A method and system for deep and concealed mine exploration

Abstract

The present invention relates to the field of data analysis and discloses a method for deep and concealed mine exploration, comprising: obtaining a mineral region to be surveyed, extracting regional characteristics of the mineral region, and analyzing the geological structure category of the mineral region; determining the regional evolution stage of the mineral region based on the geological structure category, and analyzing the mineral location of the mineral region based on the regional evolution stage; inputting the regional characteristics, geological structure category, and the mineral location as sample data into a trained mineral analysis model, and performing feature extraction on the sample data through a convolutional network in the mineral analysis model to obtain feature data; utilizing an attention mechanism in the mineral analysis model to filter out mineral description features of the mineral region from the feature data; utilizing a regression network in the mineral analysis model to calculate the mineral distribution probability of the mineral region, and generating a mineral distribution result for the mineral region based on the mineral distribution probability. The present invention can improve the efficiency of mineral resource exploration.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a deep and concealed mine exploration method and system. Background Art

[0002] Deep and hidden mineral exploration is carried out by drilling and sampling in the survey area, analyzing the geological structure of the survey area, and determining the stage of geological structural evolution of the corresponding survey area, so as to determine the direction of prospecting for deep and hidden mineral resources in the survey area. Through deep and hidden mineral exploration, the value of all the country's mineral resources can be revealed, and the material basis for the production of widely needed mineral products can be provided.

[0003] At present, deep and hidden mine exploration uses geological theoretical methods to identify the basic address characteristics of the strata, rocks, structures and minerals in the working area, and to study the mineralization laws and various mine information. This method requires a large amount of data to be collected for research and analysis, which is time-consuming and leads to low efficiency in mineral resource exploration. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a deep and concealed mine exploration method and system, which can improve the exploration efficiency of mineral resources.

[0005] In a first aspect, the present invention provides a method, medium, and storage medium for deep and concealed mine exploration, comprising:

[0006] Acquire a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics;

[0007] Determining the regional evolution stage of the mineral deposit area based on the geological structure category, and analyzing the mineral location of the mineral deposit area according to the regional evolution stage;

[0008] Inputting the regional characteristics, the geological structure category, and the mineral location as sample data into a trained mineral analysis model, so as to extract features from the sample data through a convolutional network in the mineral analysis model to obtain feature data;

[0009] Utilizing the attention mechanism in the mineral analysis model to filter out mineral description features of the mineral area from the feature data;

[0010] According to the mineral description characteristics, the regression network in the mineral analysis model is used to calculate the mineral distribution probability of the mineral area, and according to the mineral distribution probability, the mineral distribution result of the mineral area is generated.

[0011] In a possible implementation of the first aspect, extracting the regional characteristics of the mineral area includes:

[0012] Collecting regional soil data of the mineral area;

[0013] Identifying regional geological attributes in the regional soil data;

[0014] The regional characteristics of the mineral area are identified based on the regional geological attributes.

[0015] In a possible implementation of the first aspect, analyzing the geological structure category of the mineral deposit area includes:

[0016] Collecting regional soil data of the mineral area and identifying regional geological attributes in the regional soil data;

[0017] The regional characteristics of the mineral area are identified based on the regional geological attributes.

[0018] In a possible implementation of the first aspect, analyzing the geological structure category of the mineral deposit area includes:

[0019] Collecting the regional landforms of the mineral deposit area and identifying the geomorphic features of the regional landforms;

[0020] According to the landform characteristics, the geological structure category of the mineral area is analyzed.

[0021] In a possible implementation of the first aspect, determining the regional evolution stage of the mineral deposit area based on the geological structure category includes:

[0022] Analyzing the geological category characteristics of the geological structure category;

[0023] The following formula is used to calculate the logical correlation value between the category features in the geological category feature:

[0024] ρs(t)=Q(q itx )

[0025] Among them, ρs(t) represents the logical association value, i represents the sequence symbol of the category feature in the geological category feature, Q represents the association function, q itx geological category characteristics;

[0026] identifying, according to the association value, feature logical relationships between category features in the geological category features;

[0027] According to the characteristic logical relationship, the regional evolution stage of the mineral area is determined.

[0028] In a possible implementation of the first aspect, extracting features from the sample data using a convolutional network in the mineral analysis model to obtain feature data includes:

[0029] Analyzing the data relationship of the sample data using the convolutional layer in the convolutional network;

[0030] According to the data relationship, construct a relationship graph of the sample data using the association layer in the convolutional network;

[0031] According to the relationship graph, feature data of the sample data is extracted using a feature extraction function in the convolutional network.

[0032] In a possible implementation of the first aspect, a convolutional layer in the convolutional network is used to analyze data relationships of the sample data;

[0033] According to the data relationship, construct a relationship graph of the sample data using the association layer in the convolutional network;

[0034] According to the relationship graph, feature data of the sample data is extracted using a feature extraction function in the convolutional network.

[0035] In a possible implementation of the first aspect, the using the attention mechanism in the mineral analysis model to filter out the mineral description features of the mineral area from the feature data includes:

[0036] Clustering the feature data using the clustering layer in the attention mechanism to obtain clustered feature data;

[0037] According to the cluster feature data, using the rule layer in the attention mechanism to configure mineral feature extraction rules;

[0038] According to the mineral feature extraction rules, the screening layer in the attention mechanism is used to screen out the mineral description features of the mineral area.

[0039] In a possible implementation of the first aspect, calculating the mineral distribution probability of the mineral area using a regression network in the mineral analysis model according to the mineral description characteristics includes:

[0040] According to the mineral description features, using the model layer of the regression network to configure the weight coefficient of the mineral description features;

[0041] Calculating the total weight of the mineral region using a summation layer in the regression network according to the weight coefficient;

[0042] The mineral distribution probability of the mineral area is calculated according to the total weight.

[0043] In a possible implementation of the first aspect, calculating the mineral distribution probability of the mineral area according to the total weight includes:

[0044] The probability of mineral distribution in the mineral area is described using the following formula:

[0045]

[0046] Among them, MEC represents the probability of mineral distribution, represents the total weight, u n Represents the weight of the nth mineral description feature.

[0047] In a second aspect, the present invention provides a deep and concealed mine exploration system, the system comprising:

[0048] A geological classification module is used to obtain a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics;

[0049] a mineral location determination module, configured to determine the regional evolution stage of the mineral region based on the geological structure category, and analyze the mineral location of the mineral region according to the regional evolution stage;

[0050] a feature data extraction module, configured to input the regional features, the geological structure category, and the mineral location as sample data into a trained mineral analysis model, so as to extract features from the sample data through a convolutional network in the mineral analysis model to obtain feature data;

[0051] A mineral description feature acquisition module, configured to utilize the attention mechanism in the mineral analysis model to filter out the mineral description features of the mineral area from the feature data;

[0052] The mineral distribution result acquisition module is used to calculate the mineral distribution probability of the mineral area according to the mineral description characteristics using the regression network in the mineral analysis model, and generate the mineral distribution result of the mineral area according to the mineral distribution probability.

[0053] Compared with the existing technology, the technical principle and beneficial effects of this solution are:

[0054] First, the embodiment of the present invention can analyze the possibility of the existence of minerals in the area by analyzing the geological structure category of the mineral area, thereby improving the exploration efficiency of mineral resources; secondly, the embodiment of the present invention determines the regional evolution stage of the mineral area based on the geological structure category, and can judge the possibility of the existence of mineral resources in the mineral area according to the regional evolution stage through previous data, thereby improving the exploration efficiency; thirdly, the embodiment of the present invention inputs the regional characteristics, the geological structure category and the mineral location as sample data into the trained mineral analysis model, so as to extract features of the sample data through the convolutional network in the mineral analysis model, and obtain feature data based on the sample data. The prospecting model is formed, and feature data is extracted from the area where the mineral deposit area may have minerals, thereby locking the location where the minerals may exist and improving the exploration efficiency; further, the embodiment of the present invention can further analyze the geological characteristics of the location where the mineral deposits may exist by using the attention mechanism in the mineral analysis model to filter out the mineral description features of the mineral deposit area from the feature data, thereby judging whether there are characteristics of the existence of minerals and improving the exploration efficiency; then, the embodiment of the present invention can calculate the possibility of the existence of minerals in the mineral deposit area by calculating the mineral distribution probability of the mineral deposit area based on the mineral description features using the regression network in the mineral analysis model, thereby avoiding blind exploration and improving the exploration efficiency. Therefore, the deep and hidden mine exploration method and system proposed in the embodiment of the present invention can improve the exploration efficiency of mineral resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0057] Figure 1 A schematic flow chart of a method for deep and concealed mine exploration provided by one embodiment of the present invention;

[0058] Figure 2 A schematic diagram of a module of a deep and concealed mine exploration system provided by one embodiment of the present invention;

[0059] Figure 3 A schematic diagram of the internal structure of an electronic device for a method for deep and concealed mine exploration provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] The embodiments of the present invention provide a method, system and storage medium for deep and hidden mine exploration. The execution subject of the deep and hidden mine exploration method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the deep and hidden mine exploration method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0062] See Figure 1 FIG. 1 is a flow chart of a method, system and storage medium for deep and concealed mine exploration according to an embodiment of the present invention. Figure 1 A deep and concealed mine exploration method, system and storage medium described in the disclosure include:

[0063] S1. Obtain a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics;

[0064] The embodiment of the present invention can provide a location basis for subsequent mineral resource exploration in the region by obtaining a mineral region to be surveyed, wherein the mineral region refers to an area where mineral resource exploration is required.

[0065] Furthermore, by extracting regional characteristics of the mineral region, embodiments of the present invention can effectively analyze the basic characteristics of the mineral region's address, providing data support for later identifying the mineral region's location, thereby improving the efficiency of mineral resource exploration. The regional characteristics refer to the basic properties of the mineral region, such as rocky areas, gullies, and soft soil.

[0066] As an embodiment of the present invention, the extraction of regional characteristics of the mineral area includes: collecting regional soil data of the mineral area; identifying regional geological attributes in the regional soil data; and identifying the regional characteristics of the mineral area based on the regional geological attributes.

[0067] The regional soil data refers to the soil data collected in the mineral area, such as soft soil, rock, etc. The regional geological attributes refer to the regional soil attribute data obtained by analyzing the regional soil data, such as uniform rock distribution, more gullies, etc.

[0068] Furthermore, in an optional embodiment of the present invention, the regional soil data of the mineral area may be collected by a land surveying instrument.

[0069] Furthermore, in an optional embodiment of the present invention, identifying the regional characteristics of the mineral region based on the regional geological attributes can be achieved through a judgment function.

[0070] Furthermore, embodiments of the present invention can analyze the likelihood of mineral deposits in a mineral deposit area by analyzing the geological structure category of the mineral deposit area, thereby improving the efficiency of mineral resource exploration. The geological structure category refers to the category of the address, such as folds, joints, faults, etc.

[0071] As an embodiment of the present invention, the analysis of the geological structure category of the mineral area includes: collecting the regional landform of the mineral area; identifying the geomorphological characteristics of the regional landform; and analyzing the geological structure category of the mineral area based on the geomorphological characteristics.

[0072] The regional landform refers to the topographical features of the mineral deposit area, such as slopes and large pits. The geomorphic features refer to the geomorphic characteristics of the regional landform, such as upward curvature of rock layers, older rock layers in the center and progressively younger rock layers on both sides, and fractures with significant displacement. Faults are widely developed in the Earth's crust, but their distribution is uneven.

[0073] Furthermore, in an optional embodiment of the present invention, the collection of the regional topography of the mineral area can be achieved through aerial photography and satellite monitoring.

[0074] S2. Determine the regional evolution stage of the mineral deposit area based on the geological structure category, and analyze the mineral location of the mineral deposit area according to the regional evolution stage.

[0075] By determining the regional evolution stage of the mineral region based on the geological structure category, embodiments of the present invention can improve exploration efficiency by judging the likelihood of the presence of mineral resources in the mineral region based on historical data based on the regional evolution stage. The regional evolution stage refers to the stage of land evolution in the region, such as the soil stage, rock stage, and so on.

[0076] As an embodiment of the present invention, determining the regional evolution stage of the mineral region based on the geological structure category includes: analyzing geological category characteristics of the geological structure category; and calculating the logical correlation value between category characteristics in the geological category characteristics using the following formula:

[0077] ρs(t)=Q(q itx )

[0078] Among them, ρs(t) represents the logical association value, i represents the sequence symbol of the category feature in the geological category feature, Q represents the association function, q itx geological category characteristics;

[0079] According to the association value, the characteristic logical relationship between the category features in the geological category feature is identified; according to the characteristic logical relationship, the regional evolution stage of the mineral area is determined.

[0080] The geological category characteristics refer to the land characteristics of the geological structure category, for example, folded land has many slopes and fault land has many pits, and the characteristic logical relationship refers to the correlation relationship between different geological characteristics.

[0081] Furthermore, embodiments of the present invention can analyze the mineral locations of the mineral region based on the regional evolution stage to preliminarily determine the possible locations of minerals, and then conduct surveys at those locations, thereby improving the effectiveness of mineral resource exploration. The mineral locations refer to locations within the mineral region where minerals may be present.

[0082] As an embodiment of the present invention, analyzing the mineral location of the mineral area according to the regional evolution stage includes: retrieving historical mineral records of the regional evolution stage; extracting the historical mineral environment of the historical mineral records; and locating the mineral location of the mineral area according to the historical mineral environment.

[0083] The historical mineral records refer to the mineral records discovered in history, including data such as the discovery address, mineral quantity, mineral type, and the surrounding environment of the mineral. The historical mineral environment refers to the environment in which the mineral was discovered.

[0084] Furthermore, in an optional embodiment of the present invention, the retrieval of historical mineral records of the regional evolution stage can be performed by writing a crawler script in Java.

[0085] Furthermore, in an optional embodiment of the present invention, the historical mineral environment from which the historical mineral records are extracted may be queried through a query statement.

[0086] S3. Input the regional characteristics, the geological structure category and the mineral location as sample data into the trained mineral analysis model, so as to extract features of the sample data through the convolutional network in the mineral analysis model to obtain feature data.

[0087] In an embodiment of the present invention, the regional characteristics, the geological structure category, and the mineral location are input as sample data into a trained mineral analysis model, and the convolutional network in the mineral analysis model is used to extract features from the sample data. The obtained feature data can be used to generate a prospecting model based on the sample data, and modern 3D technology is used to extract feature data from areas in the mineral region where minerals may exist, thereby locking in locations where minerals may exist and improving exploration efficiency. The feature data refers to sample feature data obtained through land simulation exploration based on the sample data, such as feature data such as the presence of a large amount of hard solid matter 30 meters underground and the presence of a fault 10 meters underground.

[0088] As an embodiment of the present invention, the feature extraction of the sample data through the convolutional network in the mineral analysis model to obtain feature data includes: using the convolutional layer in the convolutional network to analyze the data relationship of the sample data; based on the data relationship, using the association layer in the convolutional network to construct a relationship graph of the sample data; based on the relationship graph, using the feature extraction function in the convolutional network to extract the feature data of the sample data.

[0089] Among them, the convolution layer refers to a layer used to acquire data and analyze the relationship between the data, the data relationship refers to the data connection between the features of the sample data, the association layer refers to a layer used to store data and perform logical construction on it, the feature relationship graph refers to a logical relationship graph between each sample data constructed through the data relationship, and the feature extraction function refers to a function used to analyze and extract key data from a large amount of data.

[0090] Furthermore, in an optional embodiment of the present invention, the feature extraction function includes:

[0091]

[0092] Among them, W(sicX) represents the feature data, f(x, y) represents the relationship diagram of sample data, β 2 represents the variance of the sample data, and x and y represent the x-th and y-th data of the sample data.

[0093] S4. Utilize the attention mechanism in the mineral analysis model to filter out mineral description features of the mineral area from the feature data.

[0094] In embodiments of the present invention, by utilizing the attention mechanism in the mineral analysis model to filter out mineral description features of the mineral region from the feature data, the geological characteristics of the location where the mineral may be located can be further analyzed, thereby determining whether the location has characteristics of the presence of minerals and improving exploration efficiency. The mineral description features refer to the descriptive feature data of the possible presence of minerals analyzed by the mineral analysis model, such as data indicating the presence of a large amount of metal substances underground in the mineral region or the discovery of liquid flow underground in the mineral region.

[0095] As an embodiment of the present invention, the use of the attention mechanism in the mineral analysis model to filter out the mineral description features of the mineral area from the feature data includes: clustering the feature data using the clustering layer in the attention mechanism to obtain cluster feature data; configuring mineral feature extraction rules using the rule layer in the attention mechanism based on the cluster feature data; and filtering out the mineral description features of the mineral area using the screening layer in the attention mechanism based on the mineral feature extraction rules.

[0096] Among them, the clustering layer refers to the layer used for data classification in the attention mechanism, the clustering feature data refers to the classification of the feature data according to different description types, such as soil description, rock description, etc. The rule layer refers to the layer used to formulate mineral feature data extraction rules in the attention mechanism, and the mineral feature extraction rules refer to the formulated data rules for extracting data that have reference significance for mineral resources. The screening layer refers to the layer used for data selection in the attention mechanism.

[0097] Furthermore, in an optional embodiment of the present invention, clustering the feature data to obtain clustered feature data may be achieved through a clustering function.

[0098] S5. Calculate the mineral distribution probability of the mineral area using the regression network in the mineral analysis model according to the mineral description characteristics, and generate the mineral distribution result of the mineral area according to the mineral distribution probability.

[0099] In the embodiment of the present invention, the probability of the presence of minerals in a mineral region can be calculated by calculating the mineral distribution probability in the mineral region based on the mineral description features using a regression network in the mineral analysis model, thereby avoiding blind surveys and improving survey efficiency. The mineral distribution probability refers to the calculated probability of mineral distribution.

[0100] As an embodiment of the present invention, the method of calculating the mineral distribution probability of the mineral area based on the mineral description characteristics using the regression network in the mineral analysis model includes: configuring the weight coefficient of each mineral description feature based on the mineral description characteristics using the weight layer of the regression network; calculating the total weight of the mineral area based on the weight coefficient using the summation layer in the regression network; and calculating the mineral distribution probability of the mineral area based on the total weight.

[0101] Among them, the weight layer refers to a layer used to set different weights for different mineral description features, and the weight coefficient refers to the weight assigned to the mineral description feature. For example, if there is liquid underground in the mineral area, the weight coefficient assigned is 0.15; if there is metal object underground in the mineral area, the weight coefficient assigned is 0.16, etc. The summation layer refers to a layer used to calculate the total weight of all weights in the mineral area, and the total weight refers to the total weight value obtained by summing the weighted values ​​of the mineral description features.

[0102] Furthermore, in an optional embodiment of the present invention, the mineral distribution probability of the mineral area is calculated using the following formula:

[0103]

[0104] Among them, MEC represents the probability of mineral distribution, represents the total weight; u n Represents the weight of the nth mineral description feature.

[0105] Furthermore, embodiments of the present invention can ultimately determine the mineral situation in a mineral region by generating a mineral distribution result for the mineral region based on the mineral distribution probability, thereby targeting the mineral resource exploration and improving exploration efficiency. The mineral distribution result refers to the mineral situation in the mineral region obtained through exploration.

[0106] As an embodiment of the present invention, the mineral distribution result of the mineral area is generated according to the mineral distribution probability by comparing the mineral distribution probability with a preset mineral existence value, removing those that do not reach the mineral existence value, and generating the mineral distribution result with the remaining minerals that reach the mineral existence value.

[0107] It can be seen that the embodiment of the present invention can analyze the possibility of the existence of minerals in the area by analyzing the geological structure category of the mineral area, thereby improving the exploration efficiency of mineral resources; secondly, the embodiment of the present invention determines the regional evolution stage of the mineral area based on the geological structure category, and can judge the possibility of the existence of mineral resources in the mineral area according to the regional evolution stage through previous data, thereby improving the exploration efficiency; thirdly, the embodiment of the present invention inputs the regional characteristics, the geological structure category and the mineral location as sample data into the trained mineral analysis model, so as to extract features of the sample data through the convolutional network in the mineral analysis model, and obtain feature data based on the sample data. Generate a prospecting model, extract feature data for the area where minerals may exist in the mineral area, thereby locking the location where minerals may exist and improving exploration efficiency; further, the embodiment of the present invention can further analyze the geological characteristics of the location where minerals may exist by using the attention mechanism in the mineral analysis model to filter out the mineral description features of the mineral area from the feature data, thereby determining whether there are characteristics of the existence of minerals and improving exploration efficiency; then, the embodiment of the present invention can calculate the possibility of the existence of minerals in the mineral area by using the regression network in the mineral analysis model based on the mineral description features, thereby avoiding blind exploration and improving exploration efficiency. Therefore, the deep and hidden mine exploration method proposed in the embodiment of the present invention can improve the exploration efficiency of mineral resources.

[0108] like Figure 2 FIG. 1 is a functional module diagram of a deep and concealed mine exploration system according to the present invention.

[0109] The deep and concealed mine exploration system 200 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the system can include a geological classification module 201, a mineral location determination module 202, a feature data extraction module 203, a mineral description feature acquisition module 204, and a mineral distribution result acquisition module 205. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function. These modules are stored in the electronic device's memory.

[0110] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0111] The geological classification module 201 is used to obtain a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics;

[0112] The mineral location determination module 202 is used to determine the regional evolution stage of the mineral area based on the geological structure category, and analyze the mineral location of the mineral area according to the regional evolution stage;

[0113] The feature data extraction module 203 is used to input the regional characteristics, the geological structure category and the mineral location as sample data into the trained mineral analysis model, so as to extract features from the sample data through the convolutional network in the mineral analysis model to obtain feature data;

[0114] The mineral description feature acquisition module 204 is used to filter out the mineral description features of the mineral area from the feature data using the attention mechanism in the mineral analysis model;

[0115] The mineral distribution result acquisition module 205 is used to calculate the mineral distribution probability of the mineral area according to the mineral description characteristics using the regression network in the mineral analysis model, and generate the mineral distribution result of the mineral area according to the mineral distribution probability.

[0116] In detail, each module in the deep and concealed mine exploration system 200 described in the embodiment of the present invention adopts the same method as above when in use. Figure 1 The above-mentioned method for deep and concealed mine exploration has the same technical means and can produce the same technical effects, so it will not be described in detail here.

[0117] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing a method for exploring deep and concealed mines according to the present invention.

[0118] The electronic device may include a processor 30 , a memory 31 , a communication bus 32 , and a communication interface 33 . It may also include a computer program stored in the memory 31 and executable on the processor 30 , such as a deep and concealed mine exploration program.

[0119] In some embodiments, the processor 30 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 30 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and lines, and executing programs or modules stored in the memory 31 (for example, executing deep and concealed mine exploration programs, etc.), as well as calling data stored in the memory 31, to perform various functions of the electronic device and process data.

[0120] The memory 31 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 31 can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 31 can also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. equipped on the electronic device. Furthermore, the memory 31 can also include both an internal storage unit of the electronic device and an external storage device. The memory 31 can not only be used to store application software and various types of data installed in the electronic device, such as the code of a deep and concealed mine exploration program, but can also be used to temporarily store data that has been output or is to be output.

[0121] The communication bus 32 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 31 and at least one processor 30.

[0122] The communication interface 33 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, for displaying information processed in the electronic device and for displaying a visual user interface.

[0123] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not limit the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0124] For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 30 via a power management system, thereby implementing functions such as charge management, discharge management, and power consumption management through the power management system. The power source may further include any components such as one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0125] It should be understood that the embodiment is for illustrative purposes only and the scope of the patent invention is not limited to this structure.

[0126] The deep and concealed mine exploration and protection program stored in the memory 31 of the electronic device is a combination of multiple computer programs. When running in the processor 30, it can achieve the following:

[0127] Acquire a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics;

[0128] Determining the regional evolution stage of the mineral deposit area based on the geological structure category, and analyzing the mineral location of the mineral deposit area according to the regional evolution stage;

[0129] Inputting the regional characteristics, the geological structure category, and the mineral location as sample data into a trained mineral analysis model, so as to extract features from the sample data through a convolutional network in the mineral analysis model to obtain feature data;

[0130] Utilizing the attention mechanism in the mineral analysis model to filter out mineral description features of the mineral area from the feature data;

[0131] According to the mineral description characteristics, the regression network in the mineral analysis model is used to calculate the mineral distribution probability of the mineral area, and according to the mineral distribution probability, the mineral distribution result of the mineral area is generated.

[0132] Specifically, the specific implementation method of the processor 30 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0133] Furthermore, if the module / unit integrated into the electronic device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0134] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0135] Acquire a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics;

[0136] Determining the regional evolution stage of the mineral deposit area based on the geological structure category, and analyzing the mineral location of the mineral deposit area according to the regional evolution stage;

[0137] Inputting the regional characteristics, the geological structure category, and the mineral location as sample data into a trained mineral analysis model, so as to extract features from the sample data through a convolutional network in the mineral analysis model to obtain feature data;

[0138] Utilizing the attention mechanism in the mineral analysis model to filter out mineral description features of the mineral area from the feature data;

[0139] According to the mineral description characteristics, the regression network in the mineral analysis model is used to calculate the mineral distribution probability of the mineral area, and according to the mineral distribution probability, the mineral distribution result of the mineral area is generated.

[0140] In the several embodiments provided herein, it should be understood that the disclosed devices, systems, and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical functional division, and actual implementation may employ other division methods.

[0141] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0142] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0143] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0144] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0145] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0146] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for exploring deep and concealed mines, characterized in that: The method comprises: Acquire a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics; Determining the regional evolution stage of the mineral deposit area based on the geological structure category, and analyzing the mineral location of the mineral deposit area according to the regional evolution stage; Inputting the regional characteristics, the geological structure category, and the mineral location as sample data into a trained mineral analysis model, so as to extract features from the sample data through a convolutional network in the mineral analysis model to obtain feature data; Utilizing the attention mechanism in the mineral analysis model to filter out mineral description features of the mineral area from the feature data; According to the mineral description characteristics, the regression network in the mineral analysis model is used to calculate the mineral distribution probability of the mineral area, and according to the mineral distribution probability, the mineral distribution result of the mineral area is generated.

2. The method according to claim 1, characterized in that The extracting of regional features of the mineral area includes: Collecting regional soil data of the mineral area and identifying regional geological attributes in the regional soil data; The regional characteristics of the mineral area are identified based on the regional geological attributes.

3. The method according to claim 1, characterized in that The analysis of the geological structure category of the mineral area includes: Collecting the regional landforms of the mineral deposit area and identifying the geomorphic features of the regional landforms; According to the landform characteristics, the geological structure category of the mineral area is analyzed.

4. The method according to claim 1, wherein Determining the regional evolution stage of the mineral region based on the geological structure category includes: Analyzing the geological category characteristics of the geological structure category; The following formula is used to calculate the logical correlation value between the category features in the geological category feature: ρs(t)=Q(q itx ) Among them, ρs(t) represents the logical association value, i represents the sequence symbol of the category feature in the geological category feature, Q represents the association function, q itx geological category characteristics; identifying, according to the association value, feature logical relationships between category features in the geological category features; According to the characteristic logical relationship, the regional evolution stage of the mineral area is determined.

5. The method according to claim 1, characterized in that The feature extraction of the sample data by the convolutional network in the mineral analysis model to obtain feature data includes: Analyzing the data relationship of the sample data using the convolutional layer in the convolutional network; According to the data relationship, construct a relationship graph of the sample data using the association layer in the convolutional network; According to the relationship graph, feature data of the sample data is extracted using a feature extraction function in the convolutional network.

6. The method according to claim 5, characterized in that The feature extraction function includes: Among them, W(sicX) represents the feature data, f(x, y) represents the relationship diagram of sample data, β 2 represents the variance of the sample data, and x and y represent the x-th and y-th data of the sample data.

7. The method according to claim 1, characterized in that The method of using the attention mechanism in the mineral analysis model to filter out mineral description features of the mineral area from the feature data includes: Clustering the feature data using the clustering layer in the attention mechanism to obtain clustered feature data; According to the cluster feature data, the rule layer in the attention mechanism is used to configure mineral feature extraction rules; According to the mineral feature extraction rules, the screening layer in the attention mechanism is used to screen out the mineral description features of the mineral area.

8. The method according to any one of claims 1 to 7, characterized in that The method of calculating the mineral distribution probability of the mineral area using the regression network in the mineral analysis model according to the mineral description characteristics includes: According to the mineral description features, using the model layer of the regression network to configure the weight coefficient of the mineral description features; Calculating the total weight of the mineral region using a summation layer in the regression network according to the weight coefficient; The mineral distribution probability of the mineral area is calculated according to the total weight.

9. The method according to claim 8, characterized in that Calculating the mineral distribution probability of the mineral area according to the total weight includes: The probability of mineral distribution in the mineral area is described using the following formula: Among them, MEC represents the probability of mineral distribution, represents the total weight, u n Represents the weight of the nth mineral description feature.

10. A deep and concealed mine exploration system, characterized in that: The system comprises: A geological classification module is used to obtain a mineral area to be surveyed, extract regional characteristics of the mineral area, and analyze the geological structure category of the mineral area based on the regional characteristics; a mineral location determination module, configured to determine the regional evolution stage of the mineral region based on the geological structure category, and analyze the mineral location of the mineral region according to the regional evolution stage; a feature data extraction module, configured to input the regional features, the geological structure category, and the mineral location as sample data into a trained mineral analysis model, so as to extract features from the sample data through a convolutional network in the mineral analysis model to obtain feature data; A mineral description feature acquisition module, configured to utilize the attention mechanism in the mineral analysis model to filter out the mineral description features of the mineral area from the feature data; The mineral distribution result acquisition module is used to calculate the mineral distribution probability of the mineral area according to the mineral description characteristics using the regression network in the mineral analysis model, and generate the mineral distribution result of the mineral area according to the mineral distribution probability.

Images