Geological mineral exploration data extraction method and system

Abstract

The invention relates to the technical field of mining industry, in particular to a geological mineral exploration data extraction method and system, and the method comprises the following steps: obtaining rock sample data, carrying out the standardization processing of the rock sample data, removing the noise and interference in the rock sample data, carrying out the trend analysis of the rock sample data, and carrying out the analysis of the trend of the rock sample data. And geological anomalies in the rock sample data are identified, and a time dependence analysis result is generated. According to the method, the capacity of capturing tiny changes of geological data is enhanced, standardization processing and noise removal are combined, and the recognition rate of geological anomalies is increased. And abnormal data points are identified by using trend analysis and abnormal score calculation, and the accuracy of the result is ensured through simulation and cross validation. The method not only improves the accuracy of resource evaluation, but also optimizes the positioning process of mineral resources. And meanwhile, through resource richness prediction and distribution characteristic analysis, the potential of mineral resources is fully excavated.

Description

Technical Field

[0001] The present invention relates to the technical field of mining, and particularly to a method and system for extracting geological and mineral exploration data. Background Art

[0002] The technical field of mining involves the science, technology, and engineering methods for extracting minerals from the earth's crust. This includes exploring, mining, refining, and processing various natural resources to obtain useful geological materials.

[0003] However, in the existing technology, the accuracy of resource assessment and operation efficiency are average, and there is room for improvement in maximizing the development of resource potential. At the same time, the lack of trend analysis and clustering analysis often makes the resource development plan formulated based on incomplete or highly error-prone data, increasing the economic burden and development risks. Therefore, improvements are needed. Summary of the Invention

[0004] The object of the present invention is to solve the drawbacks existing in the prior art, and to propose a method and system for extracting geological and mineral exploration data.

[0005] To achieve the above object, the present invention adopts the following technical solutions. A method for extracting geological and mineral exploration data includes the following steps: Obtain rock sample data, perform standardization processing on the rock sample data to remove noise and interference in the rock sample data, perform trend analysis on the rock sample data, identify geological anomalies in the rock sample data, and generate a time-dependent analysis result; Based on the time-dependent analysis result, calculate the anomaly score of each geological anomaly data point in the time-dependent analysis result, identify the anomaly data points to obtain an anomaly detection result, and perform simulation and cross-validation on the anomaly detection result to generate a complete anomaly result; Perform clustering processing on the complete anomaly result, divide the complete anomaly result into multiple resource positioning regions to obtain a mineral area division result, perform centroid analysis on each resource positioning region in the mineral area division result to locate the concentrated area of mineral resources, and generate a mineral area positioning result; Based on the mineral area positioning result, predict the resource richness of each concentrated area of mineral resources, analyze the distribution characteristics and potential of mineral resources in the concentrated area to obtain a resource distribution prediction result, and perform visual display of data based on the resource distribution prediction result to generate a resource distribution prediction map.

[0006] Preferably, the step of obtaining the time-dependent analysis result is: Obtain rock sample data, and perform standardization processing on the rock sample data to remove noise and interference to obtain standardized rock sample data; Based on the standardized rock sample data, perform trend analysis on the standardized rock sample data to identify geological anomaly points. The calculation formula is: ; where, is the anomaly score of the i-th data point, is the value of the i-th data point, is the mean of the sample data, is the standard deviation of the sample data; According to the anomaly score, identify the anomaly points and integrate the anomaly points to generate the time-dependent analysis result of the rock sample data.

[0007] Preferably, the steps for obtaining the anomaly detection result are as follows: Based on the time-dependent analysis result, extract the anomaly scores of each data point to obtain the basic anomaly score dataset; Process each data point in the basic anomaly score dataset. The processing formula is: ; where, is the weighted anomaly score of the i-th data point, is the anomaly score of the k-th data point, is the average value of the anomaly scores, is the total number of data points; Based on the weighted anomaly scores, identify the geological anomaly data points and generate the anomaly detection result.

[0008] Preferably, the steps for obtaining the complete anomaly result are as follows: Based on the anomaly detection result, deploy a simulation test environment and perform a simulation run using the past geological dataset to obtain the simulation verification result; According to the simulation verification result, design a cross-validation process, and use historical data to batch-verify the consistency and repeatability of the anomaly detection result to generate the cross-validation result; According to the cross-validation result, organize the detected anomalies to form the complete anomaly result.

[0009] Preferably, the steps for obtaining the mineral area division result are as follows: Based on the complete anomaly result, group the anomaly data, identify and summarize the anomaly points with similar geological characteristics to obtain the resource clustering grouping result; Analyze the resource clustering grouping result, judge the geological similarity and spatial continuity of the anomaly data points within each cluster, and generate the refined resource clustering analysis result; According to the refined resource clustering analysis results, define and divide the resource positioning areas, determine the boundaries and characteristics of each resource positioning area, and obtain the mineral area division results.

[0010] Preferably, the steps for obtaining the mineral area positioning results are as follows: Based on the mineral area division results, extract the geological data points of each resource positioning area to obtain a set of geological data points; Based on the set of geological data points, calculate the average geographical location of each data point to determine the centroid coordinates of each resource positioning area. The calculation formula is: and ; where, and are respectively the positions of the centroid of the resource positioning area on the x and y coordinates, and are the geographical coordinates of the i-th data point, is the importance score of the geological characteristics of the i-th data point, is the total number of data points; Based on the centroid coordinates, determine the concentrated areas of mineral resources and generate the mineral area positioning results.

[0011] Preferably, the steps for obtaining the resource distribution prediction results are as follows: Based on the mineral area positioning results, extract the centroid coordinates, geological composition, exploration records, and geographical characteristics of each positioning area to obtain a basic data set; Based on the basic data set, calculate the resource richness score. The calculation formula is: ; where, is the resource richness score of the j-th mineral area, is the geological composition index of the i-th data point, is the weighted coefficient of the geological exploration index of the data point, is the total number of data points; According to the resource richness scores of each area, conduct a quantitative analysis of the distribution characteristics of mineral resources, judge the exploitation potential and economic value of mineral resources, and obtain the resource distribution prediction results.

[0012] The present invention provides a geological and mineral exploration data extraction system, including: A data preprocessing module, which obtains rock sample data, performs standardization processing on the rock sample data, removes noise and interference in the rock sample data, conducts trend analysis on the rock sample data, and generates standardized and trend analysis data; The geological anomaly recognition module calculates the anomaly scores for each data point based on standardized and trend analysis data, identifies anomalous data points, simulates and cross - validates the anomaly detection results to generate geological anomaly detection results, and performs cluster analysis on the geological anomaly detection results to obtain cluster anomaly results; The mineral resource location module, based on the cluster anomaly results, conducts centroid analysis on each resource location area to locate the concentrated areas of mineral resources, predicts the resource richness of each concentrated area of mineral resources, analyzes the distribution characteristics and potential of mineral resources within the concentrated areas, and performs visual display of data to generate a resource distribution prediction map.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are as follows: The present invention enhances the ability to capture minor changes in geological data. By combining standardized processing and noise removal, it improves the recognition rate of geological anomalies. It uses trend analysis and anomaly score calculation to identify anomalous data points, and ensures the accuracy of the results through simulation and cross - validation. This not only improves the accuracy of resource assessment but also optimizes the process of locating mineral resources. At the same time, through resource richness prediction and distribution characteristic analysis, the potential of mineral resources is fully explored, and the generation of the resource distribution prediction map provides intuitive visual support for decision - making. It improves the efficiency and economy of mineral exploration. Brief Description of the Drawings

[0014] Figure 1 It is a schematic diagram of the steps of the present invention. Detailed Embodiment

[0015] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0016] Please refer to Figure 1 , the present invention provides a technical solution, a method for extracting geological and mineral exploration data, including the following steps: Obtain rock sample data, perform standardized processing on the rock sample data to remove noise and interference in the rock sample data, conduct trend analysis on the rock sample data to identify geological anomalies in the rock sample data, and generate a time - dependent analysis result; Based on the time - dependent analysis result, calculate the anomaly scores for each geological anomaly data point in the time - dependent analysis result, identify anomalous data points to obtain an anomaly detection result, and simulate and cross - validate the anomaly detection result to generate a complete anomaly result; Cluster the complete abnormal results, divide the complete abnormal results into multiple resource location regions to obtain the mineral area division results, perform centroid analysis on each resource location region in the mineral area division results to locate the concentrated regions of mineral resources, and generate the mineral area location results; Based on the mineral area location results, predict the resource richness of the concentrated regions of each mineral resource, analyze the distribution characteristics and potential of the mineral resources in the concentrated regions to obtain the resource distribution prediction results, and perform visual display of the data based on the resource distribution prediction results to generate the resource distribution prediction map.

[0017] The steps for obtaining the time-dependence analysis results are as follows: Obtain rock sample data, and perform standardization processing on the rock sample data to remove noise and interference to obtain the standardized rock sample data; Based on the standardized rock sample data, perform trend analysis on the standardized rock sample data to identify geological abnormal points. The calculation formula is: ; where, is the abnormal score of the i-th data point, is the value of the i-th data point, is the mean value of the sample data, is the standard deviation of the sample data; According to the abnormal scores, identify the abnormal points and integrate the abnormal points to generate the time-dependence analysis results of the rock sample data.

[0018] Specifically, obtain the rock sample data, which is immediately sent to the laboratory for analysis after being obtained. The laboratory first uses a scanning electron microscope to perform high-resolution imaging on the sample. Through the imaging data, supplemented by spectral analysis, accurately identify the mineral composition and texture structure in the sample. After that, the sample data is cleaned by an algorithm to remove various potential noises and environmental interferences caused by the equipment, such as electromagnetic interference and temperature change effects. This step ensures the accuracy of subsequent data processing, and the generated result is the cleaned and standardized rock sample data.

[0019] Formula: The advantage of is that it can calculate the deviation degree of each rock sample data point from the population average value. This deviation is standardized and reflects the abnormal degree of the data point, which is crucial for the detection of geological anomalies because it allows researchers to quickly identify areas that may contain mineral resources; the parameter is the value of the specific data point obtained by the laboratory scanning electron microscope and spectral analysis; the parameter is obtained by taking the arithmetic mean of all rock sample data point values; the parameter is obtained by calculating the standard deviation of all sample data point values.

[0020] Calculation process: There is a set of data points in the sample , obtained through data monitoring, calculate the average value and the standard deviation , for example , , and calculate the anomaly score of the first data point : ; This result indicates that represents the value is higher than the average by one standard deviation, which indicates a geological anomaly.

[0021] According to the anomaly scores of each data point, by comparing the points with scores higher than a certain set threshold, these points are marked as significant geological anomalies. This threshold is obtained through statistical analysis of historical geological data. For example, the set threshold is 2, that is, the score of the data point needs to be greater than 2 to be considered a significant anomaly. These marked points are then integrated and analyzed, combined with the geological map and existing geological information, to determine the possible mineral resources at these anomaly points. The generated result is the time-dependent analysis result of the rock sample data, which is provided to the mineral exploration company as the basis for further prospecting decisions.

[0022] The steps to obtain the anomaly detection result are as follows: Based on the time-dependent analysis result, extract the anomaly score of each data point to obtain the basic anomaly score data set; Process each data point in the basic anomaly score data set, and the processing formula is: ; Among them, is the weighted anomaly score of the i-th data point, is the anomaly score of the k-th data point, is the average value of the anomaly scores, is the total number of data points; Based on the weighted anomaly scores, identify the geological anomaly data points to generate the anomaly detection result.

[0023] Specifically, based on the time-dependent analysis results of rock sample data, the anomaly scores of each data point are extracted. This process first requires establishing a basic data set that includes all data points. This data set contains the values of each data point identified through trend analysis in the previous step. The extraction of each data point is determined based on its degree of deviation from the average trend line. The anomaly score is obtained by calculating the difference between the data point and the trend line. The larger these values are, the more obvious the anomaly of the point. The calculation of the anomaly score is not just a simple difference, but also includes the relative position of the point in the overall data set and its relative relationship with adjacent points. These calculations are completed through continuous iteration and comparison to obtain the basic anomaly score data set.

[0024] Formula The advantage is that by calculating the sum of the squares of the deviations of each data point from the average value and then taking the square root of the mean value, it can effectively enhance the sensitivity to outliers. Especially when the distribution of data points is uneven, it can more accurately identify the true geological anomaly points, thereby reducing misjudgments in geological exploration.

[0025] Calculation process: Set as the specific anomaly score, as the average value of all anomaly scores, as the total number of data points. For example, if the scores of 5 data points are {2, 4, 5, 8, 11}, then the average value , the squared deviations of the scores of each data point from the average value are {16, 4, 1, 4, 25}, the sum is 50, the average is 10, and its square root is 3.16, obtaining The calculated value of represents the weighted anomaly score.

[0026] The weighted anomaly score of 3.16 represents that in this sample, the significance of geological anomalies has been significantly improved compared to the average level. If this value is large, it indicates that the anomaly points are more concentrated and significant, otherwise the distribution is more extensive and not obvious.

[0027] Based on the weighted anomaly score Si, the threshold analysis method is applied to identify significant geological anomaly data points. This step first sets a threshold, which is usually obtained based on historical data analysis to ensure that the threshold can cover most possible anomaly situations while not causing misjudgments due to too low a threshold setting. Data points with a weighted anomaly score greater than or equal to this threshold are identified as geological anomaly points. This judgment criterion is achieved by comparing the weighted scores of each data point with the threshold. Through this method, anomaly data points with geological exploration value can be efficiently and accurately screened out to generate anomaly detection results.

[0028] The steps to obtain the complete anomaly result are: Based on the anomaly detection results, a simulation test environment is deployed and simulated using past geological data sets to obtain simulation verification results; According to the simulation verification results, a cross-validation process is designed. Historical data is used in batches to verify the consistency and repeatability of the anomaly detection results, and cross-validation results are generated; Based on the cross-validation results, the detected anomalies are sorted out to form a complete anomaly result.

[0029] Specifically, based on the anomaly detection results, a simulation test environment is deployed to verify the reliability of the results. Historical geological data sets are used for simulation to actually verify the anomaly detection results. The simulation test includes running multiple geological data. These historical data contain geological samples from different regions and different ages. Each sample is pre-labeled with anomalies by geological experts for comparative analysis. During the test, the anomaly detection results are compared with the expert labels. Statistical analysis includes precision, recall, and F1 score. These statistical metrics reflect the model's ability to identify geological anomalies. The preliminary simulation verification results show the performance of the anomaly detection model on different data sets and provide a preliminary assessment of the model's stability and reliability.

[0030] Starting from the preliminary simulation verification results, a cross-validation process is designed. This process uses historical geological data sets and tests the consistency and repeatability of the anomaly detection results with different batches of data. This cross-validation includes dividing the data set into multiple subsets and alternately using some subsets as training data and the remaining subsets as test data. By this method, the performance of the model on new and unseen data can be evaluated. During the cross-validation process, a verification result is generated for each iteration. These results are used to calculate average metrics of the model performance, such as average precision and average recall. Through these metrics, the overall performance of the anomaly detection results can be accurately estimated, and finally cross-validation results are generated.

[0031] By integrating the results of simulation tests and cross-validation, the overall performance of the anomaly detection model is evaluated. This comprehensive evaluation covers metrics obtained from multiple test cycles and data sets, such as overall precision, recall, and the model's ability to identify new anomalies. By statistically analyzing these metrics, the effectiveness and reliability of the model in practical applications can be comprehensively understood. In addition, a detailed statistical analysis of the detected anomalies is carried out, including the frequency, distribution of anomaly types, and possible geological causes. These comprehensive analyses help geologists and engineers improve the method of identifying geological anomalies and finally form a complete anomaly result.

[0032] The steps to obtain the mineral area division results are as follows: Based on the complete anomaly results, the anomaly data is grouped, and the anomaly points with similar geological characteristics are identified and summarized to obtain the resource clustering grouping results; Analyze the results of resource clustering and grouping, judge the geological similarity and spatial continuity of abnormal data points within each cluster, and generate a refined resource clustering analysis result; According to the refined resource clustering analysis result, define and divide the resource positioning areas, determine the boundaries and characteristics of each resource positioning area, and obtain the mineral area division result.

[0033] Specifically, based on the complete abnormal results, use the K-means clustering algorithm to group the abnormal data. First, initialize K clustering centers, and allocate the data points to the nearest clustering center according to the Euclidean distance between each data point and the clustering center for the first round of clustering. Optimize the positions of the clustering centers through multiple iterations until the clustering centers are stable. Calculate the mean value of each cluster in each iteration, re-determine the clustering centers, and repeat this process until the sum of the distances from each data point to its clustering center is minimized. This process effectively summarizes the abnormal points with similar geological characteristics, thereby obtaining the preliminary resource clustering and grouping result.

[0034] In the preliminary resource clustering and grouping result, conduct in-depth analysis on each cluster, evaluate the abnormal data points within each cluster, calculate the similarity of geographical and geological indicators between points within the cluster, and use statistical methods to compare the standard deviation and coefficient of variation of the data points within each cluster to ensure the spatial continuity and consistency of geological characteristics of the cluster. Use this method to confirm whether each cluster represents a single geological structure. If so, further refine the cluster; if not, adjust the clustering parameters and re-cluster. Through this process, ensure that each cluster represents a potential mineral resource area, and finally generate a refined resource clustering analysis result.

[0035] According to the refined resource clustering analysis result, determine the specific boundaries of each mineral resource positioning area, draw the geological map and resource distribution map of each area through GIS tools, accurately divide the boundaries of each cluster area, analyze the geological data and historical mineral mining data within the area, evaluate the mineral resource potential and mining value of each area, and finally define the characteristics and boundaries of each resource positioning area based on these data to accurately obtain the mineral area division result.

[0036] The steps to obtain the mineral area positioning result are as follows: Based on the mineral area division result, extract the geological data points of each resource positioning area to obtain a set of geological data points; Based on the set of geological data points, calculate the average value of the geographical positions of each data point to determine the centroid coordinates of each resource positioning area. The calculation formula is: and ; where and are the positions of the centroid of the resource location area on the x and y coordinates, respectively, and are the geographical coordinates of the i-th data point, is the importance score of the geological characteristics of the i-th data point, is the total number of data points; Based on the centroid coordinates, determine the concentrated area of mineral resources and generate the mineral area location result.

[0037] Based on the mineral area division result, analyze the geological data points of each resource location area. These data points include geographical coordinates and related geological characteristics. This process ensures an accurate understanding of mineral resources. By finely extracting the geological data of each resource location area, a complete set of geological data points can be obtained. This set provides the necessary basic data for subsequent analysis. The set of these data reflects the geological characteristics and potential resource distribution of each area and is a prerequisite for centroid analysis.

[0038] The benefit of the formula is that it can more accurately determine the geographical center of the resource location area through the weighted average of geographical coordinates and the importance score of geological characteristics. This helps to accurately locate the concentrated area of mineral resources, thereby improving the efficiency and accuracy of resource development; the parameters and represent the geographical coordinates of each data point, usually obtained through on-site measurement or remote sensing data; the parameter represents the importance score of geological characteristics, which is obtained based on geological exploration data and historical geological data analysis; the parameter is the total number of data points, which is obtained by counting all available geological sample points.

[0039] Calculation process: There are three data points, and their coordinates and characteristic importance scores are (10, 3), (15, 5), (20, 2) respectively. Then calculate C x and C y as follows: ; ; The result shows that the x coordinate of the centroid is 14.5 and the y coordinate is 24.5, indicating the accurate center position of the resource location area and facilitating resource location and development in practical applications.

[0040] Determine the concentrated area of mineral resources based on the centroid coordinates, and analyze how the centroid coordinates affect the final positioning of the mineral areas. This process not only reflects the weighted average position of each data point in terms of geographical and geological characteristics, but also establishes the effective distribution of mineral resources. The generated positioning results of the mineral areas contribute to subsequent resource development planning and management, providing a clear geographical reference to ensure the effectiveness and feasibility of resource development.

[0041] The steps to obtain the prediction results of resource distribution are as follows: Based on the positioning results of the mineral areas, extract the centroid coordinates, geological composition, exploration records, and geographical characteristics of each positioning area to obtain a basic data set; Based on the basic data set, calculate the resource richness score, and the calculation formula is: ; Where, is the resource richness score of the jth mineral area, is the geological composition index of the ith data point, is the weighted coefficient of the geological exploration index of the data point, is the total number of data points; According to the resource richness score of each area, conduct a quantitative analysis of the distribution characteristics of mineral resources, judge the mining potential and economic value of mineral resources, and obtain the prediction results of resource distribution.

[0042] Specifically, based on the positioning results of the mineral areas, extract the centroid coordinates and relevant geological data of each positioning area, including geological composition, historical exploration records, and geographical characteristics. These data are sourced from existing geological exploration archives and GIS analysis, and will be used to construct an analysis model for resource richness. The basic data set for resource richness analysis includes geological composition data and historical exploration data of hundreds of sample points collected from different mining areas. These data will be screened and verified through the evaluation of geological experts to ensure their accuracy and relevance, obtaining a set of highly accurate data sets for analysis.

[0043] Formula has the advantage that, through the method of weighted sum of squares, it emphasizes the importance of data points with higher geological composition indices, and at the same time, through the averaging process of the overall number of data points, effectively balances the contributions of each data point in the evaluation of resource richness, which is particularly important in mining areas with complex geological structures; the parameter is the geological composition index of each data point, obtained through geological sample analysis and historical data records; the parameter is the weighted coefficient of the geological exploration index, obtained based on the effectiveness of historical exploration and the importance score of geological data; the parameter is the total number of data points, directly counted from the data set.

[0044] Calculation process: Suppose there are 10 data points in a specific mineral area, and the geological composition index of each point and the weighted coefficient of geological exploration indicators are as follows respectively: ; ; The brief calculation process is as follows: ; ; ; ; This result indicates that the average resource richness score of this mineral area is 0.782, which shows that this area has medium resource potential and is a target worthy of further exploration for mining companies.

[0045] According to the resource richness scores of each area, a quantitative analysis of the distribution characteristics of mineral resources is carried out. By evaluating the exploitation potential and economic value of resources, this process includes sorting the resource richness scores of each mineral area from high to low and conducting a detailed analysis of the geological structure of high-score areas to determine the exploitation priority and investment value of these areas. Areas with high resource richness will be marked as high-potential areas, and these areas will be recommended to the management team for further detailed exploration. The obtained resource distribution prediction results provide a scientific basis for mining development and important information for investment decisions.

[0046] The steps to obtain the resource distribution prediction map are as follows: Extract the resource richness scores and geographical coordinates of each mineral area from the resource distribution prediction results and organize them into a basic data set; Import the basic data set into GIS software, set the map scale, color gradient and legend of the GIS software, and generate the resource distribution prediction map.

[0047] Specifically, extracting the resource richness scores and their geographical coordinates of each mineral area from the resource distribution prediction results. This step first involves accessing the prediction results stored in the database. By writing SQL query statements, select the records containing the resource richness and their corresponding geographical coordinates to ensure that the extracted data accurately corresponds to each mineral area. Special attention should be paid to the accuracy and execution efficiency of the SQL statements during the query operation to avoid redundancy and errors in the data extraction process. At the same time, necessary data verification and format adjustment are performed on the extracted data to meet the input requirements of subsequent processing steps, and then organize them into a basic data set.

[0048] Import the basic dataset into the GIS software. This step includes loading the sorted basic dataset through the data import tool of the GIS software. It is necessary to set appropriate data formats and coordinate systems before import to ensure that the data can be correctly mapped into the geospatial space. Then, set the visual parameters of the map in the GIS software, such as scale, color gradient, and legend. These parameter settings are based on predefined visual standards to ensure that the information display on the map is both beautiful and practical. By adjusting the color gradient to reflect different levels of resource richness, the readability of the map and the effectiveness of information transmission are enhanced. After completing these settings, use the drawing function of the GIS software to generate the final resource distribution prediction map, which clearly shows the distribution of various mineral resources and their richness levels.

[0049] The present invention provides a geological and mineral exploration data extraction system, including: A data preprocessing module, which acquires rock sample data, performs standardization processing on the rock sample data, removes noise and interference in the rock sample data, performs trend analysis on the rock sample data, and generates standardized and trend analysis data; A geological anomaly identification module, which calculates the anomaly score of each data point based on the standardized and trend analysis data, identifies abnormal data points, simulates and cross - validates the anomaly detection results, generates geological anomaly detection results, and performs clustering analysis on the geological anomaly detection results to obtain clustering anomaly results; A mineral resource location module, which performs centroid analysis on each resource location area based on the clustering anomaly results, locates the concentrated areas of mineral resources, predicts the resource richness of each concentrated area of mineral resources, analyzes the distribution characteristics and potential of mineral resources in the concentrated areas, and performs visual display of the data to generate a resource distribution prediction map.

[0050] The above is only a preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the relevant art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for extracting geological and mineral exploration data, characterized in that Including the following steps: Obtain rock sample data, perform standardization processing on the rock sample data, remove noise and interference in the rock sample data, perform trend analysis on the rock sample data, identify geological anomalies in the rock sample data, and generate a time-dependency analysis result; Based on the time-dependency analysis result, calculate the anomaly score of each geological anomaly data point in the time-dependency analysis result, identify anomaly data points, obtain an anomaly detection result, perform simulation and cross-validation on the anomaly detection result, and generate a complete anomaly result; Perform clustering processing on the complete anomaly result, divide the complete anomaly result into multiple resource location regions, obtain a mineral area division result, perform centroid analysis on each resource location region in the mineral area division result, locate the concentrated areas of mineral resources, and generate a mineral area location result; Based on the mineral area location result, predict the resource richness of the concentrated areas of each mineral resource, analyze the distribution characteristics and potential of the mineral resources in the concentrated areas, obtain a resource distribution prediction result, and perform visual display of data based on the resource distribution prediction result to generate a resource distribution prediction map.

2. The geological and mineral exploration data extraction method according to claim 1, wherein The steps for obtaining the time-dependency analysis result are as follows: Obtain rock sample data, and perform standardization processing on the rock sample data to remove noise and interference to obtain standardized rock sample data; Based on the standardized rock sample data, perform trend analysis on the standardized rock sample data to identify geological anomaly points, and the calculation formula is: ； Among them, is the anomaly score of the i-th data point, is the value of the i-th data point, is the mean of the sample data, is the standard deviation of the sample data; According to the anomaly score, identify anomaly points, and integrate the anomaly points to generate a time-dependency analysis result of the rock sample data.

3. The geological and mineral exploration data extraction method according to claim 1, wherein The steps for obtaining the anomaly detection result are as follows: Based on the time-dependency analysis result, extract the anomaly score of each data point to obtain a basic anomaly score data set; Process each data point in the basic anomaly score data set, and the processing formula is: ； Among them, is the weighted anomaly score of the i-th data point, is the anomaly score of the k-th data point, is the average value of the anomaly scores, is the total number of data points; Based on the weighted anomaly score, identify geological anomaly data points and generate an anomaly detection result.

4. The geological and mineral exploration data extraction method according to claim 1, wherein The steps for obtaining the complete anomaly result are as follows: Based on the anomaly detection result, deploy a simulation test environment, perform simulation runs using past geological data sets, and obtain a simulation verification result; According to the simulation verification result, design a cross-validation process, and use historical data to batch-verify the consistency and repeatability of the anomaly detection result to generate a cross-validation result; According to the cross-validation result, organize the detected anomalies to form a complete anomaly result.

5. The geological and mineral exploration data extraction method according to claim 1, characterized in that The steps for obtaining the mineral area division result are as follows: Based on the complete anomaly result, group the anomaly data, identify and summarize anomaly points with similar geological characteristics, and obtain a resource clustering grouping result; Analyze the resource clustering grouping result, judge the geological similarity and spatial continuity of the anomaly data points within each cluster, and generate a refined resource clustering analysis result; According to the refined resource clustering analysis result, define and divide resource location regions, determine the boundaries and characteristics of each resource location region, and obtain a mineral area division result.

6. The geological and mineral exploration data extraction method according to claim 1, wherein The steps for obtaining the mineral area location result are as follows: Based on the mineral region division results, extract the geological data points of each resource location area to obtain a set of geological data points; Based on the set of geological data points, calculate the average geographical location of each data point, and determine the centroid coordinates of each resource location area. The calculation formula is: and ; wherein, and are the positions of the centroid of the resource location area on the x and y coordinates respectively, and are the geographical coordinates of the i-th data point, is the importance score of the geological feature of the i-th data point, is the total number of data points; Based on the centroid coordinates, determine the concentrated areas of mineral resources and generate the mineral region location results.

7. The geological and mineral exploration data extraction method according to claim 1, characterized in that The steps for obtaining the resource distribution prediction results are as follows: Based on the mineral region location results, extract the centroid coordinates, geological compositions, exploration records, and geographical features of each location area to obtain a basic data set; Based on the basic data set, calculate the resource richness score. The calculation formula is: ； Among them, is the resource richness score of the j-th mineral region, is the geological composition index of the i-th data point, is the weighted coefficient of the geological exploration index of the data point, is the total number of data points; According to the resource richness scores of each area, conduct a quantitative analysis of the distribution characteristics of mineral resources, judge the mining potential and economic value of mineral resources, and obtain the resource distribution prediction results.

8. A geological and mineral exploration data extraction system for the geological and mineral exploration data extraction method according to any one of claims 1-7, characterized in that, Including: A data preprocessing module that obtains rock sample data, performs standardization processing on the rock sample data, removes noise and interference in the rock sample data, conducts trend analysis on the rock sample data, and generates standardized and trend analysis data; A geological anomaly identification module that, based on the standardized and trend analysis data, calculates the anomaly scores of each data point, identifies abnormal data points, simulates and cross - validates the anomaly detection results, generates geological anomaly detection results, and conducts cluster analysis on the geological anomaly detection results to obtain cluster anomaly results; A mineral resource location module that, based on the cluster anomaly results, conducts centroid analysis on each resource location area to locate the concentrated areas of mineral resources, predicts the resource richness of each concentrated area of mineral resources, analyzes the distribution characteristics and potential of mineral resources in the concentrated areas, and conducts visual display of the data to generate a resource distribution prediction map.

Images