Geological test data abnormal value detection method, system, equipment and medium

Abstract

The invention provides a geological test data abnormal value detection method, system and device and a medium, and the method comprises the steps: building a three-dimensional space weight matrix according to collected space coordinates, and determining the spatial correlation difference degree of geological test data between test monitoring points; performing spatial correlation screening on the geological test data of each test monitoring point by combining each spatial correlation difference degree with a preset difference degree threshold value to obtain spatial correlation abnormal data and spatial correlation normal data; inputting the spatial correlation normal data into an isolated forest model to perform local anomaly screening, and outputting local anomaly data; and fusing the spatial correlation abnormal data and the local abnormal data to generate test abnormal data of the target region. By adopting the scheme of the invention, the abnormal data in the geological test data can be identified based on the three-dimensional space autocorrelation of the geological data in combination with the geological mechanism rule.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data anomaly detection, and in particular, the present application relates to a geological test data anomaly value detection method, system, device and medium. BACKGROUND

[0002] Geological test data anomaly value detection is an important link in geological exploration and engineering application. Traditional geological data anomaly value detection methods usually rely on statistics and mathematical models, such as box plot method, standard deviation method, etc., and judge the abnormality of data based on single-dimensional numerical fluctuation.

[0003] The basic idea of traditional geological data anomaly value detection is to analyze historical data or existing data sets and identify data points that significantly deviate from the expected range. These data points are usually considered as outliers. The traditional method focuses on the processing of single-point data or two-dimensional data, lacks the understanding of three-dimensional spatial correlation of geological data and complex geological mechanism, and ignores the potential spatial dependence relationship between data and geological genesis factors. Therefore, how to identify abnormal data in geological test data based on the three-dimensional spatial autocorrelation of geological data combined with geological mechanism rules has become a difficult problem in the industry. SUMMARY

[0004] Based on this, the present application provides a geological test data anomaly value detection method and system for identifying abnormal data in geological test data based on the three-dimensional spatial autocorrelation of geological data combined with geological mechanism rules.

[0005] In a first aspect, the present application provides a geological test data anomaly value detection method, comprising the following steps: Collecting geological test data and corresponding spatial coordinates of each test monitoring point in a target area; Constructing a three-dimensional spatial weight matrix according to all spatial coordinates, and then determining the spatial correlation difference degree of geological test data between each test monitoring point based on the three-dimensional spatial weight matrix combined with all geological test data; Performing spatial correlation screening on the geological test data of each test monitoring point by combining each spatial correlation difference degree with a preset geological mechanism rule, to obtain spatial correlation abnormal data and spatial correlation normal data; Inputting the spatial correlation normal data into an isolation forest model for local anomaly screening, and outputting local abnormal data; Fusing the spatial correlation abnormal data and the local abnormal data to generate test abnormal data of the target area.

[0006] In some embodiments, constructing a three-dimensional spatial weight matrix according to all spatial coordinates specifically includes: According to all the spatial coordinates, the spatial distances between the respective test monitoring points are calculated; According to the spatial distances between the respective test monitoring points, the spatial weight values between the corresponding test monitoring points are calculated, wherein the spatial weight values are inversely proportional to the spatial distances between the corresponding test monitoring points; All the calculated spatial weight values are constructed into a three-dimensional spatial weight matrix according to the spatial coordinate relationship.

[0007] In some embodiments, based on the three-dimensional spatial weight matrix combined with all the geological test data, the spatial correlation difference degrees of the geological test data between the respective test monitoring points are determined, which specifically includes: According to all the geological test data combined with the three-dimensional spatial weight matrix, the spatial dependence relationships of the respective test monitoring points are determined; Based on the spatial dependence relationship and the geological test data of each test monitoring point, the adjacent trend data of the test monitoring point are determined; The adjacent deviation amounts of different monitoring parameters between the adjacent trend data of each test monitoring point and the corresponding geological test data are determined; According to all the adjacent deviation amounts, the spatial correlation difference degrees of the geological test data between the respective test monitoring points are calculated.

[0008] In some embodiments, by combining the respective spatial correlation difference degrees with the preset geological mechanism rules, the spatial correlation screening of the geological test data of the respective test monitoring points is performed, and the spatial correlation abnormal data and the spatial correlation normal data are obtained, which specifically includes: The preset geological mechanism rules are obtained, and then the difference degree threshold is determined according to the preset geological mechanism rules; For each test monitoring point, the spatial correlation difference degree of the test monitoring point is compared with the difference degree threshold; When the spatial correlation difference degree is greater than or equal to the difference degree threshold, the geological test data of the test monitoring point is taken as the spatial correlation abnormal data; When the spatial correlation difference degree is less than the difference degree threshold, the geological test data of the test monitoring point is taken as the spatial correlation normal data, and then the spatial correlation abnormal data and the spatial correlation normal data are obtained.

[0009] In some embodiments, the spatial correlation normal data is input into an isolation forest model for local anomaly screening, and local anomaly data is output, which specifically includes: The spatial correlation normal data is preprocessed; An isolation forest model based on an attention mechanism is constructed, wherein the attention mechanism enhances the anomaly data recognition ability by weighting specific input features; input the preprocessed spatially correlated normal data into the attention mechanism-based isolation forest model, and output an anomaly discrimination value of each test monitoring point in the spatially correlated normal data; For each test monitoring point in the spatially correlated normal data, the geological test data corresponding to all test monitoring points with an anomaly discrimination value greater than a preset anomaly discrimination threshold value are taken as local anomaly data.

[0010] In some embodiments, the fusion of the spatially correlated anomaly data and the local anomaly data generates test anomaly data of the target area, specifically including: combining the spatially correlated anomaly data and the local anomaly data, and performing visual conversion on the combined anomaly data to obtain a three-dimensional visualization map; storing the three-dimensional visualization map as test anomaly data.

[0011] In some embodiments, the geological test data includes water content, porosity, thermal conductivity, and chemical element content.

[0012] In a second aspect, the present application provides a geological test data anomaly value detection system, which comprises: a collection module configured to collect geological test data and corresponding spatial coordinates of each test monitoring point in a target area; a processing module configured to construct a three-dimensional spatial weight matrix according to all spatial coordinates, and then determine spatial correlation differences of the geological test data between each test monitoring point based on the three-dimensional spatial weight matrix and all geological test data; The processing module is further configured to perform spatial correlation screening on the geological test data of each test monitoring point by combining each spatial correlation difference with a preset geological mechanism rule, to obtain spatially correlated anomaly data and spatially correlated normal data. The processing module is further configured to input the spatially correlated normal data into an isolation forest model for local anomaly screening, and output local anomaly data. An execution module is configured to fuse the spatially correlated anomaly data and the local anomaly data to generate test anomaly data of the target area.

[0013] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned geological test data anomaly value detection method when executing the computer program.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the above-mentioned geological test data anomaly value detection method.

[0015] The technical scheme provided by the embodiments disclosed in the application has the following beneficial effects: In the geological test data anomaly value detection method and system provided in the application, first, geological test data and corresponding spatial coordinates of each test monitoring point in a target area are collected; a three-dimensional spatial weight matrix is constructed according to all the spatial coordinates, and then spatial correlation difference degrees of the geological test data between each test monitoring point are determined based on the three-dimensional spatial weight matrix and all the geological test data; the spatial correlation difference degrees are combined with a preset difference degree threshold to perform spatial correlation screening on the geological test data of each test monitoring point, to obtain spatial correlation abnormal data and spatial correlation normal data; the spatial correlation normal data are input into an isolation forest model for local anomaly screening, to output local abnormal data; and the spatial correlation abnormal data and the local abnormal data are fused to generate test abnormal data of the target area.

[0016] As can be seen, first, a three-dimensional spatial weight matrix is constructed according to all the spatial coordinates, the three-dimensional spatial weight matrix is used to represent the spatial correlation degrees between test monitoring points, and then spatial correlation difference degrees of the geological test data between each test monitoring point are determined based on the three-dimensional spatial weight matrix and all the geological test data, the spatial correlation difference degrees reflect the spatial heterogeneity of the geological test data between test monitoring points, and a test monitoring point with a larger spatial correlation difference degree has a weaker influence on other test monitoring points, and can represent a significant change in the geological conditions of the test monitoring point corresponding to the spatial correlation difference degree; then the spatial correlation difference degrees are combined with a preset difference degree threshold to perform spatial correlation screening on the geological test data of each test monitoring point, to obtain spatial correlation abnormal data and spatial correlation normal data; second, the spatial correlation normal data are input into an isolation forest model for local anomaly screening, to output local abnormal data, the isolation forest model with the attention mechanism can improve the detection accuracy of abnormal data and optimize small sample adaptability when processing complex geological test data; finally, the spatial correlation abnormal data and the local abnormal data are fused to generate test abnormal data of the target area; in summary, the scheme of the application can identify abnormal data in the geological test data based on the three-dimensional spatial autocorrelation of geological data and geological mechanism rules. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is an exemplary flowchart of a geological test data anomaly value detection method according to some embodiments of the application; Figure 2 is an application scenario schematic diagram of a geological test data anomaly value detection system according to some embodiments of the application; Figure 3 is a flowchart of determining spatial correlation difference degrees according to some embodiments of the application; Figure 4 is a structural schematic diagram of a geological test data outlier detection system according to some embodiments of the present application; Figure 5 is a structural schematic diagram of a computer device for implementing a geological test data outlier detection method according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments.

[0019] Reference Figure 1 The figure is an exemplary flowchart of a geological test data outlier detection method according to some embodiments of the present application, which mainly includes the following steps: In step 101, geological test data and corresponding spatial coordinates of each test monitoring point in the target area are collected.

[0020] In specific implementation, the geological test data and corresponding spatial coordinates of each test monitoring point in the target area can be implemented in the following manner, that is, first, a series of geological monitoring sensors, such as water content monitoring sensors, porosity monitors, thermal line method sensors, and element content monitoring sensors, are deployed at different test monitoring points in the target area. These sensors will transmit data to a central data storage device through a wireless or wired network, then, a global positioning system device is used to accurately locate each test monitoring point to obtain the spatial coordinates (i.e., longitude, latitude, and elevation information) of each test monitoring point, and the geological test data of each test monitoring point is corresponded to its corresponding spatial coordinates one by one, to ensure that the collected data can accurately reflect the geological conditions and spatial distribution of each test monitoring point in the target area, and when collecting the geological test data of each test monitoring point in the target area, time stamping can be performed according to actual needs to facilitate subsequent time series analysis.

[0021] It should be noted that the geological test data described in the present application includes different monitoring parameters such as water content, porosity, thermal conductivity, and chemical element content, and other geological test data can also be collected in other embodiments.

[0022] In some embodiments, reference Figure 2As shown, the figure is a schematic diagram of an application scenario of the geological test data outlier detection system according to some embodiments of the present application, which includes three main components: a collection device, a server and a data storage device. The collection device is responsible for collecting geological test data and corresponding spatial coordinates of each test monitoring point in the target area, and sending the collected geological test data and corresponding spatial coordinates to the server through a communication network. The geological test data outlier detection system runs in the server, and the server stores the processing results in the data storage device and visualizes them.

[0023] In step 102, a three-dimensional spatial weight matrix is constructed according to all spatial coordinates, and then the spatial correlation difference of the geological test data between each test monitoring point is determined based on the three-dimensional spatial weight matrix and all geological test data.

[0024] In some embodiments, the three-dimensional spatial weight matrix can be constructed according to all spatial coordinates by the following steps, that is: Calculate the spatial distance between each test monitoring point according to all spatial coordinates; Calculate the spatial weight value between the corresponding test monitoring points according to the spatial distance between each test monitoring point, wherein the spatial weight value is inversely proportional to the spatial distance between the corresponding test monitoring points; Construct a three-dimensional spatial weight matrix according to all calculated spatial weight values and spatial coordinate relationships.

[0025] In specific implementation, the spatial distance between each test monitoring point can be calculated according to all spatial coordinates by the following methods, for example: the Euclidean distance formula can be used to calculate the spatial distance between any two test monitoring points; for three-dimensional spatial data containing elevation information, the three-dimensional Euclidean distance formula can be used to consider the influence of vertical distribution; in addition, appropriate spherical distance calculation can be performed according to the curvature of the earth surface to ensure the accuracy of the spatial distance. In other embodiments, other suitable spatial distance calculation methods can also be used, and the present embodiment is not limited in this regard.

[0026] In specific implementation, the spatial weight value between the corresponding test monitoring points can be calculated according to the spatial distance between each test monitoring point by the following methods, that is: based on the calculated spatial distance between each two test monitoring points, the inverse relationship can be used to calculate the spatial weight value between the corresponding test monitoring points. More specifically, for each pair of test monitoring points, the spatial weight value can be calculated by the following method: the spatial weight value is inversely proportional to the distance, that is, the closer the distance, the greater the weight value. The optional calculation method is: wherein, represents the spatial weight value, represents the spatial distance between the two test monitoring points, is an adjustment factor, usually taking a value of 2 or higher, and this inverse relationship ensures that the test monitoring points closer in distance have a greater influence on the weight calculation of other test monitoring points, and the test monitoring points farther in distance have a smaller influence.

[0027] In a specific implementation, the three-dimensional spatial weight matrix can be constructed in the following manner: all the calculated spatial weight values can be organized into a matrix according to the spatial coordinate relationship between the test monitoring points, where each matrix element represents the spatial weight value between a pair of test monitoring points, and the dimension of the matrix is N x N (where N is the number of test monitoring points). It should be noted that the three-dimensional spatial weight matrix is used to represent the spatial correlation between the test monitoring points, and in addition, other existing technologies can be used to construct the three-dimensional spatial weight matrix in other embodiments, which are not limited here.

[0028] In some embodiments, referring to Figure 3 The figure is a flowchart for determining the spatial correlation difference in some embodiments of the present application. In this embodiment, the spatial correlation difference between the test monitoring points can be determined based on the three-dimensional spatial weight matrix and all the geological test data in the following steps: In step 1031, the spatial dependence relationship of each test monitoring point is determined based on all the geological test data and the three-dimensional spatial weight matrix. In step 1032, the adjacent trend data of each test monitoring point is determined based on the spatial dependence relationship and the geological test data of each test monitoring point. In step 1033, the adjacent deviation amount of different monitoring parameters between the adjacent trend data of each test monitoring point and the corresponding geological test data is determined. In step 1034, the spatial correlation difference between the test monitoring points is calculated based on all the adjacent deviation amounts.

[0029] In a specific implementation, the spatial dependence relationship of each test monitoring point can be determined based on all the geological test data and the three-dimensional spatial weight matrix in the following manner: first, the covariance between each test monitoring point can be calculated based on all the geological test data, thereby obtaining a covariance matrix; then the covariance matrix is multiplied by the three-dimensional spatial weight matrix; finally, the value of each element in the multiplied matrix is taken as the spatial dependence relationship of the corresponding test monitoring point, and the spatial dependence relationship is used to quantify the spatial correlation between the test monitoring points.

[0030] It should be noted that in the process of calculating the covariance between each test monitoring point according to all the geological test data, the weighted fusion method can be used to calculate the fusion value for different monitoring parameters in each test monitoring point, and then the fusion value is used to calculate the covariance.

[0031] In a specific implementation, the adjacent trend data of each test monitoring point can be determined based on the spatial dependence relationship of each test monitoring point and the geological test data, and the adjacent trend data of each test monitoring point can be obtained by weighting the geological test data of the adjacent test monitoring points of each test monitoring point according to the spatial dependence relationship of all test monitoring points, which reflects the change trend of the geological characteristics of the test monitoring point in the adjacent area. It should be noted that in the process of weighting the geological test data of the adjacent test monitoring points of each test monitoring point according to the spatial dependence relationship of all test monitoring points, different monitoring parameters in each geological test data can be weighted respectively, and then the weighted values of different monitoring parameters in each geological test data are combined to form the adjacent trend data of the corresponding test monitoring point.

[0032] In a specific implementation, the adjacent deviation amount of different monitoring parameters between the adjacent trend data of each test monitoring point and the corresponding geological test data can be obtained by the following method, that is, for the adjacent trend data of each test monitoring point, the weighted values of different monitoring parameters in the adjacent trend data are subtracted from the values of different monitoring parameters in the corresponding geological test data, and the subtraction values are taken as the adjacent deviation amount of different monitoring parameters, and then the adjacent deviation amount of different monitoring parameters between the adjacent trend data of each test monitoring point and the corresponding geological test data is obtained. It should be noted that the adjacent deviation amount in the present application reflects the deviation between the actual measured geological test data of the test monitoring point and the adjacent trend data thereof, and the greater the adjacent deviation amount, the more obvious the difference between the actual measured geological test data of the test monitoring point and the adjacent trend data thereof, and the more abnormal.

[0033] In a specific implementation, the spatial correlation difference degree of the geological test data between each test monitoring point can be calculated according to all the adjacent deviation amounts by the following steps, that is, for each test monitoring point, the spatial correlation difference degree of the geological test data between each test monitoring point can be calculated by weighting and averaging all the adjacent deviation amounts corresponding to the test monitoring point, wherein the spatial correlation difference degree reflects the spatial heterogeneity of the geological test data between the test monitoring points, and the test monitoring point with a larger spatial correlation difference degree has a weaker influence on other test monitoring points, which can represent the significant change of the geological conditions of the test monitoring point corresponding to the spatial correlation difference degree.

[0034] In step 103, the geological test data of each test monitoring point is screened by spatial correlation according to the preset geological mechanism rule and the spatial correlation difference degree, to obtain spatial correlation abnormal data and spatial correlation normal data.

[0035] In some embodiments, the spatial correlation screening of the geological test data of each test monitoring point by the spatial correlation difference degree and the preset geological mechanism rule can be realized by the following steps: The preset geological mechanism rule is obtained, and then the difference degree threshold is determined according to the preset geological mechanism rule; For each test monitoring point, the spatial correlation difference degree of the test monitoring point is compared with the difference degree threshold; When the spatial correlation difference degree is greater than or equal to the difference degree threshold, the geological test data of the test monitoring point is taken as spatial correlation abnormal data; When the spatial correlation difference degree is less than the difference degree threshold, the geological test data of the test monitoring point is taken as spatial correlation normal data, and then the spatial correlation abnormal data and the spatial correlation normal data are obtained.

[0036] In specific implementation, the preset geological mechanism rule can be realized by the following way, that is, it can be realized based on the rule of the geological theoretical model, for example, one or more geological mechanism models (such as rock layer interaction model, underground water flow model, etc.) are selected according to the geological characteristics of the target area, then the monitoring parameters such as rock layer interface strength, porosity, permeability, etc. are extracted from the geological mechanism model, and finally different monitoring thresholds are set for each monitoring parameter, for example, under certain geological conditions, if the strength of the rock layer is lower than 30MPa, it may cause instability, therefore a rule is set: "if the rock layer interface strength is lower than 30MPa, it is considered that there may be geological anomaly in this area, and the monitoring threshold of the rock layer interface strength is 30MPa"; in other embodiments, in specific implementation, the preset geological mechanism rule can also be realized based on the rule of experience, for example, the geological mechanism rule is refined by the geologists according to the geological characteristics of the target area, historical data and known geological events (such as mountain landslide, underground water leakage, etc.), for example, the relationship between porosity and permeability can be set as a monitoring threshold according to the geological experience; in other embodiments, other methods can also be used, which are not limited here.

[0037] In specific implementation, the difference degree threshold can be calculated by weighted average of each monitoring threshold in the preset geological mechanism rule, in other embodiments, other methods can also be used, which are not repeated here.

[0038] The geological test data of a set of normal areas are acquired, and the spatial correlation difference of the geological test data is calculated as a background data set. Then, a suitable difference threshold is selected according to the difference distribution of the background data set. For example, the standard deviation or the median can be used to determine the difference threshold, and other methods can also be used to determine the difference threshold in other embodiments, which is not limited here.

[0039] It should be noted that the spatial correlation abnormal data in the present application represents the geological test data of the corresponding test monitoring point and the spatial relationship difference of other test monitoring points in the target area, which is obviously abnormal; the spatial correlation normal data represents the geological test data of the corresponding test monitoring point and the spatial relationship of other test monitoring points in the target area, which is normal and does not show abnormal trend.

[0040] In step 104, the spatial correlation normal data is input into the isolation forest model for local anomaly screening, and the local anomaly data is output.

[0041] In some embodiments, the spatial correlation normal data is input into the isolation forest model for local anomaly screening, and the local anomaly data is output, which can be realized by the following steps, that is: The spatial correlation normal data is preprocessed; An isolation forest model based on attention mechanism is constructed, wherein the attention mechanism enhances the abnormal data recognition ability by weighting specific input features; The preprocessed spatial correlation normal data is input into the isolation forest model based on attention mechanism, and the abnormal discrimination value of each test monitoring point in the spatial correlation normal data is output; For each test monitoring point in the spatial correlation normal data, the geological test data corresponding to all test monitoring points with an abnormal discrimination value greater than a preset abnormal discrimination threshold are taken as local anomaly data.

[0042] In some embodiments, the isolation forest model based on attention mechanism can be realized by the following steps, that is: The basic structure of the isolation forest model is constructed; The correlation features of each monitoring parameter in the historical geological test data between different test monitoring points are determined in combination with the attention mechanism; All monitoring parameters in the historical geological test data are weighted according to all correlation features, and then the training of the isolation forest model is completed with all weighted monitoring parameters.

[0043] In a specific implementation, the isolated forest model based on the attention mechanism can be implemented in the following manner: a basic framework of the isolated forest model is constructed, including selecting basic parameters of the model (for example: the number of trees, the depth of the tree, etc.); in a specific implementation, the correlation characteristics of each monitoring parameter in the historical geological test data between different test monitoring points are determined in combination with the attention mechanism, which can be implemented in the following manner: a self-attention layer is constructed, which dynamically adjusts the weight (i.e. the correlation characteristics) by calculating the relative importance between the parameters of each test monitoring point; more specifically, the self-attention mechanism calculates the similarity between each test monitoring point and other test monitoring points, and assigns a correlation characteristic value to each monitoring parameter, which reflects the influence of different monitoring parameters in the isolated forest training process; in a specific implementation, the various monitoring parameters in the historical geological test data are weighted according to all the correlation characteristics, and then the training of the isolated forest model is completed with all the weighted monitoring parameters, which can be implemented in the following manner: the correlation characteristics obtained by the self-attention mechanism are used to weight the monitoring parameters in the input historical geological test data, and then these weighted monitoring parameters are used as input in the isolated forest training process, multiple random trees are generated, and abnormal data points are isolated, thereby completing the training of the isolated forest model; it should be noted that in the training process, the isolated forest model determines whether a point is an abnormal point by calculating the path length of each test monitoring point in the tree, the weighted features indirectly affect the path length by adjusting the path splitting method, thereby changing the abnormal score.

[0044] In addition, in a specific implementation, the spatially correlated normal data can be preprocessed in the following manner: for the spatially correlated normal data, missing values can be filled using a suitable interpolation method (for example: nearest neighbor interpolation or linear interpolation); the spatially correlated normal data can also be normalized or standardized, so that the numerical range of all monitoring parameters is unified to a standard range; the spatially correlated normal data can also be processed for noise, for example, using a filtering algorithm such as median filtering or Gaussian filtering to remove high-frequency noise; in other embodiments, other methods can also be used for preprocessing, which will not be described here.

[0045] In a specific implementation, the preprocessed spatially correlated normal data is input into the attention mechanism-based isolation forest model, and the output of the anomaly discrimination value of each test monitoring point in the spatially correlated normal data can be achieved in the following manner: the preprocessed spatially correlated normal data is input into the attention mechanism-based isolation forest model, the model evaluates each test monitoring point through the previously trained isolation forest, and outputs the anomaly discrimination value of each test monitoring point. More specifically, the preprocessed data of each test monitoring point is input into the isolation forest model, and the model evaluates the anomaly degree of each test monitoring point through the path length. Due to the addition of the attention mechanism, the model gives different weights according to the importance of each monitoring parameter, thereby more accurately evaluating the anomaly discrimination value of each test monitoring point. The anomaly discrimination value of each test monitoring point represents the probability or score of the test monitoring point being judged as abnormal by the isolation forest model. The higher the anomaly discrimination value, the more likely the test monitoring point is abnormal.

[0046] It should be noted that the anomaly discrimination threshold in the present application can be determined by the anomaly score distribution of historical data, for example: the upper percentile (such as 95%) of the anomaly score can be selected as the anomaly discrimination threshold. Local abnormal data represents data with large deviation in different monitoring parameters, which needs to be further studied and detected.

[0047] In addition, it should be noted that the step of using the isolation forest model with attention mechanism can improve the detection accuracy of abnormal data and optimize the small sample adaptability when processing complex geological test data.

[0048] In step 105, the spatially correlated abnormal data and the local abnormal data are fused to generate test abnormal data of the target area.

[0049] In some embodiments, the fusion of the spatially correlated abnormal data and the local abnormal data to generate test abnormal data of the target area can be achieved in the following steps: The spatially correlated abnormal data and the local abnormal data are combined, and the combined abnormal data is visualized and converted to obtain a three-dimensional visualization map; The three-dimensional visualization map is stored as test abnormal data.

[0050] In a specific implementation, the combined abnormal data is visualized and converted to obtain a three-dimensional visualization map, which can be achieved in the following manner: a three-dimensional data visualization tool can be used to convert the combined abnormal data into a three-dimensional map. In the three-dimensional map, spatial coordinates can be used as X, Y, and Z axes, and the values of each monitoring parameter in the geological test data corresponding to each test monitoring point can be used as color values of the three-dimensional visualization map, so that the abnormal density and intensity of different regions can be intuitively displayed in the map.

[0051] In addition, in another aspect of the present application, in some embodiments, the present application provides a geological test data outlier detection system, referring to Figure 4 , which is a schematic diagram of the structure of a geological test data outlier detection system according to some embodiments of the present application. The geological test data outlier detection system includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described as follows: Acquisition module 401, in this application, acquisition module 401 is mainly used to collect geological test data and corresponding spatial coordinates of each test monitoring point in the target area; Processing module 402, in this application, is mainly used to construct a three-dimensional spatial weight matrix based on all spatial coordinates, and then determine the spatial correlation difference of geological test data between each test monitoring point based on the three-dimensional spatial weight matrix and all geological test data; The processing module 402 in the present application is further used to perform spatial correlation screening on the geological test data of each test monitoring point by combining each spatial correlation difference with a preset geological mechanism rule to obtain spatial correlation abnormal data and spatial correlation normal data; The processing module 402 in the present application is further configured to input the spatially correlated normal data into an isolation forest model to perform local anomaly screening and output local anomaly data; The execution module 403 in this application is mainly used to fuse the spatial correlation anomaly data and the local anomaly data to generate the test anomaly data of the target area.

[0052] Each module in the geological test data anomaly detection system described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0053] In addition, in one embodiment, the present application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown in the figure. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store geological test data outlier detection data. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement a geological test data outlier detection method.

[0054] Those skilled in the art can understand that, Figure 5 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0055] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above geological test data outlier detection method embodiments.

[0056] In one embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to implement the steps in the above geological test data outlier detection method embodiments.

[0057] In one embodiment, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the above geological test data outlier detection method embodiments.

[0058] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0059] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0060] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for detecting outliers in geological test data, characterized in that: The steps include: Collect geological test data and corresponding spatial coordinates of each test monitoring point in the target area; Constructing a three-dimensional spatial weight matrix based on all spatial coordinates, and then determining the spatial correlation difference of the geological test data between each test monitoring point based on the three-dimensional spatial weight matrix and all geological test data; By combining the spatial correlation difference with the preset geological mechanism rules, the geological test data of each test monitoring point are spatially correlated and screened to obtain spatial correlation abnormal data and spatial correlation normal data; Inputting the spatially correlated normal data into an isolation forest model to perform local anomaly screening and outputting local anomaly data; The spatial correlation anomaly data and the local anomaly data are fused to generate test anomaly data of a target area.

2. The method according to claim 1, wherein Constructing a three-dimensional spatial weight matrix based on all spatial coordinates specifically includes: Calculate the spatial distance between each test monitoring point based on all spatial coordinates; The spatial weight values ​​between the corresponding test monitoring points are calculated based on the spatial distance between each test monitoring point, where the spatial weight value is inversely proportional to the spatial distance between the corresponding test monitoring points; All calculated spatial weight values ​​are used to construct a three-dimensional spatial weight matrix according to the spatial coordinate relationship.

3. The method according to claim 1, wherein Determining the spatial correlation difference of geological test data between various test monitoring points based on the three-dimensional spatial weight matrix and all geological test data specifically includes: Determine the spatial dependency of each test monitoring point based on all geological test data combined with the three-dimensional spatial weight matrix; Determining adjacent trend data of each test monitoring point based on the spatial dependency relationship of each test monitoring point and the geological test data; Determine the adjacent deviations of different monitoring parameters between the adjacent trend data of each test monitoring point and the corresponding geological test data; The spatial correlation difference of geological test data between each test monitoring point is calculated based on all adjacent deviations.

4. The method according to claim 1, wherein By combining the spatial correlation difference with the preset geological mechanism rules, the geological test data of each test monitoring point are spatially correlated and screened, and the spatial correlation abnormal data and spatial correlation normal data are obtained, including: Obtaining a preset geological mechanism rule, and then determining a difference threshold according to the preset geological mechanism rule; For each test monitoring point, comparing the spatial correlation difference of the test monitoring point with the difference threshold; When the spatial correlation difference is greater than or equal to the difference threshold, the geological test data of the test monitoring point is used as spatial correlation abnormal data; When the spatial correlation difference is less than the difference threshold, the geological test data of the test monitoring point is used as spatial correlation normal data, thereby obtaining spatial correlation abnormal data and spatial correlation normal data.

5. The method according to claim 1, wherein The spatially correlated normal data is input into the isolation forest model to perform local anomaly screening, and the output of local anomaly data specifically includes: Preprocessing the spatially correlated normal data; Build an Isolation Forest model based on the attention mechanism, where the attention mechanism enhances the ability to identify abnormal data by weighting specific input features; Input the preprocessed spatially correlated normal data into an isolation forest model based on an attention mechanism, and output an abnormal discrimination value for each test monitoring point in the spatially correlated normal data; For each test monitoring point in the spatially associated normal data, the geological test data corresponding to all test monitoring points whose abnormality discrimination values ​​are greater than a preset abnormality discrimination threshold are used as local abnormality data.

6. The method according to claim 1, wherein The step of fusing the spatial correlation anomaly data and the local anomaly data to generate the test anomaly data of the target area specifically includes: Combining the spatially correlated abnormal data and the local abnormal data, and performing visualization conversion on the combined abnormal data to obtain a three-dimensional visualization map; The three-dimensional visualization map is stored as test abnormality data.

7. The method according to claim 1, wherein The geological test data include: water content, porosity, thermal conductivity and chemical element content.

8. A geological test data outlier detection system, characterized in that: The system includes: The acquisition module is used to collect geological test data and corresponding spatial coordinates of each test monitoring point in the target area; A processing module is used to construct a three-dimensional spatial weight matrix based on all spatial coordinates, and then determine the spatial correlation difference of the geological test data between each test monitoring point based on the three-dimensional spatial weight matrix and all geological test data; The processing module is further used to perform spatial correlation screening on the geological test data of each test monitoring point by combining each spatial correlation difference with a preset geological mechanism rule to obtain spatial correlation abnormal data and spatial correlation normal data; The processing module is further configured to input the spatially correlated normal data into an isolation forest model to perform local anomaly screening and output local anomaly data; An execution module is used to fuse the spatial correlation anomaly data and the local anomaly data to generate test anomaly data of a target area.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the geological test data outlier detection method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the geological test data outlier detection method according to any one of claims 1 to 7 are implemented.

Images