Geological structural background prediction method, device and storage medium

Abstract

The present invention relates to a geological structure background prediction method, device and storage medium, the method comprising: obtaining multiple rock geochemical element data; preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element; constructing a corresponding target image according to each target rock geochemical element data, and dividing all target images into training samples and prediction samples; training according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model; using the rock geochemical element data to determine the rock type, the rock geochemical element data is a set of chemical element content sequences, and the order relationship is from the smallest content to the largest content. Through this technical solution, the accuracy and efficiency of geological structure background classification prediction are improved.

Description

Technical Field

[0001] The present invention relates to the field of geological structure technology, and in particular to a geological structure background prediction method, device and storage medium. Background Art

[0002] The geological structure process in the existing technology is to first obtain visible light data of the study area, then draw a geological structure map based on the geological background, and finally conduct on-site surveys to further improve the accuracy of structural interpretation. The shortcomings of the traditional method are: first, it is easily affected by factors such as adverse weather, mountain shadows, and high water vapor content, resulting in a large amount of data being unusable; second, due to the different personal subjective experiences of different staff members, the structural interpretation results are highly subjective and lack scientificity; finally, due to the limitations of manpower and material resources, the survey cannot be carried out in all study areas, limiting the accuracy of extraction. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present invention provides a geological structure background prediction method, device and storage medium, so as to improve the accuracy and efficiency of geological structure background classification prediction.

[0004] According to a first aspect of an embodiment of the present invention, a method for predicting geological structure background is provided, the method comprising:

[0005] Obtain multiple rock geochemical element data;

[0006] Preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element;

[0007] Constructing a corresponding target image according to each of the target rock geochemical element data, and dividing all target images into training samples and prediction samples;

[0008] Training is performed according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model;

[0009] The geological structure background prediction model is used to predict each prediction sample to obtain the rock type corresponding to each prediction sample.

[0010] In one embodiment, preferably, constructing a corresponding target image according to each of the target rock geochemical element data includes:

[0011] Convert each target rock geochemical element data into a target matrix of preset rows and columns according to a preset number of target chemical elements and the content of each target chemical element, wherein each eigenvalue in the target matrix corresponds to the content of a target chemical element;

[0012] According to each target matrix, construct the corresponding target image.

[0013] In one embodiment, preferably, constructing a corresponding target image according to each target matrix includes:

[0014] Convert each eigenvalue in the target matrix into a corresponding grayscale value to obtain a grayscale value matrix;

[0015] A corresponding target image is constructed according to the gray value matrix.

[0016] In one embodiment, preferably, the method further comprises:

[0017] The preset rows and columns of the target matrix are determined according to the preset number.

[0018] In one embodiment, preferably, the preset number includes 36, and the target chemical elements include: SiO2, TiO2, Al2O3, TFe2O3, MnO, MgO, CaO, Na2O, K2O, P2O5, Rb, Sr, Y, Zr, Nb, Ba, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu, Hf, Ta, Th, U, Cr and Ni.

[0019] In one embodiment, preferably, the rock comprises basalt, and the rock types comprise island arc basalt, oceanic guide basalt and mid-ocean ridge basalt.

[0020] In one embodiment, preferably, the method further comprises:

[0021] Obtain geochemical element data of rocks to be identified;

[0022] Preprocessing the rock geochemical element data to be identified to obtain processed rock geochemical element data;

[0023] Constructing a corresponding image to be identified according to the processed rock geochemical element data;

[0024] The geological structure background prediction model is used to predict the image to be identified to obtain the rock type corresponding to the rock geochemical element data to be identified, specifically including:

[0025] The rock geochemical element data is a set of chemical element content sequences, wherein the chemical element content sequences are arranged from the smallest content to the largest content;

[0026] The first calculation formula is used to calculate the content ratio of each chemical element;

[0027] After obtaining the rock geochemical element data, a pie chart is drawn clockwise from the smallest content to the largest content of each chemical element as the corresponding image to be identified, wherein the area occupied by each element in the image to be identified is obtained using the second calculation formula;

[0028] Calculating the similarity of the target chemical element using the third calculation formula;

[0029] Obtaining the geological structure background prediction model, and calculating the comprehensive similarity using the fourth calculation formula;

[0030] Selecting three rock types with the greatest comprehensive similarity in the geological structure background prediction model as a similar rock library;

[0031] Obtaining the similar rock library, performing grayscale processing on images in the rock library, and comparing structural similarity indexes in the rock library;

[0032] Calculate the comprehensive index using the fifth calculation formula, and use the rock type with the largest comprehensive index in the similar rock library as the identification structure;

[0033] The first calculation formula is:

[0034] A=B÷C

[0035] Among them, A is the content ratio of each chemical element, B is the content of the chemical element, and C is the total content of the chemical element;

[0036] The second calculation formula is:

[0037] D=K×A

[0038] Where D is the area occupied by the element and K is the coefficient;

[0039] The third calculation formula is:

[0040] E = 100% × (D i -D j )÷D i

[0041] Among them, E is the similarity of the target chemical element, D i is the area occupied by the element in the rock geochemical element data, D j is the area occupied by the elements in the geological structure background prediction model;

[0042] The fourth calculation formula is:

[0043] Z1=ΣE

[0044] Among them, Z1 is the comprehensive similarity, and ΣE is the sum of the similarities of all target chemical elements in the geological structure background prediction model.

[0045] The fifth calculation formula is:

[0046] Z=Z1+s×F

[0047] Among them, Z is the comprehensive index, s is the preset correction coefficient, and F is the structural similarity index.

[0048] According to a second aspect of an embodiment of the present invention, a geological structure background prediction device is provided, the device comprising:

[0049] An acquisition module, used to acquire multiple rock geochemical element data;

[0050] A preprocessing module, used to preprocess each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element;

[0051] A construction module, used to construct a corresponding target image according to each of the target rock geochemical element data, and divide all target images into training samples and prediction samples;

[0052] A training module, used for training according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model;

[0053] The prediction module is used to predict each prediction sample using the geological structure background prediction model to obtain the rock type corresponding to each prediction sample.

[0054] In one embodiment, preferably, the construction module includes:

[0055] A conversion unit, used to convert each target rock geochemical element data into a target matrix of preset rows and columns according to a preset number of target chemical elements and the content of each target chemical element, wherein each eigenvalue in the target matrix corresponds to the content of a target chemical element;

[0056] The image construction unit is used to construct a corresponding target image according to each target matrix.

[0057] In one embodiment, preferably, the image construction unit is used to:

[0058] Convert each eigenvalue in the target matrix into a corresponding grayscale value to obtain a grayscale value matrix;

[0059] A corresponding target image is constructed according to the gray value matrix.

[0060] In one embodiment, preferably, the device further comprises:

[0061] A determination module is used to determine preset rows and columns of the target matrix according to the preset number.

[0062] In one embodiment, preferably, the preset number includes 36, and the target chemical elements include: SiO2, TiO2, Al2O3, TFe2O3, MnO, MgO, CaO, Na2O, K2O, P2O5, Rb, Sr, Y, Zr, Nb, Ba, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu, Hf, Ta, Th, U, Cr and Ni.

[0063] In one embodiment, preferably, the rock comprises basalt, and the rock types comprise island arc basalt, oceanic guide basalt and mid-ocean ridge basalt.

[0064] In one embodiment, preferably, the method further comprises:

[0065] Obtain geochemical element data of rocks to be identified;

[0066] Preprocessing the rock geochemical element data to be identified to obtain processed rock geochemical element data;

[0067] Constructing a corresponding image to be identified according to the processed rock geochemical element data;

[0068] The geological structure background prediction model is used to predict the image to be identified to obtain the rock type corresponding to the rock geochemical element data to be identified.

[0069] According to a third aspect of an embodiment of the present invention, there is provided a geological structure background prediction device, comprising:

[0070] processor;

[0071] a memory for storing processor-executable instructions;

[0072] Wherein, the processor is configured to:

[0073] Obtain multiple rock geochemical element data;

[0074] Preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element;

[0075] Constructing a corresponding target image according to each of the target rock geochemical element data, and dividing all target images into training samples and prediction samples;

[0076] Training is performed according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model;

[0077] The geological structure background prediction model is used to predict each prediction sample to obtain the rock type corresponding to each prediction sample.

[0078] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable storage medium having computer instructions stored thereon, wherein the instructions, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0079] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0080] In the embodiment of the present invention, the geochemical data is converted into image data, so as to identify and classify the image data, realize the classification prediction of the geochemical data, and thus improve the accuracy and efficiency of the classification prediction of the geological structure background.

[0081] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0083] Figure 1 The present invention is a flow chart of a geological structure background prediction method according to an exemplary embodiment.

[0084] Figure 2 It is a flowchart of step S103 in a geological structure background prediction method according to an exemplary embodiment.

[0085] Figure 3 is a schematic diagram of a target image of island arc basalt according to an exemplary embodiment.

[0086] Figure 4 is a schematic diagram of a target image of mid-ocean ridge basalt according to an exemplary embodiment.

[0087] Figure 5 is a schematic diagram of a target image of ocean-conducting basalt according to an exemplary embodiment.

[0088] Figure 6The present invention is a flowchart of another geological structure background prediction method according to an exemplary embodiment.

[0089] Figure 7 It is a block diagram of a geological structure background prediction device according to an exemplary embodiment. DETAILED DESCRIPTION

[0090] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0091] Figure 1 The present invention is a flow chart of a geological structure background prediction method according to an exemplary embodiment.

[0092] like Figure 1 As shown, according to a first aspect of an embodiment of the present invention, a method for predicting geological structure background is provided, the method comprising:

[0093] Step S101, obtaining a plurality of rock geochemical element data; global rock geochemical element data may be downloaded from a website.

[0094] Step S102, preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element; preprocessing each rock geochemical element data includes cleaning and selecting the data, and selecting a preset number of target chemical elements.

[0095] In one embodiment, preferably, the preset number includes 36, and the target chemical elements include: SiO2, TiO2, Al2O3, TFe2O3, MnO, MgO, CaO, Na2O, K2O, P2O5, Rb, Sr, Y, Zr, Nb, Ba, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu, Hf, Ta, Th, U, Cr and Ni.

[0096] Step S103, constructing a corresponding target image according to each of the target rock geochemical element data, and dividing all target images into training samples and prediction samples; specifically, the target images can be divided into training samples and prediction samples according to a preset ratio.

[0097] Step S104, training is performed according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model;

[0098] Step S105: predict each prediction sample using the geological structure background prediction model to obtain the rock type corresponding to each prediction sample.

[0099] In this embodiment, the geochemical data is converted into image data, so as to identify and classify the image data, realize the classification prediction of the geochemical data, and thus improve the accuracy and efficiency of the classification prediction of the geological structure background.

[0100] Figure 2 It is a flowchart of step S103 in a geological structure background prediction method according to an exemplary embodiment.

[0101] like Figure 2 As shown, in one embodiment, preferably, the above step S103 includes:

[0102] Step S201, converting each target rock geochemical element data into a target matrix of preset rows and columns according to a preset number of target chemical elements and the content of each target chemical element, wherein each eigenvalue in the target matrix corresponds to the content of a target chemical element;

[0103] Step S202: construct a corresponding target image according to each target matrix.

[0104] In one embodiment, preferably, constructing a corresponding target image according to each target matrix includes:

[0105] Convert each eigenvalue in the target matrix into a corresponding grayscale value to obtain a grayscale value matrix;

[0106] A corresponding target image is constructed according to the gray value matrix.

[0107] In one embodiment, preferably, the method further comprises:

[0108] The preset rows and columns of the target matrix are determined according to the preset number.

[0109] In this embodiment, if the preset number is 36, the matrix can be 6*6, and the eigenvalues ​​in the matrix are converted into corresponding grayscale values. Specifically, the eigenvalues ​​can be directly used as grayscale values ​​to obtain a grayscale value matrix, and the target image is constructed according to the grayscale value matrix. In one embodiment, preferably, the rock includes basalt, and the rock types include island arc basalt, ocean guide basalt and mid-ocean ridge basalt. Specifically, the target image of island arc basalt is as follows Figure 3 As shown, the target image of mid-ocean ridge basalt is as follows Figure 4 As shown, the target image of Yangdao basalt is as follows Figure 5 shown.

[0110] Figure 6 The present invention is a flowchart of another geological structure background prediction method according to an exemplary embodiment.

[0111] like Figure 6 As shown, in one embodiment, preferably, the method further comprises:

[0112] Step S601, obtaining geochemical element data of the rock to be identified;

[0113] Step S602, preprocessing the rock geochemical element data to be identified to obtain processed rock geochemical element data;

[0114] Step S603, constructing a corresponding image to be identified based on the processed rock geochemical element data;

[0115] Step S604: Use the geological structure background prediction model to predict the image to be identified, so as to obtain the rock type corresponding to the rock geochemical element data to be identified.

[0116] The geological structure background prediction model is used to predict the image to be identified to obtain the rock type corresponding to the rock geochemical element data to be identified, specifically including:

[0117] The rock geochemical element data is a set of chemical element content sequences, wherein the chemical element content sequences are arranged from the smallest content to the largest content;

[0118] The first calculation formula is used to calculate the content ratio of each chemical element;

[0119] After obtaining the rock geochemical element data, a pie chart is drawn clockwise from the smallest content to the largest content of each chemical element as the corresponding image to be identified, wherein the area occupied by each element in the image to be identified is obtained using the second calculation formula;

[0120] Calculating the similarity of the target chemical element using the third calculation formula;

[0121] Obtaining the geological structure background prediction model, and calculating the comprehensive similarity using the fourth calculation formula;

[0122] Selecting three rock types with the greatest comprehensive similarity in the geological structure background prediction model as a similar rock library;

[0123] Obtaining the similar rock library, performing grayscale processing on images in the rock library, and comparing structural similarity indexes in the rock library;

[0124] Calculate the comprehensive index using the fifth calculation formula, and use the rock type with the largest comprehensive index in the similar rock library as the identification structure;

[0125] The first calculation formula is:

[0126] A=B÷C

[0127] Among them, A is the content ratio of each chemical element, B is the content of the chemical element, and C is the total content of the chemical element;

[0128] The second calculation formula is:

[0129] D=K×A

[0130] Where D is the area occupied by the element and K is the coefficient;

[0131] The third calculation formula is:

[0132] E = 100% × (D i -D j )÷D i

[0133] Among them, E is the similarity of the target chemical element, D i is the area occupied by the element in the rock geochemical element data, D j is the area occupied by the elements in the geological structure background prediction model;

[0134] The fourth calculation formula is:

[0135] Z1=ΣE

[0136] Among them, Z1 is the comprehensive similarity, and ΣE is the sum of the similarities of all target chemical elements in the geological structure background prediction model.

[0137] The fifth calculation formula is:

[0138] Z=Z1+s×F

[0139] Among them, Z is the comprehensive index, s is the preset correction coefficient, and F is the structural similarity index.

[0140] Wherein, the structural similarity index (SSIM) is used to measure the similarity between two given images;

[0141] In the embodiment of the present invention, firstly, the content distribution of key chemical elements is clarified to obtain the similarity of target chemical elements. Secondly, based on the similarity of chemical elements, the image similarity is compared to determine the comprehensive similarity, and the one with the highest comprehensive similarity is used as the corresponding rock type.

[0142] In this embodiment, the rock geochemical element data to be identified can be constructed into an image to be identified, and the image to be identified is identified using a geological structure background prediction model, so as to determine the corresponding rock type.

[0143] Figure 7 It is a block diagram of a geological structure background prediction device according to an exemplary embodiment.

[0144] like Figure 7 According to a second aspect of an embodiment of the present invention, a geological structure background prediction device is provided, the device comprising:

[0145] An acquisition module 71 is used to acquire a plurality of rock geochemical element data;

[0146] A preprocessing module 72 is used to preprocess each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element;

[0147] A construction module 73, configured to construct a corresponding target image according to each of the target rock geochemical element data, and divide all target images into training samples and prediction samples;

[0148] A training module 74 is used to perform training according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model;

[0149] The prediction module 75 is used to predict each prediction sample using the geological structure background prediction model to obtain the rock type corresponding to each prediction sample.

[0150] In one embodiment, preferably, the construction module includes:

[0151] A conversion unit, used to convert each target rock geochemical element data into a target matrix of preset rows and columns according to a preset number of target chemical elements and the content of each target chemical element, wherein each eigenvalue in the target matrix corresponds to the content of a target chemical element;

[0152] The image construction unit is used to construct a corresponding target image according to each target matrix.

[0153] In one embodiment, preferably, the image construction unit is used to:

[0154] Convert each eigenvalue in the target matrix into a corresponding grayscale value to obtain a grayscale value matrix;

[0155] A corresponding target image is constructed according to the gray value matrix.

[0156] In one embodiment, preferably, the device further comprises:

[0157] A determination module is used to determine preset rows and columns of the target matrix according to the preset number.

[0158] In one embodiment, preferably, the preset number includes 36, and the target chemical elements include: SiO2, TiO2, Al2O3, TFe2O3, MnO, MgO, CaO, Na2O, K2O, P2O5, Rb, Sr, Y, Zr, Nb, Ba, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu, Hf, Ta, Th, U, Cr and Ni.

[0159] In one embodiment, preferably, the rock comprises basalt, and the rock types comprise island arc basalt, oceanic guide basalt and mid-ocean ridge basalt.

[0160] In one embodiment, preferably, the method further comprises:

[0161] Obtain geochemical element data of rocks to be identified;

[0162] Preprocessing the rock geochemical element data to be identified to obtain processed rock geochemical element data;

[0163] Constructing a corresponding image to be identified according to the processed rock geochemical element data;

[0164] The geological structure background prediction model is used to predict the image to be identified to obtain the rock type corresponding to the rock geochemical element data to be identified.

[0165] According to a third aspect of an embodiment of the present invention, there is provided a geological structure background prediction device, comprising:

[0166] processor;

[0167] a memory for storing processor-executable instructions;

[0168] Wherein, the processor is configured to:

[0169] Obtain multiple rock geochemical element data;

[0170] Preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element;

[0171] Constructing a corresponding target image according to each of the target rock geochemical element data, and dividing all target images into training samples and prediction samples;

[0172] Training is performed according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model;

[0173] The geological structure background prediction model is used to predict each prediction sample to obtain the rock type corresponding to each prediction sample.

[0174] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable storage medium having computer instructions stored thereon, wherein the instructions, when executed by a processor, implement the steps of the method as described in any one of the embodiments of the second aspect.

[0175] It is further understood that, although the operations are described in a specific order in the accompanying drawings in the embodiments of the present invention, it should not be understood as requiring the operations to be performed in the specific order or serial order shown, or requiring the execution of all the operations shown to obtain the desired results. In certain environments, multitasking and parallel processing may be advantageous.

[0176] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0177] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for predicting geological structure background, characterized in that: The method comprises: Obtain multiple rock geochemical element data; Preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element; Constructing a corresponding target image according to each of the target rock geochemical element data, and dividing all target images into training samples and prediction samples; Training is performed according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model; Using the geological structure background prediction model to predict each prediction sample, so as to obtain the rock type corresponding to each prediction sample; Obtain geochemical element data of rocks to be identified; Preprocessing the rock geochemical element data to be identified to obtain processed rock geochemical element data; Constructing a corresponding image to be identified according to the processed rock geochemical element data; Using the geological structure background prediction model to predict the image to be identified, so as to obtain the rock type corresponding to the rock geochemical element data to be identified; The method of using the geological structure background prediction model to predict the image to be identified further includes determining the rock type using the rock geochemical element data, wherein the rock geochemical element data is a set of chemical element content sequences, wherein the chemical element content sequences are arranged from the smallest content to the largest content; The rock geochemical element data used to determine the rock type include: The first calculation formula is used to calculate the content ratio of each chemical element; After obtaining the rock geochemical element data, a pie chart is drawn clockwise from the smallest content to the largest content of each chemical element as the corresponding image to be identified, wherein the area occupied by each element in the image to be identified is obtained using the second calculation formula; Calculating the similarity of the target chemical element using the third calculation formula; Obtaining the geological structure background prediction model, and calculating the comprehensive similarity using the fourth calculation formula; Selecting three rock types with the greatest comprehensive similarity in the geological structure background prediction model as a similar rock library; Obtaining the similar rock library, performing grayscale processing on images in the rock library, and comparing structural similarity indexes in the rock library; Calculate the comprehensive index using the fifth calculation formula, and use the rock type with the largest comprehensive index in the similar rock library as the identification structure; The first calculation formula is: A=B÷C Among them, A is the content ratio of each chemical element, B is the content of the chemical element, and C is the total content of the chemical element; The second calculation formula is: D=K×A Where D is the area occupied by the element and K is the coefficient; The third calculation formula is: E=100%×(D i -D j )÷D i Among them, E is the similarity of the target chemical element, D i is the area occupied by the element in the rock geochemical element data, D j is the area occupied by the elements in the geological structure background prediction model; The fourth calculation formula is: Z1=ΣE Among them, Z1 is the comprehensive similarity, ΣE is the sum of the similarities of all target chemical elements in the geological structure background prediction model; The fifth calculation formula is: Z=Z1+s×F Among them, Z is the comprehensive index, s is the preset correction coefficient, and F is the structural similarity index; Wherein, constructing a corresponding target image according to each of the target rock geochemical element data includes: Convert each target rock geochemical element data into a target matrix of preset rows and columns according to a preset number of target chemical elements and the content of each target chemical element, wherein each eigenvalue in the target matrix corresponds to the content of a target chemical element; According to each target matrix, construct the corresponding target image; Among them, according to each target matrix, the corresponding target image is constructed, including: Convert each eigenvalue in the target matrix into a corresponding grayscale value to obtain a grayscale value matrix; Constructing a corresponding target image according to the gray value matrix; Wherein, the geological structure background prediction method further includes: Determining preset rows and columns of the target matrix according to the preset number; Wherein, the preset number includes 36, and the target chemical elements include: SiO2, TiO2, Al2O3, TFe2O3, MnO, MgO, CaO, Na2O, K2O, P2O5, Rb, Sr, Y, Zr, Nb, Ba, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu, Hf, Ta, Th, U, Cr and Ni; Among them, the rock includes basalt, and the rock types include island arc basalt, oceanic guide basalt and mid-ocean ridge basalt.

2. A geological structure background prediction device, characterized in that: The device comprises: An acquisition module, used to acquire multiple rock geochemical element data; A preprocessing module, used for preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element; A construction module, used to construct a corresponding target image according to each of the target rock geochemical element data, and divide all target images into training samples and prediction samples; A training module, used for training according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model; A prediction module, used to predict each prediction sample using the geological structure background prediction model to obtain the rock type corresponding to each prediction sample; Obtain geochemical element data of rocks to be identified; Preprocessing the rock geochemical element data to be identified to obtain processed rock geochemical element data; Constructing a corresponding image to be identified according to the processed rock geochemical element data; Using the geological structure background prediction model to predict the image to be identified, so as to obtain the rock type corresponding to the rock geochemical element data to be identified; The method of using the geological structure background prediction model to predict the image to be identified further includes using the rock geochemical element data to determine the rock type, wherein the rock geochemical element data to determine the rock type includes: The first calculation formula is used to calculate the content ratio of each chemical element; After obtaining the rock geochemical element data, a pie chart is drawn clockwise from the smallest content to the largest content of each chemical element as the corresponding image to be identified, wherein the area occupied by each element in the image to be identified is obtained using the second calculation formula; Calculating the similarity of the target chemical element using the third calculation formula; Obtaining the geological structure background prediction model, and calculating the comprehensive similarity using the fourth calculation formula; Selecting three rock types with the greatest comprehensive similarity in the geological structure background prediction model as a similar rock library; Obtaining the similar rock library, performing grayscale processing on images in the rock library, and comparing structural similarity indexes in the rock library; Calculate the comprehensive index using the fifth calculation formula, and use the rock type with the largest comprehensive index in the similar rock library as the identification structure; The first calculation formula is: A=B÷C Among them, A is the content ratio of each chemical element, B is the content of the chemical element, and C is the total content of the chemical element; The second calculation formula is: D=K×A Where D is the area occupied by the element and K is the coefficient; The third calculation formula is: E=100%×(D i -D j )÷D i Among them, E is the similarity of the target chemical element, D i is the area occupied by the element in the rock geochemical element data, D j is the area occupied by the elements in the geological structure background prediction model; The fourth calculation formula is: Z1=ΣE Among them, Z1 is the comprehensive similarity, ΣE is the sum of the similarities of all target chemical elements in the geological structure background prediction model; The fifth calculation formula is: Z=Z1+s×F Among them, Z is the comprehensive index, s is the preset correction coefficient, and F is the structural similarity index; Wherein, constructing a corresponding target image according to each of the target rock geochemical element data includes: Convert each target rock geochemical element data into a target matrix of preset rows and columns according to a preset number of target chemical elements and the content of each target chemical element, wherein each eigenvalue in the target matrix corresponds to the content of a target chemical element; According to each target matrix, construct the corresponding target image; Among them, according to each target matrix, the corresponding target image is constructed, including: Convert each eigenvalue in the target matrix into a corresponding grayscale value to obtain a grayscale value matrix; Constructing a corresponding target image according to the gray value matrix; Among them, a geological structure background prediction method also includes: Determining preset rows and columns of the target matrix according to the preset number; Wherein, the preset number includes 36, and the target chemical elements include: SiO2, TiO2, Al2O3, TFe2O3, MnO, MgO, CaO, Na2O, K2O, P2O5, Rb, Sr, Y, Zr, Nb, Ba, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu, Hf, Ta, Th, U, Cr and Ni; Among them, the rock includes basalt, and the rock types include island arc basalt, oceanic guide basalt and mid-ocean ridge basalt.

3. A geological structure background prediction device as claimed in claim 2, characterized in that: The device comprises: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Obtain multiple rock geochemical element data; Preprocessing each rock geochemical element data to obtain target rock geochemical element data, wherein the target rock geochemical element includes a preset number of target chemical elements and the content of each target chemical element; Constructing a corresponding target image according to each of the target rock geochemical element data, and dividing all target images into training samples and prediction samples; Training is performed according to the training samples and a preset convolutional neural network to obtain a geological structure background prediction model; Using the geological structure background prediction model to predict each prediction sample, so as to obtain the rock type corresponding to each prediction sample; Obtain geochemical element data of rocks to be identified; Preprocessing the rock geochemical element data to be identified to obtain processed rock geochemical element data; Constructing a corresponding image to be identified according to the processed rock geochemical element data; Using the geological structure background prediction model to predict the image to be identified, so as to obtain the rock type corresponding to the rock geochemical element data to be identified; The method further includes determining the rock type using the rock geochemical element data, wherein the rock type determined by the rock geochemical element data includes: Calculate the content ratio of each chemical element using the first calculation formula; After obtaining the rock geochemical element data, a pie chart is drawn clockwise from the smallest content to the largest content of each chemical element as the corresponding image to be identified, wherein the area occupied by each element in the image to be identified is obtained using the second calculation formula; Calculating the similarity of the target chemical element using the third calculation formula; Obtaining the geological structure background prediction model, and calculating the comprehensive similarity using the fourth calculation formula; Selecting three rock types with the greatest comprehensive similarity in the geological structure background prediction model as a similar rock library; Obtaining the similar rock library, performing grayscale processing on images in the rock library, and comparing structural similarity indexes in the rock library; Calculate the comprehensive index using the fifth calculation formula, and use the rock type with the largest comprehensive index in the similar rock library as the identification structure; The first calculation formula is: A=B÷C Among them, A is the content ratio of each chemical element, B is the content of the chemical element, and C is the total content of the chemical element; The second calculation formula is: D=K×A Where D is the area occupied by the element and K is the coefficient; The third calculation formula is: E=100%×(D i -D j )÷D i Among them, E is the similarity of the target chemical element, D i is the area occupied by the element in the rock geochemical element data, D j is the area occupied by the elements in the geological structure background prediction model; The fourth calculation formula is: Z1=ΣE Among them, Z1 is the comprehensive similarity, ΣE is the sum of the similarities of all target chemical elements in the geological structure background prediction model; The fifth calculation formula is: Z=Z1+s×F Among them, Z is the comprehensive index, s is the preset correction coefficient, and F is the structural similarity index; Wherein, constructing a corresponding target image according to each of the target rock geochemical element data includes: Convert each target rock geochemical element data into a target matrix of preset rows and columns according to a preset number of target chemical elements and the content of each target chemical element, wherein each eigenvalue in the target matrix corresponds to the content of a target chemical element; According to each target matrix, construct the corresponding target image; Among them, according to each target matrix, the corresponding target image is constructed, including: Convert each eigenvalue in the target matrix into a corresponding grayscale value to obtain a grayscale value matrix; Constructing a corresponding target image according to the gray value matrix; Among them, a geological structure background prediction method also includes: Determining preset rows and columns of the target matrix according to the preset number; Wherein, the preset number includes 36, and the target chemical elements include: SiO2, TiO2, Al2O3, TFe2O3, MnO, MgO, CaO, Na2O, K2O, P2O5, Rb, Sr, Y, Zr, Nb, Ba, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, Lu, Hf, Ta, Th, U, Cr and Ni; Among them, the rock includes basalt, and the rock types include island arc basalt, oceanic guide basalt and mid-ocean ridge basalt.

4. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method described in claim 1 are implemented.

Images