A data analysis and presentation method, device and electronic equipment based on GIS

Abstract

The present application provides a data analysis and presentation method, device and electronic device based on GIS, which effectively improves the accuracy and efficiency of geoscientific information processing and the spatial expression ability of data by accurately decomposing the geographic spatial vector sequence into the first mode decomposition vector subsequence and the second mode decomposition vector subsequence of different feature scales, and intelligently fuses them based on the spatial correlation of the units, not only realizing the deep mining and integration of large-scale geoscientific data, but also ensuring the consistency and comparability of data in the geographic space through geographic registration and standardization, laying a solid foundation for subsequent spatial analysis modeling. The accurate generation and intuitive presentation of spatial analysis modeling results greatly enhance the application value of the geoscientific information system, thereby significantly improving the processing efficiency, analysis accuracy and visualization effect of the geoscientific information system data, and providing data support for the in-depth research and wide application of geoscientific information.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more specifically, to a GIS-based data analysis and presentation method, device, and electronic device. Background Art

[0002] With the rapid development of geographic information system (GIS) technology, the ability to collect, store, process and analyze geospatial data has been significantly improved. Geospatial information system datasets usually contain a large amount of complex and multidimensional geospatial data, which has extremely high application value in many fields such as urban planning, environmental monitoring, resource exploration, disaster assessment, etc. However, traditional data analysis methods face many challenges when dealing with such large and diverse geospatial data, such as data redundancy, difficulty in feature extraction, insufficient spatial correlation analysis, etc., resulting in low data analysis efficiency and difficulty in ensuring the accuracy of results.

[0003] Existing GIS data analysis methods often focus on the processing and display of a single type of data, lacking in-depth exploration of the complex relationships between different types of geoscientific information units. In addition, due to the diverse sources and formats of data, data integration often requires tedious preprocessing, including coordinate conversion, data cleaning, format unification, etc. These steps are not only time-consuming and laborious, but may also introduce new errors. Therefore, it is particularly important to develop a GIS data analysis method that can efficiently integrate multiple geoscientific information units, automatically extract key features, and accurately analyze spatial relationships. Summary of the invention

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present application, the present application embodiment provides a GIS-based data analysis and presentation method, the method comprising:

[0005] Obtaining a sequence of geospatial vectors of geospatial information units in a geospatial information system data set to be processed;

[0006] Decomposing the geographic space vector sequence to generate a first mode decomposition vector subsequence of the geographic information unit and a second mode decomposition vector subsequence of the geographic information unit, wherein the feature scale of the first mode decomposition vector subsequence is greater than the feature scale of the second mode decomposition vector subsequence;

[0007] The first mode decomposition vector subsequences of the local geomatic information units are fused according to the unit space association of the local geomatic information units to generate an inter-unit fusion vector sequence corresponding to the first mode decomposition vector subsequence;

[0008] Performing geo-reference and standardization processing on the inter-unit fusion vector sequence to generate a fusion standardized vector sequence, and performing geo-reference and standardization processing on the second mode decomposition vector subsequences of each geo-information unit to generate a target standardized vector sequence;

[0009] Spatial analysis modeling is performed based on the fused standardized vector sequence and the target standardized vector sequence to generate a spatial analysis modeling result of the geoscientific information system data set to be processed, and the spatial analysis modeling result of the geoscientific information system data set to be processed is presented.

[0010] On the other hand, an embodiment of the present application also provides a GIS-based data analysis and presentation device, which is used to store programs, instructions or codes. When the programs, instructions or codes in the memory are executed, the above-mentioned method is implemented.

[0011] On the other hand, an embodiment of the present application also provides an electronic device, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0012] Based on the above aspects, the embodiment of the present application effectively improves the accuracy and efficiency of geospatial information processing and the spatial expression ability of data by accurately decomposing the geographic spatial vector sequence into the first mode decomposition vector subsequence and the second mode decomposition vector subsequence of different feature scales, and intelligently fuses them based on the spatial correlation of the units, which not only realizes the deep mining and integration of large-scale geospatial data, but also ensures the consistency and comparability of data in the geographic space through geographic registration and standardization, laying a solid foundation for subsequent spatial analysis modeling. The accurate generation and intuitive presentation of spatial analysis modeling results greatly enhance the application value of the geospatial information system, thereby significantly improving the processing efficiency, analysis accuracy and visualization effect of the geospatial information system data, and providing data support for the in-depth research and wide application of geospatial information. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the execution flow of the GIS-based data analysis and presentation method provided in the embodiment of the present application.

[0014] Figure 2 It is a schematic diagram of the hardware architecture of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0015] The present application will be described in detail below with reference to the accompanying drawings. Figure 1This is a flow chart of a GIS-based data analysis and presentation method provided by an embodiment of the present application. The GIS-based data analysis and presentation method is introduced in detail below.

[0016] Step S110, obtaining a sequence of geographic space vectors of each geographic information unit in the geographic information system data set to be processed.

[0017] In detail, the geospatial information system data set to be processed is a data set containing a variety of geospatial information, usually derived from geographic information systems (GIS), remote sensing data, geological exploration data, etc. These data sets contain detailed information about the earth's surface and its features, such as topography, soil, rock, hydrology, vegetation, etc. The geospatial information unit is a component in the geospatial information data set, representing a specific type of geographical feature or phenomenon, such as terrain height, soil type, rock type, river distribution, etc. Each geospatial information unit contains a series of data points related to the feature. The geospatial vector sequence is a series of vector elements containing geospatial information, and each vector element usually contains a geographical location (such as longitude and latitude coordinates) and attribute information related to the location (such as height, soil type, etc.). These vector elements are arranged in a certain order or logic to form a sequence describing geographical features.

[0018] For example, in this embodiment, a geological information system data set about the geology and landform of a certain area is taken as an example. This geological information system data set covers a variety of geological information units such as terrain height, soil type, rock type, river distribution, etc. at different locations in the area.

[0019] For the terrain height, a geological information unit, the server reads relevant data from the data set. These data exist in the form of geospatial vectors, such as the longitude and latitude coordinates of each measurement point and the corresponding height value, forming a sequence of geospatial vectors. Taking a mountainous area as an example, the server may obtain a series of vector elements such as {(30.12, 120.34,500), (30.13, 120.35, 520), (30.14, 120.36, 480)}, where the first two values ​​represent the longitude and latitude coordinates, and the third value represents the terrain height of the coordinate point.

[0020] For soil type information units, vector data may be stored according to different sampling areas. For example, {(30.10, 120.30, 'clay'), (30.11, 120.31, 'sand'), (30.12, 120.32, 'loam')}, where the first two values ​​are coordinates and the third is soil type information.

[0021] The rock type information unit is similar, such as a sequence of geospatial vectors such as {(30.08, 120.28, 'Granite'), (30.09, 120.29, 'Limestone'), (30.10, 120.30, 'Shale')}.

[0022] For the river distribution information unit, the vector sequence may contain the representation of the river's flow direction, width, etc. in geographic space. For example, {(30.15, 120.37, 'Northwest-Southeast flow direction', 10), (30.16, 120.38, 'Southwest-Northeast flow direction', 8)}, where the last value represents the approximate width of the river at that coordinate point.

[0023] The server traverses the entire geospatial information system data set to be processed, extracts the geospatial vector data of each geospatial information unit, and forms a geospatial vector sequence of each geospatial information unit for subsequent processing.

[0024] Step S120, decomposing the geospatial vector sequence to generate a first mode decomposition vector subsequence of each geospatial information unit and a second mode decomposition vector subsequence of each geospatial information unit, wherein the feature scale of the first mode decomposition vector subsequence is greater than the feature scale of the second mode decomposition vector subsequence.

[0025] In detail, the first mode decomposition vector subsequence and the second mode decomposition vector subsequence are two parts into which the geographic space vector sequence is decomposed according to the feature scale (such as quantity, range, importance, etc.). The first mode decomposition vector subsequence contains elements with larger feature scale, which usually represent major or common geographic features; the second mode decomposition vector subsequence contains elements with smaller feature scale, which may represent outliers, rare features or edge cases.

[0026] For example, take the aforementioned geospatial vector sequence of terrain height information units {(30.12, 120.34,500), (30.13, 120.35, 520), (30.14, 120.36, 480)} as an example.

[0027] Specifically, it is assumed that the server determines, based on statistical analysis of terrain height data, that vector elements with height values ​​between 450 and 550 are the first decomposition feature intervals corresponding to the first mode decomposition vector subsequence, and that vector elements with height values ​​less than 450 or greater than 550 are the second decomposition feature intervals corresponding to the second mode decomposition vector subsequence.

[0028] According to the first decomposition feature interval, the server selects {(30.12, 120.34,500), (30.13, 120.35, 520), (30.14, 120.36, 480)} vector elements belonging to this interval from the geospatial vector sequence to form the first mode decomposition vector subsequence. The elements in this sequence have a relatively concentrated scale in the feature of terrain height, representing the situation of most terrain heights in the area.

[0029] For the second mode decomposition vector subsequence, the server selects elements that do not belong to the first decomposition feature interval from the geographic space vector sequence according to the second decomposition feature interval (in this example, there is no element that meets the condition temporarily).

[0030] Take the soil type information unit {(30.10, 120.30, 'clay'), (30.11, 120.31, 'sandy'), (30.12, 120.32, 'loam')} as an example.

[0031] Assume that the server determines, based on the distribution frequency of soil types and relevant geological factors, that the vector elements corresponding to 'clay' and 'loam', two soil types that are widely distributed in the area, belong to the interval corresponding to the first mode decomposition vector subsequence, while the vector elements corresponding to 'sand', a relatively rare soil type, belong to the interval corresponding to the second mode decomposition vector subsequence.

[0032] Then the first mode decomposition vector subsequence is {(30.10, 120.30, 'clay'), (30.12,120.32, 'loam')}, and the second mode decomposition vector subsequence is {(30.11, 120.31, 'sand')}.

[0033] For the rock type information unit {(30.08, 120.28, 'Granite'), (30.09, 120.29, 'Limestone'), (30.10, 120.30, 'Shale')}.

[0034] If the server determines that the vector elements corresponding to 'granite' and 'limestone' belong to the interval corresponding to the first mode decomposition vector subsequence based on factors such as the reserves and exposed area of ​​the rocks in the area, because they have larger scale characteristics in the area, the vector elements corresponding to 'shale' belong to the interval corresponding to the second mode decomposition vector subsequence.

[0035] Then the first mode decomposition vector subsequence is {(30.08, 120.28, 'granite'), (30.09, 120.29, 'limestone')}, and the second mode decomposition vector subsequence is {(30.10, 120.30, 'shale')}.

[0036] Step S130 , fusing the first pattern decomposition vector subsequences of the local geomatics information units according to the unit space association of the local geomatics information units to generate an inter-unit fusion vector sequence corresponding to the first pattern decomposition vector subsequence.

[0037] In detail, the unit spatial correlation is the degree of correlation between different geo-information units in spatial position. For example, soil type and terrain height in the same area often have spatial correlation because they affect each other in the same geographical area. The inter-unit fusion vector sequence is a sequence generated by fusing the first mode decomposition vector subsequences of different geo-information units with spatial correlation. This fusion is usually based on the matching and integration of multiple aspects such as spatial position and attribute characteristics.

[0038] For example, it is further assumed that the server decomposes the vector sub-sequences in the first mode of processing two geoscientific information units, namely, terrain height and soil type.

[0039] For the first mode decomposition vector subsequences of terrain height {(30.12, 120.34, 500), (30.13,120.35, 520), (30.14, 120.36, 480)} and for soil type {(30.10,120.30, 'clay'), (30.12, 120.32, 'loam')}.

[0040] The server sets the number of fused geo-information units to 2. Based on the spatial association of the units, the server determines that the terrain height vector (30.12, 120.34, 500) and the soil type vector (30.12, 120.32, 'loam') are spatially associated, forming an associated geo-information unit pair {(30.12, 120.34, 500), (30.12, 120.32, 'loam')}; similarly, the terrain height vector (30.13, 120.35, 520) and the soil type vector (30.10, 120.30, 'clay') may also be determined as an associated geo-information unit pair {(30.13, 120.35, 520), (30.10, 120.30, 'clay')} because of their spatial proximity.

[0041] For the associated geo-information unit pair {(30.12, 120.34, 500), (30.12, 120.32, 'loam')}, the server fuses the two vectors. For example, according to certain rules, such as combining the height value and the soil type into a new vector element {(30.12, 120.34, 500, 'loam')}, this generates an element in the inter-unit fusion vector sequence corresponding to the associated geo-information unit pair. Similarly, for the associated geo-information unit pair {(30.13, 120.35, 520), (30.10, 120.30, 'clay')}, the fused vector element may be {(30.13,120.35, 520, 'clay')}.

[0042] The server continues to poll other possible associated geoscience information unit pairs, and continuously generates elements in the inter-unit fusion vector sequence according to the above fusion method. For example, if there is a terrain height vector (30.14, 120.36, 480) that forms an associated geoscience information unit pair with other soil type vectors, the fusion operation is also performed according to the same rules, and finally the inter-unit fusion vector sequence corresponding to the complete first mode decomposition vector subsequence is generated.

[0043] Assume that when processing the first mode decomposition vector subsequences of terrain height and rock type, the first mode decomposition vector subsequence of terrain height is {(30.12, 120.34, 500), (30.13, 120.35, 520), (30.14,120.36, 480)}, and the first mode decomposition vector subsequence of rock type is {(30.08, 120.28, 'granite'),(30.09, 120.29, 'limestone')}.

[0044] According to the setting that the number of fused geo-information units is 2, according to the spatial correlation, the associated geo-information unit pairs {(30.12, 120.34, 500), (30.08, 120.28, 'granite')} and {(30.13, 120.35,520), (30.09, 120.29, 'limestone')} may be formed.

[0045] Then, these associated geological information unit pairs are fused, such as {(30.12, 120.34, 500, 'granite')} and {(30.13, 120.35, 520, 'limestone')}, and these fused vector elements are gradually combined into inter-unit fusion vector sequences.

[0046] Step S140 , geo-registering and standardizing the inter-unit fused vector sequence to generate a fused standardized vector sequence, and geo-registering and standardizing the second mode decomposition vector subsequences of each geo-information unit to generate a target standardized vector sequence.

[0047] In detail, the georeferencing and standardization process performs operations such as coordinate conversion, projection transformation, and attribute standardization on geospatial data to ensure that data from different sources and in different formats are spatially aligned and comparable in attributes, which is crucial for spatial analysis and modeling.

[0048] The fused standardized vector sequence and the target standardized vector sequence are data sequences that have been processed by geo-reference and standardization. The fused standardized vector sequence is the standardized result of the inter-unit fused vector sequence, while the target standardized vector sequence is the standardized result of the second mode decomposition vector subsequence. Together, they provide standardized data for spatial analysis modeling.

[0049] For example, in this embodiment, the server first obtains the sample geospatial vector sequence of each sample geospatial information unit. For example, for the fusion of terrain height and soil type mentioned above, the server has some pre-marked sample area data. In sample area 1, the sample geospatial vector sequence of terrain height and soil type may be {(30.05, 120.06, 450, 'clay'), (30.06, 120.07, 460, 'loam')}; in sample area 2, it may be {(30.07, 120.08, 470, 'clay')}, etc.

[0050] The server decomposes the sample geospatial vector sequence according to the characteristic scale of each vector element in the sample geospatial vector sequence. For the sequence {(30.05, 120.06, 450, 'clay'), (30.06,120.07, 460, 'loam')} of sample area 1, assuming that according to the distribution law of height value and soil type, the vector elements with height between 450 - 465 and soil type of 'clay' or 'loam' are divided into the first mode sample decomposition vector subsequence, which is {(30.05, 120.06, 450, 'clay'), (30.06, 120.07, 460, 'loam')}.

[0051] Then, the first mode sample decomposition vector subsequences of each sample geo-information unit are fused according to the unit spatial correlation of the sample geo-information unit. For example, for the above sequence of sample area 1, the two vector elements are directly fused (assuming that the fusion method is a simple combination) to obtain the sample fusion vector sequence {(30.05, 120.06,450, 'clay', 0.8), (30.06, 120.07, 460, 'loam', 0.9)}, where the last value is a coefficient calculated based on a certain degree of spatial correlation (such as the degree of matching between soil and terrain, etc.).

[0052] The server performs clustering learning based on these sample fusion vector sequences. For example, the sample fusion vector sequences are clustered according to features such as height, soil type, and correlation coefficient. Several first mode vector clusters may be obtained, such as cluster 1 containing vector elements with a height between 450 and 460, a soil type of 'clay', and a correlation coefficient between 0.7 and 0.9, and cluster 2 containing vector elements with a height between 460 and 470, a soil type of 'loam', and a correlation coefficient between 0.8 and 1, etc.

[0053] Finally, the fused geo-reference and standardization template is generated according to the cluster center features in each first pattern vector cluster. For example, the cluster center feature of cluster 1 is {(30.055, 120.065, 455, 'clay', 0.8)}, the cluster center feature of cluster 2 is {(30.065, 120.075, 465, 'loam', 0.9)}, etc. These cluster center features constitute the fused geo-reference and standardization template, which includes each fused geo-standardization code element.

[0054] Next, for the previously generated inter-unit fusion vector sequence, such as {(30.12, 120.34, 500, 'Loam')}, the server calculates the matching degree of this vector sequence with each fused geo-normalized codeword in the fused geo-referenced and normalized template. Assume that the matching degree is calculated based on multiple factors such as the distance of spatial coordinates and the similarity of feature values. For the codeword {(30.055, 120.065, 455, 'Clay', 0.8)} in the fused geo-referenced and normalized template, the matching degree is calculated to be 0.3; for the codeword {(30.065, 120.075, 465, 'Loam', 0.9)}, the matching degree is calculated to be 0.8.

[0055] The server determines the target fused geographic normalization codeword from each fused geographic normalization codeword according to the matching degree. In this example, the codeword {(30.065, 120.075, 465, 'Loam', 0.9)} has the highest matching degree, so it is used as the fused normalization vector sequence.

[0056] Let's continue to take the second mode decomposition vector subsequence {(30.11, 120.31, 'sand')} of the soil type information unit as an example. The server obtains the sample geospatial vector sequence of each sample geospatial information unit. Assume that in the sample area, there is a sample geospatial vector sequence such as {(30.09, 120.09, 'sand', 0.2)} (the last 0.2 here is a correlation coefficient).

[0057] The sample geospatial vector sequence is decomposed according to each vector element in the characteristic scale of the sample geospatial vector sequence to generate a second mode sample decomposition vector subsequence of each sample geospatial information unit. For example, for {(30.09,120.09, 'sand', 0.2)}, it is directly used as the second mode sample decomposition vector subsequence.

[0058] According to the second mode sample decomposition of each sample geoscience information unit, the vector subsequence is clustered and learned. Assume that all sample vector elements containing the type of "sand" are clustered into one cluster, and the characteristics of this cluster are the vector elements related to "sand".

[0059] A unit georeferencing and standardization template is generated according to the cluster center features in each second pattern vector cluster. For example, this template includes a unit georeferencing and standardization template such as {(30.09, 120.09, 'sand', 0.2)}.

[0060] Next, the server calculates the matching degree of the second mode decomposition vector subsequence {(30.11, 120.31, 'sand')} of the soil type information unit with the geo-referenced and standardized templates of each unit. Assume that the matching degree with {(30.09, 120.09, 'sand', 0.2)} is calculated to be 0.9.

[0061] The target unit georeferencing and standardization template are determined from the unit georeferencing and standardization templates according to the matching degree, and {(30.09, 120.09, 'sand', 0.2)} is used as the target standardized vector sequence.

[0062] The server polls the second mode decomposition vector subsequences of each geospatial information unit respectively. For example, for the second mode decomposition vector subsequence of the rock type information unit {(30.10, 120.30, 'shale')}, the server obtains the sample geospatial vector sequence in the same way, performs decomposition and clustering learning to generate unit geo-registration and standardized templates, and then calculates the matching degree to determine the target standardized vector sequence.

[0063] Step S150, performing spatial analysis modeling based on the fused standardized vector sequence and the target standardized vector sequence, generating a spatial analysis modeling result of the geoscientific information system data set to be processed, and presenting the spatial analysis modeling result of the geoscientific information system data set to be processed.

[0064] In this embodiment, for the fused standardized vector sequence, assuming that the fused standardized vector sequence is {(30.065, 120.075, 465, 'loam', 0.9)}, the server performs feature classification on it. The spatial coordinate (30.065, 120.075) can be classified as a spatial position feature, the height value 465 is a terrain height feature, 'loam' is a soil type feature, and 0.9 is a correlation degree feature.

[0065] For the target standardized vector sequence, for example, the target standardized vector sequence is {(30.09, 120.09, 'sand', 0.2)}, feature classification is also performed. (30.09, 120.09) is the spatial location feature, 'sand' is the soil type feature, and 0.2 is the correlation coefficient feature.

[0066] Next, based on the spatial structure features in the feature classification results of the fused standardized vector sequence, such as the relationship between the terrain height 465 and the spatial position (30.065, 120.075), the basic framework of the spatial relationship model is preliminarily constructed. The terrain height can be regarded as a variable in space, and a functional relationship is established with the spatial coordinates. For example, if it is assumed that in this small area, the terrain height increases with the increase of longitude and decreases with the increase of latitude, a simple mathematical expression is preliminarily constructed to express this relationship, which forms the basic framework of the spatial relationship model.

[0067] Then, combine some features in the feature classification results of the target standardized vector sequence, such as the comparative relationship between the soil type 'sand' and the 'loam' in the previously fused standardized vector sequence. If in this area, the distribution of 'sand' and 'loam' has a certain correlation with the terrain height, for example, 'sand' is mostly distributed in areas with higher terrain, and 'loam' is mostly distributed in areas with relatively flat terrain. Then integrate this relationship into the previous basic framework to generate an initial spatial relationship model framework that includes the relevant feature relationship between the fused standardized vector sequence and the target standardized vector sequence. This framework may include the distribution relationship of terrain height and soil type in space, as well as the mutual influence relationship between them.

[0068] Then, based on the framework of the initial spatial relationship model, the data in the fused standardized vector sequence and the target standardized vector sequence are feature-associated. For each vector element in the fused standardized vector sequence, a vector element with potential association with the vector element is searched in the target standardized vector sequence. For example, the spatial position (30.065, 120.075) corresponding to the terrain height 465 in the fused standardized vector sequence and the soil type 'loam', the distribution of the related 'sand' is searched in the target standardized vector sequence. If the terrain height change of 'sand' within a certain range of (30.065, 120.075) is found, the data of the vector elements with potential association are integrated to form an associated data group. For example, (30.065, 120.075, 465, 'loam') is combined with (30.09, 120.09, 'sand') and the related data within a certain range around them to form an associated data group. Then, these related data sets are arranged and organized in the initial spatial relationship model framework according to the set logical relationship, generating an integrated spatial relationship model framework containing the related data sets. This framework more comprehensively describes the spatial relationship between different geoscientific information units.

[0069] Then, the spatial analysis factors that have a key impact on the spatial analysis are screened out from the associated data groups in the integrated spatial relationship model framework. For example, the rate of change of terrain height, the transition boundary of soil type, etc. may be determined as key spatial analysis factors. The determined spatial analysis factors are analyzed and described to determine the factor description characteristics of each spatial analysis factor. For the spatial analysis factor of the rate of change of terrain height, its factor description characteristics include its specific meaning in spatial analysis (indicating the speed of the fluctuation of terrain in space), its scope of action (for example, in the entire study area or a sub-area), and its impact on other spatial analysis factors (such as the degree of soil erosion, the speed of water flow, etc.).

[0070] Then, based on the factor description characteristics of each spatial analysis factor, the existing association clues with the spatial analysis factor are determined from the integrated spatial relationship model framework. For example, there may be association clues between the terrain height change rate and the soil type conversion boundary, because the undulating changes in the terrain may lead to changes in soil type. Based on the determined association clues, a first spatial analysis factor relationship diagram is constructed, which shows the direct connection between the spatial analysis factors. For example, in the figure, the terrain height change rate and the soil type conversion boundary are connected by a line, indicating that there is a direct relationship between them.

[0071] Next, based on the first spatial analysis factor relationship graph, the nonlinear relationship between the spatial analysis factors is determined. For example, the relationship between the terrain height change rate and the degree of soil erosion may not be a simple linear relationship, but as the terrain height change rate increases, the degree of soil erosion presents a nonlinear relationship that first increases slowly and then increases rapidly. This nonlinear relationship information is integrated into the first spatial analysis factor relationship graph to generate a second spatial analysis factor relationship graph combined with nonlinear relationships. In this graph, in addition to lines representing direct connections, different line styles or colors can also be used to represent nonlinear relationships, such as using dotted lines to represent weak nonlinear relationships and using thick lines to represent strong nonlinear relationships.

[0072] For each spatial analysis factor, determine the change trend of the spatial analysis factor at different time scales and spatial scales. For example, the rate of change of terrain height may have different change trends in the long term (time scale of decades) and the short term (time scale of several years), and may also have different performances at large spatial scales (the entire region) and small spatial scales (a certain valley). Integrate the dynamic change factors associated with these change trends into the second spatial analysis factor relationship diagram to clarify the change pattern of each spatial analysis factor under different time and space conditions and the impact of this change pattern on the relationship between other factors, and generate the third spatial analysis factor relationship diagram after integrating the dynamic change factors. In this diagram, you can add time axes and labels of different spatial scales to represent dynamic change factors.

[0073] According to the third spatial analysis factor relationship diagram, the spatial analysis factors are used as the basic components of the main structure framework of the spatial analysis model, and the hierarchical structure of the main structure framework of the spatial analysis model is determined according to the relationship between the spatial analysis factors. For example, the terrain height change rate may be at a higher level because it affects many other factors, while the soil type conversion boundary may be at a relatively lower level. The main structure framework of the spatial analysis model is constructed, which describes in detail the relationship between the various spatial analysis factors and their hierarchical structure in the model.

[0074] Thus, the parameters in the main structure of the spatial analysis model are estimated using the data in the fused standardized vector sequence and the target standardized vector sequence. For example, the parameters of the relationship between the rate of change of terrain height and the degree of soil erosion are estimated based on the actual data of terrain height and soil type. The estimated parameters are calibrated, for example, by comparing with known actual measurement data or expert experience, adjusting the parameter values, and generating the final spatial analysis model after parameter estimation and calibration. The output result of this final spatial analysis model is the spatial analysis modeling result of the geoscience information system data set to be processed.

[0075] Finally, the server presents the results of spatial analysis modeling. This can be done graphically, such as drawing a three-dimensional graph of the relationship between terrain height and soil type, showing the terrain height, soil type and the relationship between them in different areas, while marking the key spatial analysis factors and their influence range; it can also be presented in a table to present the values ​​of each spatial analysis factor and the relationship between them, etc., to facilitate analysis and decision-making by geoscientists.

[0076] Based on the above steps, the embodiment of the present application effectively improves the accuracy and efficiency of geospatial information processing and the spatial expression ability of data by accurately decomposing the geographic spatial vector sequence into the first mode decomposition vector subsequence and the second mode decomposition vector subsequence of different feature scales, and intelligently fuses them based on the spatial correlation of the units, which not only realizes the deep mining and integration of large-scale geospatial data, but also ensures the consistency and comparability of data in the geographic space through geographic registration and standardization, laying a solid foundation for subsequent spatial analysis modeling. The accurate generation and intuitive presentation of spatial analysis modeling results greatly enhance the application value of the geospatial information system, thereby significantly improving the processing efficiency, analysis accuracy and visualization effect of the geospatial information system data, and providing data support for the in-depth research and wide application of geospatial information.

[0077] In a possible implementation, step S120 includes:

[0078] A first decomposition feature interval corresponding to the first pattern decomposition vector subsequence and a second decomposition feature interval corresponding to the second pattern decomposition vector subsequence are determined according to the feature scale of each vector element in the geographic space vector sequence.

[0079] Decomposing the geographic space vector sequence according to the first decomposition feature interval corresponding to the first pattern decomposition vector subsequence to generate the first pattern decomposition vector subsequence.

[0080] Decomposing the geographic space vector sequence according to the second decomposition feature interval corresponding to the second pattern decomposition vector subsequence to generate the second pattern decomposition vector subsequence.

[0081] In this embodiment, it is assumed that the server is processing a geospatial vector sequence of terrain height information units in a mountainous area. This sequence includes multiple vector elements, such as {(30.10, 120.30, 500), (30.11, 120.31, 550), (30.12, 120.32, 450), (30.13, 120.33, 600), (30.14, 120.34, 400)}.

[0082] The server analyzes the characteristic scale of these vector elements, where the characteristic scale is the terrain height value. After statistical analysis, it is found that most of the terrain heights in the area are concentrated between 450 and 550. Therefore, the server determines that the first decomposition characteristic interval corresponding to the first mode decomposition vector subsequence is [450, 550], and the second decomposition characteristic interval corresponding to the second mode decomposition vector subsequence is less than 450 or greater than 550.

[0083] According to the first decomposition feature interval [450, 550], the server selects {(30.10, 120.30, 500), (30.11, 120.31, 550), (30.12, 120.32, 450)} from the geospatial vector sequence as the first pattern decomposition vector subsequence.

[0084] According to the second decomposition feature interval, the server selects {(30.13, 120.33,600), (30.14, 120.34, 400)} from the geographic space vector sequence as the second pattern decomposition vector subsequence.

[0085] In addition, considering the soil type information unit, the geospatial vector sequence may be {(30.05, 120.05, 'loam'), (30.06, 120.06, 'clay'), (30.07, 120.07, 'sandy'), (30.08, 120.08, 'loam'), (30.09, 120.09, 'clay')}.

[0086] The server determines the feature scale based on the distribution ratio of soil types in the area. Assuming that "loam" and "clay" are widely distributed, they are considered as a scale feature. The server determines that the first decomposition feature interval corresponding to the first mode decomposition vector subsequence is a type containing "loam" and "clay", and the second decomposition feature interval corresponding to the second mode decomposition vector subsequence is a "sand" type.

[0087] According to the first decomposition feature interval, the server selects {(30.05, 120.05, 'loam'), (30.06, 120.06, 'clay'), (30.08, 120.08, 'loam'), (30.09, 120.09, 'clay')} from the geospatial vector sequence as the first pattern decomposition vector subsequence.

[0088] According to the second decomposition feature interval, the server selects {(30.07, 120.07, 'sand')} from the geographic space vector sequence as the second pattern decomposition vector subsequence.

[0089] In another possible implementation, the first pattern decomposition vector subsequence includes a set of spatial weight vectors, and the second pattern decomposition vector subsequence includes a set of non-spatial weight vectors.

[0090] Step S120 includes:

[0091] The spatial weight interval corresponding to the spatial weight vector set and the non-spatial weight intervals associated with each of the non-spatial weight vector sets are determined according to the characteristic scale of each vector element in the geographic spatial vector sequence.

[0092] Corresponding spatial weight values ​​are determined from the geographic spatial vector sequence according to the spatial weight interval, and the spatial weight values ​​are used as the spatial weight vector set.

[0093] Corresponding non-spatial weight values ​​are respectively determined from the geographic spatial vector sequence according to the non-spatial weight intervals associated with each of the non-spatial weight vector sets, and the non-spatial weight vector sets are determined according to the non-spatial weight values.

[0094] In this embodiment, for the geospatial information unit related to a river in a certain area, it is assumed that the geospatial vector sequence contains information such as river flow and water quality, such as {(30.20, 120.40, 100, 'good'), (30.21, 120.41, 50, 'medium'), (30.22, 120.42, 150, 'good'), (30.23, 120.43, 30, 'poor')}, where the first two values ​​are coordinates, the third value is the river flow (cubic meters per second), and the last value is the water quality condition.

[0095] The server considers river flow as a spatial weight factor and water quality as a non-spatial weight factor. After analyzing the characteristic scale of the vector elements, the spatial weight interval corresponding to the spatial weight vector set is determined to be [50, 150] (flow value), and the non-spatial weight interval associated with each non-spatial weight vector set (related to water quality) is determined according to the water quality classification, such as "good" as one interval, "medium" as one interval, and "poor" as one interval.

[0096] Based on the spatial weight interval [50, 150], the server determines the corresponding spatial weight values ​​from the sequence of geographic spatial vectors as {(30.20, 120.40, 100, 'good'), (30.21, 120.41, 50, 'medium'), (30.22,120.42, 150, 'good')} and uses these as the set of spatial weight vectors.

[0097] According to the non-spatial weight intervals associated with each non-spatial weight vector set, for the "good" interval, the corresponding non-spatial weight value is determined to be {(30.20, 120.40, 100, 'good'), (30.22, 120.42, 150, 'good')}, so as to determine the non-spatial weight vector set corresponding to "good"; similarly, the non-spatial weight vector sets corresponding to "medium" and "poor" are determined.

[0098] In another possible implementation, the first pattern decomposition vector subsequence includes a spatial weight vector set and respective first pattern non-spatial weight vector sets, and the second pattern decomposition vector subsequence includes respective second pattern non-spatial weight vector sets.

[0099] Step S120 includes:

[0100] The spatial weight interval corresponding to the spatial weight vector set, the first mode non-spatial weight interval associated with each of the first mode non-spatial weight vector sets, and the second mode non-spatial weight interval associated with each of the second mode non-spatial weight vector sets are determined based on the characteristic scale of each vector element in the geographic spatial vector sequence.

[0101] Corresponding spatial weight values ​​are determined from the geographic spatial vector sequence according to the spatial weight interval, and the spatial weight values ​​are used as the spatial weight vector set.

[0102] According to the first mode non-spatial weight intervals associated with each of the first mode non-spatial weight vector sets, corresponding first mode non-spatial weight values ​​are respectively determined from the geographic spatial vector sequence, and according to the first mode non-spatial weight values, each of the first mode non-spatial weight vector sets is determined.

[0103] According to the second mode non-spatial weight intervals associated with each of the second mode non-spatial weight vector sets, corresponding second mode non-spatial weight values ​​are respectively determined from the geographic spatial vector sequence, and according to the second mode non-spatial weight values, each of the second mode non-spatial weight vector sets is determined.

[0104] In this embodiment, it is assumed that the geographic space vector sequence of a certain area contains vegetation coverage, terrain slope and soil fertility information, such as {(30.30, 120.50, 0.6, 10, 'high'), (30.31, 120.51, 0.3, 20, 'medium'), (30.32, 120.52, 0.8, 5, 'high'), (30.33, 120.53, 0.2, 30, 'low')}, where the first two values ​​are coordinates, the third value is vegetation coverage (ranging from 0 to 1), the fourth value is terrain slope (degrees), and the last value is soil fertility (divided into high, medium and low).

[0105] The server determines the spatial weight interval corresponding to the spatial weight vector set. For example, the terrain slope is regarded as a spatial weight factor, and its spatial weight interval is determined to be [5, 20] (slope value). For the first mode non-spatial weight vector set, the vegetation coverage is regarded as a first mode non-spatial weight factor, and its respective associated first mode non-spatial weight interval is determined to be [0.3, 0.8]. For the second mode non-spatial weight vector set, soil fertility is regarded as a second mode non-spatial weight factor, and its respective associated second mode non-spatial weight interval is determined according to the fertility classification ("high", "medium", "low").

[0106] Based on the spatial weight interval [5, 20], the server determines the corresponding spatial weight values ​​from the sequence of geographic spatial vectors as {(30.30, 120.50, 0.6, 10, 'high'), (30.31, 120.51, 0.3, 20, 'medium')} and uses these as the set of spatial weight vectors.

[0107] According to the first mode non-spatial weight interval [0.3,0.8] associated with each first mode non-spatial weight vector set, the corresponding first mode non-spatial weight values ​​are determined from the geographic spatial vector sequence as {(30.30, 120.50,0.6, 10, 'high'), (30.31, 120.51, 0.3, 20, 'medium'), (30.32, 120.52, 0.8, 5, 'high')}, and each first mode non-spatial weight vector set is determined based on these values.

[0108] According to the second mode non-spatial weight intervals associated with each second mode non-spatial weight vector set, for the "high" interval, the corresponding second mode non-spatial weight value is determined to be {(30.30, 120.50, 0.6, 10, 'high'), (30.32, 120.52, 0.8, 5, 'high')}, so as to determine the second mode non-spatial weight vector set corresponding to "high"; similarly, the second mode non-spatial weight vector sets corresponding to "medium" and "low" are determined.

[0109] In a possible implementation, step S130 includes:

[0110] Step S131, obtaining the number of fused geoscientific information units, and determining a plurality of associated geoscientific information unit pairs from the geoscientific information units according to the unit spatial correlation of the geoscientific information units and the number of fused geoscientific information units, wherein the associated geoscientific information unit pairs include associated geoscientific information units of the number of fused geoscientific information units.

[0111] Step S132: fuse the first pattern decomposition vector subsequences associated with the associated geo-information units of the fused geo-information unit quantity to generate an inter-unit fusion vector sequence corresponding to the associated geo-information unit pair.

[0112] Step S133: poll the plurality of associated geoscientific information unit pairs to generate inter-unit fusion vector sequences associated with the plurality of associated geoscientific information unit pairs.

[0113] In a possible implementation, step S133 includes:

[0114] Step S1331, obtaining each unassociated geoscientific information unit. When the number of the unassociated geoscientific information units is less than the number of the fused geoscientific information units, determining the geoscientific information units to be supplemented from the unassociated geoscientific information units, and calculating the difference between the number of the fused geoscientific information units and the number of the unassociated geoscientific information units to generate the number to be supplemented.

[0115] Step S1332: perform a supplementation operation on the geoscientific information units to be supplemented according to the number to be supplemented to generate supplementation operation geoscientific information units, and perform a pairing operation on the unassociated geoscientific information units and the supplementation operation geoscientific information units to generate supplementation operation geoscientific information unit pairs.

[0116] Step S1333: fuse the first mode decomposition vector subsequences associated with each of the geoscientific information units in the supplementary operation geoscientific information unit pair to generate an inter-unit fusion vector sequence corresponding to the supplementary operation geoscientific information unit pair.

[0117] In this embodiment, it is still assumed that the server is processing the first mode decomposition vector subsequence of two geo-information units, namely, terrain height and soil type. The number of fused geo-information units is set to 2.

[0118] For the first mode decomposition vector subsequence of terrain height, it is assumed to be {(30.10, 120.30, 500), (30.11, 120.31, 520), (30.12, 120.32, 480)}, and the first mode decomposition vector subsequence of soil type is {(30.08, 120.28, 'clay'), (30.09, 120.29, 'loam'), (30.10, 120.30, 'clay')}.

[0119] Based on the spatial association of the cells, the server determines that the terrain height vector (30.10, 120.30, 500) and the soil type vector (30.10, 120.30, 'clay') are spatially associated because they have the same coordinates (30.10, 120.30), forming an associated geo-information cell pair {(30.10, 120.30, 500), (30.10, 120.30, 'clay')}.

[0120] Similarly, the terrain height vector (30.11, 120.31, 520) and the soil type vector (30.09, 120.29, 'loam') may also be determined as an associated geo-information unit pair {(30.11, 120.31, 520), (30.09, 120.29, 'loam')} due to their spatial proximity (for example, within a certain distance threshold).

[0121] Next, for the associated geoscience information unit pair {(30.10, 120.30, 500), (30.10, 120.30, 'clay')}, the server fuses the two vectors. For example, the terrain height value and soil type can be combined into a new vector element {(30.10, 120.30, 500, 'clay')} according to certain rules, which generates an element in the inter-unit fusion vector sequence corresponding to the associated geoscience information unit pair.

[0122] For the associated geoscience information unit pair {(30.11, 120.31, 520), (30.09, 120.29, 'loam')}, the fused vector element may be {(30.11, 120.31, 520, 'loam')}.

[0123] For the vegetation and precipitation information unit example, the first mode decomposition vector subsequences of the two geoscience information units, vegetation coverage and precipitation, are considered, and the number of fused geoscience information units is also set to 2.

[0124] The first mode decomposition vector subsequence of vegetation cover may be {(30.20, 120.40, 0.6), (30.21, 120.41, 0.4), (30.22, 120.42, 0.8)}, and the first mode decomposition vector subsequence of precipitation is {(30.19, 120.39, 50), (30.20, 120.40, 80), (30.21, 120.41, 40)} (the values ​​here are the millimeters of precipitation).

[0125] According to the spatial correlation of the units, the server determines that the vegetation coverage vector (30.20, 120.40, 0.6) and the precipitation vector (30.20, 120.40, 80) are spatially correlated, forming a correlated geoscience information unit pair {(30.20, 120.40, 0.6), (30.20, 120.40, 80)}.

[0126] The vegetation coverage vector (30.21, 120.41, 0.4) and the precipitation vector (30.21, 120.41, 40) are also identified as the associated geoscientific information unit pair {(30.21, 120.41, 0.4), (30.21,120.41, 40)} because of the same coordinates.

[0127] For the associated geoscientific information unit pair {(30.20, 120.40, 0.6), (30.20, 120.40, 80)}, the server follows a certain fusion rule, such as combining vegetation coverage and precipitation into a new vector element {(30.20,120.40, 0.6, 80)}, which becomes an element in the inter-unit fusion vector sequence.

[0128] For the associated geographic information unit pair {(30.21, 120.41, 0.4), (30.21, 120.41, 40)}, the fused vector element is {(30.21, 120.41, 0.4, 40)}.

[0129] On this basis, the server continues to poll other possible associated geoscientific information unit pairs, and continuously generates elements in the inter-unit fusion vector sequence according to the above fusion method.

[0130] For example, in the example of terrain and soil, if there is a terrain height vector (30.12, 120.32, 480) and a soil type vector (30.08, 120.28, 'clay') forming an associated geoscience information unit pair, the fusion operation is also performed according to the same rule, and finally a complete inter-unit fusion vector sequence corresponding to the first mode decomposition vector subsequence is generated.

[0131] For example, in the example of vegetation and precipitation, if there is a vegetation coverage vector (30.22, 120.42, 0.8) that forms an associated geoscientific information unit pair with other precipitation vectors, a fusion operation is also performed to gradually construct a complete inter-unit fusion vector sequence.

[0132] In order to deal with the situation where the number of unassociated geo-information units is insufficient, it is assumed that when the server processes the first mode decomposition vector subsequence of the three geo-information units of terrain height, soil type and rock type, the number of fused geo-information units is set to 3. During the processing, some associated geo-information unit pairs may have been determined, and some unassociated geo-information units remain. For example, the unassociated vector of terrain height may be {(30.15, 120.35, 550)}, the unassociated vector of soil type is {(30.13, 120.33, 'sand')}, and the unassociated vector of rock type is {(30.14,120.34, 'granite')}. Since the number of unassociated geo-information units is 3, which is less than the number of fused geo-information units 3. The server determines the geo-information units to be supplemented from these unassociated geo-information units. For example, the terrain height vector (30.15, 120.35, 550) can be selected as the geo-information unit to be supplemented. Calculate the difference between the number of fused geoscientific information units and the number of unassociated geoscientific information units, that is, 3 - 3 = 0, and generate a number to be supplemented of 0.

[0133] Among them, although the number to be supplemented is 0, the operation is still performed according to the rules. The geoscience information unit to be supplemented (30.15, 120.35, 550) is supplemented (this may be just a formal operation, because actual supplementation is not required) to generate a supplement operation geoscience information unit.

[0134] According to the unrelated geo-information units {(30.15, 120.35, 550), (30.13, 120.33, 'sand'), (30.14, 120.34, 'granite')} and the supplementary operation geo-information units, the supplementary operation geo-information unit pairs are generated. For example, the supplementary operation geo-information unit pair {(30.15, 120.35, 550), (30.13, 120.33, 'sand'), (30.14,120.34, 'granite')}.

[0135] The first mode decomposition vector subsequences associated with each geoscientific information unit in the supplementary operation geoscientific information unit pair are fused. Assuming that according to a certain fusion rule, the fused vector element may be {(30.15, 120.35, 550, 'sand', 'granite')}, which generates the inter-unit fusion vector sequence corresponding to the supplementary operation geoscientific information unit pair.

[0136] Furthermore, for the first mode decomposition vector subsequences of the three geo-information units of vegetation coverage, precipitation and temperature, the number of fused geo-information units is set to 3. Assume that after the partial association operation, the unassociated vector of vegetation coverage is {(30.30, 120.50, 0.3)}, the unassociated vector of precipitation is {(30.29, 120.49, 30)}, and the unassociated vector of temperature is {(30.31, 120.51, 20)} (the temperature value here is in degrees Celsius). The number of unassociated geo-information units is 3, which is equal to the number of fused geo-information units 3. It is assumed here that the operation is still carried out according to the process. The vegetation coverage vector (30.30, 120.50, 0.3) is selected as the geo-information unit to be supplemented. Calculate the difference between the number of fused geo-information units and the number of unassociated geo-information units, that is, 3 - 3 = 0, and generate a number to be supplemented of 0.

[0137] After the vegetation coverage vector (30.30, 120.50, 0.3) is supplemented, the supplemented geo-information unit pairs {(30.30, 120.50, 0.3), (30.29, 120.49, 30), (30.31,120.51, 20)} are generated according to the unassociated geo-information units {(30.30, 120.50, 0.3), (30.29, 120.49, 30), (30.31,120.51, 20)}.

[0138] The first mode decomposition vector subsequences associated with each geoscientific information unit in the supplementary operation geoscientific information unit pair are fused. According to the fusion rule, the fused vector element may be {(30.30, 120.50, 0.3, 30,20)}, generating an inter-unit fusion vector sequence corresponding to the supplementary operation geoscientific information unit pair.

[0139] Therefore, according to the spatial correlation of each geoscientific information unit, the first mode decomposition vector subsequence can be fused to generate a corresponding inter-unit fusion vector sequence, which can ensure the integrity and accuracy of the processing regardless of normal situations or special situations where the number of uncorrelated geoscientific information units is insufficient.

[0140] In a possible implementation, the geo-registering and standardizing the inter-unit fused vector sequence to generate a fused standardized vector sequence includes:

[0141] A fused geographic registration and normalization template corresponding to the inter-unit fused vector sequence is obtained, wherein the fused geographic registration and normalization template includes each fused geographic normalization symbol.

[0142] The matching degrees between the inter-unit fusion vector sequences and the fused geographic normalization symbols are calculated, and a target fused geographic normalization symbol is determined from the fused geographic normalization symbols according to the matching degrees.

[0143] The target fused geographic normalization symbol is used as the fused normalization vector sequence.

[0144] The step of obtaining the fused geographic registration and standardization template corresponding to the inter-unit fused vector sequence includes:

[0145] Get the sample geospatial vector sequence of each sample geo-information unit.

[0146] The sample geospatial vector sequence is decomposed according to the characteristic scale of each vector element in the sample geospatial vector sequence to generate a first mode sample decomposed vector subsequence of each sample geospatial information unit.

[0147] The first pattern sample decomposition vector subsequences of the sample geo-information units are fused according to the unit space correlation of the sample geo-information units to generate sample fusion vector sequences.

[0148] Cluster learning is performed based on the sample fusion vector sequences to generate first pattern vector clusters, and the fusion geo-registration and standardization template is generated based on cluster center features in the first pattern vector clusters.

[0149] In this embodiment, for the geo-registration and standardization of the inter-unit fusion vector sequence, taking the fusion of terrain height and soil type as an example, the server obtains sample geospatial vector sequences of multiple sample areas. In sample area 1, the sample geospatial vector sequence of terrain height and soil type may be {(30.05, 120.06, 450, 'clay'), (30.06, 120.07, 460, 'loam'), (30.07, 120.08, 470, 'clay')}. In sample area 2, the sample geospatial vector sequence may be {(30.08, 120.09, 480, 'loam'), (30.09, 120.10,490, 'clay')}.

[0150] Next, for the sequence {(30.05, 120.06, 450, 'clay'), (30.06,120.07, 460, 'loam'), (30.07, 120.08, 470, 'clay')} of sample area 1, the server determines the feature scale based on the distribution pattern of terrain height and soil type.

[0151] Assume that according to the distribution law of height values ​​and soil types, the vector elements with heights between 450 and 470 and soil types of 'clay' or 'loam' are divided into the first mode sample decomposition vector subsequence, which is {(30.05,120.06, 450, 'clay'), (30.06, 120.07, 460, 'loam'), (30.07, 120.08, 470, 'clay')}.

[0152] For the sequence of sample area 2 {(30.08, 120.09, 480, 'loam'), (30.09, 120.10,490, 'clay')}, also according to the above rules, the first mode sample decomposition vector subsequence is determined to be {(30.08,120.09, 480, 'loam'), (30.09, 120.10, 490, 'clay')}.

[0153] Then, in sample area 1, for the first mode sample decomposition vector subsequence {(30.05, 120.06,450, 'clay'), (30.06, 120.07, 460, 'loam'), (30.07, 120.08, 470, 'clay')}, the server performs fusion according to spatial correlation.

[0154] For example, by combining adjacent vector elements according to certain rules, we can obtain the sample fusion vector sequence {(30.05,120.06, 450, 'clay', 0.8), (30.06, 120.07, 460, 'loam', 0.9), (30.07, 120.08,470, 'clay', 0.8)}, where the last value is a coefficient calculated based on a certain degree of spatial association (such as the degree of matching between soil and terrain).

[0155] In sample area 2, {(30.08, 120.09, 480, 'loam'), (30.09, 120.10, 490, 'clay')} are fused to obtain the sample fusion vector sequence {(30.08, 120.09, 480, 'loam', 0.9), (30.09, 120.10, 490, 'clay', 0.8)}.

[0156] Next, the server clusters the sample fusion vector sequences {(30.05, 120.06,450, 'clay', 0.8), (30.06, 120.07, 460, 'loam', 0.9), (30.07, 120.08, 470, 'clay', 0.8), (30.08, 120.09, 480, 'loam', 0.9), (30.09, 120.10, 490, 'clay',0.8)} of sample area 1 and sample area 2.

[0157] Clustering is performed based on features such as terrain height, soil type, and correlation coefficient. Several first mode vector clusters may be obtained, such as cluster 1 contains vector elements with a height between 450 and 460, a soil type of 'clay', and a correlation coefficient between 0.7 and 0.9, and cluster 2 contains vector elements with a height between 480 and 490, a soil type of 'loam', and a correlation coefficient between 0.8 and 1, etc.

[0158] Generate a fused geo-referenced and normalized template based on the cluster center features in each first pattern vector cluster. For example, the cluster center features of cluster 1 are {(30.055, 120.065, 455, 'clay', 0.8)}, the cluster center features of cluster 2 are {(30.085,120.095, 485, 'loam', 0.9)}, etc. These cluster center features constitute a fused geo-referenced and normalized template, which includes each fused geo-normalized code element.

[0159] Therefore, it is assumed that the previously generated inter-unit fusion vector sequence is {(30.12, 120.34, 500, 'loam')}.

[0160] The server calculates the matching degree between the vector sequence and each fused geo-normalization code element in the fused geo-registration and normalization template.

[0161] For the code element {(30.055, 120.065, 455, 'clay', 0.8)} in the fused georeferencing and normalization template, the calculation of the match may involve multiple factors.

[0162] In terms of spatial coordinates, the distance difference between (30.12, 120.34) and (30.055, 120.065) is calculated, and a coordinate matching value is calculated based on a certain distance weight; in terms of terrain height, the difference between 500 and 455 is calculated, and a height matching value is calculated based on the height difference weight; in terms of soil type, because 'loam' and 'clay' are different, a soil type matching value is calculated based on the soil type difference weight; in terms of association degree, the difference between the default association degree (assuming it is 0.5) and 0.8 is compared, and a correlation degree matching value is calculated based on the association degree weight. Combining these aspects, the matching degree with the code element {(30.055, 120.065, 455, 'clay', 0.8)} is calculated to be 0.3 through weighted summation and other methods.

[0163] For the code element {(30.085, 120.095, 485, 'Loam', 0.9)}, the matching degree is calculated in the same way as above. After comprehensive calculation of factors such as spatial coordinate distance, terrain height difference, same soil type (higher matching degree), and degree of association, the matching degree is 0.8.

[0164] Next, the server determines a target fused geographic normalization codeword from each fused geographic normalization codeword according to the calculated matching degree.

[0165] In the above example, the code element {(30.085, 120.095, 485, 'Loam', 0.9)} has the highest matching degree, so it is used as the fused normalized vector sequence.

[0166] In a possible implementation manner, the step of performing geo-registration and standardization processing on the second mode decomposition vector subsequences of the geo-information units to generate a target standardized vector sequence includes:

[0167] The unit geographic registration and standardization template corresponding to the second pattern decomposition vector subsequence is obtained, wherein the unit geographic registration and standardization template includes each unit geographic registration and standardization template.

[0168] Calculate the matching degree between the second pattern decomposition vector subsequence and each unit geo-reference and standardization template respectively, and determine the target unit geo-reference and standardization template from each unit geo-reference and standardization template according to the matching degree, and use the target unit geo-reference and standardization template as the target standardization vector sequence.

[0169] The second mode decomposition vector subsequences of the local geomatics information units are polled respectively to generate target standardized vector sequences of the local geomatics information units.

[0170] The step of obtaining the unit geo-registration and standardization template corresponding to the second mode decomposition vector subsequence includes:

[0171] Get the sample geospatial vector sequence of each sample geo-information unit.

[0172] The sample geospatial vector sequence is decomposed according to each vector element in the characteristic scale of the sample geospatial vector sequence to generate a second mode sample decomposed vector subsequence of each sample geospatial information unit.

[0173] Cluster learning is performed based on the second pattern sample decomposition vector subsequence of each sample geoscientific information unit to generate each second pattern vector cluster, and the unit geographic registration and standardization template is generated based on the cluster center features in each second pattern vector cluster.

[0174] In this embodiment, the second mode decomposition vector subsequence of each geoscientific information unit is geo-referenced and standardized, taking the second mode decomposition vector subsequence of the soil type information unit {(30.11, 120.31, 'sand')} as an example. The server obtains the sample geospatial vector sequence of each sample geoscientific information unit. In the sample area, there is a sample geospatial vector sequence such as {(30.09, 120.09, 'sand', 0.2)} (the last 0.2 here is a certain correlation coefficient). In another sample area, there may be a sample geospatial vector sequence such as {(30.10, 120.10, 'sand', 0.3)}.

[0175] For {(30.09, 120.09, 'sand', 0.2)}, it is directly used as the second mode sample to decompose the vector subsequence.

[0176] For {(30.10, 120.10, 'sand', 0.3)}, it is also decomposed into vector subsequences as the second mode sample.

[0177] Then, the server performs cluster learning on these sample vector elements {(30.09, 120.09, 'Sand', 0.2), (30.10, 120.10, 'Sand', 0.3)} containing the 'sand' type.

[0178] Since they are all of the 'sand soil' type, they may be clustered into a cluster, and the characteristics of this cluster are the vector elements related to 'sand soil'.

[0179] Generate a unit georeferencing and normalization template based on the cluster center features in this cluster. For example, this template contains a unit georeferencing and normalization template such as {(30.09, 120.09, 'sand', 0.2)}.

[0180] On this basis, the server calculates the matching degree of the second mode decomposition vector subsequence {(30.11, 120.31, 'sand')} of the soil type information unit with the geo-referenced and standardized templates of each unit respectively.

[0181] For the unit georeferencing and the standardized template {(30.09, 120.09, 'sand', 0.2)}, in terms of spatial coordinates, the distance difference between (30.11, 120.31) and (30.09, 120.09) is calculated, and a coordinate matching value is calculated based on the coordinate distance weight; the soil type is the same (higher matching), and in terms of correlation coefficient, the difference between the default correlation coefficient (assuming it is 0.5) and 0.2 is compared, and a correlation coefficient matching value is calculated based on the correlation coefficient weight. Combining these aspects, the matching degree is calculated to be 0.9 through weighted summation and other methods.

[0182] Then, the target unit georeferencing and normalization template are determined from each unit georeferencing and normalization template according to the matching degree, and {(30.09, 120.09, 'sand', 0.2)} is used as the target normalization vector sequence.

[0183] For other geological information units, such as the second mode decomposition vector subsequence of the rock type information unit {(30.10, 120.30, 'shale')}.

[0184] The processing is performed according to the above steps of obtaining a sample geospatial vector sequence, decomposing and clustering learning to generate unit geo-registration and standardized templates, and then calculating the matching degree to determine the target standardized vector sequence.

[0185] For example, obtain a sample geospatial vector sequence containing 'shale', perform decomposition and clustering learning to obtain unit geo-registration and standardized templates, and then calculate the matching degree between {(30.10, 120.30, 'shale')} and the template to determine the target standardized vector sequence.

[0186] In this way, the inter-unit fusion vector sequence and the second mode decomposition vector subsequence of each geospatial information unit can be geo-referenced and standardized to generate a fusion standardized vector sequence and a target standardized vector sequence, respectively, thereby providing a standardized data basis for subsequent spatial analysis modeling and other operations.

[0187] For example, in a possible implementation, step S150 includes:

[0188] Step S151 , performing feature classification on the fused normalized vector sequence and the target normalized vector sequence, and obtaining a feature classification result of the fused normalized vector sequence and a feature classification result of the target normalized vector sequence respectively.

[0189] In this embodiment, it is assumed that the fused standardized vector sequence is {(30.085, 120.095, 485, 'loam', 0.9)}. The server performs feature classification on this fused standardized vector sequence. The spatial coordinates (30.085, 120.095) are classified as spatial position features, which describe the specific position of the vector in geographic space. The terrain height value 485 is classified as a terrain height feature, which reflects the terrain undulations at that location. The soil type 'loam' is classified as a soil type feature, which reflects the soil texture category of the area. The correlation value 0.9 is classified as a correlation feature, which may indicate a certain degree of correlation between the terrain height and the soil type in the vector element, for example, it may be the strength of the correlation between the two calculated based on historical data or a model.

[0190] For example, the target standardized vector sequence is {(30.09, 120.09, 'sand', 0.2)}. The coordinates (30.09, 120.09) are also classified as spatial location features. The soil type 'sand' is classified as a soil type feature. The correlation value 0.2 is classified as a correlation feature, which has a similar meaning to the correlation in the fused standardized vector sequence, but is aimed at the internal relationship measurement of the vector element itself.

[0191] Step S152, preliminarily constructing a basic framework of a spatial relationship model according to the spatial structure features in the feature classification result of the fused standardized vector sequence.

[0192] Next, from the feature classification results of the fused standardized vector sequence {(30.085, 120.095, 485, 'loam', 0.9)}, the spatial structure features are mainly the spatial position (30.085, 120.095) and the terrain height 485.

[0193] When the server initially builds the basic framework of the spatial relationship model, it may regard the terrain height as a variable in space and establish a functional relationship with the spatial coordinates. For example, assuming that in this small area, the terrain height increases with the increase of longitude and decreases with the increase of latitude, a simple mathematical expression is initially constructed to express this relationship, such as H = a* lon + b* lat + c (where H represents the terrain height, lon represents the longitude, lat represents the latitude, and a, b, c are coefficients to be determined), which forms the basic framework of the spatial relationship model.

[0194] Step S153, combining some features in the feature classification result of the target standardized vector sequence, supplementing the basic framework, and generating an initial spatial relationship model framework including the relevant feature relationship between the fused standardized vector sequence and the target standardized vector sequence.

[0195] In this embodiment, the soil type 'sand' in the feature classification result of the target standardized vector sequence {(30.09, 120.09, 'sand', 0.2)} can be compared and analyzed with the 'loam' in the fused standardized vector sequence.

[0196] In this area, if it is known that 'sand soil' is mostly distributed in areas with higher terrain, and 'loam soil' is mostly distributed in areas with relatively flat terrain, then this relationship will be integrated into the previous basic framework.

[0197] For example, based on the previously constructed functional relationship between terrain height and spatial coordinates, the influence of soil type on terrain height is added. It can be assumed that the rate of change of terrain height in the "sand" distribution area is different from that in the "loam" distribution area, so the previous functional relationship is modified to H = a* lon + b* lat + c + d* soil_type (where soil_type is a variable representing soil type, and d is a coefficient related to soil type), thus generating an initial spatial relationship model framework containing the relevant feature relationship between the fused standardized vector sequence and the target standardized vector sequence.

[0198] Step S154, based on the initial spatial relationship model framework, feature association is performed on the data in the fused standardized vector sequence and the target standardized vector sequence, for each vector element in the fused standardized vector sequence, a vector element that is potentially associated with the vector element is searched in the target standardized vector sequence, the data of the vector elements that are potentially associated are integrated to form an associated data group, the associated data group is arranged and organized in the initial spatial relationship model framework according to the set logical relationship, and an integrated spatial relationship model framework containing the associated data group is generated.

[0199] In this embodiment, based on the initial spatial relationship model framework, for each vector element in the fused standardized vector sequence {(30.085, 120.095, 485, 'loam', 0.9)}, a vector element potentially associated with the vector element is searched in the target standardized vector sequence {(30.09, 120.09, 'sand', 0.2)}.

[0200] Since the spatial coordinates are close to (30.085, 120.095) and (30.09, 120.09), the soil types 'loam' and 'sand' have a certain correlation (for example, in the transition area of ​​soil types), so these two vector elements are regarded as vector elements with potential correlation.

[0201] The data of vector elements with potential associations are integrated to form an associated data group. For example, an associated data group can be {(30.085, 120.095, 485, 'loam', 0.9), (30.09, 120.09, 'sand', Then these associated data groups are arranged and organized in the initial spatial relationship model framework according to the set logical relationship. For example, if the set logical relationship is based on the distribution order of soil types, the data related to 'loam' is arranged first, and then the data related to 'sand' is arranged to generate an integrated spatial relationship model framework containing associated data groups.

[0202] Step S155, screen out spatial analysis factors that have a key impact on spatial analysis from the associated data group in the integrated spatial relationship model framework, analyze and describe the determined spatial analysis factors, and determine the factor description characteristics of each spatial analysis factor, wherein the factor description characteristics include the specific meaning of each spatial analysis factor in the spatial analysis, the scope of action, and the impact on other spatial analysis factors.

[0203] In this embodiment, spatial analysis factors having a key impact on spatial analysis are screened out from the associated data set {(30.085, 120.095, 485, 'loam', 0.9), (30.09, 120.09, 'sand', 0.2)} in the integrated spatial relationship model framework.

[0204] Terrain height485 may be a key factor because it directly affects the distribution of soil types and the hydrological characteristics of the region.

[0205] The change in soil type (from 'loam' to 'sand') may also be a key factor, reflecting changes in the geological and ecological environment of the region.

[0206] For the spatial analysis factor of terrain height, its factor description characteristics include:

[0207] Specific meaning in spatial analysis: It indicates the vertical distance of the ground in the area relative to a certain reference plane, which is an important indicator for describing terrain undulations.

[0208] Scope: In this example, the scope may be the entire study area or an area within a certain radius centered on the coordinate point.

[0209] Impact on other spatial analysis factors: Terrain height affects the degree of soil erosion. For example, soil erosion may be more serious in areas with higher terrain. Terrain height also affects the speed and direction of water flow. Higher terrain will increase the speed of water flow, thereby affecting the distribution and utilization of water resources.

[0210] For the spatial analysis factor of soil type conversion, its factor description characteristics include:

[0211] Specific meaning in spatial analysis: It refers to the phenomenon that the soil texture in a region changes from one type to another, reflecting the geological and ecological evolution process.

[0212] Scope of application: This may be along the soil type transition zone, or within the area where the distribution ratio of certain soil types changes.

[0213] Impact on other spatial analysis factors: Soil type conversion will affect the growth type and distribution of vegetation. For example, the vegetation types growing on "sand soil" and "loam" may be different. It will also affect the fertility and water retention capacity of the soil, thereby affecting agricultural production and the balance of the ecosystem.

[0214] Step S156, according to the determined spatial analysis factors and their factor description characteristics, combined with the nonlinear relationship and dynamic changes between the spatial analysis factors, construct the main structure of the spatial analysis model on the basis of the integrated spatial relationship model framework, and generate the constructed main structure of the spatial analysis model.

[0215] Step S157, using the data in the fused standardized vector sequence and the target standardized vector sequence to estimate the parameters in the main structure of the spatial analysis model, and calibrating the estimated parameters to generate a final spatial analysis model after parameter estimation and calibration. The output result of the final spatial analysis model is the spatial analysis modeling result of the geological information system data set to be processed.

[0216] In this embodiment, the parameters in the main structure of the spatial analysis model are estimated by using the data in the fused standardized vector sequence {(30.085, 120.095, 485, 'loam', 0.9)} and the target standardized vector sequence {(30.09, 120.09, 'sand', 0.2)}. For example, in the previously constructed functional relationship between terrain height and spatial coordinates H = a* lon +b* lat + c + d* soil_type, according to the actual spatial coordinates and terrain height data, the least square method and other methods can be used to estimate the values ​​of coefficients a, b, c and d.

[0217] The parameters describing the nonlinear relationship between terrain height and soil erosion degree can also be estimated based on the observed values ​​of terrain height and soil erosion degree in the actual data. For example, if a nonlinear function form is adopted (such as the quadratic function E = k* H^2 + m* H + n, where E represents the degree of soil erosion, H represents the terrain height, and k, m, and n are the parameters to be estimated), the estimated values ​​of the parameters can be obtained by substituting the actual data into the equation and solving it.

[0218] Then, the estimated parameters are calibrated. For example, the estimated parameters are substituted into the model and compared with known actual measurement data or expert experience. If there is a deviation between the terrain height calculated according to the model and the actual measured terrain height, or the soil type conversion predicted by the model is inconsistent with the actual observed conversion, then adjust the parameter value. By continuously adjusting and optimizing the parameters, the final spatial analysis model after parameter estimation and calibration is generated. The output result of this final spatial analysis model is the spatial analysis modeling result of the geoscientific information system data set to be processed. For example, the model can output spatial analysis results such as the terrain height change trend, the possibility of soil type conversion, and the change of vegetation coverage in a certain area in the future. These results can provide important decision-making basis for geoscientific research, land planning, ecological protection, etc.

[0219] For example, in a possible implementation, step S156 includes:

[0220] Step S1561, based on the factor description characteristics of each spatial analysis factor, determine the existing association clues between the spatial analysis factors from the integrated spatial relationship model framework, and construct a first spatial analysis factor relationship diagram based on the determined respective association clues, wherein the first spatial analysis factor relationship diagram shows the direct connection between the spatial analysis factors.

[0221] Step S1562: based on the first spatial analysis factor relationship graph, determine the nonlinear relationship between the spatial analysis factors, integrate the nonlinear relationship information into the first spatial analysis factor relationship graph, and generate a second spatial analysis factor relationship graph incorporating the nonlinear relationship.

[0222] Step S1563, for each spatial analysis factor, determine the change trend of the spatial analysis factor at different time scales and spatial scales, and integrate the dynamic change factors associated with the change trend into the second spatial analysis factor relationship diagram to facilitate clarifying the change pattern of each spatial analysis factor under different time and space conditions and the impact of the change pattern on the relationship between other factors, and generate a third spatial analysis factor relationship diagram after integrating the dynamic change factors.

[0223] Step S1564: Based on the third spatial analysis factor relationship diagram, the spatial analysis factors are used as the basic components of the main structural framework of the spatial analysis model. The hierarchical structure of the main structural framework of the spatial analysis model is determined according to the relationship between the spatial analysis factors, and the main structural framework of the spatial analysis model is constructed.

[0224] In this embodiment, based on the factor description features of each spatial analysis factor, existing association clues with the spatial analysis factor are determined from the integrated spatial relationship model framework.

[0225] For the spatial analysis factor of terrain height, there are clues of association between it and soil type conversion, because changes in terrain height may lead to different soil erosion and deposition processes, thus prompting soil type conversion.

[0226] A first spatial analysis factor relationship diagram is constructed based on the identified association clues. In this diagram, terrain height and soil type conversion are connected by a line, indicating a direct relationship between them. At the same time, if there are other spatial analysis factors, such as vegetation cover (assuming it is also determined as a spatial analysis factor), and it is related to both terrain height and soil type conversion, then the corresponding lines will also be connected in the diagram to indicate a direct relationship between them.

[0227] Next, based on the first spatial analysis factor relationship graph, non-linear relationships between spatial analysis factors are determined.

[0228] For example, the relationship between terrain height and soil erosion may not be a simple linear one. When the terrain height is low, the soil erosion may increase slowly as the terrain height increases; but when the terrain height exceeds a certain threshold, the soil erosion may increase dramatically.

[0229] This nonlinear relationship information is integrated into the first spatial analysis factor relationship diagram. For example, different line styles or colors can be used to represent nonlinear relationships, such as using dotted lines to represent weak nonlinear relationships and using thick lines to represent strong nonlinear relationships. If the relationship between terrain height and soil erosion degree is a strong nonlinear relationship in a certain interval, then a thick line is used to represent the line connecting them, and the expression or relevant description of the nonlinear relationship is marked next to it to generate a second spatial analysis factor relationship diagram after combining the nonlinear relationship.

[0230] For each spatial analysis factor, determine the changing trend of the spatial analysis factor at different time scales and spatial scales.

[0231] Take terrain height as an example. In the long term (time scale of several decades), terrain height may change slowly due to crustal movement or human activities (such as large-scale earthworks); in the short term (time scale of several years), terrain height may fluctuate due to seasonal rainfall and water erosion. On a large spatial scale (the entire region), the distribution of terrain height shows a macroscopic undulating feature; on a small spatial scale (a valley), the change of terrain height is more complex, and there may be local bulges and depressions.

[0232] Integrate the dynamic change factors associated with these change trends into the second spatial analysis factor relationship diagram. For example, add the time axis and the labels of different spatial scales to the diagram. For the factor of terrain height, use different colors or symbols to represent its change trend at different time and spatial scales, and explain the impact of these change trends on other factor relationships. If the rapid change of terrain height in a certain season (time scale) will lead to the acceleration of soil type conversion (the impact on other factor relationships), then make corresponding annotations in the diagram to generate the third spatial analysis factor relationship diagram after integrating the dynamic change factors.

[0233] According to the third spatial analysis factor relationship diagram, the spatial analysis factors are used as the basic components of the main structural framework of the spatial analysis model.

[0234] The hierarchical structure of the main structural framework of the spatial analysis model is determined according to the relationship between the spatial analysis factors. For example, terrain height may be at a higher level because it affects many other factors, such as soil type conversion, vegetation coverage, etc.; soil type conversion may be at an intermediate level, which is affected by terrain height and also affects vegetation coverage; vegetation coverage may be at a relatively low level, which is mainly affected by terrain height and soil type conversion.

[0235] The main structural framework of the spatial analysis model is constructed, which describes in detail the relationship between various spatial analysis factors and their hierarchical structure in the model.

[0236] Figure 2 The hardware structure of the electronic device 100 provided in the embodiment of the present application for implementing the above-mentioned GIS-based data analysis and presentation method is shown. Figure 2 As shown, the electronic device 100 may include a processor 110 , a machine-readable storage medium 120 , a bus 130 , and a communication unit 140 .

[0237] In one possible design, the electronic device 100 may be a single server or a server group. The server group may be centralized or distributed (for example, the electronic device 100 may be a distributed system). In some embodiments, the electronic device 100 may be local or remote. For example, the electronic device 100 may access information and / or data stored in the machine-readable storage medium 120 via a network. For another example, the electronic device 100 may be directly connected to the machine-readable storage medium 120 to access the stored information and / or data. In some embodiments, the electronic device 100 may be implemented on an electronic device. By way of example only, the electronic device may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

[0238] The machine-readable storage medium 120 may store data and / or instructions. In some embodiments, the machine-readable storage medium 120 may store data acquired from an external terminal. In some embodiments, the machine-readable storage medium 120 may store data and / or instructions used by the electronic device 100 to execute or use to complete the exemplary methods described in this application.

[0239] In the specific implementation process, one or more processors 110 execute computer executable instructions stored in the machine-readable storage medium 120, so that the processor 110 can execute the GIS-based data analysis and presentation method of the above method embodiment. The processor 110, the machine-readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processor 110 can be used to control the sending and receiving actions of the communication unit 140.

[0240] The specific implementation process of the processor 110 can refer to the various method embodiments executed by the above-mentioned electronic device 100. The implementation principles and technical effects are similar and will not be repeated in this embodiment.

[0241] In addition, an embodiment of the present application also provides a GIS-based data analysis and presentation device, in which computer-executable instructions are preset. When the processor executes the computer-executable instructions, the above-mentioned GIS-based data analysis and presentation method is implemented.

[0242] It should be noted that in order to simplify the description disclosed in this application and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, multiple features are sometimes combined into one embodiment, drawings, or descriptions thereof. Similarly, it should be noted that in order to simplify the description disclosed in this application and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present application, multiple features are sometimes combined into one embodiment, drawings, or descriptions thereof.

Claims

1. A GIS-based data analysis and presentation method, characterized in that: The method comprises: Obtaining a sequence of geospatial vectors of geospatial information units in a geospatial information system data set to be processed; Decomposing the geographic space vector sequence to generate a first mode decomposition vector subsequence of the geographic information unit and a second mode decomposition vector subsequence of the geographic information unit, wherein the feature scale of the first mode decomposition vector subsequence is greater than the feature scale of the second mode decomposition vector subsequence; The first mode decomposition vector subsequences of the local geomatic information units are fused according to the unit space association of the local geomatic information units to generate an inter-unit fusion vector sequence corresponding to the first mode decomposition vector subsequence; Performing geo-reference and standardization processing on the inter-unit fusion vector sequence to generate a fusion standardized vector sequence, and performing geo-reference and standardization processing on the second mode decomposition vector subsequences of each geo-information unit to generate a target standardized vector sequence; Performing spatial analysis modeling according to the fused standardized vector sequence and the target standardized vector sequence, generating a spatial analysis modeling result of the geoscientific information system data set to be processed, and presenting the spatial analysis modeling result of the geoscientific information system data set to be processed; The performing of spatial analysis modeling based on the fused standardized vector sequence and the target standardized vector sequence to generate a spatial analysis modeling result of the geoscientific information system data set to be processed includes: Performing feature classification on the fused standardized vector sequence and the target standardized vector sequence to obtain a feature classification result of the fused standardized vector sequence and a feature classification result of the target standardized vector sequence, respectively; Preliminarily constructing a basic framework of a spatial relationship model based on the spatial structure features in the feature classification results of the fused standardized vector sequence; Combining some features in the feature classification result of the target standardized vector sequence, the basic framework is supplemented to generate an initial spatial relationship model framework including the relevant feature relationship between the fused standardized vector sequence and the target standardized vector sequence; Based on the initial spatial relationship model framework, feature association is performed on the data in the fused standardized vector sequence and the target standardized vector sequence, and for each vector element in the fused standardized vector sequence, a vector element potentially associated with the vector element is searched in the target standardized vector sequence, and the data of the vector elements with potential association are integrated to form an associated data group, and the associated data group is arranged and organized in the initial spatial relationship model framework according to a set logical relationship to generate an integrated spatial relationship model framework including the associated data group; Screening out spatial analysis factors that have a key impact on spatial analysis from the associated data group in the integrated spatial relationship model framework, analyzing and describing the determined spatial analysis factors, and determining the factor description characteristics of each spatial analysis factor, wherein the factor description characteristics include the specific meaning of each spatial analysis factor in spatial analysis, the scope of action, and the impact on other spatial analysis factors; According to the determined spatial analysis factors and their factor description characteristics, combined with the nonlinear relationship and dynamic changes between the spatial analysis factors, a main structure of the spatial analysis model is constructed on the basis of the integrated spatial relationship model framework to generate a constructed main structure of the spatial analysis model; The parameters in the main structure of the spatial analysis model are estimated using the data in the fused standardized vector sequence and the target standardized vector sequence, and the estimated parameters are calibrated to generate a final spatial analysis model after parameter estimation and calibration. The output result of the final spatial analysis model is the spatial analysis modeling result of the geological information system data set to be processed.

2. The GIS-based data analysis and presentation method according to claim 1, characterized in that: The step of decomposing the geographic space vector sequence to generate a first mode decomposition vector subsequence of each geographic information unit and a second mode decomposition vector subsequence of each geographic information unit includes: Determining a first decomposition feature interval corresponding to the first pattern decomposition vector subsequence and a second decomposition feature interval corresponding to the second pattern decomposition vector subsequence according to the feature scale of each vector element in the geographic space vector sequence; Decomposing the geographic space vector sequence according to the first decomposition feature interval corresponding to the first pattern decomposition vector subsequence to generate the first pattern decomposition vector subsequence; Decomposing the geographic space vector sequence according to the second decomposition feature interval corresponding to the second pattern decomposition vector subsequence to generate the second pattern decomposition vector subsequence.

3. The GIS-based data analysis and presentation method according to claim 1, characterized in that: The first mode decomposition vector subsequence includes a set of spatial weight vectors, and the second mode decomposition vector subsequence includes sets of non-spatial weight vectors; The step of decomposing the geographic space vector sequence to generate a first mode decomposition vector subsequence of each geographic information unit and a second mode decomposition vector subsequence of each geographic information unit includes: Determining the spatial weight interval corresponding to the spatial weight vector set and the non-spatial weight intervals associated with each of the non-spatial weight vector sets according to the characteristic scale of each vector element in the geographic spatial vector sequence; Determine corresponding spatial weight values ​​from the sequence of geographic spatial vectors according to the spatial weight interval, and use the spatial weight values ​​as the set of spatial weight vectors; Corresponding non-spatial weight values ​​are respectively determined from the geographic spatial vector sequence according to the non-spatial weight intervals associated with each of the non-spatial weight vector sets, and the non-spatial weight vector sets are determined according to the non-spatial weight values.

4. The GIS-based data analysis and presentation method according to claim 1, characterized in that: The first mode decomposition vector subsequence includes a spatial weight vector set and each first mode non-spatial weight vector set, and the second mode decomposition vector subsequence includes each second mode non-spatial weight vector set; The step of decomposing the geographic space vector sequence to generate a first mode decomposition vector subsequence of each geographic information unit and a second mode decomposition vector subsequence of each geographic information unit includes: Determine, according to the characteristic scale of each vector element in the geographic spatial vector sequence, the spatial weight interval corresponding to the spatial weight vector set, the first mode non-spatial weight interval associated with each of the first mode non-spatial weight vector sets, and the second mode non-spatial weight interval associated with each of the second mode non-spatial weight vector sets; Determine corresponding spatial weight values ​​from the sequence of geographic spatial vectors according to the spatial weight interval, and use the spatial weight values ​​as the set of spatial weight vectors; Determine the corresponding first mode non-spatial weight values ​​from the geographic spatial vector sequence according to the first mode non-spatial weight intervals associated with each of the first mode non-spatial weight vector sets, and determine the first mode non-spatial weight vector sets according to the first mode non-spatial weight values; According to the second mode non-spatial weight intervals associated with each of the second mode non-spatial weight vector sets, corresponding second mode non-spatial weight values ​​are respectively determined from the geographic spatial vector sequence, and according to the second mode non-spatial weight values, each of the second mode non-spatial weight vector sets is determined.

5. The GIS-based data analysis and presentation method according to claim 1, characterized in that: The first mode decomposition vector subsequences of the local geomatics information units are fused according to the unit space association of the local geomatics information units to generate an inter-unit fusion vector sequence corresponding to the first mode decomposition vector subsequence, including: Acquire the number of fused geoscientific information units, and determine a plurality of associated geoscientific information unit pairs from the geoscientific information units according to the unit spatial correlation of the geoscientific information units and the number of fused geoscientific information units, wherein the associated geoscientific information unit pairs include associated geoscientific information units of the number of fused geoscientific information units; Fusing first pattern decomposition vector subsequences associated with the associated geo-information units of the number of fused geo-information units to generate inter-unit fusion vector sequences corresponding to the associated geo-information unit pairs; The plurality of associated geoscientific information unit pairs are polled to generate inter-unit fusion vector sequences associated with the plurality of associated geoscientific information unit pairs.

6. The GIS-based data analysis and presentation method according to claim 5, characterized in that: The step of polling the plurality of associated geoscientific information unit pairs to generate inter-unit fusion vector sequences associated with the plurality of associated geoscientific information unit pairs includes: Acquire each unassociated geo-information unit, and when the number of each unassociated geo-information unit is less than the number of the fused geo-information unit, determine the geo-information unit to be supplemented from the unassociated geo-information units, and calculate the difference between the number of the fused geo-information unit and the number of the unassociated geo-information unit to generate the number to be supplemented; Performing a supplement operation on the geoscientific information units to be supplemented according to the number to be supplemented to generate supplement operation geoscientific information units, and performing a pairing operation on the geoscientific information units that are not associated with each other and the supplement operation geoscientific information units to generate supplement operation geoscientific information unit pairs; The first mode decomposition vector subsequences respectively associated with each geoscientific information unit in the supplementary operation geoscientific information unit pair are fused to generate an inter-unit fusion vector sequence corresponding to the supplementary operation geoscientific information unit pair.

7. The GIS-based data analysis and presentation method according to claim 1, characterized in that: The step of geo-registering and standardizing the inter-unit fused vector sequence to generate a fused standardized vector sequence includes: Acquire a fused geographic registration and normalization template corresponding to the inter-unit fused vector sequence, wherein the fused geographic registration and normalization template includes each fused geographic normalization symbol; Calculating the matching degree between the inter-unit fusion vector sequence and each fusion geographic normalization symbol, and determining a target fusion geographic normalization symbol from each fusion geographic normalization symbol according to the matching degree; Taking the target fused geographic normalized symbol as the fused normalized vector sequence; The step of obtaining the fused geographic registration and standardization template corresponding to the inter-unit fused vector sequence includes: Obtaining a sample geospatial vector sequence of each sample geospatial information unit; Decomposing the sample geospatial vector sequence according to the characteristic scale of each vector element in the sample geospatial vector sequence to generate a first mode sample decomposition vector subsequence of each sample geospatial information unit; The first pattern sample decomposition vector subsequences of the sample geo-information units are fused according to the unit space association of the sample geo-information units to generate the sample fusion vector sequence; Cluster learning is performed based on the sample fusion vector sequences to generate first pattern vector clusters, and the fusion geo-registration and standardization template is generated based on cluster center features in the first pattern vector clusters.

8. The GIS-based data analysis and presentation method according to claim 1, characterized in that: The step of performing geo-registration and standardization processing on the second mode decomposition vector subsequences of the geo-information units to generate a target standardized vector sequence includes: Acquire a unit geo-reference and standardization template corresponding to the second mode decomposition vector subsequence, wherein the unit geo-reference and standardization template includes each unit geo-reference and standardization template; Calculating the matching degree between the second pattern decomposition vector subsequence and each unit geo-reference and standardized template respectively, and determining the target unit geo-reference and standardized template from each unit geo-reference and standardized template according to the matching degree, and using the target unit geo-reference and standardized template as the target standardized vector sequence; Polling the second mode decomposition vector subsequences of the local geomatics information units respectively to generate target standardized vector sequences of the local geomatics information units; The step of obtaining the unit geo-registration and standardization template corresponding to the second mode decomposition vector subsequence includes: Obtaining a sample geospatial vector sequence of each sample geospatial information unit; Decomposing the sample geospatial vector sequence according to each vector element in the characteristic scale of the sample geospatial vector sequence to generate a second mode sample decomposed vector subsequence of each sample geospatial information unit; Cluster learning is performed based on the second pattern sample decomposition vector subsequence of each sample geoscientific information unit to generate each second pattern vector cluster, and the unit geographic registration and standardization template is generated based on the cluster center features in each second pattern vector cluster.

9. A GIS-based data analysis and presentation device, characterized in that: The GIS-based data analysis and presentation device is used to store programs, instructions or codes. When the programs, instructions or codes in the memory are executed, the GIS-based data analysis and presentation method described in any one of claims 1 to 8 is implemented.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the GIS-based data analysis and presentation method described in any one of claims 1 to 8.

Images