Analysis method and device for geological spatial data, equipment and medium

Abstract

The invention relates to an analysis method and device for geological spatial data, equipment and a medium. The method comprises the steps that multi-source heterogeneous data are collected based on a preset spatial data standard, and the multi-source heterogeneous data comprise geological spatial data of multiple different geological data types; determining geological features of the geological spatial data of each geological data type, and establishing a feature matrix of the geological spatial data of the corresponding type based on the geological features; classifying the multi-source heterogeneous data on the dimension of the geological structure to obtain various geological structure data, each geological structure data corresponding to one geological structure type; and according to the feature matrix of the geological spatial data corresponding to the geological structure type, fusing the geological structure data of the corresponding type to obtain a fusion analysis result of the geological structure type. By adopting the method, fusion and analysis of geological data can be efficiently completed based on multi-source heterogeneous data.

Description

Technical Field

[0001] The present application relates to the technical field of geospatial information processing, and particularly to an analysis method, device, equipment, and medium for geological spatial data. Background Art

[0002] In today's fields related to geographic information, spatial data sources are extensive, including satellite remote sensing, aerial photogrammetry, ground survey equipment (such as total stations, GPS receivers), and various geographic information system (GIS) data, etc. These data from different sources have huge differences in formats, accuracies, attribute structures, coordinate systems, etc., making it impossible to perform efficient and convenient integrated analysis on such spatial data. Therefore, establishing an integrated management and analysis method for spatial data can effectively solve this problem, empower fields such as geological disasters and ecological restoration, and enhance the value of spatial data usage.

[0003] Currently, there are already some specialized spatial data format conversion tools in the field of geospatial information technology, which have solved the fusion problem between data of different formats to a certain extent, enabling multi-source heterogeneous spatial data to interact between different systems and applications. However, the accuracies of spatial data from different sources are different, and the spatial correlation standards are not unified, making it impossible to directly apply traditional data mining algorithms.

[0004] Currently, for the problem in the prior art that it is impossible to efficiently complete geological structure analysis based on the collected multi-source heterogeneous data, no effective solution has been proposed. Summary of the Invention

[0005] Based on this, it is necessary to provide an analysis method, device, equipment, and medium for geological spatial data in view of the above technical problems.

[0006] In a first aspect, the present application provides an analysis method for geological spatial data. The method includes:

[0007] Collecting multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types;

[0008] Determining the geological characteristics of the geological spatial data of each geological data type, and establishing a feature matrix for the geological spatial data of the corresponding type based on the geological characteristics;

[0009] Classifying the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type;

[0010] Fusing the geological structure data of the corresponding type according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain a fusion analysis result of the geological structure type.

[0011] In one embodiment, a spatial data standard is established, including:

[0012] Establishing a standardized data format specification, a standardized data content specification, and a standardized coordinate system;

[0013] Carrying out unified coding for each geological element, where each geological element after unified coding corresponds to a unique code.

[0014] In one embodiment, multi-source heterogeneous data is collected based on a preset spatial data standard, including:

[0015] Obtaining initial data;

[0016] Performing format conversion processing on the initial data, and unifying the coordinate system of the initial data based on the standardized coordinate system;

[0017] Performing data cleaning on the unified initial data to obtain multi-source heterogeneous data.

[0018] In one embodiment, classifying multi-source heterogeneous data in the dimension of geological structure to obtain various geological structure data, including:

[0019] Inputting the multi-source heterogeneous data into a trained classification model, and classifying the multi-source heterogeneous data in the dimension of geological structure through the classification model to obtain geological structure data of various geological structure types.

[0020] In one embodiment, classifying multi-source heterogeneous data in the dimension of geological structure to obtain various geological structure data, including:

[0021] Determining at least one sub-heterogeneous data set from the multi-source heterogeneous data based on a preset screening specification, and for each sub-heterogeneous data set, performing clustering calculation in the dimension of geological structure, and obtaining geological structure data of various geological structure types based on the clustering calculation results.

[0022] In one embodiment, according to the feature matrix of geological spatial data corresponding to the geological structure type, fusing the geological structure data of the corresponding type to obtain a fusion analysis result of the geological structure type, including:

[0023] Inputting the geological structure data into a trained fusion model, and performing fusion processing on the geological structure data belonging to the same geological structure type according to the feature matrix of geological spatial data to obtain a fusion analysis result, where the fusion analysis result includes a geological structure image corresponding to the geological structure type and a geological report for the geological structure type.

[0024] In one embodiment, after obtaining the fusion analysis result of the geological structure type, the method further includes:

[0025] Comparing and validating the fusion analysis result with the obtained real geological data to obtain the accuracy of the fusion result;

[0026] And / or, validating the geological structure data based on the cross-validation algorithm to obtain the accuracy of the fusion result;

[0027] Determining the accuracy rate of the fusion analysis result based on the accuracy and feeding it back to a preset feedback receiver.

[0028] In a second aspect, the present application also provides an analysis device for geological spatial data. The device includes:

[0029] An acquisition module, configured to acquire multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types;

[0030] A calculation module, configured to determine the geological features of the geological spatial data of each geological data type, and establish a feature matrix of the geological spatial data of the corresponding type based on the geological features; classifying the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type;

[0031] A generation module, configured to fuse the geological structure data of the corresponding type according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain a fusion analysis result of the geological structure type.

[0032] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Acquiring multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types;

[0034] Determining the geological features of the geological spatial data of each geological data type, and establishing a feature matrix of the geological spatial data of the corresponding type based on the geological features;

[0035] Classifying the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type;

[0036] Fusing the geological structure data of the corresponding type according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain a fusion analysis result of the geological structure type.

[0037] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0038] Collect multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types;

[0039] Determine the geological characteristics of the geological spatial data of each geological data type, and establish a feature matrix for the geological spatial data of the corresponding type based on the geological characteristics;

[0040] Classify the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type;

[0041] According to the feature matrix of the geological spatial data corresponding to the geological structure type, fuse the geological structure data of the corresponding type to obtain a fused analysis result of the geological structure type.

[0042] The above analysis method, device, equipment and medium for geological spatial data, after obtaining multi-source heterogeneous data that meets the preset spatial data standard, determine the feature matrix of the geological spatial data of each type, classify the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, and fuse the geological structure data according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain a fused analysis result of the geological structure type. Through the present application, multi-source geological data can be standardized and unified, and on this basis, the geological structure data of the same geological structure type can be fused. The fusion result includes an intuitive analysis of the geological structure type and related data. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is an application environment diagram of the analysis method for geological spatial data in an embodiment;

[0044] Figure 2 It is a flowchart of the analysis method for geological spatial data in an embodiment;

[0045] Figure 3 It is a structural block diagram of the analysis device for geological spatial data in an embodiment;

[0046] Figure 4 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] In order to make the objectives, technical solutions, and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The analysis method for geological spatial data provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. First, multi-source heterogeneous data is collected based on a preset spatial data standard, the geological features of the geological spatial data of each geological data type in the multi-source heterogeneous data are determined, and a feature matrix of the geological spatial data of the corresponding type is established based on the geological features. The multi-source heterogeneous data is classified in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type. According to the feature matrix of the geological spatial data corresponding to the geological structure type, the geological structure data of the corresponding type is fused to obtain a fusion analysis result of the geological structure type. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0049] In one embodiment, as Figure 2 shown, a method for analyzing geological spatial data is provided. Taking the method applied to the Figure 1 server 104 as an example, the method includes the following steps:

[0050] Step S210, collect multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types.

[0051] Specifically, the above spatial data standard is a preset data standard, including but not limited to, standards for data formats (such as vector data, raster data, or 3D model data, etc.), standards for data content structures (such as unifying the geometric representation of vector data, such as clarifying the meaning of point features, line features, and surface features, as well as the coordinate accuracy of point features, the drawing rules of line features, and the drawing rules of surface features, etc.), standards for data encoding (such as ensuring that the encoding of all geological features follows the principle of uniqueness, etc.), and standards for coordinate systems (such as determining a unified coordinate system, clarifying the conversion rules and methods between different coordinate systems, and specifying coordinate accuracy requirements, etc.).

[0052] After clarifying the above spatial data standard, multi-source heterogeneous data is collected according to this spatial data standard, so that the collected multi-source heterogeneous data meets the above-predefined spatial data standard. Among them, multi-source heterogeneous data includes geological spatial data of multiple different geological data types. Geological data types include but not limited to, geological exploration data types (such as drilling data types, geophysical exploration data types, geochemical exploration data types, etc.), aerospace remote sensing data types (such as satellite remote sensing data, aerial remote sensing data, drone data, etc.), and ground measurement data types (such as detection equipment measurement data types, GPS measurement data types, etc.). Geological spatial data is a digital information set that describes the morphology, structure, properties, and spatial distribution and interrelationships of geological bodies on and inside the Earth's surface.

[0053] Step S220: Determine the geological characteristics of the geological spatial data of each geological data type, and establish a feature matrix for the geological spatial data of the corresponding type based on the geological characteristics.

[0054] Specifically, the geological characteristics of the geological spatial data of each geological data type are determined, that is, the characteristics with geological significance are extracted from the data corresponding to each geological data type. For example, in remote sensing image data, the spectral characteristics of rocks are extracted through spectral analysis; such as the reflectivity differences of different rock types in specific bands (such as infrared bands), so as to identify rock types; such as in geophysical data, the density, magnetism and other physical characteristics of geological bodies are extracted from gravity, magnetism and other data, and these characteristics can reflect the structure and composition of geological bodies; such as for drilling data, the lithology, sequence and other characteristics of strata can be extracted from the description of core samples. In summary, the geological characteristics of the data corresponding to each geological data type are determined. One geological data type can correspond to multiple geological characteristics. The extraction methods of geological characteristics include but are not limited to manual extraction, feature extraction through well-trained neural networks, and the use of information gain, Gini index and other indicators to evaluate the importance of each feature, so as to selectively extract the most valuable feature data, and other methods. In summary, representative geological features are extracted from the original geological spatial data, and redundant or irrelevant information is eliminated. In practical applications, the original geological spatial data can be converted into a set of features with obvious physical or statistical significance (such as Gabor, geometric features [corner points, invariants], texture [LBP HOG]), and finally a feature matrix of the above geological spatial data is formed, thereby preserving the features and reducing the difficulty of data processing. In subsequent data processing, the feature matrix will be called to facilitate subsequent data fusion processing.

[0055] In a preferred embodiment, it is assumed that the original geological spatial data is an image with a large number of pixels. If the original image is directly processed at this time, it will lead to a surge in complexity. Feature extraction of the image can reduce the difficulty of subsequent processing. The extracted features include but are not limited to spectral information, rock formation occurrence information, geological structure information, legends and scales, etc. A corresponding feature matrix is ​​established based on the above information, and the feature matrix also contains the data information of the original data. When performing data fusion analysis, analyzing the extracted feature data can reduce difficulty and improve efficiency.

[0056] Step S230, classifying the multi-source heterogeneous data in the dimension of geological structure to obtain a variety of geological structure data, wherein each geological structure data corresponds to a geological structure type.

[0057] Specifically, multi-source heterogeneous data is classified in the dimension of geological structure to obtain various geological structure data, that is, multi-source heterogeneous data (such as geophysical exploration data, geochemical exploration data, and remote sensing data) is classified in the dimension of geological structure, and data of different geological structure categories is classified to obtain the classification results of geological bodies (such as mining areas, non-mining areas, different types of geological structures, etc.), that is, different types of multi-source heterogeneous data are classified into geological structure data of various different geological structure types. Specific classification methods include, but are not limited to, clustering algorithms, neural network models through classification, and support vector machine (SVM) and other solutions.

[0058] Step S240: According to the feature matrix of the geological space data corresponding to the geological structure type, fuse the geological structure data of the corresponding type to obtain the fusion analysis result of the geological structure type.

[0059] Specifically, the data corresponding to each geological structure type is fused separately, and the feature matrix established above can be carried in the geological space data, and / or this feature matrix can be called during data fusion. In some preferred embodiments, data fusion can be performed based on neural networks such as CNN and RNN. For example, when fusing remote sensing image data and geophysical exploration data belonging to the same geological structure type, the remote sensing image data carrying the feature matrix of the geological space data and the geophysical exploration data are input into a trained neural network. The neural network can automatically extract the complex texture features in the remote sensing image data and the spatial distribution features in the geophysical exploration data, and fuse these features through operations such as multi-layer convolution and pooling to obtain the fusion analysis result. The fusion analysis result can be better used for subsequent tasks such as geological structure recognition and mineral resource prediction. Further, in some preferred embodiments, the geological space data belonging to the same geological structure type can be input into a trained long short-term memory network (LSTM) or recurrent neural network (RNN). This neural network can be used to process geological data with time series (such as the relationship between long-term groundwater level change data and geological structure activities), so as to extract the time series features in the data and perform fusion analysis.

[0060] Through steps S210 to S240, the data collected in different formats, different precisions, and different coordinate systems are unified, classified in the dimension of geological structure, and then the geological structure data obtained after classification is integrated to obtain the fusion analysis result. This can not only efficiently clarify the complex data association relationships among multi-source heterogeneous data, but also reflect the hidden geological patterns and laws from the massive geological data according to the fused result, which helps relevant technicians to deeply understand the formation and evolution process of geological structures.

[0061] In one embodiment, a spatial data standard is established, including:

[0062] Establish standardized data format specifications, standardized data content specifications, and a standardized coordinate system;

[0063] Carry out unified coding for each geological element. Among them, each geological element after unified coding corresponds to a unique code.

[0064] Specifically, establish a preset standardized data format specification, that is, clarify the specifications of various types of spatial data, such as vector data, raster data (such as cell size, band order, etc.), and different file formats (such as Shapefile, GeoTIFF, etc.), so as to ensure the compatibility of data between different systems and software. Specifically, there are: 1. Establish a vector data format specification: clarify the storage structure of vector data, such as the representation methods of geometric elements such as points, lines, and polygons. For point elements, specify the accuracy and data type (such as double-precision floating-point numbers) of their coordinate representations; for line elements, determine the storage format composed of a series of ordered points, and the recording method of line attributes (such as color, line type, etc.); for polygon elements, clarify the storage order of boundary points and the expression method of topological relationships, such as the handling of shared boundaries between adjacent polygons. Define the file formats of vector data, such as the specific specifications of common formats such as Shapefile and GeoJSON (Geography JavaScript Object Notation). Include file header information (such as file version, coordinate system identifier, etc.), the organization method of data segments (such as the association between the attribute table and the geometric data segment), and the storage location and content requirements of metadata. 2. Establish a raster data format specification: stipulate the cell representation method of raster data, including the size, resolution, and data type (such as integer type, floating-point type, etc.) of cells. For example, in raster data representing terrain elevation, clarify the actual elevation meaning and accuracy requirements represented by cell values. Determine the storage format of raster data, such as the detailed specifications of formats such as TIFF and GeoTIFF. Include the georeference information in the file header (such as projection parameters, coordinate range, etc.), the recording method of band information (such as the arrangement order and band meaning description of multi-band data), and the provisions of data compression algorithms, etc. 3. Clarify the format specifications of other data: For other types of spatial data, such as 3D model data (formats such as OBJ, 3DS, etc.), image data (formats such as JPEG 2000 for specific geographical images), etc., relevant technical personnel can formulate corresponding standards according to actual needs, clarify their data structures, storage methods, and metadata requirements, etc., to ensure the compatibility and interoperability of different types of spatial data under a unified framework.

[0065] Moreover, this embodiment also includes establishing a standardized data content specification, such as specifying which attribute information spatial data should contain (e.g., the name, type, attribute values, etc. of geographical elements) and the logical relationships between them, so that the data has a clear structure and semantics. The specific establishment of a standardized data content specification includes but is not limited to: 1. Establishing a geological data type specification: For vector data, it is necessary to clarify the geometric representation method of geological elements. For example, point elements are used to represent isolated geological phenomena such as borehole positions and ore body outcrops; it is necessary to specify their coordinate accuracy (e.g., accurate to the meter or centimeter level). Line elements are used to represent geological structure lines (such as fault lines, stratigraphic boundaries, etc.), and it is necessary to determine the drawing rules of the lines, such as requirements for line continuity and smoothness. Face elements are used to represent geological bodies (such as rock layers, mining areas, etc.), and it is necessary to standardize the boundary drawing method and internal filling rules of the faces, etc. For raster data, it is necessary to unify the raster representation of geological attributes. For example, rasterized data such as formation thickness and rock porosity need to specify the pixel size (determined according to the research area and accuracy requirements, such as 10 meters × 10 meters or 5 meters × 5 meters, etc.), the correspondence between pixel values and geological attributes (such as pixel values representing formation depth, with the unit of meters), and the data storage format, such as GeoTIFF (Geographic Tagged Image File Format). For 3D data, it is necessary to standardize the 3D model data format of geological bodies. This includes 3D point cloud data (used to represent the irregular shape of the geological surface, specifying the coordinate accuracy and density requirements of points), 3D mesh data (describing the surface or internal structure of geological bodies, clarifying the mesh resolution, topology relationship construction rules, etc.), and voxel data (used to represent the internal attribute distribution of geological bodies, such as the change of rock physical properties in 3D space, specifying the size of voxels and the attribute storage method).

[0066] In practical applications, it is also necessary to establish a file format specification, determine a common geological data file format. In addition to internationally common formats, for specific geological data, such as geological exploration report documents, specify their electronic document formats (e.g., PDF format for final report archiving, XML format for parsable structured report content). At the same time, for the interaction of geological data between different software platforms, formulate a standard for the intermediate file format of data conversion to ensure that data can be smoothly converted and used in various geological software (such as ArcGIS (Geographic Information System), MapGIS, etc.).

[0067] Moreover, in this embodiment, it is also necessary to establish a standardized coordinate system and uniformly adopt a specific coordinate system (such as a geodetic coordinate system, a projected coordinate system, etc.) to ensure the consistency and accuracy of spatial data in terms of spatial position. Specifically, it includes clarifying the selection and definition of the coordinate system. For example, determine a unified coordinate system, and preferably choose an internationally common coordinate system suitable for geological research, such as the WGS84 (World Geodetic System 1984) geodetic coordinate system as the basic coordinate system. For specific geological research areas or project requirements, an appropriate projected coordinate system can be selected according to the actual situation. For example, the Gauss-Krüger projection (suitable for topographic surveys and geological mapping at medium and small scales, stipulating the division method of projection zones, such as dividing by 6° zones or 3° zones) or the UTM (Universal Transverse Mercator Grid System) projection (suitable for large-scale geological surveys and resource exploration areas, clarifying the numbering rules of projection zones). At the same time, define in detail the parameters of the selected coordinate system, including ellipsoid parameters (such as semi-major axis, semi-minor axis, flattening, etc.), projection origin, axis directions, etc. In practical applications, for the conversion between different coordinate systems, corresponding conversion rules can also be formulated in advance. For example, when converting from a local coordinate system to the WGS84 coordinate system, a seven-parameter or three-parameter conversion model can be used, and clarify the calculation method and acquisition channels of the parameters in the model to ensure the accuracy and reliability of coordinate conversion. At the same time, stipulate the accuracy requirements for coordinate conversion. According to the specific needs of geological research, for example, regional geological structure analysis may require the coordinate conversion accuracy to reach the meter level, while fine exploration of mining areas may require centimeter-level or even higher-precision coordinate conversion.

[0068] In some embodiments, it is also necessary to clarify the accuracy requirements of coordinates. For example, different levels of coordinate accuracy standards are formulated according to the uses and application scenarios of geological data. In regional geological surveys, for the study of macroscopic geological structures and stratigraphic distributions, the coordinate accuracy can meet the hundred-meter or kilometer level; for urban geological surveys and engineering geological investigations, the coordinate accuracy needs to reach the meter level; while in the process of mining area exploration and exploitation, the coordinate accuracy requirements for key geological elements such as borehole positions and ore body boundaries are higher, possibly reaching the centimeter level or even the millimeter level. At the same time, stipulate the recording and storage methods of coordinate data, and use appropriate data types (such as double-precision floating-point numbers) to store coordinate values to ensure that the accuracy of coordinates is not lost during data processing and transmission, and take effective data quality control measures to prevent the accumulation of errors in coordinate data.

[0069] In this embodiment, it is also necessary to uniformly encode each geological element, and to assign specific codes to different types of land objects to facilitate data identification, classification and retrieval. Specifically: 1. Clarify the coding principles of geological elements, and uniformly encode each geological element according to the coding principles, follow the principle of uniqueness, and ensure that each geological element has a unique code to avoid confusion. For example, each borehole has its own independent code and will not be repeated with the codes of other boreholes or other geological elements. At the same time, the code should be stable. Once determined, it should be kept unchanged as much as possible during data updating and long-term management to facilitate data tracing and integration. In addition, the code must also be scalable to adapt to the discovery of new types of geological elements and the expansion of data content.

[0070] In some preferred embodiments, the code should have certain semantic information and be able to reflect the main characteristics and categories of the geological elements. For example, a hierarchical coding method is adopted, where the first few digits or letters represent the major category of the geological element (such as "DG" represents stratigraphic related elements), the middle few digits represent the middle category (such as "DG01" represents the age classification of the stratigraphic layer), and the last few digits represent the specific subcategory or subdivision type (such as "DG0101" represents the Cambrian stratigraphic layer).

[0071] The following is a specific coding scheme: For rock types, the internationally accepted rock classification coding system can be adopted and refined in combination with local actual conditions. For example, granite can be coded as "RG001", where "RG" represents igneous rock and "001" represents the specific serial number of granite in the igneous rock classification. For geological structures, faults can be coded starting with "FZ", normal faults are coded as "FZ01", reverse faults are coded as "FZ02", etc. For mineral resources, copper mines can be coded as "CM001", where "CM" represents copper in metal minerals and "001" represents a specific copper mine type or grade range.

[0072] In summary, through this embodiment, a comprehensive and standardized spatial data standard can be established to ensure that data from different sources (such as geological exploration, geophysics, geochemistry, remote sensing, etc.) can be collected and standardized, so that the accuracy of the data can be improved. For example, a unified data format and encoding rules allow data from different sources to accurately correspond when integrated, reducing errors caused by inconsistent data formats or semantic ambiguity.

[0073] In one embodiment, collecting multi-source heterogeneous data based on a preset spatial data standard includes:

[0074] Get initial data;

[0075] Performing format conversion processing on the initial data, and unifying the coordinate system of the initial data based on the standardized coordinate system;

[0076] Perform data cleaning on the unified initial data to obtain the multi-source heterogeneous data.

[0077] Specifically, obtain the initial data, which includes but is not limited to geological exploration data types (such as drilling data types, geophysical exploration data types, geochemical exploration data types, etc.), aerospace remote sensing data types (such as satellite remote sensing data, aerial remote sensing data, UAV data, etc.), and ground measurement data types (such as detection equipment measurement data types, GPS measurement data types, etc.). The initial data obtained at this time is already data that conforms to the spatial data standard.

[0078] Perform preprocessing on the initial data, including but not limited to format conversion processing of the initial data. Specific processing methods include but are not limited to: Since the collected initial data comes from a variety of different devices and systems, its formats are diverse. For example, drilling data in geological exploration may be stored in a specific database format, while aerial remote sensing image data may be in GeoTIFF format. These different format data need to be converted into a unified format for subsequent processing. For vector data, the Shapefile format needs to be converted into a more general Geodatabase format; for raster data, various different image formats need to be converted into a format suitable for data analysis and mining. Then, unify the coordinate system of the initial data based on a standardized coordinate system: Different data sources may adopt different coordinate systems, such as geodetic coordinate systems (such as WGS84), local coordinate systems, or projection coordinate systems (such as Gauss-Krüger projection). Before data fusion, the coordinate systems of these data must be unified. This involves complex coordinate conversion algorithms, such as three-parameter or seven-parameter conversion models, which calculate conversion parameters through known coincidence points (points with accurate coordinates in both coordinate systems) to convert all data to the same coordinate system to ensure the consistency of data in spatial positions. Finally, perform data cleaning on the unified initial data to obtain the above-mentioned multi-source heterogeneous data. Among them, specific methods of data cleaning include but are not limited to: Considering that the collected data may have problems such as noise, error values, and missing values. For noise data, such as abnormal fluctuations caused by instrument interference in geophysical exploration data, filtering algorithms (such as mean filtering, median filtering, etc.) need to be used to remove it. For outlier values, such as obviously unreasonable coordinate values or measurement values caused by human operation errors in measurement data, they need to be identified and corrected through data verification rules (such as range checks of measurement values, logical relationship checks, etc.). For missing values, interpolation methods (such as Kriging interpolation, inverse distance weighted interpolation, etc. in spatial interpolation) can be used to supplement according to the distribution of surrounding data, or reasonable estimation can be made according to geological laws and prior knowledge.

[0079] Through this embodiment, the initially collected data is uniformly preprocessed to obtain multi-source heterogeneous data, which facilitates subsequent processing and analysis of the multi-source heterogeneous data.

[0080] In one embodiment, the multi-source heterogeneous data is classified in the dimension of geological structure to obtain various geological structure data, including:

[0081] The multi-source heterogeneous data is input into a well-trained classification model, and the multi-source heterogeneous data is classified in the dimension of geological structure through the classification model to obtain geological structure data of various geological structure types.

[0082] Specifically, in this embodiment, the multi-source heterogeneous data from different sources is classified in the dimension of geological structure to obtain various geological structure data. In this embodiment, it is preferably to complete the classification task based on a preset classification model, that is, the multi-source heterogeneous data (such as geophysical exploration data, geochemical exploration data, and remote sensing data) is used as the input layer neurons, and through the non-linear transformation of the hidden layer, the classification result of the geological structure (such as mining areas, non-mining areas, and other different types of geological structures, etc.) is obtained in the output layer. In summary, in this embodiment, the heterogeneous data from different sources is classified in the dimension of geological structure, which facilitates subsequent integration and overall analysis of different geological structures.

[0083] In one embodiment, the multi-source heterogeneous data is classified in the dimension of geological structure to obtain various geological structure data, including:

[0084] At least one sub-heterogeneous data set is determined from the multi-source heterogeneous data based on a preset screening criterion. For each sub-heterogeneous data set, clustering calculation is performed in the dimension of geological structure, and geological structure data of various geological structure types is obtained based on the clustering calculation results.

[0085] Specifically, at least one sub - heterogeneous data set is determined from multi - source heterogeneous data based on a preset screening criterion. Here, the screening criterion can be determined by relevant technical personnel according to actual needs. When performing clustering calculations for different geological structures, different sub - heterogeneous data sets need to be selected according to actual requirements. For example, there is a set of geological sample data, and the sub - heterogeneous data set includes the following characteristic data: Element content: such as the content of metal elements like copper, lead, zinc, etc.; Rock type: such as granite, sandstone, shale, etc.; Geographic location: such as the longitude and latitude coordinates of the sample. And a suitable clustering algorithm is selected, including but not limited to, K - means clustering algorithm, hierarchical clustering, DBSCAN (Density - Based Spatial Clustering of Applications with Noise), etc. When performing clustering analysis based on the above characteristic data, the algorithm will assign data points to the nearest clustering center, forming three different clusters. Cluster 1 may represent a granite area rich in copper elements, Cluster 2 may represent a sandstone area with relatively high lead and zinc content, and Cluster 3 may represent geological samples with other characteristics, such as shale or rocks with low metal content.

[0086] After confirming the sub - heterogeneous data set, the data can be classified using a clustering algorithm. Specifically: Through the prior knowledge of the data or the results of preliminary experiments, the value of K in the K - means clustering algorithm is determined. For example, when clustering geological spatial data, if it is known approximately how many types of geological types (such as different rock types or geological structure types) the data can be divided into, K can be set to the corresponding value. However, in many practical situations, the value of K may need to be determined through some evaluation methods (such as the elbow method, silhouette coefficient method, etc.). Then, the initial clustering centers are selected. In practical applications, K data points can be randomly selected from the data set as the initial clustering centers. These data points can be actual observation points in the geological spatial data. For example, when processing geological exploration data, they may be K randomly selected drilling positions; when processing geochemical sampling data, they may be K randomly selected sampling points. The selection of the initial clustering centers will affect the final result of the algorithm, and different initial selections may lead to different clustering partitions.

[0087] Then, each data point in the sub - heterogeneous data set is traversed, and the distance from it to the K clustering centers is calculated. In geological spatial data, the Euclidean distance is usually used to measure the distance between a data point and a clustering center. However, in some cases, other distance metrics can also be used according to the characteristics of the data, such as the Manhattan distance. For example, when clustering geological observation points (such as the coordinates of seismic monitoring points) on a two - dimensional plane, the Euclidean distance d=(x2 ‐ x1) 2 +(y2 ‐ y1) 2It can be used to measure the distance between two observation points, where (x1, y1) and (x2, y2) are the coordinates of the two observation points respectively. And each data point is assigned to the cluster represented by the nearest cluster center. For example, when clustering geological structure data, if the distance from a certain structural feature data point to cluster center A is less than the distances to other cluster centers, then this data point is assigned to the cluster represented by cluster center A.

[0088] After completing one round of data point assignment, for each cluster, its cluster center needs to be recalculated. For geological spatial data with numerical attributes, the cluster center is the mean value of the attribute values of all data points in the cluster. For example, when clustering borehole data, if the borehole data in the cluster contains numerical attributes such as formation thickness and rock hardness, then the values of the new cluster center on these attributes are the average values of the corresponding attribute values of all borehole data in the cluster. For spatial data (such as the spatial coordinates of boreholes), the spatial position of the cluster center is the mean value of the spatial coordinates of all data points in the cluster.

[0089] In some cases, if the range of a certain attribute value in the cluster varies greatly or there are outliers, methods such as weighted average may need to be used to calculate the cluster center to avoid the influence of outliers on the cluster center. For example, when clustering geological data containing some special high - value or low - value samples, if the simple average is directly used to calculate the cluster center, it may lead to the deviation of the cluster center from the actual situation. At this time, the weighted average cluster center can be calculated according to the weights of the data points (such as determining the weights according to the reliability and occurrence frequency of the data points).

[0090] In summary, after completing the assignment of data points in the next round, the above - mentioned process is repeated iteratively on this basis until the number of iterations reaches the preset iteration number threshold. Then, the K - means clustering algorithm outputs the result of dividing the sub - heterogeneous data set into K clusters, and each data point is assigned to one of the clusters. Different clustering results represent different geological structure types, and the data in the clustering results represent the geological structure data corresponding to the geological structure type. For example, after clustering geological spatial data, it can be obtained which borehole data belong to the same cluster (which may represent the same type of geological structure and rock type).

[0091] Furthermore, the above - mentioned cluster center information can also be used as the representative point of each cluster. In geological spatial data, the coordinates of the cluster center (for spatial data) and the attribute values (for numerical - type attribute data) can be used to describe the characteristics of the cluster. For example, in the clustering of different rock types, the attribute values such as rock hardness and density of the cluster center can reflect the typical characteristics of this type of rock.

[0092] In one embodiment, according to the characteristic matrix of geological spatial data corresponding to the geological structure type, the geological structure data of the corresponding type is fused to obtain the fused analysis result of the geological structure type, including:

[0093] Input the geological structure data into a well-trained fusion model, and according to the characteristic matrix of the geological spatial data, fuse the geological structure data belonging to the same geological structure type to obtain the fused analysis result. Among them, the fused analysis result includes the geological structure image corresponding to the geological structure type and the geological report for the geological structure type.

[0094] Specifically, input the geological structure data belonging to the same geological structure type into a well-trained fusion model, and combine it with the characteristic matrix corresponding to the geological spatial data to fuse the geological structure data belonging to the same geological structure type to obtain the fused result. Among them, the fused result includes, but is not limited to, the geological structure image corresponding to the geological structure type and the geological report for the geological structure type. Specifically, by processing geological structure data (such as remote sensing images, seismic data, etc.) through the fusion model, automatically identify structural features such as faults and folds, and generate an interpretive image, that is, the above-mentioned geological structure image. This interpretive image is generated based on the original data obtained through geological surveys, explorations, experiments, and research, and after professional processing, analysis, and comprehensive interpretation, it is used to intuitively express geological phenomena, geological features, geological laws, and the interpretation results of geological problems; then, use professional software such as Petrel and Kingdom to convert the fused data (such as seismic horizons, fault data) into a three-dimensional geological structure image or report, that is, the above-mentioned geological report, so as to support multi-angle observation and dynamic interaction. The above-mentioned geological structure report includes, but is not limited to, regional geological background, description of structural features, structural evolution history, engineering geological evaluation, conclusions and suggestions, etc.

[0095] In one embodiment, after obtaining the fused analysis result of the geological structure type, the method further includes:

[0096] Compare and verify the fused analysis result with the obtained real geological data to obtain the accuracy of the fused result;

[0097] And / or, based on the cross-validation algorithm, verify the geological structure data to obtain the accuracy of the fused result;

[0098] Determine the accuracy rate of the fused analysis result based on the accuracy and feedback it to the preset feedback receiver.

[0099] Specifically, this embodiment is used to verify the fusion analysis results. Specifically, the fusion analysis results are compared with known real geological data. For example, the mining area positions predicted by the fusion model are compared with the mining area positions determined by existing geological explorations to obtain the accuracy of the fusion results. If there are large deviations, the reasons need to be analyzed and the fusion model needs to be optimized. Such a comparison can be carried out from multiple aspects, such as the size of the mining area, the shape of the ore body, the ore grade, etc. By making a detailed comparison with known geological facts, the deficiencies of the fusion results are identified and improved.

[0100] And / or, the geological structure data can also be verified based on the cross - validation algorithm. For example, datasets related to geological structures such as basic geology, remote sensing geology, and drilling engineering are divided into a training set and a test set. The fusion model is trained on the training set and then verified on the test set. For example, using K - fold cross - validation, the dataset is divided into K subsets. Each time, K - 1 subsets are used as the training set, and the remaining one subset is used as the test set. This process is repeated K times, and indicators such as the accuracy rate, recall rate, and F1 value of each verification are calculated to obtain the accuracy of the fusion results and comprehensively evaluate the performance of the fusion model.

[0101] According to the accuracy of the verification results, the accuracy rate of the fusion analysis results can be determined and timely feedback is sent to the preset feedback receiving end to notify relevant technical personnel whether the fusion model needs to be optimized. For machine learning and deep learning models, the model parameters (such as the weights, number of layers, and number of neurons in the neural network) can be adjusted, or a more advanced algorithm structure (such as an improved convolutional neural network structure) can be adopted. Additionally, the training data volume can be increased (through data augmentation techniques) to improve the generalization ability and fusion accuracy of the model.

[0102] It should be understood that although the steps in the flowcharts involved in the above - mentioned embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above - mentioned embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0103] Based on the same inventive concept, an embodiment of the present application further provides an analysis device for geological spatial data for implementing the above-mentioned analysis method for geological spatial data. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the analysis device for geological spatial data provided below can refer to the limitations on the analysis method for geological spatial data in the above text, and will not be elaborated here.

[0104] In one embodiment, as Figure 3 shown, an analysis device for geological spatial data is provided, including: a collection module 31, a calculation module 32, and a generation module 33, where:

[0105] The collection module 31 is used to collect multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types;

[0106] The calculation module 32 is used to determine the geological characteristics of the geological spatial data of each geological data type, and establish a feature matrix of the geological spatial data of the corresponding type based on the geological characteristics; classify the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type;

[0107] The generation module 33 is used to fuse the geological structure data of the corresponding type according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain the fusion analysis result of the geological structure type.

[0108] Each module in the above analysis device for geological spatial data can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in the form of hardware or be independent of it, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0109] In one embodiment, a computer device is provided. This computer device can be a server, and its internal structure diagram can be as Figure 4As shown in the figure. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to data analysis. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes an analysis method for geological spatial data.

[0110] Those skilled in the art can understand that Figure 4 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0111] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are realized:

[0112] Collect multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of various different geological data types;

[0113] Determine the geological characteristics of the geological spatial data of each geological data type, and establish a feature matrix for the geological spatial data of the corresponding type based on the geological characteristics;

[0114] Classify the multi-source heterogeneous data in the dimension of geological structure to obtain various geological structure data, where each geological structure data corresponds to a geological structure type;

[0115] According to the feature matrix of the geological spatial data corresponding to the geological structure type, fuse the geological structure data of the corresponding type to obtain a fused analysis result of the geological structure type.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0117] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0118] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0119] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for analyzing geological spatial data, characterized in that, The method includes: Collecting multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types; Determining the geological characteristics of the geological spatial data of each geological data type, and establishing a feature matrix for the geological spatial data of the corresponding type based on the geological characteristics; Classifying the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type; Fusing the geological structure data of the corresponding type according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain the fusion analysis result of the geological structure type.

2. The method according to claim 1, wherein Establishing the spatial data standard includes: Establishing a standardized data format specification, a standardized data content specification, and a standardized coordinate system; Assigning a unified code to each geological element, where each geological element after unified coding corresponds to a unique code.

3. The method according to claim 2, wherein The collecting of multi-source heterogeneous data based on a preset spatial data standard includes: Obtaining initial data; Performing format conversion processing on the initial data, and unifying the coordinate system of the initial data based on the standardized coordinate system; Cleaning the unified initial data to obtain the multi-source heterogeneous data.

4. The method according to claim 1, wherein The classifying of the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data includes: Inputting the multi-source heterogeneous data into a trained classification model, and classifying the multi-source heterogeneous data in the dimension of geological structure through the classification model to obtain geological structure data of multiple geological structure types.

5. The method according to claim 1, characterized in that, The classifying of the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data includes: Determining at least one sub-heterogeneous data set from the multi-source heterogeneous data based on a preset screening criterion, and for each sub-heterogeneous data set, performing clustering calculation in the dimension of geological structure, and obtaining the geological structure data of multiple geological structure types based on the clustering calculation result.

6. The method according to claim 1, characterized in that, The fusing of the geological structure data of the corresponding type according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain the fusion analysis result of the geological structure type includes: Inputting the geological structure data into a trained fusion model, and fusing the geological structure data belonging to the same geological structure type according to the feature matrix of the geological spatial data to obtain the fusion analysis result, where the fusion analysis result includes a geological structure image corresponding to the geological structure type and a geological report for the geological structure type.

7. The method according to claim 1, wherein After obtaining the fusion analysis result of the geological structure type, the method further includes: Comparing and verifying the fusion analysis result with the obtained real geological data to obtain the accuracy of the fusion analysis result; And / or, verifying the geological structure data based on a cross-validation algorithm to obtain the accuracy of the fusion analysis result; Determine the accuracy rate of the fusion analysis result based on the accuracy, and feedback it to a preset feedback receiver.

8. An analysis device for geological spatial data, characterized in that, The device includes: An acquisition module, configured to acquire multi-source heterogeneous data based on a preset spatial data standard, where the multi-source heterogeneous data includes geological spatial data of multiple different geological data types; A calculation module, configured to determine the geological features of the geological spatial data of each geological data type, and establish a feature matrix of the geological spatial data of the corresponding type based on the geological features; classify the multi-source heterogeneous data in the dimension of geological structure to obtain multiple geological structure data, where each geological structure data corresponds to a geological structure type; A generation module, configured to fuse the geological structure data of the corresponding type according to the feature matrix of the geological spatial data corresponding to the geological structure type to obtain the fusion analysis result of the geological structure type.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images