Geographic information surveying and mapping data intelligent analysis method and system

Abstract

The invention provides a geographic information surveying and mapping data intelligent analysis method and system, and relates to the technical field of surveying and mapping data analysis, and the method comprises the steps: determining a to-be-analyzed region, and obtaining geographic information surveying and mapping data; gridding the to-be-analyzed region to form a plurality of spatial positions, constructing a time sequence, and extracting multi-dimensional trend feature vectors in different time windows based on the time sequence; for each spatial position, screening to obtain a final candidate neighborhood; screening to obtain an effective neighborhood according to the multi-dimensional trend feature vector; performing interpolation processing on the time sequence of the target spatial position based on the effective neighborhood to obtain a complete time sequence of each spatial position; and performing spatio-temporal change mode analysis on the complete time sequence, identifying a spatio-temporal evolution rule and generating a spatio-temporal change analysis report. According to the method, accurate identification and intelligent analysis of the spatial-temporal evolution law of the geographic surveying and mapping data can be realized, and an interpretable analysis result with geographic significance is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of surveying and mapping data analysis, and in particular to a method and system for intelligent analysis of geographic information surveying and mapping data. Background Art

[0002] With the rapid development of remote sensing technology, the Global Positioning System (GPS), the Geographic Information System (GIS), and surveying and mapping technologies, geographic information surveying and mapping data have seen significant improvements in spatial resolution, temporal coverage, and data accuracy. Modern geographic surveying and mapping data are characterized by multi-source heterogeneity, massive real-time, and spatiotemporal coupling, encompassing a variety of types, including satellite remote sensing data, aerial photography data, ground-based measurement data, and drone aerial survey data. These data provide a rich foundation for a deeper understanding of the spatiotemporal evolution of geographic phenomena, monitoring surface change processes, and supporting urban planning and environmental protection. However, due to factors such as satellite revisit cycles, weather conditions, equipment failures, and mission scheduling, geographic surveying and mapping data often exhibit severe irregularities and omissions in the temporal dimension, and also exhibit uneven density characteristics in spatial distribution, posing severe challenges to subsequent data analysis and processing.

[0003] Existing geographic data analysis techniques mainly fall into two categories: spatial analysis methods and time series analysis methods. Spatial analysis methods focus on exploring the distribution patterns and correlations of data in the spatial dimension, such as spatial interpolation, spatial clustering, and spatial regression. These methods can effectively process the spatial distribution characteristics of data but lack consideration of temporal evolution. Time series analysis methods focus on revealing the changing trends and periodic patterns of data in the temporal dimension, such as trend analysis, cycle detection, and anomaly identification. However, they generally assume that data is equally spaced and continuous in time, an assumption that is difficult to meet in actual geographic surveying and mapping data. In recent years, spatiotemporal data analysis methods have gradually become a research hotspot, aiming to simultaneously utilize the temporal and spatial information of data for comprehensive analysis. However, existing spatiotemporal analysis methods still have technical deficiencies in handling temporal irregularities, intelligently filtering spatial information, considering multi-scale features, and adaptive processing.

[0004] For example, the invention patent for geographic surveying and mapping operation data real-time acquisition and processing method and system with China's publication number CN117171533A, this patented technology mainly focuses on the real-time acquisition, coordinate conversion, attribute field standardization and basic quality verification of field surveying and mapping data by the operation terminal. Its technical core is the end-cloud collaborative transmission compression strategy and regularized field mapping table. This solution realizes the real-time acquisition and preliminary processing of surveying and mapping data through the operation data aggregation module, data preprocessing module, overlapping data screening module, etc., and has certain advantages in data acquisition efficiency and transmission optimization. However, this solution mainly solves the technical problems in the data acquisition stage, and does not provide effective solutions to the key technical problems faced after the acquisition of surveying and mapping data is completed, such as spatiotemporal sparsity, trend conflicts and intelligent enhancement. Summary of the Invention

[0005] In view of this, the present invention provides an intelligent analysis method for geographic information surveying and mapping data, which aims to solve the technical defects of existing geographic information surveying and mapping data analysis technologies in processing temporal irregularities, intelligent screening of spatial information and consideration of multi-scale features. By establishing an intelligent neighborhood screening mechanism based on trend consistency constraints and a multi-scale feature vector matching algorithm, accurate identification and intelligent analysis of the spatiotemporal evolution laws of geographic surveying and mapping data can be achieved, and interpretable analysis results with geographical significance can be provided.

[0006] The technical solution of the present invention is achieved as follows:

[0007] In one aspect, the present invention provides a method for intelligent analysis of geographic information surveying and mapping data, comprising:

[0008] S1. Determine the area to be analyzed, obtain geographic information surveying and mapping data within the area to be analyzed, including spatial coordinates, timestamps, and attribute value information, standardize the data points, and generate a data quality score;

[0009] S2. Gridding the area to be analyzed to form multiple spatial locations, assigning the standardized data points to the corresponding spatial locations according to spatial coordinates, arranging the corresponding data points for each spatial location according to timestamps and attribute values ​​to construct a time series, and extracting multi-dimensional trend feature vectors in different time windows based on the time series;

[0010] S3. For each spatial location, an initial candidate neighborhood is constructed based on the spatial distance. The data quality score is used to screen the initial candidate neighborhood to eliminate unqualified locations. When the number of candidate neighbors is insufficient, an adaptive expansion mechanism is used to reconstruct the neighborhood to obtain the final candidate neighborhood.

[0011] S4. Calculate the trend feature matching degree between each candidate neighbor in the final candidate neighborhood and the target spatial position based on the multi-dimensional trend feature vector, determine the optimal similarity threshold, and screen to obtain a valid neighborhood;

[0012] S5. Interpolate the time series of the target spatial position based on the valid neighborhood to obtain a complete time series for each spatial position;

[0013] S6. Analyze the spatiotemporal change patterns of the complete time series, identify the spatiotemporal evolution laws and generate a spatiotemporal change analysis report.

[0014] Preferably, step S1 includes:

[0015] S11. Standardize the format of geographic information surveying and mapping data and unify the coordinate system and time base;

[0016] S12. Establish an R-tree spatial index structure to support efficient spatial neighborhood queries;

[0017] S13, using Tukey fence method to identify and handle abnormal data points;

[0018] S14. Calculate the quality score of each data point based on data completeness, temporal density, and spatial coverage;

[0019] S15. Associate and store the standardized data points with the corresponding data quality scores.

[0020] Preferably, step S2 includes:

[0021] S21, determining a grid resolution according to the range of the area to be analyzed and the data density, and dividing the area to be analyzed into regular grids to form multiple spatial locations;

[0022] S22, establishing a mapping relationship between spatial positions and data points, and assigning the normalized data points to corresponding grid spatial positions according to their spatial coordinates;

[0023] S23. For each spatial location, all data points belonging to it are collected, sorted by timestamp, and a time series of the location is constructed by combining attribute value information;

[0024] S24. For each spatial location, three different time windows, short-term, medium-term, and long-term, are set. In each time window, the linear trend slope is calculated using the least squares method and the second-order curvature features are extracted using local weighted polynomial fitting. The features of the three time windows are combined to construct a six-dimensional multidimensional trend feature vector.

[0025] Preferably, the calculation formula for the linear trend slope is:

[0026]

[0027] Among them, i is the spatial position index, w k,k={1,2,3} is the time window, is the spatial position i in the time window w k The linear trend slope within n is the slope of the spatial position i in the time window w. k The number of data points in the V, t is the timestamp of the data point, i (t) is the attribute value of the data point corresponding to spatial position i at timestamp t, Represents the spatial position i in the time window w k The timestamp collection of all data points in .

[0028] Preferably, step S3 includes:

[0029] S31, taking each spatial position as the target spatial position in turn, and selecting other adjacent spatial positions based on the Euclidean distance order with the target spatial position as the center to construct an initial candidate neighborhood;

[0030] S32. For each candidate spatial location in the initial candidate neighborhood, calculate a comprehensive quality score for the spatial location based on the data quality score of its belonging data point, and eliminate spatial locations with a comprehensive quality score below a quality threshold;

[0031] S33. When the number of candidate spatial locations after screening is less than the preset minimum value, the adaptive expansion mechanism is started to gradually expand the search radius and reconstruct to obtain the final candidate neighborhood that meets the quantity requirements.

[0032] Preferably, step S4 includes:

[0033] S41, extracting the common time period between each candidate spatial position and the target spatial position in the final candidate neighborhood;

[0034] S42, recalculating the multi-dimensional trend feature vectors of the two based on the common time period;

[0035] S43, calculating the trend matching degree based on the linear trend slope, and calculating the comprehensive similarity based on the recalculated multi-dimensional trend feature vector;

[0036] S44, determining the optimal similarity threshold and neighborhood number parameters;

[0037] S45. Filter candidate spatial positions according to the optimal similarity threshold, and select the first several positions to form a valid neighborhood by sorting them in descending order of comprehensive similarity.

[0038] Preferably, the calculation formula of the trend matching degree M(i,j) is:

[0039]

[0040] Among them, w k ,k={1,2,3} is the time window, and They are spatial position i and spatial position j in time window w respectively k The slope of the linear trend in ,∈ is a small positive number to prevent the denominator from being zero;

[0041] The calculation formula of comprehensive similarity S(i,j) is:

[0042] S(i,j)=α1·M(i,j)+α2·|cos(v′ i ,v′ j )|

[0043] Among them, v′ i and v′ j The multi-dimensional trend feature vectors recalculated based on the common time period for spatial position i and spatial position j, cos(v′ i ,v′ j ) is v′ i and v′ j , α1 and α2 are the weights of trend matching and cosine similarity respectively, and α1+α2=1, α1, α2>0.

[0044] Preferably, step S5 includes:

[0045] S51, calculating the spatial distance weight from each spatial position in the valid neighborhood to the target spatial position;

[0046] S52, using the inverse distance weighted method to perform spatial interpolation calculation on the time series of each spatial position in the effective neighborhood;

[0047] S53. When original time series data exists at the target spatial location, weighted fusion is performed based on the comprehensive quality score of the time series and the interpolation result;

[0048] S54. Use the fusion or interpolation result as the complete time series of the spatial position.

[0049] Preferably, step S6 includes:

[0050] S61. Perform time domain decomposition on the complete time series of each spatial location to identify the trend component, periodic component, and random component of each spatial location;

[0051] S62. Identify spatial locations with similar change patterns and aggregate them into spatial regions through spatial autocorrelation analysis;

[0052] S63. Classify and identify the spatiotemporal evolution process at the regional level based on the identified spatial regions;

[0053] S64. Organize the analysis results by spatial region and generate a spatiotemporal change analysis report for the area to be analyzed, including change hotspot areas, evolution trend prediction, and abnormal change detection.

[0054] On the other hand, the present invention also provides a geographic information surveying and mapping data intelligent analysis system, the system is used to implement any of the above methods, the system comprising:

[0055] Data preprocessing module, used to standardize the format of input geographic information surveying and mapping data, process abnormal data and calculate quality scores;

[0056] Grid processing module, used to divide the area to be analyzed into regular grids and construct time series;

[0057] The neighborhood construction module is used to construct candidate neighborhoods for each target spatial location, perform quality screening, and output the final candidate neighborhoods for each spatial location;

[0058] Feature matching module, used to calculate the trend feature matching degree of spatial positions in candidate neighborhoods and screen valid neighborhoods;

[0059] The interpolation processing module is used to perform time series interpolation or fusion processing based on the valid neighborhood and output a complete time series;

[0060] The analysis report module is used to perform spatiotemporal change analysis and generate analysis reports.

[0061] The present invention has the following beneficial effects compared to the prior art:

[0062] (1) This paper constructs an intelligent analysis framework based on trend consistency constraints, transforming the traditional distance-oriented spatial neighborhood selection into trend consistency-oriented selection, fundamentally solving the problem of analytical accuracy of geographic information surveying and mapping data under conditions of spatiotemporal sparseness and irregular distribution. This method can effectively handle the spatiotemporal evolution analysis of multi-source heterogeneous geographic data, and improves the accuracy of spatiotemporal pattern recognition and the interpretability of analysis results while maintaining geographic authenticity.

[0063] (2) The dynamic neighborhood construction mechanism established in this paper based on data quality scoring and trend feature matching screens high-quality spatial neighbors through multi-dimensional quality evaluation indicators, effectively avoiding the negative impact of low-quality neighborhood data on analysis results in traditional methods;

[0064] (3) The six-dimensional multi-scale trend feature vector constructed by the present invention can extract linear trend and nonlinear acceleration features through three time windows: short-term, medium-term, and long-term, and can comprehensively characterize the evolution characteristics of geographical phenomena at different time scales;

[0065] (4) The confidence fusion spatial enhancement processing method adopted in this paper comprehensively considers the quality of the original observation data and the reliability of the spatial interpolation results. Through a weighted fusion strategy, it supplements missing information while preserving the authenticity of the original data. This method effectively avoids the information loss and distortion problems that may be caused by traditional interpolation methods, improving data integrity and analysis accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0067] Figure 1 is a flow chart of the method of the present invention;

[0068] Figure 2 Schematic diagram of the system of the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0070] like Figure 1 As shown, the present invention provides a method for intelligent analysis of geographic information surveying and mapping data, comprising:

[0071] S1. Determine the area to be analyzed, obtain geographic information surveying and mapping data within the area to be analyzed, including spatial coordinates, timestamps, and attribute value information, standardize the data points, and generate a data quality score;

[0072] S2. Gridding the area to be analyzed to form multiple spatial locations, assigning the standardized data points to the corresponding spatial locations according to spatial coordinates, arranging the corresponding data points for each spatial location according to timestamps and attribute values ​​to construct a time series, and extracting multi-dimensional trend feature vectors in different time windows based on the time series;

[0073] S3. For each spatial location, an initial candidate neighborhood is constructed based on the spatial distance. The data quality score is used to screen the initial candidate neighborhood to eliminate unqualified locations. When the number of candidate neighbors is insufficient, an adaptive expansion mechanism is used to reconstruct the neighborhood to obtain the final candidate neighborhood.

[0074] S4. Calculate the trend feature matching degree between each candidate neighbor in the final candidate neighborhood and the target spatial position based on the multi-dimensional trend feature vector, determine the optimal similarity threshold, and screen to obtain a valid neighborhood;

[0075] S5. Interpolate the time series of the target spatial position based on the valid neighborhood to obtain a complete time series for each spatial position;

[0076] S6. Analyze the spatiotemporal change patterns of the complete time series, identify the spatiotemporal evolution laws and generate a spatiotemporal change analysis report.

[0077] This paper adopts the core technical idea of ​​"trend consistency constraint + multi-scale feature matching" to transform the traditional distance-oriented spatial neighborhood selection into trend consistency-oriented selection. By constructing a six-dimensional multi-scale trend feature vector (covering the linear trend slope and second-order curvature characteristics of three time windows: short-term, medium-term, and long-term), combined with the comprehensive similarity calculation of cosine similarity and sigmoid mapping, a dynamic screening threshold mechanism based on statistical variation characteristics is established to achieve adaptive spatial enhancement processing with intelligent neighborhood screening and confidence fusion, thereby solving the problem of accurate analysis of geographic information surveying and mapping data under conditions of spatiotemporal sparseness and irregular distribution. Finally, through time domain decomposition and spatial autocorrelation analysis, intelligent identification of spatiotemporal evolution laws and interpretable analysis of geographical significance are achieved.

[0078] Specifically, in one embodiment of the present invention, step S1 includes:

[0079] S11. Standardize the format of geographic information surveying and mapping data and unify the coordinate system and time base;

[0080] S12. Establish an R-tree spatial index structure to support efficient spatial neighborhood queries;

[0081] S13, using Tukey fence method to identify and handle abnormal data points;

[0082] S14. Calculate the quality score of each data point based on data completeness, temporal density, and spatial coverage;

[0083] S15. Associate and store the standardized data points with the corresponding data quality scores.

[0084] In this embodiment, the boundary of the geographical area where spatiotemporal change analysis is required is first determined. The area may be an administrative boundary, a natural boundary, or an arbitrary polygonal area defined by the user.

[0085] Obtain geographic information surveying and mapping data for the area. This data includes spatial coordinate information (latitude and longitude coordinates or projected coordinates), timestamp information (recording the specific time of data collection), and attribute numerical information (such as vegetation index, surface temperature, land use type, and other quantitative or qualitative descriptive values ​​of geographic elements). Data sources can be satellite remote sensing data, aerial photography data, ground-based measurement data, drone aerial survey data, and other types.

[0086] The acquired raw data was standardized, including the coordinate system and time base, to ensure that all data points were based on the same spatial reference system and time standard. An R-tree spatial index structure was established to support efficient spatial neighborhood queries. This index structure can quickly locate data points within a specified area and supports range and nearest neighbor queries. The Tukey fence method was used for data anomaly detection and processing. This method identifies statistical outliers by calculating the interquartile range (IQR). The specific formula is: an outlier is determined when a data value is less than Q1 - 1.5 × IQR or greater than Q3 + 1.5 × IQR, where Q1 and Q3 are the first and third quartiles, respectively, and IQR = Q3 - Q1 is the interquartile range. Identified outlier data points are marked and removed or corrected based on the specific situation.

[0087] The quality score of each data point is calculated based on the three dimensions of data completeness, temporal density, and spatial coverage. The data completeness score is calculated by checking the integrity of the attribute fields of the data point. The higher the integrity, the higher the score. The temporal density score is calculated based on the data distribution density of the data point in its adjacent time window. The higher the density, the better the temporal continuity. The spatial coverage score is calculated based on the distribution density of other data points within a certain range around the data point. The higher the coverage, the stronger the spatial representativeness. The three scores are synthesized by weighted averaging to form the final data quality score. The score ranges from 0 to 1. The higher the score, the better the data quality. The standardized data points are associated with their corresponding data quality scores and stored to establish a complete data quality archive.

[0088] Specifically, in one embodiment of the present invention, step S2 includes:

[0089] S21, determining a grid resolution according to the range of the area to be analyzed and the data density, and dividing the area to be analyzed into regular grids to form multiple spatial locations;

[0090] S22, establishing a mapping relationship between spatial positions and data points, and assigning the normalized data points to corresponding grid spatial positions according to their spatial coordinates;

[0091] S23. For each spatial location, all data points belonging to it are collected, sorted by timestamp, and a time series of the location is constructed by combining attribute value information;

[0092] S24. For each spatial location, three different time windows, short-term, medium-term, and long-term, are set. In each time window, the linear trend slope is calculated using the least squares method and the second-order curvature features are extracted using local weighted polynomial fitting. The features of the three time windows are combined to construct a six-dimensional multidimensional trend feature vector.

[0093] In this example, the grid resolution is first determined based on the scope and data density of the area to be analyzed. The area to be analyzed is divided into a regular grid to form multiple spatial locations. The selection of the grid resolution requires a comprehensive consideration of the spatial distribution density of the data points, the required analysis accuracy, and computational efficiency. It is set to 1 to 3 times the average spacing between the data points.

[0094] The normalized data points are assigned to the corresponding grid spatial positions according to their spatial coordinates, and a mapping relationship between spatial positions and data points is established. The center point coordinates of each grid unit are used as the representative coordinates of the spatial position, and all data points falling within the same grid unit are assigned to the spatial position. For each spatial position, all the data points belonging to it are collected, sorted by timestamp and combined with the attribute value information to construct the time series of the position. The time series consists of a series of ordered pairs of timestamps and corresponding attribute values, in the form of (t1, V i (t1)),(t2,V i (t2)),...,(t n ,V i (t n ))$, where i is the spatial position index, t j is the timestamp, V i (t j ) is the attribute value corresponding to the timestamp.

[0095] For each spatial location, three different time windows {w1, w2, w3} are set: short-term, medium-term, and long-term. The length of the time window is determined according to the total time span of the time series and the analysis requirements. Usually, the short-term window covers 15% to 25% of the total time span, the medium-term window covers 30% to 50%, and the long-term window covers 60% to 90%.

[0096] The linear trend slope is calculated using the least squares method within each time window, and the calculation formula is:

[0097]

[0098] Among them, i is the spatial position index, w k ,k={1,2,3} is the time window, is the spatial position i in the time window w k The linear trend slope within n is the slope of the spatial position i in the time window w. kThe number of data points in the V, t is the timestamp of the data point, i (t) is the attribute value of the data point corresponding to spatial position i at timestamp t, Represents the spatial position i in the time window w k The timestamp collection of all data points in .

[0099] At the same time, the second-order curvature features are extracted by using local weighted polynomial fitting, and the quadratic polynomial V is fitted. i (t) = a2t 2 +a1t+a0 extracts the second-order coefficient a2 as the curvature feature This feature reflects the acceleration or deceleration trend of attribute changes. The linear trend slope and second-order curvature features of the three time windows are combined to construct a six-dimensional multi-dimensional trend feature vector This vector can simultaneously capture the linear change trend and nonlinear acceleration change characteristics of spatial position on three time scales: short-term, medium-term, and long-term.

[0100] For spatial locations with insufficient time series data points, if the number of data points in a time window is less than three, data from adjacent time windows are used to supplement the data or the dimension feature is set to a null value and specially marked in subsequent processing. The six-dimensional trend feature vector of each spatial location is normalized using the Z-score standardization method to ensure that the numerical range of different dimensional features is consistent. The normalization formula is (x-μ) / σ, where μ is the mean of the dimensional feature and σ is the standard deviation.

[0101] Specifically, in one embodiment of the present invention, step S3 includes:

[0102] S31, taking each spatial position as the target spatial position in turn, and selecting other adjacent spatial positions based on the Euclidean distance order with the target spatial position as the center to construct an initial candidate neighborhood;

[0103] S32. For each candidate spatial location in the initial candidate neighborhood, calculate a comprehensive quality score for the spatial location based on the data quality score of its belonging data point, and eliminate spatial locations with a comprehensive quality score below a quality threshold;

[0104] S33. When the number of candidate spatial locations after screening is less than the preset minimum value, the adaptive expansion mechanism is started to gradually expand the search radius and reconstruct to obtain the final candidate neighborhood that meets the quantity requirements.

[0105] In this embodiment, each spatial position is first processed as a target spatial position in turn, and the Euclidean distance to all other spatial positions is calculated based on the spatial coordinates of the target spatial position. The Euclidean distance calculation formula is:

[0106]

[0107] Where (x i ,y i ) and (x j ,y j ) are the coordinates of the target space position and the candidate space position respectively.

[0108] The calculated Euclidean distances are sorted in ascending order, and the nearest spatial locations are selected to form the initial candidate neighborhood. The size of the initial candidate neighborhood is determined by the spatial distribution density of the data and the required analysis accuracy. Typically, 10 to 20 nearest neighbor spatial locations are selected as the initial candidate neighborhood.

[0109] For each candidate spatial location in the initial candidate neighborhood, the comprehensive quality score of the spatial location is calculated based on the data quality scores of its belonging data points. The comprehensive quality score is calculated by taking the weighted average of the quality scores of all the belonging data points of the spatial location, and the calculation formula is:

[0110]

[0111] where Q i is the comprehensive quality score of spatial position i, n i is the number of data points belonging to this location, q k is the quality score of the kth data point, ω k The weight is determined by the temporal recency and spatial representativeness of the data point. The more recent the time and the more representative the space, the greater the weight of the data point.

[0112] A quality threshold is set to screen candidate spatial locations, eliminating those with an overall quality score below the threshold. The quality threshold is set between 0.6 and 0.8, with the specific value determined based on the overall distribution of data quality and the required analysis accuracy. After quality screening, the number of remaining candidate spatial locations is counted to determine whether they meet the preset minimum requirement.

[0113] The preset minimum value is set to 5 to 8 candidate locations to ensure the stability and reliability of the subsequent interpolation process. When the number of candidate spatial locations after screening is less than the preset minimum value, the adaptive expansion mechanism is activated to reconstruct the candidate neighborhood.

[0114] The adaptive expansion mechanism increases the number of candidate spatial locations by gradually expanding the search radius. The initial search radius is set to r0 = 3 × grid resolution, and each expansion increases the radius range by Δr = r0. The expansion process is performed at most twice, that is, the search radius is expanded to a maximum of r0 + 2Δr. After each expansion, the comprehensive quality score of the newly added spatial locations within the expanded range is recalculated, and the same quality threshold is used for screening, and the spatial locations that meet the requirements are added to the candidate neighborhood. If the number of candidate spatial locations is still less than the preset minimum value after two expansions, the quality threshold is lowered and re-screened, or the existing candidate locations are used for subsequent processing and the data quality level of the area is marked as low reliability. The final candidate neighborhood obtained through the above processing contains spatial locations that meet the requirements in both spatial proximity and data quality.

[0115] Specifically, in one embodiment of the present invention, step S4 includes:

[0116] S41, extracting the common time period between each candidate spatial position and the target spatial position in the final candidate neighborhood;

[0117] S42, recalculating the multi-dimensional trend feature vectors of the two based on the common time period;

[0118] S43, calculating the trend matching degree based on the linear trend slope, and calculating the comprehensive similarity based on the recalculated multi-dimensional trend feature vector;

[0119] S44, determining the optimal similarity threshold and neighborhood number parameters;

[0120] S45. Filter candidate spatial positions according to the optimal similarity threshold, and select the first several positions to form a valid neighborhood by sorting them in descending order of comprehensive similarity.

[0121] In this embodiment, the common observation time period T of each candidate spatial position j and the target spatial position i in the final candidate neighborhood is first determined. common =T i ∩T j , where T i is the observation time set of the target spatial position, T j is the observation time set of the candidate spatial position, and the observation time set is also the timestamp set.

[0122] Recalculate the multi-dimensional trend feature vectors of the two spatial locations within the common observation period to ensure the comparability of the feature vectors. For the target spatial location i, recalculate the six-dimensional trend feature vector v′ based on the data within the common time period. i , for the candidate spatial position j, its six-dimensional trend feature vector v′ is also recalculated based on the common time period j .

[0123] Calculate the trend matching degree of two spatial locations based on the recalculated linear trend slope characteristics:

[0124]

[0125] Among them, w k ,k={1,2,3} is the time window, and They are spatial position i and spatial position j in time window w respectively k The slope of the linear trend in , ∈ is a small positive number that prevents the denominator from being zero.

[0126] Among them, the use of As a normalization benchmark, the absolute value of the larger slope is used as the reference standard; when both slopes are small, the denominator is close to ε, and the similarity is mainly determined by the absolute difference; when one slope is large and the other is small, the denominator is determined by the larger slope, avoiding the deviation of relative comparison.

[0127] represents the absolute difference between the two slopes, Provides a normalized benchmark, Indicates the relative degree of difference; 1-relative difference is used to obtain the similarity component of the time window; the similarity components of the three time windows are weighted and multiplied to obtain the comprehensive trend matching degree.

[0128] Combined with the recalculated multi-dimensional trend feature vector, the cosine similarity is calculated using the following formula:

[0129]

[0130] This similarity measures the angular similarity of two feature vectors in multidimensional space.

[0131] Multiply the trend matching degree and the cosine similarity to get the comprehensive similarity:

[0132] S(i,j)=α1·M(i,j)+α2·|cos(v′ i ,v′ j )|

[0133] Among them, v′ i and v′ j The multi-dimensional trend feature vectors recalculated based on the common time period for spatial position i and spatial position j, cos(v′ i ,v′ j ) is v′ i and v′ jα1 and α2 are the weights of trend matching and cosine similarity respectively, and α1+α2=1, α1, α2>0. The comprehensive similarity takes into account both trend consistency and the overall similarity of feature vectors.

[0134] In this example, a leave-one-out cross-validation method was used to search for parameters within a similarity threshold range of 0.3 to 0.8 with a step size of 0.1 and a neighborhood number range of 3 to 12. For each parameter combination, historical data was used for validation, the average error of the interpolated predictions was calculated, and the parameter combination with the smallest error was selected as the optimal setting.

[0135] Based on the optimal similarity threshold determined by cross-validation, spatial locations with the required comprehensive similarity are screened from candidate neighborhoods. If the screening results meet the optimal number of neighbors, the top locations are selected in descending order of comprehensive similarity. If the screening results do not meet the optimal number of neighbors, all locations that pass the threshold screening are selected as valid neighborhoods.

[0136] When the number of locations that pass the similarity threshold is less than the minimum neighborhood requirement, a decreasing threshold strategy is typically set to 3. Each time the similarity threshold is lowered by 0.05, the screening process is repeated until a sufficient number of valid neighborhoods are obtained. A minimum threshold of 0.1 is set to prevent overly lenient screening.

[0137] Specifically, in one embodiment of the present invention, step S5 includes:

[0138] S51, calculating the spatial distance weight from each spatial position in the valid neighborhood to the target spatial position;

[0139] S52, using the inverse distance weighted method to perform spatial interpolation calculation on the time series of each spatial position in the effective neighborhood;

[0140] S53. When original time series data exists at the target spatial location, weighted fusion is performed based on the comprehensive quality score of the time series and the interpolation result;

[0141] S54. Use the fusion or interpolation result as the complete time series of the spatial position.

[0142] In this embodiment, first, the effective neighborhood N′ i For each spatial position j, the spatial distance weight to the target spatial position i is calculated, and the Gaussian distance decay function is used to calculate the weight coefficient:

[0143]

[0144] where d ij is the ellipsoidal distance, σ dis the distance decay parameter, which is determined according to the spatial distribution density of the data and is usually set to 0.5 to 1.5 times the average neighbor distance.

[0145] The inverse distance weighted method is used to perform spatial interpolation calculation on the time series of each spatial position in the effective neighborhood. For the interpolation processing of the target spatial position at time point t, the calculation formula is:

[0146]

[0147] Where V j (t) is the observed value of spatial position j at time t in the effective neighborhood, w ij is the corresponding distance weight coefficient. When the target spatial position i has the original observation data V at time point t i (t), it is necessary to perform confidence fusion processing based on the comprehensive quality score of the observation data and the interpolation result.

[0148] The calculation formula of confidence fusion is: This formula realizes the fusion of original observation data and spatial interpolation results, which not only retains the authenticity of the original data but also supplements possible missing or erroneous information through spatial information.

[0149] According to the characteristics of different stages of the target location time series, a segmented adaptive enhancement strategy is used for differential processing. In the inverse distance weighted interpolation process, when the coefficient of variation of the neighborhood data of the target location is large, it indicates that the data in this area fluctuates greatly. At this time, the conservatism of the interpolation should be appropriately increased. In the rapid change stage, that is, the coefficient of variation CV i >CV high When , the value of the basic threshold τ0 is increased to rely more on the neighbors with high matching degree, ensuring that the interpolation result can accurately reflect the rapidly changing characteristics. i <CV low When the threshold is appropriately lowered to expand the effective neighbor range, more spatial information is used to improve the stability of the interpolation. In the turning stage, special attention is paid to the neighboring positions that have also experienced a turning point, and the contribution of these positions in the interpolation is enhanced through weighted adjustment. For the case where the target spatial position completely lacks observation data at certain time points, the spatial interpolation result is directly used as the value of that time point, and the data source is marked as spatial enhancement. The time series data obtained after interpolation processing or confidence fusion is checked for integrity to ensure that all time points have corresponding values, and the processing method and quality level information of each data point are recorded. The complete time series after processing is used as the final time series data of the spatial position.

[0150] Specifically, in one embodiment of the present invention, step S6 includes:

[0151] S61. Perform time domain decomposition on the complete time series of each spatial location to identify the trend component, periodic component, and random component of each spatial location;

[0152] S62. Identify spatial locations with similar change patterns and aggregate them into spatial regions through spatial autocorrelation analysis;

[0153] S63. Classify and identify the spatiotemporal evolution process at the regional level based on the identified spatial regions;

[0154] S64. Organize the analysis results by spatial region and generate a spatiotemporal change analysis report for the area to be analyzed, including change hotspot areas, evolution trend prediction, and abnormal change detection.

[0155] In this embodiment, the complete time series of each spatial location is first intelligently decomposed in the time domain to establish a geographic semantic-aware time series decomposition framework, which not only performs mathematical component decomposition but also can identify and annotate time patterns with geographical significance.

[0156] The process for constructing a geographic semantic pattern library is as follows: First, basic geographic change patterns are defined, including five basic patterns: monotonic increase, monotonic decrease, cyclical fluctuation, step change, and sudden anomaly. Each pattern is represented by a standardized time series template, with a fixed length of 30 time points. For the input time series, a sliding window method is used to extract subsequences of the same length. These subsequences are then Pearson correlation coefficients calculated with the templates in the pattern library. The pattern corresponding to the template with the highest correlation coefficient is the semantic annotation result for that time period.

[0157] A pattern matching calculation mechanism is established, and the calculation formula is:

[0158]

[0159] Among them, PMD k (t) is the matching degree of the kth semantic pattern at time t, DTW(·) is the dynamic time warping distance function, V i (t) is the observation sequence, is the i-th feature sequence of pattern k, w i is the corresponding weight, σ is the normalization parameter, and the DTW distance is converted to similarity through the exponential function. The smaller the distance, the higher the similarity. Decompose the time series:

[0160] X(t)=T(t)+S(t)+R(t)

[0161] Where T(t) is the trend component, S(t) is the periodic component, and R(t) is the random component. A multi-level time anomaly intelligent recognition system is established, and a three-layer anomaly detection architecture is constructed. The statistical anomaly layer is based on the improved CUSUM method, and the calculation formula is:

[0162]

[0163] Introducing adaptive control limit h t =h0·(1+γ·CV t ), where CV t is the rolling coefficient of variation. The trend anomaly layer is based on trend change rate detection, and the calculation formula is:

[0164]

[0165] When TCD>TCD threshold The pattern anomaly layer is based on semantic pattern deviation detection, and the calculation formula is:

[0166]

[0167] When MAD>MAD threshold It is identified as a pattern abnormality.

[0168] Intelligent anomaly classification rules are established. Isolated point anomalies are detected only by the statistical layer, trend reversal anomalies are detected jointly by the statistical and trend layers, pattern breaking anomalies are detected jointly by the statistical and pattern layers, and systematic anomalies are detected simultaneously by all three layers. Specifically, the statistical anomaly layer uses the 3σ principle, identifying statistical anomalies when a data point deviates from the mean by more than three standard deviations. The trend anomaly layer calculates the slope of the linear trend over a 30-day sliding window, identifying a trend anomaly when the absolute value of the slope exceeds the 95th percentile of the distribution of historical slopes for the same period. The pattern anomaly layer identifies a pattern anomaly when the highest correlation coefficient between the time series and all patterns in the semantic pattern library is less than 0.3, indicating the emergence of an unknown pattern of change. The Hurst exponent of the time series is calculated to assess its long-term memory and predictability, and the Ljung-Box test is used to assess the white noise characteristics of the series. ARIMA or state-space models are developed to describe the mathematical characteristics of the time series, providing a quantitative basis for short-term forecasting and trend extrapolation.

[0169] Spatial autocorrelation analysis was used to identify spatial locations with similar change patterns, and Moran's I index was used to calculate spatial autocorrelation. The calculation formula is:

[0170]

[0171] Where n is the total number of spatial locations, w ij is the spatial weight matrix, x i is the attribute value of spatial position i, is the mean of the attribute values.

[0172] Based on spatial autocorrelation results and time series similarity metrics, K-means or hierarchical clustering methods are used to cluster spatial locations with similar spatiotemporal variation patterns into spatial regions, forming pattern partitions of spatiotemporal evolution. Based on the identified spatial regions, regional-level spatiotemporal evolution processes are classified and identified. Spatial adjacency relationships and transition probabilities between different pattern regions are calculated, and a Markov chain model of spatiotemporal evolution is constructed to reveal the macroevolutionary mechanisms of geographical phenomena. Multi-scale visualization analysis results are generated, including spatiotemporal variation trajectory maps, trend intensity distribution maps, pattern partition maps, and anomaly detection result maps. Analysis results are organized by spatial region, and a structured analysis report is output, containing key information such as hotspot identification, evolution trend prediction, anomaly change detection, change rate statistics, turning point identification, and confidence interval estimation. Output is supported in multiple data formats, including JSON, XML, and GeoJSON, to produce a complete spatiotemporal change analysis report for the analyzed area.

[0173] In addition, if Figure 2 As shown, the present invention also provides a geographic information surveying and mapping data intelligent analysis system, the system is used to implement any of the above methods, the system includes:

[0174] Data preprocessing module, used to standardize the format of input geographic information surveying and mapping data, process abnormal data and calculate quality scores;

[0175] Grid processing module, used to divide the area to be analyzed into regular grids and construct time series;

[0176] The neighborhood construction module is used to construct candidate neighborhoods for each target spatial location, perform quality screening, and output the final candidate neighborhoods for each spatial location;

[0177] Feature matching module, used to calculate the trend feature matching degree of spatial positions in candidate neighborhoods and screen valid neighborhoods;

[0178] The interpolation processing module is used to perform time series interpolation or fusion processing based on the valid neighborhood and output a complete time series;

[0179] The analysis report module is used to perform spatiotemporal change analysis and generate analysis reports.

[0180] In this embodiment, the intelligent analysis system for geographic information surveying and mapping data adopts a modular architecture design and is composed of six core functional modules. Each module works together to realize intelligent analysis and processing of geographic information surveying and mapping data. The data preprocessing module serves as the data input end of the system and is responsible for receiving geographic information surveying and mapping data from different data sources, including GPS measurement data, remote sensing image data, topographic map data, engineering measurement data and other data types. The module has built-in multiple data format parsers and supports automatic recognition and parsing of mainstream data formats such as ESRI Shapefile, GeoJSON, KML, GPX, CSV, etc. The format standardization processing subunit adopts the GDAL / OGR open source geographic data processing library to achieve unified conversion of coordinate systems, support mutual conversion of multiple coordinate systems such as WGS84, UTM, Gauss Krüger projection, and ensure that all input data uses a unified spatial reference system. The time base standardization processing adopts UTC time as a unified base, automatically identifying and converting various time formats including ISO8601 standard time, local time, timestamp and other formats. The abnormal data processing subunit integrates multiple anomaly detection algorithms, including those based on statistical distribution, clustering, and time series. It automatically identifies and marks data points that significantly deviate from the normal range. The quality score calculation subunit establishes a comprehensive evaluation system, generating a quality score between 0 and 1 for each data point.

[0181] The gridding processing module is responsible for spatially discretizing the geographic area to be analyzed and automatically calculating the optimal grid resolution based on the input geographic boundary range and data density analysis results. This module uses a quadtree data structure to optimize spatial partitioning efficiency, adopting finer grid resolutions in data-dense areas and relatively coarse grid resolutions in data-sparse areas, thereby implementing an adaptive grid partitioning strategy. The spatial index construction subunit uses the R-tree algorithm to establish an efficient spatial index structure, supporting fast spatial neighborhood queries and range retrieval operations. The time series construction subunit sorts data points belonging to the same grid cell according to timestamps, constructs the original time series of the spatial location, and automatically identifies the sampling frequency and time interval characteristics of the time series. The multidimensional trend feature extraction subunit implements an automatic partitioning mechanism for three time windows: short-term, medium-term, and long-term, and uses sliding window technology to extract trend features at each time scale, including multidimensional feature parameters such as linear trend slope and second-order curvature features.

[0182] The neighborhood construction module intelligently constructs high-quality candidate neighborhoods for each target spatial location. This module adopts a multi-level neighborhood construction strategy to ensure the spatial representativeness and data quality of the neighborhood. The spatial distance calculation subunit uses the ellipsoidal distance calculation method to calculate accurate spatial distances taking into account the characteristics of the earth's curved surface, and supports distance calculations in different projection coordinate systems. The initial candidate neighborhood construction subunit uses a spatial index structure to quickly retrieve candidate spatial locations around the target location based on the set search radius or neighbor number threshold. The quality screening subunit screens the candidate spatial locations based on their comprehensive quality scores, eliminating locations with quality scores below the set threshold to ensure the data quality of the candidate neighborhood. The adaptive expansion mechanism automatically activates when the number of candidate neighbors is insufficient, increasing the number of candidate locations by gradually expanding the search radius, and dynamically adjusting the quality threshold to balance the requirements of neighborhood size and data quality.

[0183] The feature matching module implements an intelligent matching algorithm based on multi-dimensional trend features, ensuring that the selected valid neighborhoods have a high degree of similarity in trend features with the target location. The common time period extraction subunit automatically identifies the overlapping time series intervals between the candidate spatial location and the target location, ensuring the fairness and consistency of feature comparison. The trend feature recalculation subunit recalculates the multi-dimensional trend feature vectors of the candidate and target locations based on the common time period, eliminating the impact of time range differences on feature comparison. The trend matching calculation subunit calculates trend matching using a weighted geometric average. The comprehensive similarity calculation subunit combines trend matching with cosine similarity to form a comprehensive similarity metric. The dynamic threshold calculation subunit determines the optimal similarity threshold and neighborhood number parameters based on historical data, screens candidate spatial locations based on the optimal similarity threshold, and selects the top several locations in descending order of comprehensive similarity to form a valid neighborhood.

[0184] The interpolation processing module performs intelligent interpolation processing on the target spatial position based on the effective neighborhood obtained by screening to generate high-quality complete time series data. The spatial weight calculation subunit uses the Gaussian distance decay function to calculate the weight coefficient of each spatial position in the effective neighborhood. The closer the distance, the greater the contribution to the interpolation. The inverse distance weighted interpolation subunit implements the classic spatial interpolation algorithm and performs weighted average calculation of the time series data of each position in the neighborhood according to the spatial weight. In the case where the target position already has original observation data, the quality fusion processing subunit intelligently fuses the quality score of the original data with the interpolation result, retaining the authenticity of the original data while using spatial information to enhance the quality. The integrity verification subunit performs quality checks on the generated complete time series to ensure that all time points have corresponding values ​​and mark the source and processing method of each data point.

[0185] The analysis and reporting module conducts in-depth spatiotemporal change analysis on complete time series data, generating comprehensive analysis reports and visualizations. The time domain decomposition subunit utilizes advanced algorithms such as empirical mode decomposition and wavelet decomposition to decompose the time series into its components, identifying trend, cyclical, and random components, and revealing the inherent structural characteristics of the time series. The spatial autocorrelation analysis subunit employs spatial statistical methods such as the Moran's I index and Geary's C index to analyze correlations between spatial locations and identify clusters of locations with similar change patterns. The cluster analysis subunit employs methods such as K-means clustering and hierarchical clustering to cluster similar locations into spatial regions, forming geographically meaningful spatial partitions. The spatiotemporal evolution analysis subunit classifies spatiotemporal evolution processes at the regional level based on the identified spatial regions, constructing a Markov chain model to describe the transition relationships between regions. The report generation subunit integrates the analysis results into a structured report, including identification of hotspots, prediction of evolutionary trends, detection of abnormal changes, and statistical summary information. The visualization output subunit generates a variety of charts and maps, including spatiotemporal change trajectory maps, trend intensity distribution maps, pattern partition maps, and anomaly detection result maps, supporting output in multiple image formats. The system also provides a flexible data interface, supporting output in multiple formats such as JSON, XML, and GeoJSON, facilitating integration with other geographic information systems and data analysis platforms.

[0186] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for intelligent analysis of geographic information surveying and mapping data, characterized in that: include: S1. Determine the area to be analyzed, obtain geographic information surveying and mapping data within the area to be analyzed, including spatial coordinates, timestamps, and attribute value information, standardize the data points, and generate a data quality score; S2. Gridding the area to be analyzed to form multiple spatial locations, assigning the standardized data points to the corresponding spatial locations according to spatial coordinates, arranging the corresponding data points for each spatial location according to timestamps and attribute values ​​to construct a time series, and extracting multi-dimensional trend feature vectors in different time windows based on the time series; S3. For each spatial location, an initial candidate neighborhood is constructed based on the spatial distance. The data quality score is used to screen the initial candidate neighborhood to eliminate unqualified locations. When the number of candidate neighbors is insufficient, an adaptive expansion mechanism is used to reconstruct the neighborhood to obtain the final candidate neighborhood. S4. Calculate the trend feature matching degree between each candidate neighbor in the final candidate neighborhood and the target spatial position based on the multi-dimensional trend feature vector, determine the optimal similarity threshold, and screen to obtain a valid neighborhood; S5. Interpolate the time series of the target spatial position based on the valid neighborhood to obtain a complete time series for each spatial position; S6. Analyze the spatiotemporal change patterns of the complete time series, identify the spatiotemporal evolution laws and generate a spatiotemporal change analysis report.

2. The method for intelligent analysis of geographic information surveying and mapping data according to claim 1, characterized in that: Step S1 includes: S11. Standardize the format of geographic information surveying and mapping data and unify the coordinate system and time base; S12. Establish an R-tree spatial index structure to support efficient spatial neighborhood queries; S13, using Tukey fence method to identify and handle abnormal data points; S14. Calculate the quality score of each data point based on data completeness, temporal density, and spatial coverage; S15. Associate and store the standardized data points with the corresponding data quality scores.

3. The method for intelligent analysis of geographic information surveying and mapping data according to claim 1, characterized in that: Step S2 includes: S21, determining a grid resolution according to the range of the area to be analyzed and the data density, and dividing the area to be analyzed into regular grids to form multiple spatial locations; S22, establishing a mapping relationship between spatial positions and data points, and assigning the normalized data points to corresponding grid spatial positions according to their spatial coordinates; S23. For each spatial location, all data points belonging to it are collected, sorted by timestamp, and a time series of the location is constructed by combining attribute value information; S24. For each spatial location, three different time windows, short-term, medium-term, and long-term, are set. In each time window, the linear trend slope is calculated using the least squares method and the second-order curvature features are extracted using local weighted polynomial fitting. The features of the three time windows are combined to construct a six-dimensional multidimensional trend feature vector.

4. The method for intelligent analysis of geographic information surveying and mapping data according to claim 3, characterized in that: The formula for calculating the slope of a linear trend is: Among them, i is the spatial position index, w k ,k={1,2,3} is the time window, is the spatial position i in the time window w k The linear trend slope within n is the slope of the spatial position i in the time window w. k The number of data points in the V, t is the timestamp of the data point, i (t) is the attribute value of the data point corresponding to spatial position i at timestamp t, Represents the spatial position i in the time window w k The timestamp collection of all data points in .

5. The method for intelligent analysis of geographic information surveying and mapping data according to claim 3, characterized in that: Step S3 includes: S31, taking each spatial position as the target spatial position in turn, and selecting other adjacent spatial positions based on the Euclidean distance sorting with the target spatial position as the center to construct an initial candidate neighborhood; S32. For each candidate spatial location in the initial candidate neighborhood, calculate a comprehensive quality score for the spatial location based on the data quality score of its belonging data point, and eliminate spatial locations with a comprehensive quality score below a quality threshold; S33. When the number of candidate spatial locations after screening is less than the preset minimum value, the adaptive expansion mechanism is started to gradually expand the search radius and reconstruct to obtain the final candidate neighborhood that meets the quantity requirements.

6. The method for intelligent analysis of geographic information surveying and mapping data according to claim 5, characterized in that: Step S4 includes: S41, extracting the common time period between each candidate spatial position and the target spatial position in the final candidate neighborhood; S42, recalculating the multi-dimensional trend feature vectors of the two based on the common time period; S43, calculating the trend matching degree based on the linear trend slope, and calculating the comprehensive similarity based on the recalculated multi-dimensional trend feature vector; S44, determining the optimal similarity threshold and neighborhood number parameters; S45. Filter candidate spatial positions according to the optimal similarity threshold, and select the first several positions to form a valid neighborhood by sorting them in descending order of comprehensive similarity.

7. The method for intelligent analysis of geographic information surveying and mapping data according to claim 6, characterized in that: The calculation formula of trend matching degree M(i,j) is: Among them, w k ,k={1,2,3} is the time window, and They are spatial position i and spatial position j in time window w respectively k The slope of the linear trend in ,∈ is a small positive number to prevent the denominator from being zero; The calculation formula of comprehensive similarity S(i,j) is: S(i,j)=α1·M(i,j)+α2·|cos(v′ i ,v′ j )| Among them, v′ i and v′ j are the multi-dimensional trend feature vectors recalculated based on the common time period for spatial position i and spatial position j, cos(v′i,v′j) is the cosine similarity of v′i and v′j, α1 and α2 are the weights of trend matching and cosine similarity, and α1+α2=1, α1, α2>0.

8. The method for intelligent analysis of geographic information surveying and mapping data according to claim 6, characterized in that: Step S5 includes: S51, calculating the spatial distance weight from each spatial position in the valid neighborhood to the target spatial position; S52, using the inverse distance weighted method to perform spatial interpolation calculation on the time series of each spatial position in the effective neighborhood; S53. When original time series data exists at the target spatial location, weighted fusion is performed based on the comprehensive quality score of the time series and the interpolation result; S54. Use the fusion or interpolation result as the complete time series of the spatial position.

9. The method for intelligent analysis of geographic information surveying and mapping data according to claim 6, characterized in that: Step S6 includes: S61. Perform time domain decomposition on the complete time series of each spatial location to identify the trend component, periodic component, and random component of each spatial location; S62. Identify spatial locations with similar change patterns and aggregate them into spatial regions through spatial autocorrelation analysis; S63. Classify and identify the spatiotemporal evolution process at the regional level based on the identified spatial regions; S64. Organize the analysis results by spatial region and generate a spatiotemporal change analysis report for the area to be analyzed, including change hotspot areas, evolution trend prediction, and abnormal change detection.

10. A geographic information surveying and mapping data intelligent analysis system, characterized in that: The system is used to implement the method according to any one of claims 1 to 9, and the system includes: Data preprocessing module, used to standardize the format of input geographic information surveying and mapping data, process abnormal data and calculate quality scores; Grid processing module, used to divide the area to be analyzed into regular grids and construct time series; The neighborhood construction module is used to construct candidate neighborhoods for each target spatial location, perform quality screening, and output the final candidate neighborhoods for each spatial location; Feature matching module, used to calculate the trend feature matching degree of spatial positions in candidate neighborhoods and screen valid neighborhoods; The interpolation processing module is used to perform time series interpolation or fusion processing based on the valid neighborhood and output a complete time series; The analysis report module is used to perform spatiotemporal change analysis and generate analysis reports.

Images