Geographical mapping data processing and analysis method and system based on big data

Abstract

The present invention relates to the technical field of data processing, and particularly to a method and system for processing and analyzing geodetic surveying data based on big data. The method includes: obtaining the outlier factor of all spatial points in the collected geodetic surveying data through the LOF algorithm; determining the outlier index of each spatial point; constructing the proximity range of each spatial point; determining the density distance between spatial points; dividing all spatial points into regions to obtain each region of the geodetic surveying data; determining the fitting threshold for distinguishing inliers from outliers in the RANSAC algorithm for each region; and using the RANSAC algorithm to fit the target region to identify abnormal data points, thereby completing the processing and analysis of the geodetic surveying data. The present invention determines the fitting threshold by comprehensively considering the range radius value, the mean outlier index of spatial points in the target region, and the standard deviation of the data point intensity, and can more reasonably set the fitting threshold for different regions, effectively avoiding the problem of unstable fitting caused by a unified threshold.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for processing and analyzing geodetic surveying data based on big data. Background Art

[0002] Geodetic surveying data covers various attribute information of the target area and has numerous applications in fields such as urban planning and land management. In geodetic surveying data, spatial point data is an important data type for expressing the three-dimensional spatial characteristics of the target area, and can accurately present topographic features, building structures, and other geographical elements.

[0003] However, during the acquisition process, affected by factors such as environmental interference and sensor errors, spatial point data may have anomalies such as noise, outliers, or uneven sampling, which in turn affect the reliability of the data and the accuracy of subsequent applications. Therefore, it is necessary to process the abnormal data points in the spatial point data to reduce the interference of abnormal data points, improve the quality of geodetic surveying data, and ensure the effective application of geodetic surveying data in fields such as urban planning and land management.

[0004] The Random Sample Consensus (RANSAC) algorithm can effectively extract the inliers of the main geometric structures (such as building planes or road straight lines) in the geodetic surveying scene through random sampling and model fitting. The spatial points outside the inliers are abnormal data points, and thus anomalies such as noise, outliers, or uneven sampling in the spatial point data can be identified, thereby improving the reliability of geodetic surveying data analysis. However The algorithm uses the same fitting threshold to divide inliers and outliers for the global data, which is prone to problems such as unstable fitting and high randomness in scenarios with complex surveying scenes and uneven data density, resulting in a decrease in the accuracy of identifying abnormal data points, and further affecting the application effect of geodetic surveying data in fields such as urban planning and land management. Summary of the Invention

[0005] To solve the problem that the algorithm uses the same fitting threshold to divide inliers and outliers for the global data, which is prone to disadvantages such as unstable fitting and high randomness in scenarios with complex surveying scenes and uneven data density, resulting in a decrease in the accuracy of identifying abnormal data points, and further affecting the application effect of geodetic surveying data in fields such as urban planning and land management, the present invention provides a method and system for processing and analyzing geodetic surveying data based on big data.

[0006] In the first aspect, the present invention provides a method for processing and analyzing geodetic surveying data based on big data, adopting the following technical solutions:

[0007] A method for processing and analyzing geodetic surveying data based on big data, including: by An algorithm to obtain the outlier factor of all spatial points in the collected geodetic surveying data; Denote any spatial point as the target spatial point, and determine the outlier index of the target spatial point according to the outlier factor of the target spatial point, the mean of the distances between the target spatial point and all spatial points within the neighborhood of the target spatial point, and the standard deviation of the coordinates of all spatial points within the neighborhood; Take the mean of the radii of the neighborhoods of all spatial points as the range radius value, and construct the proximity range of the target spatial point according to the range radius value; Determine the density distance between the target spatial point and any other spatial point according to the distance between the target spatial point and any other spatial point, the outlier index, and the number of spatial points within the proximity range; Divide all spatial points into several regions according to the magnitude of the density distance; Determine the fitting threshold for distinguishing inliers and outliers in the algorithm according to the range radius value, the mean of the outlier indices of all spatial points within the target region among several regions, and the standard deviation of the data point intensity of all spatial points within the target region; According to the fitting threshold, use the algorithm to fit the target region to obtain the inliers and outliers of the target region, so as to identify abnormal data points and complete the processing and analysis of geodetic surveying data.

[0008] Through the algorithm of the present invention, the outlier factor of each spatial point is calculated, so that outliers or abnormal data points can be more accurately identified according to the local density change of the spatial points. Compared with the traditional algorithm based on global criteria, the present invention can process according to the local situation of each point and separate inliers and outliers more precisely; By calculating the outlier index of the target spatial point, the density distance of the points within the neighborhood, and other related parameters, the fitting threshold applicable to this region is dynamically determined, which can effectively avoid the errors that may be brought by using a global fixed threshold in the case of uneven data density or complex scenarios, and improve the stability and accuracy of fitting; In complex surveying scenarios, the data distribution and density may be very uneven, and it is difficult for the traditional algorithm to adapt to this change. However, the present invention comprehensively considers factors such as the outlier factor of spatial points, the distance within the neighborhood, and the standard deviation, so as to better process the data in complex scenarios and improve the stability of data analysis.

[0009] Further, the neighborhood is the -distance neighborhood of the target spatial point in the algorithm.

[0010] Further, the outlier index satisfies: ; In the formula, is the outlier index of the spatial point in the geodetic surveying data, is the outlier factor of the spatial point , is the mean distance between all spatial points within the -distance neighborhood of the spatial point and the spatial point . , and are the standard deviations of the , , and coordinates of all spatial points within the -distance neighborhood of the spatial point , respectively.

[0011] By comprehensively considering the outlier factor, the mean neighborhood distance, and the standard deviation of coordinates, the present invention can more accurately identify abnormal data points in spatial points; introducing the standard deviation of coordinates within the spatial point neighborhood improves the calculation accuracy of the outlier index and adapts to the complex situation of uneven spatial data distribution.

[0012] Further, constructing the proximity range of the target spatial point according to the range radius value includes: taking the target spatial point as the center and the spherical range with the range radius value as the radius as the proximity range of the target spatial point.

[0013] Further, the density distance satisfies: ; where is the density distance between the spatial point and the spatial point in the geodetic surveying data, is the distance between the spatial point and the spatial point , and are the numbers of spatial points within the proximity ranges of the spatial points and the spatial point , respectively, and are the outlier indices of the spatial points and the spatial point , respectively, is a hyperparameter, is the absolute value symbol.

[0014] By comprehensively considering the number of neighboring points and the outlier index, the density distance can more accurately reflect the local spatial characteristics, enabling the algorithm to maintain good performance in different regions; the density distance calculation method combined with the outlier index can more finely distinguish normal points and abnormal points, improving the accuracy of abnormal data detection; when performing regional division subsequently, using the density distance can improve the accuracy and stability of the division.

[0015] Further, it is characterized in that the distance is the Euclidean distance.

[0016] Further, according to the magnitude of the density distance, all spatial points are divided into regions, obtaining several regions, including: dividing the spatial points with a density distance less than a preset region threshold and the target pixel points into the same region until all spatial points are divided, obtaining multiple regions; in response to the density distance between two spatial points not belonging to the same region being less than the preset region threshold, merging the regions to which the two spatial points belong until all regions are no longer merged, obtaining several regions.

[0017] The partitioning method based on density distance of the present invention can ensure that adjacent and similar spatial points are classified into the same region, improving the rationality and accuracy of region partitioning; through the preset region threshold and merging rules, region partitioning can be efficiently performed, reducing unnecessary calculation steps and improving the speed of data processing.

[0018] Further, the fitting threshold satisfies: ; in the formula, is the fitting threshold of the th region, is the range radius value, is the th mean of the outlier indices of all spatial points in the region, is the th standard deviation of the data point intensities of all spatial points in the region, is the linear normalization function.

[0019] The fitting threshold of the present invention is calculated based on the local characteristics of each region, for example, the mean of the outlier indices and the standard deviation of the data point intensities, enabling the algorithm to automatically adjust the threshold according to the characteristics of different regions, improving the local self - adaptability of the algorithm; by considering the degree of dispersion and intensity change of the data within the region, the fitting threshold can more accurately reflect the true distribution of the data, thereby improving the fitting accuracy of the algorithm within the region; the introduction of the outlier index enables the fitting threshold to better identify and process outliers, improving the accuracy and reliability of abnormal data point detection.

[0020] Further, the use of The algorithm fits the target area to obtain the inliers and outliers of the target area for identifying abnormal data points, including: randomly selecting three spatial points within the target area to form a plane according to a preset number of times, calculating the perpendicular distance from each spatial point within the target area except the spatial points forming the plane to the plane each time, if the perpendicular distance is less than the fitting threshold, then taking this spatial point as an inlier of the target area, otherwise, taking this spatial point as an outlier of the target area, and obtaining the number of times each spatial point is an outlier of the target area; in response to the number of outliers being greater than a preset abnormal threshold, determining the spatial point as an abnormal data point in the geodetic surveying data.

[0021] In a second aspect, the present invention provides a geodetic surveying data processing and analysis system based on big data, adopting the following technical solution:

[0022] The geodetic surveying data processing and analysis system based on big data includes: a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned geodetic surveying data processing and analysis method based on big data is implemented.

[0023] By adopting the above technical solution, the above-mentioned geodetic surveying data processing and analysis method based on big data is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0024] The present invention has the following technical effects:

[0025] By comprehensively considering the range radius value, the mean outlier index of spatial points within the target area, and the standard deviation of data point intensity to determine the fitting threshold, it changes the traditional algorithm's way of using the same fitting threshold for global data, so that in the case of complex surveying scenes and uneven data density, a more reasonable fitting threshold can be set for different areas, effectively avoiding the fitting instability problem caused by a unified threshold, and improving the stability and reliability of fitting; in the process of determining the outlier index, density distance, and fitting threshold of the target spatial point, multiple factors are comprehensively considered, such as the outlier factor of the spatial point, the distance from neighboring points, the standard deviation of the coordinates of inlier points within the neighborhood, the number of spatial points within the neighboring range, etc., making the analysis of spatial points more comprehensive and accurate, reducing the randomness brought by simply relying on a single standard, and thus making the results of data processing and analysis more reliable; through the comprehensive analysis of spatial points, reasonable regional division, and the specifically determined fitting threshold, the inliers and outliers within the target area can be distinguished more accurately, and then the abnormal data points can be identified more precisely. Compared with the traditional The algorithm effectively improves the accuracy of identifying abnormal data points; since it can more accurately identify abnormal data points, the processing and analysis of geodetic surveying data are more reliable, providing a better data foundation for the application of geodetic surveying data in fields such as urban planning and land management, thus effectively enhancing the application effect of geodetic surveying data in these fields and enabling geodetic surveying data to better serve relevant decision-making and planning. Brief Description of the Drawings

[0026] Figure 1 It is a flowchart of the method in the method for processing and analyzing geodetic surveying data based on big data according to an embodiment of the present invention. Detailed Embodiments

[0027] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] An embodiment of the present invention discloses a method for processing and analyzing geodetic surveying data based on big data. Referring to Figure 1 , it includes steps S1 - step S7:

[0029] S1: Obtain the outlier factor of all spatial points in the collected geodetic surveying data through the algorithm.

[0030] Implementers can set the number of neighbors in the algorithm according to specific implementation situations , for example, 20.

[0031] S2: Determine the outlier index of each spatial point.

[0032] It should be noted that geodetic surveying data has the characteristics of complex and unfixed scenarios, and the geodetic surveying data collected in different surveying scenarios has different distribution states. In order to better eliminate the influence of factors such as noise, outliers, and uneven sampling in geodetic surveying data on geodetic surveying data analysis, the outlier index is calculated through the coordinates of each spatial point in the geodetic surveying data.

[0033] Denote any spatial point as the target spatial point, and determine the outlier index of the target spatial point according to the outlier factor of the target spatial point, the mean value of the distances between the target spatial point and all spatial points in the neighborhood of the target spatial point, and the standard deviation of the coordinates of all spatial points in the neighborhood, where the distance is the Euclidean distance.

[0034] Specifically, the neighborhood is the one of the target spatial point in the algorithm - distance neighborhood.

[0035] Specifically, the outlier index satisfies:

[0036] ;

[0037] In the formula, is the spatial point in the geodetic surveying data 's outlier index, is the outlier factor of the spatial point , is the spatial point 's - the mean of the Euclidean distances between all spatial points in the distance neighborhood and the spatial point , , and are respectively the standard deviations of the 's - coordinates of all spatial points in the distance neighborhood , and .

[0038] Among them, The larger it is, the more likely the spatial point is in the sparse area of the geodetic surveying data. Then the outlier index of the spatial point is larger. The smaller it is, the more likely the spatial point is in the dense area of the geodetic surveying data. Then the outlier index of the spatial point is smaller; at the same time, the average distance between the spatial point and the data points in its k - th neighborhood is larger, indicating that the distance between the spatial point and other geodetic surveying data points is larger. Then the spatial point is more outlier, and the outlier index of the spatial point is larger; the average Euclidean distance - between the spatial point and the spatial points in its - distance neighborhood is smaller, indicating that the distance between the spatial point and the spatial points in other geodetic surveying data is smaller. Then the spatial points around the spatial point are more dense, and the outlier index of the spatial point is smaller; When it is larger, it indicates that the spatial points around the spatial point are more discrete. Then the spatial point The more likely it is an outlier data point, the spatial point has a larger outlier index. When it is smaller, it indicates that the spatial points around are more densely distributed, indicating that the spatial point is more likely to be in the dense area of the geodetic survey data. The outlier index of the spatial point is smaller.

[0039] S3: Construct the neighborhood range of each spatial point.

[0040] Take the mean of the radii of the neighborhoods of all spatial points as the range radius value. According to the range radius value, construct the neighborhood range of the target spatial point.

[0041] Specifically, the constructing the neighborhood range of the target spatial point according to the range radius value includes:

[0042] Taking the spherical range centered on the target spatial point with the range radius value as the radius as the neighborhood range of the target spatial point.

[0043] S4: Determine the density distance between spatial points.

[0044] It should be noted that geodetic survey data may have different densities, noise levels and outlier ratios in different scenarios. Geodetic survey data in the same scenario may also have different densities in different regions of the scenario due to different objects in the scenario. In order to improve the robustness of the algorithm so that it can be better applied in different geodetic survey scenarios, the present invention calculates the density distance through the distance, outlier index between spatial points in the geodetic survey data, and the number of spatial points within the neighborhood range, so as to perform regional division on the geodetic survey data subsequently.

[0045] According to the distance, outlier index between the target spatial point and any other spatial point, and the number of spatial points within the neighborhood range, determine the density distance between the target spatial point and any other spatial point.

[0046] Specifically, the density distance satisfies:

[0047] ;

[0048] In the formula, is the density distance between the spatial point and the spatial point in the geodetic survey data, is the Euclidean distance between the spatial point and the spatial point , and are respectively the spatial point and the spatial point The number of spatial points within the proximity range of and are respectively the outlier indices of spatial point and spatial point ; is a hyperparameter, and

[0049] The implementer can set the hyperparameter according to the specific implementation situation, for example, 0.5.

[0050] Among them, the smaller is, the more likely it is that the two spatial points are on the same object or the same plane in the geospatial mapping scenario, and the more they should be divided into the same region, then the density distance between the two points is smaller; the larger is, the more likely it is that the two spatial points are not on the same object or the same plane in the geospatial mapping scenario, and the less they should be divided into the same region, then the density distance between the two points is larger; is the gap between the number of spatial points within the proximity range of spatial point and spatial point Since the surface morphology of the same object is similar, the number of spatial points within the proximity range of the spatial points on the same object is similar. Therefore, the larger is, the more likely it is that spatial point and spatial point are not on the same object or the same plane in the geospatial mapping scenario, and the less they should be divided into the same region, then the density distance between the two points is larger; the smaller is, the more likely it is that spatial point and spatial point are on the same object or the same plane in the geospatial mapping scenario, and the more they should be divided into the same region, then the density distance between the two points is smaller. To avoid the situation where due to the contingency of data, the number of data points within the proximity range of two spatial points on different objects is equal, resulting in a density distance of 0 between the data points on different objects and causing the two points to be divided into the same region, therefore is used to avoid this situation; is the difference between the outlier indices of spatial point and spatial point With spatial points The more likely they are on the same object or the same plane in the geodetic survey scenario, the more they should be divided into the same region, and the smaller the density distance between the two points. Similarly, using Avoid The impact on region division caused by the case where it is 0.

[0051] S5: Divide all spatial points into regions to obtain each region of the geodetic survey data.

[0052] Divide all spatial points into regions according to the magnitude of the density distance to obtain several regions.

[0053] Specifically, the dividing all spatial points into regions according to the magnitude of the density distance to obtain several regions includes:

[0054] Divide the spatial points with a density distance less than a preset region threshold and the target pixel points into the same region until all spatial points are divided, obtaining multiple regions;

[0055] In response to the density distance between two spatial points that do not belong to the same region being less than the preset region threshold, merge the regions to which the two spatial points belong until all regions are no longer merged, obtaining several regions.

[0056] Implementers can set the region threshold according to the specific implementation situation. For example, 10.

[0057] S6: Determine the fitting threshold for distinguishing inliers and outliers in each region in the algorithm.

[0058] It should be noted that since the algorithm uses the same fitting threshold to divide inliers and outliers for global data, and the geodetic survey data may have uneven data point distributions due to different scenarios. However, the algorithm is sensitive to the fitting threshold for inlier judgment and is prone to problems such as unstable fitting and high randomness when the data density is uneven or the abnormal situation is serious. Therefore, in this step, the fitting threshold for each region is calculated through the spatial points in each region of the geodetic survey data. In this step, the range radius value is used as the base value of the fitting threshold for each region, and implementers can set the base value according to the specific implementation situation.

[0059] According to the range radius value, the mean of the outlier indices of all spatial points in the target region among several regions, and the standard deviation of the data point intensities of all spatial points in the target region, determine the fitting threshold for the target region to distinguish inliers and outliers in the algorithm.

[0060] Specifically, the fitting threshold satisfies:

[0061] ;

[0062] In the formula, is the fitting threshold of the th region, is the range radius value, is the mean of the outlier indices of all spatial points in the th region, is the standard deviation of the data point intensities of all spatial points in the th region, is the linear normalization function.

[0063] Among them, The larger it is, the more outlier all spatial points in this region are. In order not to wrongly exclude valid data, the fitting threshold should be set more loosely, so that the fitting threshold is larger, The smaller it is, the more concentrated all spatial points in this region are. In order to effectively fit the surface of the object in the geodetic survey scenario, the fitting threshold should be set more strictly, so that the fitting threshold is smaller; The larger it is, the greater the volatility of the data point intensities of the spatial points in this region, and the worse the consistency of the data in this region. Then a larger fitting threshold should be used to avoid spatial points on the object in the geodetic survey scenario from being identified as outliers, The smaller it is, the smaller the volatility of the data point intensities of the spatial points in this region, and the stronger the consistency of the data in this region. Then the outliers in this region are easier to identify, and a smaller fitting threshold can be used to distinguish the abnormal data. Therefore The smaller it is, the smaller the fitting threshold that should be used.

[0064] S7: Use the algorithm to fit the target region to identify abnormal data points and complete the processing and analysis of geodetic survey data.

[0065] According to the fitting threshold, use the algorithm to fit the target region to obtain the inliers and outliers of the target region to identify abnormal data points. Furthermore, when applying geodetic survey data, the interference of abnormal data points can be avoided, and the influence of abnormal situations such as noise, outliers or uneven sampling in geodetic survey data on applications such as urban planning and land management can be weakened, and the processing and analysis of geodetic survey data based on big data can be completed.

[0066] Specifically, the use of the algorithm to fit the target region to obtain the inliers and outliers of the target region to identify abnormal data points includes:

[0067] According to a preset number of times, randomly select three spatial points within the target area to form a plane, and calculate the perpendicular distance from each spatial point within the target area except the spatial points forming the plane to the plane. If the perpendicular distance is less than the fitting threshold, then regard this spatial point as an inlier of the target area; otherwise, regard this spatial point as an outlier of the target area, and obtain the number of times each spatial point is an outlier of the target area.

[0068] In response to the number of outliers being greater than a preset anomaly threshold, determine that the spatial point is an abnormal data point in the geodetic surveying data.

[0069] Implementers can set the preset number of times and the anomaly threshold according to the specific implementation situation. For example, if there are spatial points in this area, then the preset number of times is , where is the ceiling function symbol; the anomaly threshold is .

[0070] Among them, the perpendicular distance from a spatial point to a plane refers to the length of the line segment between the point and the foot of the perpendicular when a perpendicular line is drawn from the spatial point to the plane. The perpendicular distance can be obtained by the vector method and will not be elaborated here.

[0071] The embodiment of the present invention also discloses a geodetic surveying data processing and analysis system based on big data, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the geodetic surveying data processing and analysis method based on big data of the present invention is implemented.

[0072] The above system also includes other components well known to those skilled in the art such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be elaborated here.

[0073] The above are all the preferred embodiments of the present invention, and the protection scope of the present invention is not limited by this. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A geographic surveying and mapping data processing and analysis method based on big data, characterized in that: include: pass The algorithm obtains the outlier factors of all spatial points in the collected geographic surveying and mapping data; Any spatial point is recorded as a target spatial point, and the outlier index of the target spatial point is determined according to the outlier factor of the target spatial point, the mean of the distances between the target spatial point and all spatial points in the neighborhood of the target spatial point, and the standard deviation of the coordinates of all spatial points in the neighborhood; The neighborhood is the target space point in In the algorithm -Distance neighborhood; The outlier index satisfies: ； In the formula, For spatial points in geographic surveying data The outlier index of For space point The outlier factor, For space point of -The distance between all spatial points and spatial points in the neighborhood The mean of the distances, , and The spatial points of -The distance from all spatial points in the neighborhood , and Standard deviation of coordinates; The average value of the radius of the neighborhood of all spatial points is used as the range radius value, and the neighborhood range of the target spatial point is constructed according to the range radius value; Determine the density distance between the target spatial point and any other spatial point according to the distance between the target spatial point and any other spatial point, the outlier index, and the number of spatial points in the vicinity; According to the size of the density distance, all spatial points are divided into regions to obtain a number of regions; The target area is determined based on the range radius value, the mean of the outlier index of all spatial points in the target area of ​​the plurality of areas, and the standard deviation of the data point intensity of all spatial points in the target area. The fitting threshold that distinguishes inliers from outliers in the algorithm; The fitting threshold satisfies: ； In the formula, For the The fitting threshold of the region, is the range radius value, For the The mean of the outlier index of all spatial points in the region, For the The standard deviation of the data point intensity at all spatial points in the region, is a linear normalization function; According to the fitting threshold, using The algorithm fits the target area and obtains the inner and outer points of the target area to identify abnormal data points and complete the processing and analysis of geographic surveying and mapping data.

2. The method for processing and analyzing geographic surveying and mapping data based on big data according to claim 1, characterized in that: The step of constructing a proximity range of the target space point according to the range radius value includes: The spherical range with the target space point as the center and the range radius value as the radius is the proximity range of the target space point.

3. The method for processing and analyzing geographic surveying and mapping data based on big data according to claim 1, characterized in that: The density distance satisfies: ； In the formula, For spatial points in geographic surveying data With space point The density distance, For space point With space point The distance and The spatial points and spatial points The number of spatial points in the vicinity of and The spatial points and spatial points The outlier index of is a hyperparameter, is the absolute value symbol.

4. The method for processing and analyzing geographic surveying and mapping data based on big data according to claim 1 or 3, characterized in that: The distance is the Euclidean distance.

5. The method for processing and analyzing geographic surveying and mapping data based on big data according to claim 1, characterized in that: According to the size of the density distance, all spatial points are divided into regions to obtain several regions, including: Divide the spatial points whose density distance is less than a preset regional threshold and the target pixel points into the same region until all spatial points are divided to obtain multiple regions; In response to the density distance between two spatial points that do not belong to the same region being less than a preset region threshold, the regions to which the two spatial points belong are merged until all regions are no longer merged, thereby obtaining a plurality of regions.

6. The method for processing and analyzing geographic surveying and mapping data based on big data according to claim 1, characterized in that: The utilization The algorithm fits the target area to obtain the inner and outer points of the target area to identify abnormal data points, including: According to the preset number of times, three spatial points are randomly selected in the target area to form a plane, and the vertical distance from each spatial point in the target area except the spatial points forming the plane to the plane is calculated each time. If the vertical distance is less than the fitting threshold, the spatial point is regarded as an inner point of the target area, otherwise, the spatial point is regarded as an outer point of the target area, and the number of times each spatial point is regarded as an outer point of the target area is obtained; In response to the number of outliers being greater than a preset anomaly threshold, the spatial point is identified as an abnormal data point in the geographic surveying and mapping data.

7. A geographic surveying and mapping data processing and analysis system based on big data, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the geographic surveying and mapping data processing and analysis method based on big data according to any one of claims 1 to 6 is implemented.

Images