An intelligent data acquisition method and system for geophysical exploration

Abstract

The present application relates to the field of data acquisition technology, and specifically discloses an intelligent data acquisition method and system for geophysical exploration, which utilizes a seismic detector to collect seismic wave detection electrical signals of multiple data acquisition points in a target exploration area, performs signal noise reduction processing on the seismic wave detection electrical signals of each acquisition point, and further introduces data processing technology based on depth information to perform waveform semantic feature extraction and global correlation analysis on each seismic wave detection electrical signal, so as to utilize the global waveform oscillation mode of the seismic wave detection electrical signal to reveal potential oil and gas reservoir information, and intelligently decode the location of the oil and gas reservoir. In this way, the automatic and intelligent identification of the location of the oil and gas reservoir can be realized, and the accuracy and efficiency of geophysical exploration can be improved.

Description

Technical Field

[0001] The present application relates to the field of data acquisition technology, and more specifically, to an intelligent data acquisition method and system for geophysical exploration. Background Art

[0002] Geophysical exploration is a key link in the exploration and development of oil and gas resources. It infers underground structure and composition by measuring geophysical fields (such as gravity, magnetism, conductivity or seismic waves), and indirectly detects underground geological structures and oil and gas reservoir distribution. Among them, seismic exploration has become one of the most commonly used methods in the oil and gas industry due to its high resolution and sensitivity to deep geological structures.

[0003] The basic principle of seismic exploration is to artificially stimulate seismic waves (such as using explosives or controlled vibrators to generate vibrations). When these seismic waves propagate in the underground medium, they will encounter interfaces of different lithologies, resulting in reflection, refraction and other phenomena. The reflected waves carry the structural information of the underground medium back to the ground, and are received by seismic detectors arranged on the surface or in the well and converted into electrical signals for recording. By analyzing the seismic wave signals returned to the surface, the distribution and properties of the underground rock formations can be inferred.

[0004] However, in traditional seismic exploration methods, the location and distribution of oil and gas reservoirs are mainly identified by manually interpreting seismic wave signals. This method is highly dependent on the experience and skills of technicians, and the processing is cumbersome, time-consuming, and easily affected by subjective factors, resulting in uncertainty and inconsistency in the interpretation results.

[0005] Therefore, an intelligent data collection method and system for intelligent geophysical exploration is expected. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an intelligent data acquisition method and system for geophysical exploration, which uses a seismic detector to collect seismic wave detection electrical signals from multiple data collection points in the target exploration area, and after performing signal noise reduction processing on the seismic wave detection electrical signals of each collection point, further introduces data processing technology based on depth information to perform waveform semantic feature extraction and global correlation analysis on each seismic wave detection electrical signal, so as to use the global waveform oscillation mode of the seismic wave detection electrical signal to reveal potential oil and gas reservoir information, and intelligently decode the location of the oil and gas reservoir. In this way, the automatic and intelligent identification of the location of the oil and gas reservoir can be achieved, and the accuracy and efficiency of geophysical exploration can be improved.

[0007] According to one aspect of the present application, there is provided an intelligent data acquisition method for geophysical exploration, which comprises:

[0008] Set up multiple data collection points in the target exploration area;

[0009] Using seismic wave detection electrical signals collected by seismic detectors deployed at each data collection point to obtain a set of seismic wave detection electrical signals;

[0010] Extracting waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors;

[0011] Performing adaptive feature compensation aggregation coding on the set of the seismic wave detection electric signal waveform semantic coding feature vectors to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector;

[0012] The location of the oil and gas reservoir is determined based on the semantic aggregation coding vector of the seismic wave detection electrical signal waveform.

[0013] According to another aspect of the present application, there is provided an intelligent data acquisition system for geophysical exploration, comprising:

[0014] A data collection point deployment module is used to set up multiple data collection points in the target exploration area;

[0015] A seismic wave signal acquisition module, used to obtain a set of seismic wave detection electrical signals by using seismic wave detection electrical signals acquired by seismic detectors deployed at each data acquisition point;

[0016] A waveform feature extraction module, used to extract the waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors;

[0017] A feature compensation aggregation coding module, used for performing adaptive feature compensation aggregation coding on the set of the seismic wave detection electric signal waveform semantic coding feature vectors to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector;

[0018] The oil and gas reservoir positioning module is used to determine the oil and gas reservoir position based on the semantic aggregation coding vector of the seismic wave detection electrical signal waveform.

[0019] Compared with the prior art, the intelligent data acquisition method and system for geophysical exploration provided by the present application utilizes seismic detectors to collect seismic wave detection electrical signals from multiple data acquisition points in the target exploration area, performs signal noise reduction processing on the seismic wave detection electrical signals at each acquisition point, and further introduces data processing technology based on depth information to perform waveform semantic feature extraction and global correlation analysis on each seismic wave detection electrical signal, so as to utilize the global waveform oscillation mode of the seismic wave detection electrical signal to reveal potential oil and gas reservoir information, and intelligently decode the location of the oil and gas reservoir. In this way, the automatic and intelligent identification of the location of the oil and gas reservoir can be realized, and the accuracy and efficiency of geophysical exploration can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0021] Figure 1 The present invention is a flowchart of an intelligent data collection method for geophysical exploration according to an embodiment of the present application.

[0022] Figure 2 Schematic diagram of data flow of an intelligent data collection method for geophysical exploration according to an embodiment of the present application.

[0023] Figure 3 This is a flowchart of sub-step S3 of the intelligent data acquisition method for geophysical exploration according to an embodiment of the present application.

[0024] Figure 4 This is a flowchart of sub-step S4 of the intelligent data acquisition method for geophysical exploration according to an embodiment of the present application.

[0025] Figure 5 This is a flowchart of sub-step S42 of the intelligent data acquisition method for geophysical exploration according to an embodiment of the present application.

[0026] Figure 6 It is a block diagram of an intelligent data acquisition system for geophysical exploration according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0028] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0029] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0030] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0031] It is worth noting that in this application, all actions to obtain data are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0032] In response to the technical problems described in the above background technology, this application proposes an intelligent data acquisition method for geophysical exploration, which uses seismic detectors to collect seismic wave detection electrical signals from multiple data acquisition points in the target exploration area, and after performing signal noise reduction processing on the seismic wave detection electrical signals at each acquisition point, further introduces data processing technology based on depth information to perform waveform semantic feature extraction and global correlation analysis on each seismic wave detection electrical signal, so as to use the global waveform oscillation mode of the seismic wave detection electrical signal to reveal potential oil and gas reservoir information and intelligently decode the location of the oil and gas reservoir. In this way, the automatic and intelligent identification of the location of the oil and gas reservoir can be achieved, and the accuracy and efficiency of geophysical exploration can be improved.

[0033] Figure 1 The present invention is a flowchart of an intelligent data collection method for geophysical exploration according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the intelligent data collection method for geophysical exploration according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the intelligent data collection method for geophysical exploration includes the following steps: S1, setting a plurality of data collection points in the target exploration area; S2, using the seismic wave detection electrical signals collected by the seismic detectors deployed at the respective data collection points to obtain a set of seismic wave detection electrical signals; S3, extracting the waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors; S4, performing adaptive feature compensation aggregation coding on the set of seismic wave detection electrical signal waveform semantic coding feature vectors to obtain a seismic wave detection electrical signal waveform semantic aggregation coding vector; S5, determining the location of the oil and gas reservoir based on the seismic wave detection electrical signal waveform semantic aggregation coding vector.

[0034] In the above-mentioned intelligent data collection method for geophysical exploration, the step S1 sets multiple data collection points in the target exploration area. It should be understood that due to the complexity and diversity of the underground geological structure, the information captured by a single data collection point can only reflect the geological characteristics of a very limited area near the point, and cannot fully display the geological picture of the entire target exploration area. Therefore, the present application reasonably distributes multiple data collection points in the target exploration area to collect underground geological information from different locations, such as the thickness of the geological layer, the nature of the rock, and possible oil and gas reservoirs, so as to more comprehensively understand the changes of seismic waves on different paths, thereby providing a comprehensive and sufficient data basis for subsequent geological structure inference, thereby improving the accuracy of the judgment of the location of potential oil and gas reservoirs.

[0035] Specifically, in order to ensure the effectiveness and accuracy of seismic wave detection signals, the selection and layout of data collection points are crucial. After selecting the target exploration area, the potential oil and gas reservoir locations and possible geological structural features were determined through preliminary geological surveys and historical data analysis. Based on this information, the team will use advanced computer simulation technology to construct an underground three-dimensional geological model, which not only helps to understand the complexity of the underground structure, but also provides a scientific basis for the subsequent layout of data collection points. On this basis, we began to consider how to distribute the data collection points. Reasonable layout can not only improve the accuracy of underground structure analysis, but also optimize resource allocation and reduce unnecessary cost expenditures, while taking into account the need for more in-depth exploration that may be carried out in the future.

[0036] When selecting specific collection point locations, topographic factors must be taken into account, and a grid or linear arrangement is usually used. The grid spacing is designed based on the desired exploration depth and the expected size of the geological body; for deep or subtle structures, smaller grid spacing can provide more detailed images, while larger spacing is suitable for preliminary surveys of shallow large areas. In some special cases, such as places where complex geological structures or important geological interfaces are known, the grid may be encrypted or the shape of the grid may be adjusted to enhance the data density of a specific area. This flexible design method can enrich the seismic wave reflection signal, thereby improving the quality of underground structure imaging. Flat and open areas are conducive to equipment installation and operation, and are also convenient for later maintenance. However, in some cases, such as mountainous or hilly areas, despite the increased difficulty of operation, it is still necessary to set up collection points in these places under certain geological conditions to obtain important information. At this time, engineers will use modern technical means such as drone surveys, satellite images, and LiDAR (laser radar) scanning to assist in site selection, ensuring that suitable locations can be found even in complex natural environments. For example, high-resolution satellite imagery can be used to identify small platforms suitable for establishing collection points, while low-altitude drone flights can provide finer surface details, helping to discover those subtle but critical locations.

[0037] In addition to geographical conditions, attention should also be paid to the influence of underground medium characteristics. Different rock types have different effects on the propagation speed of seismic waves. Therefore, when designing the distribution map of acquisition points, it is necessary to combine the existing geological model to predict which areas may have special rock layers or faults, and adjust the acquisition point density accordingly. For example, the number of acquisition points can be increased in places where high impedance contrast interfaces are expected to be present, so as to better capture the changes in reflection signals and thus improve the imaging quality. In addition, factors such as groundwater flow direction and temperature gradient need to be considered, because these will affect the speed of seismic waves and thus affect the final data interpretation results. In addition, environmental protection is also a factor that cannot be ignored. Before conducting field operations, local laws and regulations must be observed and the potential impact of the activities on the environment must be assessed. Try to avoid damaging vegetation, water sources and other components of the ecosystem. If work is unavoidable in sensitive areas, necessary protective measures must be taken, such as restricting vehicle routes and using environmentally friendly materials to build temporary facilities. In some extreme cases, it may also be necessary to work with local communities to jointly develop environmental protection plans to ensure that exploration activities do not have a negative impact on the living environment of local residents.

[0038] When all preparations are completed, seismic detectors need to be installed at various predetermined locations. Each detector is strictly calibrated to ensure that it can accurately convert weak vibrations received from deep underground into electrical signals. At the same time, a communication network needs to be built to connect various collection points with the central control system to achieve real-time data transmission. For those remote collection points far away from the base station, solar panels or other forms of independent power supply systems may be equipped to ensure long-term stable operation. Considering the uncertainty of the field environment, the selection of equipment should not only consider performance indicators, but also have good durability and reliability to cope with various severe weather conditions and unexpected situations.

[0039] In the above-mentioned intelligent data acquisition method for geophysical exploration, the step S2 uses the seismic wave detection electrical signals collected by the seismic detectors deployed at the various data acquisition points to obtain a collection of seismic wave detection electrical signals. It should be understood that the seismic wave itself is a mechanical wave that is difficult to record and process directly, and the seismic detector can convert the received seismic wave into an electrical signal that is easy to record and process, thereby realizing the collection and preservation of underground seismic wave information. Specifically, the seismic detector mainly works based on the principle of electromagnetic induction. The common moving coil seismic detector consists of an inertial mass block, a coil and a permanent magnet. When the seismic wave propagates to the location of the detector, the ground vibrates, and the inertial mass block of the detector will be displaced relative to the shell due to inertia. This displacement causes the coil to cut the magnetic lines of force in the magnetic field of the permanent magnet. According to the law of electromagnetic induction, an induced electromotive force, i.e., an electrical signal, will be generated in the coil. The characteristics of the electrical signal, such as the amplitude, frequency and phase, are closely related to the vibration characteristics of the seismic wave. For example, the amplitude of the seismic wave determines the speed at which the coil cuts the magnetic field lines, which in turn affects the amplitude of the induced electromotive force; the frequency of the seismic wave determines the frequency of the coil vibration, which makes the generated electrical signal have a corresponding frequency. Therefore, by analyzing the electrical signal collected by the seismic detector, the underground geological information carried by the seismic wave can be indirectly obtained.

[0040] Specifically, in the process of collecting seismic waves to detect electrical signals, the seismic detector, as a key device for receiving seismic waves, must be installed to ensure that the detector can firmly contact the ground or well wall, and minimize the impact of the external environment on signal reception. On land, seismic detectors are generally buried directly in the soil or rock through special fixing devices to ensure that they can remain stable even under external interference such as strong winds or vehicle traffic. In the marine environment, specially designed seabed nodes or towed cable systems are used to place the detectors on the seabed surface or below a certain depth.

[0041] After installation, each seismic detector needs to be calibrated and tested to ensure that all equipment is in optimal working condition. This step is crucial because any slight error may lead to deviations in subsequent data analysis. Technicians will use standardized sound or vibration sources to generate signals of known frequency and amplitude to verify whether the detector can record them accurately. At the same time, they will also check whether there are any faults in the connecting lines and whether the synchronization clock is accurate to ensure that the time tags of all data are consistent, which is convenient for splicing and comparison of multiple data channels during post-processing.

[0042] After the seismic detectors are in place and calibrated, preparations are made to excite seismic waves. This can be achieved in a variety of ways, including but not limited to the use of explosive blasts, heavy hammer strikes, air gun arrays, etc., and the appropriate excitation method needs to be selected based on actual needs. For example, in land exploration, explosive blasts and controllable source vehicles are commonly used; in marine exploration, air gun arrays are more common. Regardless of the method used, the goal is to generate seismic waves of sufficient intensity and with specific spectral characteristics so that these waves can effectively propagate in the underground medium and reflect and refract when encountering interfaces of different lithologies. In order to ensure the safety and effectiveness of the excitation event, each operation will be carefully evaluated and planned, including calculating the required energy level, determining the safe distance, and formulating emergency plans.

[0043] As seismic waves propagate outward, part of the energy is reflected back at the interfaces of various rock layers. These reflected waves carry information about the structure of the underground medium and are captured by pre-arranged seismic detectors when they return to the surface. In order to improve the signal-to-noise ratio, the excitation is often repeated multiple times at the same location, and then the results of multiple recordings are superimposed to enhance the useful signal and weaken the influence of random noise. In addition, considering that seismic waves propagating in different directions may bring different information, some advanced exploration plans will also design multi-directional excitation modes, such as circular arrangements or cross-line layouts, in order to more comprehensively understand the geological conditions in the three-dimensional underground space.

[0044] When the seismic detector receives the returned seismic waves, it performs an analog-to-digital conversion to convert the original analog signal into a data stream in digital format. This process occurs on-site or through wireless transmission to a nearby central processing station. In order to ensure data integrity, the system will also synchronously record timestamps and other auxiliary information, such as geographic location coordinates, environmental parameters, etc., to provide a reference for later data interpretation. Digital signals are not only convenient for subsequent processing and analysis, but also easy to store, manage and remotely monitor. In order to ensure the validity and reliability of the data, technicians will strictly monitor the equipment status, signal quality and acquisition progress on-site, and promptly solve possible problems such as signal loss and noise pollution, so as to ensure the smooth completion of the entire seismic exploration mission.

[0045] During the entire data collection process, all the seismic wave detection electrical signals obtained by the seismic detectors from each data collection point will constitute a huge data set. This set contains key information about the structure and properties of the underground medium, waiting for further processing and analysis. In order to ensure the validity and reliability of the data, technicians will strictly monitor the equipment status, signal quality and collection progress on site, and promptly solve possible problems such as signal loss and noise pollution, so as to ensure the smooth completion of the entire seismic exploration mission.

[0046] In the above-mentioned intelligent data collection method for geophysical exploration, the step S3 extracts the waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors. Figure 3 FIG. 1 is a flow chart of sub-step S3 of the intelligent data collection method for geophysical exploration according to an embodiment of the present application. Figure 3 As shown, the step S3 includes the steps of: S31, performing signal denoising on each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of denoised seismic wave detection electrical signals; S32, using an electrical signal waveform feature extractor based on a one-dimensional convolutional layer to perform waveform feature extraction on each denoised seismic wave detection electrical signal in the set of denoised seismic wave detection electrical signals to obtain a set of waveform semantic coding feature vectors of the seismic wave detection electrical signals.

[0047] Specifically, in a specific example of the present application, the step S31 includes: using a Butterworth filter to filter each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain the set of seismic wave detection electrical signals after noise reduction. Specifically, the present application takes into account that in the actual process of collecting seismic wave detection electrical signals, it may be interfered by various factors such as environmental noise (such as vibration noise generated by wind, water flow, human activities, etc.), instrument noise itself (such as thermal noise of electronic components, noise of amplifiers, etc.) and interference noise in the signal transmission process, thereby reducing the quality and reliability of the electrical signal and affecting the extraction and analysis of useful geological information in the electrical signal. Therefore, in order to improve the quality of the signal and highlight the useful geological information, the present application further performs noise reduction on each seismic wave detection electrical signal collected. In a specific example of the present application, a Butterworth filter is used to filter each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain the set of seismic wave detection electrical signals after noise reduction. It should be understood that the Butterworth filter is a filter with a maximum flat frequency response, which can make the frequency response in the passband as flat as possible, thereby retaining the useful information in the signal as much as possible during the filtering process, while effectively suppressing out-of-band noise. By filtering the seismic wave detection electrical signal with a Butterworth filter, noise interference can be effectively removed, the signal quality can be improved, and a more accurate and reliable data basis can be provided for subsequent signal processing and analysis.

[0048] Specifically, in step S32, the waveform feature extractor of each de-noised seismic wave detection electrical signal in the set of de-noised seismic wave detection electrical signals is used to extract waveform features to obtain a set of semantic encoding feature vectors of the seismic wave detection electrical signal waveforms. It should be understood that due to the interface reflection of different geological layers, the existence of oil and gas reservoirs, etc., specific changes in the seismic wave waveform will be caused. Therefore, the present application further captures the amplitude change mode of each seismic wave detection electrical signal by extracting waveform features of each de-noised seismic wave detection electrical signal to reveal the underground geological structure characteristics. It should be known to those skilled in the art that the one-dimensional convolutional layer has the characteristics of local perception and parameter sharing. It performs convolution operations on each de-noised seismic wave detection electrical signal in a sliding window manner, and can automatically identify and extract waveform features in the electrical signal that are closely related to the underground geological structure, such as sudden changes in amplitude, changes in frequency, etc., to reveal the basic properties of seismic waves, and provide more accurate information basis for subsequent geological structure inference and oil and gas reservoir identification.

[0049] In the above-mentioned intelligent data acquisition method for geophysical exploration, the step S4 performs adaptive feature compensation aggregation coding on the set of semantic coding feature vectors of the seismic wave detection electrical signal waveform to obtain the semantic aggregation coding vector of the seismic wave detection electrical signal waveform. Specifically, in actual geological exploration, the underground geological structure is a continuous and interconnected whole, and there is often an inherent correlation and mutual influence between the seismic wave detection electrical signals at different locations. Therefore, in order to more accurately reveal the overall picture of the underground geological structure, the present application proposes an adaptive feature compensation aggregation coding method, which extracts core hub features and dynamically compensates aggregation coding for each seismic wave detection electrical signal waveform semantic coding feature vector by learning the inherent correlation and mutual influence between different seismic wave detection electrical signals, thereby obtaining an electrical signal feature representation that comprehensively reflects the underground geological structure and oil and gas reservoir information of the entire exploration area, so as to more accurately reflect the actual situation of the underground geological structure. Among them, Figure 4 FIG. 4 is a flow chart of sub-step S4 of the intelligent data collection method for geophysical exploration according to an embodiment of the present application. Figure 4 As shown, the step S4 includes the steps of: S41, inputting the set of semantic coding feature vectors of the seismic wave detection electrical signal waveform into the hub feature extraction network to obtain the seismic wave detection electrical signal waveform semantic hub feature coding vector; S42, based on the seismic wave detection electrical signal waveform semantic hub feature coding vector, performing significant dynamic modulation based on complementary information on each seismic wave detection electrical signal waveform semantic coding feature vector in the set of seismic wave detection electrical signal waveform semantic coding feature vectors to obtain a set of significantly modulated seismic wave detection electrical signal-hub feature complementary information embedded coding vectors; S43, fusing the seismic wave detection electrical signal waveform semantic hub feature coding vector and the set of significantly modulated seismic wave detection electrical signal-hub feature complementary information embedded coding vectors to obtain the seismic wave detection electrical signal waveform semantic aggregation coding vector.

[0050] Specifically, the step S41 is expressed by the formula:

[0051]

[0052] in, represents the hub feature extraction network, represents a set of semantically encoded feature vectors of the seismic wave detection electric signal waveform, , , and respectively represent the first, second, and third in the set of semantic coding feature vectors of the seismic wave detection electric signal waveform and Seismic wave detection electric signal waveform semantic encoding feature vector, is the number of semantically encoded feature vectors of the seismic wave detection electrical signal waveform, and Respectively represent the weight parameter matrix and bias term of the hub feature extraction network, represents the hub feature relevance score transformation vector of the hub feature extraction network, Indicates the The corresponding hub feature relevance scoring factor, represents matrix multiplication, represents the normalized exponential function, Indicates the The corresponding normalized hub feature relevance score factor, Represents the semantic pivot feature encoding vector of the seismic wave detection electrical signal waveform.

[0053] That is, the present application constructs a hub feature extraction network based on a neural network architecture to utilize the powerful feature extraction capabilities of the neural network to perform hub feature correlation analysis on the semantic encoding feature vectors of each seismic wave detection electrical signal waveform, learn the potential correlations between the semantic features of each seismic wave detection electrical signal waveform, and thereby identify and extract representative signal waveform features from the set of seismic wave detection electrical signal waveform semantic encoding feature vectors, and generate a seismic wave detection electrical signal waveform semantic hub feature encoding vector.

[0054] Figure 5 FIG. 4 is a flow chart of sub-step S42 of the intelligent data collection method for geophysical exploration according to an embodiment of the present application. Figure 5 As shown, the step S42 includes the steps of: S421, extracting complementary information of each seismic wave detection electric signal waveform semantic coding feature vector in the set of seismic wave detection electric signal waveform semantic coding feature vectors relative to the seismic wave detection electric signal waveform semantic hub feature coding vector to obtain a set of seismic wave detection electric signal-hub feature complementary information embedded coding vectors; S422, performing complementary information significance marking on each seismic wave detection electric signal-hub feature complementary information embedded coding vector in the set of seismic wave detection electric signal-hub feature complementary information embedded coding vectors to obtain a set of seismic wave detection electric signal waveform semantic complementary information attention weights; S423, based on the set of seismic wave detection electric signal waveform semantic complementary information attention weights, performing attention modulation on the set of seismic wave detection electric signal-hub feature complementary information embedded coding vectors to obtain the set of significantly modulated seismic wave detection electric signal-hub feature complementary information embedded coding vectors.

[0055] More specifically, in a specific example of the present application, the step S421 includes: performing point convolution coding based on the Sigmoid activation function on the seismic wave detection electrical signal waveform semantic coding feature vector and the seismic wave detection electrical signal waveform semantic hub feature coding vector to obtain a standardized seismic wave detection electrical signal waveform semantic coding feature vector and a standardized seismic wave detection electrical signal waveform semantic hub feature coding vector; using the position difference vector between the standardized seismic wave detection electrical signal waveform semantic coding feature vector and the standardized seismic wave detection electrical signal waveform semantic hub feature coding vector as a weight vector, performing complementary feature enhancement modulation and aggregation coding on the seismic wave detection electrical signal waveform semantic coding feature vector and the seismic wave detection electrical signal waveform semantic hub feature coding vector to obtain the seismic wave detection electrical signal-hub feature complementary information embedded coding vector. The above step S421 is expressed by the formula:

[0056]

[0057] in, represents the Sigmoid activation function, Represents the semantic encoding feature vector of the standardized seismic wave detection electrical signal waveform, Represents the semantic pivot feature encoding vector of the standardized seismic wave detection electric signal waveform, and represents different weight matrices, represents point convolutional coding, represents the seismic wave detection electrical signal-hub feature differential feature encoding vector, represents the difference operation, To take the absolute value, Indicates the The corresponding seismic wave detection electrical signal-hub feature complementary information is embedded in the coding vector.

[0058] That is, in order to ensure that too much detailed information in the seismic wave detection electrical signal is not lost during the hub feature extraction process, the present application further integrates and associates the unique waveform semantic features of each seismic wave detection electrical signal itself with the seismic wave detection electrical signal waveform semantic hub feature coding vector as the core. In this process, by evaluating the complementarity of each seismic wave detection electrical signal waveform semantic coding feature vector relative to the seismic wave detection electrical signal waveform semantic hub feature coding vector, the characteristic differences and unique contributions of each seismic wave detection electrical signal waveform semantic feature relative to the global core information (i.e., hub feature) of the seismic wave detection electrical signal are captured, and a set of seismic wave detection electrical signal-hub feature complementary information embedded coding vectors is generated, so as to restore the characteristic components of each seismic wave detection electrical signal waveform semantic coding feature vector that are not considered and absorbed during the hub feature extraction process, thereby more completely reflecting the complexity and diversity of the original seismic wave detection electrical signal.

[0059] More specifically, the step S422 is expressed by the formula:

[0060]

[0061]

[0062] in, express The corresponding significant identification factor is and They represent the weight parameter matrix and bias term of the complementary information saliency identification module, represents the complementary information saliency score conversion vector of the complementary information saliency identification module, represents the exponential function operation with e as the base, express The corresponding attention weights of the semantic complementary information of the seismic wave detection electrical signal waveform.

[0063] That is, considering that the complementary information of each seismic wave detection electrical signal relative to the global core information of the signal set may supplement or enhance the underground geological structure and oil and gas reservoir information of the entire exploration area, it may also be redundant data or noise, and direct application to subsequent geological structure inference may lead to inaccurate results. Therefore, the present application further introduces an adaptive feature compensation aggregation mechanism, which evaluates the importance of each seismic wave detection electrical signal-hub feature complementary information embedded in the coding vector, and dynamically adjusts its weight distribution in the information aggregation process. In this way, more critical and discriminative complementary information will be given a higher weight to ensure that it occupies a more important position in the final analysis; and those feature information that are considered to be noise or unimportant will be appropriately weakened or ignored. This dynamic weight adjustment not only improves the accuracy of data analysis, but also enhances the reliability of the interpretation of underground geological structures, thereby providing more accurate data support for oil and gas reservoir positioning.

[0064] More specifically, the step S423 is expressed by the formula:

[0065]

[0066] in, , , and Respectively , , and The corresponding seismic wave detection electrical signal-hub feature complementary information embedding coding vector, , , and Respectively , , and The corresponding attention weight of the semantic complementary information of the seismic wave detection electric signal waveform, Represents the set of embedded coding vectors of the significantly modulated seismic wave detection electrical signal-hub feature complementary information.

[0067] That is, according to the calculated set of attention weights of the semantic complementary information of the seismic wave detection electric signal waveform, the set of the seismic wave detection electric signal-hub feature complementary information embedded coding vector is adjusted for attention, and by enhancing or suppressing specific features, it is ensured that the set of modulated seismic wave detection electric signal-hub feature complementary information embedded coding vector can more accurately reflect the key role and contribution of each seismic wave detection electric signal in the description of underground geological structure characteristics in the exploration area. In this way, those signal features that are crucial to the interpretation of underground geological structures can be highlighted, while reducing the impact of noise or irrelevant information.

[0068] Specifically, in a specific example of the present application, the step S43 includes: cascading the seismic wave detection electric signal waveform semantic hub feature coding vector and the set of the significantly modulated seismic wave detection electric signal-hub feature complementary information embedded coding vector to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector, which is expressed by the formula:

[0069]

[0070] in, represents a cascade function, Represents the semantic aggregation coding vector of the seismic wave detection electrical signal waveform.

[0071] That is, through cascade fusion, the set of the significantly modulated seismic wave detection electrical signal-hub feature complementary information embedded coding vectors and the seismic wave detection electrical signal waveform semantic hub feature coding vectors are combined to comprehensively consider the global core information of seismic wave detection electrical signals from multiple locations, while retaining the local detail information and unique contribution of the seismic wave detection electrical signals at each location to improve the accuracy and comprehensiveness of feature expression. The final generated seismic wave detection electrical signal waveform semantic aggregation coding vector can more accurately capture the key features reflecting the underground geological structure and oil and gas reservoirs, thereby improving the accuracy and reliability of geological structure inference and oil and gas reservoir identification in the entire exploration area.

[0072] In the above-mentioned intelligent data collection method for geophysical exploration, the step S5 determines the location of the oil and gas reservoir based on the semantic aggregation coding vector of the seismic wave detection electric signal waveform. In a specific example of the present application, the step S5 includes: inputting the semantic aggregation coding vector of the seismic wave detection electric signal waveform into the oil and gas reservoir location detector based on the decoder to obtain the decoded value of the oil and gas reservoir location. Here, the decoder adopts a multi-layer perceptron (MLP) structure to parse and infer the underground geological structure and oil and gas reservoir information contained in the semantic aggregation coding vector of the seismic wave detection electric signal waveform. Specifically, the decoder learns the spatial distribution characteristics of the underground geological structure contained in the vector by performing layer-by-layer nonlinear transformation and feature mapping on the semantic aggregation coding vector of the seismic wave detection electric signal waveform, and infers the possible location of the oil and gas reservoir based on this, so as to convert the abstract coding feature representation into actual geographical location information, and output the decoded value of the oil and gas reservoir location, thereby providing direct and critical guidance for geophysical exploration, so that the exploration work can be carried out more targeted, thereby improving the exploration efficiency and success rate.

[0073] In a preferred example of the present application, inputting the semantic aggregation coding vector of the seismic wave detection electric signal waveform into a decoder-based oil and gas reservoir position detector to obtain a decoded value of the oil and gas reservoir position includes:

[0074] First, determine the eigenvalue mean corresponding to the semantic aggregation coding vector of the seismic wave detection electric signal waveform and the standard deviation of the eigenvalues ;

[0075] Secondly, the seismic wave detection electric signal waveform semantic aggregation coding vector and the point subtraction vector of the eigenvalue mean and the eigenvalue standard deviation are multiplied to obtain the first seismic wave detection electric signal waveform semantic aggregation fair target vector, which is expressed as:

[0076]

[0077] in, represents the semantic aggregation coding vector of the seismic wave detection electric signal waveform, and represent the eigenvalue mean and eigenvalue standard deviation corresponding to the semantic aggregation coding vector of the seismic wave detection electric signal waveform respectively, It means subtracting by position. It means point multiplication by position. Represents the first seismic wave detection electric signal waveform semantic aggregation fair target vector;

[0078] Next, the seismic wave detection electric signal waveform semantic aggregation coding vector and the point subtraction vector of the eigenvalue standard deviation are multiplied by the eigenvalue mean to obtain the second seismic wave detection electric signal waveform semantic aggregation fair target vector, which is expressed as:

[0079]

[0080] in, Represents the semantic aggregation fair target vector of the second seismic wave detection electric signal waveform;

[0081] Then, after multiplying the bit-by-bit inverse of the second seismic wave detection electric signal waveform semantic aggregation fair target vector by the first seismic wave detection electric signal waveform semantic aggregation fair target vector, take the bit-by-bit logarithm with base 2 to obtain the seismic wave detection electric signal waveform semantic aggregation information correction vector, which is expressed as follows:

[0082]

[0083] in, represents the bit-wise reciprocal of a vector, Represents the correction vector of semantic aggregation information of seismic wave detection electric signal waveform;

[0084] Next, the eigenvalue mean Divide by the standard deviation of the eigenvalue The square root of the quotient is multiplied by the weight hyperparameter, and then the optimized seismic wave detection electric signal waveform semantic aggregation information correction vector is obtained by the formula:

[0085]

[0086] in, represents the weight hyperparameter, Represents an optimized semantic aggregation coding vector of the seismic wave detection electric signal waveform;

[0087] Finally, the optimized seismic wave detection electrical signal waveform semantic aggregation coding vector is input into the decoder-based oil and gas reservoir position detector to obtain the decoded value of the oil and gas reservoir position.

[0088] Here, since each seismic wave detection electrical signal waveform semantic coding feature vector in the set of seismic wave detection electrical signal waveform semantic coding feature vectors respectively represents the signal waveform semantic features of each denoised seismic wave detection electrical signal, when performing feature dynamic compensation aggregation on them, the signal source domain differences of each denoised seismic wave detection electrical signal will cause fine-grained distortion in sequence hub calculation, thereby making each seismic wave detection electrical signal waveform semantic coding feature vector in the set of seismic wave detection electrical signal waveform semantic coding feature vectors have dynamic compensation aggregation fairness differences, thereby affecting the interactive inclusiveness of the aggregation feature distribution of the seismic wave detection electrical signal waveform semantic aggregation coding vector, and reducing the accuracy of the decoding results obtained by inputting the decoder-based oil and gas reservoir position detector.

[0089] Therefore, taking into account the attribute level fairness differences of the data population corresponding to the sequence fusion features of the seismic wave detection electrical signal waveform semantic aggregation coding vector, in order to improve the aggregation interaction inclusiveness under the feature distribution diversity of the seismic wave detection electrical signal waveform semantic aggregation coding vector, the crossover probability value constraint based on the seismic wave detection electrical signal waveform semantic aggregation coding vector is used as the interactive fairness target representation to correct the group feature information interaction propagation of the seismic wave detection electrical signal waveform semantic aggregation coding vector, and the unified statistical feature response interaction based on the seismic wave detection electrical signal waveform semantic aggregation coding vector is used as the feature distribution multi-level fairness target bias to achieve a robust distribution fairness unified representation of the seismic wave detection electrical signal waveform semantic aggregation coding vector, forming a fair collaboration paradigm under the feature distribution framework of the seismic wave detection electrical signal waveform semantic aggregation coding vector, and improving the accuracy of the decoded value of the oil and gas reservoir position obtained by the decoder-based oil and gas reservoir position detector.

[0090] In summary, the intelligent data acquisition method for geophysical exploration based on the embodiment of the present application is explained, which uses a seismic detector to collect seismic wave detection electrical signals from multiple data collection points in the target exploration area, and after performing signal noise reduction processing on the seismic wave detection electrical signals at each collection point, further introduces data processing technology based on depth information to perform waveform semantic feature extraction and global correlation analysis on each seismic wave detection electrical signal, so as to use the global waveform oscillation mode of the seismic wave detection electrical signal to reveal potential oil and gas reservoir information, and intelligently decode the location of the oil and gas reservoir. In this way, the automatic and intelligent identification of the location of the oil and gas reservoir can be achieved, and the accuracy and efficiency of geophysical exploration can be improved.

[0091] Furthermore, an intelligent data acquisition system for geophysical exploration is also provided.

[0092] Figure 6FIG. 1 is a block diagram of an intelligent data acquisition system for geophysical exploration according to an embodiment of the present application. Figure 6 As shown, according to the embodiment of the present application, the intelligent data acquisition system 100 for geophysical exploration includes: a data acquisition point deployment module 110, which is used to set multiple data acquisition points in the target exploration area; a seismic wave signal acquisition module 120, which is used to obtain a set of seismic wave detection electrical signals by using seismic detectors deployed at the respective data acquisition points to acquire seismic wave detection electrical signals; a waveform feature extraction module 130, which is used to extract the waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors; a feature compensation aggregation coding module 140, which is used to perform adaptive feature compensation aggregation coding on the set of seismic wave detection electrical signal waveform semantic coding feature vectors to obtain a seismic wave detection electrical signal waveform semantic aggregation coding vector; and an oil and gas reservoir positioning module 150, which is used to determine the position of the oil and gas reservoir based on the seismic wave detection electrical signal waveform semantic aggregation coding vector.

[0093] Here, those skilled in the art will appreciate that the specific operations of each module in the intelligent data acquisition system for geophysical exploration have been described in detail above. Figures 1 to 5 The invention has been described in detail in the description of the intelligent data acquisition method for geophysical exploration, and therefore, its repeated description will be omitted.

[0094] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0095] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0096] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0097] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0098] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent data collection method for geophysical exploration, characterized in that: include: Set up multiple data collection points in the target exploration area; Using seismic wave detection electrical signals collected by seismic detectors deployed at each data collection point to obtain a set of seismic wave detection electrical signals; Extracting waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors; Performing adaptive feature compensation aggregation coding on the set of the seismic wave detection electric signal waveform semantic coding feature vectors to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector; Determine the location of the oil and gas reservoir based on the semantic aggregation coding vector of the seismic wave detection electrical signal waveform; The method of performing adaptive feature compensation aggregation coding on the set of the seismic wave detection electric signal waveform semantic coding feature vectors to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector comprises: Inputting the set of semantic encoding feature vectors of the seismic wave detection electric signal waveform into a pivot feature extraction network to obtain a semantic pivot feature encoding vector of the seismic wave detection electric signal waveform; Based on the seismic wave detection electric signal waveform semantic hub feature coding vector, each seismic wave detection electric signal waveform semantic coding feature vector in the set of seismic wave detection electric signal waveform semantic coding feature vectors is dynamically modulated based on complementary information to obtain a set of significantly modulated seismic wave detection electric signal-hub feature complementary information embedded coding vectors; The seismic wave detection electric signal waveform semantic hub feature coding vector and the set of the significantly modulated seismic wave detection electric signal-hub feature complementary information embedding coding vector are fused to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector.

2. The intelligent data collection method for geophysical exploration according to claim 1, characterized in that: Extracting the waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors, including: Performing signal noise reduction on each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of noise-reduced seismic wave detection electrical signals; An electrical signal waveform feature extractor based on a one-dimensional convolutional layer is used to extract waveform features of each denoised seismic wave detection electrical signal in the set of denoised seismic wave detection electrical signals to obtain a set of waveform semantic encoding feature vectors of the seismic wave detection electrical signals.

3. The intelligent data collection method for geophysical exploration according to claim 2, characterized in that: Performing signal noise reduction on each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of noise-reduced seismic wave detection electrical signals, comprising: A Butterworth filter is used to filter each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain the set of noise-reduced seismic wave detection electrical signals.

4. The intelligent data collection method for geophysical exploration according to claim 3, characterized in that: Based on the seismic wave detection electric signal waveform semantic hub feature coding vector, each seismic wave detection electric signal waveform semantic coding feature vector in the set of seismic wave detection electric signal waveform semantic coding feature vectors is dynamically modulated based on complementary information to obtain a set of significantly modulated seismic wave detection electric signal-hub feature complementary information embedded coding vectors, including: Extracting complementary information of each seismic wave detection electric signal waveform semantic coding feature vector in the set of seismic wave detection electric signal waveform semantic coding feature vectors relative to the seismic wave detection electric signal waveform semantic pivot feature coding vector to obtain a set of seismic wave detection electric signal-pivot feature complementary information embedded coding vectors; Performing complementary information significance marking on each seismic wave detection electric signal-pivot feature complementary information embedding coding vector in the set of seismic wave detection electric signal-pivot feature complementary information embedding coding vectors to obtain a set of attention weights of the seismic wave detection electric signal waveform semantic complementary information; Based on the set of attention weights of the semantic complementary information of the seismic wave detection electrical signal waveform, the set of seismic wave detection electrical signal-hub feature complementary information embedded coding vectors is subjected to attention modulation to obtain the set of significantly modulated seismic wave detection electrical signal-hub feature complementary information embedded coding vectors.

5. The intelligent data collection method for geophysical exploration according to claim 4, characterized in that: Extracting complementary information of each seismic wave detection electric signal waveform semantic coding feature vector in the set of seismic wave detection electric signal waveform semantic coding feature vectors relative to the seismic wave detection electric signal waveform semantic pivot feature coding vector to obtain a set of seismic wave detection electric signal-pivot feature complementary information embedded coding vectors, including: Performing point convolution encoding based on Sigmoid activation function on the seismic wave detection electric signal waveform semantic encoding feature vector and the seismic wave detection electric signal waveform semantic pivot feature encoding vector respectively to obtain a standardized seismic wave detection electric signal waveform semantic encoding feature vector and a standardized seismic wave detection electric signal waveform semantic pivot feature encoding vector; Taking the positional difference vector between the standardized seismic wave detection electrical signal waveform semantic coding feature vector and the standardized seismic wave detection electrical signal waveform semantic hub feature coding vector as the weight vector, the seismic wave detection electrical signal waveform semantic coding feature vector and the seismic wave detection electrical signal waveform semantic hub feature coding vector are subjected to complementary feature enhancement modulation and aggregation coding to obtain the seismic wave detection electrical signal-hub feature complementary information embedding coding vector.

6. The intelligent data collection method for geophysical exploration according to claim 5, characterized in that: The seismic wave detection electric signal waveform semantic hub feature coding vector and the set of the significantly modulated seismic wave detection electric signal-hub feature complementary information embedding coding vector are integrated to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector, including: The seismic wave detection electrical signal waveform semantic hub feature coding vector and the set of the significantly modulated seismic wave detection electrical signal-hub feature complementary information embedded coding vector are cascaded and fused to obtain the seismic wave detection electrical signal waveform semantic aggregation coding vector.

7. The intelligent data collection method for geophysical exploration according to claim 6, characterized in that: Determining the location of the oil and gas reservoir based on the semantic aggregation coding vector of the seismic wave detection electric signal waveform includes: The semantic aggregation coding vector of the seismic wave detection electric signal waveform is input into the decoder-based oil and gas reservoir position detector to obtain the decoded value of the oil and gas reservoir position.

8. An intelligent data acquisition system for geophysical exploration, characterized in that: include: A data collection point deployment module is used to set up multiple data collection points in the target exploration area; A seismic wave signal acquisition module, used to obtain a set of seismic wave detection electrical signals by using seismic wave detection electrical signals acquired by seismic detectors deployed at each data acquisition point; A waveform feature extraction module, used to extract the waveform features of each seismic wave detection electrical signal in the set of seismic wave detection electrical signals to obtain a set of seismic wave detection electrical signal waveform semantic coding feature vectors; A feature compensation aggregation coding module, used for performing adaptive feature compensation aggregation coding on the set of the seismic wave detection electric signal waveform semantic coding feature vectors to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector; An oil and gas reservoir positioning module, used to determine the oil and gas reservoir position based on the semantic aggregation coding vector of the seismic wave detection electrical signal waveform; The feature compensation aggregation coding module is used to: Inputting the set of semantic encoding feature vectors of the seismic wave detection electric signal waveform into a pivot feature extraction network to obtain a semantic pivot feature encoding vector of the seismic wave detection electric signal waveform; Based on the seismic wave detection electric signal waveform semantic hub feature coding vector, each seismic wave detection electric signal waveform semantic coding feature vector in the set of seismic wave detection electric signal waveform semantic coding feature vectors is dynamically modulated based on complementary information to obtain a set of significantly modulated seismic wave detection electric signal-hub feature complementary information embedded coding vectors; The seismic wave detection electric signal waveform semantic hub feature coding vector and the set of the significantly modulated seismic wave detection electric signal-hub feature complementary information embedding coding vector are fused to obtain the seismic wave detection electric signal waveform semantic aggregation coding vector.

Images