Multi-source heterogeneous logging data integrated processing method, device, equipment and medium

Abstract

The embodiment of the invention provides a multi-source heterogeneous logging data integrated processing method and device, equipment and a medium. The method comprises the following steps: firstly, acquiring a logging data file; analyzing the logging data file based on a preset analysis engine to obtain a structured data table; then preprocessing the structured data table to obtain a standardized data table; further performing multi-dimensional analysis on the standardized data table to obtain a multi-dimensional analysis result and a visual chart generated based on the multi-dimensional analysis result; and finally, forming a data analysis result package by using the standardized data table, the multi-dimensional analysis result and the visual chart. By means of the method, the processing efficiency of the logging data file is improved, and automatic, efficient, processing and analysis of the logging data are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil and gas exploration and development information, and particularly relates to a multi-source heterogeneous well logging data integrated processing method and device, equipment and medium. BACKGROUND

[0002] In the field of oil and gas exploration and development, well logging data is the core basis for evaluating reservoir characteristics (such as porosity, permeability, oil saturation, etc.), identifying fluid types (oil, gas, water), and calculating reserves. Well logging data usually exists in the form of multi-source heterogeneity, including industry standard formats such as Log ASCII Standard (LAS) files and non-standard formats such as Text File (TXT) files. These data may come from different oil fields, different equipment or different years of acquisition systems, and their encoding methods, data separators, unit representations, data starting lines, etc. are significantly different. In addition, with the expansion of oilfield scale and digital transformation, a single work area may involve thousands of wells of well logging data, and the amount of data grows exponentially.

[0003] In the prior art, the processing method of well logging data usually relies on manual operation, and specific geologists need to preprocess (such as missing value processing, format standardization), quality control, statistical analysis and visualization of these data to support reservoir parameter calculation, fluid identification and development plan formulation.

[0004] However, the traditional method relies on manual operation and fragmented tools, resulting in low processing efficiency and poor result consistency, which is difficult to meet the efficiency and scientificity requirements of modern oil and gas exploration and development for data processing. SUMMARY

[0005] The embodiments of the present application provide a multi-source heterogeneous well logging data integrated processing method, device, equipment and medium, to solve the problem of low processing efficiency and poor result consistency in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a multi-source heterogeneous well logging data integrated processing method, comprising:

[0007] obtaining well logging data files, the well logging data files including standard format files and non-standard format files;

[0008] analyzing the well logging data files based on a preset analysis engine to obtain a structured data table;

[0009] preprocessing the structured data table to obtain a standardized data table;

[0010] perform multi-dimensional analysis on the standardized data table to obtain a multi-dimensional analysis result and a visual chart generated based on the multi-dimensional analysis result;

[0011] form the standardized data table, the multi-dimensional analysis result and the visual chart into a data analysis result package.

[0012] In a possible implementation, the preset parsing engine includes a standard format parsing engine and a non-standard format parsing engine.

[0013] The well logging data file is parsed based on the preset parsing engine to obtain a structured data table, including:

[0014] The file format of the well logging data file is determined.

[0015] When the file format is determined to be a standard format file, the well logging data and metadata corresponding to the well logging data file are read by using the standard format parsing engine to obtain a structured data table.

[0016] When the file format is determined to be a non-standard format file, the character encoding mode of the non-standard format file is identified by using the non-standard format parsing engine.

[0017] The file content of the non-standard format file is analyzed by using the non-standard format parsing engine to determine the field separator type.

[0018] The well name identifier, the depth identifier and the parameter unit row are identified by using the non-standard format parsing engine to determine the starting position of the well logging data.

[0019] The structured data table is obtained based on the character encoding mode, the field separator type and the starting position of the well logging data.

[0020] In a possible implementation, the structured data table is preprocessed to obtain a standardized data table, including:

[0021] The missing values and / or invalid values in the structured data table are identified according to preset values, and the missing values and / or invalid values are replaced with standard null values to obtain a first standardized data table.

[0022] The standard null values in each column of well logging data in the first standardized data table are counted to calculate the missing rate of each column of well logging data.

[0023] For each column of well logging data, the column of well logging data with a missing rate greater than a preset missing rate threshold is deleted to obtain a second standardized data table.

[0024] Data rows containing standard null values in the second standardized data table are removed to generate a data matrix.

[0025] adding a well name identification column to the data matrix to obtain a standardized data table.

[0026] In a possible implementation, the multi-dimensional analysis includes distribution characteristic analysis, statistical characteristic analysis, and correlation analysis.

[0027] The multi-dimensional analysis of the standardized data table obtains a multi-dimensional analysis result, and includes:

[0028] The distribution characteristic analysis is performed on the standardized data table to calculate statistical distribution characteristics of each logging parameter.

[0029] The statistical characteristic analysis is performed on the standardized data table to calculate data characteristics of each logging parameter, and the data characteristics include a median, a mean, a variance, a standard deviation, a quartile, and a dispersion condition.

[0030] The correlation analysis is performed on the standardized data table to calculate a Pearson correlation coefficient matrix and a Spearman correlation coefficient matrix between logging parameters.

[0031] The multi-dimensional analysis result is obtained according to the statistical distribution characteristics, the data characteristics, the Pearson correlation coefficient matrix, and the Spearman correlation coefficient matrix.

[0032] In a possible implementation, the visualized chart generated based on the multi-dimensional analysis result includes:

[0033] The kernel density estimation curve of the logging parameter is generated based on the statistical distribution characteristics.

[0034] The box plot of the logging parameter is generated based on the data characteristics.

[0035] The heat map and the logging parameter correlation diagram are generated based on the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix.

[0036] In a possible implementation, the method further includes:

[0037] According to the number of processor cores, a plurality of process pools are created to match the number of processor cores.

[0038] According to the number of logging data files, the logging data files are distributed to the process pools.

[0039] The parsing, preprocessing, and multi-dimensional analysis tasks of the logging data files are performed in parallel through the process pools.

[0040] In a second aspect, an embodiment of the present application provides a multi-source heterogeneous logging data integrated processing apparatus, including:

[0041] An acquisition module is configured to acquire a well logging data file, the well logging data file including a standard format file and a non-standard format file;

[0042] A first processing module is configured to parse the well logging data file based on a preset parsing engine to obtain a structured data table;

[0043] A second processing module is configured to pre-process the structured data table to obtain a standardized data table;

[0044] An analysis module is configured to perform multi-dimensional analysis on the standardized data table to obtain a multi-dimensional analysis result and a visualized chart generated based on the multi-dimensional analysis result;

[0045] An output module is configured to form a data analysis result package including the standardized data table, the multi-dimensional analysis result and the visualized chart.

[0046] In a possible implementation, the preset parsing engine includes a standard format parsing engine and a non-standard format parsing engine; and the first processing module is specifically configured to:

[0047] determine a file format of the well logging data file;

[0048] when determining that the file format is a standard format file, read well logging data and metadata corresponding to the well logging data file by using the standard format parsing engine to obtain a structured data table;

[0049] when determining that the file format is a non-standard format file, identify a character encoding mode of the non-standard format file by using the non-standard format parsing engine;

[0050] analyze file content of the non-standard format file by using the non-standard format parsing engine to determine a field separator type;

[0051] identify a well name identifier, a depth identifier and a parameter unit row by using the non-standard format parsing engine to determine a starting position of well logging data;

[0052] obtain a structured data table based on the character encoding mode, the field separator type and the starting position of well logging data.

[0053] In a possible implementation, the second processing module is specifically configured to:

[0054] identify missing values and / or invalid values in the structured data table according to a preset value, and replace the missing values and / or invalid values with standard null values to obtain a first standardized data table;

[0055] counting the standard null values in each column of the first standardized data table to calculate a missing rate of each column of the well logging data;

[0056] For each column of well logging data, the column of well logging data with a missing rate greater than a preset missing rate threshold is deleted to obtain a second standardized data table;

[0057] The data rows containing the standard null values in the second standardized data table are removed to generate a data matrix;

[0058] A well name identification column is added to the data matrix to obtain a standardized data table.

[0059] In a possible implementation, the multi-dimensional analysis includes distribution characteristic analysis, statistical characteristic analysis, and correlation analysis; and the analysis module is specifically configured to:

[0060] The standardized data table is subjected to distribution characteristic analysis to calculate statistical distribution characteristics of each well logging parameter;

[0061] The standardized data table is subjected to statistical characteristic analysis to calculate data characteristics of each well logging parameter, the data characteristics including median, mean, variance, standard deviation, quartile, and dispersion;

[0062] The standardized data table is subjected to correlation analysis to calculate a Pearson correlation coefficient matrix and a Spearman correlation coefficient matrix between well logging parameters;

[0063] The multi-dimensional analysis result is obtained according to the statistical distribution characteristics, the data characteristics, the Pearson correlation coefficient matrix, and the Spearman correlation coefficient matrix.

[0064] In a possible implementation, the analysis module is specifically configured to:

[0065] A kernel density estimation curve graph of the well logging parameter is generated based on the statistical distribution characteristics;

[0066] A box plot of the well logging parameter is generated based on the data characteristics;

[0067] A heat map and a well logging parameter correlation graph are generated based on the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix.

[0068] In a possible implementation, the multi-source heterogeneous well logging data integrated processing apparatus further includes a third processing module configured to:

[0069] According to the number of processor cores, a plurality of process pools matched with the number of processor cores are created;

[0070] According to the number of well logging data files, the well logging data files are distributed to the process pools;

[0071] The parsing, preprocessing, and multi-dimensional analysis tasks of the logging data files are performed in parallel by the respective process pools.

[0072] In a third aspect, an electronic device is provided, including: a memory, a processor;

[0073] The memory stores computer-executable instructions.

[0074] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the first aspect and / or various possible implementation manners of the first aspect.

[0075] In a fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementation manners of the first aspect.

[0076] In a fifth aspect, a computer program product is provided, and the computer program product includes a computer program, which, when executed by a processor, implements the first aspect and / or various possible implementation manners of the first aspect.

[0077] The embodiments of the present application provide a multi-source heterogeneous logging data integrated processing method, device, equipment and medium. The method comprises the following steps: first, obtaining a logging data file; then, based on a preset parsing engine, parsing the logging data file, and converting logging data of original standard format files and non-standard format files into a structured data table in a unified format, thereby solving the compatibility problem between different data source files; then, preprocessing the structured data table to obtain a standardized data table, so as to improve the accuracy and comparability of the data; further, performing multi-dimensional analysis on the standardized data table to improve the comprehensiveness and pertinence of the analysis; further, generating a visual chart based on the multi-dimensional analysis result, so that complex geological and engineering information is presented in an intuitive form, facilitating quick understanding and decision support in geological research; finally, forming a complete data analysis result package by combining the standardized data table, the multi-dimensional analysis result and the visual chart, thereby realizing full-process closed-loop management of data from acquisition, cleaning, analysis to output. Through the above method, the processing efficiency of the logging data file is improved, and automatic and efficient processing and analysis of the logging data are realized. BRIEF DESCRIPTION OF DRAWINGS

[0078] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application.

[0079] Figure 1A flowchart of a multi-source heterogeneous logging data integrated processing method provided by an embodiment of the present application is shown in FIG. 1.

[0080] FIG. 2(a) is a box plot of a logging data file provided by an embodiment of the present application;

[0081] FIG. 2(b) is a kernel density plot of a logging data file provided by an embodiment of the present application;

[0082] FIG. 2(c) is a Pearson correlation coefficient matrix heat map of a logging data file provided by an embodiment of the present application;

[0083] FIG. 2(d) is a Spearman correlation coefficient matrix heat map of a logging data file provided by an embodiment of the present application;

[0084] FIG. 2(e) is a logging parameter correlation plot of a logging data file provided by an embodiment of the present application;

[0085] Figure 3 A structural diagram of a multi-source heterogeneous logging data integrated processing device provided by an embodiment of the present application is shown in FIG. 3.

[0086] Figure 4 A structural diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 4.

[0087] The above-described drawings show specific embodiments of the present application, and more detailed descriptions will be given hereinafter. These drawings and written descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0088] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same reference numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all the implementations consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0089] In the field of oil and gas exploration and development, logging data is the core basis for evaluating reservoir characteristics (such as porosity, permeability, oil saturation, etc.), identifying fluid types (oil, gas, water), and calculating reserves. Logging data usually exists in a multi-source heterogeneous form, including industry standard formats (such as LAS files) and non-standard formats (such as TXT text files). These data may come from different oil fields, different equipment or different years of acquisition systems, and their encoding methods, data separators, unit representations, data starting lines, etc. are significantly different. In addition, with the expansion of oilfield scale and digital transformation, a single work area may involve logging data from thousands of wells, and the amount of data grows exponentially.

[0090] In the prior art, the processing method of logging data usually relies on manual operation. Specific geologists need to preprocess these data (such as missing value processing, format standardization), quality control, statistical analysis and visualization display to support reservoir parameter calculation, fluid identification and development plan formulation.

[0091] However, the traditional method relies on manual operation and fragmented tools. For example, for TXT files, engineers need to manually check file encoding, separators, data starting lines, etc., rely on Excel or text editors to adjust line by line, which is tedious and prone to errors. In addition, invalid values are screened by hand, and curves with high missing rates are manually removed. This process relies on experience and lacks automated rules, resulting in low efficiency and easy omission of key data. Finally, the traditional single-process serial processing method cannot handle massive data (such as thousands of well work areas), resulting in long processing time and inability to meet rapid evaluation needs.

[0092] Based on this, the present application proposes a logging data processing method. To solve the problems of traditional logging data processing relying on manual and fragmented tools, low processing efficiency and poor result consistency, the present application improves the processing efficiency of multi-source heterogeneous logging data files by building an automated, standardized and integrated processing method. First, different original logging data files are parsed into structured data tables by a pre-set parsing engine, and geological domain knowledge (such as invalid value marking, missing rate threshold) is solidified as preprocessing rules, reducing labor costs and improving preprocessing efficiency. After standardized preprocessing to ensure data consistency, multi-dimensional analysis is performed in a unified platform and visual charts are generated, and finally a complete data analysis result package is formed. Through this method, the whole process of data acquisition, parsing, preprocessing, analysis and result output is automated, avoiding manual intervention and tool fragmentation, improving data processing efficiency and the accuracy, consistency and traceability of results, thus better meeting the needs of modern oil and gas exploration and development for efficient and scientific data processing.

[0093] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes can not be described again in some examples. The embodiments of the present application will be described below with reference to the drawings.

[0094] Figure 1 A flowchart of a multi-source heterogeneous logging data integrated processing method provided by the embodiments of the present application is shown in FIG. 1. As shown in FIG. 1, the method comprises the following steps. Figure 1

[0095] S101, obtaining a logging data file.

[0096] The logging data file comprises a standard format file and a non-standard format file.

[0097] It should be noted that the standard format file is an industry standard format file, for example, a LAS file, which has a structure complying with certain specifications; the non-standard format file generally has no unified rules in terms of encoding, delimiters, table header structure, etc., for example, a TXT file.

[0098] S102, parsing the logging data file based on a preset parsing engine to obtain a structured data table.

[0099] The preset parsing engine is a parsing rule pre-constructed according to different format files; the preset parsing engine comprises a standard format parsing engine and a non-standard format parsing engine.

[0100] In an implementable manner, first, the file format of the logging data file is determined; when it is determined that the file format is a standard format file, the standard format parsing engine is used to read the logging data and metadata corresponding to the logging data file to obtain a structured data table;

[0101] When it is determined that the file format is a non-standard format file, the non-standard format parsing engine is used to identify the character encoding mode of the non-standard format file; then, the non-standard format parsing engine is used to analyze the file content of the non-standard format file to determine the field delimiter type; then, the non-standard format parsing engine is used to identify the well name identifier, the depth identifier and the parameter unit row to determine the starting position of the logging data; finally, the structured data table is obtained based on the character encoding mode, the field delimiter type and the starting position of the logging data.

[0102] It can be understood that the file format corresponding to the logging data file can be determined by obtaining the extension name corresponding to the logging data file, for example, for a standard format file, the extension name of the logging data file is file name.las; and for a non-standard format file, the extension name of the logging data file is file name, which can be file name.txt.​

[0103] Further, when the file format is determined to be a standard format file, a standard format parsing engine, such as the lasio library, can be used to directly read and parse the header key-value pairs, curve table and data section, extract well name, depth axis, curve code, unit and annotation, and output a structured data table containing all curve data and metadata; when the file format is determined to be a standard format file, a non-standard format parsing engine is used to process the non-standard format file. The non-standard parsing engine first detects the file character encoding, then analyzes the content of the first few lines to infer the field separator (such as comma, space, tab, etc.) or fixed width rule, identifies the header line / unit line / annotation line and locates the data start line, then identifies the depth identifier and well name identifier and normalizes the curve name, and finally converts the non-standard format file into a structured data table.

[0104] It can be understood that the automatic parsing of multi-source heterogeneous files is realized through the standard / non-standard parsing engine constructed in a targeted manner, which greatly improves the automatic recognition and conversion rate, avoids manual file-by-file configuration, improves parsing efficiency and reduces human errors; for the problem of uncertain data start line, the non-standard parsing engine can skip useless file header annotations and accurately find the position of the data start, avoiding errors caused by misreading annotations as data, and significantly improving the reliability and scalability of batch processing as a whole.

[0105] S103, preprocessing the structured data table to obtain a standardized data table.

[0106] In an implementable manner, first, the missing values and / or invalid values in the structured data table are identified according to preset values, and the missing values and / or invalid values are replaced with standard null values to obtain a first standardized data table; then, the standard null values in each column of logging data in the first standardized data table are counted, and the missing rate of each column of logging data is calculated; further, for each column of logging data, the column of logging data with a missing rate greater than a preset missing rate threshold is deleted to obtain a second standardized data table; then, data rows containing standard null values in the second standardized data table are removed to generate a data matrix; finally, a well name identifier column is added to the data matrix to obtain a standardized data table.

[0107] The preset values are common missing value and / or invalid value markers in geology, such as -99999, -9999, 0, etc., and can also be customized according to specific data conditions.

[0108] It should be understood that after the well logging data files in different formats are parsed into a unified structured data table, the data in the structured data table also needs to be preprocessed to eliminate the differences between different source files in terms of missing value marking method, curve completeness, row and column consistency, etc. Specifically, first, according to the missing value and / or invalid value marking commonly used in geology, the abnormal data in the structured data table are identified and uniformly replaced with a standard null value, such as NaN (non-number), to ensure the consistency of well logging data from different sources in terms of missing value processing, thereby obtaining a first standardized data table. Then, the first standardized data table is counted column by column, the proportion of the number of standard null values in each column to the total number of data points, i.e. the missing rate, is calculated, and the columns with a missing rate greater than a preset threshold (such as 50%) are deleted, thereby forming a second standardized data table, avoiding the influence of a large number of invalid curves on subsequent analysis to obtain a second standardized data table. Then, the row records of the second standardized data table are checked, and the rows containing standard null values are removed, thereby generating a completely continuous, non-empty high-quality data matrix. Finally, a well name identification column is uniformly added to the data matrix to ensure the traceability of data from different wells, thereby obtaining a final standardized data table.

[0109] It can be understood that through missing value replacement and threshold rejection, abnormal encoding and low-quality curves in the data are effectively shielded, and the data integrity and reliability are improved. Through row-level null value rejection, the matrix obtained is more conducive to direct input into subsequent statistical analysis and modeling algorithms, reducing the bias caused by null value interpolation or abnormal value introduction. The uniform addition of the well name column realizes the traceability and consistency of the data in batch processing and cross-well comparison. Overall, this step significantly improves the quality of well logging data and reduces the burden of manual cleaning, providing a data foundation for subsequent large-scale parallel processing and automated analysis.

[0110] S104, performing multi-dimensional analysis on the standardized data table to obtain a multi-dimensional analysis result and a visualization chart generated based on the multi-dimensional analysis result.

[0111] The multi-dimensional analysis includes distribution characteristic analysis, statistical characteristic analysis, and correlation analysis.

[0112] It can be understood that through multi-dimensional analysis of the standardized data table, the distribution characteristics, statistical characteristics, and relationships between parameters of well logging data can be comprehensively revealed, and intuitive visualization charts can be automatically generated. This not only improves the analysis efficiency and reduces manual operation, but also ensures the consistency and scientificity of the results.

[0113] S105, forming a data analysis result package from the standardized data table, the multi-dimensional analysis result, and the visualization chart.

[0114] It should be noted that the data analysis result package is obtained by automatically structuring the standardized data table, the multi-dimensional analysis result and the visual chart, which avoids the omission and confusion caused by manual dispersed storage, and improves the completeness and traceability of the result.

[0115] It should be further noted that, in order to improve the processing efficiency of the logging data file, the embodiment of the present application adopts a multi-process parallel mode to process the logging data file, specifically:

[0116] Firstly, a plurality of process pools matched with the number of processor cores are created according to the number of processor cores; then, the logging data files are distributed to the process pools according to the number of logging data files; finally, the parsing, preprocessing and multi-dimensional analysis tasks of the logging data files are executed in parallel by the process pools.

[0117] It can be understood that, in order to improve the processing efficiency of the logging data file, the embodiment of the present application adopts a multi-process parallel mode to process the logging data file. Specifically, firstly, a plurality of process pools matched with the number of processor cores are created to make full use of computing resources; then, the logging data files are distributed to different process pools according to the number of logging data files to achieve balanced distribution of tasks; finally, the parsing, preprocessing and multi-dimensional analysis tasks of the logging data files are executed in parallel by the process pools, thereby significantly shortening the overall processing time and improving the efficiency and scalability of large-scale logging data processing.

[0118] The embodiment of the present application provides a multi-source heterogeneous logging data integrated processing method, which comprises the following steps: firstly, obtaining logging data files; then, based on a preset parsing engine, the logging data files are parsed to convert the logging data of original standard format files and non-standard format files into structured data tables in a unified format, thereby solving the compatibility problem between different data source files; then, the structured data tables are preprocessed to obtain standardized data tables, so as to improve the accuracy and comparability of the data; further, the standardized data tables are subjected to multi-dimensional analysis to improve the comprehensiveness and pertinence of the analysis; further, based on the multi-dimensional analysis result, a visual chart is generated, so that complex geological and engineering information is presented in an intuitive form, which is convenient for rapid understanding and decision support in geological research; finally, the standardized data tables, the multi-dimensional analysis result and the visual chart form a complete data analysis result package, realizing the whole-process closed-loop management of data from acquisition, cleaning, analysis to result output. Through the above method, the processing efficiency of the logging data file is improved, and automatic and efficient processing and analysis of the logging data are realized.

[0119] In an implementable manner, first, the distribution characteristics of the standardized data table are analyzed to calculate the statistical distribution characteristics of each logging parameter; then, the statistical characteristics of the standardized data table are analyzed to calculate the data characteristics of each logging parameter; then, the correlation analysis of the standardized data table is performed to calculate the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix between the logging parameters; finally, the multi-dimensional analysis result is obtained according to the statistical distribution characteristics, the data characteristics, the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix.

[0120] The data characteristics include the median, the mean, the variance, the standard deviation, the quartile and the dispersion.

[0121] It should be further noted that after obtaining the multi-dimensional analysis result, the visualized chart generated according to the multi-dimensional analysis result includes:

[0122] First, the kernel density estimation curve of the logging parameter is generated based on the statistical distribution characteristics; then, the box plot of the logging parameter is generated based on the data characteristics; finally, the heat map and the logging parameter correlation diagram are generated based on the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix.

[0123] It should be understood that first, the distribution characteristics of each column of logging parameters in the standardized data table are analyzed to calculate the data distribution, including the frequency distribution, skewness and kurtosis, and then the kernel density estimation (KDE) curve is generated according to the distribution characteristics, which can intuitively show the value distribution range and trend of each logging parameter, and can quickly identify abnormal values, skewed data and parameter concentration areas, providing intuitive basis for geological reservoir characteristics judgment, while reducing the workload of manual drawing and statistical analysis.

[0124] Then, the statistical characteristics of each column of logging parameters in the standardized data table are analyzed to calculate the key indicators including the median, the mean, the variance, the standard deviation, the quartile and the dispersion, which reflect the concentration trend and fluctuation characteristics of the data, and provide data basis for reservoir evaluation, lithology analysis and fluid identification, while ensuring the consistency and comparability of the analysis.

[0125] Finally, based on the standardized data table, the Pearson correlation coefficient matrix (measuring linear relationship) and the Spearman correlation coefficient matrix (measuring monotonic relationship) between the logging parameters are calculated to reveal the correlation and coupling degree between the parameters, which provides a basis for subsequent geological modeling and parameter correlation analysis.

[0126] It can be understood that by performing distribution feature analysis, statistical feature analysis and correlation analysis on the standardized data table, and generating kernel density curve graph, box plot, heat map and logging parameter correlation graph, the value distribution, concentration trend, dispersion degree and linear and monotonic relationship between parameters of the logging parameters can be reflected. The method not only realizes multi-dimensional quantitative analysis of logging data, but also intuitively presents the analysis results through visual charts, significantly improves the data interpretation efficiency and accuracy, reduces the workload and subjective judgment of manual analysis, and makes the reservoir evaluation, fluid identification and subsequent geological modeling have scientific and traceable quantitative basis.

[0127] FIG. 2(a) is a box plot of a logging data file provided by an embodiment of the present application; FIG. 2(b) is a kernel density plot of a logging data file provided by an embodiment of the present application; FIG. 2(c) is a Pearson correlation coefficient matrix heat map of a logging data file provided by an embodiment of the present application; FIG. 2(d) is a Spearman correlation coefficient matrix heat map of a logging data file provided by an embodiment of the present application; and FIG. 2(e) is a logging parameter correlation graph of a logging data file provided by an embodiment of the present application. As shown in FIG. 2, the embodiment is based on the logging data file of the reservoir in the example of the embodiment, and the box plot, kernel density plot, Pearson correlation coefficient matrix heat map, Spearman correlation coefficient matrix heat map and logging parameter correlation graph are generated. Figure 1 On the basis of the embodiment, experiments are performed on real logging data files, and corresponding visual charts are generated, including box plots, kernel density plots, Pearson correlation coefficient matrix heat maps, Spearman correlation coefficient matrix heat maps and logging parameter correlation graphs, which are described as follows.

[0128] The embodiments of the present application collect real logging data files from certain oilfields in the northwest and southwest regions to test the present application, wherein the logging data includes logging data of 100 well sites in a certain oilfield in the northwest region, logging data of 100 well sites of coal rock gas, and logging data of 100 well sites in a certain oilfield in the southwest region. In FIG. 2(a), the horizontal coordinate is the logging curve name; the vertical coordinate is the numerical scale, and it can be seen that the minimum value of the GR curve is about 50, the maximum value is about 155, and the median is about 100; in FIG. 2(b), each subgraph is the kernel density distribution of a logging curve, and the horizontal coordinate of each subgraph is the numerical range of the logging curve, and the vertical coordinate is the probability density estimate value, which represents the relative possibility of the data points in the vicinity of the value. The higher the curve, the more data points in the region; the lower the curve, the more sparse the data points. Taking the GR curve as an example, it presents an obvious unimodal shape, and most of the data points are distributed around 100. FIG. 2(c) is a Pearson correlation coefficient thermodynamic matrix diagram between the logging curves, the horizontal coordinate is the logging curve name, and the vertical coordinate is the correlation score. From FIG. 2(c), the linear relationship between each two logging curves can be intuitively displayed. Taking SOG and POR as examples, the Pearson coefficient between SOG and POR is 0.83, and there is a high positive correlation between them. SOG directly represents the reservoir gas saturation, and POR indicates the rock porosity development degree; high porosity provides more optimal reservoir space and occurrence probability for natural gas occurrence. It is highly consistent with the classical reservoir geophysical mechanism. FIG. 2(d) is a Spearman correlation coefficient thermodynamic matrix diagram between the logging curves, the horizontal coordinate is the logging curve name, and the vertical coordinate is the monotonicity score. FIG. 2(d) can intuitively display the monotonic relationship between each two logging curves. Taking SOG, POR and PERM as examples, the Spearman correlation coefficient of SOG, POR and PERM is as high as 0.99, revealing a nearly perfect positive monotonic statistical dependence relationship. SOG directly represents the reservoir gas saturation, and POR and PERM respectively quantify the rock porosity and permeability; high porosity and high permeability reservoirs provide superior geological conditions for natural gas enrichment and efficient exploitation. This strong correlation fully complies with the basic theory that reservoir properties control fluid distribution. FIG. 2(e) is a correlation diagram of each two variables. The upper triangular area is a scatter plot of each two logging characteristics; the lower triangular area is a kernel density estimation plot; and the diagonal area is a histogram and kernel density curve superimposed plot.

[0129] Figure 3 The structure diagram of the multi-source heterogeneous logging data integrated processing device provided by the embodiments of the present application is shown in FIG. 1, Figure 3 as shown, the device comprises:

[0130] The acquisition module 301 is configured to acquire logging data files, and the logging data files include standard format files and non-standard format files.

[0131] The first processing module 302 is configured to parse the well logging data file based on a preset parsing engine to obtain a structured data table.

[0132] The second processing module 303 is configured to pre-process the structured data table to obtain a standardized data table.

[0133] The analysis module 304 is configured to perform multi-dimensional analysis on the standardized data table to obtain a multi-dimensional analysis result and a visualized chart generated based on the multi-dimensional analysis result.

[0134] The output module 305 is configured to form the standardized data table, the multi-dimensional analysis result and the visualized chart into a data analysis result package.

[0135] In a possible implementation, the preset parsing engine includes a standard format parsing engine and a non-standard format parsing engine; and the first processing module 302 is specifically configured to:

[0136] determine a file format of the well logging data file;

[0137] when it is determined that the file format is a standard format file, read well logging data and metadata corresponding to the well logging data file by using the standard format parsing engine to obtain the structured data table;

[0138] when it is determined that the file format is a non-standard format file, identify a character encoding mode of the non-standard format file by using the non-standard format parsing engine;

[0139] analyze file content of the non-standard format file by using the non-standard format parsing engine to determine a field separator type;

[0140] identify a well name identifier, a depth identifier and a parameter unit row by using the non-standard format parsing engine to determine a starting position of the well logging data;

[0141] obtain the structured data table based on the character encoding mode, the field separator type and the starting position of the well logging data.

[0142] In a possible implementation, the second processing module 303 is specifically configured to:

[0143] identify missing values and / or invalid values in the structured data table according to a preset value, and replace the missing values and / or the invalid values with standard null values to obtain a first standardized data table;

[0144] count the standard null values in each column of well logging data of the first standardized data table to calculate a missing rate of each column of well logging data;

[0145] for each column of well logging data, delete the column of well logging data with a missing rate greater than a preset missing rate threshold to obtain a second standardized data table;

[0146] remove the data rows containing standard null values in the second standardized data table to generate a data matrix;

[0147] add a well name identification column to the data matrix to obtain a standardized data table.

[0148] In a possible implementation, the multi-dimensional analysis includes distribution characteristic analysis, statistical characteristic analysis, and correlation analysis; the analysis module 304 is specifically configured to:

[0149] perform distribution characteristic analysis on the standardized data table to calculate statistical distribution characteristics of each logging parameter;

[0150] perform statistical characteristic analysis on the standardized data table to calculate data characteristics of each logging parameter, the data characteristics including median, mean, variance, standard deviation, quartile, and dispersion;

[0151] perform correlation analysis on the standardized data table to calculate a Pearson correlation coefficient matrix and a Spearman correlation coefficient matrix between the logging parameters;

[0152] obtain a multi-dimensional analysis result according to the statistical distribution characteristics, the data characteristics, the Pearson correlation coefficient matrix, and the Spearman correlation coefficient matrix.

[0153] In a possible implementation, the analysis module 304 is specifically configured to:

[0154] generate a kernel density estimation curve diagram of the logging parameters based on the statistical distribution characteristics;

[0155] generate a box plot of the logging parameters based on the data characteristics;

[0156] generate a heat map and a logging parameter correlation diagram based on the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix.

[0157] In a possible implementation, the multi-source heterogeneous logging data integrated processing apparatus further includes a third processing module configured to:

[0158] create a plurality of process pools matched with the number of processor cores according to the number of processor cores;

[0159] distribute the logging data files to the process pools according to the number of logging data files;

[0160] perform, by each process pool, parallel execution of the parsing, preprocessing, and multi-dimensional analysis tasks of the logging data files.

[0161] The multi-source heterogeneous logging data integrated processing apparatus provided in the embodiments of the present application can execute the method provided in the method embodiments, and has similar implementation principles and technical effects, which will not be described here in detail.

[0162] Figure 4 A structural schematic diagram of an electronic device provided in an embodiment of the present application is shown in FIG. 4. As shown in the figure, the electronic device 40 provided in the embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, the memory 402 and the communication component 403 are connected through a bus 404. Figure 4

[0163] In the implementation process, the at least one processor 401 executes the computer-executed instructions stored in the memory 402, so that the at least one processor 401 performs the method described above.

[0164] The specific implementation process of the processor 401 can refer to the method embodiments described above, which have similar implementation principles and technical effects, and thus will not be described here again in the embodiment.

[0165] In the above-described embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as the execution of the hardware processor, or be executed by the combination of hardware and software modules in the processor.

[0166] The memory can include a random access memory (RAM), and can also include a non-volatile memory (NVM), such as at least one disk memory.

[0167] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0168] ​The application further provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions.

[0169] The readable storage medium can be implemented by any type of volatile or nonvolatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0170] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0171] The division of units is only a logical function division, and in actual implementation, there can be another division mode, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0172] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiment.

[0173] In addition, the functional units in each embodiment of the application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0174] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the method of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0175] It can be understood by those skilled in the art that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The aforementioned program can be stored in a computer readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, and various media that can store program codes.

[0176] Finally, it should be noted that: those skilled in the art will easily think of other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application that follow the general principles of the present application and include common knowledge or conventional technical means in the art that are not disclosed in the present application, and is not limited to the precise structure described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is only limited by the appended claims.

Claims

1. A method for integrated processing of multi-source heterogeneous logging data, characterized in that, include: Acquire well logging data files, including standard format files and non-standard format files; The well logging data file is parsed based on a preset parsing engine to obtain a structured data table. The preset parsing engine is a parsing rule pre-built according to different file formats. The structured data table is preprocessed to obtain a standardized data table; The standardized data table is subjected to multi-dimensional analysis to obtain multi-dimensional analysis results and visualization charts generated based on the multi-dimensional analysis results. The standardized data tables, multi-dimensional analysis results, and visualization charts are combined into a data analysis outcome package.

2. The method according to claim 1, characterized in that, The preset parsing engine includes a standard format parsing engine and a non-standard format parsing engine; The well logging data file is parsed using a preset parsing engine to obtain a structured data table, including: Determine the file format of the well logging data file; When the file format is determined to be a standard format file, the standard format parsing engine is used to read the logging data and its metadata corresponding to the logging data file to obtain a structured data table; When a file is determined to be a non-standard format file, the non-standard format parsing engine is used to identify the character encoding method of the non-standard format file. The non-standard format parsing engine is used to analyze the file content of the non-standard format file to determine the field delimiter type. The non-standard format parsing engine is used to identify well name identifiers, depth identifiers, and parameter unit rows to determine the starting position of logging data. Based on the character encoding method, field separator type, and the starting position of the logging data, a structured data table is obtained.

3. The method according to claim 1 or 2, characterized in that, The preprocessing of the structured data table to obtain a standardized data table includes: Identify missing and / or invalid values ​​in the structured data table according to preset values, and replace the missing and / or invalid values ​​with standard null values ​​to obtain the first standardized data table; The standard missing values ​​in each column of logging data in the first standardized data table are statistically analyzed, and the missing rate of each column of logging data is calculated. For each column of logging data, the logging data in that column with a missing rate greater than the preset missing rate threshold is deleted to obtain the second standardized data table; Remove data rows containing standard null values ​​from the second standardized data table to generate a data matrix; Add a well name identifier column to the data matrix to obtain a standardized data table.

4. The method according to claim 1, characterized in that, The multidimensional analysis includes distribution feature analysis, statistical feature analysis, and correlation analysis; The multi-dimensional analysis of the standardized data table yields the following results: The standardized data table is subjected to distribution characteristic analysis to calculate the statistical distribution characteristics of each logging parameter; Statistical feature analysis is performed on the standardized data table to calculate the data characteristics of each logging parameter. The data characteristics include median, mean, variance, standard deviation, quartiles, and dispersion. Correlation analysis was performed on the standardized data table to calculate the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix between the logging parameters; Based on the statistical distribution characteristics, data characteristics, Pearson correlation coefficient matrix, and Spearman correlation coefficient matrix, multidimensional analysis results are obtained.

5. The method according to claim 4, characterized in that, The visualization charts generated based on the multi-dimensional analysis results include: Based on the statistical distribution characteristics, a kernel density estimation curve of the logging parameters is generated; A box plot of logging parameters is generated based on the data characteristics; Heat maps and well logging parameter correlation maps are generated based on the Pearson correlation coefficient matrix and the Spearman correlation coefficient matrix.

6. The method according to claim 1, characterized in that, The method further includes: Create multiple process pools that match the number of processor cores. The well logging data files are allocated to the process pool according to the number of files. The well logging data files are parsed, preprocessed, and analyzed in parallel by each process pool.

7. A multi-source heterogeneous well logging data integrated processing device, characterized in that, include: The acquisition module is used to acquire well logging data files, including standard format files and non-standard format files; The first processing module is used to parse the well logging data file based on a preset parsing engine to obtain a structured data table; The second processing module is used to preprocess the structured data table to obtain a standardized data table; The analysis module is used to perform multi-dimensional analysis on the standardized data table, obtain multi-dimensional analysis results and visualization charts generated based on the multi-dimensional analysis results; The output module is used to combine the standardized data tables, multi-dimensional analysis results, and visualization charts into a data analysis outcome package.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it is used to implement the method as described in any one of claims 1-6.

Images