Big data intelligent prospecting operation method based on multi-source geological relation data

Abstract

The invention provides a big data intelligent prospecting operation method based on multi-source geological relation data. An artificial intelligence technology, a big data technology and a geological theory research result are applied to the technical field of mineral exploration. The method comprises the following steps: respectively collecting or constructing detailed knowledge maps of a single ore type or multiple ore types according to different conditions, and dividing a prospecting target area into a plurality of unit modules with spatial information as most basic geological relationship knowledge map carrier units; on the basis, corresponding attribute contents are endowed to the unit modules on the basis of spatial positions, description contents and geological knowledge; performing knowledge fusion and disambiguation on the attribute content in the unit module by referring to an existing related mineral type knowledge graph, and constructing a geological relationship knowledge graph of the unit module; and according to the weight, obtaining the score of each unit module or the mineralization possibility score of different types of ore types of each unit module, thereby efficiently and accurately delineating the prospecting prospective area or determining the dominant ore types.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data intelligent prospecting, and specifically relates to a big data intelligent prospecting operation method based on multi-source geological relationship data. Background Art

[0002] Mineral resources are an important material basis for economic and social development. In recent years, with the rapid development and popularization of artificial intelligence technology and big data technology, big data intelligent prospecting methods - the integration of artificial intelligence technology and big data technology with traditional mineral exploration technology, have gradually become one of the most active technological frontiers in the field of mineral exploration, and many valuable research results have emerged. For example, the invention patent with authorization announcement number CN117557401B discloses a method for intelligent delineation of uranium prospecting target areas based on geological big data. The main technical contents of this method are as follows:

[0003] Collect different logging curves corresponding to different historical and current mines, and obtain historical logging data and current logging data according to the different logging curves;

[0004] Construct a preset data-driven model, input historical logging data and current logging data into the preset data-driven model, and obtain a historical geological feature matrix and a current geological feature matrix; match the historical geological feature matrix with the current geological feature matrix to obtain approximate geological feature data of the current uranium prospecting target area to be delineated;

[0005] Constructing a three-dimensional histogram based on the geological feature data, calculating the matching degree of nodes in the historical geological feature matrix and the current geological feature matrix and the local matching degree between individual boreholes, and obtaining the best matching result of the current geological feature data;

[0006] Calculate the local approximation between the historical geological feature matrix and the current geological feature matrix, and then establish a rectangular coordinate system with the first target data value as the origin, obtain the slope and distance values ​​according to the binary group of the rectangular coordinate system, and obtain the distribution of adjacent boreholes in the rectangular coordinate system according to the slope and distance values;

[0007] Obtaining coordinates of adjacent drill holes in the first target data value in a rectangular coordinate system and a minimum distance value between adjacent drill holes in the second target data value, calculating the mine hole matching degree of the minimum distance value and the distance value from the drill hole of the minimum distance value in the second target data value to the origin, and obtaining a local matching degree between the first completely undirected graph and the second completely undirected graph;

[0008] According to the best matching result, the data distribution of the current geological characteristic data is obtained; according to the data distribution, the hit ratio of the same geological characteristic data is calculated, and based on the hit ratio, the intelligent delineation of the uranium prospecting target area is completed;

[0009] Constructing graph structure data of the historical geological feature matrix and the current geological feature matrix to obtain a first completely undirected graph and a second completely undirected graph, wherein a single borehole in the first completely undirected graph and the second completely undirected graph is a node, and the edge weights between the nodes are a pair of directions and distance values ​​between the corresponding boreholes;

[0010] Matching the approximation of the first completely undirected graph and the second completely undirected graph, obtaining a first target data value in the historical geological feature matrix corresponding to the first completely undirected graph and a second target data value in the current geological feature matrix corresponding to the second completely undirected graph, performing an AND operation on the first target data value and the second target data value to obtain a matching degree matrix with the same number;

[0011] According to the ratio of the accumulated value of all values ​​in the matching degree matrix and the number of all data in the first target data value or the second target data value matrix, the matching degree of the first completely undirected graph and the second completely undirected graph is obtained; based on the matching degree, the approximate geological characteristic data of the uranium prospecting target area to be currently delineated are obtained.

[0012] For example, the invention patent application with application publication number CN115907151A discloses an intelligent mineralization prediction method based on geological big data. The main technical content of the method includes the following steps:

[0013] Step S1, selection of prospecting prediction factors

[0014] On the basis of geological survey and literature research in the study area, the three-level prediction factors for regional gold prospecting are summarized and concluded, and 9 types of third-level factors are used as feature data for machine learning; among them, the first-level factors include geological factors, geochemical factors and geophysical factors; the second-level factors corresponding to the geological factors include strata, structure and igneous rocks, the second-level factors corresponding to the geochemical factors include 1:50,000 stream sediment geochemical exploration data, and the second-level factors corresponding to the geophysical factors include 1:50,000 high-precision magnetic geophysical exploration data; the third-level factors corresponding to the strata include Xinghongpu Formation, Gudaoling Formation and other strata, the third-level factors corresponding to the structure include NW-trending brittle-ductile faults, NE-trending brittle faults, fault intersections and anticline structures, the third-level factors corresponding to the igneous rocks include the distance from the Huahongshuping rock body, the third-level factors corresponding to the 1:50,000 stream sediment geochemical exploration data include Au element geochemistry and R-type factor analysis related to Au F5, and the third-level factors corresponding to the 1:50,000 high-precision magnetic geophysical exploration data include regionalized polar susceptibility ΔT;

[0015] Step S2: Division of prediction units

[0016] According to the survey of known deposits (points), the closest distance between gold deposits (points) is 170m. According to the theory of Carranza et al., 2009, the minimum scale of the prediction unit at the scale of 1:50,000 is 75m×75m. Therefore, this study divides the study area into prediction units according to the standard of 100m×100m. The total area of ​​the study area is 500.83km 2 , a total of 50083 prediction units were divided;

[0017] Step S3, quantitative characterization of predictors and data fusion

[0018] Through GIS technology, the quantitative representation of each prediction factor was achieved, and the numerical data of various prediction factors corresponding to all prediction units in the study area were obtained, and the data were fused to construct a data set;

[0019] Step S4, sample set construction

[0020] The prediction units with gold deposits (points) are taken as positive samples, and the prediction units with non-gold deposits (lead-zinc mines, copper mines, etc.) are taken as negative samples. The positive and negative samples together constitute the sample set, thereby ensuring the accuracy and representativeness of the modeling data. 70% of the sample set is randomly divided into the training set, and the remaining samples are used as the test set;

[0021] Step S5: Training and tuning of machine learning prediction models

[0022] Select five machine learning algorithms, including random forest RF, support vector machine SVM, gradient boosted decision tree GBDT, naive Bayes NB, and logistic regression LR, to build a model. Train the model with training set samples, and use random search, grid search and other methods to tune the hyperparameters of the prediction model.

[0023] Step S6: Quantitative evaluation and optimization of machine learning prediction models

[0024] The performance of the model was quantitatively evaluated using the test set samples. The evaluation indicators included accuracy, precision, recall, F1 value, AUC value, etc. Through the quantitative evaluation of the above five prediction models, the random forest model was selected as the prediction model for gold mineralization in the study area. The accuracy of the random forest model on both the training set and the test set reached more than 95%, indicating that the model has excellent prediction ability.

[0025] Step S7, calculation of mineralization probability in the study area

[0026] The trained random forest model was used to calculate the gold mineralization probability of 50,083 prediction units in the study area, and the mineralization probability of the study area was displayed using GIS technology;

[0027] Step S8: Delineation of mineralization target area

[0028] According to the "success rate curve" method proposed by Rodriguez, 2015, the study area is divided into extremely high potential areas for gold mineralization, high potential areas and general potential areas. Among them, the extremely high potential areas and high potential areas can be used as target areas for gold exploration in the area.

[0029] In addition to the above-mentioned invention patents or patent applications, there are many research and development results related to big data intelligent prospecting methods, which will not be repeated here. In general, compared with traditional mineral exploration technology, the existing big data intelligent prospecting methods have greatly improved the efficiency of mineral exploration. However, the existing big data intelligent prospecting methods, including the technical solutions recorded in the invention patent of CN117557401B and the invention patent application of CN115907151A, also have some defects, mainly in the coupling between the mineralization information reflected by multi-source geological data and the field geological relationship, as well as the full mining and reasonable selection and application of various mineralization models and basic geological research results. There are deficiencies, especially insufficient attention to the relevant mineralization theory research results. In addition, the existing big data intelligent prospecting methods are only for specific mineral species and mineralization types, and have little application value for finding unknown deposit types, so there are strong limitations.

[0030] At present, my country has accumulated rich geological data, and there are many research results and literature on the mineralization models of various mineral deposits. The basic geological research results related to mineralization are also relatively complete. Faced with a large amount of geological and mineral information, traditional mineral exploration technology is difficult to cope with, and the application of artificial intelligence technology and big data technology can effectively make up for the shortcomings of traditional mineral exploration technology in information processing. However, in the process of using artificial intelligence technology and big data technology, if we do not pay attention to the relevant geological theory research results, such as the mineralization theory research results expressed in the form of geological knowledge maps, it will also lead to blindness in the work, and even make the final results, such as the scope of the prospecting prospect area, delineated, have large deviations. And the deviation of the scope of the prospecting prospect area often leads to unnecessary investment and ineffective work.

[0031] It should be emphasized that although the results of geological theoretical research, including mineralization theory, need to be constantly tested in practice, and gradually improved in the process of practical testing, and even be superseded by new theoretical research results, the existing geological theoretical research results have an important guiding role in both the mining of deep-level key mineralization information and the correlation of seemingly unrelated deep-level geological information. While using artificial intelligence technology and big data technology, how to fully and effectively use the existing geological theoretical research results is a technical problem that needs to be solved in the field of mineral exploration technology. Summary of the invention

[0032] The purpose of the present invention is to apply the research results of artificial intelligence technology, big data technology and related geological theories (especially metallogenic theory) to the field of mineral exploration technology, so as to fully explore the geological background information of metallogenicity and deep-level key information of metallogenicity, and to organically integrate various professional prospecting information horizontally to reduce human interference, and to associate seemingly unrelated deep-level geological information vertically to explore more clues for prospecting, and to reduce unnecessary investment and ineffective work, thereby greatly improving the efficiency of prospecting.

[0033] In order to achieve the above object, the present invention adopts the following technical solutions:

[0034] A big data intelligent prospecting operation method based on multi-source geological relationship data includes the following steps:

[0035] S01: According to the project objectives and tasks, determine the prospecting target area and determine the target mineral species and type;

[0036] S02: It is divided into two categories: a and b. In case of a, the prospecting target mineral species and types have been determined, and the prospecting prospecting area of ​​this type of mineral species only needs to be delineated; in case of b, the prospecting target mineral species and / or types are uncertain, and the distribution range of different advantageous prospecting target mineral species and / or types in the prospecting target area needs to be delineated;

[0037] S03: Collect relevant geological data of the target area, including published papers, monographs, research reports, intelligence information and other relevant data on geology, geophysical exploration, geochemical exploration and remote sensing, and process them according to two types of situations: a) collect or construct a detailed knowledge map of a single mineral type; b) collect or construct a detailed knowledge map of multiple mineral types;

[0038] S04: Divide the prospecting target area into several unit modules with spatial information as the most basic geological relationship knowledge map carrier unit;

[0039] S05: Based on the spatial position, the plane map with spatial information is overlapped with the unit module, and the geological characteristics and geological relationship attributes are assigned to the corresponding unit module;

[0040] S06: Based on the description content, the reports, drawings, and schedules corresponding to the attributes in the unit module are combined to mine the deep geological information that cannot be reflected in the plane map and assign it to the unit module as the corresponding attribute content;

[0041] S07: Based on geological knowledge, we mine the specific mineralization geological information related to specific mineral deposits from published scientific papers, monographs, research reports, intelligence information and other related materials, and assign it to the unit module as the corresponding attribute content;

[0042] S08: Refer to the existing knowledge graph of relevant mineral types, perform knowledge fusion and disambiguation on the attribute content in the unit module to ensure the consistency of the description content, and construct the geological relationship knowledge graph of the unit module, assign weights to each triple (entity-relationship-entity). The basic principle of weight assignment is that the direct prospecting signs closely related to prospecting have a high weight, and the indirect prospecting clues have a low weight;

[0043] S09: It is divided into two cases, a and b: case a is to calculate the similarity between the geological relationship knowledge map and the target type mineral prospecting knowledge map, and obtain the score of each unit module according to the weight; case b is to calculate the similarity between the geological relationship knowledge map and the series type mineral prospecting knowledge map, and obtain the metallogenic possibility score of different types of minerals in each unit module according to the weight;

[0044] S10: It is divided into two situations, a and b. In case a, the minimum score for possible mineralization is determined based on the different scores of unit modules and with reference to the mineralization geological theory, and the prospecting area for the target type of mineral is delineated. In case b, the distribution range of each dominant type of mineral in the prospecting target area is delineated based on the different scores of unit modules among different types of minerals.

[0045] On the basis of the above technical solutions, the present invention may adopt the following additional technical means to better or more specifically solve the technical problems to be solved by the present invention:

[0046] The geological characteristics and geological relationship attributes include the temporal and spatial distribution characteristics of geological bodies, structures, alteration, geophysical and geochemical anomalies, and remote sensing anomalies at the unit module, their relationships with each other, the distance from each feature point, whether there is feature superposition, and various geological phenomena that have been observed in the field.

[0047] Furthermore, the deep-level geological information includes the basic geological characteristics, causes, evolution, influencing factors, and the connection between the macro and micro aspects of specific geological elements.

[0048] Furthermore, the specific geological elements include geological elements in terms of rocks, minerals, strata, structures, geological age, alteration, geophysics, geochemistry, remote sensing, etc.

[0049] Furthermore, when executing step S02, if it meets Class B situation, that is, when the target mineral species and / or type is uncertain, first select Class B situation to determine the prospecting target of the dominant type of mineral species in the prospecting target area, and then select Class A situation based on the determined dominant type of mineral species to delineate the prospecting prospecting area of ​​the dominant type of mineral species.

[0050] Furthermore, referring to the content of the geological relationship knowledge graph, the detailed knowledge graph of a single mineral type collected or constructed in step S03, or the detailed knowledge graph of multiple mineral types collected or constructed in step S03, is modified and improved so that it has as many identical triple units as possible with the geological relationship knowledge graph.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention applies the research results of artificial intelligence technology, big data technology and related geological theories (especially metallogenic theory) to the field of mineral exploration technology; according to different situations, detailed knowledge graphs of a single mineral type or multiple mineral types are collected or constructed respectively, and the prospecting target area is divided into a number of unit modules with spatial information as the most basic geological relationship knowledge graph carrier unit; on this basis, the corresponding attribute content is assigned to the unit module based on the spatial position, description content and geological knowledge; with reference to the existing knowledge graphs of related mineral types, the attribute content in the unit module is fused and disambiguated to ensure the consistency of the description content, and the geological relationship knowledge graph of the unit module is constructed, and each triple is assigned a weight; according to the weight, the score of each unit module or the metallogenic possibility score of different types of minerals in each unit module is obtained, so as to efficiently and accurately delineate the prospecting prospecting area or determine the dominant mineral species. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a flow chart of the big data intelligent prospecting operation method based on multi-source geological relationship data of the present invention;

[0054] Figure 2 It is a structural diagram of the detailed knowledge map of porphyry copper deposits;

[0055] Figure 3 It is a schematic diagram of unit module division;

[0056] Figure 4 It is a schematic diagram of the geological body after being assigned to the unit module;

[0057] Figure 5 It is a schematic diagram after the geochemical anomaly is assigned to the unit module;

[0058] Figure 6 It is a schematic diagram of the technical route to mine the common rare earth element characteristics of porphyry copper deposits through literature;

[0059] Figure 7 It is a schematic diagram of the geological relationship knowledge graph. DETAILED DESCRIPTION

[0060] In order to facilitate those skilled in the art to fully understand the technical solution and working principle of the present invention, two embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0061] Example 1

[0062] like Figure 1 As shown (this embodiment belongs to Figure 1 A big data intelligent prospecting operation method based on multi-source geological relationship data includes the following steps:

[0063] S01: According to the project objectives and tasks, the target area for prospecting is determined to be the Xiongmei area in Tibet (longitude: 89°01′50″-89°08′40″; latitude: 31°23′00″-31°28′00″). Based on the existing geological data, it is preliminarily determined that the target mineral is copper ore, and its type is porphyry.

[0064] S02: The target mineral species and type has been determined to be porphyry copper deposits, with the goal of specifically defining the prospecting area for this type of mineral in the Xiongmei area of ​​Tibet.

[0065] S03: Collect relevant geological data in the target area of ​​Xiongmei, Tibet and its surrounding areas and areas with the same geological background, including published papers, monographs, research reports, intelligence information and other relevant materials on geology, geophysical exploration, geochemical exploration and remote sensing, and collect or construct a detailed knowledge map of porphyry copper deposits. The main contents of this knowledge map are as follows: Figure 2 shown.

[0066] S04: Divide the prospecting target area into several unit modules with spatial information as the most basic geological relationship knowledge map carrier unit; the division of unit modules is closely related to the prospecting target area, target mineral species and types, and comprehensive selection is made. In general, the prospecting target area is large and the unit module grid can be appropriately sparse. When the prospecting target mineral species and types are small in scale or vein-like ore bodies, the unit module grid should be denser. The prospecting target of this embodiment is a large-scale porphyry deposit, and the target area is about 100km 2 , the unit module is set to 100m×100m, and a total of 10341 unit modules are divided. The unit modules are divided as follows Figure 3 shown.

[0067] S05: Based on the spatial position, the plane map with spatial information is overlapped with the unit module, and the geological characteristics and geological relationship attributes are assigned to the corresponding unit module. The spatial information in this step includes geological bodies, geochemical anomalies, etc. The content displayed after the geological body is assigned to the unit module is as follows: Figure 4 shown. Figure 4 Different colors in the table represent different geological bodies. For example, red represents Late Cretaceous granodiorite porphyry, pink represents Late Cretaceous monzogranite, and white represents contact zone. For geological bodies represented by other colors, see Figure 4The contents displayed after the geochemical anomaly is assigned to the unit module are as follows Figure 5 As shown, Figure 5 The dark areas in the figure represent geochemical anomaly areas.

[0068] S06: Based on the description content, the reports, drawings, and appendices corresponding to the attributes in the unit module are combined to mine the deep geological information that cannot be reflected on the plane map, and are assigned to the unit module as the corresponding attribute content. Regarding the description content in this step, for example, the geological map shows γδπK2 (Late Cretaceous granodiorite porphyry). Except for the distribution location and contact relationship with the surrounding geological elements, no more information can be obtained in the geological map. In the report corresponding to the geological map, there is a detailed description of γδπK2 (Late Cretaceous granodiorite porphyry), including geological and petrographic characteristics, rock formation age, rock geochemical characteristics, rock classification, tectonic background and a series of related descriptions. These descriptions can be used as the attribute content of the rock mass and assigned to the corresponding unit module.

[0069] S07: Based on geological knowledge, we mine the specific mineralization geological information related to porphyry copper deposits (such as the specific trace elements and isotope characteristics of the porphyry copper deposit mineralization rock mass) from published scientific papers, monographs, research reports, intelligence information and other related materials, and assign them to the unit module as the corresponding attribute content. The basic technical ideas of this step are as follows: Figure 6 As shown. Regarding the geological knowledge in this step, take the academic paper "Exploration of Source Rocks or Source Areas of Porphyry Copper Deposits" published by Rui Zongyao et al. in Acta Petrologica Sinica in 2004 as an example. The paper mentioned several common rock geochemical characteristics of porphyry copper deposits: for example, the common REE (rare earth elements) characteristics of porphyry copper deposits are "right-oblique, light soil is relatively enriched, heavy rare earth is relatively depleted, and Eu anomaly is not significant". Then porphyry bodies with similar REE characteristics can be used as a clue for prospecting, expanding the basis for prospecting and incorporating some seemingly unrelated indirect basis for prospecting into the clues for prospecting.

[0070] S08: Refer to the existing knowledge graph of relevant porphyry copper deposits, perform knowledge fusion and disambiguation on the attribute content in the unit module to ensure the consistency of the description content, and construct the geological relationship knowledge graph of the unit module, and assign weights to each triple (in the triple, that is, in the entity-relationship-entity, the two entities before and after refer to specific objects or concepts, and these two objects or concepts are related through a certain relationship). The basic principle of weight assignment is that direct prospecting signs closely related to prospecting have high weights (for example, malachite found in the field is a direct prospecting clue with a high weight), and indirect prospecting clues have low weights (for example, granodiorite porphyry has an insignificant Eu anomaly with a low weight). In addition, the disambiguation in this step refers to ensuring that the content of the same description represents the same meaning. For example, "enrichment of ore-forming element copper" and "relative enrichment of copper in trace elements in surrounding rocks" can both be simply expressed as "enriched Cu", but the copper content referred to by the two is not of the same order of magnitude, and the content is ambiguous. The expression needs to be modified to ensure unique expression.

[0071] S09: Geological relationship knowledge graph (e.g. Figure 7 The similarity between the geological relationship knowledge graph shown in FIG. 1 and the prospecting knowledge graph of the target type of mineral species is calculated, and the score of each unit module is obtained according to the weight;

[0072] S10: With reference to the mineralization geological theory of porphyry copper deposits, determine the minimum score for possible mineralization, delineate the specific prospecting area for porphyry copper deposits in the Xiongmei area of ​​Tibet, and provide work for the next step.

[0073] It should be noted that, in this embodiment, the geological characteristics and geological relationship attributes include geological bodies, structures, eras, alterations, and geophysical and geochemical anomalies. The deep geological information includes the geochemical characteristics and structural occurrence of specific rock bodies. In addition, when executing step S03, this embodiment refers to the geological relationship knowledge map content of porphyry copper mines, and modifies and improves the detailed knowledge map of porphyry copper mines collected or constructed in step S03, so that it has as many identical triplet units as possible with the geological relationship knowledge map.

[0074] Example 2

[0075] like Figure 1 As shown, this embodiment (belonging to Figure 1 The basic steps of the embodiment (b) are the same as those of the embodiment 1, except that it is necessary to collect or construct a knowledge graph of multiple mineral species and / or types in the prospecting target area. Specifically, this embodiment differs from the embodiment 1 in the following four aspects:

[0076] First, in this embodiment, when executing step S02, the prospecting target mineral species or / and type are not determined, but the distribution ranges of different advantageous prospecting target mineral species or / and types need to be delineated within the prospecting target area;

[0077] Second, when executing step S03, this embodiment collects or constructs a detailed knowledge map of multiple types of minerals; the determination of the target minerals or / and types should be determined by studying the geological background of the target area and its surroundings, so that the target minerals or / and types are more targeted and avoid blind prospecting. For example, taking the prospecting target area mentioned in Example 1 as an example, its fault structure and intrusive rocks are relatively developed. Through previous geological work research, there are prospecting clues for hydrothermal deposits. Then the possible target minerals or / and types in this area include porphyry type, hydrothermal vein type, skarn type copper, molybdenum, lead, zinc, silver, etc.

[0078] Third, the similarity between the geological relationship knowledge map and the prospecting knowledge map of the series of types of minerals is calculated, and the mineralization possibility scores of different types of minerals in each unit module are obtained according to the weights; for example, the score of a unit module porphyry copper ore is 9.8 points, the score of porphyry molybdenum ore is 7.6 points, the score of skarn copper ore is 6.8 points, the score of skarn lead-zinc ore is 6.5 points, and the score of quartz vein silver ore is 2.3 points, indicating that among the target minerals in this module, the porphyry copper ore has the greatest mineralization possibility, followed by porphyry molybdenum ore, skarn copper ore, skarn lead-zinc ore, and the quartz vein silver ore has the lowest mineralization possibility. In other unit modules, the quartz vein type mineralization possibility may be the highest, and the possibility of porphyry copper ore is the lowest.

[0079] Fourth, based on the different scores of each unit module among different types of mineral species, the distribution of each target mineral species or / and type in the prospecting target area is determined, and one or several target mineral species or / and types with the most prospecting prospects are determined to provide further work.

[0080] It should be noted that, in addition to the above four differences, in this embodiment, the deep geological information includes the basic geological characteristics, causes, evolution, influencing factors, and the connection between macro and micro of specific geological elements such as rocks, minerals, strata, structures, geological eras, alteration, geophysics, geochemistry, and remote sensing. In other words, compared with Example 1, this embodiment involves more specific geological elements when executing step S06. Of course, this difference is relative. In fact, when executing step S06 in Example 1, if a person skilled in the art deems it necessary, the above-mentioned various specific geological elements can also be fully involved.

Claims

1. A big data intelligent prospecting operation method based on multi-source geological relationship data, characterized in that: The steps include: S01: According to the project objectives and tasks, determine the prospecting target area and determine the target mineral species and type; S02: It is divided into two categories: a and b. In case of a, the prospecting target mineral species and types have been determined, and the prospecting prospecting area of ​​this type of mineral species only needs to be delineated; in case of b, the prospecting target mineral species and / or types are uncertain, and the distribution range of different advantageous prospecting target mineral species and / or types in the prospecting target area needs to be delineated; S03: Collect relevant geological data of the target area, including published papers, monographs, research reports, and intelligence information on geology, geophysical exploration, geochemical exploration, and remote sensing, and process them according to two types of situations: a) collect or construct a detailed knowledge map of a single mineral type; b) collect or construct a detailed knowledge map of multiple mineral types; S04: Divide the prospecting target area into several unit modules with spatial information as the most basic geological relationship knowledge map carrier unit; S05: Based on the spatial position, the plane map with spatial information is overlapped with the unit module, and the geological characteristics and geological relationship attributes are assigned to the corresponding unit module; S06: Based on the description content, the reports, drawings and appendices corresponding to the attributes in the unit module are combined to mine the deep geological information that cannot be reflected in the plane map and assign it to the unit module as the corresponding attribute content; S07: Based on geological knowledge, we mine specific mineralization geological information related to specific mineral deposits from published scientific papers, monographs, research reports, and intelligence information, and assign it to the unit module as the corresponding attribute content; S08: Refer to the existing knowledge graph of relevant mineral types, perform knowledge fusion and disambiguation on the attribute content in the unit module to ensure the consistency of the description content, and construct the geological relationship knowledge graph of the unit module, assign weights to each triplet. The basic principle of weight assignment is that the direct prospecting signs closely related to prospecting have a high weight, and the indirect prospecting clues have a low weight; S09: It is divided into two cases, a and b: case a is to calculate the similarity between the geological relationship knowledge map and the target type mineral prospecting knowledge map, and obtain the score of each unit module according to the weight; case b is to calculate the similarity between the geological relationship knowledge map and the series type mineral prospecting knowledge map, and obtain the metallogenic possibility score of different types of minerals in each unit module according to the weight; S10: It is divided into two situations, a and b. In case a, the minimum score for possible mineralization is determined based on the different scores of unit modules and with reference to the mineralization geological theory, and the prospecting area for the target type of mineral is delineated. In case b, the distribution range of each dominant type of mineral in the prospecting target area is delineated based on the different scores of unit modules among different types of minerals.

2. The big data intelligent prospecting operation method based on multi-source geological relationship data according to claim 1, characterized in that: The geological characteristics and geological relationship attributes include the temporal and spatial distribution characteristics of geological bodies, structures, alteration, geophysical and geochemical anomalies, and remote sensing anomalies at the unit module, their relationships with each other, the distance from each feature point, whether there is feature superposition, and various geological phenomena that have been observed in the field.

3. The big data intelligent prospecting operation method based on multi-source geological relationship data according to claim 1, characterized in that: The deep-level geological information includes the basic geological characteristics, causes, evolution, influencing factors, and the connection between the macro and micro aspects of specific geological elements.

4. The big data intelligent prospecting operation method based on multi-source geological relationship data according to claim 3 is characterized by: The specific geological elements include rocks, minerals, strata, structures, geological age, alteration, geophysics, geochemistry, and remote sensing geological elements.

5. The big data intelligent prospecting operation method based on multi-source geological relationship data according to claim 1, characterized in that: When executing step S02, if it meets Class B situation, that is, when the target mineral species and / or type is uncertain, first select Class B situation to determine the prospecting target of the dominant type of mineral species in the prospecting target area, and then select Class A situation based on the determined dominant type of mineral species to delineate the prospecting prospecting area of ​​the dominant type of mineral species.

6. The big data intelligent prospecting operation method based on multi-source geological relationship data according to any one of claims 1 to 5, characterized in that: With reference to the content of the geological relationship knowledge graph, the detailed knowledge graph of a single mineral type collected or constructed in step S03, or the detailed knowledge graph of multiple mineral types collected or constructed in step S03, is modified and improved so that it has as many identical triple units as possible with the geological relationship knowledge graph.

Images