A fast method for extracting drilling histogram information
Through text recognition and target value matching, information-experience position collection is generated, and the problem of in-depth training data or inability to extract information in batches in the existing technology is solved, and the rapid and batch processing of drilling bar chart information is achieved without training data is improved. Information acquisition speed and processing efficiency.
Patent Information
- Application Number
- CN202210265364.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-03-17
- Publication Date
- 2025-01-03
- Estimated Expiration
- 2042-03-17
AI Technical Summary
The existing drilling bar chart information extraction method requires training data in advance or cannot extract information in batches, which limits the rapid acquisition and processing efficiency of information.
Create a drilling histogram file through text recognition, create a target value set for matching, generate an information-experience position set, optimize the information extraction speed of subsequent table files, and realize batch processing without training data.
Without extracting training data, it can directly process the drilling histogram chart file, which improves information acquisition speed and supports batch processing of multiple styles of drilling histograms.
Smart Images

Figure CN114648009B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of geological information processing, and in particular relates to a fast method for extracting borehole columnar graph information. Background Art
[0002] Currently, a large amount of drilling information is saved in the form of drilling histograms. This format meets the needs of engineers on site, but is difficult to be further utilized because most software can only use structured information. Therefore, it is very important to efficiently and automatically extract structured information from drilling histograms.
[0003] There are two types of existing methods: 1. Fully automatic extraction method based on machine learning technology 2. Interactive information extraction method based on GIS software. Both methods have their own advantages and disadvantages:
[0004] (1) Fully automatic extraction method based on machine learning technology: Since it requires preliminary training data, it can only process drilling histograms that are consistent with the training data style, but it can be fully automated. However, if you want to process new styles of histograms, you need new data for training and you also need to modify the code to a certain extent.
[0005] (2) Interactive extraction method based on GIS software: It can adapt to various styles of drill hole histograms and is very flexible. However, it is a semi-automatic information extraction method and cannot extract information in batches. It also relies on specific GIS software, which in turn limits the source data format. Summary of the invention
[0006] In view of the above-mentioned deficiencies in the prior art, the present invention provides a fast method for extracting information from a drilling histogram, which solves the problem that the existing method for extracting information from a drilling histogram requires advance training data or cannot extract information from the drilling histogram in batches.
[0007] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is: a fast drilling histogram information extraction method, comprising the following steps:
[0008] S1, extracting the information of the drilling histogram and obtaining a table file of the drilling histogram;
[0009] S2, extracting drilling information from the table file of the drilling histogram;
[0010] S3. Storing the drilling information in a database and extracting the drilling histogram information.
[0011] Further: the step S1 is specifically as follows:
[0012] The drill column chart is extracted for text recognition, and a drill column chart table file is established according to the information extracted from the drill column chart, wherein the drill column chart table file includes a plurality of drill column chart tables.
[0013] Further: the step S2 comprises the following sub-steps:
[0014] S21, creating a target value set according to the information of the drilling histogram;
[0015] S22, matching the target values of the first drilling histogram table according to the target value set to obtain drilling information and an information-experience position set;
[0016] S23, obtaining the drilling information of the next drilling histogram table according to the information-experience position set, and updating the information-experience position set;
[0017] S24, repeat step S23 to obtain the drilling information of the remaining drilling histogram tables, and complete the extraction of drilling information based on the obtained drilling information of all drilling histogram tables.
[0018] The beneficial effect of the above further scheme is: the method of the present invention can be used to obtain drilling information from the drilling bar chart table file in batches. As the table file of the drilling bar chart is processed, the obtained information-empirical position set will be improved, so that the speed of extracting drilling information from the drilling bar chart table will gradually increase.
[0019] Further: the step S21 specifically includes: creating a target value set according to the keywords used in the drilling histogram;
[0020] The target value set is specifically a set of drilling information to be extracted and its corresponding target value, and the target value is specifically a keyword corresponding to the drilling information to be extracted.
[0021] Further: in the step S22, the drilling information is specifically information of all cells in the drilling bar chart table;
[0022] The method for matching the target value is specifically as follows: searching and matching all cells of the first drilling bar chart table according to the target value, obtaining information in the cell and generating an information-experience position record; wherein the information-experience position record includes the cell position information and the number of cell hits;
[0023] The step S22 is specifically as follows: based on the first drilling histogram table, all target value matches are completed in the target value set to obtain drilling information, and the obtained information-empirical position record is used to construct an information-empirical position set.
[0024] The above further solution has the beneficial effect that after processing the first drilling histogram table, an information-experience position set is generated, thereby optimizing the information extraction speed of the remaining drilling histogram tables. The more drilling histogram tables are processed, the faster the processing speed of the next drilling histogram table may be.
[0025] Further: In the step S23, the method for obtaining the table information of the next drilling histogram is specifically as follows:
[0026] SA1. According to the cell position information in the information-experience position set, try to obtain the information in the cells of the drilling bar chart table from high to low in terms of the number of cell hits, and update the number of cell hits recorded in the information-experience position;
[0027] SA2. Check whether all the information in the drilling histogram table has been obtained;
[0028] If yes, then the drilling column chart table information acquisition is completed;
[0029] If not, the target value is matched on the drilling bar chart table information to obtain the information in the cell, and the obtained new information-experience position record is added to the information-experience position set to complete the acquisition of the drilling bar chart table information.
[0030] Further: in the step S23, the method for updating the information-experience position set is specifically: after the drilling information based on the drilling bar chart table is acquired, the cell position information in the information-experience position set is arranged from high to low according to the number of cell hits.
[0031] The beneficial effects of the present invention are:
[0032] (1) The present invention does not need to extract training data and can directly process the drilling bar chart table file. In addition, the method of the present invention is not limited to the bar chart and can also process the drilling bar chart table files in batches.
[0033] (2) Compared with the drilling information extraction method that only uses keywords to match the drilling histogram table, the method of the present invention can utilize the information-empirical position set generated during the processing of the drilling histogram to accelerate the processing, thereby improving the speed of obtaining drilling information. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 Flowchart of a fast drilling histogram information extraction method.
[0035] Figure 2 This is an information diagram of the drilling histogram of the present invention. DETAILED DESCRIPTION
[0036] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.
[0037] Embodiment 1:
[0038] like Figure 1 As shown, in one embodiment of the present invention, a fast method for extracting drilling histogram information includes the following steps:
[0039] S1, extracting the information of the drilling histogram and obtaining a table file of the drilling histogram;
[0040] S2, extracting drilling information from the table file of the drilling histogram;
[0041] S3. Storing the drilling information in a database and extracting the drilling histogram information.
[0042] The step S1 is specifically as follows:
[0043] The drill column chart is extracted for text recognition, and a drill column chart table file is established according to the information extracted from the drill column chart, wherein the drill column chart table file includes a plurality of drill column chart tables.
[0044] The step S2 comprises the following sub-steps:
[0045] S21, creating a target value set according to the information of the drilling histogram;
[0046] S22, matching the target values of the first drilling histogram table according to the target value set to obtain drilling information and an information-experience position set;
[0047] S23, obtaining the drilling information of the next drilling histogram table according to the information-experience position set, and updating the information-experience position set;
[0048] S24, repeat step S23 to obtain the drilling information of the remaining drilling histogram tables, and complete the extraction of drilling information based on the obtained drilling information of all drilling histogram tables.
[0049] The beneficial effect of this embodiment is: the method of the present invention can be used to obtain drilling information from the drilling bar chart table file in batches. As the table file of the drilling bar chart is processed, the obtained information-empirical position set will be improved, so that the speed of extracting drilling information from the drilling bar chart table will gradually increase.
[0050] The basic steps to extract drilling information from the drilling bar chart table are to search for the cell containing the target value in the table and extract the value of the cell. So the key is how to determine the location of the target cell.
[0051] The present invention adopts two basic methods: 1. Acquiring information based on target value matching, 2. Acquiring information based on information-experience position set. Among them, method 1, acquiring information based on target value matching, is the most reliable, and can ensure that information is acquired when there is information; while method 2, acquiring information based on information-experience position set, uses the data acquired in 1 to accelerate the speed of information acquisition.
[0052] like Figure 2 As shown in the figure, the drilling information of the drilling column chart can be divided into two types of information: basic information and layered information. Among them, the position of the basic information is less affected by the actual drilling situation. For example, if there are many experiments in the drilling, the horizontal coordinate position of the basic position information will change, but the vertical coordinate will remain unchanged. The layered information is completely dependent on the actual drilling situation. For example, the number of layers of strata exposed by the drilling will determine the number of layers of cells, and the thickness of each layer also affects the number and size of cells.
[0053] Therefore, the position of basic information is stable, while the position of hierarchical information varies greatly. However, the key to obtaining hierarchical information is to find the position of the graph header. After determining the position of the graph header, the target value matching can be used along the column direction to obtain information. At the same time, the relative position of the graph header and basic information is basically stable. By taking advantage of the stable position of basic information and the stable relative position of the graph header and basic information, an optimized structure is formed: information-experience position set, which can accelerate the acquisition of information from the table.
[0054] Target value: the keyword corresponding to the information. The relationship between information and target value is one-to-many, such as the target values corresponding to the drilling name information include hole name and drilling name.
[0055] Target value set: that is, the set of all the information to be extracted and its corresponding target values.
[0056] Information-Experience Location: The table location to be accessed to obtain certain information. The relationship between information and table location is one-to-many, such as: azimuth-2 rows and 8 columns, 3 rows and 7 columns. At the same time, the number of hits for each index should be recorded, and the one with the highest number of hits will be used first. That is, azimuth-2 rows and 8 columns (5 times), 3 rows and 7 columns (3 times).
[0057] Information-experience position set: that is, the set of all information and corresponding experience positions.
[0058] The step S21 specifically includes: creating a target value set according to the keywords used in the drilling histogram;
[0059] The target value set is specifically a set of drilling information to be extracted and its corresponding target value, and the target value is specifically a keyword corresponding to the drilling information to be extracted.
[0060] In the step S22, the drilling information is specifically information of all cells in the drilling bar chart table;
[0061] The method for matching the target value is specifically as follows: searching and matching all cells of the first drilling bar chart table according to the target value, obtaining information in the cell and generating an information-experience position record; wherein the information-experience position record includes the cell position information and the number of cell hits;
[0062] The step S22 is specifically as follows: based on the first drilling histogram table, all target value matches are completed in the target value set to obtain drilling information, and the obtained information-empirical position record is used to construct an information-empirical position set.
[0063] Since the information-experience position set is empty when processing the first drill histogram table, the information-experience position set is generated after processing the first drill histogram table, thereby optimizing the information extraction speed of the remaining drill histogram tables. The more drill histogram tables are processed, the faster the processing speed of the next drill histogram table may be.
[0064] In step S23, the method for obtaining the table information of the next drilling histogram is specifically as follows:
[0065] SA1. According to the cell position information in the information-experience position set, try to obtain the information in the cells of the drilling bar chart table from high to low in terms of the number of cell hits, and update the number of cell hits recorded in the information-experience position;
[0066] SA2. Check whether all the information in the drilling histogram table has been obtained;
[0067] If yes, then the drilling column chart table information acquisition is completed;
[0068] If not, the target value is matched on the drilling bar chart table information to obtain the information in the cell, and the obtained new information-experience position record is added to the information-experience position set to complete the acquisition of the drilling bar chart table information.
[0069] For example, by matching the target value to find the [Drilling Hole Name] information, that is, by finding the cell containing the target value "Hole Name", the information can be obtained from the cell, and the information-experienced position record can be obtained at the same time. After the drilling hole bar chart table is fully processed, the information-experienced position set is updated. The specific process is to obtain the [Drilling Hole Name] information, the target value is "Hole Name", and finally find the cell value of the 3rd row and 4th column is "Hole Name zk1", then take out the information zk1 and generate the information-experienced position record: Drilling Hole Name-3 rows and 4 columns.
[0070] The basic idea of the present invention is to extract drilling information from the drilling bar chart table. The essence of the present invention is to use the processed data to obtain experience values, and to construct an information-experience position set based on this, and then use the information-experience position set to accelerate the processing speed, thereby achieving the effect of faster processing speed.
[0071] In step S23, the method for updating the information-experience position set is specifically as follows: after the drilling information based on the drilling bar chart table is acquired, the cell position information in the information-experience position set is arranged from high to low according to the number of cell hits.
[0072] The beneficial effects of the present invention are as follows: the present invention can directly process the drilling histogram table file without extracting training data, and the method of the present invention is not limited to the histogram, and can also process the drilling histogram table files in batches.
[0073] Compared with the drilling information extraction method using only the drilling histogram table with keyword matching, the method of the present invention can utilize the information-empirical position set generated during the processing of the drilling histogram to accelerate the processing, thereby improving the speed of obtaining drilling information.
[0074] In the description of the present invention, it is necessary to understand that the orientation or positional relationship indicated by the terms "center", "thickness", "upper", "lower", "horizontal", "top", "bottom", "inner", "outer", "radial", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", and "third" are used only for descriptive purposes, and cannot be understood as indicating or implying the relative importance or the number of implicitly specified technical features. Therefore, the features defined by "first", "second", and "third" may explicitly or implicitly include one or more of the features.
Claims
1. A fast method for extracting drilling histogram information, characterized in that: The following steps are involved: S1, extracting the information of the drilling histogram and obtaining a table file of the drilling histogram; S2, extracting drilling information from the table file of the drilling histogram; S3, storing the drilling information into the database and completing the extraction of drilling histogram information; The step S2 comprises the following sub-steps: S21, creating a target value set according to the information of the drilling histogram; S22, matching the target values of the first drilling histogram table according to the target value set to obtain drilling information and an information-experience position set; S23, obtaining the drilling information of the next drilling histogram table according to the information-experience position set, and updating the information-experience position set; S24, repeat step S23 to obtain the remaining drilling information of the drilling histogram table, and complete the extraction of drilling information based on the obtained drilling information of all drilling histogram tables; In step S23, the method for obtaining the table information of the next drilling histogram is specifically as follows: SA1. According to the cell position information in the information-experience position set, try to obtain the information in the cells of the drilling bar chart table from high to low in terms of the number of cell hits, and update the number of cell hits recorded in the information-experience position; SA2. Check whether all the information in the drilling histogram table has been obtained; If yes, then the drilling column chart table information acquisition is completed; If not, the target value is matched on the drilling histogram table information to obtain the information in the cell, and the obtained new information-experience position record is added to the information-experience position set to complete the acquisition of the drilling histogram table information; In step S23, the method for updating the information-experience position set is specifically as follows: after the drilling information based on the drilling bar chart table is acquired, the cell position information in the information-experience position set is arranged from high to low according to the number of cell hits.
2. The rapid drilling histogram information extraction method according to claim 1 is characterized in that: The step S1 is specifically as follows: The drill column chart is extracted for text recognition, and a drill column chart table file is established according to the information extracted from the drill column chart, wherein the drill column chart table file includes a plurality of drill column chart tables.
3. The rapid drilling histogram information extraction method according to claim 1 is characterized in that: The step S21 specifically includes: creating a target value set according to the keywords used in the drilling histogram; The target value set is specifically a set of drilling information to be extracted and its corresponding target value, and the target value is specifically a keyword corresponding to the drilling information to be extracted.
4. The rapid drilling histogram information extraction method according to claim 1 is characterized in that: In the step S22, the drilling information is specifically information of all cells in the drilling bar chart table; The method for matching the target value is specifically as follows: searching and matching all cells of the first drilling bar chart table according to the target value, obtaining information in the cell and generating an information-experience position record; wherein the information-experience position record includes the cell position information and the number of cell hits; The step S22 is specifically as follows: based on the first drilling histogram table, all target value matches are completed in the target value set to obtain drilling information, and the obtained information-empirical position record is used to construct an information-empirical position set.
