Seismic attribute image recommendation method and device

Abstract

The invention discloses a seismic attribute image recommendation method and device, and belongs to the field of information processing. The method comprises the following steps: acquiring a plurality of seismic attribute images; performing feature extraction on each seismic attribute image in the plurality of seismic attribute images by adopting a feature extraction model to obtain a seismic attribute feature of each seismic attribute image; determining the similarity between the seismic attribute feature of each seismic attribute image in the plurality of seismic attribute images and the seismic attribute feature of the target seismic image; determining at least one seismic attribute image from the plurality of seismic attribute images according to the similarity between the seismic attribute features of the plurality of seismic attribute images and the seismic attribute features of the target seismic image; and recommending the at least one seismic attribute image. The seismic attribute image screening difficulty and the screening complexity can be simplified, and the screening effect is guaranteed.

Description

Technical Field

[0001] This application relates to the field of information processing, and particularly to a method and device for recommending seismic attribute images. Background Art

[0002] In the process of interpreting seismic data, multiple seismic attribute images can be obtained based on the seismic data, and the types of reservoirs and geological bodies can be predicted based on these seismic attribute images. For example, the types of reservoirs include clastic rock layers, carbonate rock layers, igneous rock layers, etc., and the types of geological bodies include channels, carbonate rock fractures and caves, bioherms, volcanoes, etc. In the process of interpreting seismic data, it is necessary to screen out seismic attribute images with specific seismic attributes from multiple seismic attribute images to predict the types of reservoirs and geological bodies.

[0003] Currently, the screening of seismic attribute images is usually carried out manually. However, manual screening is difficult and the screening process is complex. Summary of the Invention

[0004] This application provides a method and device for recommending seismic attribute images, which can simplify the screening difficulty and complexity of seismic attribute images and ensure the screening effect. The technical solutions of this application are as follows.

[0005] In a first aspect, a method for recommending seismic attribute images is provided. The method includes:

[0006] Obtain multiple seismic attribute images;

[0007] Use a feature extraction model to extract features from each of the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image;

[0008] Determine the similarity between the seismic attribute features of each seismic attribute image in the multiple seismic attribute images and the seismic attribute features of a target seismic image;

[0009] Determine at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image;

[0010] Recommend the at least one seismic attribute image.

[0011] Optionally, the method further includes:

[0012] Obtain a visual set group network;

[0013] Delete the classification sub-network in the visual set group network to obtain an initial feature extraction model;

[0014] Train the initial feature extraction model based on a training image set to obtain the feature extraction model, where the training image set includes multiple historical seismic attribute images.

[0015] Optionally, determining at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image includes:

[0016] Sort the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image;

[0017] Determine at least one seismic attribute image from the multiple seismic attribute images according to the sorting order.

[0018] Optionally, recommending the at least one seismic attribute image includes:

[0019] Display the at least one seismic attribute image on a display interface.

[0020] Optionally, after displaying the at least one seismic attribute image on the display interface, the method further includes:

[0021] Receive an operation instruction triggered by a user on the display interface, where the operation instruction is used to indicate whether the user is satisfied with the at least one seismic attribute image;

[0022] In the case where the operation instruction is used to indicate that the user is not satisfied with the at least one seismic attribute image, update the feature extraction model based on the multiple seismic attribute images, and perform the steps from feature extraction of the multiple seismic attribute images to recommending seismic attribute images based on the updated feature extraction model.

[0023] In a second aspect, a device for recommending seismic attribute images is provided, and the device includes:

[0024] A first acquisition module, configured to acquire multiple seismic attribute images;

[0025] An extraction module, configured to use a feature extraction model to perform feature extraction on each seismic attribute image in the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image;

[0026] A first determination module, configured to determine the similarity between the seismic attribute features of each seismic attribute image in the multiple seismic attribute images and the seismic attribute features of a target seismic image;

[0027] A second determination module, configured to determine at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image;

[0028] A recommendation module, configured to recommend the at least one seismic attribute image.

[0029] Optionally, the apparatus further includes:

[0030] A second acquisition module, configured to acquire a visual set group network;

[0031] A deletion module, configured to delete a classification sub-network in the visual set group network to obtain an initial feature extraction model;

[0032] A training module, configured to train the initial feature extraction model based on a training image set to obtain the feature extraction model, where the training image set includes multiple historical seismic attribute images.

[0033] Optionally, the second determination module is configured to:

[0034] Sort the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image;

[0035] Determine at least one seismic attribute image from the multiple seismic attribute images according to the sorting order.

[0036] Optionally, the recommendation module is configured to display the at least one seismic attribute image on a display interface.

[0037] Optionally, the apparatus further includes:

[0038] A receiving module, configured to receive an operation instruction triggered by a user on the display interface after the recommendation module displays the at least one seismic attribute image on the display interface, where the operation instruction is used to indicate whether the user is satisfied with the at least one seismic attribute image;

[0039] An update module, configured to, when the operation instruction is used to indicate that the user is not satisfied with the at least one seismic attribute image, update the feature extraction model based on the multiple seismic attribute images, and trigger the extraction module, the first determination module, the second determination module, and the recommendation module to sequentially execute steps of performing feature extraction on the multiple seismic attribute images to recommending seismic attribute images based on the updated feature extraction model.

[0040] In a third aspect, a recommendation apparatus for seismic attribute images is provided, including a memory and a processor;

[0041] The memory is used to store a computer program;

[0042] The processor is used to execute the computer program stored in the memory so that the seismic attribute image recommendation device executes the seismic attribute image recommendation method provided in the first aspect or any optional implementation manner of the first aspect.

[0043] In a fourth aspect, a computer device is provided. The computer device may be a terminal device such as a smart phone, a tablet computer, a laptop computer, or a desktop computer. The computer device includes the seismic attribute image recommendation device provided in the second aspect or any optional implementation manner of the second aspect, or the computer device includes the seismic attribute image recommendation device provided in the third aspect.

[0044] In a fifth aspect, a computer-readable storage medium is provided. A computer program is stored in the computer-readable storage medium, and when the computer program is executed, the seismic attribute image recommendation method provided in the first aspect or any optional manner of the first aspect is implemented.

[0045] In a sixth aspect, a computer program product is provided. The computer program product includes a program or code, and when the program or code is executed, the seismic attribute image recommendation method provided in the first aspect or any optional manner of the first aspect is implemented.

[0046] The beneficial effects brought by the technical solution provided in this application include:

[0047] For the seismic attribute image recommendation method and device provided in this application, the recommendation method is executed by the seismic attribute image recommendation device. After the recommendation device obtains multiple seismic attribute images, a feature extraction model is used to extract features of each seismic attribute image in the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image. The recommendation device determines at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image, and recommends the at least one seismic attribute image. Thus, in this application, the recommendation device screens seismic attribute images with seismic attribute features relatively similar to those of the target seismic image from multiple seismic attribute images, that is, the recommendation device screens seismic attribute images according to the similarity. Compared with manual screening of seismic attribute images, the difficulty and complexity of screening can be simplified, and the screening effect can be guaranteed. Description of the Drawings

[0048] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0049] Figure 1 is a flowchart of a method for recommending seismic attribute images provided by an embodiment of the present application;

[0050] Figure 2 is a schematic diagram of a display interface provided by an embodiment of the present application;

[0051] Figure 3 is a schematic diagram of another display interface provided by an embodiment of the present application;

[0052] Figure 4 is a flowchart of another method for recommending seismic attribute images provided by an embodiment of the present application;

[0053] Figure 5 is a schematic diagram of a device for recommending seismic attribute images provided by an embodiment of the present application;

[0054] Figure 6 is a schematic diagram of another device for recommending seismic attribute images provided by an embodiment of the present application.

[0055] The accompanying drawings here are incorporated into the specification and form a part of the specification, showing the embodiments in line with the present application, and are used together with the specification to explain the principles of the present application. Detailed Embodiments

[0056] In order to make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the present application in detail with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0057] In the process of interpreting seismic data, multiple seismic attribute images can be obtained based on the seismic data, and the types of reservoirs and geological bodies can be predicted based on these seismic attribute images. For example, seismic attribute images are obtained from seismic data, seismic attribute images are generated based on seismic data, etc. Among them, the types of reservoirs include clastic rock layers, carbonate rock layers, igneous rock layers, etc., and the types of geological bodies include channels, carbonate rock fractures and caves, bioherms, volcanoes, etc. In the process of interpreting seismic data, it is necessary to screen out seismic attribute images with specific seismic attributes from multiple seismic attribute images to predict the types of reservoirs and geological bodies.

[0058] Currently, the screening of seismic attribute images is usually carried out manually. For example, manually screen seismic attribute images with seismic attributes from multiple seismic attribute images according to the effectiveness of the multiple seismic attribute images, the coincidence rate of the multiple seismic attribute images with well logging data, etc. However, the manual screening is difficult, the screening process is complex, and the seismic attribute images screened manually may be poor, and the screening effect is poor.

[0059] The embodiments of the present application provide a method and device for recommending seismic attribute images. The method for recommending seismic attribute images is executed by a device for recommending seismic attribute images. After obtaining multiple seismic attribute images, the recommendation device extracts features of each seismic attribute image in the multiple seismic attribute images by using a feature extraction model to obtain the seismic attribute features of each seismic attribute image. The recommendation device determines at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of a target seismic image, and recommends the at least one seismic attribute image. Thus, in the embodiments of the present application, the recommendation device screens seismic attribute images with seismic attribute features that are relatively similar to the seismic attribute features of the target seismic image from multiple seismic attribute images, that is, the recommendation device screens seismic attribute images according to the similarity. Compared with the manual screening of seismic attribute images, the screening difficulty and complexity can be simplified, and the screening effect can be guaranteed.

[0060] The embodiments of the method for recommending seismic attribute images of the present application are introduced below.

[0061] Please refer to Figure 1 , which shows a flowchart of a method for recommending seismic attribute images provided by an embodiment of the present application. The method for recommending seismic attribute images is executed by a device for recommending seismic attribute images (hereinafter simply referred to as the recommendation device). The method for recommending seismic attribute images includes the following steps S101 to S105.

[0062] S101. Obtain multiple seismic attribute images.

[0063] In an optional embodiment, the recommendation device obtains multiple seismic attribute images based on seismic data. Specifically, the recommendation device inputs the seismic data into seismic attribute extraction software, which is used to extract seismic attributes from the seismic data, generate multiple seismic attribute images based on the seismic attributes, and output the multiple seismic attribute images. The recommendation device obtains the multiple seismic attribute images output by the seismic attribute extraction software. For example, the seismic attribute extraction software is GeoEast (an integrated software system for seismic data processing and interpretation). Among them, the seismic data is obtained by a seismic detection instrument after seismic testing of the work area.

[0064] S102. Use a feature extraction model to perform feature extraction on each of the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image.

[0065] Wherein, the feature extraction model is used to extract seismic attribute features from seismic attribute images.

[0066] In one embodiment, for each of the multiple seismic attribute images, the recommendation device inputs the seismic attribute image into the feature extraction model. The feature extraction model performs feature extraction on the seismic attribute image to obtain the seismic attribute features of the seismic attribute image, and outputs the seismic attribute features of the seismic attribute image. The recommendation device obtains the seismic attribute features output by the feature extraction model.

[0067] Optionally, before S102, the recommendation device obtains the feature extraction model. For example, the recommendation device obtains the pre-trained feature extraction model. Or the recommendation device trains the feature extraction model. In this embodiment of the present application, the example of the recommendation device training the feature extraction model is used for illustration. In one embodiment, the recommendation device obtains a Visual Geometry Group (VGG) 16 network, and the VGG16 network includes a feature extraction sub-network and a classification sub-network. For example, the VGG16 network includes multiple network layers, and the classification sub-network is the last network layer in the VGG16 network. The recommendation device deletes the classification sub-network in the VGG16 network to obtain an initial feature extraction model. The recommendation device trains the initial feature extraction model based on a training image set to obtain the feature extraction model, and the training image set includes multiple historical seismic attribute images. By way of example, the recommendation device uses the remaining part after deleting the classification sub-network in the VGG16 as the initial feature extraction model. For example, the remaining part is the feature extraction sub-network, and the recommendation device uses the feature extraction sub-network as the initial feature extraction model.

[0068] In one embodiment, the training image set for training the feature extraction model includes multiple historical seismic attribute images. For each historical seismic attribute image in the multiple historical seismic attribute images, the recommendation device inputs the historical seismic attribute image into the initial feature extraction model, enabling the initial feature extraction model to perform feature extraction on the historical seismic attribute image to obtain the seismic attribute features of the historical seismic attribute image. The recommendation device adjusts the model parameters of the initial feature extraction model according to the seismic attribute features of the historical seismic attribute image until the termination condition is satisfied. The recommendation device determines the feature extraction model obtained when the termination condition is satisfied as the finally trained feature extraction model. Among them, in order to ensure the training effect of the feature extraction model, the multiple historical seismic attribute images come from different work areas. That is, the multiple historical seismic attribute images are seismic attribute images obtained by performing seismic tests on different work areas.

[0069] In a specific embodiment, each historical seismic attribute image among the multiple historical seismic attribute images corresponds to a standard seismic attribute feature. The standard seismic attribute feature corresponding to each historical seismic attribute image can be obtained by manually or by a computer annotating the historical seismic attribute image, and the standard seismic attribute feature corresponding to each historical seismic attribute image can be the actual seismic attribute feature of the historical seismic attribute image. For each historical seismic attribute image among the multiple historical seismic attribute images: the recommendation device inputs the historical seismic attribute image into the initial feature extraction model, enabling the initial feature extraction model to extract features from the historical seismic attribute image to obtain the seismic attribute feature of the historical seismic attribute image. The recommendation device adjusts the model parameters of the initial feature extraction model according to the difference between the seismic attribute feature of the historical seismic attribute image extracted by the initial feature extraction model and the standard seismic attribute feature corresponding to the historical seismic attribute image; the recommendation device inputs the historical seismic attribute image into the model with adjusted parameters, enabling the model with adjusted parameters to extract features from the historical seismic attribute image again to obtain the seismic attribute feature of the historical seismic attribute image; the recommendation device adjusts the model parameters again according to the difference between the seismic attribute feature of the historical seismic attribute image obtained by extracting features again and the standard seismic attribute feature corresponding to the historical seismic attribute image, and then extracts features again; the recommendation device repeats the process of inputting the historical seismic attribute image to adjust the model parameters for model training until a termination condition is met. Among them, the process from inputting the historical seismic attribute image to adjusting the model parameters is an iterative process. The termination condition includes at least one of the following: the difference between the seismic attribute feature of the historical seismic attribute image extracted by the feature extraction model and the standard seismic attribute feature corresponding to the historical seismic attribute image is less than a preset difference; the number of training iterations (i.e., the number of iterative processes during the training process) reaches a preset number; the change in the seismic attribute features obtained by the feature extraction model continuously extracting features from the same historical seismic attribute image multiple times is small.

[0070] It should be noted that the VGG16 network adopted in the embodiments of the present application is the VGG16 network after being trained using the ImageNet dataset. The VGG16 network includes a feature extraction sub-network and a classification sub-network, so that the VGG16 network has a feature extraction function and a classification function. Among them, the VGG16 network is a deep convolutional neural network in the field of deep learning technology. The VGG16 network can learn the internal laws of the sample data input into the VGG16 network to obtain the information contained in the sample data.

[0071] The embodiments of the present application take the feature extraction model as the VGG16 network model as an example for illustration, which does not constitute a limitation on the embodiments of the present application. The feature extraction model can also be any other possible network model.

[0072] S103. Determine the similarity between the seismic attribute features of each seismic attribute image in the multiple seismic attribute images and the seismic attribute features of the target seismic image.

[0073] Among them, the target seismic image is an image with target seismic attributes, and the target seismic attributes are the seismic attributes that need to be explored (or called identified) in the embodiments of the present application. For example, the target seismic image is a seismic attribute image with clastic rock formations, carbonate rock formations or igneous rock formations, or the target seismic image is a seismic attribute image with channels, carbonate rock fractures and caves, bioherms or volcanoes. The embodiments of the present application do not make limitations on this.

[0074] In an optional embodiment, the recommendation device obtains the seismic attribute features of the target seismic image. For each seismic attribute image in the multiple seismic attribute images, the recommendation device calculates the similarity between the seismic attribute features of the seismic attribute image and the seismic attribute features of the target seismic image based on a similarity algorithm. By way of example, the similarity is represented by the Euclidean distance. For each seismic attribute image in the multiple seismic attribute images, the recommendation device calculates the Euclidean distance between the seismic attribute features of the seismic attribute image and the seismic attribute features of the target seismic image through the Euclidean distance formula, and the recommendation device determines the Euclidean distance between the seismic attribute features of the seismic attribute image and the seismic attribute features of the target seismic image as the similarity between the seismic attribute features of the seismic attribute image and the seismic attribute features of the target seismic image. It should be noted that for each seismic attribute image in the multiple seismic attribute images, the greater the similarity between the seismic attribute features of the seismic attribute image and the seismic attribute features of the target seismic image, the more similar the seismic attribute image is to the target seismic image. The smaller the similarity between the seismic attribute features of the seismic attribute image and the seismic attribute features of the target seismic image, the less similar the seismic attribute image is to the target seismic image.

[0075] In an optional embodiment, the recommendation device stores the seismic attribute features of the target seismic image, and the recommendation device obtains the seismic attribute features of the target seismic image from the storage space of the recommendation device. Alternatively, in S102, the recommendation device extracts the seismic attribute features of the target seismic image by using a feature extraction model.

[0076] S104. Determine at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image.

[0077] In an alternative embodiment, the recommendation device obtains a recommended quantity, and the number of at least one seismic attribute image determined by the recommendation device from the multiple seismic attribute images is equal to the recommended quantity. For example, the recommendation device obtains the recommended quantity input by the user. For instance, the recommendation device includes a human-computer interaction component, and the user inputs the recommended quantity to the recommendation device through the human-computer interaction component. Among them, the human-computer interaction component can be a voice input component, a touch display component, etc., and the touch display component can be a touch screen.

[0078] In one embodiment, the recommendation device sorts the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image, and the recommendation device determines (or selects) at least one seismic attribute image from the multiple seismic attribute images according to the sorting order. For example, the recommendation device sorts the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image, and uses a bubble sort algorithm, a selection sort algorithm, or an insertion sort algorithm to sort the multiple seismic attribute images. The similarity between the seismic attribute features of at least one seismic attribute image determined by the recommendation device from the multiple seismic attribute images according to the sorting order and the seismic attribute features of the target seismic image is relatively large. For example, the recommendation device sorts the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image in descending order of similarity, and the recommendation device determines the first n seismic attribute images in the sorting order as the at least one seismic attribute image, where n is a positive integer.

[0079] In another embodiment, the recommendation device determines, from the multiple seismic attribute images, seismic attribute images whose similarity between the seismic attribute features and the seismic attribute features of the target seismic image is greater than a similarity threshold, and the recommendation device determines the seismic attribute images whose similarity between the seismic attribute features and the seismic attribute features of the target seismic image is greater than the similarity threshold in the multiple seismic attribute images as the at least one seismic attribute image.

[0080] S105. Recommend the at least one seismic attribute image.

[0081] In an alternative embodiment, after the recommendation device determines (or selects) at least one seismic attribute image that is relatively similar to the target seismic image from the multiple seismic attribute images, the recommendation device reads the at least one seismic attribute image and displays the at least one seismic attribute image on a display interface to recommend the at least one seismic attribute image to the user. For example, the recommendation device displays the at least one seismic attribute image on the display interface through the display component of the recommendation device. The image reading function of the recommendation device is developed based on an image reading module provided by TensorFlow (a deep learning framework).

[0082] In one embodiment, as Figure 2 shown, it shows a schematic diagram of a display interface provided by an embodiment of the present application. The display interface includes a first display area A1 and a second display area A2. In the first display area A1, m seismic attribute images to be screened are displayed. In the second display area A2, a display box A21 is displayed. In the display box A21, a recommended quantity, a similarity algorithm used by the recommended device to screen the seismic attribute images, a recommended progress bar, a start button, a cancel button, a close button, etc. are displayed. The user can trigger a start instruction by clicking the start button. After the recommended device receives the start instruction, the recommended device uses a feature extraction model to extract features of each of the m seismic attribute images to obtain seismic attribute features of each seismic attribute image. And, the recommended device determines at least one seismic attribute image from the m seismic attribute images according to the similarity between the seismic attribute features of the m seismic attribute images and the seismic attribute features of a target seismic image. The quantity of the at least one seismic attribute image is equal to the recommended quantity. During the process of the recommended device screening the seismic attribute images (that is, during the process from receiving the start instruction to determining at least one seismic attribute image), the recommended progress bar in the display box A21 changes continuously to indicate that the recommended progress is increasing continuously. When the recommended progress bar indicates that the recommended progress reaches 100%, the recommended device determines the at least one seismic attribute image, and then the recommended device outputs the at least one seismic attribute image. By way of example, the recommended quantity is 9. When Figure 2 the recommended progress bar in the shown display interface indicates that the recommended progress reaches 100%, the recommended device displays a display interface as Figure 3 shown to recommend 9 seismic attribute images determined from the m seismic attribute images to the user.

[0083] During the process of the recommended device screening the seismic attribute images, the user can also trigger a cancel instruction by clicking the cancel button in the display box A21. After the recommended device receives the cancel instruction, it stops the process of screening the seismic attribute images. And, the user can also trigger a close instruction by clicking the close button. After the recommended device receives the close instruction, it closes the display box A21.

[0084] In an alternative embodiment, after the recommendation device displays the at least one seismic attribute image on the display interface, the user triggers an operation instruction on the display interface, and the recommendation device receives the operation instruction triggered by the user on the display interface. The operation instruction is used to indicate whether the user is satisfied with the at least one seismic attribute image. In one embodiment, when the operation instruction is used to indicate that the user is satisfied with the at least one seismic attribute image, it means that the seismic attribute features obtained by feature extraction of the seismic attribute image based on the feature extraction model meet the expectations, and the recommendation device ends the recommendation process. In another embodiment, when the operation instruction is used to indicate that the user is not satisfied with the at least one seismic attribute image, it means that the seismic attribute features obtained by feature extraction of the seismic attribute image based on the feature extraction model do not meet the expectations. The recommendation device updates the feature extraction model based on the multiple seismic attribute images, and executes the above S102 to S105 based on the updated feature extraction model. Specifically, for each seismic attribute image in the multiple seismic attribute images, the recommendation device uses the updated feature extraction model to perform feature extraction on the seismic attribute image to obtain the seismic attribute features of the seismic attribute image. The recommendation device determines the similarity between the seismic attribute features of the seismic attribute image extracted by the updated feature extraction model and the seismic attribute features of the target seismic image. The recommendation device determines at least one seismic attribute image from the multiple seismic attribute images and recommends at least one seismic attribute image according to the similarity between the seismic attribute features of the multiple seismic attribute images extracted by the updated feature extraction model and the seismic attribute features of the target seismic image. For example, the recommendation device displays the at least one seismic attribute image on the display interface. After the recommendation device displays the at least one seismic attribute image on the display interface, the user can continue to trigger an operation instruction on the display interface. The recommendation device receives the operation instruction triggered by the user on the display interface. When the operation instruction is used to indicate that the user is not satisfied with the at least one seismic attribute image, the recommendation device re-updates the feature extraction model based on the multiple seismic attribute images, and executes the above S102 to S105 based on the updated feature extraction model, and repeats this process until the user is satisfied with the recommended seismic attribute images.

[0085] Exemplarily, as Figure 3 shown, 9 seismic attribute images determined by the recommendation device from the m seismic attribute images are displayed on the display interface, and a satisfied button and a dissatisfied button are also displayed. The user can click the satisfied button or the dissatisfied button on the display interface to trigger an operation instruction. For example, the operation instruction triggered by the user clicking the satisfied button is used to indicate that the user is satisfied Figure 3The nine seismic attribute images shown in [the figure], this operation instruction is also called a satisfaction instruction, and the recommendation device ends the recommendation process after receiving this satisfaction instruction. For another example, the operation instruction triggered by the user clicking the dissatisfaction button in the display interface is used to indicate that the user is dissatisfied. Figure 3 The nine seismic attribute images shown in [the figure], this operation instruction is also called a dissatisfaction instruction. After the recommendation device receives this dissatisfaction instruction, it updates the feature extraction model based on the above-mentioned m seismic attribute images, and executes the above S102 to S105 based on the updated feature extraction model, and repeats this process until the user is satisfied with the recommended seismic attribute images.

[0086] As an example, as Figure 4 shown, after the recommendation device obtains the target seismic image and multiple seismic attribute images, the recommendation device preprocesses the target seismic image and the multiple seismic attribute images respectively. For example, the preprocessing includes: modifying the format of the seismic attribute image to a format that meets the requirements of the feature extraction model, such as JPG format or PNG format, and modifying the size of the seismic attribute image to the size required by the feature extraction model (for example, 224×224), etc. The recommendation device obtains the feature extraction model. For each seismic attribute image in the preprocessed target seismic image and the preprocessed multiple seismic attribute images, the recommendation device uses the feature extraction model to extract the seismic attribute features of the seismic attribute image to obtain the seismic attribute features of the seismic attribute image. The recommendation device determines the similarity between the seismic attribute features of each seismic attribute image in the multiple seismic attribute images and the seismic attribute features of the target seismic image. The recommendation device determines at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image, and recommends the at least one seismic attribute image. When the user is satisfied with the at least one seismic attribute image, the recommendation device ends the recommendation process. When the user is not satisfied with the at least one seismic attribute image, the recommendation device re-obtains the feature extraction model (that is, updates the feature extraction model based on the multiple seismic attribute images), and the recommendation device executes the steps from extracting the features of the multiple seismic attribute images to recommending the seismic attribute images based on the updated feature extraction model. Repeat this process until the user is satisfied and the recommendation process ends.

[0087] In summary, for the method for recommending seismic attribute images provided in the embodiments of the present application, after obtaining multiple seismic attribute images, the recommendation device uses a feature extraction model to extract features from each of the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image. The recommendation device determines at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image, and recommends the at least one seismic attribute image. Thus, in the embodiments of the present application, the recommendation device screens out seismic attribute images whose seismic attribute features are relatively similar to the seismic attribute features of the target seismic image from the multiple seismic attribute images, that is, the recommendation device screens the seismic attribute images according to the similarity. Compared with manual screening of seismic attribute images, the difficulty and complexity of screening can be simplified, and the screening effect can be guaranteed.

[0088] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0089] Please refer to Figure 5 , which shows a schematic diagram of a recommendation device 500 for seismic attribute images provided in the embodiments of the present application. The recommendation device 500 is used to execute Figure 1 the method provided in the shown embodiment. The recommendation device 500 includes a first acquisition module 501, an extraction module 502, a first determination module 503, a second determination module 504, and a recommendation module 505.

[0090] The first acquisition module 501 is configured to acquire multiple seismic attribute images;

[0091] The extraction module 502 is configured to use a feature extraction model to extract features from each of the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image;

[0092] The first determination module 503 is configured to determine the similarity between the seismic attribute features of each seismic attribute image in the multiple seismic attribute images and the seismic attribute features of the target seismic image;

[0093] The second determination module 504 is configured to determine at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image;

[0094] The recommendation module 505 is configured to recommend the at least one seismic attribute image.

[0095] Optionally, please continue to refer to Figure 5 , the recommendation device 500 further includes:

[0096] A second acquisition module 506, configured to acquire a visual set group network;

[0097] A deletion module 507, configured to delete a classification sub-network in the visual set group network to obtain an initial feature extraction model;

[0098] A training module 508, configured to train the initial feature extraction model based on a training image set to obtain the feature extraction model, where the training image set includes multiple historical seismic attribute images.

[0099] Optionally, a second determination module 504 is configured to:

[0100] Sort the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image;

[0101] Determine at least one seismic attribute image from the multiple seismic attribute images according to the sorting order.

[0102] Optionally, a recommendation module 505 is configured to display the at least one seismic attribute image in a display interface.

[0103] Optionally, please continue to refer to Figure 5 , the recommendation device 500 further includes:

[0104] A receiving module 509, configured to receive an operation instruction triggered by a user in the display interface after the recommendation module displays the at least one seismic attribute image in the display interface, where the operation instruction is used to indicate whether the user is satisfied with the at least one seismic attribute image;

[0105] An update module 510, configured to, when the operation instruction is used to indicate that the user is not satisfied with the at least one seismic attribute image, update the feature extraction model based on the multiple seismic attribute images, and trigger the extraction module 502, the first determination module 503, the second determination module 504, and the recommendation module 505 to sequentially execute steps of performing feature extraction on the multiple seismic attribute images to recommending seismic attribute images based on the updated feature extraction model.

[0106] In summary, for the technical solution provided in the embodiment of the present application, after the recommendation device obtains multiple seismic attribute images, a feature extraction model is used to extract features from each of the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image. The recommendation device determines at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image, and recommends the at least one seismic attribute image. Thus, in the embodiment of the present application, the recommendation device screens out the seismic attribute images whose seismic attribute features are relatively similar to the seismic attribute features of the target seismic image from the multiple seismic attribute images. That is, the recommendation device screens the seismic attribute images according to the similarity. Compared with manual screening of seismic attribute images, the difficulty and complexity of screening can be simplified, and the screening effect can be guaranteed.

[0107] The embodiment of the present application provides a recommendation device for seismic attribute images, including a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory so that the recommendation device executes the method for recommending seismic attribute images provided in the above embodiment.

[0108] As an example, please refer to Figure 6 , which shows a schematic diagram of another recommendation device 600 for seismic attribute images provided in the embodiment of the present application. The recommendation device 600 is a computer device or a functional component deployed in a computer device. The computer device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc. The recommendation device 600 is used to execute Figure 1 the method provided in the illustrated embodiment.

[0109] Generally, the recommendation device 600 includes: a processor 601 and a memory 602.

[0110] The processor 601 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. The processor 601 may be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), or programmable logic array (PLA). The processor 601 may include, but is not limited to, a central processing unit (CPU). In some embodiments, the processor 601 may be integrated with a graphics processing unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. The processor 601 may also include an artificial intelligence (AI) processor to process computational operations related to machine learning.

[0111] The memory 602 includes one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory 602 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 601 to implement the method for recommending seismic attribute images provided in the embodiments of the present application.

[0112] In some embodiments, the recommendation device 600 may also optionally include: a peripheral device interface 603 and at least one peripheral device. The processor 601, the memory 602, and the peripheral device interface 603 may be connected through a bus or signal lines. Each peripheral device may be connected to the peripheral device interface 603 through a bus, signal lines, or a circuit board. The peripheral device may include at least one of a radio frequency circuit 604, a display screen 605, a camera 606, an audio circuit 607, a positioning component 608, and a power supply 609.

[0113] The peripheral device interface 603 may be used to connect at least one peripheral device related to input / output (I / O) to the processor 601 and the memory 602. In some embodiments, the processor 601, the memory 602, and the peripheral device interface 603 are integrated on the same chip or circuit board; in some embodiments, any one or two of the processor 601, the memory 602, and the peripheral device interface 603 may be implemented on a separate chip or circuit board, and this embodiment does not limit this.

[0114] The radio frequency circuit 604 is used to receive and transmit radio frequency (RF) signals, also known as electromagnetic signals. The radio frequency circuit 604 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 604 converts electrical signals into electromagnetic signals for transmission, or converts the received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 604 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, and so on. The radio frequency circuit 504 can communicate with other devices through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, metropolitan area network, intranet, generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area network. The embodiments of the present application do not limit this.

[0115] The display screen 605 is used to display a user interface (UI). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 605 is a touch display screen, the display screen 605 also has the ability to collect touch signals on or above the surface of the display screen 605. The touch signal can be input to the processor 601 as a control signal for processing. At this time, the display screen 605 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, the display screen 605 can be a flexible display screen. Even, the display screen 605 can be set to an irregular non-rectangular shape, that is, an irregular-shaped screen. The display screen 605 can be a liquid crystal display (LCD), an organic light-emitting diode (OLED) display screen, etc.

[0116] The camera module 606 is used to collect images or videos. Optionally, the camera module 606 includes a front camera and a rear camera. Optionally, the computer device is a terminal device such as a smart phone or a tablet computer. Generally, the front camera is set on the front panel of the computer device, and the rear camera is set on the back of the computer device. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth camera, a wide-angle camera, and a telephoto camera, to realize the function of background blurring by fusing the main camera and the depth camera, panoramic shooting by fusing the main camera and the wide-angle camera, and virtual reality (VR) shooting function or other fusion shooting functions. In some embodiments, the camera module 606 can also include a flash. The flash can be a single-color temperature flash or a two-color temperature flash. The two-color temperature flash refers to the combination of a warm light flash and a cold light flash, which can be used for light compensation under different color temperatures.

[0117] The audio circuit 607 may include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, convert the sound waves into electrical signals and input the electrical signals to the processor 601 for processing, or input the electrical signals to the radio frequency circuit 604 to achieve voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the computer device. The microphone may also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert the electrical signals from the processor 601 or the radio frequency circuit 604 into sound waves. The speaker may be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into sound waves audible to humans, but also convert electrical signals into sound waves inaudible to humans for uses such as ranging.

[0118] The positioning component 608 is used to locate the geographical position of the computer device to achieve navigation or location based service (LBS). The positioning component 608 may be a positioning component based on the global positioning system (GPS), the Beidou system or the Galileo system.

[0119] The power supply 609 is used to supply power to each component in the computer device. The power supply 609 may be alternating current, direct current, a disposable battery or a rechargeable battery. When the power supply 609 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil.

[0120] In some embodiments, the volume determination device 600 further includes one or more sensors 610. The one or more sensors 610 include but are not limited to: a fingerprint sensor 611, an optical sensor 612, a proximity sensor 613, a pressure sensor 614, an acceleration sensor 615 and a gyroscope sensor 616.

[0121] The fingerprint sensor 611 is used to collect the user's fingerprint. The processor 601 identifies the user's identity according to the fingerprint collected by the fingerprint sensor 611, or the fingerprint sensor 611 identifies the user's identity according to the collected fingerprint. When the identity of the user is identified as a trusted identity, the processor 601 authorizes the user to perform relevant sensitive operations, and the sensitive operations include unlocking the screen, viewing encrypted information, downloading software, making payments and changing settings, etc. The fingerprint sensor 611 may be arranged on the front, back or side of the computer device. When there are physical buttons or manufacturer logos on the computer device, the fingerprint sensor 611 may be integrated with the physical buttons or manufacturer logos.

[0122] The optical sensor 612 is used to collect the ambient light intensity. In one embodiment, the processor 601 can control the display brightness of the display screen 605 according to the ambient light intensity collected by the optical sensor 612. Specifically, when the ambient light intensity is high, the display brightness of the display screen 605 is increased; when the ambient light intensity is low, the display brightness of the display screen 605 is decreased. In another embodiment, the processor 601 can also dynamically adjust the shooting parameters of the camera module 607 according to the ambient light intensity collected by the optical sensor 612.

[0123] The proximity sensor 613, also known as the distance sensor, is usually disposed on the front panel of the display screen 605 of the computer device. The proximity sensor 613 is used to collect the distance between the user and the display screen 605. In one embodiment, when the proximity sensor 613 detects that the distance between the user and the display screen 605 is gradually decreasing, the processor 601 controls the display screen 605 to switch from the lit state to the off state; when the proximity sensor 613 detects that the distance between the user and the display screen 605 is gradually increasing, the processor 601 controls the display screen 605 to switch from the off state to the lit state.

[0124] The pressure sensor 614 can be disposed on the side frame of the computer device and / or the lower layer of the touch display screen 605. When the pressure sensor 614 is disposed on the side frame of the computer device, it can detect the holding signal of the user on the computer device, and the processor 601 performs left / right hand recognition or shortcut operations according to the holding signal collected by the pressure sensor 614. When the pressure sensor 614 is disposed on the lower layer of the touch display screen 605, the processor 601 controls the operable controls on the UI interface according to the pressure operation of the user on the touch display screen 605. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0125] The acceleration sensor 615 can detect the magnitudes of the accelerations on the three coordinate axes of the coordinate system established with the computer device. For example, the acceleration sensor 615 can be used to detect the components of the gravitational acceleration on the three coordinate axes. The processor 601 can control the touch display screen 605 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 615. The acceleration sensor 615 can also be used for collecting game or user's motion data.

[0126] The gyroscope sensor 616 can detect the body direction and rotation angle of the computer device. The gyroscope sensor 616 can cooperate with the acceleration sensor 615 to collect the 3D actions of the user on the computer device. According to the data collected by the gyroscope sensor 612, the processor 601 can implement the following functions: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0127] Those skilled in the art can understand that Figure 6 the structure shown in does not constitute a limitation on the recommendation device 600. The recommendation device 600 may include more or fewer components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0128] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed (for example, when executed by a computer device, a recommendation device for seismic attribute images, one or more processors, etc.), all or part of the steps of the method for recommending seismic attribute images provided in the above embodiment are implemented.

[0129] An embodiment of the present application provides a computer program product, which includes a program or code. When the program or code is executed (for example, when executed by a computer device, a recommendation device for seismic attribute images, one or more processors, etc.), all or part of the steps of the method for recommending seismic attribute images provided in the above embodiment are implemented.

[0130] It should be understood that the term "at least one" in the present application refers to one or more, and "a plurality" refers to two or more. The term "and / or" in the present application is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, for the convenience of clear description, in the present application, terms such as "first", "second", "third", etc. are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms such as "first", "second", "third", etc. do not limit the quantity and execution order.

[0131] The method embodiments, device embodiments, and other different types of embodiments provided in the present application can all refer to each other, and the present application embodiments do not limit this. The order of operations in the method embodiments provided in the present application can be appropriately adjusted, and the operations can also be increased or decreased according to the situation. Any method that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered within the protection scope of the present application, so details will not be described herein.

[0132] In the corresponding embodiments provided in the present application, it should be understood that the disclosed devices, etc. can be implemented in other constitutive manners. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0133] The modules described as separate components may or may not be physically separated, and the components described as modules may or may not be physical modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] As mentioned above, it is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for recommending seismic attribute images, characterized in that, the method includes: Obtain multiple seismic attribute images; Use a feature extraction model to extract features from each of the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image; Determine the similarity between the seismic attribute features of each seismic attribute image among the multiple seismic attribute images and the seismic attribute features of the target seismic image; Determine at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image; Recommend the at least one seismic attribute image.

2. The method according to claim 1, characterized in that, the method further includes: Obtain a visual set group network; Delete the classification sub-network in the visual set group network to obtain an initial feature extraction model; Train the initial feature extraction model based on a training image set to obtain the feature extraction model, where the training image set includes multiple historical seismic attribute images.

3. The method according to claim 1 or 2, characterized in that, the determining at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image includes: Sort the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image; Determine at least one seismic attribute image from the multiple seismic attribute images according to the sorting order.

4. The method according to any one of claims 1 to 3, characterized in that, the recommending the at least one seismic attribute image includes: Display the at least one seismic attribute image on a display interface.

5. The method according to claim 4, characterized in that, after displaying the at least one seismic attribute image on the display interface, the method further includes: Receive an operation instruction triggered by the user on the display interface, where the operation instruction is used to indicate whether the user is satisfied with the at least one seismic attribute image; In the case where the operation instruction is used to indicate that the user is not satisfied with the at least one seismic attribute image, update the feature extraction model based on the multiple seismic attribute images, and execute the steps from feature extraction of the multiple seismic attribute images to recommending seismic attribute images based on the updated feature extraction model.

6. A device for recommending seismic attribute images, characterized in that, the device includes: A first acquisition module for obtaining multiple seismic attribute images; An extraction module for using a feature extraction model to extract features from each of the multiple seismic attribute images to obtain the seismic attribute features of each seismic attribute image; A first determination module for determining the similarity between the seismic attribute features of each seismic attribute image among the multiple seismic attribute images and the seismic attribute features of the target seismic image; A second determination module, configured to determine at least one seismic attribute image from the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image; A recommendation module, configured to recommend the at least one seismic attribute image.

7. The apparatus according to claim 6, wherein, the apparatus further includes: A second acquisition module, configured to acquire a visual collective group network; A deletion module, configured to delete the classification sub-network in the visual collective group network to obtain an initial feature extraction model; A training module, configured to train the initial feature extraction model based on a training image set to obtain the feature extraction model, wherein the training image set includes multiple historical seismic attribute images.

8. The apparatus according to claim 6 or 7, wherein, the second determination module is configured to: sort the multiple seismic attribute images according to the similarity between the seismic attribute features of the multiple seismic attribute images and the seismic attribute features of the target seismic image; determine at least one seismic attribute image from the multiple seismic attribute images according to the sorting order.

9. The apparatus according to any one of claims 6 to 8, wherein, the recommendation module is configured to display the at least one seismic attribute image in a display interface.

10. The apparatus according to claim 9, wherein, the apparatus further includes: A receiving module, configured to receive an operation instruction triggered by a user in the display interface after the recommendation module displays the at least one seismic attribute image in the display interface, where the operation instruction is used to indicate whether the user is satisfied with the at least one seismic attribute image; An update module, configured to, when the operation instruction is used to indicate that the user is not satisfied with the at least one seismic attribute image, update the feature extraction model based on the multiple seismic attribute images, and trigger the extraction module, the first determination module, the second determination module, and the recommendation module to sequentially execute the steps of performing feature extraction on the multiple seismic attribute images to recommending seismic attribute images based on the updated feature extraction model.

Images