A method for automatically matching and identifying key parameters of a well drilling operation report

Abstract

The present application relates to the petroleum industry data application technical field, more particularly, it relates to a kind of well drilling operation report key parameter automatic matching identification method, specifically comprising the following steps: S1.read well drilling operation report;S2.the key parameter in well drilling operation report is identified and analyzed and collated, and is divided into several metadata;S3 key parameter automatic matching;S4.table identification;S5.cell attribute and value segmentation;S6.resolve result storage and extraction.The present application aims at overcoming the shortcomings of prior art, provides a kind of well drilling operation report key parameter automatic matching identification method, can efficiently effectively identify and extract the information therein, greatly improve the application value of this kind of data, also promote the improvement of related process research efficiency, provide good application foundation for subsequent big data analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data application in the petroleum industry, and more particularly to a method for automatically matching and identifying key parameters of a drilling operation report. BACKGROUND

[0002] The drilling operation report is very important information in the process of drilling construction on site in the petroleum industry, and has a high real-time requirement, so it is necessary to quickly analyze the formed drilling operation report for analysis and research by geology researchers and drilling construction personnel. At present, due to the long cycle of manual data collection, all business personnel cannot quickly obtain first-hand on-site construction information, thereby hindering related technical research, especially after an accident occurs at the well site, further analysis and research need to be carried out through such data. At the same time, a drilling operation report is generated every day for each drilling, and a large number of drilling operation reports are accumulated in each petroleum enterprise. If only manual input is relied on, a large amount of manpower, material resources and financial resources need to be spent, and the time is also relatively lagging, which greatly affects the process and geological research. How to quickly and automatically analyze a large number of drilling operation reports has become an urgent need.

[0003] A Chinese patent discloses an engineering daily report analysis method based on a deep learning algorithm, which can read and store the content related to the predefined keywords in the engineering daily report. However, the content that has not been predefined cannot be identified, and the data cannot be classified and sorted in a targeted manner when reading, and it is also impossible to identify whether the reading is complete. SUMMARY

[0004] The present application aims to overcome the deficiencies of the prior art and provide a method for automatically matching and identifying key parameters of a drilling operation report, which can efficiently identify and extract information in the report, greatly improve the application value of such data, and promote the improvement of the efficiency of related process research, thereby providing a good application foundation for subsequent big data analysis.

[0005] To solve the above technical problems, the technical solution adopted by the present application is as follows:

[0006] The present application provides a method for automatically matching and identifying key parameters of a drilling operation report, characterized in that it comprises the following steps:

[0007] S1. reading a drilling operation report;

[0008] S2. identifying, analyzing and sorting the key parameters in the drilling operation report, and dividing them into a plurality of metadata;

[0009] S3. Automatic matching of key parameters: based on regular expressions, the key parameters are matched to the corresponding statistical table according to the rules of the business meaning of the key parameters in step S2;

[0010] S4. Table identification: the object content and boundary of different types of tables in the drilling operation report are identified;

[0011] S5. Segmentation of attributes and values in a cell: the attributes and corresponding values of objects in the same cell in the drilling operation report are segmented;

[0012] S6. Storage and extraction of parsing results: after the drilling operation report data is parsed, the data needs to be organized in the form of metadata, so that a tree structure storage mode is formed in the statistical table, thereby facilitating data extraction and application.

[0013] Further, after step S5, it further includes step Sa. Identification of the starting and ending positions of multi-row data; for the multi-row data table in the drilling operation report, the starting and ending positions of the data are judged according to the read content to ensure the completeness of the read content;

[0014] Further, the key parameters in step S2 include wellbore objects, operation activities, operation activity hierarchical relationships, operation activity occurrence frequencies, and record number frequencies.

[0015] Further, the identification of the key parameters in step S2 is as follows:

[0016] Calibration of wellbore objects: the wellbore is identified according to the Chinese name, English name, and various abbreviation formats of business habits of the wellbore;

[0017] Calibration of operation activities: the operation activities are identified according to the names of the operation activities and the abbreviations or aliases in the operation activity habits;

[0018] Calibration of operation activity hierarchical relationships: the upper and lower levels are defined according to the inclusion relationship of different operation activities in the drilling operation process;

[0019] Calibration of operation activity occurrence frequencies: the number of times the operation activity occurs under the parent activity of the operation activity is identified, wherein N represents multiple times, and S represents a single time;

[0020] Calibration of record number frequencies: the number of records generated under the same wellbore and operation activity is identified, wherein M represents multiple records, and O represents a single record;

[0021] Calibration of attributes: the standard name and alias of the attribute are identified by matching regular expressions, and the default type and dimension unit of the attribute are identified.

[0022] Further, the automatic matching of the key parameters in the step S3 is as follows: according to the defined objects, activities and attribute information, the matching rules are used to extract the actual data in the drilling operation report analysis process, which includes the identification according to different data types, such as character type, numerical type, date type and combined type.

[0023] Further, the character type includes combined analysis of multiple attributes, the numerical type includes pure numerical value and combination with dimension unit, the date type includes Chinese and English date formats and different separators, and the combined type includes multi-segment combination of numerical value and symbol or dimension.

[0024] Further, the judgment of the end position of the multiple-row data in the step Sa is as follows: the end position is determined when the first column is empty or the first column is a serial number or a pre-filled value, and the subsequent columns have no actual data.

[0025] Further, the identification of the start and end positions of the multiple-row data in the step Sa determines the boundary positions of different types of drilling operation report forms in complex table styles, and the start and end positions of the content in the drilling operation report need to be obtained after processing according to different situations. The specific steps are as follows:

[0026] Sa01. The drilling operation report is a horizontal data table. If the first row is a table header, the second row is the table content, and the table content ends when the entire row is empty. If the table header has multiple rows and some columns have merged cells, the table header characteristic code needs to be established to determine whether each column is merged across rows and the number of rows crossed, so as to determine the real starting row of the table content.

[0027] Sa02. The drilling operation report is a vertical data table, which also needs to use the table header characteristic code for judgment. First, the characteristic code is used to determine the number of table header columns, including the case of merging across columns and rows, so as to determine the starting column of the data.

[0028] Sa03. If the first column of the horizontal data table or the first row of the vertical data table is the start of the data content and is a serial number or a specific preset content, but other columns or rows of the same data record are empty, the data record row or column is invalid data, which needs to be judged by the data characteristics. The data characteristics need to be determined according to the core attributes defined by different data tables. The core attribute must not be empty for the data record to be valid.

[0029] Further, the specific process of the table recognition in the step S4 is as follows: the content is recognized according to the name of the key parameter and the alias rule, and the non-standard expression of the key parameter name in the drilling operation report is corrected.

[0030] Further, the correction method is as follows: the features of each key parameter core attribute are extracted to form specific feature codes, and the feature codes are used for unified and standardized description.

[0031] Further, the splitting of the cell attribute and value in the step S5 is specifically as follows: since the attribute and actual value in the same cell are composed of multiple spaces and line breaks, the attribute and corresponding value are obtained by overall extraction and segmentation, and the corresponding dimension unit is separated from the attribute text.

[0032] Further, the splitting of the cell attribute and value in the step S5 is specifically as follows:

[0033] S501. The conventional table is parsed by recognizing the table header and the type of table content;

[0034] S502. The composite table, in which the attribute name, dimension unit and attribute value are placed in the same cell, and different types of content are separated by different identifiers;

[0035] S503. The irregular cell, in which the cell border line is incomplete, and for the cross-page table, the cell content needs to be extracted and parsed after special recognition of the border line;

[0036] S504. When part of the cell content is close to the cell border line, the cell content recognition will be affected, and for the number 1 or character l, the character height of the table content is obtained first, and then the cell content is extracted and parsed after comparison with the border line height.

[0037] Further, the storage and extraction of the parsed results in the step S6 are specifically as follows: for the parsed table and data type, the data is stored according to the architecture of the metadata, wherein a unique row identifier needs to be specified for different attribute combinations from the unified activity, which is used to distinguish the different records belonging to the data table.

[0038] Further, the parsed results of the drilling report document content in the step S6 are stored in a tree structure in the form of metadata, through the tree structure, all the data tables and attribute data of the one-time activity contained in the drilling report are flexibly and logically connected to the corresponding hierarchical position in the form of leaf nodes, and in this way, the unified maintenance and management are carried out, and the data from different sources is provided to the user for comparative analysis.

[0039] Compared with the prior art, the beneficial effects of the present application are:

[0040] The application provides a drilling operation report rapid batch automatic analysis method based on a camelot algorithm, efficiently identifies and extracts information in the report, greatly improves the application value of the data, and promotes the improvement of the related process research efficiency; meanwhile, by establishing object, activity and attribute metadata structures, the tree type structure storage and management of the analysis results are carried out, the unified association dimension of the object, activity and attribute metadata definition and the structured data can be established, so that the seamless integration of the unstructured information and the structured data is realized, and a good application foundation is provided for subsequent big data analysis. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flow chart of a drilling operation report key parameter automatic matching and identifying method of the application.

[0042] Figure 2 An object tree type structure storage schematic diagram of a wellbore of the application. DETAILED DESCRIPTION

[0043] The application will be further described below in combination with specific embodiments. The drawings are only used for exemplary description, and the representation is only a schematic diagram, not a physical diagram, and cannot be understood as a limitation on the patent; in order to better illustrate the embodiments of the application, some components in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product; for those skilled in the art, it can be understood that some well-known structures in the drawings and their descriptions can be omitted.

[0044] In the description of the application, it should be understood that the terms “center”, “longitudinal”, “transverse”, “length”, “width”, “thickness”, “upper”, “lower”, “front”, “rear”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inner”, “outer”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential” and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the application and simplifying the description, and therefore cannot be understood as indicating or implying that the devices or elements indicated must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the application.

[0045] In addition, the terms “first” and “second” are only for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with “first” and “second” can explicitly or implicitly include at least one of the features. In the description of the application, the meaning of “multiple” is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0046] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0047] Embodiment 1

[0048] As Figure 1 The first embodiment of the well drilling operation report key parameter automatic matching and identification method of the present application is shown, which specifically comprises the following steps:

[0049] S1. reading the well drilling operation report;

[0050] S2. identifying, analyzing and arranging the key parameters in the well drilling operation report, and dividing them into several metadata;

[0051] The key parameters include wellbore object, operation activity, operation activity hierarchical relationship, operation activity frequency, and record number frequency. The specific steps are as follows:

[0052] Calibration of wellbore object: identifying the wellbore according to the Chinese name, English name and various abbreviation formats of business habits;

[0053] Calibration of operation activity: identifying the operation activity according to the name of the operation activity and the abbreviation or alias of the operation activity habit;

[0054] Calibration of operation activity hierarchical relationship: defining the upper and lower levels according to the containing and belonging relationship of different operation activities in the well drilling operation process;

[0055] Calibration of operation activity frequency: identifying the number of times the operation activity occurs under the parent activity of the operation activity, wherein N represents multiple times and S represents single time;

[0056] Calibration of record number frequency: identifying the number of records generated under the same wellbore and operation activity, wherein M represents multiple records and O represents single record;

[0057] Calibration of attribute: identifying the standard name and alias of the attribute by matching regular expression, and identifying the default type and dimension unit of the attribute.

[0058] S3. Key parameter automatic matching: based on regular expressions, according to the corresponding rules of the business meaning of the key parameters in step S2, each metadata is matched to the corresponding statistical table;

[0059] For different drilling operation reports, due to the habit difference of the preparation personnel, different documents have different expression and naming methods in terms of objects, activities and attribute naming, which is also an important reason why the batch analysis of this type of document data cannot be well performed for a long time. The present application uses big data as the basis, and statistically analyzes different objects, business activities and attributes, and combines the actual business specifications to comb and define relatively perfect recognition rules and algorithms, so that the operation report can be batch recognized with high accuracy.

[0060] According to the defined object, activity and attribute information, matching rules are used for actual data extraction in the drilling operation report analysis process, which includes identification according to different data types, such as character type, numerical type, date type and combined type. The character type includes multi-attribute combined analysis, the numerical type includes pure numerical value and combination with dimension unit, the date type includes Chinese and English date format and different separators, and the combined type includes multi-segment combination of numerical value and symbol or dimension.

[0061] S4. Table recognition: the object content and boundary of different types of tables in the drilling operation report are clearly recognized;

[0062] In the drilling operation report PDF, in order to facilitate printing, different direction and dimension data tables are often combined in the same page, which also leads to a large automatic recognition error. The present application uses the method of combining metadata and table feature code to fundamentally solve the problem of recognition error.

[0063] According to the name and alias rules of the key parameters, the content is recognized, and the non-standard expression of the key parameter name in the drilling operation report is corrected. The correction method is as follows: the characteristics of each key parameter core attribute are extracted to form a specific feature code, and the feature code is used for unified and standardized description.

[0064] S5. Attribute and value segmentation in a cell: the attribute and corresponding value of the object in the same cell in the drilling operation report are segmented;

[0065] In the drilling operation report PDF, the same attribute, dimension unit and actual value are distributed in the same cell according to the business habit. In the actual analysis process, the irregular cell border and special attribute value content need to be preprocessed before the content is segmented and analyzed. The specific steps are as follows:

[0066] S501. Regular table, parsed by identifying the table header and the type of table content;

[0067] S502. Compound table, part of the table in the drilling operation report places the attribute name, unit of dimension and attribute value in the same cell, and different types of content are separated by different identifiers;

[0068] S503. Irregular cell, the cell border line in part of the drilling operation report is incomplete, and for the table across the page, the cell content needs to be extracted and parsed after special identification of the border line;

[0069] S504. When part of the cell content is close to the cell border line, it will affect the identification of the cell content, and for the number 1 or character 1, the character height of the table content needs to be obtained first, compared with the border line height, and then the cell content is extracted and parsed.

[0070] Sa. Identification of the starting and ending positions of multi-row data; for the multi-row data table in the drilling operation report, the starting and ending positions of the data are determined according to the read content to ensure the completeness of the read content;

[0071] The start and end positions of the actual content of the data table can determine the boundary positions of different types of data tables in complex table styles, and the start and end positions of the content in the data table need to be obtained after special processing according to different situations, and the specific steps are as follows:

[0072] Sa01. The drilling operation report is a horizontal data table, if the first row is the table header, the second row is the table content, and the table content ends when the whole row is empty; if the table header has multiple rows and part of the columns have merged cells, at this time, the table header characteristic code needs to be established, and the characteristic of the table header is used to determine whether each column is merged across rows and the number of rows crossed, so as to determine the real starting row of the table content;

[0073] Sa02. The drilling operation report is a vertical data table, which also needs to use the table header characteristic code for judgment, first determine the number of table header columns according to the characteristic code, including the case of merging across columns and rows, so as to determine the starting column of the data;

[0074] Sa03. If the first column of the horizontal data table content or the first row of the vertical data table is the starting of the data content, and is the serial number or specific preset content, such as depth, but other columns or rows of the same data record are empty, the data record row or column is invalid data, which needs to be judged by the data characteristic, and the data characteristic needs to be determined according to the core attribute defined by different data tables. The core attribute must not be empty for the data record to be valid.

[0075] S6. Analyze the results of storage and extraction; after parsing the drilling operation report data, the data needs to be organized according to the metadata mode, so that a tree structure storage mode is formed in the statistical table, thereby facilitating data extraction and application.

[0076] For the parsed table and data type, the data is stored according to the metadata architecture, wherein a unique row identifier needs to be specified for different attribute combinations from the unified activity, for distinguishing the different record attributions of the data table.

[0077] Further, the drilling report document content parsing results in step S6 are stored in a tree structure according to the metadata mode. Through the tree structure, the data table and attribute data content of all primary activities contained in the drilling report are flexibly and logically connected to the corresponding hierarchical position in the form of leaf nodes. In this way, unified maintenance and management are performed, and data from different sources are provided to users for comparative analysis.

[0078] Embodiment 2

[0079] The following is a second embodiment of a drilling operation report key parameter automatic matching and identification method of the present application. The present application is described in detail below. In the implementation process, different processing is performed according to different table style types and cell types. The specific implementation steps are as follows:

[0080] S1. Read the drilling operation report;

[0081] According to the drilling operation report transmitted back by the drilling site every day, the latest report file is automatically extracted from a specific directory. The drilling operation report contains the name of the oil and gas field, the region, the wellbore object, and the characteristics of the wellbore, including but not limited to wellbore name, drilling identification number, water depth, well type, well type, risk category, etc.

[0082] S2. Identify, analyze and arrange the key parameters in the drilling operation report, and divide them into several metadata;

[0083] The wellbore object in the drilling operation report is identified, and the wellbore object is taken as an example for illustration;

[0084] S3. Key parameter automatic matching: based on regular expressions, according to the corresponding rules of the business meaning of the key parameters in step S2, each metadata is matched to the corresponding statistical table;

[0085] According to the arranged wellbore alias library, the corresponding wellbore name in the report is automatically identified and extracted by regular expressions, including the wellbore name or code in Chinese and English documents, and is automatically matched to the standard wellbore master data;

[0086] Extracting report date; the operation report is one per day, and all operation activity information corresponds to the date. By reading specific attributes, the operation report date is obtained, and different date formats (including Chinese and English and other formats) are extracted and standardized according to the date format rules; all contents related to the wellbore object are identified and matched one by one.

[0087] S4. Table identification: the object content and boundary of different types of tables in the drilling operation report are clearly identified;

[0088] For the drilling operation report, due to the different content filled in each day, the length or style of different tables may change, therefore, the boundaries of different types of tables need to be identified first, so as to determine the range of different operation activity data;

[0089] Table classification identification; the established drilling operation report activity relationship classifies and arranges various drilling operation activities involved in the drilling operation report, and establishes the upper and lower level attribution relationship; according to the established operation report activity characteristic code, the content in each table boundary range is matched to determine the corresponding operation activity type;

[0090] S5. Splitting of attributes and values in cells: splitting the attributes and corresponding values of objects in the same cell in the drilling operation report;

[0091] Table style identification; according to the activity classification determined by table classification identification, the table style is identified;

[0092] According to the table header characteristic code, it is judged whether it is a horizontal table;

[0093] According to the table header characteristic code, it is judged whether it is a vertical table;

[0094] According to the table header characteristic code, it is judged whether it is a composite table;

[0095] For horizontal table, the table header is identified by combining the table header characteristic code determined by operation activity type;

[0096] According to the horizontal table header characteristic code, the single row table header is identified, and the table header attribute is extracted;

[0097] According to the horizontal table content characteristic code, the start and end row positions of the table content are identified;

[0098] For vertical table, the table header is identified by combining the table header characteristic code determined by operation activity type;

[0099] According to the vertical table header characteristic code, the single table header is identified, and the table header attribute is extracted;

[0100] According to the vertical table content characteristic code, the start and end column positions of the table content are identified;

[0101] For the composite table, the cell border line is recognized, and the incomplete border line in the cross-page table is recognized by calculating the font height of the cell content;

[0102] The cell content is cut; for the cell content in the composite table, the table attribute, dimension unit and attribute value in the cell content are recognized according to the table content characteristic code;

[0103] S6. Analysis result storage and extraction; after the drilling operation report data is parsed, the data needs to be organized in the form of metadata, so that a tree structure storage mode is formed in the statistical table, thereby facilitating data extraction and application.

[0104] For the table headers and table contents obtained in different table styles, the matching and standardization of the operation activity attributes are performed;

[0105] For different levels of operation activities, the metadata is synthesized according to the sorted operation activity classification results;

[0106] The recognized metadata is standardized, including object, activity and attribute standard name processing, and dimension unit standardization conversion processing, to form data conforming to the storage specification.

[0107] The storage model is as shown in Figure 2 .

[0108] Through the above implementation, the user can quickly automatically parse and standardize the storage of the drilling operation report returned from the field, and associate the main data with the structured data center to form a unified data storage and management, so as to provide a basis for the engineering researchers to obtain drilling site operation parameters in time, and for the geological researchers to comprehensively compare and analyze the geological research results.

[0109] Embodiment 3

[0110] The following is a third embodiment of a drilling operation report key parameter automatic matching and identifying method of the present application, which is similar to the second embodiment, and the difference lies in that the drilling operation report further includes a multi-row data table. For the multi-row data table, the starting and ending positions need to be identified through the following steps:

[0111] The following steps follow step S5;

[0112] Sa. Identification of the starting and ending positions of the multi-row data; for the multi-row data table in the drilling operation report, the starting and ending positions of the data are judged according to the read content to ensure the completeness of the read content;

[0113] The multi-row table header is recognized according to the horizontal table header characteristic code;

[0114] For the transverse multi-row table header, a merged cell in the table header is identified, and table header attributes are extracted;

[0115] According to the longitudinal table header feature code, the multi-table header is identified;

[0116] For the longitudinal multi-table header, a merged cell in the table header is identified, and table header attributes are extracted;

[0117] Subsequent access step S6 is performed for the next operation.

[0118] Obviously, the above embodiments of the present application are merely exemplary and are not intended to limit the embodiments of the present application. Based on the above description, other different forms of changes or variations can be made by those of ordinary skill in the art. Here, it is not necessary and impossible to exhaust all the embodiments. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the claims of the present application.

Claims

1. A method for automatically matching and identifying key parameters of a drilling operation report, characterized in that, Specifically comprising the following steps: S1, reading a drilling operation report; S2, identifying and analyzing key parameters in the drilling operation report, and dividing them into several metadata; The key parameters include wellbore objects, operation activities, operation activity hierarchical relationships, operation activity occurrence frequencies, and record frequencies; The identification of the key parameters is as follows: Calibration of wellbore objects: identifying wellbores according to Chinese names, English names, and various abbreviation formats of business habits; Calibration of operation activities: identifying operation activities according to names and abbreviations or aliases of operation activities in business habits; Calibration of operation activity hierarchical relationships: defining upper and lower levels according to the inclusion relationship of different operation activities in the drilling operation process; Calibration of operation activity occurrence frequencies: identifying the number of times an operation activity occurs under its parent activity, where N represents multiple times and S represents a single time; Calibration of record frequencies: identifying the number of records generated under the same wellbore and operation activity, where M represents multiple records and O represents a single record; S3, automatic matching of key parameters: based on regular expressions, each metadata is matched to the corresponding statistical table according to the corresponding rules of the business meaning of the key parameters in step S2; S4, table identification: clearly identifying the object content and boundaries of different types of tables in the drilling operation report; S5, segmentation of attributes and values within a cell: segmenting the attributes and corresponding values of objects within the same cell in the drilling operation report; After step S5, the step Sa of identifying the starting and ending positions of multiple rows of data is also included, and the specific steps are as follows: Sa01, the drilling operation report is a horizontal data table. If the first row is a table header, the second row is the table content, and the table content ends when the entire row is empty. If the table header has multiple rows and some columns have merged cells, a table header characteristic code needs to be established to determine whether each column is merged across rows and the number of rows crossed, thereby determining the actual starting row of the table content; Sa02, the drilling operation report is a vertical data table, which also needs to be judged by a table header characteristic code. The characteristic code is used to determine the number of table header columns, including the case of cross-column and cross-row merging, thereby determining the column where the data starts; Sa03, if the first column of the horizontal data table or the first row of the vertical data table is the starting point of the data content and is a serial number or a specific preset content, but other columns or rows of the same data record are empty, then the data record row or column is invalid data, which needs to be judged with the aid of data characteristics. The data characteristics need to be determined according to the core attributes defined for different data tables. The core attributes must not be empty for the data record to be valid; S6, storage and extraction of parsed results; After parsing the drilling operation report data, the data needs to be organized in the form of metadata to form a tree-like storage mode in the statistical table, thereby facilitating data extraction and application.

2. The method of claim 1, wherein, The automatic matching of the key parameters in the step S3 is as follows: according to the defined objects, activities and attribute information, the matching rules are used to extract the actual data in the drilling operation report analysis process, which includes the identification according to different data types, including character type, numerical type, date type and combination type.

3. The method of claim 2, wherein, The character type includes the combination analysis of multiple attributes, the numerical type includes pure numerical value and combination with dimension unit, the date type includes Chinese and English date format and different separators, and the combination type includes multi-segment combination of numerical value and symbol or dimension.

4. The method of claim 3, wherein, The specific process of the table identification in the step S4 is as follows: the content is identified according to the name of the key parameter and the alias rule, and the non-standard expression of the key parameter name in the drilling operation report is corrected.

5. The method of claim 4, wherein, The correction method is as follows: the characteristics of the core attribute of each key parameter are extracted to form a specific feature code, and the feature code is used for unified and standardized description.

6. The method of claim 1, wherein, The specific operation of the attribute and value segmentation in the cell in the step S5 is as follows: since the attribute and actual value in the same cell are composed of multiple spaces and line breaks, the attribute and corresponding value are obtained by segmenting after overall extraction, and the corresponding dimension unit is separated from the attribute text.

7. The method of claim 1, wherein, The storage and extraction of the analysis results in the step S6 are as follows: for the parsed tables and data types, the data is stored according to the architecture of the metadata, and the unique row identifier needs to be specified for different attribute combinations from the unified activity, which is used to distinguish the different record attributions of the data table.

Images