Big data intelligent prospecting prediction method, device, equipment, medium and product

Abstract

The invention discloses a big data intelligent prospecting prediction method and device, equipment, a medium and a product, and belongs to the field of prospecting prediction, and the method comprises the steps: building a big data metallogenic prediction database according to multi-region exploration data; based on a knowledge graph and a random forest algorithm, a prospecting prediction model is established according to the big data metallogenic prediction database; training the prospecting prediction model according to exploration data of a to-be-measured metallogenic zone, and constructing a prediction model of the to-be-measured metallogenic zone; the exploration data of the to-be-measured metallogenic zone is extracted from the big data metallogenic prediction database; and predicting the metallogenic position of the to-be-measured metallogenic zone according to the prediction model of the to-be-measured metallogenic zone. According to the method and the device, the prospecting prediction accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of mineral prospecting and prediction, and in particular to a big data intelligent mineral prospecting and prediction method, device, equipment, medium and product. Background Art

[0002] Although the metallogenic belts have accumulated a large amount of geological and mineral data, including geological, mineral, geophysical, geochemical and remote sensing data of different scales and their research reports, there is an urgent need to further sort out, collect and organize the latest data and information of the existing geological and mineral data of any scale of the metallogenic belt and establish a database of metallogenic elements of the metallogenic belt.

[0003] The work area has carried out geological and mineral exploration work at various scales in a relatively systematic manner, generating a large amount of geological, mineral, geophysical, geochemical and remote sensing data. Some multi-source data fusion mineralization prediction work has been carried out in the work area, including mineral resource potential evaluation based on comprehensive mineralization information. However, no intelligent prospecting and prediction of gold deposits based on big data has been carried out in the mineralization belts, and the accuracy of prospecting and prediction is low. Summary of the invention

[0004] The purpose of this application is to provide a big data intelligent prospecting and prediction method, device, equipment, medium and product to solve the problem of low accuracy of prospecting and prediction.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In the first aspect, the present application provides a big data intelligent prospecting prediction method, comprising:

[0007] A big data mineralization prediction database is established based on multi-regional exploration data; the multi-regional exploration data includes unstructured data and structured data; the unstructured data includes field notebooks, geological mineral maps and remote sensing image data; the structured data includes geophysical data, geochemical data, typical mineral deposit data, mineral data, text reports, articles and monographs;

[0008] Based on the knowledge graph and random forest algorithm, a mineral prospecting prediction model is established according to the big data mineralization prediction database;

[0009] The prospecting prediction model is trained according to the exploration data of the mineralization belt to be measured, and the prediction model of the mineralization belt to be measured is constructed; the exploration data of the mineralization belt to be measured is extracted from the big data mineralization prediction database;

[0010] The mineralization position of the mineralization belt to be measured is predicted according to the prediction model of the mineralization belt to be measured.

[0011] In the second aspect, the present application provides a big data intelligent prospecting prediction device, comprising:

[0012] A big data mineralization prediction database establishment module is used to establish a big data mineralization prediction database based on multi-region exploration data; the multi-region exploration data includes unstructured data and structured data; the unstructured data includes field notebooks, geological mineral maps and remote sensing image data; the structured data includes geophysical data, geochemical data, typical mineral deposit data, mineral data, text reports, articles and monographs;

[0013] A mineral prospecting prediction model establishment module is used to establish a mineral prospecting prediction model based on the knowledge graph and random forest algorithm according to the big data mineralization prediction database;

[0014] A prediction model building module for the mineralization belt to be measured, which is used to train the mineralization prediction model according to the exploration data of the mineralization belt to be measured, and to build a prediction model for the mineralization belt to be measured; the exploration data of the mineralization belt to be measured is extracted from the big data mineralization prediction database;

[0015] A prediction module is used to predict the mineralization position of the mineralization belt to be measured according to the prediction model of the mineralization belt to be measured.

[0016] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described big data intelligent mineral prospecting and prediction methods.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned big data intelligent mineral prospecting and prediction methods.

[0018] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned big data intelligent mineral prospecting and prediction methods.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0020] This application uses big data thinking that combines data-driven and knowledge-driven, establishes a big data mineralization prediction database based on multi-regional exploration data, and converts the multi-regional exploration data in the big data mineralization prediction database into entities, attributes and relationship nodes in the knowledge graph, and uses the random forest algorithm to determine important features to construct a mineral exploration prediction model, thereby improving the prediction accuracy of the mineral exploration prediction model; finally, based on the exploration data of the mineralization belt to be tested, the constructed mineral exploration prediction model is trained for the exploration data of any mineralization belt or the exploration data of other specific mineralization belts, and a prediction model corresponding to the mineralization belt to be tested is generated, which further improves the prediction accuracy for the specific mineralization belt and helps to make breakthroughs in gold prospecting in the mineralization belt or other specific mineralization belts. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A flow chart of a big data intelligent prospecting prediction method provided in one embodiment of the present application;

[0023] Figure 2 A technical flow chart of a big data intelligent prospecting prediction method provided in one embodiment of the present application;

[0024] Figure 3 A flowchart of the mineral prospecting prediction model training and evaluation provided in one embodiment of the present application;

[0025] Figure 4 A schematic diagram of a computer device provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0028] This application focuses on the needs of big data intelligent mineral exploration prediction and evaluation, and develops a series of big data intelligent mineral exploration prediction technologies, methods, algorithms and models to form a big data intelligent mineral exploration prediction technology and method system. Taking a certain mineralization belt as an example, the technical solution of this application is explained.

[0029] Collect large-scale geological mineral, geochemical, geophysical, remote sensing, drilling and other data and exploration reports, research literature and mine development data in demonstration areas such as mineralization belts, build a multi-source information database for demonstration areas such as mineralization belts, build an intelligent prospecting, prediction and evaluation model for demonstration areas such as mineralization belts, delineate prospective mineralization areas, and verify the feasibility of big data intelligent prospecting, prediction and evaluation technical methods.

[0030] The present application embodiment provides a big data intelligent prospecting prediction method, which is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the present application embodiment, Figure 1 As shown, the method includes the following steps.

[0031] S1: Establish a big data mineralization prediction database based on multi-regional exploration data; the multi-regional exploration data includes unstructured data and structured data; the unstructured data includes field notebooks, geological mineral maps and remote sensing image data; the structured data includes geophysical data, geochemical data, typical mineral deposit data, mineral data, text reports, articles and monographs.

[0032] S2: Based on the knowledge graph and random forest algorithm, a mineral exploration prediction model is established according to the big data mineralization prediction database.

[0033] S3: training the mineral prospecting prediction model according to the exploration data of the mineralization belt to be measured, and constructing a prediction model of the mineralization belt to be measured; the exploration data of the mineralization belt to be measured is extracted from the big data mineralization prediction database.

[0034] S4: Predicting the mineralization position of the mineralization belt to be measured according to the prediction model of the mineralization belt to be measured.

[0035] In an exemplary embodiment, S1 may be replaced by the following steps.

[0036] S11: Collect multi-regional exploration data within the demonstration area, including mineral geological survey reports and data at large scales of 1:200,000, 1:250,000, and 1:50,000. Secondly, collect relevant research literature and test analysis data within the demonstration area, sort out geological and mineral data of different types, scales, and sources, and establish a big data mineralization prediction database for the demonstration area.

[0037] In an exemplary embodiment, S2 may be replaced by the following steps.

[0038] S21: Based on the mineral prospecting prediction model, the multi-regional exploration data in the big data mineralization prediction database are converted into entities, attributes and relationship nodes in the knowledge graph, and a link relationship between the multi-regional exploration data is established.

[0039] S22: Based on the constructed knowledge graph, use the random forest algorithm to determine important features.

[0040] S23: Based on the important features, a mineral exploration prediction model is established using a machine learning algorithm.

[0041] In an exemplary embodiment, before S2, the step further includes:

[0042] S24: Clean the multi-region exploration data in the big data mineralization prediction database, and select a learning model as the mineral exploration prediction model; the learning model includes a machine learning model and a deep learning model built using Tensorflow; the deep learning model is built based on a multi-layer perceptron or a convolutional neural network.

[0043] In practical applications, such as Figure 2 As shown in the figure, a mineral prospecting prediction model is established based on the knowledge graph and random forest algorithm.

[0044] In the intelligent interaction part, Python+TensorFlow framework is selected to realize intelligent prediction of mineralization location and knowledge graph in intelligent interaction. The main steps include: ① Data preparation, using Pandas tools to collect and clean relevant data of mineralization belts; ② Model selection, using Tensorflow to build machine learning models, and adjusting and optimizing data features based on deep learning model architectures such as Multilayer Perceptron (MLP) or Convolutional Neural Networks (CNN); ③ Model training and optimization, dividing the data set (i.e., multi-regional exploration data in the big data mineralization prediction database) into training set, validation set and test set, using TensorFlow for model training, and optimizing model parameters through cross-validation technology; ④ Model evaluation and prediction, evaluating the performance of the model on the test set, such as prediction accuracy, regression indicators, etc., and applying integrated learning technologies such as bagging and boosting to improve the prediction effect.

[0045] The relevant influencing factors, such as the type of ore deposit, the size and shape of the ore body, are introduced into the above model for prediction. The prediction process of the prospecting prediction model is as follows: Figure 3 shown.

[0046] Figure 3Data preprocessing includes: collecting the latest research results related to prospecting in the work area and the latest research progress of big data artificial intelligence prospecting, and summarizing the key points and problems in detail. Systematically collect research materials and data on geology, minerals, geochemistry, geophysics, remote sensing, etc. in the work area, focusing on collecting large-scale geophysical, chemical and remote sensing data and exploration and development data in key mining areas in the work area, classifying and arranging the collected data, reading and analyzing the previous data, providing a basis for project work deployment, and preprocessing the data in the study area.

[0047] ① Collection, analysis and arrangement of basic data: not only the basic geological data of the area in the past are collected, but also the geological, physical, chemical and remote data are reinterpreted. The focus is on comprehensive processing and reinterpretation of various data related to mineralization, geological structures, ore-bearing strata, typical ore deposits, ore-bearing rock bodies, regional tectonic evolution background, etc.

[0048] ② The Paleogene, Neogene and Quaternary systems in the metallogenic belt are severely covered. We will explore the methods and models of deep prospecting in the metallogenic belt and summarize the methods and processes of big data intelligent mineral prediction in the covered area. We will use the new technology of "big data" and "artificial intelligence" to "uncover" the covered area, laying the foundation for the subsequent prediction of the prospective mineralization areas in the covered area.

[0049] ③ Research on the mineralization geological background: Conduct field dissection of the regional strata, structures, magmatic rocks and other mineralization-controlling factors and representative mineral deposits, focus on the research of mineralization geological structure background, deeply understand the mineralization conditions, mineralization environment and mineral deposit characteristics, and conduct necessary test analysis to clarify the temporal and spatial distribution characteristics and mineralization evolution laws of the main mineralization systems. Make full use of a variety of geological, geochemical and geophysical data to study the regional scale mineralization-controlling factors and prospecting signs.

[0050] ④ Use machine learning methods to use the bedrock-structure prediction and inference map of the outcrop area as prior geological knowledge, and integrate geological, physical, chemical, and remote sensing information to infer the bedrock-structure structure of the newly developed coverage area.

[0051] In an exemplary embodiment, S3 may be replaced by the following steps.

[0052] S31: Based on the knowledge graph and the prospecting prediction model, and according to the exploration data of the mineralization belt to be measured, a machine learning model is used to extract regional prospecting information.

[0053] S32: constructing a mineralization information thematic map based on the regional prospecting information; the mineralization information thematic map includes a regional gold mineralization regularity map, a regional geophysical anomaly map, a regional geochemical anomaly map, a regional prospecting landmark map, and a line loop structure and alteration map interpreted by remote sensing.

[0054] S33: Constructing a prediction model of the mineralization belt to be measured based on the mineralization information thematic map.

[0055] In practical applications, deep prospecting information is extracted based on nonlinear methods to carry out quantitative prediction and exploration of mineral resources.

[0056] ① Based on the study of geological structural evolution, mineralization geological background and mineralization system of the mineralization belt, the complex influence of Quaternary cover on mineralization information, the attenuation and shielding effect of Quaternary cover on mineralization information, especially the law of upward migration of elements under the cover layer, are studied. Aiming at the composite superposition characteristics of weak and slow mineralization information and information in the working area, on the one hand, based on the theory of mineralization singularity, the multi-fractal local singularity analysis / mapping method is used to carry out nonlinear extraction and identification of weak and slow mineralization (physical, chemical, remote sensing) information, solve the problem of enhancing and extracting weak and slow information of hidden minerals under the interference of cover layer superposition, and reasonably infer the geological structural characteristics and hidden spatial structure under the cover layer, especially to lock the hidden mineralization structure and mineral control mark. On the other hand, according to the generalized self-similarity principle of geological anomalies, nonlinear fractal models such as concentration-area fractal model, spectrum-area fractal model, noise-fractal model and weighted fractal model are used. According to the different fractal structure characteristics reflected in the anomaly and background sites, fractal filters are constructed to decompose the composite mineralization information under the influence of the cover layer and extract useful hidden mineralization anomaly information.

[0057] ② Establish a corresponding big data artificial intelligence prediction model for gold deposit types in the metallogenic belt. On the basis of nonlinear extraction and identification of deep-level prospecting information, further explore the effectiveness of each prediction factor, divide the prediction unit, and construct the prediction variable. Study how to use multi-source geological information such as geology, physics, chemistry, and remote sensing to reveal the hidden structural framework and geological characteristics under the development of Quaternary cover. Use fuzzy evidence weight model, weighted comprehensive information fusion model and multi-point geological statistical simulation methods to solve the problem of integrating geological structure prior information with statistical simulation and spatial decision-making in conventional methods. Under the technical environment of Geographic Information System (GIS), effectively integrate multi-metallogenic information (geology, physics, chemistry, remote sensing, etc.), carry out quantitative resource evaluation, so as to delineate and optimize prospecting areas, and carry out uncertainty and risk evaluation.

[0058] In practical applications, the unstructured data of the mineralization belt to be measured is analyzed based on the knowledge graph and mineral exploration prediction model, and the regional mineral exploration information is extracted using the machine learning model.

[0059] Furthermore, the exploration data corresponding to the mineralization belts are extracted and integrated from the big data mineralization prediction database such as the mineralization belts, and converted into entities, attributes and relationship nodes in the knowledge graph, and the link relationship between them is established.

[0060] Based on the constructed knowledge graph, the random forest model is used to output the importance of each feature. It is usually based on the number of times the feature is used in the model or the gain brought by the split, to determine the important features, and to extract topological features such as the distance between nodes and path length from the relationship nodes.

[0061] On this basis, a machine learning algorithm is used to construct a capacity prediction model. The mineralization belt data is used as a training set to train the model. The cross-validation technology is used to optimize the model parameters and hyperparameters, and then optimized again to improve the prediction performance of the model. The feasibility and effectiveness of this application are verified by analyzing the predictions of multiple mineralization belts.

[0062] In an exemplary embodiment, after S33, the following steps are further included:

[0063] S34: Processing the exploration data of the mineralization belt to be measured, and using the processed exploration data as a training set to train a prediction model for the mineralization belt to be measured.

[0064] S35: Use cross-validation techniques to select model parameters and hyperparameters of the trained prediction model.

[0065] S36: Optimizing the trained prediction model according to the selected model parameters and hyperparameters to determine the optimized prediction model.

[0066] In an exemplary embodiment, after S4, the following steps are further included:

[0067] S5: Conduct geological interpretation based on the mineralization location and analyze the mineralization laws and ore-controlling factors.

[0068] This application establishes a big data mineralization prediction database including the scale of mineralization belts. Through the big data intelligent prospecting prediction method provided in this application, gold mines in the mineralization belts are predicted, and compared with the results of the national potential evaluation to verify the effectiveness of the method model, which provides support for gold exploration in the mineralization belts and lays the foundation for the promotion and application of big data intelligent prospecting methods in other mineralization belts in the next step.

[0069] This application aims to address the difficulties and challenges of conducting big data intelligent prediction in mineralization zones, and introduces machine learning and other artificial intelligence model algorithms to solve the problem of big data intelligent mineralization prediction in demonstration zones.

[0070] First, we collected regional exploration data in the demonstration area, including mineral geological survey reports and data at large scales of 1:200,000, 1:250,000, and 1:50,000. Secondly, we collected relevant research literature and test analysis data in the demonstration area, sorted out geological and mineral data of different types, scales, and sources, and established a big data mineralization prediction database for the demonstration area. From the scale of the mineralization belt, we used big data intelligent mineralization prediction methods to carry out the prediction of gold resources in the western mineralization belt and delineate the prospecting target area.

[0071] Based on the same inventive concept, the embodiment of the present application also provides a big data intelligent prospecting prediction device for implementing the big data intelligent prospecting prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more big data intelligent prospecting prediction device embodiments provided below can refer to the limitations of the big data intelligent prospecting prediction method above, and will not be repeated here.

[0072] In an exemplary embodiment, a big data intelligent prospecting prediction device is provided, comprising:

[0073] A big data mineralization prediction database establishment module is used to establish a big data mineralization prediction database based on multi-regional exploration data; the multi-regional exploration data includes unstructured data and structured data; the unstructured data includes field notebooks, geological mineral maps and remote sensing image data; the structured data includes geophysical data, geochemical data, typical mineral deposit data, mineral data, text reports, articles and monographs.

[0074] The mineral exploration prediction model establishment module is used to establish a mineral exploration prediction model based on the knowledge graph and random forest algorithm according to the big data mineralization prediction database.

[0075] The prediction model construction module of the mineralization belt to be measured is used to train the mineralization prediction model according to the exploration data of the mineralization belt to be measured and construct the prediction model of the mineralization belt to be measured; the exploration data of the mineralization belt to be measured is extracted from the big data mineralization prediction database.

[0076] A prediction module is used to predict the mineralization position of the mineralization belt to be measured according to the prediction model of the mineralization belt to be measured.

[0077] In an exemplary embodiment, a computer device is provided, such as Figure 4As shown, the computer device can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 big data intelligent prospecting prediction data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication 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, a big data intelligent prospecting prediction method is implemented.

[0078] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above method is implemented when the processor executes the computer program.

[0079] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above method when executed by a processor.

[0080] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0081] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ReadOnlyMemory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (Magnetoresistive RandomAccess Memory, MRAM), ferroelectric random access memory (Ferroelectric RandomAccess Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (RandomAccess Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0082] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0083] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0084] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0085] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A big data intelligent prospecting prediction method, characterized in that: The big data intelligent prospecting prediction method comprises: A big data mineralization prediction database is established based on multi-regional exploration data; the multi-regional exploration data includes unstructured data and structured data; the unstructured data includes field notebooks, geological mineral maps and remote sensing image data; the structured data includes geophysical data, geochemical data, typical mineral deposit data, mineral data, text reports, articles and monographs; Based on the knowledge graph and random forest algorithm, a mineral prospecting prediction model is established according to the big data mineralization prediction database; The prospecting prediction model is trained according to the exploration data of the mineralization belt to be measured, and the prediction model of the mineralization belt to be measured is constructed; the exploration data of the mineralization belt to be measured is extracted from the big data mineralization prediction database; The mineralization position of the mineralization belt to be measured is predicted according to the prediction model of the mineralization belt to be measured.

2. The big data intelligent prospecting prediction method according to claim 1 is characterized in that: Based on the knowledge graph and random forest algorithm, a prospecting prediction model is established according to the big data mineralization prediction database, specifically including: Based on the mineral prospecting prediction model, the multi-regional exploration data in the big data mineralization prediction database is converted into entities, attributes and relationship nodes in the knowledge graph, and a link relationship between the multi-regional exploration data is established; Based on the constructed knowledge graph, the random forest algorithm is used to determine important features; Based on the important features, a mineral exploration prediction model is established using a machine learning algorithm.

3. The big data intelligent prospecting prediction method according to claim 1 is characterized in that: Based on the knowledge graph and random forest algorithm, a prospecting prediction model is established according to the big data mineralization prediction database, which also includes: The multi-regional exploration data in the big data mineralization prediction database are cleaned, and a learning model is selected as the mineral exploration prediction model; the learning model includes a machine learning model and a deep learning model built using Tensorflow; the deep learning model is built based on a multi-layer perceptron or a convolutional neural network.

4. The big data intelligent prospecting prediction method according to claim 1 is characterized in that: The ore prospecting prediction model is trained according to the exploration data of the ore-forming belt to be tested, and the prediction model of the ore-forming belt to be tested is constructed, which specifically includes: Based on the knowledge graph and the prospecting prediction model, according to the exploration data of the mineralization belt to be measured, a machine learning model is used to extract regional prospecting information; Construct a mineralization information thematic map based on the regional prospecting information; the mineralization information thematic map includes a regional gold mineralization regularity map, a regional geophysical anomaly map, a regional geochemical anomaly map, a regional prospecting sign map, and a line loop structure and alteration map interpreted by remote sensing; Based on the mineralization information thematic map, a prediction model for the mineralization belt to be measured is constructed.

5. The big data intelligent prospecting prediction method according to claim 4 is characterized in that: According to the mineralization information thematic map, a prediction model of the mineralization belt to be measured is constructed, and then the following steps are included: Processing the exploration data of the mineralization belt to be measured, and using the processed exploration data as a training set to train a prediction model for the mineralization belt to be measured; Select model parameters and hyperparameters of the trained prediction model using cross-validation techniques; The trained prediction model is optimized according to the selected model parameters and hyperparameters to determine the optimized prediction model.

6. The big data intelligent prospecting prediction method according to claim 1 is characterized in that: Predicting the mineralization position of the mineralization belt to be measured according to the prediction model of the mineralization belt to be measured, and then further comprising: Based on the mineralization location, geological interpretation is carried out to analyze the mineralization laws and controlling factors.

7. A big data intelligent prospecting prediction device, characterized in that: The big data intelligent prospecting prediction device comprises: A big data mineralization prediction database establishment module is used to establish a big data mineralization prediction database based on multi-region exploration data; the multi-region exploration data includes unstructured data and structured data; the unstructured data includes field notebooks, geological mineral maps and remote sensing image data; the structured data includes geophysical data, geochemical data, typical ore deposit data, mineral data, text reports, articles and monographs; A mineral prospecting prediction model establishment module is used to establish a mineral prospecting prediction model based on the knowledge graph and random forest algorithm according to the big data mineralization prediction database; A prediction model building module for the mineralization belt to be measured, which is used to train the mineralization prediction model according to the exploration data of the mineralization belt to be measured, and to build a prediction model for the mineralization belt to be measured; the exploration data of the mineralization belt to be measured is extracted from the big data mineralization prediction database; A prediction module is used to predict the mineralization position of the mineralization belt to be measured according to the prediction model of the mineralization belt to be measured.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the big data intelligent prospecting and prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the big data intelligent prospecting and prediction method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the big data intelligent prospecting and prediction method described in any one of claims 1 to 6 is implemented.

Images