Relative geological time prediction method and device, computer equipment and storage medium

Abstract

The application provides a relative geologic time prediction method and device, computer equipment and a storage medium, and belongs to the technical field of oil and gas seismic exploration and seismic interpretation. The method comprises the following steps: segmenting block seismic data of a target block to be predicted to obtain a plurality of block sub-data of the target block; training a relative geologic time prediction model based on the plurality of target block sub-data, wherein the target block sub-data is block sub-data of part of seismic data including at least one first horizon in the plurality of block sub-data; predicting the plurality of block sub-data based on the trained relative geologic time prediction model to obtain the predicted relative geologic time of each horizon in the plurality of block sub-data; and merging the predicted relative geologic time of each horizon in the plurality of block sub-data to obtain the predicted relative geologic time of a plurality of second horizons. The above technical solution can improve the prediction efficiency of the relative geologic time while improving the accuracy of the prediction result.

Description

Technical Field

[0001] This application relates to the field of oil and gas seismic exploration and seismic interpretation technology, and in particular to a method, apparatus, computer equipment and storage medium for predicting relative geological time. Background Technology

[0002] In seismic exploration, seismic horizon interpretation is the foundation of seismic analysis, and horizon identification and tracing are crucial steps in this process. Typically, the relative geological time (RGT) of seismic data is analyzed to identify and trace horizons within the corresponding block. Traditional methods for generating RGTs primarily involve manually selecting as many horizons as possible and then interpolating the identified horizons to obtain the RGT. While this method is direct, its heavy reliance on subjective experience in horizon selection leads to low accuracy in the generated RGT. Therefore, obtaining a more accurate RGT is a technical problem that needs to be solved.

[0003] With the development of big data and artificial intelligence technologies, geophysicists have proposed using end-to-end neural network models to predict the relative ground truth (RGT) of seismic data. In related technologies, supervised learning methods are typically employed. Based on multiple seismic datasets and their RGTs, a neural network model is trained to predict more accurate RGTs.

[0004] However, since the above scheme does not have constraints on the neural network model in the process of predicting RGT, the predicted RGT still needs to be finely processed, which results in the low prediction efficiency of the neural network model for RGT. Summary of the Invention

[0005] This application provides a method, apparatus, computer device, and storage medium for predicting relative geological time, which can improve the accuracy of prediction results while increasing the efficiency of the relative geological time prediction model in predicting relative geological time. The technical solution is as follows:

[0006] On the one hand, a relative geological time prediction method is provided, the method comprising:

[0007] The seismic data of the target plot to be predicted is segmented to obtain multiple plot sub-data of the target plot. The plot seismic data includes seismic data of multiple first layers with relative geological time marked and seismic data of multiple second layers without relative geological time marked in the target plot. The relative geological time is used to indicate the relative formation time of the layer in the target plot. The plot sub-data includes partial seismic data of at least one layer in the target plot.

[0008] A relative geological time prediction model is trained based on multiple target plot sub-data, wherein the target plot sub-data is plot sub-data that includes at least one first-layer partial seismic data.

[0009] Based on the relative geological time prediction model obtained through training, predictions are made for the multiple plot sub-data to obtain the predicted relative geological time for each layer in the multiple plot sub-data.

[0010] The predicted relative geological time of each layer in the multiple plot sub-data is merged to obtain the predicted relative geological time of the multiple second layers.

[0011] On the other hand, a relative geological time prediction device is provided, the device comprising:

[0012] The segmentation module is used to segment the seismic data of the target land parcel to be predicted, thereby obtaining multiple sub-data of the target land parcel. The seismic data of the land parcel includes seismic data of multiple first-layer layers with labeled relative geological time and seismic data of multiple second-layer layers without labeled relative geological time in the target land parcel. The relative geological time is used to indicate the relative formation time of the layer in the target land parcel. The sub-data of the land parcel includes partial seismic data of at least one layer in the target land parcel.

[0013] The training module is used to train a relative geological time prediction model based on multiple target plot sub-data, wherein the target plot sub-data is plot sub-data that includes at least one first-layer partial seismic data.

[0014] The prediction module is used to predict the relative geological time of the multiple plot sub-data based on the trained relative geological time prediction model, and to obtain the predicted relative geological time of each layer in the multiple plot sub-data.

[0015] The merging module is used to merge the predicted relative geological time of each layer in the multiple plot sub-data to obtain the predicted relative geological time of the multiple second layers.

[0016] In some embodiments, the training module includes:

[0017] The prediction unit is used to predict any target plot sub-data among the plurality of target plot sub-data based on the relative geological time prediction model, to obtain prediction information of the target plot sub-data, and the prediction information is used to indicate the predicted relative geological time of each layer in the target plot sub-data;

[0018] A determining unit is configured to determine the training loss of the relative geological time prediction model based on the target plot sub-data and the prediction information, wherein the training loss is used to indicate the difference between the prediction information and the relative geological time marked in the target plot sub-data;

[0019] An update unit is used to update the model parameters of the relative geological time prediction model based on the training loss.

[0020] In some embodiments, the target plot sub-data includes partial seismic data from multiple layers, the multiple layers including at least one first layer;

[0021] The determining unit includes:

[0022] The acquisition sub-unit is used to acquire the relative geological time of at least one first layer based on partial seismic data of at least one first layer in the target block sub-data;

[0023] The first determining sub-unit is used to determine the constraint loss of the target plot sub-data based on the predicted relative geological time of the at least one first stratum and the relative geological time of the at least one first stratum, wherein the constraint loss is used to indicate the difference between the predicted relative geological time of the at least one first stratum and the relative geological time of the at least one first stratum.

[0024] The second determining subunit is used to determine the structural loss of the target plot subdata based on the gradient vector of the target plot subdata and the gradient vector of the predicted relative geological time of the multiple layers. The structural loss is used to indicate the difference between the gradient vector of the predicted relative geological time of the multiple layers and the gradient vector of the target plot subdata.

[0025] The third determining subunit is used to perform a weighted summation of the structural loss and the constraint loss to obtain the training loss.

[0026] In some embodiments, the second determining subunit is configured to determine the tensor matrix of the target plot subdata based on the gradient vector of the target plot subdata; perform singular value decomposition on the tensor matrix to obtain the normal vector of the target plot subdata and the quality parameter of the normal vector, the quality parameter being used to indicate the accuracy of the normal vector; and perform a weighted summation of the normal vector, the quality parameter, and the gradient vector of the predicted relative geological time to obtain the structural loss.

[0027] In some embodiments, the apparatus further includes:

[0028] The determination module is used to determine multiple layers in the target land area that are associated with the well logging locations, based on the well logging locations of the target land area;

[0029] The annotation module is used to annotate the multiple layers based on the well logging interpretation information of the target block to obtain the seismic data of the block. The well logging interpretation information is used to indicate the relative geological time of the multiple layers.

[0030] In some embodiments, the apparatus further includes:

[0031] The determining module is further configured to determine multiple strata interpreted by the stratigraphic interpretation information based on the stratigraphic interpretation information of the target plot, wherein the stratigraphic interpretation information is used to indicate the relative geological time of the multiple strata;

[0032] The annotation module is also used to annotate the multiple target layers based on the stratigraphic interpretation information to obtain the seismic data of the block.

[0033] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded and executed by the processor to implement the relative geological time prediction method in the embodiments of this application.

[0034] On the other hand, a computer-readable storage medium is provided, wherein at least one computer program is stored in the computer-readable storage medium, the at least one computer program being loaded and executed by a processor to implement the relative geological time prediction method as described in the embodiments of this application.

[0035] On the other hand, a computer program product is provided, including a computer program that is executed by a processor to implement the relative geological time prediction method provided in the embodiments of this application.

[0036] This application provides a relative geological time prediction method. By segmenting the seismic data of a target landmass, which includes seismic data from multiple first-layer seismic layers labeled with relative geological time and multiple second-layer seismic data from landmasses without relative geological time labeling, multiple sub-data of landmasses, including partial seismic data from at least one layer of the target landmass, can be obtained. Compared with traditional supervised training methods, this application, based on the target landmass sub-data including partial seismic data from at least one first-layer seismic layer labeled with relative geological time, can perform semi-supervised training on the relative geological time prediction model. It does not require the pre-production of a large number of labels, reducing the workload of manually interpreting seismic data. Furthermore, during the prediction of the target landmass' seismic data, the first-layer seismic data from the target landmass with labeled relative geological time is introduced during training to constrain the prediction results of the second-layer seismic data without labeled relative geological time. This improves both the accuracy and efficiency of the relative geological time prediction model in predicting relative geological time. Attached Figure Description

[0037] 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram illustrating the implementation environment of a relative geological time prediction method provided in an embodiment of this application;

[0039] Figure 2 This is a flowchart of a relative geological time prediction method provided according to an embodiment of this application;

[0040] Figure 3 This is a flowchart of another relative geological time prediction method provided according to an embodiment of this application;

[0041] Figure 4 This is a schematic diagram illustrating a method for obtaining target plot sub-data according to an embodiment of this application;

[0042] Figure 5 This is a schematic diagram of a block seismic data provided according to an embodiment of this application;

[0043] Figure 6 This is a flowchart illustrating the training process of a relative geological time prediction model according to an embodiment of this application.

[0044] Figure 7 This is a schematic diagram of relative geological time according to an embodiment of this application;

[0045] Figure 8 This is a schematic diagram of another relative geological time according to an embodiment of this application;

[0046] Figure 9 This is a block diagram of a relative geological time prediction device according to an embodiment of this application;

[0047] Figure 10 This is a block diagram of another relative geological time prediction device provided according to an embodiment of this application;

[0048] Figure 11 This is a structural block diagram of a terminal provided according to an embodiment of this application;

[0049] Figure 12 This is a schematic diagram of the structure of a server according to an embodiment of this application. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0051] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or execution order.

[0052] In this application, the term "at least one" means one or more, and "multiple" means two or more.

[0053] 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 seismic data and relative geological time of the land parcel involved in this application were obtained with full authorization.

[0054] The training method for the relative geological time prediction model provided in this application can be applied to a computer device. In some embodiments, the computer device is a terminal or a server. The following section first uses a computer device as a server as an example to describe the implementation environment of the training method for the relative geological time prediction model provided in this application. Figure 1 This is a schematic diagram illustrating the implementation environment of a training method for a relative geological time prediction model provided in an embodiment of this application. See also... Figure 1 The implementation environment includes terminal 101 and server 102. Terminal 101 and server 102 can be connected directly or indirectly via wired or wireless communication, which is not limited herein.

[0055] In some embodiments, terminal 101 may be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited thereto. An application capable of displaying the relative geological time of multiple strata within the target plot is installed and runs on terminal 101. This application is associated with server 102, which provides background services.

[0056] In some embodiments, 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 can segment the seismic data of the target land parcel to be predicted, and predict the relative geological time of the segmented sub-data based on a trained relative geological time prediction model, obtaining the relative geological time of each layer in the sub-data. The prediction results of the sub-data are then merged to obtain the relative geological time of each layer in the target land parcel. Server 102 returns the relative geological time to terminal 101, which displays it through an application.

[0057] In some embodiments, server 102 undertakes the primary computing task, and terminal 101 undertakes the secondary computing task; or, server 102 undertakes the secondary computing task, and terminal 101 undertakes the primary computing task; or, server 102 and terminal 101 collaborate on computing using a distributed computing architecture. Optionally, the number of servers may be more or fewer, and this embodiment does not limit this. Of course, server 102 may also include other functional servers to provide more comprehensive and diversified services.

[0058] Figure 2 This is a flowchart of a relative geological time prediction method provided according to an embodiment of this application, such as... Figure 2 As shown in the embodiments of this application, the method is described using an example executed by a server. The relative geological time prediction method includes the following steps:

[0059] 201. The server segments the seismic data of the target plot to be predicted, obtaining multiple plot sub-data of the target plot. The plot seismic data includes seismic data of multiple first-layer layers with labeled relative geological time and seismic data of multiple second-layer layers without labeled relative geological time in the target plot. The relative geological time is used to indicate the relative formation time of the layer in the target plot. The plot sub-data includes partial seismic data of at least one layer in the target plot.

[0060] In this embodiment, the target site is an underground rock stratum with a certain geological structure. The target site includes multiple strata, each with a different relative geological time. The relative geological time of a stratum indicates its relative formation time within the target site. Relative geological time refers to the chronological order of the formation process of multiple strata within the target site; this chronological order only indicates the relative formation time of a particular stratum relative to other strata, and does not represent the actual formation time of the strata. The seismic data for the site is two-dimensional or three-dimensional seismic data used to indicate the geological structure of the target site, such as two-dimensional seismic profiles or three-dimensional amplitude images. The seismic data includes seismic data from multiple strata within the target site, including multiple first strata with labeled relative geological times and multiple second strata without labeled relative geological times. The server segments the seismic data of the target site to obtain multiple sub-data sets. Each sub-data set includes partial seismic data from at least one stratum within the target site; this stratum can be either a first or second stratum, and this embodiment does not impose any limitations on this.

[0061] 202. The server trains a relative geological time prediction model based on multiple target plot sub-data. The target plot sub-data is the plot sub-data that includes at least one first-layer partial seismic data.

[0062] In this embodiment, the server, based on seismic data from multiple first-layer horizons within a target land parcel, can determine multiple target land parcel sub-data from multiple land parcel sub-data. These target land parcel sub-data include partial seismic data from at least one first-layer horizon. Since the first-layer horizons are horizons with labeled relative geological times, the server can use the relative geological times of the first-layer horizons in the target land parcel sub-data as supervisory information to train a relative geological time prediction model. The target land parcel sub-data includes not only partial seismic data from the first-layer horizons with labeled relative geological times but also partial seismic data from second-layer horizons without labeled relative geological times. Correspondingly, the supervisory information during training can only indicate the relative geological times of some horizons within the target land parcel. Therefore, the server can employ a semi-supervised training method to train the relative geological time prediction model based on multiple target land parcel sub-data.

[0063] 203. Based on the trained relative geological time prediction model, the server predicts the relative geological time of each layer in multiple plot sub-data, thereby obtaining the predicted relative geological time.

[0064] In this embodiment of the application, the relative geological time prediction model is used to predict the relative geological time of each layer in the target plot. Therefore, based on the trained relative geological time prediction model, the server predicts multiple plot sub-data of the target plot respectively, and can obtain the prediction results of multiple plot sub-data. The prediction results include the predicted relative geological time of each layer in the plot sub-data.

[0065] 204. The server merges the predicted relative geological time of each layer in multiple plot sub-data to obtain multiple predicted relative geological times of the second layer.

[0066] In this embodiment, since each sub-data parcel includes partial seismic data from at least one stratum, the strata corresponding to different sub-data parcels may be the same or different. Therefore, the predicted relative geological time for each stratum in the multiple sub-data parcels predicted based on the relative geological time prediction model is not entirely the same. By merging the prediction results of multiple sub-data parcels, the server can obtain the predicted relative geological time for each stratum in the sub-data parcel seismic data, thus obtaining the predicted relative geological time for multiple second strata in the sub-data parcels that are not labeled with relative geological time.

[0067] In this embodiment, the server, based on a relative geological time prediction model, can predict the seismic data of a target block for which only some strata have been labeled with relative geological times. This yields the predicted relative times of unlabeled strata within the target block, reducing the workload of manual labeling of relative geological times and improving the processing efficiency of the target block's seismic data. Furthermore, based on the predicted relative geological times of multiple strata within the target block, strata can be identified and tracked according to isochronous surfaces composed of the same relative geological times. It can also detect faults within the target block even when relative geological times are discontinuous, thereby providing a better interpretation of the target block's geological structure.

[0068] This application provides a relative geological time prediction method. By segmenting the seismic data of a target landmass, which includes seismic data from multiple first-layer seismic layers labeled with relative geological time and multiple second-layer seismic data from landmasses without relative geological time labeling, multiple sub-data of landmasses, including partial seismic data from at least one layer of the target landmass, can be obtained. Compared with traditional supervised training methods, this application, based on the target landmass sub-data including partial seismic data from at least one first-layer seismic layer labeled with relative geological time, can perform semi-supervised training on the relative geological time prediction model. It does not require the pre-production of a large number of labels, reducing the workload of manually interpreting seismic data. Furthermore, during the prediction of the target landmass' seismic data, the first-layer seismic data from the target landmass with labeled relative geological time is introduced during training to constrain the prediction results of the second-layer seismic data without labeled relative geological time. This improves both the accuracy and efficiency of the relative geological time prediction model in predicting relative geological time.

[0069] Figure 3 This is a flowchart of another relative geological time prediction method provided according to an embodiment of this application, such as... Figure 3 As shown in the embodiments of this application, the method is described using an example executed by a server. The relative geological time prediction method includes the following steps:

[0070] 301. The server obtains the seismic data of the target plot to be predicted. The seismic data of the plot includes seismic data of multiple first-layer layers with labeled relative geological time and seismic data of multiple second-layer layers without labeled relative geological time. The relative geological time is used to indicate the relative formation time of the layer in the target plot.

[0071] In this embodiment, the target site is a subsurface rock stratum with a certain geological structure. The target site includes multiple strata, each with a different relative geological time. The relative geological time of a stratum indicates its relative formation time within the target site. The seismic data for the site is two-dimensional or three-dimensional seismic data used to indicate the geological structure of the target site, such as two-dimensional seismic profiles or three-dimensional amplitude images. The seismic data includes seismic data from multiple strata within the target site, comprising multiple first strata with labeled relative geological times and multiple second strata without labeled relative geological times.

[0072] In some embodiments, before obtaining the seismic data of the target site to be predicted, the server needs to annotate the relative geological time of certain strata within the target site. Accordingly, the server can obtain the seismic data of the target site through Method 1 and Method 2 described below.

[0073] Method 1: The server determines multiple strata associated with the well logging locations within the target block. Based on the well logging interpretation information of the target block, these strata are labeled to obtain the block's seismic data. The well logging interpretation information indicates the relative geological time of these strata. Specifically, the well logging interpretation information is used to interpret multiple strata associated with the well logging locations within the target block, such as the location of the strata and their relative geological time. Based on the relative geological time of these strata associated with the well logging locations in the well logging interpretation information, the server can label multiple strata, thereby obtaining the block's seismic data, which includes seismic data from multiple first-level strata with labeled relative geological times.

[0074] Method 2: The server, based on the stratigraphic interpretation information of the target block, determines multiple stratigraphic layers interpreted by the stratigraphic interpretation information, which indicates the relative geological time of these layers. Based on this information, the server labels these multiple target stratigraphic layers to obtain the block's seismic data. The stratigraphic interpretation information is used to interpret the attributes of the stratigraphic layers within the target block, such as their location and relative geological time. The server, based on the relative geological time of multiple layers in the stratigraphic interpretation information, can label these multiple layers, thereby obtaining the block's seismic data, which includes seismic data from multiple first-layer stratigraphic layers with labeled relative geological time.

[0075] 302. The server segments the seismic data of the target plot to obtain multiple plot sub-data of the target plot. The plot sub-data includes partial seismic data of at least one layer in the target plot.

[0076] In this embodiment, the server can segment the seismic data of a target plot according to a pre-set size of the plot sub-data, resulting in multiple plot sub-data. Each plot sub-data includes partial seismic data from at least one layer within the target plot. This layer can be either a first layer or a second layer, and this embodiment does not impose any limitation on this.

[0077] For example, when the seismic data of a land parcel is 3D seismic data, the server can set the size of the land parcel sub-data input to the relative geological time prediction model to d. x ×d y ×d t Among them, d x d represents the length of the data range of the plot sub-data in the horizontal x-direction. y d represents the length of the data range of the plot sub-data in the vertical y-direction. t This represents the length of the data range of the plot sub-data along the time direction t. The size of the plot sub-data can be selected based on the server's computing power.

[0078] 303. For any target plot sub-data in multiple target plot sub-data, the server predicts the target plot sub-data based on the relative geological time prediction model to obtain the prediction information of the target plot sub-data. The prediction information is used to indicate the predicted relative geological time of each layer in the target plot sub-data.

[0079] In this embodiment, the server, based on seismic data from multiple first-layer horizons within a target plot, can determine multiple target plot sub-data from multiple plot sub-data. These target plot sub-data include partial seismic data from at least one first-layer horizon. Since the first-layer horizons are horizons with labeled relative geological times, the server can use the relative geological times of the first-layer horizons in the target plot sub-data as supervisory information to train a relative geological time prediction model. During the training of the relative geological time prediction model based on multiple target plot sub-data, for any target plot sub-data, the server, based on the relative geological time prediction model, can predict the target plot sub-data to obtain prediction information. This prediction information is used to indicate the predicted relative geological time for each horizon in the plot sub-data.

[0080] For example, Figure 4 A schematic diagram illustrating a method for obtaining target plot sub-data according to an embodiment of this application. (See diagram below.) Figure 4 As shown, the triangle represents the well location (x0, y0) in the block's seismic data, and the surface formed by the solid lines represents the first layer with the relative geological time already marked. Figure 4 The cubes formed by solid lines represent the seismic data of the block, while the cubes formed by dashed lines represent the sub-data of the target block. Based on well locations and the first stratigraphic level, the server can segment sub-data of size d from the block seismic data. x ×d y ×d t The target block sub-data includes partial seismic data of the strata associated with the well location or partial seismic data of the first stratum.

[0081] For example, Figure 5 This is a schematic diagram of seismic data for a land parcel provided according to an embodiment of this application. For example... Figure 5 As shown, Figure 5 (1) is the seismic data of the land parcel, that is, the two-dimensional seismic profile of the target land parcel. Figure 5 (2) A schematic diagram of the relative geological time of multiple layers in the target plot, with each color representing the relative geological time of a layer. Figure 5 (2) These are multiple isochrones obtained based on the relative geological time of multiple strata, and the strata on the same isochrone have the same relative geological time.

[0082] 304. Based on the target plot sub-data and the prediction information of the target plot sub-data, the server determines the training loss of the relative geological time prediction model. The training loss is used to indicate the difference between the prediction information and the relative geological time marked in the target plot sub-data.

[0083] In this embodiment, for any target plot sub-data, the server, based on the target plot sub-data and its prediction information, can determine the training loss of the relative geological time prediction model. This training loss indicates the difference between the predicted relative geological time in the prediction information and the relative geological time labeled in the target plot sub-data. The training loss is inversely correlated with accuracy; the smaller the training loss of the relative geological time prediction model, the smaller the difference between the predicted relative geological time of the stratum and the pre-labeled relative geological time, and the more accurate the predicted relative geological time obtained by the relative geological time prediction model based on the target plot sub-data.

[0084] In some embodiments, the server can determine the structural loss and constraint loss of the target plot sub-data based on the target plot sub-data and the prediction information of the target plot sub-data, and then determine the training loss based on the structural loss and constraint loss. Accordingly, the server can determine the training loss of the relative geological time prediction model through the following steps (1)-(4).

[0085] (1) The server obtains the relative geological time of at least one first layer based on partial seismic data of at least one first layer in the target plot sub-data.

[0086] In this embodiment of the application, the target plot sub-data includes partial seismic data from multiple layers, including at least one first layer. Since the first layer is a layer in the target plot with a labeled relative geological time, the server can obtain the relative geological time of at least one first layer based on the partial seismic data of at least one first layer.

[0087] (2) The server determines the constraint loss of the target plot subdata based on the predicted relative geological time of at least one first layer and the relative geological time of at least one first layer. The constraint loss is used to indicate the difference between the predicted relative geological time of at least one first layer and the relative geological time of at least one first layer.

[0088] In this embodiment, the prediction information of the target plot sub-data is used to indicate the relative geological time of each layer in the target plot sub-data. The target plot sub-data includes partial seismic data of at least one first layer. Therefore, the server determines the constraint loss of the target plot sub-data based on the predicted relative geological time of at least one first layer in the prediction information and the pre-labeled relative geological time of at least one first layer. This constraint loss is used to indicate the difference between the predicted relative geological time of at least one first layer and the relative geological time of at least one first layer. The smaller the constraint loss, the smaller the difference between the predicted relative geological time of the first layer in the target plot sub-data and the relative geological time labeled in the target plot sub-data.

[0089] In some embodiments, the server determines the constraint loss of the target plot sub-data based on the predicted relative geological time of at least one first stratum and the relative geological time of at least one first stratum using the following formula 1.

[0090] Formula 1:

[0091]

[0092] Among them, Loss control The constraint loss is denoted by K, where K is the number of well logs in the target block sub-data. For the target block sub-data and the well logging location (x k ,y k The relative geological time of the first associated stratum, For the target block sub-data and the well logging location (x k ,y k The predicted relative geological time of the first layer associated with it.

[0093] In some embodiments, the server determines the constraint loss of the target plot sub-data based on the predicted relative geological time of at least one first stratum and the relative geological time of at least one first stratum using the following Formula 2.

[0094] Formula 2:

[0095]

[0096] Among them, Loss control The constraint loss is K for the target plot sub-data, where K is the number of first-level locations in the target sub-data, and τ is the number of locations in the first-level location. k p(x) represents the relative geological time of the first stratum labeled in the target plot subdata. k ,y k ,t k (x) represents the predicted relative geological time of the first stratum in the target plot sub-data. k ,yk ,t k () represents any point in the first layer.

[0097] (3) The server determines the structural loss of the target plot sub-data based on the gradient vector of the target plot sub-data and the gradient vector of the predicted relative geological time of multiple layers. The structural loss is used to indicate the difference between the gradient vector of the predicted relative geological time of multiple layers and the gradient vector of the target plot sub-data.

[0098] In this embodiment, when the target plot sub-data is 3D seismic data, the server can obtain the gradient vector of the target plot sub-data by determining the gradients in the x, y, and t directions. Similarly, the server can determine the gradient vectors of the predicted relative geological time for multiple layers in the target plot sub-data by determining the gradients in the x, y, and t directions. Based on the gradient vectors of the target plot sub-data and the gradient vectors of the predicted relative geological time for multiple layers, the server can determine the structural loss of the target plot sub-data. The smaller the structural loss, the smaller the difference between the gradient vectors, and the closer the gradient vector of the predicted relative geological time is to being parallel with the gradient vector of the target seismic sub-data.

[0099] In some embodiments, the server determines the tensor matrix of the target plot sub-data based on the gradient vector of the target plot sub-data. Then, it performs singular value decomposition (SVD) on the tensor matrix to obtain the normal vector and its quality parameter, which indicates the accuracy of the normal vector. The server then performs a weighted sum of the normal vector, the quality parameter, and the gradient vector for the predicted relative geological time to obtain the structural loss. Here, the tensor matrix is ​​a symmetric matrix. The server performs SVD on this symmetric matrix to obtain multiple eigenvectors and their eigenvalues. The normal vector of the target plot sub-data is an eigenvector of the tensor matrix. The server performs a weighted sum of the eigenvalues ​​of these eigenvectors to obtain the quality parameter of the normal vector. The server obtains the structural loss of the target plot sub-data by performing a weighted sum of the normal vector, the quality parameter, and the gradient vector for the predicted relative geological time.

[0100] In some embodiments, when the target plot sub-data is three-dimensional seismic data, the tensor matrix of the target plot sub-data is as shown in Formula 3. The server performs singular value decomposition on the tensor matrix using Formula 4 below to obtain the normal vector and the quality parameter of the normal vector of the target plot sub-data.

[0101] Formula 3:

[0102]

[0103] Formula 4:

[0104] T = λ u uu T +λ v vv T +λ w ww T

[0105] Where T is the tensor matrix of the target plot sub-data, g is the gradient vector of the target plot sub-data, and g = [g x ,g y ,g t ] T g x Let g be the unit vector of the gradient vector in the horizontal direction x. y Let g be the unit vector of the gradient vector in the vertical direction y. t Let λ be the unit vector of the gradient vector along the time direction t. u, v, and w are multiple eigenvectors of the tensor matrix, and λ is the eigenvector of the tensor matrix. u , λ v , λ w Let be the multiple eigenvalues ​​of the tensor matrix. Here, u is the normal vector of the target parcel subdata, and the quality parameter of the normal vector is...

[0106] In some embodiments, the server uses Formula 5 below to perform a weighted summation of the normal vector, quality parameters, and gradient vector of the predicted relative geological time to determine the structural loss of the target plot sub-data.

[0107] Formula 5:

[0108]

[0109] Among them, Loss structure The structural loss of the target plot subdata is w, where w is the normal vector [n x ,n y ,n t ] T The quality parameter, n x Let n be the unit vector of the normal vector in the horizontal direction x. y Let n be the unit vector of the normal vector in the vertical direction y. t Let be the unit vector of the normal vector in the time direction t. as well as To predict the gradient of relative geological time τ(x,y,t) in three directions, ||.|| L2 It is an L2 norm.

[0110] (4) The server performs a weighted sum of the structural loss and constraint loss to obtain the training loss.

[0111] In this embodiment, for any target plot sub-data, the server performs a weighted sum of the structural loss and constraint loss of the target plot sub-data to obtain the training loss generated in training the relative geological time prediction model based on the target plot sub-data. This training loss is used to indicate the difference between the predicted relative geological time in the prediction information of the target plot sub-data and the relative geological time marked in the target plot sub-data.

[0112] In some embodiments, the server uses Formula 6 below to perform a weighted summation of the structural loss and the constraint loss to obtain the training loss.

[0113] Formula Six:

[0114] LOSS all =LOSS structure +εLOSS control

[0115] Among them, Loss all Loss is the training loss for the relative geological time prediction model. structure Loss is the structural loss of the target plot subdata. control ε represents the constraint loss of the target plot sub-data, and ε is the weight of the constraint loss.

[0116] For example, Figure 6 This is a flowchart illustrating the training process of a relative geological time prediction model according to an embodiment of this application. Figure 6 As shown, the server predicts the target plot sub-data based on a relative geological time prediction model, obtaining the predicted relative geological time for each layer in the target plot sub-data. Then, based on the predicted relative time of at least one first layer in the target plot sub-data and the relative geological time of at least one first layer marked in the target plot sub-data, the constraint loss of the target plot sub-data is obtained. The server processes the target plot sub-data to determine the normal vector and the quality parameter of the normal vector based on the tensor matrix of the target plot sub-data. Then, based on the normal vector, the quality parameter of the normal vector, and the predicted relative geological time of each layer in the target plot sub-data, the structural loss of the target plot sub-data is determined. Finally, the server performs a weighted sum of the constraint loss and the structural loss to obtain the training loss of the relative geological time prediction model.

[0117] 305. The server updates the model parameters of the relative geological time prediction model based on the training loss.

[0118] In this embodiment, the server can update the model parameters of the relative geological time prediction model based on the training loss, thereby reducing the training loss of the relative geological time prediction model and training an updated relative geological time prediction model. If the updated relative geological time prediction model meets the training termination condition, such as the number of training iterations being the target number, or the training loss of the relative geological time prediction model being within the target range, then the updated relative geological time prediction model is taken as the completed relative geological time prediction model.

[0119] 306. Based on the trained relative geological time prediction model, the server predicts the relative geological time of each layer in multiple plot sub-data, thereby obtaining the predicted relative geological time.

[0120] In this embodiment of the application, the relative geological time prediction model is used to predict the relative geological time of each layer in the target plot. Therefore, based on the trained relative geological time prediction model, the server predicts multiple plot sub-data of the target plot respectively, and can obtain the prediction results of multiple plot sub-data. The prediction results include the predicted relative geological time of each layer in the plot sub-data.

[0121] For example, Figure 7 This is a schematic diagram of relative geological time according to an embodiment of this application. For example... Figure 7 As shown, Figure 7 (1) Sub-data of the block, which includes partial seismic data of two first-level horizons A and B with labeled relative geological time. Figure 7 (2) The predicted relative geological time of other layers in the sub-data of the land parcel that are not marked with relative geological time is obtained by the server based on the relative geological time prediction model.

[0122] For example, Figure 8 This is a schematic diagram of another relative geological time according to an embodiment of this application. For example... Figure 8 As shown, the relative geological times of multiple strata predicted by the relative geological time model after multiple iterations are presented. The relative geological time prediction model outputs more accurate relative geological times with increasing iteration count.

[0123] 307. The server merges the predicted relative geological time of each layer in multiple plot sub-data to obtain multiple predicted relative geological times of the second layer.

[0124] In this embodiment, since each sub-data parcel includes partial seismic data from at least one stratum, the strata corresponding to different sub-data parcels may be the same or different. Therefore, the predicted relative geological time for each stratum in the multiple sub-data parcels predicted based on the relative geological time prediction model is not entirely the same. By merging the prediction results of multiple sub-data parcels, the server can obtain the predicted relative geological time for each stratum in the sub-data parcel seismic data, thus obtaining the predicted relative geological time for multiple second strata in the sub-data parcels that are not labeled with relative geological time.

[0125] In this embodiment, the server, based on a relative geological time prediction model, can predict the seismic data of a target block for which only some strata have been labeled with relative geological times. This yields the predicted relative times of unlabeled strata within the target block, reducing the workload of manual labeling of relative geological times and improving the processing efficiency of the target block's seismic data. Furthermore, based on the predicted relative geological times of multiple strata within the target block, strata can be identified and tracked according to isochronous surfaces composed of the same relative geological times. It can also detect faults within the target block even when relative geological times are discontinuous, thereby providing a better interpretation of the target block's geological structure.

[0126] This application provides a relative geological time prediction method. By segmenting the seismic data of a target landmass, which includes seismic data from multiple first-layer seismic layers labeled with relative geological time and multiple second-layer seismic data from landmasses without relative geological time labeling, multiple sub-data of landmasses, including partial seismic data from at least one layer of the target landmass, can be obtained. Compared with traditional supervised training methods, this application, based on the target landmass sub-data including partial seismic data from at least one first-layer seismic layer labeled with relative geological time, can perform semi-supervised training on the relative geological time prediction model. It does not require the pre-production of a large number of labels, reducing the workload of manually interpreting seismic data. Furthermore, during the prediction of the target landmass' seismic data, the first-layer seismic data from the target landmass with labeled relative geological time is introduced during training to constrain the prediction results of the second-layer seismic data without labeled relative geological time. This improves both the accuracy and efficiency of the relative geological time prediction model in predicting relative geological time.

[0127] Figure 9 This is a block diagram of a relative geological time prediction device according to an embodiment of this application. The device is used to perform the aforementioned relative geological time prediction method. (See also...) Figure 9 The device includes: a segmentation module 901, a training module 902, a prediction module 903, and a merging module 904.

[0128] The segmentation module 901 is used to segment the seismic data of the target plot to be predicted, and obtain multiple plot sub-data of the target plot. The plot seismic data includes seismic data of multiple first layers with labeled relative geological time and seismic data of multiple second layers without labeled relative geological time in the target plot. The relative geological time is used to indicate the relative formation time of the layer in the target plot. The plot sub-data includes partial seismic data of at least one layer in the target plot.

[0129] Training module 902 is used to train a relative geological time prediction model based on multiple target plot sub-data. The target plot sub-data is plot sub-data that includes at least one first-layer partial seismic data.

[0130] Prediction module 903 is used to predict the relative geological time of multiple plot sub-data based on the trained relative geological time prediction model, and to obtain the predicted relative geological time of each layer in the multiple plot sub-data.

[0131] The merging module 904 is used to merge the predicted relative geological time of each layer in multiple plot sub-data to obtain multiple predicted relative geological times of the second layer.

[0132] In some embodiments, Figure 10 This is a block diagram of another relative geological time prediction device provided according to an embodiment of this application. See also... Figure 10 Training module 902 includes:

[0133] The prediction unit 1001 is used to predict any target plot sub-data in multiple target plot sub-data based on a relative geological time prediction model, and obtain prediction information of the target plot sub-data. The prediction information is used to indicate the predicted relative geological time of each layer in the target plot sub-data.

[0134] The determination unit 1002 is used to determine the training loss of the relative geological time prediction model based on the target plot sub-data and prediction information. The training loss is used to indicate the difference between the prediction information and the relative geological time marked in the target plot sub-data.

[0135] Update unit 1002 is used to update the model parameters of the relative geological time prediction model based on the training loss.

[0136] In some embodiments, the target plot sub-data includes partial seismic data from multiple layers, including at least one first layer;

[0137] See also Figure 10 Unit 1002 is defined as including:

[0138] Acquire sub-unit 10021, used to acquire the relative geological time of at least one first layer based on partial seismic data of at least one first layer in the target block sub-data;

[0139] The first determining sub-unit 10022 is used to determine the constraint loss of the target block sub-data based on the predicted relative geological time of at least one first stratum and the relative geological time of at least one first stratum. The constraint loss is used to indicate the difference between the predicted relative geological time of at least one first stratum and the relative geological time of at least one first stratum.

[0140] The second determining sub-unit 10023 is used to determine the structural loss of the target plot sub-data based on the gradient vector of the target plot sub-data and the gradient vector of the predicted relative geological time of multiple layers. The structural loss is used to indicate the difference between the gradient vector of the predicted relative geological time of multiple layers and the gradient vector of the target plot sub-data.

[0141] The third determined subunit 10024 is used to perform a weighted summation of the structural loss and constraint loss to obtain the training loss.

[0142] In some embodiments, the second determining subunit 10023 is used to determine the tensor matrix of the target plot subdata based on the gradient vector of the target plot subdata; perform singular value decomposition on the tensor matrix to obtain the normal vector and the quality parameter of the normal vector of the target plot subdata, wherein the quality parameter is used to indicate the accuracy of the normal vector; and perform a weighted summation of the normal vector, the quality parameter and the gradient vector of the predicted relative geological time to obtain the structural loss.

[0143] In some embodiments, see continue to see Figure 10 The device also includes:

[0144] The determination module 905 is used to determine multiple layers in the target block that are associated with the well logging locations, based on the well logging locations of the target block;

[0145] The annotation module 906 is used to annotate multiple layers based on well logging interpretation information of the target block to obtain seismic data of the block. The well logging interpretation information is used to indicate the relative geological time of multiple layers.

[0146] In some embodiments, the apparatus further includes:

[0147] The determination module 905 is also used to determine multiple strata interpreted by the stratigraphic interpretation information based on the stratigraphic interpretation information of the target plot. The stratigraphic interpretation information is used to indicate the relative geological time of the multiple strata.

[0148] The annotation module 906 is also used to annotate multiple target layers based on the stratigraphic interpretation information to obtain block seismic data.

[0149] This application provides a relative geological time prediction device. By segmenting the seismic data of a target landmass, which includes seismic data from multiple first-layer seismic layers labeled with relative geological time and seismic data from multiple second-layer seismic layers without relative geological time labeling, multiple sub-data of landmasses, including partial seismic data from at least one layer of the target landmass, can be obtained. Compared with traditional supervised training methods, this application, based on the target landmass sub-data including partial seismic data from at least one first-layer seismic layer labeled with relative geological time, can perform semi-supervised training on the relative geological time prediction model. This eliminates the need for pre-creating a large number of labels, reducing the workload of manually interpreting seismic data. Furthermore, during the prediction of the target landmass' seismic data, the first-layer seismic data from the target landmass with labeled relative geological time is introduced during training to constrain the prediction results of the second-layer seismic data without labeled relative geological time. This improves both the accuracy of the prediction results and the efficiency of the relative geological time prediction model in predicting relative geological time.

[0150] It should be noted that the relative geological time prediction device 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 relative geological time prediction device and the relative geological time prediction method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0151] In the embodiments of this application, the computer device can be configured as a terminal or a server. When the computer device is configured as a terminal, the terminal can act as the execution subject to implement the technical solutions provided in the embodiments of this application. When the computer device is configured as a server, the server can act as the execution subject to implement the technical solutions provided in the embodiments of this application. Alternatively, the technical solutions provided in this application can be implemented through the interaction between the terminal and the server. The embodiments of this application do not limit this.

[0152] Figure 11 This is a structural block diagram of a terminal 1100 provided according to an embodiment of this application.

[0153] Typically, terminal 1100 includes a processor 1101 and a memory 1102.

[0154] Processor 1101 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1101 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 1101 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 1101 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 1101 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0155] The memory 1102 may include one or more computer-readable storage media, which may be non-transitory. The memory 1102 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 1102 are used to store at least one computer program, which is executed by the processor 1101 to implement the relative geological time prediction method provided in the method embodiments of this application.

[0156] In some embodiments, the terminal 1100 may also optionally include a peripheral device interface 1103 and at least one peripheral device. The processor 1101, memory 1102, and peripheral device interface 1103 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1103 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 1104, a display screen 1105, a camera assembly 1106, an audio circuit 1107, and a power supply 1108.

[0157] Peripheral device interface 1103 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1101 and memory 1102. In some embodiments, processor 1101, memory 1102 and peripheral device interface 1103 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1101, memory 1102 and peripheral device interface 1103 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0158] Radio frequency (RF) circuit 1104 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. RF circuit 1104 communicates with communication networks and other communication devices via electromagnetic signals. RF circuit 1104 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. In some embodiments, RF circuit 1104 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. RF circuit 1104 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi. Wireless Fidelity (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1104 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0159] Display screen 1105 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1105 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 1101 for processing. In this case, display screen 1105 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 1105, disposed on the front panel of terminal 1100; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1100 or in a folded design; in still other embodiments, display screen 1105 may be a flexible display screen, disposed on a curved or folded surface of terminal 1100. Furthermore, display screen 1105 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1105 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0160] The camera assembly 1106 is used to acquire images or videos. In some embodiments, the camera assembly 1106 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. 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 1106 may also include a flash. The flash can 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.

[0161] The audio circuit 1107 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 1101 for processing, or input to the radio frequency circuit 1104 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 1100. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1101 or the radio frequency circuit 1104 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 1107 may also include a headphone jack.

[0162] Power supply 1108 is used to power the various components in terminal 1100. Power supply 1108 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1108 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0163] In some embodiments, the terminal 1100 further includes one or more sensors 1109. The one or more sensors 1109 include, but are not limited to: an acceleration sensor 1110, a gyroscope sensor 1111, a pressure sensor 1112, an optical sensor 1113, and a proximity sensor 1114.

[0164] Accelerometer 1110 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established with terminal 1100. For example, accelerometer 1110 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1101 can control display screen 1105 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1110. Accelerometer 1110 can also be used for games or for acquiring user motion data.

[0165] The gyroscope sensor 1111 can detect the orientation and rotation angle of the terminal 1100. The gyroscope sensor 1111 can work in conjunction with the accelerometer sensor 1110 to collect the user's 3D movements on the terminal 1100. Based on the data collected by the gyroscope sensor 1111, the processor 1111 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.

[0166] The pressure sensor 1112 can be disposed on the side bezel of the terminal 1100 and / or on the lower layer of the display screen 1105. When the pressure sensor 1112 is disposed on the side bezel of the terminal 1100, it can detect the user's grip signal on the terminal 1100, and the processor 1101 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1112. When the pressure sensor 1112 is disposed on the lower layer of the display screen 1105, the processor 1101 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1105. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0167] An optical sensor 1113 is used to collect ambient light intensity. In one embodiment, the processor 1101 can control the display brightness of the display screen 1105 based on the ambient light intensity collected by the optical sensor 1113. Specifically, when the ambient light intensity is high, the display brightness of the display screen 1105 is increased; when the ambient light intensity is low, the display brightness of the display screen 1105 is decreased. In another embodiment, the processor 1101 can also dynamically adjust the shooting parameters of the camera assembly 1106 based on the ambient light intensity collected by the optical sensor 1113.

[0168] The proximity sensor 1114, also known as a distance sensor, is typically located on the front panel of the terminal 1100. The proximity sensor 1114 is used to detect the distance between the user and the front of the terminal 1100. In one embodiment, when the proximity sensor 1114 detects that the distance between the user and the front of the terminal 1100 is gradually decreasing, the processor 1101 controls the display screen 1105 to switch from a screen-on state to a screen-off state; when the proximity sensor 1104 detects that the distance between the user and the front of the terminal 1100 is gradually increasing, the processor 1101 controls the display screen 1105 to switch from a screen-off state to a screen-on state.

[0169] Those skilled in the art will understand that Figure 11 The structure shown does not constitute a limitation on terminal 1100 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0170] Figure 12This is a schematic diagram of a server structure according to an embodiment of this application. The server 1200 can vary considerably due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1201 and one or more memories 1202. The memory 1202 stores at least one computer program, which is loaded and executed by the processor 1201 to implement the relative geological time prediction method provided in the above-described method embodiments. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated here.

[0171] 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 relative geological time prediction method in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, or optical data storage device, etc.

[0172] This application also provides a computer program product, which is executed by a processor to implement the relative geological time prediction method in the above embodiments.

[0173] 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.

[0174] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting relative geological time, characterized in that, The method includes: The seismic data of the target site to be predicted is segmented to obtain multiple sub-data of the target site. The sub-data includes seismic data of multiple first-layer layers with labeled relative geological time and multiple second-layer layers without labeled relative geological time. The relative geological time is used to indicate the relative formation time of the layer in the target site. The sub-data includes partial seismic data of at least one layer in the target site. The target sub-data includes partial seismic data of multiple layers, including at least one first layer. A relative geological time prediction model is trained based on multiple target plot sub-data, wherein the target plot sub-data is plot sub-data that includes at least one first-layer partial seismic data. Based on the relative geological time prediction model obtained through training, predictions are made for the multiple plot sub-data to obtain the predicted relative geological time for each layer in the multiple plot sub-data. The predicted relative geological time of each layer in the multiple sub-data of the plots is merged to obtain the predicted relative geological time of the multiple second layers; Specifically, based on the target plot sub-data and prediction information, the training loss of the relative geological time prediction model is determined, including: Based on partial seismic data of at least one first layer in the target plot sub-data, the relative geological time of the at least one first layer is obtained; Based on the predicted relative geological time of the at least one first stratum and the relative geological time of the at least one first stratum, a constraint loss of the target block sub-data is determined, the constraint loss being used to indicate the difference between the predicted relative geological time of the at least one first stratum and the relative geological time of the at least one first stratum. Based on the gradient vector of the target plot sub-data, determine the tensor matrix of the target plot sub-data; Using formula (4), singular value decomposition is performed on the tensor matrix to obtain the normal vector of the target plot sub-data and the quality parameter of the normal vector. The quality parameter is used to indicate the accuracy of the normal vector. in, Let u be the tensor matrix of the target plot sub-data. , These are multiple eigenvectors of the tensor matrix. , , Let u be the normal vector of the target plot subdata, and let u be the eigenvalues ​​of the tensor matrix. Then the quality parameter of the normal vector is: ; The structural loss is obtained by weighted summation of the normal vector, the quality parameter, and the gradient vector of the predicted relative geological time using formula (5). The structural loss is used to indicate the difference between the gradient vectors of the predicted relative geological time of the multiple strata and the gradient vectors of the target block sub-data. in, The structural loss of the target plot sub-data is represented by W, where W is the quality parameter. The normal vector is in the horizontal direction unit vector, Let be the unit vector of the normal vector in the vertical direction y. Let be the unit vector of the normal vector in the time direction t. , as well as To predict relative geological time Gradients in the three directions, It is an L2 norm; The training loss is obtained by weighted summation of the structural loss and the constraint loss.

2. The method according to claim 1, characterized in that, The training of the relative geological time prediction model based on multiple target plot sub-data includes: For any target plot sub-data among the plurality of target plot sub-data, the target plot sub-data is predicted based on the relative geological time prediction model to obtain the prediction information of the target plot sub-data. The prediction information is used to indicate the predicted relative geological time of each layer in the target plot sub-data. Based on the target plot sub-data and the prediction information, the training loss of the relative geological time prediction model is determined, and the training loss is used to indicate the difference between the prediction information and the relative geological time marked in the target plot sub-data; The model parameters of the relative geological time prediction model are updated based on the training loss.

3. The method according to claim 1, characterized in that, The method further includes: Based on the well logging locations of the target site, multiple strata associated with the well logging locations within the target site are determined; Based on the well logging interpretation information of the target block, the multiple strata are labeled to obtain the seismic data of the block. The well logging interpretation information is used to indicate the relative geological time of the multiple strata.

4. The method according to claim 1, characterized in that, The method further includes: Based on the stratigraphic interpretation information of the target plot, multiple stratigraphic layers interpreted by the stratigraphic interpretation information are determined, and the stratigraphic interpretation information is used to indicate the relative geological time of the multiple stratigraphic layers; Based on the stratigraphic interpretation information, multiple target stratigraphic layers are labeled to obtain the seismic data of the block.

5. A relative geological time prediction device, characterized in that, The device includes: The segmentation module is used to segment the seismic data of the target land parcel to be predicted, obtaining multiple sub-data of the target land parcel. The seismic data of the land parcel includes seismic data of multiple first-layer layers with labeled relative geological time and seismic data of multiple second-layer layers without labeled relative geological time in the target land parcel. The relative geological time is used to indicate the relative formation time of the layer in the target land parcel. The sub-data of the land parcel includes partial seismic data of at least one layer in the target land parcel. The sub-data of the target land parcel includes partial seismic data of multiple layers, and the multiple layers include at least one first layer. The training module is used to train a relative geological time prediction model based on multiple target plot sub-data, wherein the target plot sub-data is plot sub-data that includes at least one first-layer partial seismic data. The prediction module is used to predict the relative geological time of the multiple plot sub-data based on the trained relative geological time prediction model, and to obtain the predicted relative geological time of each layer in the multiple plot sub-data. The merging module is used to merge the predicted relative geological time of each layer in the multiple plot sub-data to obtain the predicted relative geological time of the multiple second layers. Specifically, based on the target plot sub-data and prediction information, the training loss of the relative geological time prediction model is determined, including: Based on partial seismic data of at least one first layer in the target plot sub-data, the relative geological time of the at least one first layer is obtained; Based on the predicted relative geological time of the at least one first stratum and the relative geological time of the at least one first stratum, a constraint loss of the target block sub-data is determined, the constraint loss being used to indicate the difference between the predicted relative geological time of the at least one first stratum and the relative geological time of the at least one first stratum. Based on the gradient vector of the target plot sub-data, determine the tensor matrix of the target plot sub-data; Using formula (4), singular value decomposition is performed on the tensor matrix to obtain the normal vector of the target plot sub-data and the quality parameter of the normal vector. The quality parameter is used to indicate the accuracy of the normal vector. in, Let u be the tensor matrix of the target plot sub-data. , These are multiple eigenvectors of the tensor matrix. , , Let u be the normal vector of the target plot subdata, and let u be the eigenvalues ​​of the tensor matrix. Then the quality parameter of the normal vector is: ; The structural loss is obtained by weighted summation of the normal vector, the quality parameter, and the gradient vector of the predicted relative geological time using formula (5). The structural loss is used to indicate the difference between the gradient vectors of the predicted relative geological time of the multiple strata and the gradient vectors of the target block sub-data. in, The structural loss of the target plot sub-data is represented by W, where W is the quality parameter. The normal vector is in the horizontal direction unit vector, Let be the unit vector of the normal vector in the vertical direction y. Let be the unit vector of the normal vector in the time direction t. , as well as To predict relative geological time Gradients in the three directions, It is an L2 norm; The training loss is obtained by weighted summation of the structural loss and the constraint loss.

6. A computer device, characterized in that, The computer device includes a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded by the processor and executed as the relative geological time prediction method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store at least one computer program for performing the relative geological time prediction method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the relative geological time prediction method as described in any one of claims 1 to 4.

Images