Construction method and device of fault sample and computer equipment

Abstract

The embodiment of the application discloses a fault sample construction method and device and computer equipment, and belongs to the field of seismic data processing. The method comprises the following steps: superimposing a seismic profile and a fault image to obtain a superimposed image; for each fault line in the superimposed image, a plurality of grids through which each fault line passes are marked with a fault label respectively; a plurality of first areas are determined in the superimposed image, and a feature array and a label array of each first area are generated, the feature array comprising seismic data corresponding to each grid in the first area, and the label array comprising the fault label marked for each grid in the first area; and a fault sample is constructed based on the feature array and the label array of each first area. The above scheme can efficiently and quickly generate a large number of fault samples according to the seismic profile of different seismic trace sets and the corresponding fault image, thereby providing sufficient and accurate training samples for training of a fault identification model, and improving the efficiency and accuracy of training of the fault identification model.

Description

Technical Field

[0001] This application relates to the field of seismic data processing, and in particular to a method, apparatus, and computer device for constructing fault samples. Background Technology

[0002] Faults serve as both storage spaces for oil and gas and channels for their transfer and transportation; therefore, fault identification is a crucial component of seismic data interpretation. With the development of artificial intelligence, machine learning models are gradually replacing traditional fault identification methods. These machine learning models typically rely on abundant and accurate fault samples for training. Given the scarcity of fault samples, efficiently and accurately constructing such samples for model training remains a significant technical challenge. Summary of the Invention

[0003] This application provides a method, apparatus, and computer device for constructing tomographic samples, which can efficiently and rapidly generate a large number of tomographic samples. The technical solution is as follows:

[0004] On the one hand, a method for constructing tomographic samples is provided, the method comprising:

[0005] A superimposed image is obtained by overlaying seismic profiles and fault images. The seismic profile is obtained by seismic imaging processing of seismic data from multiple seismic traces. The seismic profile is divided into multiple grids. The fault image includes multiple fault lines, which are used to reflect the location of the fault on the seismic profile.

[0006] For each fault line in the overlay image, fault labels are marked on multiple grids that each fault line passes through, and the fault labels are used to indicate that there is a fault line on the grid.

[0007] Multiple first regions are determined in the overlay image, and a feature array and a label array are generated for each first region. The first region includes at least one grid labeled with the fault label. The feature array includes seismic data corresponding to each grid in the first region, and the label array includes the fault label labeled for each grid in the first region.

[0008] Based on the feature array and label array of each first region, a tomographic sample is constructed.

[0009] On the other hand, an apparatus for constructing tomographic samples is provided, the apparatus comprising:

[0010] The overlay module is used to overlay seismic profiles and fault images to obtain an overlay image. The seismic profile is obtained by performing seismic imaging processing on seismic data from multiple seismic traces. The seismic profile is divided into multiple grids. The fault image includes multiple fault lines, which are used to reflect the position of the fault on the seismic profile.

[0011] The annotation module is used to annotate multiple grids through which each fault line passes in the overlay image with fault labels, wherein the fault labels are used to indicate the presence of a fault line on the grid.

[0012] A determination module is used to determine multiple first regions in the overlay image and generate a feature array and a label array for each first region. The first region includes at least one grid labeled with the fault label. The feature array includes seismic data corresponding to each grid in the first region, and the label array includes the fault label labeled for each grid in the first region.

[0013] A construction module is used to construct tomographic samples based on the feature array and label array of each first region.

[0014] In some embodiments, the annotation module is configured to determine a preset region in the overlaid image, the preset region including a plurality of fault lines; for any fault line in the preset region, determine a plurality of grids through which the fault line passes; and annotate the plurality of grids through which the fault line passes with fault labels.

[0015] In some embodiments, the annotation module is configured to, for any fault line in the preset region, determine the second intersection coordinates of the fault line based on at least one of the endpoint coordinates, inflection point coordinates, and first intersection coordinates of the fault line, wherein the first intersection coordinates include the coordinates of at least one intersection point of the fault line with the boundary line of the preset region, and the second intersection coordinates include the coordinates of the intersection points of the fault line with the plurality of grids; and determine the plurality of grids through which the fault line passes based on the second intersection coordinates.

[0016] In some embodiments, the annotation module is used to annotate multiple grids through which the fault line passes with fault labels carrying the fault identifier, the fault identifier being used to identify the fault reflected by the fault line.

[0017] In some embodiments, the determining module is configured to determine a plurality of second regions from the overlay image based on a preset size and a preset coverage, wherein the preset size is used to indicate the size of the second region and the preset coverage is used to indicate the overlapping area of ​​two adjacent second regions; for any second region, the intersection point of the transverse midline of the second region with each fault line in the second region is determined, wherein the transverse midline is a horizontal line that divides the second region into two regions of equal area; for any intersection point, a first region centered on the intersection point is determined according to a preset length and a preset width.

[0018] In some embodiments, the determining module is further configured to, for any intersection point, determine multiple extension points of the intersection point based on the coordinates of the intersection point, wherein the distance between the extension points and the intersection point is less than a preset distance; and for any extension point, determine a first region centered on the extension point according to a preset length and a preset width.

[0019] In some embodiments, the determining module is configured to, for any first region, acquire seismic data corresponding to multiple grids in the first region; interpolate the seismic data corresponding to the multiple grids in the first region to obtain seismic data corresponding to each grid in the first region; and generate a feature array of the first region based on the seismic data corresponding to each grid in the first region.

[0020] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to implement the method for constructing tomographic samples as described above.

[0021] On the other hand, a computer-readable storage medium is provided, wherein at least one computer program is stored therein, the at least one computer program being loaded and executed by a processor to implement the method for constructing tomographic samples as described above.

[0022] On the other hand, a computer program product is provided, including a computer program loaded and executed by a processor to implement the method for constructing tomographic samples as described above.

[0023] This application provides a method for constructing fault samples, which can overlay seismic profiles and corresponding fault images to determine multiple grids along which the fault line in the fault image passes within the seismic profile, thus accurately identifying the fault region within the seismic profile. Fault labels are then labeled for the grids along which the fault line passes. Furthermore, based on the seismic data corresponding to each grid within any region of the seismic profile and the fault labels labeled for each grid, a fault sample for that region can be constructed. Through this method, a large number of fault samples can be generated efficiently and quickly based on seismic profiles and corresponding fault images from different seismic gathers, thereby providing sufficient and accurate training samples for training fault identification models and improving the efficiency and accuracy of training these models. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application;

[0026] Figure 2 This is a flowchart of a method for constructing a tomographic sample provided in an embodiment of this application;

[0027] Figure 3 This is a schematic diagram of an overlay image provided in an embodiment of this application;

[0028] Figure 4 This is a flowchart of another method for constructing tomographic samples provided in an embodiment of this application;

[0029] Figure 5 This is a schematic diagram of a fault line provided in an embodiment of this application;

[0030] Figure 6 This is a schematic diagram of a second region provided in an embodiment of this application;

[0031] Figure 7 This is a schematic diagram of a first region provided in an embodiment of this application;

[0032] Figure 8 This is a schematic diagram of a bilinear interpolation method provided in an embodiment of this application;

[0033] Figure 9 This is a flowchart illustrating the construction of a tomographic sample according to an embodiment of this application;

[0034] Figure 10 This is a schematic diagram of a tomographic identification method provided in an embodiment of this application;

[0035] Figure 11 This is a schematic diagram of a device for constructing tomographic samples provided in an embodiment of this application;

[0036] Figure 12 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0038] It is understood that the terms "first," "second," etc., used in this application may be used to describe various concepts herein, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of this application, the coordinates of the first intersection point may be referred to as the coordinates of the second intersection point, and similarly, the coordinates of the second intersection point may be referred to as the coordinates of the first intersection point.

[0039] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the earthquake data involved in this application was obtained with full authorization.

[0040] The following is a brief introduction to the terminology used in this application.

[0041] Fault identification: In the field of seismic exploration, fault identification refers to the process of determining the location, shape, scale, and properties of faults. Fault identification is a crucial component of seismic data interpretation. Since faults serve as both storage spaces for oil and gas and channels for their transfer and transportation, fault identification provides vital theoretical support for seismic exploration and oil and gas extraction. Traditional fault identification methods rely on interpreters identifying faults based on discontinuities in the reflection phase axes on seismic profiles.

[0042] Fault: A fault is a structural feature in the Earth's crust that fractures under stress, resulting in significant relative displacement of rock blocks on either side of the fracture surface. Faults vary in size, ranging from hundreds of kilometers along their strike to only tens of centimeters. Faults are widely developed in the Earth's crust and are one of its important structural features.

[0043] Fault lines: Lines used to indicate the location of a fault on a seismic profile. Fault lines are the visual representation of a fault on a two-dimensional plane (such as a seismic profile). The reflection phase axes on both sides of the fault line usually show characteristics such as discontinuity, interruption, or abrupt angular changes. These discontinuous features are important for identifying faults.

[0044] Seismic profile: An image showing the vertical variation of underground geological structures, typically obtained through seismic exploration methods. Seismic profiles can display the reflection patterns of different strata. In seismic profiles, faults typically exhibit discontinuities such as breaks, twists, or abrupt terminations in the reflection phase axes.

[0045] Fault image: An image that includes multiple fault lines. Fault images typically correspond to seismic profiles, and the fault lines in a fault image accurately reflect the location of the fault on the seismic profile.

[0046] The implementation environment of the embodiments of this application is described below.

[0047] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application. See also... Figure 1 The implementation environment includes a terminal 101 and a server 102. The terminal 101 can be connected to the server 102 via a wireless network or a wired network.

[0048] Optionally, terminal 101 can be at least one of devices such as smartphones, desktop computers, laptops, and tablet computers. In some embodiments, terminal 101 can construct multiple fault samples based on seismic profiles and fault images. The seismic profiles and fault images can be stored locally on terminal 101 or uploaded to terminal 101 by other devices; this embodiment does not impose any limitations on this. The fault samples are used to train a fault identification model. The trained fault identification model can accurately identify possible underground faults based on the input seismic data.

[0049] In some embodiments, an application may be installed and run on terminal 101 for constructing fault samples. This application is associated with server 102, which provides background services. Accordingly, users can log in to the application through terminal 101 and upload seismic profiles and fault images to server 102, which then constructs fault samples based on the received seismic profiles and fault images.

[0050] Optionally, server 102 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. In some embodiments, server 102 undertakes the main computing work, and terminal 101 undertakes the secondary computing work; or, server 102 undertakes the secondary computing work, and terminal 101 undertakes the main computing work; or, server 102 and terminal 101 collaborate on computing using a distributed computing architecture.

[0051] Terminal 101 can refer to one of a plurality of terminals; this embodiment uses terminal 101 as an example. Those skilled in the art will understand that the number of terminals can be more or less. For example, there may be several terminals, or dozens or hundreds of terminals, or even more. This application embodiment does not limit the number of terminals or the type of device.

[0052] Figure 2 This is a flowchart illustrating a method for constructing a tomographic sample according to an embodiment of this application. This embodiment is executed by a terminal as an example. (See also...) Figure 2 The method includes:

[0053] 201. The terminal superimposes the seismic profile and fault images to obtain the superimposed image. The seismic profile is divided into multiple grids, and the fault image includes multiple fault lines, which are used to reflect the position of the fault on the seismic profile.

[0054] In this embodiment, a seismic profile, as a form of displaying seismic data, is typically obtained by performing seismic imaging processing on seismic data from multiple seismic traces. A seismic profile can visually demonstrate changes in underground geological structures, presenting information such as stratigraphic interfaces and geological formations at different depths in the form of a two-dimensional image. For example, in two-dimensional seismic exploration, multiple geophones are deployed along the seismic survey line to acquire seismic data. After seismic imaging processing, this seismic data is plotted with the travel time of seismic waves as the vertical axis and the distance along the survey line as the horizontal axis, forming a two-dimensional seismic profile. Seismic imaging processing includes, but is not limited to, stacking, migration, and deconvolution.

[0055] To facilitate data processing of seismic profiles, they can be divided into multiple grids. Grid partitioning is an effective method for data partitioning and processing in seismic data processing and interpretation. For example, in a two-dimensional seismic profile, grids can be created using time (vertical axis) and distance (horizontal axis). The time range corresponding to each grid defines the travel time range of the seismic data contained within that grid, and the distance range corresponding to each grid defines the location of the seismic data along the seismic line contained within that grid.

[0056] Fault images are images corresponding to seismic profiles. They are used to visually represent the location of faults on the seismic profile using fault lines. The geometry of the fault lines can intuitively reflect the length and strike of the fault. Optionally, interpreters can identify faults and mark fault lines on the seismic profile based on the discontinuity of reflected phase axes, resulting in a fault image that includes multiple fault lines.

[0057] In some embodiments, the seismic profile and fault image are the same size. The terminal overlays the fault image onto the seismic profile to obtain a superimposed image. Figure 3 This is a schematic diagram of an overlay image provided in an embodiment of this application. For example... Figure 3 As shown, the line located above seismic profile 301 is the fault line. 302 is an example fault line.

[0058] 202. For each fault line in the overlay image, the terminal labels the multiple grids that each fault line passes through.

[0059] In this embodiment, since the seismic profile is divided into multiple grids, after obtaining the overlay image, the terminal can determine the multiple grids that each fault line passes through and label these grids with fault tags. The fault tags indicate the presence of fault lines on the grids. By labeling the grids with fault tags, the presence of fault lines on the grids can be visually represented, that is, the locations of faults on the seismic profile are marked using fault tags, which helps in the subsequent generation of fault samples based on the grids labeled with fault tags.

[0060] 203. The terminal determines multiple first regions in the overlay image and generates a feature array and a label array for each first region.

[0061] In this embodiment, the first region includes at least one grid labeled with fault tags. Optionally, the first regions of adjacent chains typically do not overlap. Alternatively, there may be partial overlap between two adjacent first regions; this embodiment does not limit this. After the terminal determines multiple first regions, for any given first region, the terminal acquires the seismic data corresponding to each grid in that first region and constructs a feature array for that first region based on the acquired seismic data. The terminal can also acquire the fault tags labeled on each grid in that first region and construct a tag array for that first region based on the acquired fault tags. Optionally, for any grid, if the grid is not labeled with a fault tag, the terminal can set the fault tag of that grid to 0.

[0062] 204. The terminal constructs tomographic samples based on the feature array and label array of each first region.

[0063] In this embodiment, after the terminal constructs a set of fault samples corresponding to each first region in the overlay image based on the feature array and label array, the set of fault samples includes multiple corresponding feature arrays and multiple label arrays. Subsequently, a fault identification model is trained based on these fault samples, enabling the model to learn the characteristics of seismic data containing faults during training. The trained fault identification model can then accurately identify faults based on seismic data, providing accurate theoretical support for subsequent seismic exploration and oil and gas extraction.

[0064] This application provides a method for constructing fault samples, which can overlay seismic profiles and corresponding fault images to determine multiple grids along which the fault line in the fault image passes within the seismic profile, thus accurately identifying the fault region within the seismic profile. Fault labels are then labeled for the grids along which the fault line passes. Furthermore, based on the seismic data corresponding to each grid within any region of the seismic profile and the fault labels labeled for each grid, a fault sample for that region can be constructed. Through this method, a large number of fault samples can be generated efficiently and quickly based on seismic profiles and corresponding fault images from different seismic gathers, thereby providing sufficient and accurate training samples for training fault identification models and improving the efficiency and accuracy of training these models.

[0065] The above Figure 2 The main flow of the method for constructing a fault sample provided in the embodiments of this application is illustrated. The construction scheme of the fault sample will be described in detail below. Figure 4 This is a flowchart of another method for constructing tomographic samples provided in an embodiment of this application. This method is executed by a terminal. See [link to flowchart]. Figure 4 The method includes:

[0066] 401. The terminal superimposes the seismic profile and fault images to obtain the superimposed image. The seismic profile is divided into multiple grids, and the fault image includes multiple fault lines, which are used to reflect the position of the fault on the seismic profile.

[0067] In this embodiment, the process of overlaying seismic profiles and fault images on the terminal is the same as step 201 described above, and will not be repeated here.

[0068] It should be further noted that in the process of generating seismic profiles, the fault interpretation directions typically include inline and crossline directions. The inline direction refers to the direction parallel to the seismic survey line, while the crossline direction refers to the direction perpendicular to the seismic survey line. In 3D seismic exploration, seismic imaging processing of seismic data acquired by multiple seismic detectors arranged along the inline direction can generate an inline-oriented seismic profile; similarly, seismic imaging processing of seismic data acquired by multiple seismic detectors arranged along the crossline direction can generate a crossline-oriented seismic profile. In the embodiments of this application, the superimposed seismic profiles can be either inline or crossline-oriented, and this application does not impose any limitation on this.

[0069] 402. The terminal determines a preset region in the overlaid image, and the preset region includes multiple fault lines.

[0070] In this embodiment, the preset region is the area to be processed in the overlay image, that is, the area actually used in the overlay image during the construction of the fault sample. The preset region includes multiple fault lines. By defining the preset region as including multiple fault lines, areas that do not contain faults or contain few faults can be removed in advance before constructing the fault sample, avoiding the construction of fault samples based on areas with few fault lines, thereby ensuring that the fault sample contains more faults for the fault recognition model to learn. Optionally, the preset region can be manually determined by the interpreter. The interpreter inputs the coordinates of multiple vertices of the preset region to the terminal, and the terminal determines the preset region enclosed by the coordinates of multiple vertices in the overlay image.

[0071] 403. For any fault line in the preset area, the terminal determines the multiple grids through which the fault line passes.

[0072] In this embodiment, since the seismic profile is divided into multiple grids and fault images are overlaid on the upper layer of the seismic profile, the terminal can determine the grids traversed by each fault line within a preset area based on the overlaid images. The process of the terminal determining the multiple grids traversed by any fault line within the preset area is described below using this example.

[0073] In some embodiments, for any fault line in a preset region, the terminal determines the coordinates of a second intersection point of the fault line based on at least one of the fault line's endpoint coordinates, inflection point coordinates, and first intersection point coordinates. The endpoint coordinates include the coordinates of the two endpoints of the fault line. The inflection point coordinates include the coordinates of the inflection point of the fault line. An inflection point of a fault line is a point where the fault line's direction changes significantly. For example, when the fault line's direction suddenly changes from one direction to another, this turning point is the fault line's inflection point. The first intersection point coordinates include the coordinates of at least one intersection point between the fault line and the boundary line of the preset region. For example, see the above. Figure 3 ,exist Figure 3 In the case of the superimposed image representing the preset region, fault line 301 intersects the boundary line of the preset region at two points, located at the upper and right boundaries of the preset region, respectively. The coordinates of the second intersection point include the coordinates of the intersection points of the fault line with multiple grids. Based on the coordinates of the second intersection point, the terminal can determine the multiple grids through which the fault line passes. Since the endpoint coordinates, inflection point coordinates, and first intersection point coordinates of the fault line can accurately represent the position of the fault line in the superimposed image, the intersection point coordinates of the fault line with multiple grids in the superimposed image can be quickly determined using at least one of the aforementioned coordinates, thereby accurately determining the multiple grids through which the fault line passes.

[0074] The following is combined Figure 5 The schematic diagram of the fault line shown illustrates the process of determining the coordinates of the intersection points of the fault line with multiple grids based on the endpoint coordinates, using the endpoint coordinates as an example. Figure 5 As shown, 501 represents any fault line within the preset area, and the grid filled with diagonal lines represents the grid through which fault line 501 passes. Black dots indicate the positions of the intersection points of fault line 501 and the grid. If the coordinates of the two endpoints of fault line 501 are (x1, y1) and (x2, y2), then the ordinate y of the intersection point of fault line 501 and grid line x can be expressed as y1 + (x - x1) * (y2 - y1) / (x2 - x1). Therefore, the coordinates of the intersection point of the fault line and grid line x are (x, y). It should be noted that... Figure 5 The example below uses a single grid line x as an example. Grid line x can be any horizontal line. After obtaining the coordinates (x, y) of a second intersection point of the fault line, the terminal can determine the two grids through which the fault line passes using the following formula.

[0075] m11 = ceil(y + 0.1)

[0076] m21 = floor(y + 0.1)

[0077] Here, m11 and m21 are the two grids through which the fault line passes. `ceil` is the floor function, and `floor` is the floor function. For example, `ceil(3.1)` returns 4, and `floor(3.1)` returns 3. By rounding the ordinate of the intersection point coordinates upwards or downwards using the above formulas, the two grids adjacent to the second intersection point coordinates in the vertical direction can be quickly found. Correspondingly, in the horizontal direction, the terminal can also quickly find the two grids adjacent to the second intersection point coordinates in the horizontal direction using `ceil(x+0.1)` and `floor(x+0.1)`.

[0078] 404. The terminal marks multiple grids through which the fault line passes with fault labels. The fault labels are used to indicate the presence of fault lines on the grids.

[0079] In this embodiment, after the terminal determines any grid through which the fault line passes, it can label that grid with a fault label. By labeling the grid through which the fault line passes with fault labels, the presence of a fault line on that grid can be intuitively indicated by the fault labels. That is, the location of a fault on the seismic profile is marked by the fault labels, which helps to generate fault samples based on the grids labeled with fault labels.

[0080] In some embodiments, the terminal can label multiple grids traversed by a fault line with fault tags carrying fault identifiers. The fault identifier is used to identify the fault reflected by the fault line. For example, the fault identifier can be "Fault 1", "Fault 2", etc. Accordingly, if a fault line represents Fault 1, the terminal can label all grids traversed by that fault line with the fault tag "Fault 1". By labeling grids with fault tags carrying fault identifiers, not only can the presence of a fault line on the grid be indicated by the fault tag, but the fault reflected by that fault line can also be indicated by the fault tag, further increasing the amount of information conveyed by the fault tag.

[0081] 405. The terminal determines multiple first regions in the preset area of ​​the overlay image and generates a feature array and a label array for each first region.

[0082] In this embodiment, the first region includes at least one grid labeled with fault tags. The feature array of the first region includes seismic data corresponding to each grid in the first region. The label array of the first region includes the fault tags labeled for each grid in the first region. It should be noted that, for any grid in the first region, if the grid is not labeled with a fault tag, the terminal can set the fault tag of that grid to 0 in the label array.

[0083] For example, if the first region includes M*N grids, then the feature array and label array of the first region are both two-dimensional arrays with dimensions M*N. Each element in the two-dimensional array is used to represent the seismic data corresponding to the grid at the same location, or the fault label marked by the grid at the same location.

[0084] The process of determining multiple first regions in a preset area of ​​an overlay image by the terminal is explained below through the following steps (1)-(3).

[0085] (1) The terminal determines multiple second regions from a preset area of ​​the overlay image based on a preset size and a preset coverage rate. The preset size indicates the size of the second region. For example, the preset size can be a preset width, in which case the width of the second region is the preset width. The preset coverage rate indicates the overlap area between two adjacent second regions. The higher the preset coverage rate, the greater the overlap area between two adjacent second regions. The specific values ​​of the preset size and preset coverage rate can be set according to requirements, and this embodiment does not limit this. Figure 6 This is a schematic diagram of a second region provided in an embodiment of this application, such as... Figure 6 As shown, the area marked with a dashed box is the second region determined from the overlay image. The second region 601 and the second region 602 are adjacent, and they have a partially overlapping area.

[0086] (2) For any second region, the terminal determines the intersection point of the transverse midline of the second region with each fault line in the second region. The transverse midline is the line that divides the second region into two regions of equal area. In other words, the transverse midline can divide the second region into two regions of equal area, upper and lower. See above. Figure 6 The second region 601 includes multiple dots, which are the intersections of the transverse midline of the second region 601 and each fault line in the second region 601.

[0087] (3) For any intersection point, the terminal determines a first region centered on that intersection point according to a preset length and a preset width. The preset length and preset width can be set according to actual needs, and this embodiment does not limit them. Figure 7 This is a schematic diagram of a first region provided in an embodiment of this application, such as... Figure 7 As shown, the area marked with a rectangle is the defined first region. To clearly and intuitively display the first region, in Figure 7 The first region 701, the first region 702 and the first region 703 are specially marked.

[0088] Through the above steps (1)-(3), the terminal can determine the intersection points of multiple fault lines and transverse midlines in each second region, and then determine multiple first regions centered on the intersection points, thereby ensuring that fault lines exist in the first regions and thus ensuring the accuracy of constructing fault samples based on the first regions.

[0089] In some embodiments, for any intersection point, the terminal can also determine multiple extension points of the intersection point based on its coordinates. An extension point is a point whose distance from the intersection point is less than a preset distance. The extension points of an intersection point can be located around the intersection point, such as on its left or right sides. For any extension point, the terminal can also determine a first region centered on that extension point according to a preset length and a preset width, thereby obtaining multiple first regions. By determining multiple first regions based on the extension points of the intersection point, a sufficient number of first regions can be determined, thus enabling the construction of a sufficient number of tomographic samples.

[0090] Additionally, it should be noted that when the terminal determines the first region centered on the intersection point according to the preset length and preset width, if the first region exceeds the boundary of the preset region in the overlay image, or if the first region exceeds the boundary of the overlay image, the terminal can remove the part that exceeds the boundary in the first region and retain the part that does not exceed the boundary, thereby ensuring the validity of the data in the first region.

[0091] The above embodiments mainly describe the process by which the terminal determines multiple first regions within a preset area of ​​an overlaid image. The process by which the terminal generates a feature array of the first regions is described below.

[0092] In some embodiments, for any first region, the terminal acquires seismic data corresponding to multiple grids within the first region. Then, the terminal interpolates the seismic data corresponding to the multiple grids in the first region to obtain seismic data corresponding to each grid in the first region. Optionally, the terminal may use a bilinear interpolation algorithm to interpolate the seismic data corresponding to the multiple grids. Then, the terminal generates a feature array for the first region based on the seismic data corresponding to each grid in the first region. For example, if the first region includes 128*128 grids, the feature array for the first region is a two-dimensional array with dimensions of 128*128. Each element in the two-dimensional array can represent the seismic data corresponding to the grid at the same location. By interpolating the seismic data, the continuity of the seismic data can be ensured, avoiding ladder-like defects in the seismic data interpretation results.

[0093] The following section uses the bilinear interpolation algorithm as an example to illustrate the process of interpolating seismic data corresponding to multiple grids using the bilinear interpolation algorithm at the terminal. Figure 8 This is a schematic diagram of a bilinear interpolation method provided in an embodiment of this application, such as... Figure 8As shown, the coordinates of R11 are (x1, y1), R21 are (x2, y1), R12 are (x1, y2), and R22 are (x2, y2). In the X-axis direction, the seismic data f(R1) at point R1 can be obtained using the linear interpolation algorithm as (x2-x) / (x2-x1)f(R11)+(x-x1) / (x2-x1)*f(R21); the seismic data f(R2) at point R2 can be obtained using the linear interpolation algorithm as (x2-x1) / (x2-x)*f(R12)+(x-x1) / (x2-x1)*f(R22). Here, x represents the x-coordinate of R1 and R2, and f(R11), f(R21), (R12), and f(R22) represent the seismic data at points R11, R21, R12, and R22, respectively. Then, the seismic data for point P is calculated using a linear interpolation algorithm: f(P) = (y2-y) / (y2-y1)*f(R1) + (y-y1) / (y2-y1)*f(R2). Here, y is the ordinate of point P.

[0094] 406. The terminal constructs tomographic samples based on the feature array and label array of each first region.

[0095] In this embodiment, after obtaining the feature array and label array of each first region in the overlay image, the terminal can construct a set of fault samples corresponding to the overlay image. Each fault sample includes multiple corresponding feature arrays and multiple label arrays. Then, following steps 401-406 above, the terminal can construct multiple sets of fault samples based on other seismic profiles and the corresponding fault images, thereby obtaining a fault sample set including multiple sets of fault samples.

[0096] To more clearly illustrate the process of constructing tomographic samples, the following section combines... Figure 9 The flowchart shown above illustrates the overall process of constructing a tomographic sample. Figure 9As shown, the terminal first overlays the seismic profile and its corresponding fault image to obtain a superimposed image. Then, the terminal identifies multiple grids along each fault line in the superimposed image and labels these grids with fault tags. Next, the terminal divides the superimposed image into multiple computational regions, also known as the second region; then, within each computational region, the terminal identifies multiple sample regions, also known as the first region. The process of determining the computational region and the sample region within the computational region is described in step 405 above and will not be repeated here. Then, the terminal constructs a feature array for each sample region based on the seismic data corresponding to each grid; and constructs a label array for each sample region based on the fault tags labeled for each grid. Finally, the terminal constructs a set of fault samples based on the feature array and label array for each sample region. The terminal then performs the same process for the next seismic profile, thus constructing a set of fault samples based on each seismic profile and its corresponding fault image, ultimately obtaining a fault sample set composed of multiple sets of fault samples.

[0097] It should also be noted that training the fault identification model with the fault sample set obtained in the above manner enables the fault identification model to learn the characteristics of seismic data containing faults during the training process. The trained fault identification model can accurately identify faults based on seismic data, which not only improves the efficiency and accuracy of fault identification, but also provides accurate theoretical support for subsequent seismic exploration and oil and gas extraction. Figure 10 This is a schematic diagram of a tomographic identification method provided in an embodiment of this application. Figure 10 (a) in the image is a fault image with fault lines marked. Figure 10 (b) in the figure is a fault prediction image obtained by the fault identification model after processing the seismic data. By comparing the two images, it can be seen that the fault sample constructed by the method provided in the embodiment of this application to train the fault identification model enables the fault identification model to accurately identify faults based on the seismic data.

[0098] This application provides a method for constructing fault samples, which can overlay seismic profiles and corresponding fault images to determine multiple grids along which the fault line in the fault image passes within the seismic profile, thus accurately identifying the fault region within the seismic profile. Fault labels are then labeled for the grids along which the fault line passes. Furthermore, based on the seismic data corresponding to each grid within any region of the seismic profile and the fault labels labeled for each grid, a fault sample for that region can be constructed. Through this method, a large number of fault samples can be generated efficiently and quickly based on seismic profiles and corresponding fault images from different seismic gathers, thereby providing sufficient and accurate training samples for training fault identification models and improving the efficiency and accuracy of training these models.

[0099] Figure 11This is a schematic diagram of a tomographic sample construction device provided in an embodiment of this application. See also... Figure 11 The device includes: an overlay module 1101, an annotation module 1102, a determination module 1103, and a construction module 1104.

[0100] The overlay module 1101 is used to overlay seismic profiles and fault images to obtain an overlay image. The seismic profile is obtained by performing seismic imaging processing on seismic data from multiple seismic traces. The seismic profile is divided into multiple grids. The fault image includes multiple fault lines, which are used to reflect the position of the fault on the seismic profile.

[0101] The annotation module 1102 is used to annotate the multiple grids that each fault line passes through in the superimposed image with fault labels. The fault labels are used to indicate that there is a fault line on the grid.

[0102] The determination module 1103 is used to determine multiple first regions in the overlay image and generate a feature array and a label array for each first region. The first region includes at least one grid labeled with fault labels, the feature array includes seismic data corresponding to each grid in the first region, and the label array includes fault labels labeled for each grid in the first region.

[0103] Module 1104 is used to construct tomographic samples based on the feature array and label array of each first region.

[0104] In some embodiments, the annotation module 1102 is used to determine a preset region in the overlay image, the preset region including multiple fault lines; for any fault line in the preset region, determine multiple grids through which the fault line passes; and annotate the multiple grids through which the fault line passes with fault labels.

[0105] In some embodiments, the annotation module 1102 is used to determine the second intersection coordinates of any fault line in a preset region based on at least one of the endpoint coordinates, inflection point coordinates, and first intersection coordinates of the fault line. The first intersection coordinates include the coordinates of at least one intersection point between the fault line and the boundary line of the preset region, and the second intersection coordinates include the coordinates of the intersection points between the fault line and multiple grids. Based on the second intersection coordinates, the multiple grids through which the fault line passes are determined.

[0106] In some embodiments, the annotation module 1102 is used to annotate multiple grids through which the fault line passes with fault labels carrying fault identifiers, the fault identifiers being used to identify the faults reflected by the fault line.

[0107] In some embodiments, the determining module 1103 is used to determine a plurality of second regions from the overlay image based on a preset size and a preset coverage, wherein the preset size is used to indicate the size of the second region and the preset coverage is used to indicate the overlapping area of ​​two adjacent second regions; for any second region, the intersection point of the transverse midline of the second region with each fault line in the second region is determined, wherein the transverse midline is a horizontal line that divides the second region into two regions of equal area; for any intersection point, a first region centered on the intersection point is determined according to a preset length and a preset width.

[0108] In some embodiments, the determining module 1103 is further configured to, for any intersection point, determine multiple extension points of the intersection point based on the coordinates of the intersection point, wherein the distance between the extension points and the intersection point is less than a preset distance; and for any extension point, determine a first region centered on the extension point according to a preset length and a preset width.

[0109] In some embodiments, the determining module 1103 is configured to, for any first region, acquire seismic data corresponding to multiple grids in the first region; interpolate the seismic data corresponding to multiple grids in the first region to obtain seismic data corresponding to each grid in the first region; and generate a feature array of the first region based on the seismic data corresponding to each grid in the first region.

[0110] This application provides a fault sample construction apparatus that can overlay seismic profiles and corresponding fault images to determine multiple grids along which the fault lines in the fault images pass within the seismic profiles, thus accurately identifying the fault regions within the seismic profiles. Fault labels are then labeled for the grids along which the fault lines pass. Based on the seismic data corresponding to each grid within any region of the seismic profile and the fault labels labeled for each grid, a fault sample for that region can be constructed. Through this method, a large number of fault samples can be generated efficiently and rapidly based on seismic profiles and corresponding fault images from different seismic gathers, thereby providing sufficient and accurate training samples for training fault identification models and improving the efficiency and accuracy of training these models.

[0111] It should be noted that the tomographic sample construction apparatus provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the terminal can be divided into different functional modules to complete all or part of the functions described above. In addition, the tomographic sample construction apparatus and the tomographic sample construction method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0112] This application also provides a terminal, which includes a processor and a memory. The memory stores at least one computer program, which is loaded and executed by the processor to implement the method for constructing tomographic samples described in the above embodiments.

[0113] Figure 12 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application.

[0114] Terminal 1200 includes a processor 1201 and a memory 1202.

[0115] Processor 1201 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1201 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1201 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1201 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1201 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0116] The memory 1202 may include one or more computer-readable storage media, which may be non-transitory. The memory 1202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1202 are used to store at least one computer program, which is used by the processor 1201 to implement the method for constructing tomographic samples provided in the method embodiments of this application.

[0117] In some embodiments, the terminal 1200 may also optionally include: a peripheral device interface 1203 and at least one peripheral device. The processor 1201, memory 1202, and peripheral device interface 1203 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1203 via a bus, signal line, or circuit board. Optionally, the peripheral device includes at least one of: a radio frequency circuit 1204, a display screen 1205, a camera assembly 1206, an audio circuit 1207, and a power supply 1208.

[0118] Peripheral device interface 1203 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1201 and memory 1202. In some embodiments, processor 1201, memory 1202 and peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1201, memory 1202 and peripheral device interface 1203 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0119] The radio frequency (RF) circuit 1204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1204 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1204 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1204 can communicate with other devices via at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: metropolitan area networks (MANs), various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks (WLANs), and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1204 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0120] Display screen 1205 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1205 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1201 for processing. In this case, display screen 1205 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1205, disposed on the front panel of terminal 1200; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1200 or in a folded design; in still other embodiments, display screen 1205 may be a flexible display screen, disposed on a curved or folded surface of terminal 1200. Furthermore, display screen 1205 may also be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1205 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0121] The camera assembly 1206 is used to acquire images or videos. Optionally, the camera assembly 1206 includes a front-facing camera and a rear-facing camera. The front-facing camera is disposed on the front panel of the terminal 1200, and the rear-facing camera is disposed on the back of the terminal 1200. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1206 may also include a flash. The flash may be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cool light flash, which can be used for light compensation at different color temperatures.

[0122] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1201 for processing, or input to the radio frequency circuit 1204 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1200. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1201 or the radio frequency circuit 1204 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1207 may also include a headphone jack.

[0123] Power supply 1208 is used to power the various components in terminal 1200. Power supply 1208 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1208 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0124] In some embodiments, the terminal 1200 further includes one or more sensors 1209. The one or more sensors 1209 include, but are not limited to: an acceleration sensor 1120, a gyroscope sensor 1211, a pressure sensor 1212, an optical sensor 1213, and a proximity sensor 1214.

[0125] Accelerometer 1120 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established with terminal 1200. For example, accelerometer 1120 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1201 can control display screen 1205 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1120. Accelerometer 1120 can also be used for games or for acquiring user motion data.

[0126] The gyroscope sensor 1211 can detect the orientation and rotation angle of the terminal 1200. The gyroscope sensor 1211 can work in conjunction with the accelerometer sensor 1120 to collect the user's 3D movements on the terminal 1200. Based on the data collected by the gyroscope sensor 1211, the processor 1201 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0127] The pressure sensor 1212 can be disposed on the side bezel of the terminal 1200 and / or on the lower layer of the display screen 1205. When the pressure sensor 1212 is disposed on the side bezel of the terminal 1200, it can detect the user's grip signal on the terminal 1200, and the processor 1201 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1212. When the pressure sensor 1212 is disposed on the lower layer of the display screen 1205, the processor 1201 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1205. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0128] Optical sensor 1213 is used to collect ambient light intensity. In one embodiment, processor 1201 can control the display brightness of display screen 1205 based on the ambient light intensity collected by optical sensor 1213. Optionally, when the ambient light intensity is high, the display brightness of display screen 1205 is increased; when the ambient light intensity is low, the display brightness of display screen 1205 is decreased. In another embodiment, processor 1201 can also dynamically adjust the shooting parameters of camera assembly 1206 based on the ambient light intensity collected by optical sensor 1213.

[0129] The proximity sensor 1214, also known as a distance sensor, is installed on the front panel of the terminal 1200. The proximity sensor 1214 is used to detect the distance between the user and the front of the terminal 1200. In one embodiment, when the proximity sensor 1214 detects that the distance between the user and the front of the terminal 1200 is gradually decreasing, the processor 1201 controls the display screen 1205 to switch from a screen-on state to a screen-off state; when the proximity sensor 1214 detects that the distance between the user and the front of the terminal 1200 is gradually increasing, the processor 1201 controls the display screen 1205 to switch from a screen-off state to a screen-on state.

[0130] Those skilled in the art will understand that Figure 12 The structure shown does not constitute a limitation on terminal 1200 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0131] This application also provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to implement the method for constructing tomographic samples as described in the above embodiments.

[0132] This application also provides a computer program product, including a computer program loaded and executed by a processor to implement the method for constructing tomographic samples as described in the above embodiments.

[0133] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0134] The above are merely optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present application should be included within the protection scope of the present application.

Claims

1. A method for constructing a tomographic sample, characterized in that, The method includes: A superimposed image is obtained by overlaying seismic profiles and fault images. The seismic profile is obtained by seismic imaging processing of seismic data from multiple seismic traces. The seismic profile is divided into multiple grids. The fault image includes multiple fault lines, which are used to reflect the location of the fault on the seismic profile. For each fault line in the overlay image, fault labels are marked on multiple grids that each fault line passes through, and the fault labels are used to indicate that there is a fault line on the grid. Multiple first regions are determined in the overlay image, and a feature array and a label array are generated for each first region. The first region includes at least one grid labeled with the fault label. The feature array includes seismic data corresponding to each grid in the first region, and the label array includes the fault label labeled for each grid in the first region. Based on the feature array and label array of each first region, a tomographic sample is constructed.

2. The method according to claim 1, characterized in that, For each fault line in the overlay image, the fault labels are marked on multiple grids along which each fault line passes, including: A preset region is determined in the overlaid image, the preset region including a plurality of the fault lines; For any fault line in the preset region, determine the multiple grids through which the fault line passes; The fault labels are marked on the multiple grids through which the fault line passes.

3. The method according to claim 2, characterized in that, For any fault line in the preset region, determining the multiple grids through which the fault line passes includes: For any fault line in the preset region, the second intersection coordinates of the fault line are determined based on at least one of the endpoint coordinates, inflection point coordinates, and first intersection coordinates of the fault line. The first intersection coordinates include the coordinates of at least one intersection point of the fault line with the boundary line of the preset region, and the second intersection coordinates include the coordinates of the intersection points of the fault line with the plurality of grids. Based on the coordinates of the second intersection point, the multiple grids through which the fault line passes are determined.

4. The method according to claim 2, characterized in that, The step of labeling the fault along multiple grids includes: The fault line is marked with multiple grid markings carrying the fault identifier, which is used to identify the fault reflected by the fault line.

5. The method according to claim 1, characterized in that, Determining multiple first regions in the overlay image includes: Based on a preset size and a preset coverage, a plurality of second regions are determined from the overlay image. The preset size is used to indicate the size of the second region, and the preset coverage is used to indicate the overlap area of ​​two adjacent second regions. For any second region, determine the intersection point of the transverse midline of the second region with each fault line in the second region, wherein the transverse midline is a transverse line that divides the second region into two regions of equal area; For any intersection point, a first region centered on the intersection point is determined according to a preset length and a preset width.

6. The method according to claim 5, characterized in that, The method further includes: For any intersection point, based on the coordinates of the intersection point, multiple extension points of the intersection point are determined, and the distance between the extension points and the intersection point is less than a preset distance; For any extension point, a first region centered on the extension point is determined according to a preset length and a preset width.

7. The method according to claim 1, characterized in that, The generation of the feature array for each first region includes: For any first region, acquire seismic data corresponding to multiple grids within the first region; Interpolate the seismic data corresponding to multiple grids in the first region to obtain the seismic data corresponding to each grid in the first region; Based on the seismic data corresponding to each grid in the first region, a feature array for the first region is generated.

8. A device for constructing a tomographic sample, characterized in that, The device includes: The overlay module is used to overlay seismic profiles and fault images to obtain an overlay image. The seismic profile is obtained by performing seismic imaging processing on seismic data from multiple seismic traces. The seismic profile is divided into multiple grids. The fault image includes multiple fault lines, which are used to reflect the position of the fault on the seismic profile. The annotation module is used to annotate multiple grids through which each fault line passes in the overlay image with fault labels, wherein the fault labels are used to indicate the presence of a fault line on the grid. A determination module is used to determine multiple first regions in the overlay image and generate a feature array and a label array for each first region. The first region includes at least one grid labeled with the fault label. The feature array includes seismic data corresponding to each grid in the first region, and the label array includes the fault label labeled for each grid in the first region. A construction module is used to construct tomographic samples based on the feature array and label array of each first region.

9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one computer program, which is loaded and executed by the processor to implement the method for constructing a tomographic sample as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to implement the method for constructing a tomographic sample as described in any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, The computer program is loaded and executed by a processor to implement the method for constructing a tomographic sample as described in any one of claims 1 to 7.

Images