A method and device for digitizing drilling column chart based on structural pattern recognition

Abstract

The present invention discloses a method and device for digitizing a borehole column chart based on structural pattern recognition, the method comprising: determining the left and right boundaries of the column chart from a borehole column chart file; identifying the lithology symbols contained within the left and right boundary ranges; wherein the lithology symbols include a geometrical element or a combination of multiple geometrical elements for representing different lithology information; segmenting the column chart according to the boundaries of the same lithology symbol to obtain multiple different stratigraphic sections; matching the stratigraphic sections with templates in a preset lithology recognition database layer by layer to determine the lithology name corresponding to each stratigraphic section; and obtaining the digitization result of the borehole column chart according to the correspondence between the lithology symbols and the lithology names. In this way, the lithology symbols in the borehole column chart can be directly converted into corresponding structured lithology name data, solving the problem of lithology digitization of the borehole column chart with only lithology symbols but no lithology names.

Description

Technical Field

[0001] The present invention relates to the technical field of geological information processing, and in particular to a method, device, electronic equipment and storage medium for digitizing a borehole column chart based on structural pattern recognition. Background Art

[0002] With the continuous advancement of geological exploration technology and the improvement of geological information systems, the standardized management of geological data and three-dimensional geological modeling have become the core work of the information construction of the geological industry. In this process, the effective management of a large amount of borehole information is particularly important. It is an important part of the standardized management of geological data, and it is also an indispensable basic data for three-dimensional geological modeling. Borehole information is usually recorded and displayed in the form of a borehole column chart. This graphical expression is intuitive and easy to understand. However, in practical applications, borehole column charts are mostly raw data generated by professional software according to preset templates, and their information extraction work faces many challenges. At present, most software only supports the processing of structured information. For unstructured information in borehole column charts, such as lithology symbols, there is still a lack of effective automated extraction methods.

[0003] Existing methods mainly focus on digitizing the tabular files of lithology text information in the borehole column. This method can achieve good results when the text information is clear and the format is standardized. However, when there is only lithology symbol information in the borehole column, the existing methods cannot effectively recognize and digitize these symbol information. This not only limits the comprehensive utilization of geological data, but also hinders the improvement of the accuracy of 3D geological modeling. Summary of the invention

[0004] The embodiments of the present invention solve the problem that the prior art cannot digitize the lithology of a borehole column chart that only has lithology symbols but no lithology names by providing a method, device, electronic device and storage medium for digitizing a borehole column chart based on structural pattern recognition.

[0005] In order to achieve the above object, the technical solution of the embodiment of the present invention is:

[0006] In a first aspect, the present invention provides a method for digitizing a borehole column chart based on structural pattern recognition, comprising: determining the left and right boundaries of the column chart from a borehole column chart file; identifying the lithology symbols contained in the left and right boundaries; wherein the lithology symbols include a geometric element or a combination of multiple geometric elements for representing different lithology information; segmenting the column chart according to the boundaries of the same lithology symbol to obtain multiple different stratigraphic segments; matching the stratigraphic segments layer by layer with templates in a preset lithology identification database to determine the lithology name corresponding to each stratigraphic segment; and obtaining the digitization result of the borehole column chart based on the correspondence between the lithology symbols and the lithology names.

[0007] In some possible implementations, after determining the lithology name corresponding to each stratigraphic segment, the method further includes: determining the elevation value of each stratigraphic segment; and determining the depth of each stratigraphic segment based on a mapping relationship between a preset elevation value and a lithology depth.

[0008] In some possible implementations, according to the correspondence between lithology symbols and lithology names, a digitized result of a borehole column chart is obtained, including: associating and saving the lithology symbols, the lithology names corresponding to the lithology symbols, and the depths of the stratigraphic sections in a database.

[0009] In some possible implementations, the preset lithology identification database stores at least a plurality of lithology symbols and their corresponding lithology names.

[0010] In some possible implementations, when there are lithology symbols and lithology names corresponding to the lithology symbols in the drilling column chart file, the method also includes: determining the left and right boundaries of the track where the lithology name is located; using the left and right boundaries of the track where the lithology name is located as auxiliary tracks to determine the rock layer depth corresponding to the lithology name.

[0011] In some possible implementations, according to the correspondence between lithology symbols and lithology names, a digitized result of a borehole column diagram is obtained, including: associating and saving the lithology symbols, the lithology names corresponding to the lithology symbols, and the rock layer depths corresponding to the lithology names in a database.

[0012] In a second aspect, the present invention provides a borehole column chart digitization device based on structural pattern recognition, comprising: a determination module, used to determine the left and right boundaries of the column chart from the borehole column chart file; an identification module, used to identify the lithology symbols contained in the left and right boundaries; wherein the lithology symbols include a geometric element or a combination of multiple geometric elements for representing different lithology information; a segmentation module, used to segment the column chart according to the boundaries of the same lithology symbol to obtain multiple different stratigraphic segments; a matching module, used to match the stratigraphic segment with the template in the preset lithology identification database layer by layer to determine the lithology name corresponding to each stratigraphic segment; an acquisition module, used to obtain the digitization result of the borehole column chart according to the correspondence between the lithology symbol and the lithology name.

[0013] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing the method provided in the first aspect of the present invention when executing the executable instructions or computer programs stored in the memory.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, implement the method provided in the first aspect of the present invention.

[0015] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0016] In the present invention, the left and right boundaries of the column chart are determined from the borehole column chart file; the lithology symbols contained in the left and right boundary ranges are identified; wherein the lithology symbols include a variety of geometric primitives for representing different lithology information; the column chart is segmented according to the boundaries of the lithology symbols to obtain a plurality of different stratigraphic sections; the stratigraphic sections are matched layer by layer with the templates in the preset lithology identification database to determine the lithology name corresponding to each stratigraphic section; and the digitization result of the borehole column chart is obtained according to the correspondence between the lithology symbols and the lithology names. In this way, by directly identifying the most basic geometric primitives constituting the corresponding lithology symbols, different stratigraphic sections are divided, and the lithology symbols in the borehole column chart can be directly converted into corresponding structured lithology name data, thereby solving the problem of digitization of the lithology of the borehole column chart with only lithology symbols but no lithology names. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention, the accompanying drawings required for use in the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0018] Figure 1 A schematic flow chart of an embodiment of a method for digitizing a drilling histogram based on structural pattern recognition provided for the implementation of the present invention;

[0019] Figure 2a It is the lithological symbol of loess;

[0020] Figure 2b It is the lithology symbol of sandy mudstone;

[0021] Figure 2c It is the lithology symbol of carbonaceous mudstone;

[0022] Figure 3 A schematic flow chart of another embodiment of a method for digitizing a drilling histogram based on structural pattern recognition provided by an embodiment of the present invention;

[0023] Figure 4 It is a structural schematic diagram of a drilling histogram digitization device based on structural pattern recognition in an embodiment of the present invention;

[0024] Figure 5 The figure is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In the relevant description of this embodiment, the terms "including, containing, having" and the like are open terms and are generally understood to include but not be limited to; the term "at least one" is generally understood to mean one or more, where "plurality" refers to two or more; the term "at least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items, for example, "at least one of a, b or c", or "at least one of a, b and c", can all represent: a, b, c, ab (i.e., a and b), ac, bc, or abc, where a, b, c can be single or multiple, respectively; the symbol "A / B" is used to describe the selection relationship of associated objects, generally indicating an "or" relationship before and after.

[0027] In the following description of the present embodiment, the terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "an" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0028] Those skilled in the art should understand that in the following description of the embodiments of the present invention, the order of serial numbers does not mean the order of execution, some or all of the steps can be executed in parallel or sequentially, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0029] It will be appreciated by those skilled in the art that the numerical ranges in the embodiments of the present invention are to be understood as each intermediate value between the upper and lower limits of the scope being specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the range is also included in the present invention. The upper and lower limits of these smaller ranges may be independently included or excluded in the scope.

[0030] Unless otherwise specified, the technical / scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs. Although the present invention only describes preferred methods and materials, any methods and materials similar or equivalent to those herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials related to the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0031] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0032] With the continuous advancement of geological exploration technology and the improvement of geological information systems, the standardized management of geological data and three-dimensional geological modeling have become the core work of the information construction of the geological industry. In this process, the effective management of a large amount of borehole information is particularly important. It is an important part of the standardized management of geological data, and it is also an indispensable basic data for three-dimensional geological modeling. Borehole information is usually recorded and displayed in the form of a borehole column chart. This graphical expression is intuitive and easy to understand. However, in practical applications, borehole column charts are mostly raw data generated by professional software according to preset templates, and their information extraction work faces many challenges. At present, most software only supports the processing of structured information. For unstructured information in borehole column charts, such as lithology symbols, there is still a lack of effective automated extraction methods.

[0033] Existing methods mainly focus on digitizing the tabular files of lithology text information in the borehole column. This method can achieve good results when the text information is clear and the format is standardized. However, when there is only lithology symbol information in the borehole column, the existing methods cannot effectively recognize and digitize these symbol information. This not only limits the comprehensive utilization of geological data, but also hinders the improvement of the accuracy of 3D geological modeling.

[0034] Therefore, developing a method that can efficiently and automatically extract structured information from drill hole column charts, especially for the extraction of lithology symbol information, has become a technical problem that needs to be solved in the current field of geological data management and 3D geological modeling. By solving this problem, not only can the efficiency of geological data processing be improved, but also the accuracy and reliability of 3D geological modeling can be improved, providing more accurate data support for geological exploration and mineral resource development.

[0035] Based on this, the present invention solves the problem that the prior art cannot digitize the lithology of a borehole column chart that only has lithology symbols but no lithology names by providing a method, device, electronic device and storage medium for digitizing a borehole column chart based on structural pattern recognition.

[0036] Figure 1 A schematic diagram of an embodiment of a method for digitizing a drilling column chart based on structural pattern recognition provided for the implementation of the present invention is shown in FIG. Figure 1 As shown, the above method may include:

[0037] S101, determining left and right boundaries of a histogram from a drilling histogram file;

[0038] Among them, the borehole histogram file can be a graphic file stored in electronic form, which is used to display the geological information of the borehole. It can be an image file (such as JPEG, PNG, etc.), a vector graphic file (such as SVG, DXF, etc.), or a specific format file generated by special engineering software (such as CAD, etc.). The file contains all the visual elements of the borehole histogram, such as lines, colors, symbols and text annotations, etc., to reflect the properties of different strata and rocks passed by the borehole. The borehole histogram file integrates a variety of geological information, including stratum name, thickness, lithology description, sampling location, etc., and presents it in an intuitive graphical way. In geological exploration and mineral resource development, the borehole histogram file is an important basis for geological engineers and researchers to conduct geological interpretation and resource evaluation.

[0039] In some embodiments, the method for determining the left and right boundaries of the drilling bar graph may be to identify the boundaries of the bar graph through image processing technology. For example, edge detection algorithm is used to identify edge information in the image, so as to determine the left and right boundaries of the bar graph. Alternatively, it may be a method based on template matching. For example, the bar graph file has a fixed format and layout, and a template may be predefined to determine the boundary position of the bar graph through template matching. Alternatively, a combination of multiple methods may be used to determine the left and right boundaries of the bar graph. For example, the boundary range may be preliminarily determined using image processing technology, and then fine-tuned through template matching to improve the accuracy and reliability of boundary determination. In the embodiments of the present invention, selection may be made according to specific circumstances and needs.

[0040] It is understandable that the determination of the left and right boundaries of the histogram directly affects the accuracy and efficiency of subsequent information extraction. In the process of automatically extracting structured information, determining the left and right boundaries is a prerequisite for identifying different geological information elements (such as stratigraphic lines, lithology symbols, etc.). Only when the boundary range is clear can the elements within the boundary be accurately analyzed and processed. By accurately identifying the left and right boundaries of the histogram, the area range for information extraction can be delineated to avoid misjudgment and extraction of irrelevant information.

[0041] S102, identifying the lithology symbols contained in the left and right boundaries;

[0042] The lithology symbol includes one geometrical element or a combination of multiple geometrical elements for representing different lithology information;

[0043] In the embodiment of the present invention, after the left and right boundaries of the borehole histogram are determined in the above step S101, various lithology symbols can be accurately identified and extracted within the area defined by the boundaries.

[0044] It should be noted that lithology symbols are an important part of geological information expression. Lithology symbols usually appear in the form of multiple geometric primitives to represent different lithology information. For example, a line is one of the most basic primitives, which can appear in different directions, lengths and thicknesses to represent key information such as the strike, dip and thickness of a stratum. For example, a horizontal line is usually used to represent a horizontal stratum, while an oblique line may represent an inclined or folded stratum. In addition to a single line, a lithology symbol can also use a combination of multiple lines. These combinations can form complex patterns to distinguish different stratum types or reveal the contact relationship between strata. For example, a group of parallel and equally spaced lines may represent a uniform stratum, while the density of the lines may reflect the gradual change of the lithology or the thickness change of the stratum. Alternatively, a stratum type can be represented by a horizontal or oblique line, and another stratum type can be represented by a combination of dots and circles. In an embodiment of the present invention, by specifically identifying and analyzing the most basic geometric primitives that constitute the lithology symbol of the bar graph, different geological strata can be accurately determined. This not only helps us better understand the distribution and change patterns of strata, but also provides important reference for subsequent geological exploration, resource development and engineering construction.

[0045] Specifically, before lithology identification, a library of configuration relationships between lithology symbols and lithology names can be established. The same lithology may have multiple lithology symbols, so the lithology library needs to be continuously expanded to ensure the accuracy of lithology digitization. In the lithology channel of the lithology column, each lithology column is composed of one or more groups of graph elements. The unit graph element of the lithology symbol can be identified by the graph element recognition method to determine the lithology it represents.

[0046] For example, FIG2 is a schematic diagram of the structure of a unit element of a lithology symbol in an embodiment of the present invention. Referring to FIG2, Figure 2a It is the lithological symbol of loess, which is represented by multiple parallel vertical lines; Figure 2b It is the lithology symbol of sandy mudstone. Sandy mudstone can have three unit elements; Figure 2c is the lithology symbol of carbonaceous mudstone, which can have two unit elements. The lithology columns in the column chart are composed of these unit elements.

[0047] It is understandable that when there are messy images in the original map, the existing method will be disturbed by these impurities during digitization through picture and graphic recognition, which reduces the accuracy of graphic recognition. However, in the embodiment of the present invention, these impurities can be ignored through primitive recognition, and unit primitives can be found. The most basic primitives such as points and lines are used for recognition. Unit primitives are first divided and then recognized to avoid interference from other primitives, which can improve the accuracy of lithology classification.

[0048] In some embodiments, when the lithology of the histogram is digitized, it is usually necessary to convert the depth on the graph into the actual depth of the borehole, so the top and bottom depths of the borehole can be specified on the graph. In the embodiment of the present invention, the "ruler" track on the histogram can be selected, any two depth scales can be selected, and the depth can be calibrated through proportional transformation to confirm the depth ratio of the histogram, thereby confirming the top and bottom depths of each lithology section.

[0049] In some embodiments, the lithology symbols within the left and right boundaries can be identified by analyzing and processing the images within the left and right boundaries using image processing technology or pattern recognition algorithms, etc. Features such as lines, line shapes, regions and / or colors in the images can be detected to obtain various lithology symbols.

[0050] Understandably, due to the wide variety of lithological symbols, there may be many variants and special cases in practical applications, so the recognition process can have a certain degree of flexibility and accuracy. In order to improve the accuracy and efficiency of recognition, a combination of multiple technical means can be used, such as combining machine learning algorithms for automatic recognition and classification, or using human-computer interaction for auxiliary correction and confirmation.

[0051] S103, segmenting the column chart according to the boundaries of the same lithology symbol to obtain a plurality of different stratigraphic segments;

[0052] In the embodiment of the present invention, after the lithology symbols in the histogram are identified in the above step S102, the histogram can be segmented according to the boundaries of these lithology symbols. The boundaries of the lithology symbols can reflect the boundaries between different strata, so by accurately identifying these boundaries, the histogram can be divided into multiple different stratigraphic segments. Each stratigraphic segment is composed of the same lithology symbols and is used to refer to different geological layers.

[0053] In some embodiments, the geometric characteristics and spatial relationships of the lithology symbols may be considered during the segmentation of the histogram. For example, some lithology symbols may be represented by lines or color blocks. In this case, image processing technology may be used to detect the boundary lines between different lithology symbols and use them as the basis for segmentation. By segmenting the histogram, multiple different stratigraphic segments may be obtained, each of which represents different geological layers and lithology characteristics.

[0054] S104, matching the stratigraphic sections with the templates in the preset lithology identification database layer by layer to determine the lithology name corresponding to each stratigraphic section;

[0055] It should be noted that the preset lithology identification database is a collection of multiple lithology templates. These templates can be constructed based on a large amount of geological data and professional knowledge, and are representative and universal. Each template corresponds to one or more specific lithology information, and contains geological information and feature descriptions related to the lithology.

[0056] In some embodiments, the preset lithology identification database stores at least a plurality of lithology symbols and their corresponding lithology names.

[0057] When matching, each stratigraphic segment in the borehole column chart can be extracted, and its related lithological symbols, such as specific color, texture, geometric structure, etc., can be extracted. Then, these lithological symbols are compared one by one with the templates in the lithological identification database. Through layer-by-layer matching, the lithological template that best matches each stratigraphic segment can be found, thereby determining its corresponding lithological name. In the process of comparison, algorithms and technical means such as pattern recognition and machine learning can be used to improve the accuracy and efficiency of matching.

[0058] In some embodiments, due to the complexity and diversity of geological phenomena, it may be difficult to find a lithology template that fully matches the stratigraphic segment. In this case, a comprehensive judgment can be made by combining multiple information sources and professional knowledge, or other identification methods and technical means can be used to further improve the accuracy of identification.

[0059] In some embodiments, after determining the lithology name corresponding to each of the stratigraphic segments in step S104, the method may further include:

[0060] Determine the elevation value of each stratigraphic section; determine the depth of each stratigraphic section based on the mapping relationship between the preset elevation value and the lithology depth.

[0061] The elevation value of the stratigraphic segment can be the height of the divided column chart in the vertical direction, and this height is determined based on a certain datum or reference point. Specifically, after the column chart is divided according to the boundary of the lithology symbol to obtain multiple stratigraphic segments, the top and bottom of each stratigraphic segment will have a corresponding elevation value. These elevation values ​​can be obtained by measurement or calculation with reference to sea level, a fixed point or a datum with a known elevation.

[0062] It is understandable that the geological structure is a complex three-dimensional system. Knowing only the lithology name and elevation value of the stratigraphic segment is not enough to fully describe its shape and position in the underground space. By determining the depth of the stratigraphic segment, we can more intuitively understand its extension in the vertical direction.

[0063] In some embodiments, the mapping relationship between the preset elevation value and the lithology depth can be a ratio or conversion relationship, which is used to convert the elevation value on the bar graph into the lithology depth of the actual stratum underground. Exemplarily, by selecting two sets of calibration points. These calibration points are points whose screen Y values ​​and corresponding actual depths are known. For example, P1 and P2 are two points on the bar graph, and their Y values ​​correspond to D1 and D2 of the actual stratum depths, respectively. These two sets of data are used as a benchmark, and the corresponding actual depths can be inferred based on the Y values ​​of other points.

[0064] In some embodiments, a formula or algorithm may be established based on the two groups of calibration points through linear interpolation or other mathematical methods to calculate the actual depth of any point.

[0065] For example, the depth of the formation segment can be expressed by the following formula (1):

[0066] d=D1+(P Y -P1 Y ) / (P2 Y -P1 Y )*(D2-D1)(1)

[0067] In formula (1), P Y 、P1 Y 、P2 Y They are the Y values ​​of point P, point P1, and point P2 respectively. According to the Y value of point P (between P1 and P2), and the actual depths D1 and D2 corresponding to P1 and P2, the actual depth d of the stratum section corresponding to point P is calculated. By establishing a mapping relationship, not only the accuracy of geological data processing is improved, but also the distribution of strata in the underground can be understood and analyzed more intuitively.

[0068] S105, obtaining a digitized result of a borehole column chart according to the correspondence between the lithology symbols and the lithology names.

[0069] In some embodiments, the above step S105 may include: associating and saving the lithology symbol, the lithology name corresponding to the lithology symbol, and the depth of the stratigraphic section in a database.

[0070] Specifically, in the database, an independent record can be created for each stratigraphic segment, which contains fields such as lithology symbol, lithology name, and depth. In this way, when it is necessary to query the information of a specific stratigraphic segment, it is only necessary to search by lithology symbol or other related conditions, and the database can quickly return the corresponding record. In addition, by associating and saving information such as lithology symbol, lithology name, and depth, a logical relationship between stratigraphic segments can also be established.

[0071] The following is a specific example to illustrate the method for digitizing a drilling column chart based on structural pattern recognition according to the present invention.

[0072] Figure 3 FIG. 1 is a flow chart of a method for digitizing a drilling histogram based on structural pattern recognition in an embodiment of the present invention, see Figure 3 As shown, the method includes:

[0073] S31, obtaining a mapping relationship between a preset elevation value and a lithology depth;

[0074] S32, determine whether the mapping relationship is legal; if so, execute step S33, otherwise end the process;

[0075] S33, determining the left and right boundaries of the histogram;

[0076] S34, identifies the lithology symbols contained within the boundary;

[0077] S35, segmenting the column chart according to the lithology symbol to obtain a plurality of different stratigraphic sections;

[0078] S36, matching the stratigraphic sections with the templates in the preset lithology identification database layer by layer to determine the lithology name corresponding to each stratigraphic section;

[0079] S37, determining the depth of each stratigraphic section according to the elevation value of the stratigraphic section and the mapping relationship between the preset elevation value and the lithology depth;

[0080] S38, recording the recognition result;

[0081] S39, determine whether the recognition is complete, if so, execute step S310, otherwise, execute step S36;

[0082] S310, editing the recognition result;

[0083] S311, judging whether the recognition result is satisfactory and determining whether to save the recognition result; if so, executing step S312, otherwise abandoning the recognition result and ending;

[0084] S312, the lithology symbol, the lithology name corresponding to the lithology symbol, and the depth of the stratigraphic section are associated and saved in a database.

[0085] In the embodiment of the present invention, the left and right boundaries of the column chart are determined from the borehole column chart file; the lithology symbols contained in the left and right boundary range are identified; wherein the lithology symbols include a variety of geometric elements for representing different lithology information; the column chart is segmented according to the boundaries of the lithology symbols to obtain a plurality of different stratigraphic sections; the stratigraphic sections are matched layer by layer with the templates in the preset lithology identification database to determine the lithology name corresponding to each stratigraphic section; and the digitization result of the borehole column chart is obtained according to the correspondence between the lithology symbols and the lithology names. In this way, the lithology symbols in the borehole column chart can be directly converted into structured lithology name data corresponding to the depth scale, solving the problem of lithology digitization of the borehole column chart with only lithology symbols but no lithology names.

[0086] In some embodiments, when there are lithology symbols and lithology names corresponding to the lithology symbols in the drilling column chart file, the above method may further include:

[0087] Determine the left and right boundaries of the trace where the lithology name is located;

[0088] The left and right boundaries of the trace where the lithology name is located are used as auxiliary traces to determine the depth of the rock layer corresponding to the lithology name.

[0089] Specifically, by using the left and right boundaries of the track where the lithology name is located as auxiliary tracks, the rock formation depth corresponding to the lithology name can be determined as follows: First, the left and right boundaries of the track where the lithology name is located can be determined. By identifying the specific logo or format in the track, the location of the lithology name can be accurately located. The determination of the left and right boundaries not only helps us understand the distribution range of the lithology name in the figure, but also provides an important reference for subsequent processing steps. Afterwards, the left and right boundaries of the track where the lithology name is located can be used as auxiliary tracks. This auxiliary track can be a virtual reference line, which can help us more accurately locate and measure the relationship between the lithology name and the formation depth. Through the auxiliary track, the rock formation depth corresponding to the lithology name can be easily found.

[0090] In the process of determining the depth of rock formations, since the bar graph is usually drawn at a certain scale, some mathematical calculations or scale conversion methods can be used to convert the distance on the graph into the actual depth value. With the help of auxiliary graphs, the conversion can be achieved to obtain accurate rock formation depth information.

[0091] Based on this, in some embodiments, the above step S105 may specifically include: associating and saving the lithology symbol, the lithology name corresponding to the lithology symbol, and the rock layer depth corresponding to the lithology name in a database.

[0092] In the embodiment of the present invention, the left and right boundaries of the column chart are determined from the borehole column chart file; the lithology symbols contained in the left and right boundary range are identified; wherein the lithology symbols include a variety of geometric elements for representing different lithology information; the column chart is segmented according to the boundaries of the lithology symbols to obtain a plurality of different stratigraphic sections; the stratigraphic sections are matched layer by layer with the templates in the preset lithology identification database to determine the lithology name corresponding to each stratigraphic section; and the digitization result of the borehole column chart is obtained according to the correspondence between the lithology symbols and the lithology names. In this way, the lithology symbols in the borehole column chart can be directly converted into structured lithology name data corresponding to the depth scale, solving the problem of lithology digitization of the borehole column chart with only lithology symbols but no lithology names.

[0093] Based on the same inventive concept, an embodiment of the present invention further provides a drilling histogram digitization device based on structural pattern recognition. Figure 4 FIG. 1 is a schematic diagram of a structural diagram of a drilling histogram digitizing device based on structural pattern recognition in an embodiment of the present invention, see Figure 4 As shown, the borehole column chart digitization device 400 based on structural pattern recognition may include: a determination module 401, used to determine the left and right boundaries of the column chart from the borehole column chart file; an identification module 402, used to identify the lithology symbols contained in the left and right boundaries; wherein the lithology symbols include a geometric element or a combination of multiple geometric elements for representing different lithology information; a segmentation module 403, used to segment the column chart according to the boundaries of the same lithology symbol to obtain multiple different stratigraphic segments; a matching module 404, used to match the stratigraphic segment with the template in the preset lithology identification database layer by layer to determine the lithology name corresponding to each stratigraphic segment; an acquisition module 405, used to obtain the digitization result of the borehole column chart according to the correspondence between the lithology symbol and the lithology name.

[0094] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, which may be consistent with the drilling histogram digitization method based on structural pattern recognition in one or more of the above embodiments. Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device in an embodiment of the present invention, see Figure 5 As shown, the electronic device 500 may adopt general computer hardware, including a processor 501 and a memory 502 .

[0095] In some possible implementations, at least one processor may constitute any physical device having a circuit that performs a logical operation on one or more inputs. For example, at least one processor may include one or more integrated circuits (ICs), including application specific integrated circuits (ASICs), microchips, microcontrollers, microprocessors, all or part of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or other circuits suitable for executing instructions or performing logical operations. The instructions executed by at least one processor may be preloaded, for example, into a memory integrated with or embedded in a controller, or may be stored in a separate memory. The memory may include a random access memory (RAM), a read-only memory (ROM), a hard disk, an optical disk, a magnetic medium, a flash memory, other permanent, fixed or volatile memory, or any other mechanism capable of storing instructions. In some embodiments, at least one processor may include more than one processor. Each processor may have a similar structure, or the processor may have different configurations that are electrically connected or disconnected from each other. For example, the processor may be a separate circuit or integrated in a single circuit. When more than one processor is used, the processor may be configured to operate independently or collaboratively. The processors may be coupled electrically, magnetically, optically, acoustically, mechanically, or by other means that allow them to interact.

[0096] Based on the same inventive concept, the present invention provides a computer storage medium storing computer executable instructions. After the computer executable instructions are executed by a processor, a drilling column chart digitization method based on structural pattern recognition as described in one or more of the above embodiments can be implemented.

[0097] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments.

[0098] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some or all of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the present invention.

Claims

1. A method for digitizing a drilling column chart based on structural pattern recognition, characterized in that: include: Determine the left and right boundaries of the histogram from the drilling histogram file; specifically, use an edge detection algorithm to preliminarily identify the edge range in the image, and then adjust the edge range through a template matching method to determine the left and right boundaries of the histogram; Identify the lithology symbols contained in the left and right boundary ranges, specifically by using the most basic graphic elements such as points and lines to identify the lithology symbols, first divide the unit graphic elements, and then identify the unit graphic elements; wherein the lithology symbols include a geometric graphic element or a combination of multiple geometric graphic elements for representing different lithology information; Segmenting the column chart according to the boundaries of the same lithology symbol to obtain a plurality of different stratigraphic segments; The stratigraphic sections are matched layer by layer with the templates in the preset lithological identification database to determine the lithological name corresponding to each stratigraphic section; when matching, the lithological symbols related to each stratigraphic section in the borehole columnar diagram are extracted, including specific colors, textures and geometric structures; then, these lithological symbols are compared one by one with the templates in the lithological identification database using pattern recognition or machine learning algorithms; through layer-by-layer matching, the lithological template that best matches each stratigraphic section is found to determine its corresponding lithological name; then the elevation value of each stratigraphic section is determined; according to the mapping relationship between the preset elevation value and the lithological depth, the depth of each stratigraphic section is determined, specifically: two calibration points P1 and P2 on the columnar diagram are selected, and their screen Y values ​​correspond to the actual stratigraphic depths D1 and D2 respectively, and the depth d of the stratigraphic section corresponding to any point P between points P1 and P2 is calculated by the following formula: d=D1+(P Y -P1 Y ) / (P2 Y -P1 Y )*(D2-D1), where P Y 、P1 Y 、P2 Y are the screen Y values ​​of point P, point P1, and point P2 respectively; when there are lithology symbols and lithology names corresponding to the lithology symbols in the borehole histogram file, first determine the left and right boundaries of the graph track where the lithology name is located; then use the left and right boundaries of the graph track where the lithology name is located as auxiliary graph tracks to determine the rock layer depth corresponding to the lithology name; According to the correspondence between the lithology symbols and the lithology names, the digitized result of the borehole column chart is obtained, specifically, the lithology symbols, the lithology names corresponding to the lithology symbols and the depth of the stratigraphic section are associated and saved in a database.

2. The method according to claim 1, characterized in that The preset lithology identification database at least stores a plurality of lithology symbols and their corresponding lithology names.

3. A drilling column chart digitization device based on structural pattern recognition, characterized in that: include: The determination module is used to determine the left and right boundaries of the histogram from the drilling histogram file; specifically, the edge detection algorithm is used to preliminarily identify the edge range in the image, and then the edge range is adjusted by the template matching method to determine the left and right boundaries of the histogram; The identification module is used to identify the lithology symbols contained in the left and right boundary ranges; specifically, the identification is performed based on the most basic graphic elements such as points and lines, firstly dividing the unit graphic elements, and then identifying the unit graphic elements; wherein the lithology symbols include a geometric graphic element or a combination of multiple geometric graphic elements for representing different lithology information; A segmentation module, used for segmenting the column chart according to the boundaries of the same lithology symbol to obtain a plurality of different stratigraphic segments; The matching module is used to match the stratigraphic sections with the templates in the preset lithological identification database layer by layer to determine the lithological name corresponding to each stratigraphic section; when matching, the lithological symbols related to each stratigraphic section in the borehole columnar diagram are extracted, including specific colors, textures and geometric structures; then, these lithological symbols are compared one by one with the templates in the lithological identification database using pattern recognition or machine learning algorithms; through layer-by-layer matching, the lithological template that best matches each stratigraphic section is found to determine its corresponding lithological name; then the elevation value of each stratigraphic section is determined; according to the mapping relationship between the preset elevation value and the lithological depth, the depth of each stratigraphic section is determined, specifically: two calibration points P1 and P2 on the columnar diagram are selected, and their screen Y values ​​correspond to the actual stratigraphic depths D1 and D2 respectively, and the depth d of the stratigraphic section corresponding to any point P between points P1 and P2 is calculated by the following formula: d=D1+(P Y -P1 Y ) / (P2 Y -P1 Y )*(D2-D1), where P Y 、P1 Y 、P2 Y are the screen Y values ​​of point P, point P1, and point P2 respectively; when there are lithology symbols and lithology names corresponding to the lithology symbols in the borehole histogram file, first determine the left and right boundaries of the graph track where the lithology name is located; then use the left and right boundaries of the graph track where the lithology name is located as auxiliary graph tracks to determine the rock layer depth corresponding to the lithology name; The acquisition module is used to obtain the digital result of the borehole column chart according to the correspondence between the lithology symbol and the lithology name, specifically to associate and save the lithology symbol, the lithology name corresponding to the lithology symbol and the depth of the stratigraphic section in a database.

4. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; A processor, configured to implement the method according to any one of claims 1 to 3 when executing the executable instructions or computer programs stored in the memory.

5. A computer-readable storage medium storing executable instructions or computer programs, characterized in that: When the executable instructions are executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images