A spatial data gridding statistics device and method

Abstract

The application relates to the technical field of data gridding statistics, in particular to a spatial data gridding statistics device and method, the device comprises a data acquisition module, a model establishment module, a data analysis module, a multi-source verification module and a data output and management module, the method comprises the following steps: step one, data acquisition and model establishment; step two, data analysis and multi-source verification; step three, data output and management. The DBSCAN algorithm is adopted to perform data analysis operation on actual reference data, dense areas and sparse areas in the data can be automatically identified, the grid size or shape does not need to be previously set, the clusters of any shape can be processed, and therefore the efficiency and accuracy of the spatial data gridding analysis result are improved.

Description

A spatial data gridding statistical device and method Technical Field

[0001] This invention relates to the field of data gridding and statistical technology, specifically to a spatial data gridding and statistical device and method. Background Technology

[0002] Spatial data gridding statistics is a method that divides continuous spatial data into several regular or irregular grid cells according to specific rules, and then performs statistical analysis on the spatial data within each grid cell. In spatial data research, raw data is often widely distributed and diverse in form. Through gridding, complex spatial information can be transformed into a discrete set of grid cells, each assigned specific attribute values ​​(such as the number of buildings, total area, population density, and other statistical indicators within the grid). This not only simplifies the complexity of spatial data and facilitates its storage, management, and computation, but also more intuitively displays the distribution characteristics and trends of spatial data.

[0003] Existing technologies, such as spatial data gridding statistical methods based on mathematical interpolation, use regular grids to cover the area to be statistically analyzed. The value of each grid is calculated by dividing the statistical value of the area where the grid center is located by the number of grids in that area. Then, the average value of each grid is used to replace the original value of that grid. Under the premise that the total value of the statistical area remains unchanged, the smoothed grid value is used as the weight to adjust the grid value to form a cycle. Through multiple smoothing and adjustment, a continuous surface of statistical values ​​can be obtained.

[0004] While the above methods can achieve gridded statistics of spatial data to a certain extent, because they are based on regular grids for interpolation, the interpolation results may not accurately reflect the real situation when faced with complex distribution data. This may lead to bias in the statistical results and reduce the accuracy of the gridded analysis results of spatial data.

[0005] In summary, the spatial data gridding statistical method based on mathematical interpolation may lead to biased statistical results when dealing with complex data distributions, which reduces the accuracy of spatial data gridding analysis results. This problem has become an urgent issue to be solved in this field. Therefore, it is necessary to propose a spatial data gridding statistical device and method. Summary of the Invention

[0006] To address the aforementioned issues, this invention provides a spatial data gridding statistical device and method. By employing the DBSCAN algorithm to perform data analysis on actual reference data, it can automatically identify dense and sparse regions in the data without pre-setting the grid size or shape, enabling it to handle clusters of arbitrary shapes, thereby improving the efficiency and accuracy of spatial data gridding analysis results.

[0007] To achieve the above objectives, the technical solution of the present invention is as follows: A spatial data gridding and statistical device, comprising the following modules:

[0008] The data acquisition module integrates satellite remote sensing imagery technology, real-time point cloud technology from mobile surveying vehicles, IoT sensor networks, and a historical archive digitization platform to construct an integrated air-space-ground acquisition system, collecting remote sensing image information, real-time geographic information, field measurement information, and historical archive information for the area to be surveyed.

[0009] The model building module is used to establish a probabilistic model of building distribution based on historical archive information and real-time geographic information collected by the data acquisition module, and to establish a real-time information database based on remote sensing image information, real-time geographic information and field measurement information. The incremental model of building change is established through the real-time information database. The probabilistic model of building distribution and the incremental model of building change are dynamically weighted and integrated to obtain a comprehensive analysis model.

[0010] The data analysis module is used to perform data analysis on actual reference data through a comprehensive analysis model and the DBSCAN algorithm, obtain analysis results, and calculate the matching rate between the obtained analysis results and the actual reference data. The actual reference data consists of remote sensing image information, real-time geographic information, and field measurement information in the real-time information database.

[0011] The multi-source validation module is used to adjust the output of the analysis results based on the matching rate between the analysis results and the actual reference data, using a multi-level decision-making mechanism.

[0012] The data output and management module is used to classify and encode the output analysis results, create charts based on the analysis results, and archive and back up all data during the collection and analysis process.

[0013] Furthermore, the data acquisition module includes the following units:

[0014] The remote sensing image acquisition unit is used to interface with the satellite API and automatically retrieve the latest remote sensing image information.

[0015] The geographic information acquisition unit is used to acquire road network and terrain data of the area to be statistically analyzed in real time through GeoServer and integrate them into real-time geographic information.

[0016] The measurement information acquisition unit is used to conduct on-site measurements of buildings in the area to be surveyed using real-time point cloud technology from a mobile measurement vehicle and an IoT sensor network, thereby obtaining on-site measurement information.

[0017] The historical archives collection unit is used to query historical archives information of the area to be statistically analyzed through a large-scale internet model.

[0018] Furthermore, the model building module includes the following units:

[0019] The probabilistic model building unit is used to extract key factors from historical archive information and real-time geographic information, and to build a probabilistic model of building distribution based on the extracted key factors. The specific algorithm formula is as follows:

[0020] (1).

[0021] Where y=1 represents the probability of the existence of a building, and x is the feature vector. These are the weight parameters obtained through training with historical data.

[0022] The incremental model building unit is used to monitor and predict changes in buildings in real time based on remote sensing image information, identify new buildings based on real-time geographic information, analyze the usage status of buildings based on on-site measurement information, build a real-time information database, and then build an incremental model of building changes based on the real-time information database.

[0023] The model integration unit is used to dynamically weight and integrate the probability model of building distribution and the incremental model of building change using Kalman filtering technology to obtain a comprehensive analysis model.

[0024] Furthermore, the specific process of the DBSCAN algorithm is as follows:

[0025] Given an object p, its... - The neighborhood is defined using the following formula:

[0026] (2).

[0027] Where D is the dataset, Let be the distance from point p to point q.

[0028] When point p - When the neighborhood contains MinPts points, p is the core point, specifically represented as follows:

[0029] (3).

[0030] At this time, when point q is at point p - In the neighborhood, and when p is the core point, q is directly density-reachable from p; when there exists a point sequence p1, p2, ..., p n And where p1=p, p n =q, and p i+1 From p iIf a point is directly reachable by density, then q is reachable by density from p; if there exists a point o, and both points p and q are reachable by density from point o, then p and q are density-connected.

[0031] Furthermore, the formula for calculating the matching rate is as follows:

[0032] (4).

[0033] Where g is the matching rate, f is the analysis result, and c is the reference data.

[0034] Furthermore, the operation flow of the multi-source verification module is as follows:

[0035] When the matching rate is greater than 90%, the multi-source verification module will directly output the analysis results.

[0036] When the matching rate is between 70% and 90%, the multi-source verification module adjusts the analysis results and displays the adjusted results to the staff. After the staff confirms the results, the analysis results are output.

[0037] When the matching rate is less than 70%, the multi-source verification module sends an alarm to the staff, who then manually intervene to correct the analysis results. After the correction is completed, the corrected analysis results are output.

[0038] Furthermore, the historical archive acquisition unit is also used to identify paper documents using OCR technology, and then extract data from the paper documents using NLP technology to obtain the historical archives in the paper documents.

[0039] Furthermore, the multi-source validation module includes a self-learning unit. When the matching rate is between 70% and 90%, the multi-source validation module adjusts the analysis results through the self-learning unit, records the adjustment parameters, and feeds them back to the model building module, so that the model building module updates the parameters of the comprehensive analysis model according to the adjustment parameters.

[0040] Furthermore, the data output and management module includes a blockchain evidence storage unit, which is used to generate hash values ​​for the analysis results, all collected data and processing logs and upload them to the blockchain for evidence storage.

[0041] Furthermore, a spatial data gridding statistical method includes the following steps:

[0042] Step 1, Data Acquisition and Model Building: Collect remote sensing image information, real-time geographic information, field measurement information, and historical archive information of the area to be statistically analyzed. Based on the historical archive information and real-time geographic information, establish a probability model of building distribution. At the same time, based on the remote sensing image information, real-time geographic information, and field measurement information, establish a real-time information database. Then, based on the real-time information database, establish a building change increment model. Finally, integrate the probability distribution model and the building change increment model to obtain a comprehensive analysis model.

[0043] Step 2, Data Analysis and Multi-Source Validation: The actual reference data is analyzed using the DBSCAN algorithm and a comprehensive analysis model. After obtaining the analysis results, the matching rate between the actual reference data and the actual reference data is calculated. A multi-level decision-making mechanism is established with the matching rate as the reference data to adjust the output of the analysis results.

[0044] Step 3, Data Output and Management: After outputting the analysis results, archive and back up all the data from this analysis, classify and code the output analysis results, and create charts based on the output analysis results.

[0045] The technical principles of the above solution are as follows:

[0046] The data acquisition module first collects remote sensing image information, real-time geographic information, field measurement information, and historical archive information for the area to be statistically analyzed. Then, the model building module establishes a probabilistic model of building distribution based on the historical archive information and real-time geographic information, and establishes a real-time information database based on the remote sensing image information, real-time geographic information, and field measurement information. Based on the real-time information database, a building change increment model is established. Finally, the probabilistic model of building distribution and the building change increment model are dynamically weighted and integrated to obtain a comprehensive analysis model.

[0047] After the comprehensive analysis model is derived, the DBSCAN algorithm is used by the data analysis module to analyze the actual reference data, obtain the analysis results, and simultaneously calculate the matching rate with the actual reference data. After obtaining the matching rate, the multi-source verification module adjusts and outputs the analysis results according to the specific matching rate. Finally, the data output and management module archives and backs up all data, classifies and encodes the output analysis results, and creates charts based on the analysis results.

[0048] The above approach has the following beneficial effects:

[0049] 1. This invention, by employing the DBSCAN algorithm to perform data analysis on actual reference data, can automatically identify dense and sparse regions in the data without pre-setting the grid size or shape, enabling it to handle clusters of arbitrary shapes, thereby improving the efficiency and accuracy of spatial data gridding analysis results.

[0050] 2. This invention obtains a comprehensive analysis model by dynamically weighting and integrating the building distribution probability model and the building change increment model. This model fully considers the historical distribution and real-time changes of buildings, thus improving the accuracy and adaptability of the comprehensive analysis model.

[0051] 3. This invention provides staff with intuitive analytical results by classifying and encoding the output analysis results and creating charts based on these results. Simultaneously, the archiving and backup of all data during the collection and analysis processes ensures data security and traceability.

[0052] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0053] Figure 1 is a schematic diagram of the spatial data gridding statistical device of the present invention.

[0054] Figure 2 is a schematic diagram of the data acquisition module in the spatial data gridding statistical device of the present invention.

[0055] Figure 3 is a schematic diagram of the model building module in the spatial data gridding statistical device of the present invention.

[0056] Figure 4 is a schematic diagram of the method steps of the spatial data gridding statistical method of the present invention. Detailed Implementation

[0057] The following detailed description illustrates the specific implementation method:

[0058] Example 1:

[0059] As shown in Figure 1: A spatial data gridding statistical device includes a data acquisition module for data acquisition operations, a model building module for establishing a comprehensive analysis model, a data analysis module for analyzing actual reference data using the DBSCAN algorithm and the comprehensive analysis model, a multi-source verification module for adjusting the output of the analysis results using a multi-level decision-making mechanism, and a data output and management module for managing all data.

[0060] The functions of each module are explained in detail below:

[0061] As shown in Figure 2, the data acquisition module integrates satellite remote sensing imagery technology, real-time point cloud technology from mobile surveying vehicles, IoT sensor networks, and a historical archive digitization platform to construct an integrated air-space-ground acquisition system. This system collects remote sensing image information, real-time geographic information, on-site measurement information, and historical archive information for the area to be surveyed. It includes a remote sensing image acquisition unit, a geographic information acquisition unit, a measurement information acquisition unit, and a historical archive acquisition unit.

[0062] The remote sensing image acquisition unit is used to interface with the satellite API and automatically retrieve the latest remote sensing image information.

[0063] The geographic information acquisition unit is used to acquire road network and terrain data of the area to be statistically analyzed in real time through GeoServer and integrate them into real-time geographic information.

[0064] The measurement information acquisition unit is used to conduct on-site measurements of buildings in the area to be surveyed using real-time point cloud technology from a mobile measurement vehicle and an IoT sensor network, thereby obtaining on-site measurement information.

[0065] The historical archive collection unit is used to query historical archive information of the area to be statistically analyzed through the Internet big data model. It is also used to recognize paper documents through OCR technology and extract data from paper documents through NLP technology to obtain the historical archives in the paper documents.

[0066] Specifically, the data acquisition module first interfaces with the satellite API through the remote sensing image acquisition unit to retrieve the latest remote sensing image information. Then, it interfaces with the GeoServer through the geographic information acquisition unit to obtain road network and terrain data for the area to be surveyed. This data is then integrated to form real-time geographic information. After obtaining the real-time geographic information, the data acquisition module uses the measurement information acquisition unit, employing real-time point cloud technology from a mobile surveying vehicle and an IoT sensor network, to conduct on-site measurements of buildings in the area to be surveyed. The measurement results are then integrated into on-site measurement information. Simultaneously, the historical archive acquisition unit uses a large-scale internet model to query historical archive information for the area to be surveyed. When it is necessary to read information from historical archives in paper documents, it first uses OCR technology to recognize the paper documents and then uses NLP technology to extract the data from them.

[0067] As shown in Figure 3, the model building module is used to establish a probabilistic model of building distribution based on historical archive information and real-time geographic information collected by the data acquisition module, and to establish a real-time information database based on remote sensing image information, real-time geographic information and field measurement information. The incremental model of building change is established through the real-time information database. The probabilistic model of building distribution and the incremental model of building change are dynamically weighted and integrated to obtain a comprehensive analysis model, which includes a probabilistic model building unit, an incremental model building unit and a model integration unit.

[0068] The probabilistic model building unit is used to extract key factors from historical archive information and real-time geographic information, and to build a probabilistic model of building distribution based on the extracted key factors. The specific algorithm formula is as follows:

[0069] (1).

[0070] Where y=1 represents the probability of the existence of a building, and x is the feature vector. These are the weight parameters obtained through training with historical data.

[0071] The incremental model building unit is used to monitor and predict changes in buildings in real time based on remote sensing image information, identify new buildings based on real-time geographic information, analyze the usage status of buildings based on on-site measurement information, build a real-time information database, and then build an incremental model of building changes based on the real-time information database.

[0072] The model integration unit is used to dynamically weight and integrate the probability model of building distribution and the incremental model of building change using Kalman filtering technology to obtain a comprehensive analysis model.

[0073] Specifically, the model building module first extracts key factors from historical archives and real-time geographic information through the probabilistic model building unit. Based on the extracted key factors, a probabilistic model of building distribution is built. After the probabilistic model is built, the model building module uses the incremental model building unit to monitor and predict changes in buildings in real time based on remote sensing image information, identifies new buildings based on real-time geographic information, analyzes the usage status of buildings based on on-site measurement information, and builds a real-time information database. Finally, an incremental model of building changes is built based on the real-time information database.

[0074] After establishing the probability model and the incremental building change model, the model building module uses the model integration unit to dynamically and weightedly integrate the probability model of building distribution and the incremental building change model using Kalman filtering technology to obtain a comprehensive analysis model.

[0075] The data analysis module is used to perform data analysis on actual reference data through a comprehensive analysis model and the DBSCAN algorithm, obtain analysis results, and calculate the matching rate between the obtained analysis results and the actual reference data. The actual reference data consists of remote sensing image information, real-time geographic information, and field measurement information in the real-time information database.

[0076] The specific process of the DBSCAN algorithm is as follows:

[0077] Given an object p, its... - The neighborhood is defined using the following formula:

[0078] (2).

[0079] Where D is the dataset, Let be the distance from point p to point q.

[0080] When point p - When the neighborhood contains MinPts points, p is the core point, specifically represented as follows:

[0081] (3).

[0082] At this time, when point q is at point p - In the neighborhood, and when p is the core point, q is directly density-reachable from p; when there exists a point sequence p1, p2, ..., p n And where p1=p, p n =q, and p i+1 From p i If a point is directly reachable by density, then q is reachable by density from p; if there exists a point o, and both points p and q are reachable by density from point o, then p and q are density-connected.

[0083] Specifically, after the comprehensive analysis model is established, the data analysis module performs data analysis on the actual reference data through the comprehensive analysis model and the DBSCAN algorithm, obtains the analysis results, and simultaneously calculates the matching rate between the analysis results and the actual reference data, thus obtaining the specific value of the matching rate.

[0084] The multi-source validation module is used to adjust the output of the analysis results based on the matching rate between the analysis results and the actual reference data, using a multi-level decision-making mechanism.

[0085] The matching rate is calculated using the following formula:

[0086] (4).

[0087] Where g is the matching rate, f is the analysis result, and c is the reference data.

[0088] The operation flow of the multi-source verification module is as follows:

[0089] When the matching rate is greater than 90%, the multi-source verification module will directly output the analysis results.

[0090] When the matching rate is between 70% and 90%, the multi-source verification module adjusts the analysis results and displays the adjusted results to the staff. After the staff confirms the results, the analysis results are output.

[0091] When the matching rate is less than 70%, the multi-source verification module sends an alarm to the staff, who then manually intervene to correct the analysis results. After the correction is completed, the corrected analysis results are output.

[0092] The multi-source validation module includes a self-learning unit. When the matching rate is between 70% and 90%, the multi-source validation module adjusts the analysis results through the self-learning unit, records the adjustment parameters, and feeds them back to the model building module, so that the model building module updates the parameters of the comprehensive analysis model according to the adjustment parameters.

[0093] Specifically, after obtaining the specific numerical value of the matching rate, the staff classifies it into different levels according to the specific situation of the matching rate. Different levels correspond to different methods of processing the analysis results, and they communicate with the staff to form a multi-level decision-making mechanism.

[0094] When the matching rate is above 90%, the multi-source validation module directly outputs the analysis results. When the matching rate is between 70% and 90%, the multi-source validation module adjusts the parameters of the analysis results through its self-learning unit, and then displays the results to the staff for confirmation before outputting them. When the matching rate is below 70%, the multi-source validation module sends an alarm to the staff, who then intervene to correct the results. After correction, the corrected results are output. During this process, when the matching rate is between 70% and 90%, the multi-source validation module, after adjusting the analysis results through its self-learning unit, simultaneously records the adjusted parameters and feeds them back to the model building module, allowing the model building module to update the parameters of the comprehensive analysis model based on the adjusted parameters.

[0095] The data output and management module is used to classify and encode the output analysis results, create charts based on the analysis results, and archive and back up all data during the collection and analysis process.

[0096] The data output and management module includes a blockchain evidence storage unit, which is used to generate hash values ​​for analysis results, all collected data and processing logs and upload them to the blockchain for evidence storage.

[0097] Specifically, after the analysis results are output, the data output and management module will classify and encode the output analysis results, and create charts based on the analysis results to provide staff with an intuitive visual display. It will also archive and back up all data generated during the collection and analysis process for subsequent staff to query and use. Specifically, the data output and management module generates hash values ​​for the analysis results, all collected data and processing logs through the blockchain notarization unit and uploads them to the blockchain for notarization.

[0098] Example 2:

[0099] As shown in Figure 4, the difference from Embodiment 1 is that a spatial data gridding statistical method includes the following steps:

[0100] Step 1, Data Acquisition and Model Building: First, remote sensing image information, real-time geographic information, field measurement information, and historical archive information of the area to be statistically analyzed are collected. Based on the historical archive information and real-time geographic information, a probability model of building distribution is established. At the same time, a real-time information database is established based on the remote sensing image information, real-time geographic information, and field measurement information. Then, a building change increment model is established based on the real-time information database. Finally, the probability distribution model and the building change increment model are integrated to obtain a comprehensive analysis model.

[0101] Step 2, Data Analysis and Multi-Source Validation: After obtaining the comprehensive analysis model, the actual reference data is analyzed using the DBSCAN algorithm and the comprehensive analysis model to obtain the analysis results. After obtaining the analysis results, the matching rate between the results and the actual reference data is calculated. Using the matching rate as reference data, a multi-level decision-making mechanism is established, and the output of the analysis results is adjusted accordingly based on the multi-level decision-making mechanism.

[0102] Step 3, Data Output and Management: After outputting the analysis results, archive and back up all the data from this analysis. At the same time, classify and code the output analysis results, and create charts based on the output analysis results to provide staff with a more intuitive visual display.

[0103] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A spatial data gridding statistical device, characterized in that, It includes the following modules: a data acquisition module, which integrates satellite remote sensing imagery technology, mobile measurement vehicle real-time point cloud technology, IoT sensor network and historical archive digitization platform to build an integrated air-space-ground acquisition system to collect remote sensing image information, real-time geographic information, field measurement information and historical archive information of the area to be surveyed; The model building module is used to establish a probabilistic model of building distribution based on historical archive information and real-time geographic information collected by the data acquisition module. It also establishes a real-time information database based on remote sensing image information, real-time geographic information, and field measurement information. Through this database, it builds an incremental model of building changes. The probabilistic model of building distribution and the incremental model of building changes are dynamically weighted and integrated to obtain a comprehensive analysis model. The data analysis module, after establishing the comprehensive analysis model, performs data analysis on the actual reference data using the comprehensive analysis model and the DBSCAN algorithm to obtain the analysis results. The multi-source verification module is used to adjust the output of the analysis results based on the matching rate between the analysis results and the actual reference data, employing a multi-level decision-making mechanism. The data output and management module is used to classify and encode the output analysis results, create charts based on the analysis results, and archive and back up all data during the collection and analysis process.

2. The spatial data gridding and statistical device according to claim 1, characterized in that, The data acquisition module includes the following units: a remote sensing image acquisition unit, which interfaces with the satellite API to automatically retrieve the latest remote sensing image information; and a geographic information acquisition unit, which uses GeoServer to acquire road network and terrain data of the area to be analyzed in real time and integrates them into real-time geographic information. The measurement information acquisition unit is used to conduct on-site measurements of buildings in the area to be surveyed using real-time point cloud technology from a mobile measurement vehicle and an IoT sensor network, and to obtain on-site measurement information; the historical archive acquisition unit is used to query historical archive information of the area to be surveyed through a large Internet model.

3. The spatial data gridding and statistical device according to claim 2, characterized in that, The model building module includes the following unit: a probabilistic model building unit, used to extract key factors from historical archive information and real-time geographic information, and to build a probabilistic model of building distribution based on the extracted key factors. The specific algorithm formula is as follows: (1); where y=1 is the probability of the existence of a building, and x is the eigenvector. The weight parameters are obtained through training with historical data; the incremental model building unit is used to monitor and predict changes in buildings in real time based on remote sensing image information, identify new buildings based on real-time geographic information, and analyze the usage status of buildings based on on-site measurement information to establish a real-time information database, and then establish an incremental model of building changes based on the real-time information database; the model integration unit is used to dynamically weight and integrate the probability model of building distribution and the incremental model of building changes using Kalman filtering technology to obtain a comprehensive analysis model.

4. The spatial data gridding and statistical device according to claim 3, characterized in that, The specific process of the DBSCAN algorithm is as follows: Given an object p, perform a search on it... - The neighborhood is defined using the following formula: (2); where D is the dataset, Let be the distance from point p to point q; when point p's - When the neighborhood contains MinPts points, p is the core point, specifically represented as follows: (3); At this time, when point q is at point p - In the neighborhood, and when p is the core point, q is directly density-reachable from p; when there exists a point sequence p1, p2, ..., p n And where p1=p, p n =q, and p i+1 From p i If a point is directly reachable by density, then q is reachable by density from p; if there exists a point o, and both points p and q are reachable by density from point o, then p and q are density-connected.

5. The spatial data gridding and statistical device according to claim 4, characterized in that, The operation process of the multi-source verification module is as follows: When the matching rate is greater than 90%, the multi-source verification module directly outputs the analysis results; when the matching rate is between 70% and 90%, the multi-source verification module adjusts the analysis results and displays the adjusted analysis results to the staff. After the staff confirms, the analysis results are output; when the matching rate is less than 70%, the multi-source verification module sends an alarm to the staff, who then manually intervene to correct the analysis results. After the correction is completed, the corrected analysis results are output.

6. The spatial data gridding and statistical device according to claim 5, characterized in that, The formula for calculating the matching rate is as follows: (4); where g is the matching rate, f is the analysis result, and c is the reference data.

7. The spatial data gridding and statistical device according to claim 6, characterized in that, The historical archive acquisition unit is also used to identify paper documents using OCR technology, and then extract data from the paper documents using NLP technology to obtain historical archives from the paper documents.

8. The spatial data gridding and statistical device according to claim 7, characterized in that, The multi-source validation module includes a self-learning unit. When the matching rate is between 70% and 90%, the multi-source validation module adjusts the analysis results through the self-learning unit, records the adjustment parameters, and feeds them back to the model building module, so that the model building module updates the parameters of the comprehensive analysis model according to the adjustment parameters.

9. The spatial data gridding and statistical device according to claim 8, characterized in that, The data output and management module includes a blockchain evidence storage unit, which is used to generate hash values ​​for analysis results, all collected data and processing logs and upload them to the blockchain for evidence storage.

10. A spatial data gridding statistical method, based on the spatial data gridding statistical device according to any one of claims 1-9, characterized in that, Includes the following steps: Step 1, Data Acquisition and Model Building: Collect remote sensing image information, real-time geographic information, field measurement information, and historical archive information of the area to be statistically analyzed. Based on the historical archive information and real-time geographic information, establish a probabilistic model of building distribution. Simultaneously, based on the remote sensing image information, real-time geographic information, and field measurement information, establish a real-time information database. Then, establish a building change increment model based on the real-time information database. Finally, integrate the probabilistic distribution model and the building change increment model to obtain a comprehensive analysis model. Step 2, Data Analysis and Multi-Source Validation: Analyze the actual reference data using the DBSCAN algorithm and the comprehensive analysis model. After obtaining the analysis results, calculate the matching rate between the results and the actual reference data. Use the matching rate as reference data to establish a multi-level decision-making mechanism to adjust the output of the analysis results. Step 3, Data Output and Management: After outputting the analysis results, archive and back up all the data from this analysis, classify and code the output analysis results, and create charts based on the output analysis results.

Images