A Magnetotelluric Sounding Evaluation Method and System

Abstract

This specification provides a magnetotelluric sounding evaluation method and system. The method is executed based on a processor of the magnetotelluric sounding evaluation system, and includes: obtaining historical geological data of a mining area, human activity information at multiple preset time points, and power equipment operation information at multiple preset time points; and obtaining multiple sets of original electromagnetic monitoring data; determining at least one set of electromagnetic monitoring spectra based on the human activity information at multiple preset time points, the power equipment operation information at multiple preset time points, and the multiple sets of original electromagnetic monitoring data; determining at least one set of mining geological evaluation information based on the at least one set of electromagnetic monitoring spectra; and determining a mining geological inference result from the at least one set of mining geological evaluation information based on the historical geological data of the mining area, the human activity information at multiple preset time points, and the power equipment operation information at multiple preset time points.

Description

Technical Field

[0001] This specification relates to the field of electromagnetic prospecting, and particularly to a magnetotelluric prospecting evaluation method and system. Background Art

[0002] To ensure the smooth progress of mine development work, technicians usually need to detect the vein trend and geological structure of the mining area in advance. Magnetotelluric sounding can invert the resistivity distribution information of underground media at different depths by studying the electromagnetic data collected on the surface, so as to understand the distribution of rock and soil media and geological structure in the mining area. However, when large electrical equipment in the mine suddenly starts or shuts down, or the load suddenly changes, step signals, charge and discharge signals, and square wave signals will be generated, which have a great impact on the quality of electromagnetic detection signals and evaluation results.

[0003] Therefore, it is necessary to propose a magnetotelluric prospecting evaluation method and system to improve the signal quality and accuracy of magnetotelluric prospecting. Summary of the Invention

[0004] One or more embodiments of this specification provide a magnetotelluric prospecting evaluation method. The method is executed based on a processor of a magnetotelluric prospecting evaluation system. The method includes: obtaining historical geological data of a mining area, human activity information at multiple preset time points, and power equipment operation information at multiple preset time points based on an interaction device of the magnetotelluric prospecting evaluation system; and obtaining multiple groups of original electromagnetic monitoring data based on a magnetotelluric detection device of the magnetotelluric prospecting evaluation system; determining at least one group of electromagnetic monitoring spectra based on the human activity information at the multiple preset time points, the power equipment operation information at the multiple preset time points, and the multiple groups of original electromagnetic monitoring data; determining at least one group of mine geological evaluation information based on the at least one group of electromagnetic monitoring spectra; and determining a mine geological inference result from at least one group of mine geological evaluation information based on the historical geological data of the mining area, the human activity information at the multiple preset time points, and the power equipment operation information at the multiple preset time points.

[0005] One or more embodiments of this specification provide a magnetotelluric prospecting evaluation system, including a magnetotelluric monitoring device, an interaction device, and a processor; the magnetotelluric detection device is configured to obtain multiple groups of original electromagnetic monitoring data; the multiple groups of original electromagnetic data are electromagnetic monitoring data at multiple preset time points; the interaction device is configured to: obtain historical geological data of a mining area, human activity information at multiple preset time points, and power equipment operation information at multiple preset time points; the human activity information at the multiple preset time points includes activity intensity; the power equipment operation information at the multiple preset time points includes power equipment opening and closing changes; the processor is configured to determine a mine geological inference result.

[0006] One or more embodiments of this specification provide a computer-readable storage medium storing computer instructions, which, when read by a computer, cause the computer to execute the foregoing method. Description of the Drawings

[0007] This specification will be further illustrated by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same reference numerals represent the same structures, where:

[0008] Figure 1 is a schematic diagram of a magnetotelluric sounding evaluation system according to some embodiments of this specification;

[0009] Figure 2 is an exemplary flowchart of a magnetotelluric sounding evaluation method according to some embodiments of this specification;

[0010] Figure 3 is a schematic diagram of an electromagnetic monitoring spectrum determination model according to some embodiments of this specification;

[0011] Figure 4 is a schematic diagram of mine geological evaluation information according to some embodiments of this specification;

[0012] Figure 5 is a schematic diagram of an inference reliability model according to some embodiments of this specification. Detailed Description of the Embodiments

[0013] To more clearly illustrate the technical solutions of the embodiments of this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the context or otherwise stated, the same reference numerals in the figures represent the same structures or operations.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein is a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0015] As shown in this specification and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the previous or subsequent operations are not necessarily executed precisely in sequence. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 is a schematic diagram of a magnetotelluric sounding evaluation system according to some embodiments of this specification.

[0018] In some embodiments, as Figure 1 shown, the magnetotelluric sounding evaluation system 100 may include a magnetotelluric monitoring device 110, an interaction device 120, and a processor 130.

[0019] The magnetotelluric monitoring device 110 refers to a device for acquiring magnetotelluric monitoring signals. For example, the magnetotelluric monitoring device may include at least one of an electromagnetic inductor, a magnetotelluric instrument, etc.

[0020] In some embodiments, the magnetotelluric monitoring device 110 is configured to acquire multiple sets of original electromagnetic monitoring data. For more information on the multiple sets of original electromagnetic monitoring data, see Figure 2 the relevant description.

[0021] The interaction device 120 refers to a device for information interaction. For example, the interaction device may be a terminal with a screen. In some embodiments, the interaction device 120 is configured to acquire historical geological data of the mining area, human activity information at multiple preset time points, and power equipment operation information at multiple preset time points. For more information on the historical geological data of the mining area, human activity information at multiple preset time points, and power equipment operation information at multiple preset time points, see Figure 2 the relevant description.

[0022] The processor 130 refers to a server that can process data and / or information obtained from other devices or system components. The processor 130 executes program instructions based on these data, information, and / or processing results to perform one or more functions described in this application.

[0023] The processor 130 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processor can be local or remote. In some embodiments, the processor can be implemented on a cloud platform. By way of example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc. or any combination thereof.

[0024] In some embodiments, the processor 130 is configured to determine a mine geological inference result.

[0025] In some embodiments, the processor 130 is further configured to: obtain historical geological data of a mine area, human activity information at multiple preset time points, power equipment operation information at multiple preset time points, and multiple sets of original electromagnetic monitoring data; determine at least one set of electromagnetic monitoring spectra based on the human activity information at multiple preset time points, the power equipment operation information at multiple preset time points, and the multiple sets of original electromagnetic monitoring data; determine at least one set of mine geological assessment information based on the at least one set of electromagnetic monitoring spectra; and determine a mine geological inference result from the at least one set of mine geological assessment information based on the historical geological data of the mine area, the human activity information at multiple preset time points, and the power equipment operation information at multiple preset time points.

[0026] In some embodiments, the processor 130 is further configured to: determine at least one set of electromagnetic monitoring spectra based on the human activity information at multiple preset time points, the power equipment operation information at multiple preset time points, and the multiple sets of original electromagnetic monitoring data through an electromagnetic monitoring spectrum determination model.

[0027] In some embodiments, the processor 130 is further configured to: determine the similarity features and difference features of the corresponding mine area based on the at least one set of mine geological assessment information; and determine a mine geological inference result based on the historical geological data of the mine area, the human activity information at multiple preset time points, the power equipment operation information at multiple preset time points, the at least one set of mine geological assessment information, and its corresponding similarity features and difference features.

[0028] In some embodiments, the processor 130 is further configured to: determine similarity features and difference features based on the historical geological data of the mine area, the human activity information at multiple preset time points, the power equipment operation information at multiple preset time points, and the at least one set of mine geological assessment information.

[0029] A data connection can be established between the magnetotelluric monitoring device 110, the interaction device 120, and the processor 130 in a wired or wireless manner.

[0030] In some embodiments of this specification, based on the magnetotelluric sounding evaluation system, an information operation closed-loop can be formed among the magnetotelluric monitoring device, the interaction device, and the processor, effectively improving the efficiency and accuracy of magnetotelluric sounding, thereby improving the accuracy of mine geological inference results.

[0031] It should be understood that Figure 1 the system and its modules shown can be implemented in various ways.

[0032] It should be noted that the above description of the magnetotelluric sounding evaluation system 100 and its modules is only for convenience of description and does not limit this specification within the scope of the exemplified embodiments. It can be understood that for those skilled in the art, after understanding the principle of the system, they may, without departing from this principle, make any combination of the various modules, or form a subsystem and connect it with other modules. In some embodiments, Figure 1 the magnetotelluric detection device 110, the interaction device 120, and the processor 130 disclosed in [reference] can be different modules in a system, or a module can implement the functions of two or more of the above modules. For example, the various modules can share a storage module, or each module can have its own storage module respectively. Such deformations are all within the protection scope of this specification.

[0033] Figure 2 is an exemplary flowchart of the magnetotelluric sounding evaluation method according to some embodiments of this specification. As Figure 2 shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by the processor.

[0034] Step 210, based on the interaction device of the magnetotelluric sounding evaluation system, obtain the historical geological data of the mine area, the human activity information at multiple preset time points, and the operation information of power equipment at multiple preset time points; and based on the magnetotelluric detection device of the magnetotelluric sounding evaluation system, obtain multiple groups of original electromagnetic monitoring data.

[0035] The historical geological data of the mine area refers to the geological information data of different areas of the mine obtained by historical surveying and mapping. The historical geological data of the mine area includes the altitude, topography, and stratigraphic structure of different areas.

[0036] In some embodiments, the processor can import the historical geological data of the mine area from the historical database. The historical database can be constructed from the geological information data surveyed by the user and input through the interaction device.

[0037] Human activity information refers to the situation of workers participating in production activities within the mining area. Human activity information may include characteristics of human activities, and example activity characteristics may include activity intensity. Among them, activity intensity can be measured by the number of people participating in the activity. The more people there are, the greater the activity intensity. For example, the activity intensity when 200 people enter the mining area simultaneously to participate in production activities is greater than that when 100 people enter the mining area simultaneously to participate in production activities.

[0038] Multiple preset time points refer to the time points preset artificially for recording human activity information in the mining area. For example, multiple preset time points can be 8:00 am, 12:00 noon, and 18:00 pm every day, etc.

[0039] In some embodiments, the processor can obtain human activity information at multiple preset time points from the historical database. For example, it can obtain human activity information at multiple historical time points that are the same as the preset time points. For example, if the multiple preset time points are 8:00 am, 12:00 noon, and 18:00 pm on Tuesday, the processor can obtain the human activity information at 8:00 am, 12:00 noon, and 18:00 pm last Tuesday.

[0040] Power equipment operation information refers to the relevant characteristics of the operation of power equipment in the mining area. The power equipment operation information includes the on and off situations of the power equipment. For example, at 8:00 am, power equipment 1 changes from on to off, and at 18:00 pm, power equipment 2 changes from off to on.

[0041] Multiple preset time points refer to the time points preset artificially for recording power equipment operation information. For example, multiple preset time points can be 8:00 am, 12:00 noon, and 18:00 pm. In some embodiments, the preset time points for recording human activity information in the mining area are the same as those for recording power equipment operation information.

[0042] In some embodiments, the processor can obtain power equipment operation information at multiple preset time points from the historical database. For example, the processor can obtain power equipment operation information at multiple historical time points that are the same as the preset time points. By way of example, if the multiple preset time points are 8:00 am, 12:00 noon, and 18:00 pm on Tuesday, then the power equipment operation information at 8:00 am, 12:00 noon, and 18:00 pm last Tuesday can be obtained.

[0043] Original electromagnetic monitoring data refers to the electromagnetic data of the mine detected by the magnetotelluric detection device, such as the electromagnetic spectrum.

[0044] Multiple sets of original electromagnetic monitoring spectra refer to the original electromagnetic monitoring data obtained at multiple preset time points. For example, a set of original electromagnetic monitoring data is obtained at 8:00 in the morning, a set of original electromagnetic monitoring data is obtained at 12:00 noon, and a set of original electromagnetic monitoring data is obtained at 18:00 in the afternoon. In some embodiments, the preset time points of the original electromagnetic monitoring data are the same as the preset time points of the human activity information in the mining area and the preset time points of the power equipment operation information.

[0045] Step 220: Based on the human activity information at multiple preset time points, the power equipment operation information at multiple preset time points, and multiple sets of original electromagnetic monitoring data, determine at least one set of electromagnetic monitoring spectra.

[0046] The electromagnetic monitoring spectrum refers to the electromagnetic spectrum obtained after denoising the original electromagnetic monitoring data.

[0047] In some embodiments, the processor can obtain the electromagnetic monitoring spectrum in various ways. For example, the processor can determine the possible non-related electromagnetic signals through a preset table according to the known human activity information at multiple preset time points and the power equipment operation information at multiple preset time points. The preset table is constructed based on the corresponding relationship between historical human activity information, historical power equipment operation information, and the subsequently monitored non-related electromagnetic signals. Among them, the non-related electromagnetic signals refer to the noise, interference, or other noises that are irrelevant or not related to the underground structure of the mine in electromagnetic monitoring. These non-related electromagnetic signals may come from various sources, such as human activity interference, power equipment influence, natural electromagnetic radiation, etc. The non-related signals will affect the quality and interpretation of the electromagnetic monitoring data, reducing the accuracy and reliability of the exploration results.

[0048] In some embodiments, the processor can denoise multiple sets of original electromagnetic monitoring data according to the types of non-related electromagnetic signals and then convert them to obtain the electromagnetic monitoring spectrum. For example, for the non-related electromagnetic signals caused by human activity interference, the influence of human interference can be reduced or eliminated through shielding facilities or interference elimination technologies. For the non-related electromagnetic signals caused by the operation of power equipment, the original electromagnetic monitoring data can be denoised by mathematical calculation methods such as wavelet transform, wavelet packet transform, multi-scale analysis, etc.

[0049] For more ways to determine the electromagnetic monitoring spectrum, please refer to Figure 3 and its related descriptions.

[0050] Step 230: Based on at least one set of electromagnetic monitoring spectra, determine at least one set of mine geological assessment information.

[0051] The mine geological assessment information refers to the geological and resource information of the mine obtained by analyzing and evaluating the mine geological conditions, vein distribution, resource reserves, etc.

[0052] In some embodiments, the processor may determine at least one set of mine geological assessment information based on at least one set of electromagnetic monitoring spectra through magnetotelluric inversion technology. In some embodiments, the electromagnetic monitoring spectra correspond to the mine geological assessment information, that is, the processor determines one set of mine geological assessment information corresponding to one set of electromagnetic monitoring spectra.

[0053] Magnetotelluric inversion technology is a technique for underground exploration using electromagnetic phenomena. By using the response characteristics of underground media to electromagnetic fields for inversion, information about the underground structure can be obtained, including parameters such as underground resistivity, conductivity, and magnetic susceptibility. By analyzing the distribution and changes of these parameters, the distribution of underground rock formations, ore bodies, mineralized zones and other targets can be revealed.

[0054] Step 240, based on the historical geological data of the mine area, the human activity information at multiple preset time points, and the operation information of power equipment at multiple preset time points, determine the mine geological inference result from at least one set of mine geological assessment information.

[0055] The mine geological inference result refers to the result obtained by analyzing and evaluating the mine geological conditions, vein distribution, resource reserves, etc. For example, the trend of deep underground veins, the distribution of veins, etc. Another example is the composition of the real strata, the distribution of rock layer thickness, etc.

[0056] In some embodiments, the processor may feedback at least one set of mine geological assessment information, historical geological data, human activity information at multiple preset time points, and operation information of power equipment at multiple preset time points to the user through an interaction device, and the user can select one set of mine geological assessment information and determine it as the mine geological inference result. For more ways to determine the mine geological inference result, see the following and its related descriptions.

[0057] In some embodiments of this specification, by obtaining multiple sets of original electromagnetic monitoring data through a magnetotelluric detection device, denoising the original electromagnetic monitoring data, and then determining the mine geological inference result, the noise generated by human activities and power equipment on the electromagnetic monitoring data can be effectively removed, the quality of the electromagnetic monitoring data can be improved, and thus the accuracy of the mine geological inference result can be improved.

[0058] In some embodiments, the processor may determine at least one set of electromagnetic monitoring spectra based on the human activity information at multiple preset time points, the operation information of power equipment at multiple preset time points, and multiple sets of original electromagnetic monitoring data through an electromagnetic monitoring spectrum determination model. For more descriptions and acquisition methods of human activity information, power equipment operation information, and original electromagnetic monitoring data, see Figure 2 the relevant descriptions.

[0059] The electromagnetic monitoring spectrum determination model refers to a model for denoising the original electromagnetic monitoring data. In some embodiments, the electromagnetic monitoring spectrum determination model can be a machine learning model. For example, the electromagnetic monitoring spectrum determination model can include Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), etc., or any combination thereof, which can be multiple models.

[0060] In some embodiments, the input of the electromagnetic monitoring spectrum determination model includes the human activity information, power equipment operation information, and the original electromagnetic monitoring data corresponding to at least one of multiple preset time points, and the output of the electromagnetic monitoring spectrum determination model includes the electromagnetic monitoring spectrum.

[0061] In some embodiments, the preset time points corresponding to the human activity information, power equipment operation information, and the original electromagnetic monitoring data in the input of the electromagnetic monitoring spectrum determination model are the same.

[0062] In some embodiments, the input of the electromagnetic monitoring determination model can be the human activity information, power equipment operation information, and the original electromagnetic monitoring data at a certain preset time point, and the output of the electromagnetic monitoring determination model can be 1 electromagnetic monitoring spectrum. By inputting into the electromagnetic monitoring determination model multiple times, multiple electromagnetic monitoring spectra can be output respectively.

[0063] In some embodiments, the electromagnetic monitoring spectrum determination model can be obtained by training based on a large number of first training samples with first labels through various feasible methods. Exemplarily, the training process can include: training based on the gradient descent method. For example, inputting multiple first training samples with first labels into the electromagnetic monitoring spectrum determination model, constructing a loss function through the first labels and the results of the electromagnetic monitoring spectrum determination model, and iteratively updating the parameters of the electromagnetic monitoring spectrum determination model based on the loss function. When the loss function of the electromagnetic monitoring spectrum determination model meets the preset conditions, the model training is completed, and the trained electromagnetic monitoring spectrum determination model is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0064] In some embodiments, the first training samples can include the human activity information, power equipment operation information, and multiple groups of original electromagnetic monitoring data at multiple preset time points in the historical data. In some embodiments, after denoising multiple groups of actually detected original electromagnetic monitoring data through various feasible methods, multiple electromagnetic maps are formed, and based on the multiple electromagnetic maps, corresponding mine geological inference results are obtained. The electromagnetic map corresponding to the mine geological inference result that is more consistent with the subsequent actual exploration result is used as the first label.

[0065] Figure 3It is a schematic diagram of an electromagnetic monitoring spectrum determination model shown in some embodiments of this specification.

[0066] In some embodiments, as Figure 3 shown, the electromagnetic monitoring spectrum determination model may include a non-electromagnetic signal determination layer 310 and an electromagnetic spectrum determination layer 320.

[0067] In some embodiments, the input of the non-electromagnetic signal determination layer 310 includes human activity information 311 and power equipment operation information 312, and the output includes non-related electromagnetic signal characteristics 313. In some embodiments, the non-electromagnetic signal determination layer 310 may be a deep neural network model.

[0068] In some embodiments, the processor may obtain at least one preset time point among multiple preset time points, the corresponding human activity information and power equipment operation information. Among them, the preset time points of the obtained human activity information and power equipment operation information are the same. By way of example, for a certain preset time point, at this time point, the processor can obtain human activity information and power equipment operation information.

[0069] The non-related electromagnetic signal characteristics refer to the characteristics of some electromagnetic signals that are not related to telluric magnetism. For example, the characteristics of electromagnetic signals generated by mechanical equipment or communication equipment. In some embodiments, the non-related electromagnetic signal characteristics include the distance between the generation source and the monitoring point, the signal intensity, and the time of interference.

[0070] The generation source refers to the location of the source of the electromagnetic signal. For example, the location of a certain mechanical equipment that generates an electromagnetic signal, the location of a certain communication device that conducts communication, etc. The monitoring point refers to the location where the telluric magnetism monitoring device obtains electromagnetic signals. The time of interference refers to the time corresponding to the generation of non-related electromagnetic signals.

[0071] In some embodiments, the input of the electromagnetic spectrum determination layer 320 includes non-related electromagnetic signal characteristics 313 and original electromagnetic monitoring data 321, and the output includes an electromagnetic monitoring spectrum 322. In some embodiments, the electromagnetic spectrum determination layer 320 may be a convolutional neural network model.

[0072] In some embodiments, the original electromagnetic monitoring data 321 is the original electromagnetic monitoring data corresponding to the same preset time point as the human activity information and power equipment operation information input to the non-electromagnetic signal determination layer. After inputting the original electromagnetic monitoring data corresponding to this preset time point and the non-related electromagnetic signal characteristics output by the non-electromagnetic signal determination layer to the electromagnetic spectrum determination layer, the electromagnetic spectrum determination layer outputs an electromagnetic monitoring spectrum.

[0073] In some embodiments, the non - electromagnetic signal determination layer can be obtained through separate training based on a large number of second training samples with second tags in various feasible ways. Exemplarily, the separate training process can include: training based on the gradient descent method. Only as an example, multiple second training samples with second tags can be input into the non - electromagnetic signal determination layer, a loss function can be constructed through the second tags and the results of the non - electromagnetic signal determination layer, and the parameters of the non - electromagnetic signal determination layer can be iteratively updated based on the loss function. When the loss function of the non - electromagnetic signal determination layer meets the preset conditions, the model training is completed, and the trained non - electromagnetic signal determination layer is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0074] In some embodiments, the second training samples can include human activity information and power equipment operation information at multiple preset time points in historical data, and the second tags can include non - relevant electromagnetic signal characteristics actually detected subsequently corresponding to the second training samples. In some embodiments, the non - relevant electromagnetic signal characteristics can be separately extracted as the second tags by filtering the electromagnetic signals generated by human activity information and power equipment operation information.

[0075] In some embodiments, the electromagnetic map determination layer can also be obtained through separate training based on a large number of third training samples with third tags in a training manner similar to that of the non - electromagnetic signal determination layer.

[0076] In some embodiments, the third training samples can include historical non - relevant electromagnetic signal characteristics and historical original electromagnetic monitoring data at multiple preset time points in historical data. The third training label can be an electromagnetic map that conforms to the subsequent actual exploration results corresponding to the third training samples.

[0077] In some embodiments, the processor performs denoising on the historical original electromagnetic monitoring data in various ways (for example, Fourier transform) to obtain multiple electromagnetic maps, then obtains the corresponding mine geological inference results according to the electromagnetic maps, and uses the electromagnetic map corresponding to the mine geological inference result that is more in line with the subsequent actual exploration results as the third tag. For more descriptions and acquisition methods of the mine geological inference results, reference can be made to Figure 2 the relevant descriptions.

[0078] In some embodiments of this specification, through the non - electromagnetic signal determination layer and the electromagnetic map determination layer of the trained electromagnetic monitoring spectrum determination model, based on human activity information, power equipment operation information, and original electromagnetic monitoring data for processing, the electromagnetic monitoring spectrum can be quickly determined, and by constructing the results output by the model, the influence of mine human activities and mechanical and electrical facilities can be effectively excluded.

[0079] In some embodiments, step 240 includes the following steps. In some embodiments, step 240 can be executed by the processor.

[0080] Step 241: Based on at least one set of mine geological assessment information, determine the similar features and different features of the corresponding mine area.

[0081] The similar features refer to the similarities among multiple sets of mine geological assessment information. For example, the similarity of geological structures, the consistency of mineral compositions, or the commonality of landforms. In some embodiments, the similar features include similar areas and similarity degrees.

[0082] The different features refer to the differences among multiple sets of mine geological assessment information. For example, the differences in geological structures, the diversity of mineral compositions, or the inconsistencies of landforms. In some embodiments, the different features include different areas and difference degrees.

[0083] In some embodiments, the similar features and different features can be determined in various ways based on multiple assessment data in the mine geological assessment information. In some embodiments, the processor can compare the multiple assessment data of each set of mine geological assessment information. If the similarity between two or more pieces of assessment data is less than the assessment threshold, the corresponding assessment data is determined as a different item, the area corresponding to the different item is determined as a different area, and the reciprocal of the similarity is determined as the difference degree.

[0084] In some embodiments, if the similarity between two or more pieces of assessment data is greater than or equal to the assessment threshold, the corresponding assessment data is determined as a similar item, and the area corresponding to the similar item is determined as a similar area. For example, among the 4 sets of assessment data regarding area A in the mine geological assessment information, the similarity between 3 sets of assessment data is greater than the assessment threshold, and the similarity between 1 set of assessment data and the other three sets of assessment data is less than the assessment threshold. Then, these 3 sets of assessment data are similar items, the similar area of these 3 sets of assessment data is area A, this 1 set of assessment data and these 3 sets of assessment data are different items, and the different area of this 1 set of assessment data is area A.

[0085] In some embodiments, if the data categories of two or more pieces of assessment data are different (for example, the data category of one piece of assessment data is height, and the data category of another piece of assessment data is mineral composition), the two pieces of assessment data can be directly determined as different items.

[0086] In some embodiments, the processor can determine the similar features and different features based on the historical geological data of the mine area, the human activity information at multiple preset time points, the operation information of power equipment at multiple preset time points, and at least one set of mine geological assessment information.

[0087] In some embodiments, the processor may determine similar features and different features through a clustering algorithm based on historical geological data of a mine area, human activity information at multiple preset time points, power equipment operation information at multiple preset time points, and at least one set of mine geological assessment information.

[0088] Figure 4 It is a schematic diagram of mine geological assessment information shown according to some embodiments of this specification.

[0089] In some embodiments, the clustering algorithm may include, but is not limited to, K-Means clustering and / or density-based clustering methods (such as DBSCAN), etc. In some embodiments, determining similar features and different features includes the following steps:

[0090] Step 2411, draw an image based on the mine geological assessment information, perform grid processing on the image to obtain a number of unit information regions, such as Figure 4 shown.

[0091] The image drawing can be performed based on existing image drawing techniques. For example, remote sensing image analysis or a detailed geological map generated based on GIS (Geographic Information System) technology can be used. The unit information region refers to the smallest unit region divided for obtaining information. For example, the size of the unit information region can be 1m * 1m. In some embodiments, the unit information region includes the mine geological assessment information of each region.

[0092] In some embodiments, the grid processing can be performed based on a preset region size. For example, divide the image according to the preset region size, and each cell after division is the unit information region.

[0093] Step 2412, determine a preset number of sub-regions based on a number of unit information regions.

[0094] In some embodiments, the processor may respectively construct a clustering feature vector based on each unit information region; perform clustering on multiple clustering feature vectors to obtain a preset number of clustering feature vector aggregation regions, and each clustering feature vector aggregation region is used as a sub-region.

[0095] In some embodiments, the clustering vector may be determined based on the mine geological assessment information within each unit information region.

[0096] In some embodiments, the processor may determine the clustering vector of each unit information area based on the content included in the mine geological assessment information. For example, the mine geological assessment information includes riverbed morphology, landslide thickness, aquifer thickness, and rock mass quality, and the corresponding clustering vector of each unit information area includes the riverbed morphology within the unit information area, the landslide thickness within the unit information area, the aquifer thickness within the unit information area, and the rock mass quality within the unit information area.

[0097] In some embodiments, the content included in the mine geological assessment information may be determined based on the purpose of speculating on the mine geological conditions. For example, when the purpose is to speculate on the existence of underground water sources, it is necessary to speculate on the content related to water sources. Therefore, the mine geological assessment information includes the thickness of the underground aquifer, riverbed morphology, etc.

[0098] In some embodiments, the preset quantity may be determined based on the amount of information in the mine geological assessment information. The amount of information in the mine geological assessment information refers to the number of assessment data items included in the mine geological assessment information.

[0099] In some embodiments, when the amount of information in the mine geological assessment information is less than the preset value, it indicates that the geological composition of the area is relatively simple, and the preset quantity can be set lower. For example, the amount of information in the mine geological assessment information includes riverbed morphology and landslide thickness, and the total number of items of these two types of assessment data is 5. At this time, it can be determined that the amount of information in the mine geological assessment information is 5 items.

[0100] In some embodiments, the preset quantity may also be determined based on a preset quantity comparison table. The preset quantity comparison table may include the correspondence between the amount of information in the mine geological assessment information and the preset quantity. In some embodiments, the preset quantity comparison table may be constructed based on historical experience.

[0101] In some embodiments, the preset quantity comparison table may be constructed by comparing the clustering results of different preset quantities. For example, when the amount of assessment information is 5 items, clustering is performed with preset quantities of 2, 3, and 4 respectively. If the sub-region similarities of the clustering results of the three preset quantities are very high, it indicates that the preset quantity for clustering can be set to 2 categories. If the sub-region differences between the clustering results with preset quantity of 2 and preset quantity of 3 are very high, then the preset quantity should be set to at least 3. For the description of sub-region similarity and sub-region difference, refer to the following text.

[0102] Step 2413: Cluster each piece of mine geological assessment information based on the above Steps 2411 and 2412, and compare the sub-regions after clustering of multiple pieces of mine geological assessment information to determine the similar features and different features.

[0103] In some embodiments, the processor may construct sub-region feature vectors based on sub-region features, and thereby calculate the vector similarity of different sub-region feature vectors. Exemplary sub-region features include the range of position longitude and latitude, the type to which the sub-region belongs (such as the type of underground riverbed), etc. The processor may determine the sub-regions corresponding to the vector similarity between sub-regions being higher than the sub-region similarity threshold as similar sub-regions, determine the vector similarity between sub-regions as the sub-region similarity, and use the similar sub-regions and the sub-region similarity as similar features. Similarly, the processor may determine the sub-regions corresponding to the vector similarity between sub-regions being lower than the sub-region similarity threshold as different sub-regions with characteristic differences, determine the reciprocal of the sub-region similarity as the sub-region difference degree, and use the different sub-regions and the sub-region difference degree as difference features.

[0104] For example, a number of unit information regions formed by gridifying the mine geological assessment information A are clustered to form 1 first sub-region a, and a number of unit information regions formed by gridifying the mine geological assessment information B are clustered to form 1 first sub-region b. If the vector similarity between the first sub-region a and the first sub-region b is higher than the sub-region similarity threshold, then the first sub-region a and the first sub-region b are similar sub-regions, and the vector similarity is the sub-region similarity.

[0105] In some embodiments, the sub-region features may only include the region range. The processor can determine the similar features and the different features by comparing the positions of different sub-regions on the map and the region range. For example, the processor may evaluate the positions of different sub-regions on the map and the region range to obtain a similarity degree value. If the similarity degree value is greater than or equal to the preset range threshold, the corresponding sub-region is a similar sub-region, and the similarity degree value is the sub-region similarity; if the similarity degree value is less than the preset range threshold, the corresponding sub-region is a different sub-region, and the reciprocal of the similarity degree value is the sub-region similarity.

[0106] In some embodiments of this specification, through the clustering algorithm, it is possible to determine its similar regions, different regions, and the difference degree according to the mine geological assessment information, which is beneficial to more accurately and effectively evaluating the subsequent mine geological inference results.

[0107] Step 242: Determine the mine geological inference result based on the historical geological data of the mine area, the human activity information at multiple preset time points, the power equipment operation information at multiple preset time points, at least one set of mine geological assessment information, and its corresponding similar features and different features.

[0108] In some embodiments, the mine geological assessment information with the most similar regions and the smallest total difference degree of all different regions may be used as the mine geological inference result.

[0109] In some embodiments, the processor may determine the inference reliability based on non-correlated electromagnetic signal features, historical geological data, human activity information at multiple preset time points, power equipment operation information at multiple preset time points, at least one set of mine geological assessment information, and the similarity features and difference features of its area, and determine the mine geological inference result based on the inference reliability through an inference reliability determination model.

[0110] Figure 5 It is a schematic structural diagram of the inference reliability model shown in some embodiments of this specification.

[0111] The inference reliability model 500 refers to a model used to determine whether the inference result of the mine geological assessment information is reliable. In some embodiments, the inference reliability model 500 may be a machine learning model, such as a deep neural network model. As Figure 5 shown, the inputs of the inference reliability model 500 may include non-correlated electromagnetic signal features 501, historical geological data 502, human activity information 503 at multiple preset time points, power equipment operation information 504 at multiple preset time points, mine geological assessment information 505, and the similarity features 506 and difference features 507 of the area corresponding to the mine geological assessment information, and the output may include the inference reliability 508 corresponding to the mine geological assessment information 505.

[0112] In some embodiments, the non-correlated electromagnetic signal features may be obtained by inputting the human activity information and the power equipment operation information into the non-electromagnetic signal determination layer. For more descriptions and acquisition methods of the non-correlated electromagnetic signal features, historical geological data, human activity information, power equipment operation information, mine geological assessment information, similarity features, and difference features, please refer to the relevant content Figures 2-4 above.

[0113] In some embodiments, the processor may train through various methods based on the fourth sample with the fourth training label to obtain a trained inference reliability model. For example, training may be performed based on the gradient descent method. Only as an example, multiple fourth samples with the fourth training label may be input into the initial inference reliability model, a loss function may be constructed based on the fourth training label and the result of the initial inference reliability model, and the parameters of the initial inference reliability model may be iteratively updated based on the loss function. When the loss function of the initial inference reliability model meets the preset conditions, the model training is completed, and a trained inference reliability model is obtained. Among them, the preset conditions may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0114] In some embodiments, the fourth sample may include historical non - relevant electromagnetic signal characteristics, historical geological data, historical human activity information at multiple historical time points, historical power equipment operation information at multiple historical time points, at least one set of historical mine geological assessment information, and historical similarity characteristics and historical difference characteristics of the area corresponding to the historical mine geological assessment information. The fourth training label may be the historical inference reliability corresponding to the fourth sample.

[0115] In some embodiments, the similarity between the geological exploration results of the area actually explored subsequently under the condition of the fourth sample and the mine geological assessment information may be used as the historical inference reliability.

[0116] In some embodiments, the higher the inference reliability, the higher the reliability of the inference. After determining the inference reliability through the inference reliability determination model, a set of mine geological assessment information corresponding to the highest inference reliability can be selected as the geological inference result.

[0117] In some embodiments of this specification, by using the inference reliability model to determine the inference reliabilities corresponding to multiple sets of mine geological assessment information respectively, the mine geological assessment information with the highest reliability and most in line with the actual situation can be obtained, ensuring the accuracy and effectiveness of the data.

[0118] Some embodiments of this specification provide a computer - readable storage medium storing computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the magnetotelluric sounding assessment method in any one of the embodiments of this specification.

[0119] The basic concepts have been described above. Obviously, for those skilled in the art, the above - mentioned detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0120] Meanwhile, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification is not necessarily the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be combined appropriately.

[0121] Similarly, it should be noted that, in order to simplify the presentation disclosed in this specification and thus assist in the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, sometimes multiple features are incorporated into one embodiment, drawing, or description thereof. However, this method of disclosure does not mean that the features required for the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0122] Except for application history documents that are inconsistent with or conflict with the content of this specification, and also except for documents that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0123] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered to be consistent with the teachings of this specification. The embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A magnetotelluric sounding evaluation method, characterized in that The method is executed based on a processor of a magnetotelluric sounding evaluation system, and includes: Based on an interaction device of the magnetotelluric sounding evaluation system, obtaining historical geological data of a mining area, human activity information and power equipment operation information at multiple preset time points; and based on a magnetotelluric detection device of the magnetotelluric sounding evaluation system, obtaining multiple sets of original electromagnetic monitoring data; Based on the human activity information and the power equipment operation information at the multiple preset time points, and the multiple sets of original electromagnetic monitoring data, determining at least one set of electromagnetic monitoring spectra; Based on the at least one set of electromagnetic monitoring spectra, determining at least one set of mining geological evaluation information; Based on the at least one set of mining geological evaluation information, determining corresponding similar features and different features of the mining area, where the similar features include similar areas and similarity degrees, and the different features include different areas and difference degrees; Based on the historical geological data of the mining area, the human activity information and the power equipment operation information at the multiple preset time points, the at least one set of mining geological evaluation information, and the corresponding similar features and different features, determining a mining geological inference result, including: Based on non-related electromagnetic signal features, the historical geological data, the human activity information and the power equipment operation information at the multiple preset time points, the at least one set of mining geological evaluation information, and the corresponding similar features and different features, determining an inference reliability through an inference reliability model, and determining the mining geological inference result based on the inference reliability; The non-related electromagnetic signal features are determined based on the human activity information and the power equipment operation information at the multiple preset time points, and include the distance between the electromagnetic signal generation source and the monitoring point, the signal intensity, and the time of interference occurrence.

2. The method according to claim 1, characterized in that The determining of at least one set of electromagnetic monitoring spectra based on the human activity information and the power equipment operation information at the multiple preset time points, and the multiple sets of original electromagnetic monitoring data, includes: Based on the human activity information and the power equipment operation information at the multiple preset time points, and the multiple sets of original electromagnetic monitoring data, determining the at least one set of electromagnetic monitoring spectra through an electromagnetic monitoring spectrum determination model; the electromagnetic monitoring spectrum determination model is a machine learning model.

3. The method according to claim 1, characterized in that, The method further includes: determining the similar features and the different features based on the historical geological data of the mining area, the human activity information and the power equipment operation information at the multiple preset time points, and the at least one set of mining geological evaluation information.

4. A magnetotelluric sounding evaluation system, characterized in that, Including a magnetotelluric detection device, an interaction device and a processor; The magnetotelluric detection device is configured to obtain multiple sets of original electromagnetic monitoring data; the multiple sets of original electromagnetic monitoring data are electromagnetic monitoring data at multiple preset time points; The interaction device is configured to: obtain historical geological data of a mining area, human activity information and power equipment operation information at multiple preset time points; the human activity information includes activity intensity; the power equipment operation information includes power equipment opening and closing changes; The processor is configured to determine the mine geological inference result, including: Based on the interaction device of the magnetotelluric exploration evaluation system, obtaining the historical geological data of the mine area, the human activity information at the plurality of preset time points, and the power equipment operation information; and based on the magnetotelluric detection device of the magnetotelluric exploration evaluation system, obtaining the multiple sets of original electromagnetic monitoring data; Based on the human activity information and the power equipment operation information at the plurality of preset time points, and the multiple sets of original electromagnetic monitoring data, determining at least one set of electromagnetic monitoring spectra; Based on the at least one set of electromagnetic monitoring spectra, determining at least one set of mine geological evaluation information; Based on the at least one set of mine geological evaluation information, determining the similarity features and difference features of the corresponding mine area, where the similarity features include the similar area and similarity, and the difference features include the difference area and difference degree; Based on the historical geological data of the mine area, the human activity information and the power equipment operation information at the plurality of preset time points, the at least one set of mine geological evaluation information, and the corresponding similarity features and difference features, determining the mine geological inference result, including: Based on the non-related electromagnetic signal features, the historical geological data, the human activity information and the power equipment operation information at the plurality of preset time points, the at least one set of mine geological evaluation information, and the corresponding similarity features and difference features, determining the inference reliability through an inference reliability model, and determining the mine geological inference result based on the inference reliability; The non-related electromagnetic signal features are determined based on the human activity information and the power equipment operation information at the plurality of preset time points, and include the distance between the electromagnetic signal generation source and the monitoring point, the signal intensity, and the time of interference occurrence.

5. The system according to claim 4, wherein The processor is further configured to: Based on the human activity information and the power equipment operation information at the plurality of preset time points, and the multiple sets of original electromagnetic monitoring data, determining the at least one set of electromagnetic monitoring spectra through an electromagnetic monitoring spectrum determination model; the electromagnetic monitoring spectrum determination model is a machine learning model.

6. The system according to claim 4, wherein The processor is further configured to: Based on the historical geological data of the mine area, the human activity information and the power equipment operation information at the plurality of preset time points, and the at least one set of mine geological evaluation information, determining the similarity features and the difference features.

7. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1-3.

Images