processing real estate surveying and mapping data based on intelligent data of the present invention. In this example, the method for processing real estate surveying and mapping data based on intelligent data includes the following steps:

[0078] Step S1: acquiring multi-source real estate surveying and mapping data; performing spatiotemporal synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping spatial alignment data; performing real estate spatial feature extraction on the multi-source real estate surveying and mapping spatial alignment data to obtain real estate spatial feature data; performing cross-domain feature fusion on the multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data;

[0079] In an embodiment of the present invention, real estate surveying and mapping data is obtained in a variety of ways, and these data come from different sensors, surveying and mapping platforms or third-party data providers. Common data sources include: satellite remote sensing data, laser radar (LiDAR) data, geographic information system (GIS) data, unmanned aerial vehicle (UAV) data and sensor data. Different data sources have different formats, and common ones include geographic coordinate systems (such as WGS84), point cloud data formats (such as LAS), image formats (such as JPEG, TIFF), etc. According to the timestamp or acquisition time, data at different times are synchronized. If the time of data acquisition is inconsistent, an interpolation algorithm can be used for time compensation or the data can be aligned based on the timestamp. Data in different coordinate systems are converted to a unified reference coordinate system. For example, a spatial reference conversion tool (such as EPSG code) is used to convert data from different coordinate systems (such as geographic coordinate system and projection coordinate system) to the same coordinate system. Spatial alignment is performed for different measurement data (such as LiDAR point clouds and satellite images). Image registration techniques (such as feature-based matching methods and point cloud-based registration algorithms) are used to ensure that all data are in the same spatial framework. The least squares method (Least Squares) or ICP (Iterative Closest Point) algorithm is usually used for accurate registration. Through the process of spatiotemporal synchronization and spatial alignment, a multi-source data set in a unified spatial framework is obtained. Based on the aligned multi-source data, the spatial features related to real estate are extracted. Common features include: extracting the outline and boundary of the building through image processing or LiDAR point clouds. Extracting the height information of the building from LiDAR data or digital elevation model (DEM). Analyzing land use types (such as residential, commercial, industrial land, etc.) based on remote sensing images. Extracting spatial information of infrastructure such as roads and bridges from GIS data. Using classification algorithms (such as K-means clustering, support vector machines, etc.) to extract the types of objects (such as trees, water bodies, etc.) from data from different sources. The final feature data includes building location, shape, height, land type, etc. By cross-domain fusion of spatial features of multi-source real estate surveying and mapping data, more comprehensive and accurate spatial information can be obtained. Cross-domain feature fusion means integrating features from different fields (such as LiDAR point cloud data and remote sensing image data). According to the accuracy and reliability of different data sources, different weights are assigned to each feature, and weighted average or weighted sum is performed. For example, when fusing building height information, higher weights can be given according to the accuracy of LiDAR data. Use machine learning methods (such as deep neural networks, random forests, etc.) to map features from different data sources to a unified feature space, and automatically discover the mapping relationship between data sources through learning models.Multimodal learning methods are used to fuse features from different data sources. For example, the fusion of images and point clouds can extract image features through convolutional neural networks (CNN) and then fuse them with point cloud data.

[0080] Step S2: confirming the public surveying and mapping points of multi-source real estate surveying and mapping data by integrating the spatial feature data of real estate surveying and mapping to obtain the public surveying and mapping point data of real estate surveying and mapping; using the public surveying and mapping point data of real estate surveying and mapping to perform local surveying and mapping distortion correction to generate structural surveying and mapping correction data; reconstructing the real estate surveying and mapping high-dimensional space on the structural surveying and mapping correction data to generate three-dimensional real estate model data; and identifying the real estate use pattern on the three-dimensional real estate model data to generate real estate use pattern data;

[0081] In an embodiment of the present invention, public surveying and mapping points refer to points with common coordinates in multi-source real estate surveying and mapping data. These points are usually high-precision, representative objects or feature points. Public surveying and mapping points are used for registration, alignment, and subsequent correction and fusion between different data sources. First, each data source (such as satellite images, LiDAR point clouds, GIS data, etc.) in the multi-source real estate surveying and mapping data is evaluated for accuracy. The accuracy of each data source is evaluated using existing geographic reference points or measurement calibration points. Based on the fused spatial feature data, a spatial matching algorithm (such as the nearest neighbor algorithm, RANSAC algorithm, SIFT / SURF feature matching algorithm, etc.) is used to identify the same objects or feature points in different data sources. These points become public surveying and mapping points after being confirmed. By calculating the matching degree (such as Euclidean distance or angle matching degree) between different data sources, public surveying and mapping points are determined and a data set is generated. These points will be used as reference points in subsequent corrections. Surveying and mapping distortion usually refers to geometric errors caused by different measurement tools, measurement angles, or data processing algorithms. These errors are manifested as offsets, distortions, or irregularities in point clouds. Local distortion correction aims to accurately fix these errors and ensure the accuracy of surveying and mapping data. Using the public surveying and mapping point data of real estate surveying and mapping as a benchmark, local error analysis is performed on the points in each data source to identify local distortion areas in the surveying and mapping data. These areas include building edges, road lines or natural features. Through mathematical modeling, a local distortion model is established. Common methods include models based on Gaussian error correction, Lagrange interpolation or least squares method. The surveying and mapping data are corrected using the established distortion model, and the distorted areas are repaired by adjusting the coordinate positions of the measuring points. After local correction, the geometric accuracy of the surveying and mapping data is improved, and corrected structural surveying and mapping data are generated, which lays the foundation for subsequent three-dimensional reconstruction and pattern recognition. The corrected structural surveying and mapping data is used for high-dimensional space reconstruction to generate three-dimensional real estate model data with high accuracy and integrity. This process includes steps such as point cloud reconstruction and surface fitting. First, the structural surveying and mapping correction data is converted into point cloud data. Then, the point cloud data is downsampled to reduce the data volume and improve processing efficiency. Common downsampling methods include voxel grid or random sampling. The downsampled point cloud data is divided into multiple regions, each containing points with similar features. Based on these regions, the corresponding spatial features are extracted. A three-dimensional grid is generated by triangulating the point cloud data (such as Delaunay triangulation). Then, a three-dimensional space model is constructed using the point cloud data and regional features. The three-dimensional grid is smoothed using surface fitting techniques (such as B-spline fitting) to generate a more accurate surface structure and repair gaps caused by noise or missing data. Finally, after high-dimensional space reconstruction, a highly accurate three-dimensional real estate model data is obtained, covering the spatial information of real estate such as buildings, roads, and green spaces.Real estate use patterns refer to the identification and classification of real estate space usage, function, configuration and other features. For example, a building is defined as commercial land, residential, office building, etc., and use pattern recognition aims to extract these functional information from the three-dimensional real estate model. First, the known real estate use patterns are matched with the spatial features in the three-dimensional model through manual annotation or historical data annotation. Common annotation methods include annotating building types, uses, number of floors, etc. Relevant features such as building height, floor area, shape, etc. are extracted from the three-dimensional real estate model data. Combined with sensor data (such as environmental monitoring data), multi-dimensional feature analysis is performed. Machine learning algorithms (such as support vector machines, decision trees, deep learning networks, etc.) are used to train and classify the extracted features to identify different real estate use patterns. Based on the recognition results, real estate use pattern data is generated.

[0082] Step S3: performing multi-layer semantic label association on the three-dimensional real estate model data according to the real estate use pattern data to generate multi-layer semantic label data; performing rule mining on the real estate semantic label data to generate real estate association rule mining data; constructing graph nodes and edges on the multi-layer semantic label data based on the real estate association rule mining data to generate a real estate surveying and mapping semantic association map;

[0083] In an embodiment of the present invention, semantic labels of different levels are defined according to the real estate use pattern data. For example, the top-level label may include "real estate type" (such as residential, commercial, office, etc.), the middle-level label may involve the specific functions of the building (such as bedroom, living room, kitchen, etc.), and the bottom-level label may be related to the structural characteristics of the building (such as wall material, window type, floor number, etc.). The real estate use pattern data is parsed and semantically annotated using natural language processing (NLP) and knowledge graph technology. In this process, a hierarchical semantic label system is constructed by combining spatial data, structural data, and use patterns. Each real estate unit (such as a building, a room, etc.) is assigned one or more semantic labels according to its spatial location, function, use type, and other attributes. Semantic labels of the same type or similar functions are associated through label association algorithms (such as label-based similarity calculation, cluster analysis, etc.). For example, the labels "residential area" and "bedroom" can be associated through certain specific similarity algorithms. This process establishes semantic connections between different levels to form a multi-level label system. Finally, the label of each real estate unit will generate a multi-level semantic label dataset based on its attributes and functions. This dataset includes multiple levels of label information, such as real estate type, use, structural characteristics, etc. By mining the rules of multi-layer semantic label data, the potential correlation and dependency between real estate attributes can be discovered, thereby guiding subsequent management and optimization decisions. For example, the "relationship between the number of bedrooms and the number of family members in a residential area" or the "relationship between the number of floors in a commercial area and the rental price" can be mined. Common rule mining algorithms include Apriori algorithm, FP-growth algorithm, etc., which can extract frequent item sets and their association rules from a large amount of data. In this step, the multi-layer semantic label data of real estate is used as input, and the relationship between labels is mined through the association rule mining algorithm. After mining the potential rules, the rules are evaluated and those with high support, confidence and lift are selected as valid association rules. These rules reveal the mutual influence between different usage patterns, functions and attributes of real estate. Through rule mining, a real estate association rule dataset is generated, which includes association rules between different semantic labels and indicates the potential connections and dependencies between different real estate units. The semantic labels of real estate and their associations are represented as a graph model, where each node represents a real estate unit or label, and the edges represent the semantic associations or regular relationships between different nodes. The attributes of the nodes can include the spatial characteristics, usage patterns, label information, etc. of the real estate. Each real estate unit is constructed as a node in the graph through its corresponding multi-layer semantic labels. For example, residential areas, office buildings, commercial streets, etc. can be used as different nodes, and specific functional labels such as "bedroom" or "living room" can be used as node attributes.Through real estate label data, real estate units are further divided, for example, more detailed nodes are constructed according to the floor, purpose, structure and other information of the building. Use association rules to mine data and construct edges between graph nodes. Each edge represents the relationship between two nodes (such as two real estate units or two labels). These relationships can be functional similarities, spatial proximity, or potential connections obtained based on rule mining results. The weight of the edge can be represented by parameters such as the confidence and support of the rule. For example, if the rule between "residential area" and "bedroom" has a higher support, then the edge weight between them is larger. Based on the nodes and edges constructed above, a complete semantic association graph for real estate surveying and mapping is formed.

[0084] Step S4: The semantic label data of the real estate surveying and mapping semantic association map is stored on the chain to generate the real estate surveying and mapping semantic chain storage data; the data stored on the real estate surveying and mapping semantic chain is collaboratively shared to generate real-time shared surveying and mapping data to execute the real estate surveying and mapping data processing sharing operation.

[0085] In the embodiment of the present invention, in order to ensure the transparency, immutability and decentralized storage of data, data can be stored on the chain based on blockchain technology. The decentralized nature of blockchain makes the data storage of the semantic association map of real estate surveying and mapping safe and reliable. Encode each semantic label data in the semantic association map of real estate surveying and mapping so that it can conform to the storage format of the blockchain smart contract. Usually, the label data is encrypted using a hash algorithm, and a hash value is generated, and the data is stored through a smart contract. The unique hash value of each semantic label will be associated with the corresponding real estate unit to ensure the uniqueness and immutability of the data. To store semantic label data, a storage structure based on blockchain can be designed, in which each block stores a certain amount of semantic label data, and each block points to the next block to form a chain structure. The specific content of data storage includes information such as multi-layer semantic labels of real estate units, association relationships between labels (association rules represented by edges), etc. After all the data in the semantic association map of real estate surveying and mapping are encoded in the above manner, they are uploaded to the blockchain network to generate real estate surveying and mapping semantic chain storage data. This data set will contain encrypted storage versions of all real estate-related spatial features, functional labels, usage patterns, association rules and other information. Design a distributed data access strategy based on blockchain to ensure that all parties can access the data stored on the real estate surveying and mapping semantic chain according to their permissions. In this strategy, public key encryption and private key decryption mechanisms are used to protect the security of data. Different users (such as urban planners, real estate developers, architects, etc.) can access data according to different permissions to obtain some information related to their work. Establish a collaborative sharing mechanism for real estate data, that is, all parties can collaboratively access and share real estate surveying and mapping semantic data through smart contract protocols. This mechanism ensures that multiple users share data without compromising data security and privacy, and promotes the efficient use of data. Use the real-time nature of blockchain to ensure that real estate surveying and mapping semantic data can be updated and shared in real time. When real estate data changes (such as building structure adjustments, functional changes, etc.), the corresponding semantic labels will be automatically updated, and the data will be updated synchronously in the blockchain through the smart contract mechanism. This enables all authorized users to obtain the latest real estate surveying and mapping semantic data. Through data collaborative sharing, real-time shared surveying and mapping data is generated, which can be viewed, edited and analyzed by authorized users at any time. The shared data includes not only structural information, spatial features, usage patterns, etc., but also association rules and predictive analysis data obtained through graph analysis. Based on the real-time shared surveying and mapping data, all parties can automatically perform a series of data processing operations through smart contracts. For example, based on the shared surveying and mapping data, tasks such as building planning optimization, construction progress monitoring, and asset evaluation can be automatically performed. These operations can be processed through integrated tools and platforms to generate further analysis results.To achieve automatic processing and sharing of real estate surveying and mapping data, smart contracts are designed to automate data access, processing, and sharing operations. For example, smart contracts can set rules to specify which data can be shared with which users and which data can be updated under specific conditions. The execution process of the contract does not require an intermediary and automatically completes the exchange and operation of data. Through the trigger mechanism in the blockchain, smart contracts can be automatically triggered under specific conditions. For example, when real estate surveying and mapping data is updated, the smart contract will automatically detect the change of the data and process the data accordingly (such as rebuilding a three-dimensional model, updating spatial feature labels, etc.), and then store the processing results on the chain and share them with the corresponding users. Build a blockchain-based data sharing platform to support data access, analysis, and collaboration for multiple stakeholders in the real estate field (such as real estate developers, governments, architects, etc.). These users can use the platform to collaboratively operate and analyze real-time shared surveying and mapping data to maximize the use of data. Provide API interfaces for third-party applications or systems to enable them to access data stored on the real estate surveying and mapping semantic chain. Through these APIs, users can obtain shared data in real time and conduct further analysis and processing.

[0086] Preferably, step S1 comprises the following steps:

[0087] Step S11: Acquire multi-source real estate surveying and mapping data;

[0088] Step S12: performing time synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping synchronization data; performing spatial coordinate alignment on the multi-source real estate surveying and mapping synchronization data to generate multi-source real estate surveying and mapping spatial alignment data;

[0089] Step S13: performing data preprocessing on the multi-source real estate surveying and mapping spatial alignment data to generate standard real estate surveying and mapping data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0090] Step S14: extracting real estate spatial features from the standard real estate surveying and mapping data to obtain real estate spatial feature data; and performing cross-domain feature fusion on the standard real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data.

[0091] In an embodiment of the present invention, real estate-related data is collected from multiple sources. Data sources may include: cadastral information system (GIS) data; data collected by high-precision measuring instruments (such as laser radar, drones, satellite remote sensing, etc.); real estate registration information, construction drawings, land use information, etc. These data can be two-dimensional geographic data, or three-dimensional building models or point cloud data, covering multiple spatial dimensions of real estate. In the collected multi-source data, the time information is different, so all data need to be synchronized in time. This process needs to be matched according to the timestamp of the data to ensure that all source data are at the same time reference point. Since different measurement methods and sensor systems have different coordinate systems or data formats, these data need to be converted to a unified coordinate system (such as WGS84, UTM, etc.) to ensure spatial consistency. Common alignment methods include: using a total station, GPS or other positioning equipment for spatial alignment, or using a matching algorithm (such as an ICP algorithm) to accurately align point cloud data. Remove duplicate, incomplete or useless data points. Apply filtering algorithms (such as median filtering, Kalman filtering, etc.) to remove noise and errors in the data. Use interpolation methods (such as linear interpolation, Lagrange interpolation, etc.) to fill in the missing data in the measurement. Standardize the data from different measurement sources and convert all data to a unified metric to ensure that the comparison and fusion of data are not affected by scale differences. After these processes, the generated standard real estate surveying and mapping data will have a unified time, space and data format. Based on the standardized real estate surveying and mapping data, extract spatial feature information, such as the height, shape, volume of the building, and the land use type of the surrounding environment. These features can reflect the geometric characteristics, functional zoning and other aspects of the real estate. Fusion of the extracted spatial features with data from other fields (such as social economy, environmental impact, traffic flow, etc.) to form multi-dimensional comprehensive spatial feature data. This process can be carried out through data fusion techniques such as multimodal learning and graph convolutional networks (GCN), with the aim of utilizing the complementarity of data from different fields to improve the understanding and application of real estate information. Ultimately, the generated real estate surveying and mapping fusion spatial feature data will integrate information from different data sources and fields, providing richer and more comprehensive basic data for subsequent analysis and decision-making.

[0092] Preferably, cross-domain feature fusion of standard real estate surveying and mapping data based on real estate spatial feature data includes:

[0093] Perform high-level spatial feature decomposition on real estate spatial feature data to generate real estate high-level spatial feature decomposition data; perform low-level spatial feature decomposition on standard real estate surveying and mapping data to generate real estate low-level spatial feature decomposition data;

[0094] Perform feature distribution difference analysis on real estate low-level spatial feature decomposition data and real estate high-level spatial feature decomposition data to generate spatial feature distribution difference data; perform spatial cross-domain feature comparison on real estate low-level spatial feature decomposition data and real estate high-level spatial feature decomposition data based on spatial feature distribution difference data to generate real estate surveying and mapping spatial feature alignment data;

[0095] The real estate surveying and mapping spatial feature alignment data is used to perform multi-dimensional feature fusion on the standard real estate surveying and mapping data to generate real estate surveying and mapping fused spatial feature data.

[0096] In the embodiment of the present invention, by applying wavelet transform to decompose spatial data, extracting spatial features of different scales and frequencies, it is possible to identify high-level features such as the global shape, structure and complexity of real estate objects. Reduce the dimension of high-dimensional spatial feature data, retain the main components, and generate a low-dimensional representation that can represent the main information of spatial data. Use deep learning models such as convolutional neural networks (CNN) to process spatial images, point clouds or other spatial data of real estate to extract high-level spatial features, such as the type of buildings, functional zoning, etc. After these processes, the obtained real estate high-level spatial feature decomposition data will mainly reflect information such as spatial structure, layout, and function. Generate low-level spatial feature data by calculating the geometric features of real estate spatial objects (such as area, boundary, angle, side length, volume, etc.). Apply edge detection algorithms (such as Canny algorithm) and texture analysis methods (such as gray level co-occurrence matrix) to extract low-level spatial features from image data, such as the outline of the building, wall texture, etc. Cluster the real estate surveying and mapping data to identify low-level spatial features of different regions, such as density distribution of different building areas, land use type, etc. Finally, the obtained real estate low-level spatial feature decomposition data will be expressed as the basic unit of the spatial structure and its geometric features. The distribution difference between low-level and high-level features is evaluated by statistical methods (such as chi-square test, KL divergence, etc.). For example, the distribution difference between the basic geometric features of a building and its spatial functional zoning can be analyzed. The similarity and difference between low-level spatial features and high-level spatial features are evaluated by correlation analysis (such as Pearson correlation coefficient, mutual information) to help identify the connection and difference between cross-domain features. The generated spatial feature distribution difference data will provide a basis for subsequent feature alignment and fusion. The spatial position between low-level and high-level features is adjusted by optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) to ensure the consistency of the two in space. The low-level features are mapped to the high-level features by mapping algorithms (such as nonlinear mapping, projection method) to ensure their consistency in spatial dimensions. This step will generate real estate surveying and mapping spatial feature alignment data, which provides a basis for multi-dimensional feature fusion. According to the real estate surveying and mapping spatial feature alignment data, the spatial features of different dimensions (such as geometry, function, environment, etc.) are weighted and fused to form a unified spatial feature representation. By combining spatial features from different sensors, measurement methods, and data sources, end-to-end fusion is performed through deep learning methods (such as deep convolutional neural networks) to optimize the comprehensive performance of spatial features. After fusion, the generated real estate surveying and mapping fusion spatial feature data will be able to fully reflect the various dimensional characteristics of real estate, providing rich data support for further analysis, modeling, and decision-making.

[0097] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0098] Step S21: performing real estate structural analysis on multi-source real estate surveying and mapping data by integrating spatial feature data with real estate surveying and mapping to generate real estate surveying and mapping structural data; confirming public surveying and mapping points on multi-source real estate surveying and mapping data based on the real estate surveying and mapping structural data to obtain real estate surveying and mapping public surveying and mapping point data;

[0099] Step S22: using the real estate surveying and mapping public surveying and mapping point data to perform local surveying and mapping distortion analysis on the real estate surveying and mapping structure data to generate real estate local surveying and mapping distortion data; performing surveying and mapping data correction on the real estate surveying and mapping structure data using the real estate local surveying and mapping distortion data to generate structure surveying and mapping correction data;

[0100] Step S23: reconstructing the real estate surveying and mapping high-dimensional space on the structural surveying and mapping correction data to generate three-dimensional real estate model data; performing dynamic spatiotemporal grid analysis on the three-dimensional real estate model data to generate three-dimensional real estate dynamic spatiotemporal grid data;

[0101] Step S24: Based on the three-dimensional real estate dynamic spatiotemporal grid data, real estate use pattern recognition is performed on the three-dimensional real estate model data to generate real estate use pattern data.

[0102] In an embodiment of the present invention, the structural features of real estate are identified by using geometric analysis methods (such as morphological analysis, boundary detection, topological analysis, etc.). By extracting the geometric forms of the building's appearance, roof structure, doors and windows, etc., a structural representation of the real estate is established. A spatial segmentation algorithm (such as Voronoi diagram, Delaunay triangulation) is applied to subdivide the real estate area to identify different functional areas, building units and peripheral facilities. Based on the aforementioned spatial segmentation data, the structural features of the real estate are extracted, including the number of floors, volume, floor area, building spacing, etc. of the building. Combined with data from different sources (such as satellite images, ground laser scanning, remote sensing data, etc.), the comprehensive structural data of the real estate is generated through fusion technology (such as multi-source data weighted fusion, deep learning model). These data can be used as the basis for subsequent surveying and mapping analysis. Using spatial data alignment technology, the public surveying and mapping points are confirmed based on the known public surveying and mapping points of the real estate (such as road intersections, building corners, etc.). Similarity matching or key point recognition algorithms can be used, such as feature point detection methods based on SIFT, ORB, etc., to find the public surveying and mapping points in the real estate data, and calibrate and confirm them. Analyze the geometric distortion in real estate surveying and mapping data through local consistency test. For example, the deviation or distortion in surveying and mapping data can be identified by comparing the positions of common surveying and mapping points in different data sources. Apply the least squares method or other optimization algorithms to perform distortion detection on surveying and mapping data, identify local surveying and mapping errors, and provide data support for error correction. By comparing the positions and distances of surveying and mapping points from different data sources, local surveying and mapping distortion data are generated to indicate the position and size of deviations during the surveying and mapping process. Using the local real estate surveying and mapping distortion data, the real estate surveying and mapping data is accurately corrected through local correction algorithms (such as RANSAC algorithm, Kalman filter, etc.) to eliminate distortion and errors. Finally, based on the corrected data, structural surveying and mapping correction data is generated to provide accurate basic data for subsequent spatial reconstruction and analysis. Reconstruct the two-dimensional surveying and mapping data into three-dimensional spatial data through stereo vision-based algorithms (such as multi-view geometric reconstruction) or point cloud reconstruction technology (such as point cloud processing based on laser scanning data). Through 3D modeling software (such as Revit, Blender, etc.) or custom algorithms, based on the corrected data, an accurate 3D model is constructed to reflect the spatial structure, appearance and function of the real estate. According to the reconstruction algorithm, the 3D model data of the real estate is obtained, which includes detailed information such as the three-dimensional form of the building, building materials, functional zoning, indoor and outdoor structures, etc. According to the data of the 3D model, the spatiotemporal characteristics of the real estate are analyzed by applying spatiotemporal grid division technology (such as grid-based spatial segmentation). By modeling the changes in the 3D real estate data in the time dimension, the spatiotemporal changes in the use of the real estate (such as the frequency of use of the building, environmental changes, etc.) are analyzed. The spatiotemporal grid data is combined with the 3D model of the real estate to generate dynamic spatiotemporal grid data containing time and space changes.Use machine learning algorithms (such as support vector machines, decision trees, cluster analysis, etc.) to analyze the three-dimensional dynamic spatiotemporal data of real estate and identify the use patterns of real estate. Extract relevant features of real estate use (such as frequency of use, spatial function, environmental impact, etc.) from dynamic spatiotemporal grid data. Based on the extracted features, use classification algorithms to identify the use patterns of real estate, such as different functional modes such as residential, commercial, and industrial. According to the identified use patterns, convert them into a structured data format, including information such as the use type, spatial utilization, and spatiotemporal characteristics of the real estate, to provide support for subsequent management and decision-making.

[0103] Preferably, step S22 includes the following steps:

[0104] Step S221: extract key geometric information from real estate surveying and mapping structure data using real estate surveying and mapping public surveying and mapping point data to obtain real estate key geometric information data; perform spatial topological characteristic analysis on real estate surveying and mapping structure data using real estate key geometric information data to generate real estate spatial topological characteristic data;

[0105] Step S222: Perform dynamic offset calculation on the real estate space topology characteristic data to obtain real estate space topology dynamic offset data; wherein the formula for dynamic offset calculation is as follows:

[0106]

[0107] Where D(x, y, z) is the offset distance, x is the horizontal coordinate of the survey point offset, y is the vertical coordinate of the survey point offset, and z is the vertical coordinate of the survey point offset. t Expressed as the horizontal position of the theoretical survey point, y t Expressed as the vertical position of the theoretical survey point, z t Expressed as the vertical coordinate of the theoretical survey point, x s Represented as the actual horizontal coordinate of the surveying point, y s Expressed as the actual ordinate of the surveying point, z s It is expressed as the actual vertical coordinate of the surveying point;

[0108] Step S223: converting the real estate spatial topology dynamic offset data into an offset curve to generate a surveying and mapping offset curve; calculating the offset curvature of the surveying and mapping offset curve to obtain offset curvature data; and performing distortion space mapping on the real estate surveying and mapping structure data through the offset curvature data to generate real estate local surveying and mapping distortion data;

[0109] Step S224: performing surveying and mapping data correction on the real estate surveying and mapping structure data using the real estate local surveying and mapping distortion data to generate structure surveying and mapping correction data.

[0110] In an embodiment of the present invention, key geometric features such as building boundary lines, corner points, curve contours, roof lines, and wall connection points are extracted from real estate surveying and mapping structure data. Common methods include edge detection (such as Canny edge detection algorithm), Hough transform (for extracting straight line and circular features) and morphological operations (such as corrosion and expansion) to extract basic geometric information. If the data is in point cloud format, geometric key points or regions can be extracted using methods such as normal vector calculation, surface fitting, and point cloud segmentation. The key geometric information of real estate extracted by the algorithm (such as the shape of the building, segmentation line, key measurement points, etc.) is stored in the form of data for subsequent analysis. The data format can select a description of 3D geometry (such as Mesh, point cloud, B-rep, etc.) or other structured data formats. Topological analysis is performed on the extracted geometric information to determine the connection relationship between the various parts of the real estate (such as adjacent buildings, door and window positions, and the connection between walls and windows). Algorithms in graph theory, such as the shortest path algorithm or the minimum spanning tree algorithm, can be used to analyze the topological relationship. Based on the topological analysis results, spatial topological characteristic data reflecting the structure of the real estate is generated. This data usually includes information such as spatial connections between various parts of the real estate, adjacency, and enclosed areas. Calculate the offset distance of the survey point, where: x represents the horizontal coordinate of the survey point offset, y represents the vertical coordinate of the survey point offset, and z represents the vertical coordinate of the survey point offset. t Expressed as the horizontal position of the theoretical survey point, y t Expressed as the vertical position of the theoretical survey point, z t Expressed as the vertical coordinate of the theoretical survey point, x s Represented as the actual horizontal coordinate of the surveying point, y s Expressed as the actual ordinate of the surveying point, z sIt is expressed as the actual vertical coordinate of the surveying point; for each surveying point, the offset distance between its theoretical position and the actual position is calculated, and the obtained offset data can be used to describe the deviation or error in the surveying process. The dynamic offset data of all surveying points are integrated to generate the overall spatial offset data, which characterizes the offset change of the real estate structure during the surveying process. This data can be used for further distortion analysis and correction. By smoothing and fitting the dynamic offset data of the real estate spatial topology (for example, using B-spline curve fitting, Lagrange interpolation and other methods), a smooth offset curve is generated. This step helps to eliminate noise and clearly show the overall trend of the data. The offset data is converted into a visual offset curve chart to reflect the trend of the position change of the measuring point during the surveying process. Through the above processing, a set of curve data representing the surveying offset situation is obtained for subsequent analysis. According to the generated surveying offset curve, the curvature data is calculated to evaluate the curvature and change rate of the curve. The curvature can be calculated by the second-order derivative or extracted by the curve fitting method. The calculated curvature value is the offset curvature data, which reflects the offset change characteristics of different areas during the surveying process. Based on the offset curvature data, distortion space mapping is performed to identify and map the distorted areas in the real estate structure. Common methods include interpolation algorithms based on local features or spatial mapping techniques to map the offset curvature to the spatial coordinate system of the surveying and mapping data for local distortion analysis. According to the results of the offset curvature, the areas with distortion in the real estate structure are marked, and local real estate surveying and mapping distortion data are generated. These data are helpful in analyzing the accuracy of surveying and mapping and provide a basis for subsequent correction. According to the local real estate surveying and mapping distortion data, the real estate surveying and mapping data is corrected using a suitable distortion correction algorithm. For example, a correction method based on a transformation model (such as affine transformation, perspective transformation, etc.) or an optimization algorithm (such as least squares method, genetic algorithm, etc.) can be used to adjust local errors. Through the optimization algorithm, the deviation caused by distortion in the surveying and mapping data is corrected, and the corrected data is generated to ensure that the measurement data is more accurate. Finally, the corrected real estate surveying and mapping data will be organized into structural surveying and mapping correction data to provide accurate basic data for subsequent analysis and model building.

[0111] Preferably, step S224 specifically includes:

[0112] Extracting regional error distribution features of real estate surveying and mapping structure data through real estate local surveying and mapping distortion data to obtain regional error distribution feature data, wherein the regional error distribution feature data includes an offset vector, a distortion radius, and an error intensity;

[0113] Perform Gaussian error correction calculation on the local real estate surveying and mapping distortion data according to the offset vector, distortion radius and error intensity to generate local correction parameter data;

[0114] Based on the local correction parameter data, correction matrices are generated for the offset vector, distortion radius and error intensity respectively to obtain preliminary correction matrix data; the real estate surveying and mapping structure data is globally corrected and optimized through the preliminary correction matrix data to generate global optimized correction data;

[0115] The global optimization correction data is used to perform multi-scale correction on the real estate surveying and mapping structural data to generate structural surveying and mapping correction data, wherein the multi-scale correction application includes macro correction, meso correction and micro correction.

[0116] In an embodiment of the present invention, by comparing the positions of the actual measurement point and the theoretical measurement point, the offset vector of each measurement point (i.e., the difference between the actual position and the theoretical position of the measurement point) is extracted. The offset vector represents the direction and magnitude of the error in space. The distortion radius of each measurement point is calculated by geometric analysis, and the distortion radius describes the degree of spatial deviation of the measurement point from the theoretical position to the actual position. The distortion radius can be determined by calculating the spatial relationship between each measurement point and its adjacent points. Based on the offset vector and the distortion radius, the error intensity, i.e., the comprehensive degree of offset and distortion, is calculated. The error intensity index can be used to quantify the size of the error. For example, the error intensity can be calculated by a combination of vector length and distortion. The offset vector, distortion radius, and error intensity data set obtained from the above calculation generate regional error distribution feature data, which are used to describe the real estate distortion characteristics within the measurement area and provide a basis for subsequent correction. Assuming that the measurement error obeys a Gaussian distribution, a Gaussian error model can be applied to correct the measurement data. Error correction is performed by maximizing the likelihood estimate or minimizing the square error. Based on the regional error distribution feature data (offset vector, distortion radius, and error intensity), Gaussian error correction is performed on the deviation of the measurement point. Specifically, the expected value and standard deviation of the Gaussian distribution are used to correct the position of each measurement point. Through the Gaussian error correction calculation, a set of local correction parameters are obtained, which will be used for the subsequent correction matrix generation. The offset vector is corrected using the local correction parameter data to adjust the position of the measurement point to make it closer to the theoretical position. The correction of the offset vector can be performed by weighted average or least squares method. The distortion radius is adjusted according to the local correction parameter data to reduce the distortion error in real estate surveying and mapping. The error intensity is adjusted according to the local correction parameter data to optimize the error intensity distribution and reduce inconsistency. The correction results of the offset vector, distortion radius and error intensity are combined to generate preliminary correction matrix data. This matrix represents the necessary transformation to adjust the surveying and mapping data to ensure that the data is more consistent. The preliminary correction matrix is ​​optimized using a global optimization algorithm (such as genetic algorithm, particle swarm optimization, simulated annealing, etc.) to achieve a globally consistent correction effect. This step adjusts the errors in the measurement data to ensure the consistency of the measurement data in spatial distribution. Through global optimization, the influence of local errors is eliminated, so that the data of the entire surveying and mapping area reaches global consistency. The optimization goal is to minimize the measurement error of the entire area. The optimized correction data reflects the correction results of the entire surveying area, generating global optimization correction data as the final correction data. Based on the global optimization correction data, macro-scale correction is first performed to correct errors in a large range within the surveying area. This usually involves adjusting the overall position, such as the approximate position of a building. Then, meso-scale correction is performed to adjust medium-scale errors within the surveying area, such as errors between walls and floors. Finally, micro-scale correction is performed, down to the accuracy correction of a single measurement point.This step focuses on small-scale details in the measurement, such as accurate correction of small structures, equipment or wall corners, etc. Through macro, moderate and micro scale corrections, the final structural mapping correction data is generated, which is accurately corrected to reflect the real, real estate structural space information.

[0117] Preferably, reconstructing the real estate surveying and mapping high-dimensional space of the structural surveying and mapping correction data includes:

[0118] Perform point cloud conversion on the structural surveying and mapping correction data to generate structural surveying and mapping point cloud data; perform point cloud downsampling on the structural surveying and mapping point cloud data to generate structural surveying and mapping downsampling point cloud data;

[0119] Perform regional point cloud segmentation on the downsampled point cloud data of structural surveying and mapping to generate regional point cloud segmentation data; perform structural angle feature key point extraction on the regional point cloud segmentation data to obtain structural angle feature key point data; perform Euclidean distance calculation on the regional point cloud segmentation data based on the structural angle feature key point data to obtain the real estate structure point cloud adjacency graph;

[0120] Perform point cloud triangulation on the adjacency graph of the real estate structure point cloud to generate point cloud triangulated mesh data; perform surface fitting on the point cloud triangulated mesh data to generate real estate point cloud surface fitting data;

[0121] The three-dimensional real estate model data is generated by performing three-dimensional model texture mapping on the point cloud triangular mesh data through real estate point cloud surface fitting data.

[0122] In an embodiment of the present invention, the original surveying and mapping data is converted into point cloud data by performing point cloud conversion on the structural surveying and mapping correction data. Each measurement point generates a point according to its coordinate position, representing a spatial position in the real estate structure. A point cloud generation algorithm (such as voxelization or interpolation) is used to convert the correction data into dense point cloud data. Each point in the point cloud carries spatial coordinate information (x, y, z). The point cloud data contains the spatial information of the real estate structure and is the basis for subsequent processing and reconstruction. The structural surveying and mapping point cloud data is downsampled to reduce the density of the data in order to increase the processing speed and reduce the computational complexity. Common downsampling methods include: dividing the space into voxel units of equal size, selecting a representative point (such as a center point) in each voxel as the downsampling result. A certain proportion of points are randomly selected to reduce the amount of data in the point cloud. Through downsampling, the density of the point cloud data is reasonably controlled while still retaining sufficient structural information. The downsampled point cloud data contains key spatial information and is suitable for further analysis and processing. The downsampled point cloud data for structural mapping is regionally segmented, and the entire point cloud space is divided into multiple small areas. The point cloud data within each area has similar spatial characteristics, which is convenient for the analysis of local features. Regional segmentation can be based on spatial density or geometric features. Common methods include grid-based segmentation or segmentation based on clustering algorithms (such as K-means clustering). Each block of data represents the point cloud data within a region, which can be processed independently and also provides spatial organization for subsequent feature extraction and analysis. The key points of the structural angle feature are extracted in each regional point cloud block. The structural angle feature mainly refers to the important feature points in the point cloud that can represent the structure, such as the corners and edges of the building. The extraction method can use normal calculation to identify the corners or edge points in the point cloud by calculating the normal direction of each point. Common algorithms such as RANSAC (random sampling consensus) algorithm can be used to extract local geometric features. These key points can be local maximum curvature points, or areas with significant changes in the point cloud, representing important geometric features in the real estate structure. The extracted key point data is used to represent the important features in the real estate structure, providing a basis for further calculating the adjacency relationship of the point cloud. According to the extracted key point data of the structural angle feature, the Euclidean distance between each point in the point cloud is calculated. By calculating the distance, it is possible to identify which points are adjacent and which points are geometrically related. This provides a basis for generating a point cloud adjacency graph. The real estate structure point cloud adjacency graph obtained through Euclidean distance calculation can represent the spatial relationship between point clouds and help the subsequent triangular mesh generation. Based on the real estate structure point cloud adjacency graph, the point cloud is triangulated. Triangulation is the process of converting point cloud data into a mesh composed of triangles, each triangle consisting of three adjacent points, which is used to represent the geometric shape of the spatial surface. Commonly used triangulation algorithms include Delaunay triangulation and Voronoi diagram.These algorithms can automatically generate reasonable triangular meshes based on the adjacency relationship of point clouds. After the point cloud is triangulated, the generated mesh data can better express the surface information of the real estate structure, providing a basis for subsequent surface fitting and three-dimensional modeling. The purpose of surface fitting the point cloud triangular mesh data is to generate a smooth surface through the fitting algorithm so that the mesh can better simulate the real shape of the real estate. Commonly used surface fitting methods include least squares fitting and B-spline surface fitting, which can generate smooth and continuous three-dimensional surfaces based on point cloud data. The surface morphology of the real estate structure is represented by the fitted surface data, providing accurate geometric data for subsequent texture mapping and three-dimensional modeling. The texture mapping of the three-dimensional model is performed using the real estate point cloud surface fitting data. Texture mapping is the mapping of image textures (such as photos or other material surfaces) to the surface of the three-dimensional model to increase the realism of the model. Texture mapping usually uses the UV mapping method to correspond the two-dimensional texture image to the three-dimensional surface coordinates. Through texture mapping, the obtained three-dimensional real estate model not only contains geometric morphology information, but also texture information, making the model more realistic and intuitive.

[0123] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0124] Step S31: assigning semantic labels to the real estate use pattern data to generate real estate semantic label data;

[0125] Step S32: semantically associating the three-dimensional real estate model data according to the real estate semantic label data to generate real estate semantic label associated data;

[0126] Step S33: performing multi-layer label nesting on the real estate semantic label data through the real estate semantic label association data to generate multi-layer semantic label data;

[0127] Step S34: perform association rule mining on the multi-layer semantic label data to generate real estate association rule mining data; construct graph nodes and edges on the multi-layer semantic label data based on the real estate association rule mining data to generate a real estate surveying and mapping semantic association graph.

[0128] In the embodiment of the present invention, semantic labels are assigned to the real estate use pattern data (such as functional zoning, area, purpose, etc.). The assignment of semantic labels is to match the original data with specific semantic categories, so that the data is more meaningful, easy to understand and analyze. Semantic labels can be classifications for different use functions of real estate (such as residential, commercial, industrial), architectural features (such as high-rise, low-rise, garden), or use status (such as rented, for sale, sold), etc. Commonly used label types include: functional labels: such as "residential area" and "commercial area". Status labels: such as "for rent" and "rented". Location labels: such as "city center" and "suburbs". Through natural language processing (NLP) or rule matching algorithms, corresponding semantic labels are automatically attached to data points. Each real estate instance (such as a building, an area, a unit) will be assigned one or more semantic labels to form a data set containing semantic information. Semantic association is performed based on the semantic label data of the real estate. Semantic association refers to identifying potential connections or dependencies between real estate objects by analyzing the relationship between different labels. For example, the relationship between a residential area and a "high-rise" label, and the relationship between a commercial area and an "office building" label. For example, the downtown area is associated with the labels "high traffic" and "commercial area". For example, the label "for sale" in a certain area is associated with the label "residential", indicating that there are houses for sale in the area. Use graph-based semantic relationship modeling methods, such as semantic networks or ontologies, to capture the relationship between labels. The label data of real estate will be used to establish the association between labels to form an information structure containing label relationships. Based on the real estate semantic label association data, a more complex semantic structure is constructed by multi-layer label nesting. Multi-layer nesting means organizing semantic labels according to different levels to form a hierarchical semantic system. For example: the first layer can be basic function labels, such as "residential area" and "commercial area". The second layer can be detailed regional function labels, such as "high-rise residential" and "apartment". The third layer can further describe specific attribute labels, such as "luxury apartment" and "single room for rent". Through the hierarchical processing of label data, each label can be deeply analyzed and mined according to its hierarchy and correlation. Tree structure or multi-level classification model can be used to nest and organize labels. The resulting multi-layer label data can represent the multi-dimensionality and complexity of real estate information, and can be queried and analyzed through hierarchical relationships. The purpose of association rule mining on multi-layer semantic label data is to discover implicit association rules between different labels. Association rule mining is to automatically discover strong associations between labels through algorithms, for example: based on frequent item set mining, find label combinations that often appear together. The rules mined can be: if the label is "residential area" and the label is "high-rise", then the label "elevator" exists. If the label is "commercial area" and the label is "office building", then the label "parking lot" exists.These association rules help to understand the mutual influence and relationship between different labels, thus providing a basis for decision support. The data contains association rules based on real estate semantic labels, which are used to guide subsequent label analysis and processing. Based on the real estate association rules, data is mined, graph nodes and edges are constructed, and a semantic association map of real estate surveying and mapping is generated. The nodes in the map represent different semantic labels of real estate, and the edges represent the semantic associations between labels. Each semantic label (such as "residential area" and "city center") becomes a node in the graph. Data is mined according to the association rules, and edges are generated to represent the relationship between labels. For example, "residential area" and "high-rise" can be connected by an edge to represent the association between them. Using the map visualization tool, nodes and edges are drawn into a graph to facilitate intuitive display of semantic relationships and data associations. The map can be used to display and analyze the associations, dependencies and patterns between real estate semantic labels, and provide support for real estate analysis and decision-making.

[0129] Preferably, step S4 comprises the following steps:

[0130] Step S41: storing the semantic label data chain of the real estate surveying and mapping semantic association map to generate real estate surveying and mapping semantic chain storage data;

[0131] Step S42: constructing a distributed data access strategy for the data stored on the real estate surveying and mapping semantic chain to generate a distributed data access strategy; using the distributed data access strategy to collaboratively analyze the data stored on the real estate surveying and mapping semantic chain to generate real estate surveying and mapping semantic collaborative analysis data;

[0132] Step S43: compress and share the real estate surveying and mapping semantic collaborative analysis data, thereby generating real-time shared surveying and mapping data to execute real estate surveying and mapping data processing and sharing operations.

[0133] In the embodiment of the present invention, the generated real estate surveying and mapping semantic association map data is stored on the chain to ensure the reliability, immutability and traceability of the data. The core idea of ​​on-chain storage is to convert data (such as semantic tags, node relationships, etc.) into digital blockchain data blocks, which are connected in sequence to form a secure and decentralized storage network. During the storage process, each node in the real estate surveying and mapping semantic map (such as the functional tag of the real estate, the geographic location tag, etc.) is first hashed to ensure data security. Smart contracts can be used to automate storage operations, verify the correctness of data, and ensure that the access and modification permissions of real estate surveying and mapping data are managed according to preset rules. The final on-chain storage data not only retains the semantic information of real estate surveying and mapping, but also has the characteristics of blockchain (such as decentralization, data immutability and transparency). Based on the data stored on the real estate surveying and mapping semantic chain, a distributed data access strategy is constructed to achieve efficient and secure data access. The construction of a distributed data access strategy includes the following aspects: defining which users or systems can access which data. For example, real estate developers only access geographic information in a certain area, while policymakers can access global data. The real estate data is stored in shards according to region, function or other characteristics to reduce the data burden on each node and improve query efficiency. The redundant characteristics of the distributed system are used to ensure that the data can still be accessed when some nodes fail. Using the above strategies, the data stored on the real estate surveying and mapping semantic chain is collaboratively analyzed, that is, multiple nodes or systems can analyze and mine the data at the same time. Collaborative analysis can include, for example, data fusion analysis between real estate developers and municipal planning departments to optimize urban planning through shared data. Data from different regions and industries are analyzed in a linked manner, such as combining real estate market data with traffic flow data to predict market trends and generate real estate surveying and mapping semantic collaborative analysis data. This data set will contain the results of collaborative analysis by all parties to provide support for further decision-making. Data compression is performed on real estate surveying and mapping semantic collaborative analysis data to reduce the cost of data transmission and storage and improve efficiency. It ensures that the compressed data does not lose information, which is suitable for surveying and mapping data with high precision requirements. For some data that does not require complete accuracy, lossy compression algorithms can be used, such as video streams, picture data, etc. The compressed data will be packaged and protected using encryption technology to ensure privacy and security during data sharing. Utilize existing cloud computing or distributed platforms to ensure that data can be efficiently shared between different nodes. Use API interfaces and data exchange protocols (such as RESTful API) to provide data access points for different systems and applications, support real-time data sharing and interaction, and generate real-time shared mapping data, which can be accessed and processed in real time after being compressed and encrypted.For example, architects, urban planners or real estate investors can access up-to-date, compressed real estate mapping data to complete their respective work.

Claims

1. A real estate surveying and mapping data processing method based on intelligent data, characterized in that: The following steps are involved: Step S1: acquiring multi-source real estate surveying and mapping data; performing spatiotemporal synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping spatial alignment data; Extracting real estate spatial features from multi-source real estate surveying and mapping spatial alignment data to obtain real estate spatial feature data; performing cross-domain feature fusion on multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data; Step S2: confirming the public surveying and mapping points of multi-source real estate surveying and mapping data by integrating the spatial feature data of real estate surveying and mapping to obtain the public surveying and mapping point data of real estate surveying and mapping; using the public surveying and mapping point data of real estate surveying and mapping to perform local surveying and mapping distortion correction to generate structural surveying and mapping correction data; reconstructing the real estate surveying and mapping high-dimensional space on the structural surveying and mapping correction data to generate three-dimensional real estate model data; and identifying the real estate use pattern on the three-dimensional real estate model data to generate real estate use pattern data; Step S3: performing multi-layer semantic label association on the three-dimensional real estate model data according to the real estate use pattern data to generate multi-layer semantic label data; performing rule mining on the real estate semantic label data to generate real estate association rule mining data; constructing graph nodes and edges on the multi-layer semantic label data based on the real estate association rule mining data to generate a real estate surveying and mapping semantic association map; Step S4: The semantic label data of the real estate surveying and mapping semantic association map is stored on the chain to generate the real estate surveying and mapping semantic chain storage data; the data stored on the real estate surveying and mapping semantic chain is collaboratively shared to generate real-time shared surveying and mapping data to execute the real estate surveying and mapping data processing sharing operation.

2. The real estate surveying and mapping data processing method based on intelligent data according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire multi-source real estate surveying and mapping data; Step S12: performing time synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping synchronization data; performing spatial coordinate alignment on the multi-source real estate surveying and mapping synchronization data to generate multi-source real estate surveying and mapping spatial alignment data; Step S13: performing data preprocessing on the multi-source real estate surveying and mapping spatial alignment data to generate standard real estate surveying and mapping data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S14: extracting real estate spatial features from the standard real estate surveying and mapping data to obtain real estate spatial feature data; and performing cross-domain feature fusion on the standard real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data.

3. The real estate surveying and mapping data processing method based on intelligent data according to claim 2 is characterized in that: The cross-domain feature fusion of standard real estate surveying and mapping data based on real estate spatial feature data includes: Perform high-level spatial feature decomposition on real estate spatial feature data to generate real estate high-level spatial feature decomposition data; perform low-level spatial feature decomposition on standard real estate surveying and mapping data to generate real estate low-level spatial feature decomposition data; Perform feature distribution difference analysis on real estate low-level spatial feature decomposition data and real estate high-level spatial feature decomposition data to generate spatial feature distribution difference data; perform spatial cross-domain feature comparison on real estate low-level spatial feature decomposition data and real estate high-level spatial feature decomposition data based on spatial feature distribution difference data to generate real estate surveying and mapping spatial feature alignment data; The real estate surveying and mapping spatial feature alignment data is used to perform multi-dimensional feature fusion on the standard real estate surveying and mapping data to generate real estate surveying and mapping fused spatial feature data.

4. The real estate surveying and mapping data processing method based on intelligent data according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing real estate structural analysis on multi-source real estate surveying and mapping data by integrating spatial feature data with real estate surveying and mapping to generate real estate surveying and mapping structural data; confirming public surveying and mapping points on multi-source real estate surveying and mapping data based on the real estate surveying and mapping structural data to obtain real estate surveying and mapping public surveying and mapping point data; Step S22: using the real estate surveying and mapping public surveying and mapping point data to perform local surveying and mapping distortion analysis on the real estate surveying and mapping structure data to generate real estate local surveying and mapping distortion data; performing surveying and mapping data correction on the real estate surveying and mapping structure data using the real estate local surveying and mapping distortion data to generate structure surveying and mapping correction data; Step S23: reconstructing the real estate surveying and mapping high-dimensional space on the structural surveying and mapping correction data to generate three-dimensional real estate model data; performing dynamic spatiotemporal grid analysis on the three-dimensional real estate model data to generate three-dimensional real estate dynamic spatiotemporal grid data; Step S24: Based on the three-dimensional real estate dynamic spatiotemporal grid data, real estate use pattern recognition is performed on the three-dimensional real estate model data to generate real estate use pattern data.

5. The real estate surveying and mapping data processing method based on intelligent data according to claim 4 is characterized in that: Step S22 includes the following steps: Step S221: extract key geometric information from real estate surveying and mapping structure data using real estate surveying and mapping public surveying and mapping point data to obtain real estate key geometric information data; perform spatial topological characteristic analysis on real estate surveying and mapping structure data using real estate key geometric information data to generate real estate spatial topological characteristic data; Step S222: Perform dynamic offset calculation on the real estate space topology characteristic data to obtain real estate space topology dynamic offset data; wherein the formula for dynamic offset calculation is as follows: Where D(x, y, z) is the offset distance, x is the horizontal coordinate of the survey point offset, y is the vertical coordinate of the survey point offset, and z is the vertical coordinate of the survey point offset. t Expressed as the horizontal position of the theoretical survey point, y t Expressed as the vertical position of the theoretical survey point, z t Expressed as the vertical coordinate of the theoretical survey point, x s Represented as the actual horizontal coordinate of the surveying point, y s Expressed as the actual ordinate of the surveying point, z s It is expressed as the actual vertical coordinate of the surveying point; Step S223: converting the real estate spatial topology dynamic offset data into an offset curve to generate a surveying and mapping offset curve; calculating the offset curvature of the surveying and mapping offset curve to obtain offset curvature data; and performing distortion space mapping on the real estate surveying and mapping structure data through the offset curvature data to generate real estate local surveying and mapping distortion data; Step S224: performing surveying and mapping data correction on the real estate surveying and mapping structure data using the real estate local surveying and mapping distortion data to generate structure surveying and mapping correction data.

6. The real estate surveying and mapping data processing method based on intelligent data according to claim 5 is characterized in that: Step S224 specifically includes: Extracting regional error distribution features of real estate surveying and mapping structure data through real estate local surveying and mapping distortion data to obtain regional error distribution feature data, wherein the regional error distribution feature data includes an offset vector, a distortion radius, and an error intensity; Perform Gaussian error correction calculation on the local real estate surveying and mapping distortion data according to the offset vector, distortion radius and error intensity to generate local correction parameter data; Based on the local correction parameter data, correction matrices are generated for the offset vector, distortion radius and error intensity respectively to obtain preliminary correction matrix data; the real estate surveying and mapping structure data is globally corrected and optimized through the preliminary correction matrix data to generate global optimized correction data; The global optimization correction data is used to perform multi-scale correction on the real estate surveying and mapping structural data to generate structural surveying and mapping correction data, wherein the multi-scale correction application includes macro correction, meso correction and micro correction.

7. The real estate surveying and mapping data processing method based on intelligent data according to claim 4 is characterized in that: Reconstructing the high-dimensional space of real estate surveying and mapping based on the structural surveying and mapping correction data includes: Perform point cloud conversion on the structural surveying and mapping correction data to generate structural surveying and mapping point cloud data; perform point cloud downsampling on the structural surveying and mapping point cloud data to generate structural surveying and mapping downsampling point cloud data; Perform regional point cloud segmentation on the downsampled point cloud data of structural surveying and mapping to generate regional point cloud segmentation data; perform structural angle feature key point extraction on the regional point cloud segmentation data to obtain structural angle feature key point data; perform Euclidean distance calculation on the regional point cloud segmentation data based on the structural angle feature key point data to obtain the real estate structure point cloud adjacency graph; Perform point cloud triangulation on the adjacency graph of the real estate structure point cloud to generate point cloud triangulated mesh data; perform surface fitting on the point cloud triangulated mesh data to generate real estate point cloud surface fitting data; The three-dimensional real estate model data is generated by performing three-dimensional model texture mapping on the point cloud triangular mesh data through real estate point cloud surface fitting data.

8. The real estate surveying and mapping data processing method based on intelligent data according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: assigning semantic labels to the real estate use pattern data to generate real estate semantic label data; Step S32: semantically associating the three-dimensional real estate model data according to the real estate semantic label data to generate real estate semantic label associated data; Step S33: performing multi-layer label nesting on the real estate semantic label data through the real estate semantic label association data to generate multi-layer semantic label data; Step S34: perform association rule mining on the multi-layer semantic label data to generate real estate association rule mining data; construct graph nodes and edges on the multi-layer semantic label data based on the real estate association rule mining data to generate a real estate surveying and mapping semantic association graph.

9. The real estate surveying and mapping data processing method based on intelligent data according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: storing the semantic label data chain of the real estate surveying and mapping semantic association map to generate real estate surveying and mapping semantic chain storage data; Step S42: constructing a distributed data access strategy for the data stored on the real estate surveying and mapping semantic chain to generate a distributed data access strategy; using the distributed data access strategy to collaboratively analyze the data stored on the real estate surveying and mapping semantic chain to generate real estate surveying and mapping semantic collaborative analysis data; Step S43: compress and share the real estate surveying and mapping semantic collaborative analysis data, thereby generating real-time shared surveying and mapping data to execute real estate surveying and mapping data processing and sharing operations.

10. A real estate surveying and mapping data processing system based on intelligent data, characterized in that: For executing the real estate surveying and mapping data processing method based on intelligent data as claimed in claim 1, the real estate surveying and mapping data processing system based on intelligent data comprises: A feature fusion module is used to obtain multi-source real estate surveying and mapping data; perform spatiotemporal synchronization on the multi-source real estate surveying and mapping data to generate multi-source real estate surveying and mapping spatial alignment data; perform real estate spatial feature extraction on the multi-source real estate surveying and mapping spatial alignment data to obtain real estate spatial feature data; perform cross-domain feature fusion on the multi-source real estate surveying and mapping data based on the real estate spatial feature data to generate real estate surveying and mapping fusion spatial feature data; The distortion correction module is used to confirm the public surveying and mapping points of multi-source real estate surveying and mapping data by integrating the spatial feature data of real estate surveying and mapping, and obtain the public surveying and mapping point data of real estate surveying and mapping; use the public surveying and mapping point data of real estate surveying and mapping to perform local surveying and mapping distortion correction, and generate structural surveying and mapping correction data; reconstruct the real estate surveying and mapping high-dimensional space of the structural surveying and mapping correction data, and generate three-dimensional real estate model data; perform real estate use pattern recognition on the three-dimensional real estate model data, and generate real estate use pattern data; The association graph construction module is used to associate multi-layer semantic labels with three-dimensional real estate model data according to real estate use pattern data to generate multi-layer semantic label data; to perform rule mining on real estate semantic label data to generate real estate association rule mining data; to construct graph nodes and edges on multi-layer semantic label data based on real estate association rule mining data to generate real estate surveying and mapping semantic association graph; The storage sharing module is used to store the semantic label data of the real estate surveying and mapping semantic association map on the chain, generate the real estate surveying and mapping semantic chain storage data; perform data collaborative sharing on the real estate surveying and mapping semantic chain storage data, generate real-time shared surveying and mapping data, and execute the real estate surveying and mapping data processing sharing operation.

Images