Method, device, terminal and readable storage medium for determining clastic rock components

Abstract

The present application is about a method, device, terminal and readable storage medium for determining clastic rock components, and relates to the field of rock identification technology. The method includes: obtaining a clastic rock thin section sample image; inputting the clastic rock thin section sample image into a clastic rock identification binary classification model, and outputting a first component set image and a second component set image; receiving surface scanning data; verifying the second component identification result based on the surface scanning data to obtain a verification result; and determining the clastic rock components based on the first component identification result, the second component identification result and the verification result. The component identification result in the second component area is verified twice by the surface scanning data. In this process, only the position corresponding to the second component set image needs to be surface scanned, and the surface scanning area is reduced, so as to reduce the working time consumed by the surface scanning, thereby improving the efficiency of determining the clastic rock components.

Description

Technical Field

[0001] The present application relates to the technical field of rock identification, and in particular to a method, device, terminal and readable storage medium for determining clastic rock components. Background Art

[0002] In the field of rock identification, for clastic rocks, their structure is usually accurately identified through surface scanning analysis.

[0003] In the related art, the instruments used for surface scanning include but are not limited to at least one of a molecular spectrometer, an X-ray fluorescence spectrometer, an X-ray energy spectrometer, a microscope, and a scanning electron microscope. After the clastic rock is cut into clastic rock slices to obtain a sample with a polished surface, the surface of the clastic rock slice sample is completely scanned by the instrument. In one example, a circular clastic rock slice sample of 25mm*25mm in size is fully scanned using an X-ray fluorescence spectrometer, and the scanning result is mapped into an image. By analyzing the image, the properties of the clastic rock slice sample are further determined.

[0004] However, the surface scanning method in the related art is time-consuming, resulting in low efficiency in the process of determining the clastic rock components through the surface scanning analysis method. Summary of the invention

[0005] The present application is about a method, device, terminal and readable storage medium for determining clastic rock components, which can improve the efficiency of determining clastic rock components. The technical solution is as follows:

[0006] In one aspect, a method for determining clastic rock components is provided, the method comprising:

[0007] Acquire a clastic rock thin section sample image, wherein the clastic rock thin section sample image includes at least two component regions;

[0008] Inputting the clastic rock thin section sample image into the clastic rock recognition binary classification model, outputting a first component set image and a second component set image, wherein the first component set image includes at least one first component region and a first component recognition result corresponding to the first component region, and the second component set image includes at least one second component region and a second component recognition result corresponding to the second component region;

[0009] receiving surface scanning data, the surface scanning data being data obtained by surface scanning the clastic rock thin section sample corresponding to the second component set image;

[0010] Verifying the second component recognition result based on the surface scanning data to obtain a verification result;

[0011] The components of the clastic rock are determined based on the first component identification result, the second component identification result and the verification result.

[0012] In another aspect, a device for determining clastic rock components is provided, the device comprising:

[0013] An acquisition module is used to acquire a clastic rock thin section sample image, wherein the clastic rock thin section sample image includes at least two component regions;

[0014] An input module is used to input a clastic rock thin section sample image into a clastic rock identification binary classification model, and output a first component set image and a second component set image, wherein the first component set image includes at least one first component region and a first component identification result corresponding to the first component region, and the second component set image includes at least one second component region and a second component identification result corresponding to the second component region;

[0015] A receiving module, used for receiving surface scanning data, where the surface scanning data is data obtained by surface scanning the clastic rock thin section sample corresponding to the second component set image;

[0016] A verification module, used to verify the second component recognition result based on the surface scanning data to obtain a verification result;

[0017] The determination module is used to determine the components of the clastic rock based on the first component identification result, the second component identification result and the verification result.

[0018] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the processor can load and execute at least one instruction, at least one program, a code set or an instruction set to implement the method for determining the clastic rock components provided in the above-mentioned embodiment of the present application.

[0019] On the other hand, a computer-readable storage medium is provided, in which at least one instruction, at least one program, code set or instruction set is stored. The processor can load and execute at least one instruction, at least one program, code set or instruction set to implement the method for determining the clastic rock components provided in the above-mentioned embodiment of the present application.

[0020] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer program instructions, the computer program instructions being stored in a computer-readable storage medium. A processor reads the computer instructions from the computer-readable storage medium and executes the computer instructions, so that the computer device executes the method for determining the clastic rock component as provided in the embodiments of the present application.

[0021] The beneficial effects of the technical solution provided by this application include at least:

[0022] Before determining the components of the clastic rock thin section sample by means of surface scanning, the clastic rock thin section sample image is divided into a first component set image and a second component set image by means of a clastic rock identification binary classification model. After determining the component identification result in the first component set image, the content in the second component set image is further verified, and finally the components of the clastic rock thin section sample are determined by combining the first component identification result, the second component identification result and the verification result. The clastic rock thin section sample image is identified by means of the clastic rock identification binary classification model, and after selecting the area corresponding to the second component set image, the component identification result in the second component area is secondarily verified by means of surface scanning data. In this process, only the position corresponding to the second component set image needs to be surface scanned, thereby reducing the surface scanning area, thereby reducing the working time consumed by the surface scanning, and improving the efficiency of determining the clastic rock components. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flow chart showing a method for determining clastic rock components provided by an exemplary embodiment of the present application is shown;

[0025] Figure 2 A schematic structural diagram of a clastic rock binary classification model provided by an exemplary embodiment of the present application is shown;

[0026] Figure 3 A flow chart showing another method for determining clastic rock components provided by an exemplary embodiment of the present application;

[0027] Figure 4 A schematic diagram of the structure of a clastic rock identification binary classification model provided by an exemplary embodiment of the present application is shown;

[0028] Figure 5 A schematic structural diagram of a device for determining clastic rock components provided by an exemplary embodiment of the present application is shown;

[0029] Figure 6 A schematic structural diagram of a device for determining clastic rock components provided by an exemplary embodiment of the present application is shown;

[0030] Figure 7A schematic diagram of the structure of a computer device for executing a method for determining clastic rock components provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0032] First, the terms involved in each embodiment of the present application are explained:

[0033] Clastic rock is a rock formed by the transportation, deposition, compaction and cementation of components produced by mechanical weathering of parent rock and rock fragments, which mainly includes clastic particles, matrix and cement. In one example, clastic rock can be divided into conglomerate and breccia, sandstone, siltstone, etc. according to particle size. In the embodiment of the present application, the components in the clastic rock include non-terrigenous clastic components, rock fragment components, quartz feldspar clastic components, siliceous calcareous cement components, mud cement components and matrix filling components.

[0034] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Artificial Intelligence attempts to understand the essence of intelligence and produce an intelligent machine that can respond in a similar way to human intelligence. The purpose of artificial intelligence is to enable machines to have the functions of perception, reasoning and decision-making.

[0035] Artificial intelligence technology is a comprehensive discipline covering a wide range of fields. Basic artificial intelligence technologies include, but are not limited to, sensor technology, artificial intelligence chip technology, cloud computing technology, big data processing technology, and mechatronics technology. The artificial intelligence technology used in the embodiments of this application is machine learning technology, and the machine learning device is applied to computer devices.

[0036] Surface scanning, i.e. surface scanning analysis, is the mainstream method for accurately identifying clastic rocks using test instruments. The usual practice is to cut the clastic rocks into thin slices or make samples with a smooth surface, and then use surface scanning to accurately identify the components therein. The test instruments used for surface scanning include but are not limited to molecular spectra such as infrared spectra and Raman spectra, X-ray fluorescence (X-ray Fluorescence, XRF) spectra, X-ray energy spectrum analysis (Energy DispersiveX-ray Spectroscopy, EDS), etc., and in some embodiments of the present application, the surface scanning process can be combined with a microscope or a scanning electron microscope to combine microscopic observation with micro-area analysis.

[0037] In the related art, in the process of surface scanning of clastic rock thin section samples, the surface of the clastic rock thin section samples is usually completely and comprehensively scanned and stored by point-by-point scanning. In one example, the surface of a circular clastic rock thin section sample with a radius of 25 mm is scanned by XRF. The scanning process can last up to 10 hours. After the scanning results are obtained, the components of the clastic rock can be determined based on the scanning results. This process is inefficient in determining the components of clastic rocks.

[0038] The present application provides a method for determining the composition of clastic rocks, which can perform surface scanning on only the partial positions corresponding to the clastic rock thin section sample image, thereby reducing the surface scanning area, thereby reducing the working time consumed by the surface scanning, and improving the efficiency of determining the clastic rock components.

[0039] Figure 1 A flowchart of a method for determining clastic rock components provided by an exemplary embodiment of the present application is shown, and the method is described by taking the application of the method in a computer device as an example. The method includes:

[0040] Step 101: Acquire a clastic rock thin section sample image, wherein the clastic rock thin section sample image includes at least two component regions.

[0041] In the embodiment of the present application, the computer device has a storage function, a communication function and a data processing function. In one example, the computer device has a storage function and obtains a clastic rock thin section sample image according to a storage path; in another example, the computer device is directly connected to an image acquisition device such as a camera and obtains a clastic rock thin section sample image from the image acquisition device; in another example, the computer device is connected to the image acquisition device in communication and introduces the clastic rock thin section sample image sent by the image acquisition device through a communication network. The embodiment of the present application does not limit the specific way in which the computer device obtains the clastic rock thin section sample image.

[0042] In the embodiment of the present application, the clastic rock thin section sample image is an image corresponding to the clastic rock thin section sample, that is, an image acquisition device such as a camera photographs the clastic rock thin section sample and obtains the image. The clastic rock sample can be obtained after cutting, polishing, leveling and other processing operations are performed on the clastic rock sample.

[0043] In the embodiment of the present application, a component region is used to indicate a component. The clastic rock thin section sample image includes at least two component regions. Optionally, the components indicated by the at least two component regions are different, or there is a component region indicating the same component in the at least two component regions.

[0044] Step 102, inputting the clastic rock thin section sample image into a clastic rock identification binary classification model, and outputting a first component set image and a second component set image, wherein the clastic rock identification binary classification model is a neural network model based on deep learning.

[0045] In an embodiment of the present application, the first component set image includes at least one first component region and a first component identification result corresponding to the first component region, and the second component set image includes at least one second component region and a second component identification result corresponding to the second component region. Optionally, corresponding to the situation in the present application where the components in the clastic rock include non-terrigenous clastic components, rock debris components, quartz feldspar clastic components, siliceous calcareous cement components, mud cement components and matrix filling components, the identification results include identification results corresponding to the above components, namely, non-terrigenous clastic identification results, rock debris identification results, quartz feldspar clastic identification results, siliceous calcareous cement identification results, mud cement identification results and matrix filling identification results.

[0046] Based on the above classification method, in one example of the present application, the clastic rock identification binary classification model is implemented as a single model, and the clastic rock identification binary classification model is used to divide the clastic rock thin section sample image into a first component set image and a second component set image, and in the classification process, each component is synchronously identified to obtain the identification result corresponding to each component area; in another embodiment of the present application, the clastic rock identification binary classification model is implemented as a combination of multiple sub-models, and through the combination of multiple sub-models, the clastic rock identification binary classification model completes the classification of the first component set image and the second component set image and the identification of each component area. The present application does not limit the specific implementation form of the clastic rock identification binary classification model.

[0047] It should be noted that the "models" appearing in the various embodiments of the present application, including but not limited to the two-classification model for clastic rock identification, and the various classification sub-models and identification sub-models appearing below, are all neural network models based on machine learning through artificial intelligence technology. The above models are trained and debugged by sample set identification. Optionally, the above models also have the function of active learning.

[0048] Step 103 , receiving surface scanning data, where the surface scanning data is data obtained by performing surface scanning on the clastic rock thin section sample corresponding to the second component set image.

[0049] In the embodiment of the present application, the computer device is also connected to the surface scanning device. The surface scanning device is implemented as a test instrument for accurately identifying clastic rocks as described above. In the embodiment of the present application, the surface scanning device includes but is not limited to at least one of molecular spectra such as infrared spectra and Raman spectra, X-ray fluorescence (X-ray Fluorescence, XRF) spectra, and X-ray energy spectrum analysis (Energy Dispersive X-ray Spectroscopy, EDS). Optionally, the computer device is connected to the surface scanning device for communication, and the computer device sends the position corresponding to the second component set image to the surface scanning device. The surface scanning area performs surface scanning on the clastic rock thin section sample image based on the above position, and feeds the generated surface scanning data back to the computer device.

[0050] Step 104 , verifying the second component recognition result based on the surface scanning data to obtain a verification result.

[0051] The surface scanning data can be used to determine each component region in the second component set image from the mineral dimension, wherein each second component region in the second component set image corresponds to surface scanning data indicating its mineral characteristics, so the surface scanning data can be used to verify the second component identification result of each second component region in the second component set image.

[0052] Step 105, determining the components of the clastic rock based on the first component identification result, the second component identification result and the verification result.

[0053] In the embodiment of the present application, the first component identification result is the result obtained through the clastic rock thin section sample image, and the first component identification result can directly characterize the component corresponding to each first component area. At the same time, the components corresponding to each second distinguished area are obtained by combining the second component identification result and the verification result. In one example, the second component identification result shows that the component corresponding to the second component area is component A, and the probability of component A is 50%, and the verification result shows that the component corresponding to the second component area is component B, and the probability of component B is 70%. The verification result is selected, and the corresponding component in the second component area is determined to be component B.

[0054] After determining the recognition results corresponding to each component area, the various components in the clastic rock thin section sample image can be determined, and then the components of the clastic rock can be determined. In an embodiment of the present application, the determination results of the components of the clastic rock will be output in the form of a clastic rock component image. In one example, the clastic rock component image includes a clastic rock thin section sample image, on which the division of component areas and the components corresponding to each component area are superimposed. In other embodiments of the present application, the determination results of the components of the clastic rock will be output in the form of a list. The embodiment of the present application does not limit the composition content of the clastic rock.

[0055] In summary, the method provided in the embodiment of the present application, before determining the components of the clastic rock thin section sample by means of surface scanning, divides the clastic rock thin section sample image into a first component set image and a second component set image by means of a clastic rock identification binary classification model, after determining the component identification result in the first component set image, further verifies the content in the second component set image, and finally determines the components of the clastic rock thin section sample by combining the first component identification result, the second component identification result and the verification result. The clastic rock thin section sample image is identified by means of a clastic rock identification binary classification model, and after selecting the area corresponding to the second component set image, the component identification result in the second component area is verified twice by means of surface scanning data. In this process, only the position corresponding to the second component set image needs to be surface scanned, thereby reducing the surface scanning area, thereby reducing the working time consumed by the surface scanning, and improving the efficiency of determining the components of the clastic rock.

[0056] In one embodiment of the present application, the first component region is a non-single crystalline component region, and the second component region is a single crystalline component region. Corresponding to the division of the first component region and the second component region, the binary classification model for clastic rock identification needs to divide various component regions. In the embodiment of the present application, the components are divided by a multi-level binary classification method.

[0057] First, the components are divided into clastic components or interstitial components. Among them, clastics are a component of sedimentary rocks or sediments, which are the product of mechanical weathering of parent rocks; interstitial components are the connecting materials between individual clastics.

[0058] Subsequently, the debris components are divided into terrigenous debris components and non-terrigenous debris components. Among them, terrigenous debris refers to the debris formed by physical weathering or mechanical destruction of the parent rock in the terrigenous area, mainly including quartz debris, feldspar debris, rock debris, etc., and non-terrigenous debris refers to the debris formed by physical weathering or mechanical destruction of the parent rock in the non-terrigenous area, mainly including endogenous debris, volcanic debris, etc. At the same time, the filling material component is divided into a cementing material component and a miscellaneous filling material component. Among them, the miscellaneous filling material indicates the fine mechanical admixtures filled between the debris particles. In an embodiment of the present application, the miscellaneous filling material can be realized as at least one of silt, clay material, subdivision, and carbonate mortar. The cementing material indicates the chemical precipitation position in the filling material other than the miscellaneous filling material.

[0059] Subsequently, the cement component is further divided into siliceous calcareous component and muddy component according to its material composition, and the terrigenous debris component is divided into quartz feldspar component and rock debris component according to its debris morphology.

[0060] Figure 2 A structural schematic diagram of a clastic rock binary classification model provided by an exemplary embodiment of the present application is shown, wherein the clastic rock binary classification model 200 includes a first classification model level 210, a second classification model level 220 and a third classification model level 230, wherein the first classification model level 210 includes a component classification sub-model 211, the second classification model level 220 includes a clastic classification sub-model 221 and a filling material classification sub-model 222, and the third classification model level 230 includes a terrigenous clastic classification sub-model 231 and a cementation material classification sub-model 232. At this time, the component classification submodel 211 in the first classification model level 210 is connected to the debris classification submodel 221 and the filling material classification submodel 222 in the second classification model level 220; the debris classification submodel 221 in the second classification model level 220 is connected to the terrigenous debris classification submodel 231 in the third classification model level 230, and the filling material classification submodel 222 in the second classification model level 220 is connected to the cementation material classification submodel 232 in the third classification model level 230.

[0061] In the above-mentioned clastic rock binary classification model, when the clastic rock thin section sample image 201 is input into the clastic rock identification binary classification model 200, the clastic rock thin section sample image first passes through the component classification sub-model 211 in the first classification model level 210 to obtain a clastic sub-image 213 corresponding to the clastic classification result and a filling sub-image 214 corresponding to the filling classification result.

[0062] Secondly, the debris sub-image 213 will be input into the debris classification sub-model 221, and the output will be the non-terrigenous debris sub-image 223 corresponding to the non-terrigenous debris classification result and the terrigenous debris sub-image 224 corresponding to the terrigenous debris classification result; the interstitial material sub-image will be input into the interstitial material classification sub-model 222, and the output will be the cementation material sub-image 225 corresponding to the cementation classification result and the base interstitial material sub-image 226 corresponding to the base classification result. At this time, the non-terrigenous debris sub-image 223 will be directly used as the non-terrigenous debris identification result, and the base interstitial material sub-image 226 will be directly used as the base identification result.

[0063] Finally, the terrigenous debris sub-image 224 will be input into the terrigenous debris classification sub-model 231, and the output will be the rock debris sub-image 233 corresponding to the rock debris identification result and the quartz feldspar debris sub-image 234 corresponding to the quartz feldspar debris identification result. The cement sub-image 225 will be input into the cement classification sub-image 232, and the output will be the mud cement sub-image 235 corresponding to the mud cement identification result and the siliceous calcareous cement sub-image 236 corresponding to the siliceous calcareous cement identification result. The rock debris sub-image 233 will directly determine the rock debris identification result, the quartz feldspar debris sub-image 234 will directly determine the quartz feldspar debris identification result, the mud cement identification sub-image 235 will directly determine the mud cement identification result, and the siliceous calcareous cement sub-image 236 will directly determine the siliceous calcareous cement identification result.

[0064] Based on the above model, in some embodiments of the present application, a lower-level recognition model will be connected at the end of the classification model to further verify the recognition result. At the same time, during the verification process, during the surface scanning process, the scanning area is further determined. Figure 3 A flowchart of a method for determining clastic rock components provided by an exemplary embodiment of the present application is shown. Taking the method applied to a computer device as an example, the method includes:

[0065] Step 301, obtaining a clastic rock thin section sample image.

[0066] As mentioned above, the clastic rock thin section sample image includes at least two component areas, and at least two component areas include at least two different components. The clastic rock thin section sample image can be an image pre-stored in a computer device, or an image received from other computer devices through a communication network, or an image obtained and processed from an image acquisition device through a data line connection. The embodiment of the present application does not limit the actual generation method of the clastic rock thin section sample image.

[0067] Step 302: Input the clastic rock thin section sample image into the component classification sub-model, and output a clastic sub-image and a filling material sub-image.

[0068] In the embodiment of the present application, the two-classification model for clastic rock identification is composed of a classification sub-model and an identification sub-model, and is used to classify and identify and verify clastic rock thin section sample images based on the components in the clastic rock.

[0069] Figure 4 FIG. 4 is a schematic diagram showing a structure of a clastic rock identification binary classification model 400 provided by an exemplary embodiment of the present application. Figure 4 The clastic rock identification binary classification model 400 includes a first classification model level 410, a second classification model level 420, a third classification model level 430, a first identification model level 440, and a second identification model level 450. The first classification model level 410 includes a component classification sub-model 411, the second classification model level 420 includes a clastic classification sub-model 421 and a filling material classification sub-model 422, the third classification model level 430 includes a terrigenous clastic classification sub-model 431 and a cement classification sub-model 432, the first identification model level 440 includes a non-terrigenous clastic rock identification sub-model 441 and a matrix identification sub-model 442, and the second identification model level 450 includes a rock clastic identification sub-model 451, a quartz feldspar identification sub-model 452, a siliceous calcareous identification sub-model 453, and a muddy identification sub-model 454.

[0070] At this time, the component classification submodel 411 is connected to the debris classification submodel 421 and the interstitial material classification submodel 422, the debris classification submodel 421 is connected to the terrigenous debris classification submodel 431, the debris classification submodel 421 is connected to the non-terrigenous debris identification submodel 441, and the interstitial material classification submodel 422 is connected to the matrix identification submodel 442; the terrigenous debris classification submodel 431 is respectively connected to the rock debris identification submodel 451 and the quartz feldspar identification submodel 452, and the cementation classification submodel 432 is respectively connected to the siliceous calcareous identification submodel 453 and the muddy identification submodel 454.

[0071] As described in the above embodiments, the above classification sub-model and the recognition sub-model are both neural network models based on deep learning. In one example, the structures of the above classification sub-models are the same, and the structures of the above recognition sub-models are the same; in another example, the structures of the above classification sub-model and the recognition sub-model are different. On the premise that the above models are neural network models based on deep learning, this application does not limit the specific forms of the classification sub-model and the recognition sub-model.

[0072] In step 302, the debris sub-image and the interstitial sub-image may be images obtained by reassembling the contents of the non-similar components in the rock image after deleting them, or may be images obtained by directly deleting the contents of the non-similar components in the rock image. The embodiment of the present application does not limit the specific generation method and presentation form of the debris sub-image and the interstitial sub-image.

[0073] Step 303, input the debris sub-image into the debris classification sub-model, and output a non-terrigenous debris sub-image and a terrigenous debris sub-image.

[0074] In the embodiment of the present application, the terrigenous debris sub-image is used to indicate that the component area in the sub-image belongs to terrigenous debris, and the non-terrigenous debris sub-image is used to indicate that the component area in the sub-image belongs to non-terrigenous debris. As described in step 302, the terrigenous debris sub-image and the non-terrigenous debris sub-image are both sub-images obtained by deleting or reorganizing the debris sub-image.

[0075] Step 304, input the terrigenous debris sub-image into the terrigenous debris classification sub-model, and output a rock debris sub-image and a quartz feldspar debris sub-image.

[0076] In the embodiment of the present application, the rock debris sub-image is used to indicate that the component region in the sub-image belongs to rock debris, and the quartz feldspar debris sub-image is used to indicate that the component region in the sub-image belongs to quartz or feldspar. As described in step 302, the rock debris sub-image and the quartz feldspar debris sub-image are both sub-images obtained by deleting or reorganizing the terrigenous debris sub-image.

[0077] Step 305, input the interstitial material sub-image into the interstitial material classification sub-model, and output the interstitial material sub-image and the cementing material sub-image.

[0078] In the embodiment of the present application, the miscellaneous interstitial material sub-image is used to indicate that the component region in the sub-image belongs to the miscellaneous interstitial material, and the cementing material sub-image is used to indicate that the component region in the sub-image belongs to the cementing material. As described in step 402, the miscellaneous interstitial material sub-image and the cementing material sub-image are both sub-images obtained by deleting or reorganizing the interstitial material sub-image.

[0079] Step 306, input the cementation sub-image into the cementation classification sub-model, and output a siliceous and calcareous cementation sub-image and a shale cementation sub-image.

[0080] In the embodiment of the present application, the siliceous calcareous cement sub-image is used to indicate that the component region in the sub-image belongs to siliceous cement or calcareous cement, and the argillaceous cement sub-image is used to indicate that the component region in the sub-image belongs to argillaceous cement. As described in step 302, both the siliceous calcareous cement sub-image and the argillaceous cement sub-image are sub-images obtained by deleting or reorganizing the cement sub-image.

[0081] In the embodiment of the present application, step 303 and step 304 are synchronously executed after step 302 is executed, and step 305 and step 306 are synchronously executed after step 303 and step 304 are executed.

[0082] Step 307, input the non-terrigenous debris sub-image into the non-terrigenous debris identification sub-model, output the non-terrigenous debris identification result, and determine the non-terrigenous debris area based on the non-terrigenous debris identification result.

[0083] In the embodiment of the present application, the non-terrigenous debris identification result is the result obtained after the non-terrigenous debris sub-image is identified and tested. In one example, the non-terrigenous debris identification result screens out some positions in the non-terrigenous debris sub-image, selects the remaining non-terrigenous debris sub-image as the non-terrigenous debris identification result, and determines the non-terrigenous debris area.

[0084] Step 308 , input the rock debris sub-image into the rock debris identification sub-model, output a rock debris identification result, and determine the rock debris area based on the rock debris identification result.

[0085] In the embodiment of the present application, the rock debris identification result is the result obtained after the rock debris sub-image is identified and tested. In one example, the rock debris identification result screens out some positions in the rock debris sub-image, selects the remaining rock debris sub-image as the rock debris identification result, and determines the rock debris area.

[0086] Step 309: input the quartz feldspar debris sub-image into a quartz feldspar debris identification module, output a quartz feldspar debris identification result, and determine the quartz feldspar debris area based on the quartz feldspar debris identification result.

[0087] In the embodiment of the present application, the quartz feldspar fragment identification result is the result obtained after the quartz feldspar fragment sub-image is identified and tested. In one example, the quartz feldspar fragment identification result screens out some positions in the quartz feldspar fragment sub-image, selects the remaining quartz feldspar fragment sub-image as the quartz feldspar fragment identification result, and determines the quartz feldspar fragment area. Optionally, the quartz feldspar fragment identification result will further distinguish quartz from feldspar.

[0088] Step 310, inputting the impurity-based interstitial-filler sub-image into an impurity-based interstitial-filler recognition module, outputting an impurity-based interstitial-filler recognition result, and determining an impurity-based interstitial-filler region based on the impurity-based interstitial-filler recognition result.

[0089] In the embodiment of the present application, the miscellaneous interstitial identification result is the result obtained after the miscellaneous interstitial sub-image is identified and tested. In one example, the miscellaneous interstitial identification result screens out some positions in the miscellaneous interstitial sub-image, selects the remaining miscellaneous interstitial sub-image as the miscellaneous interstitial identification result, and determines the miscellaneous interstitial area.

[0090] Step 311, input the siliceous calcareous cement sub-image into a siliceous calcareous cement identification model, output a siliceous calcareous cement identification result, and determine the siliceous calcareous cement area based on the siliceous calcareous cement identification result.

[0091] In the embodiment of the present application, the siliceous calcareous cement identification result is the result obtained after the siliceous calcareous cement sub-image is identified and tested. In one example, the siliceous calcareous cement identification result screens out some positions in the siliceous calcareous cement sub-image, and selects the remaining siliceous calcareous cement sub-image as the siliceous calcareous cement identification result. Optionally, the siliceous calcareous cement identification result will further distinguish between siliceous materials and calcareous materials, and determine the siliceous calcareous cement area.

[0092] Step 312: input the mud cementation sub-image into a mud cementation recognition model, output a mud cementation recognition result, and determine the mud cementation area based on the mud cementation recognition result.

[0093] In the embodiment of the present application, the mud cementation recognition result is the result obtained after the mud cementation sub-image is recognized and tested. In one example, the mud cementation recognition result screens out some positions in the mud cementation sub-image, selects the remaining mud cementation sub-image as the mud cementation recognition result, and determines the mud cementation area.

[0094] In the embodiment of the present application, steps 307 to 312 are executed synchronously after step 305 and step 306 are executed. In other embodiments of the present application, steps 307 to 312 can be executed after receiving their corresponding sub-images; or, steps 307 to 312 are executed according to the priority preset in the computer device. The present application does not limit the execution order of steps 307 to 312.

[0095] Step 313, determining the single crystal component region based on the quartz feldspar debris region and the siliceous calcareous cement region.

[0096] In the embodiment of the present application, the material in the clastic rock is divided into a single crystalline form and a non-single crystalline form. The single crystalline state indicates that a component region includes and only includes one grain. In the clastic rock, the single crystalline component generally includes quartz, feldspar, siliceous component and calcareous component. Therefore, in the present application, the quartz-feldspar clastic region and the siliceous-calcareous cement component region are taken as the single crystalline component region.

[0097] Step 314, determining the non-single crystalline component region based on the non-terrigenous debris identification results, the cement identification results, the matrix filling material identification results and the mud cement identification results.

[0098] In the embodiment of the present application, except for the single crystalline component area shown in step 313, the remaining areas, that is, the areas indicated by the non-terrigenous debris identification results, cementation identification results, matrix filling material identification results and mud cementation identification results are non-single crystalline component areas.

[0099] In the embodiment of the present application, a first component set image may be generated based on the non-single crystalline component region, and a second component set image may be generated based on the single crystalline component region.

[0100] Step 315, input the second group set image into the region screening model, and output the region screening result.

[0101] In the embodiment of the present application, the second component set image is an image corresponding to the single crystal component region, and the component of this part needs to be verified by surface scanning.

[0102] In the embodiment of the present application, as described above, the regional screening model is a neural network model based on deep learning, and is used to screen the portion of the single crystal component region suitable for surface scanning. In the embodiment of the present application, the screening criterion is the number of impurities per unit area. After screening, the computer device can obtain the regional screening results.

[0103] In one example of the present application, the process is the process of screening clean areas in the component area, and the purpose of the process of screening clean areas is to avoid interference factors in the surface scanning process. Interference factors are mainly divided into the first type of interference factors and the second type of interference factors. The first type of interference factors indicates interference factors related to the properties of the mineral itself, including alteration phenomena, twinning phenomena, inclusion phenomena, crack phenomena, etc. caused by the properties of the mineral itself. Among them, alteration refers to the process in which the composition of minerals changes and new minerals are generated due to the influence of the outside world. In one example, feldspar is easily altered into clay minerals; twinning refers to the regular intergrowth of two or more crystals of the same kind, and the connection between the crystals may interfere with the test. In one example, polysynthetic twinning is common in plagioclase; inclusions refer to a closed system composed of one or more phases of matter in a mineral and having a phase boundary with the main crystal mineral. In one example, quartz has rutile inclusions; cracks refer to the fracture of minerals caused by external stress. In one example, quartz has cracks. The second type of interference factors indicates interference factors generated during the sample preparation process. Including but not limited to situations where the sample is contaminated with polishing powder, slicing glue, impurities, etc.

[0104] Step 316: Send the area screening result to the scanning device.

[0105] In the embodiment of the present application, the scanning device is a detection instrument connected to a computer device. In one example, the scanning device and the image acquisition device are integrated into the same device, and the present application does not limit the actual implementation of the scanning device. Optionally, the clastic rock thin section sample image is located on the scanning device, and after receiving the regional screening result sent by the computer device, the scanning device performs a surface scan based on the regional screening result, and sends the surface scanning data obtained by the surface scanning to the computer device.

[0106] Step 317, receiving surface scan data.

[0107] Step 317 is the process in which the computer device receives the surface scanning data sent by the scanning device.

[0108] Step 318, determining a surface scan recognition result based on the surface scan data.

[0109] In the present embodiment, the surface scan data is used to indicate the mineral determination result for the components in the single crystal component region.

[0110] Step 319 , in response to the face scan recognition result being the same as the second component recognition result, determining that the verification result indicates that the verification is passed, and determining that the second component recognition result is unchanged.

[0111] In some embodiments of the present application, the surface scanning recognition result is the same as the second component recognition result. In this case, it can be determined that the second component recognition result remains unchanged.

[0112] Step 320 , in response to the face scan recognition result being different from the second component recognition result, determining that the verification result indicates that the verification has failed.

[0113] In some embodiments of the present application, the surface scanning result is different from the second component identification result. In this case, the verification in the single crystal component region fails.

[0114] Step 321 : determining a second component recognition result based on the type of scanning device and the surface scanning recognition result.

[0115] In the event that the verification fails, the computer device stores both the face scanning recognition result and the second component recognition result. At this time, the difference between the face scanning recognition result and the second component recognition result is caused by the type of the scanning device and the image acquisition device that perform the face scanning. In this case, the second component recognition result is determined according to the type of scanning device for the face scanning. In one example, the scanning device includes a first scanning device and a second scanning device. The computer device stores a recognition result determination rule. When the scanning device is a first scanning device and the face scanning recognition result is different from the second component recognition result, the face scanning recognition result is used as the second component recognition result; when the face scanning device is a second scanning device and the face scanning recognition result is different from the second component recognition result, the second component recognition result is used as the second component recognition result, that is, the second component recognition result is determined to be unchanged.

[0116] In one example, the scanning device is a molecular spectroscopy analysis device, which has the advantage of having the feature of fingerprint recognition of minerals, but the disadvantage is that it is easily interfered by fluorescence and molecular spectroscopy sensitive minerals. If the surface scanning recognition result is feldspar and the second component recognition result is quartz, the final result is feldspar; if the surface scanning recognition result is fluorescence interference (interference from altered clay minerals) and the second component recognition result is feldspar, the final result is feldspar; if the surface scanning recognition result is rutile (inclusions, molecular spectroscopy sensitive minerals) and the second component recognition result is quartz, the final result is quartz; if the surface scanning recognition result is silicon carbide (polishing agent) and the second component recognition result is quartz, the final result is quartz.

[0117] Step 322: determine the components of the clastic rock based on the first component identification result and the second component identification result.

[0118] In the embodiment of the present application, after the above steps, the components of each area in the clastic rock thin section sample image are determined. Optionally, at this time, if some areas are screened out due to screening reasons in the above steps, the screened out parts are re-identified to improve the final determination accuracy of the components of the clastic rock.

[0119] In an embodiment of the present application, the final determination result of the clastic rock component can be presented in at least one visual manner. In one example, the final determination result of the clastic rock component is implemented as a visual chart; in another example, the final determination result of the clastic rock component is implemented as a visual text description paragraph; in another example, the final determination result of the clastic rock component is implemented as a picture labeled with the names of each component. The present application does not limit the visualization method of the final determination result of the clastic rock component.

[0120] In summary, the method provided in the embodiment of the present application, before determining the components of the clastic rock thin section sample by means of surface scanning, divides the clastic rock thin section sample image into a first component set image and a second component set image by means of a clastic rock identification binary classification model, after determining the component identification result in the first component set image, further verifies the content in the second component set image, and finally determines the components of the clastic rock thin section sample by combining the first component identification result, the second component identification result and the verification result. The clastic rock thin section sample image is identified by means of a clastic rock identification binary classification model, and after selecting the area corresponding to the second component set image, the component identification result in the second component area is verified twice by means of surface scanning data. In this process, only the position corresponding to the second component set image needs to be surface scanned, thereby reducing the surface scanning area, thereby reducing the working time consumed by the surface scanning, and improving the efficiency of determining the components of the clastic rock.

[0121] The method provided in the embodiment of the present application distinguishes the six common component types in clastic rocks based on the binary classification method of the application classification sub-model group, and determines the components of the clastic rocks based on the distinction results. During the operation process, the component areas are divided and determined based on the output results of the independent trained and improved sub-models, which further improves the accuracy of determining the components of the clastic rocks.

[0122] The method provided in the embodiment of the present application first screens the surface scanning area before performing a surface scanning of the single crystal component area, and performs a surface scanning on the screened area, thereby eliminating the influence of impurities in the surface scanning process and further improving the accuracy of determining the clastic rock components.

[0123] Figure 5 A schematic diagram of a device for determining clastic rock components provided by an exemplary embodiment of the present application is shown, the device comprising:

[0124] An acquisition module 501 is used to acquire a clastic rock thin section sample image, wherein the clastic rock thin section sample image includes at least two component regions;

[0125] An input module 502 is used to input a clastic rock thin section sample image into a clastic rock identification binary classification model, and output a first component set image and a second component set image, wherein the first component set image includes at least one first component region and a first component identification result corresponding to the first component region, and the second component set image includes at least one second component region and a second component identification result corresponding to the second component region, and the clastic rock identification binary classification model is a neural network model based on deep learning;

[0126] A receiving module 503 is used to receive surface scanning data, where the surface scanning data is data obtained by surface scanning the clastic rock thin section sample corresponding to the second component set image;

[0127] A verification module 504 is used to verify the second component recognition result based on the surface scanning data to obtain a verification result;

[0128] The determination module 505 is used to determine the components of the clastic rock based on the first component identification result, the second component identification result and the verification result.

[0129] In an optional embodiment, the first component region is a non-single crystalline component region, and the second component region is a single crystalline component region;

[0130] The second component identification results corresponding to the non-single-crystalline component area include non-terrigenous clastic area, cement area, matrix filling area and mud cement area;

[0131] The single crystal component area includes the quartz feldspar debris area and the siliceous calcareous cement area.

[0132] In an optional embodiment, the binary classification model for clastic rock identification includes a classification sub-model group, and the classification sub-model group includes a component classification sub-model, a clastic classification sub-model, a terrigenous clastic classification sub-model, a filling material classification sub-model and a cementation material classification sub-model.

[0133] The input module 502 is also used to input the clastic rock thin section sample image into the component classification sub-model, and output a clastic sub-image and a filling material sub-image;

[0134] The debris sub-image is input into the debris classification sub-model, and the non-terrigenous debris sub-image and the terrigenous debris sub-image are output;

[0135] The terrigenous debris sub-image is input into the terrigenous debris classification sub-model, and the rock debris sub-image and the quartz feldspar debris sub-image are output;

[0136] Input the interstitial material sub-image into the interstitial material classification sub-model, and output the interstitial material sub-image and the cementing material sub-image;

[0137] Input the cementation sub-image into the cementation classification sub-model, and output the siliceous calcareous cementation sub-image and the argillaceous cementation sub-image;

[0138] The determination module 505 is further used to determine the first component set image based on the non-terrigenous debris sub-image, the rock debris sub-image, the matrix filling material sub-image and the mud cementation material sub-image;

[0139] The second component set image is determined based on the quartz feldspar debris sub-image and the siliceous calcareous cement sub-image.

[0140] In an optional embodiment, the clastic rock identification binary classification model also includes an identification sub-model group, and the identification sub-model group includes a non-terrigenous clastic identification sub-model, a rock clastic identification sub-model, a quartz feldspar clastic identification sub-model, a siliceous calcareous cement identification sub-model, a mud cement identification sub-model and a matrix filling identification sub-model;

[0141] The input module 502 is further used to input the non-terrigenous debris sub-image into the non-terrigenous debris identification sub-model, output the non-terrigenous debris identification result, and determine the non-terrigenous debris area based on the non-terrigenous debris identification result;

[0142] Inputting the rock debris sub-image into the rock debris identification sub-model, outputting the rock debris identification result, and determining the rock debris area based on the rock debris identification result;

[0143] The quartz feldspar fragment sub-image is input into the quartz feldspar fragment identification sub-model, and the quartz feldspar fragment identification result is output, and the quartz feldspar fragment area is determined based on the quartz feldspar fragment identification result;

[0144] Inputting the miscellaneous interstitial material sub-image into the miscellaneous interstitial material identification sub-model, outputting the miscellaneous interstitial material identification result, and determining the miscellaneous interstitial material region based on the miscellaneous interstitial material identification result;

[0145] Inputting the siliceous-calcic cement sub-image into the siliceous-calcic cement identification sub-model, outputting the siliceous-calcic cement identification result, and determining the siliceous-calcic area based on the siliceous-calcic cement identification result;

[0146] Inputting the mud cementation sub-image into the mud cementation identification sub-model, outputting the mud cementation identification result, and determining the mud cementation area based on the mud cementation identification result;

[0147] The determination module 505 is further used to determine the single crystal component region based on the quartz feldspar debris region and the siliceous and calcic region;

[0148] Based on the identification results of non-terrigenous clasts, siliceous calcareous cements, matrix fillings, quartz feldspar clasts and argillaceous cements, the non-single crystalline component area is determined;

[0149] A first component collective image is generated based on the non-single crystalline component region, and a second component collective image is generated based on the single crystalline component region.

[0150] In an optional embodiment, before receiving the surface scanning data, the input module 502 is further used to input the second component set image into the region screening model, and output a region screening result, where the region screening result is used to indicate a portion of the second component set image used for performing the surface scanning data;

[0151] Please refer to Figure 6 The device also includes a sending module 506, which is used to send the area screening result to the scanning device, and the scanning device is used to generate surface scanning data according to the area screening result and send the surface scanning data to the computer device.

[0152] In an optional embodiment, the determination module 505 is further configured to determine the surface scanning recognition result based on the surface scanning data;

[0153] In response to the face scan recognition result being the same as the second component recognition result, it is determined that the verification result indicates that the verification is passed, and it is determined that the second component recognition result is unchanged.

[0154] In an optional embodiment, after determining the surface scan recognition result based on the surface scan data, the determination module 505 is further configured to determine that the verification result indicates that the verification fails in response to the surface scan recognition result being different from the second component recognition result;

[0155] The second component recognition result is determined based on the type of scanning device and the surface scanning recognition result.

[0156] In summary, the device for determining the components of clastic rock provided in the embodiment of the present application, before determining the components of the clastic rock thin section sample by means of surface scanning, divides the clastic rock thin section sample image into a first component set image and a second component set image by means of a clastic rock identification binary classification model, after determining the component identification result in the first component set image, further verifies the content in the second component set image, and finally determines the components of the clastic rock thin section sample by combining the first component identification result, the second component identification result and the verification result. The clastic rock thin section sample image is identified by means of the clastic rock identification binary classification model, and after selecting the area corresponding to the second component set image, the component identification result in the second component area is verified twice by means of surface scanning data. In this process, only the position corresponding to the second component set image needs to be surface scanned, thereby reducing the surface scanning area, thereby reducing the working time consumed by the surface scanning, and improving the efficiency of determining the components of the clastic rock.

[0157] It should be noted that the device for determining the clastic rock components provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above.

[0158] Figure 7 A schematic diagram of the structure of a computer device for executing a method for determining clastic rock components provided by an exemplary embodiment of the present application is shown, and the computer device includes:

[0159] The processor 701 includes one or more processing cores. The processor 1201 executes various functional applications and data processing by running software programs and modules.

[0160] The receiver 702 and the transmitter 703 can be implemented as a communication component, and the communication component can be a communication chip. Optionally, the communication component can implement a signal transmission function. That is, the transmitter 1203 can be used to transmit a control signal to the image acquisition device and the scanning device, and the receiver 702 can be used to receive the corresponding feedback instruction.

[0161] The memory 704 is connected to the processor 701 via a bus 705 .

[0162] The memory 704 may be used to store at least one instruction, and the processor 701 may be used to execute the at least one instruction to implement each step in the above method embodiment.

[0163] An embodiment of the present application also provides a computer-readable storage medium, which stores at least one instruction, at least one program, code set or instruction set, which is loaded and executed by a processor to implement the above-mentioned method for determining the clastic rock components.

[0164] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for determining the clastic rock component described in any of the above embodiments.

[0165] Optionally, the computer readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a solid state drive (SSD), or an optical disk. Among them, the random access memory may include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM). The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0166] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0167] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for determining clastic rock components, characterized in that: The method is applied in a computer device, and the method comprises: Acquire a clastic rock thin section sample image, wherein the clastic rock thin section sample image includes at least two component regions; Inputting the clastic rock thin section sample image into a clastic rock identification binary classification model, outputting a first component set image and a second component set image, wherein the first component set image includes at least one first component region and a first component identification result corresponding to the first component region, and the second component set image includes at least one second component region and a second component identification result corresponding to the second component region, and the clastic rock identification binary classification model is a neural network model based on deep learning; receiving surface scanning data, wherein the surface scanning data is data obtained by surface scanning the clastic rock thin section sample corresponding to the second component set image; Verifying the second component identification result based on the surface scanning data to obtain a verification result; Determining the components of the clastic rock based on the first component identification result, the second component identification result, and the verification result; The first component region is a non-single crystalline component region, and the second component region is a single crystalline component region; The non-single crystalline component region includes a non-terrigenous debris region, a cement region, a matrix filling region and a mud cement region; The single crystal component region includes a quartz feldspar debris region and a siliceous calcareous cement region; The clastic rock identification binary classification model includes a classification sub-model group; The classification sub-model group includes a component classification sub-model, a debris classification sub-model, a terrigenous debris classification sub-model, a gap filling classification sub-model and a cement classification sub-model; The step of inputting the clastic rock thin section sample image into a clastic rock identification binary classification model and outputting a first component set image and a second component set image comprises: Inputting the clastic rock thin section sample image into the component classification sub-model, and outputting a clastic sub-image and a gap-filling material sub-image; Inputting the debris sub-image into the debris classification sub-model, and outputting a non-terrigenous debris sub-image and a terrigenous debris sub-image; Inputting the terrigenous debris sub-image into the terrigenous debris classification sub-model, and outputting a rock debris sub-image and a quartz feldspar debris sub-image; Inputting the interstitial material sub-image into an interstitial material classification sub-model, and outputting an impurity interstitial material sub-image and a cementing material sub-image; Inputting the cementation sub-image into a cementation classification sub-model, and outputting a siliceous calcareous cementation sub-image and a shale cementation sub-image; Determine the first component set image based on the non-terrigenous debris sub-image, the rock debris sub-image, the matrix interstitial material sub-image and the mud cementation material sub-image; Determining the second component set image based on the quartz feldspar debris sub-image and the siliceous calcareous cement sub-image; The clastic rock identification binary classification model also includes an identification sub-model group. The identification sub-model group includes a non-terrigenous debris identification sub-model, a rock debris identification sub-model, a quartz feldspar debris identification sub-model, a siliceous calcareous cement identification sub-model, a muddy cement identification sub-model and a matrix filling identification sub-model; After the cementation sub-image is input into the cementation classification sub-model and the siliceous and calcareous cementation sub-image and the argillaceous cementation sub-image are output, the method comprises: Inputting the non-terrigenous debris sub-image into the non-terrigenous debris identification sub-model, outputting the non-terrigenous debris identification result, and determining the non-terrigenous debris area based on the non-terrigenous debris identification result; Inputting the rock debris sub-image into the rock debris identification sub-model, outputting the rock debris identification result, and determining the rock debris area based on the rock debris identification result; Inputting the quartz feldspar debris sub-image into the quartz feldspar debris identification sub-model, outputting the quartz feldspar debris identification result, and determining the quartz feldspar debris area based on the quartz feldspar debris identification result; Inputting the miscellaneous interstitial material sub-image into the miscellaneous interstitial material identification sub-model, outputting the miscellaneous interstitial material identification result, and determining the miscellaneous interstitial material region based on the miscellaneous interstitial material identification result; Inputting the siliceous-calcic cement sub-image into the siliceous-calcic cement identification sub-model, outputting the siliceous-calcic cement identification result, and determining the siliceous-calcic area based on the siliceous-calcic cement identification result; Inputting the mud cementation sub-image into the mud cementation identification sub-model, outputting the mud cementation identification result, and determining the mud cementation area based on the mud cementation identification result; Determining the single crystal component region based on the quartz feldspar debris region and the siliceous and calcic region; Determine the non-single crystalline component region based on the identification result of the non-terrigenous debris, the identification result of the siliceous calcareous cement, the identification result of the matrix interstitial material, the identification result of the quartz feldspar debris and the identification result of the argillaceous cement; generating the first component set image based on the non-single-crystalline component region, and generating the second component set image based on the single-crystalline component region, Before receiving the surface scanning data, the method further includes: Inputting the second component set image into a region screening model, and outputting a region screening result, wherein the region screening result is used to indicate a portion of the second component set image used for performing surface scanning data; The area screening result is sent to a scanning device, and the scanning device is used to generate surface scanning data according to the area screening result and send the surface scanning data to the computer device.

2. The method according to claim 1, characterized in that The verifying the second component identification result based on the surface scanning data includes: Determine a face scan recognition result based on the face scan data; In response to the face scan recognition result being the same as the second component recognition result, determining that the verification result indicates that the verification is passed, and determining that the second component recognition result is unchanged.

3. The method according to claim 2, characterized in that After determining the surface scanning recognition result based on the surface scanning data, the method further includes: In response to the face scan identification result being different from the second component identification result, determining that the verification result indicates that the verification failed; The second component recognition result is determined based on the type of the scanning device and the surface scanning recognition result.

4. A device for determining clastic rock components, using the method of claim 1, characterized in that: The device comprises: An acquisition module, used for acquiring a clastic rock thin section sample image, wherein the clastic rock thin section sample image includes at least two component regions; An input module, used for inputting the clastic rock thin section sample image into the clastic rock recognition binary classification model, and outputting a first component set image and a second component set image, wherein the first component set image includes at least one first component region and a first component recognition result corresponding to the first component region, and the second component set image includes at least one second component region and a second component recognition result corresponding to the second component region; A receiving module, configured to receive surface scanning data, wherein the surface scanning data is data obtained by surface scanning the clastic rock thin section sample corresponding to the second component set image; A verification module, used for verifying the second component recognition result based on the surface scanning data to obtain a verification result; A determination module is used to determine the components of the clastic rock based on the first component identification result, the second component identification result and the verification result.

5. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the method for determining the clastic rock components as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that: The readable storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by a processor to implement the method for determining the clastic rock components as described in any one of claims 1 to 4.

Images