Intelligent extraction method for key information of borehole histogram
By combining block segmentation and OCR technology, the problem of automating and intelligently extracting borehole columnar section information was solved, achieving efficient and accurate data extraction and management, and reducing manual intervention and errors.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INST OF MINERAL RESOURCES CHINA METALLURGICAL GEOLOGY ADMINISTRATION
- Filing Date
- 2025-12-03
- Publication Date
- 2026-04-21
AI Technical Summary
Existing technologies cannot effectively automate and intelligently extract information from borehole columnar sections, resulting in low data processing efficiency, poor accuracy, and a large workload for manual data entry, leading to numerous human errors.
The key areas are located using block segmentation technology, text recognition is performed using OCR technology, and information is spliced and matched using semantic analysis or rule matching methods, ultimately outputting a structured data table.
It enables automated and high-precision information extraction from borehole columnar sections, significantly reducing manual intervention, improving data processing efficiency and accuracy, reducing human error, and supporting intelligent management of geological data.
Smart Images
Figure CN121904797A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of geology, and in particular to a method for intelligent extraction of key information from borehole columnar sections. Background Technology
[0002] The efficient utilization of geological data is an important foundation for the informatization and intelligentization of drilling. The extraction of information from geological data such as borehole columnar sections is an important link in the multi-source data fusion of the drilling process and has important application value and engineering significance.
[0003] Information extraction from geological data such as borehole columnar sections is a crucial foundation for multi-source data fusion in the drilling process and a key step in achieving efficient utilization of geological data. With the rapid accumulation of drilling operation data, the widespread application of unstructured data, and the increasing demand for information technology in the drilling process, traditional processing methods relying on manual interpretation and entry are no longer sufficient to meet the requirements for efficient management of massive amounts of unstructured geological drilling data. In particular, the dense and complex information in borehole columnar section images leads to low efficiency in manual entry, further hindering the application of data standardization and intelligent analysis. Therefore, achieving intelligent and automated extraction of unstructured information from the drilling process has become an urgent problem to be solved. Summary of the Invention
[0004] The purpose of this invention is to provide a method for intelligent extraction of key information from borehole column charts, in order to solve the problem that existing technologies cannot achieve automated and intelligent information extraction and processing for batch borehole column charts, improve the efficiency and accuracy of data processing, reduce the workload of manual data entry and verification, and reduce human error.
[0005] The above-mentioned objective of this application is achieved through the following technical solution: S1: The borehole columnar section is segmented into key information blocks to obtain key areas; the key information includes: borehole number, formation name, and bottom depth of the formation. S2: Use OCR technology to recognize text in key areas and extract text information; S3: Intelligently splice, combine and modify the identified text information, and complete the item matching based on the correspondence between the information; 4: Output the matched text information as a structured data table to realize automated data extraction and organization.
[0006] Optionally, step S1 includes: The block segmentation employs image cropping technology, specifically including: Based on the layout structure of the borehole columnar section, key areas are located; Image processing algorithms are used to segment key regions. These algorithms include edge detection, contour extraction, or template matching methods. Output multiple independent key information image blocks, i.e. key regions.
[0007] Optionally, step S2 includes: Use a pre-trained OCR model to recognize text in key areas; The recognition results include the text content and its location information in the image; The recognition formula is:
[0008] in, Indicates the key regions after segmentation. This represents the text information obtained through recognition.
[0009] Optionally, step S3 includes: The entry matching and trimming process includes: The text is spliced together from the initial text information to a predetermined number of lines, restoring the original paragraph structure of the text information; Semantic analysis or rule matching methods are used to associate borehole number, formation name and bottom depth. The splicing formula is:
[0010] in, This indicates the identified scattered text fragments. This indicates a text concatenation operation for a preset number of lines. This represents the item matching and correction function. This represents the complete information entry after concatenation and matching.
[0011] Optionally, step S3 includes: The entry matching and trimming process includes: The text is spliced together from the initial text information to a predetermined number of lines, restoring the original paragraph structure of the text information; Semantic analysis or rule matching methods are used to associate borehole number, formation name and bottom depth. The splicing formula is:
[0012] in, This indicates the identified scattered text fragments. This indicates a text concatenation operation for a preset number of lines. This represents the item matching and correction function. This represents the complete information entry after concatenation and matching.
[0013] Optionally, the overall processing steps of the method are as follows:
[0014] Where I is the input borehole histogram, C is the block segmentation and cropping function, S is each cropped key region, OCR is the image text recognition process, K is the text information obtained from the corresponding region, M is the item matching and correction function, T is the complete information item after splicing and matching, F is the item matching and formatted output function, and D is the output structured data table.
[0015] An electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to enable the electronic device to perform a method for intelligent extraction of key information from borehole columnar sections.
[0016] A computer-readable storage medium storing instructions that, when executed, perform a method for intelligent extraction of key information from borehole columnar sections.
[0017] The beneficial effects of the technical solution provided in this application are: 1. The intelligent extraction method for key information of borehole columnar diagrams based on block identification and item matching of the present invention can effectively locate and extract key information such as borehole number, stratum name, and bottom depth by performing block segmentation and regional identification on the image content, thereby reducing manual intervention and improving the automation level of information extraction. 2. This invention introduces a standardized processing mechanism for information splicing and item matching, which realizes the automatic integration of multi-line descriptive information and the accurate correspondence between key information, ensuring the integrity and consistency of the data structure; 3. The identification results are output as standardized structured tabular data, which facilitates subsequent geological data analysis and information management, and provides reliable technical support for the standardization and intelligent processing of geological drilling data. Attached Figure Description
[0018] The present application will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings: Figure 1 This is a flowchart of an embodiment of this application; Figure 2 This is an example diagram of intelligent extraction of key information from borehole columnar section diagrams in the embodiments of this application; Figure 3 This is a comparison result of the intelligent extraction of key information from the borehole columnar diagram in the embodiments of this application; Figure 4 This is a schematic diagram of the electronic device structure in the embodiments of this application; Figure 5This is a borehole columnar diagram from an embodiment of this application. Detailed Implementation
[0019] To provide a clearer understanding of the technical features, objectives, and effects of this application, the specific embodiments of this application will now be described in detail with reference to the accompanying drawings.
[0020] The embodiments of this application provide a method for intelligent extraction of key information from borehole columnar section diagrams.
[0021] Please refer to Figure 1 , Figure 1 This is a flowchart of a method for intelligent extraction of key information from borehole columnar section diagrams according to an embodiment of this application, including: S1: The borehole columnar section is segmented into key information blocks to obtain key areas; the key information includes: borehole number, formation name, and bottom depth of the formation. S2: Use OCR technology to recognize text in key areas and extract text information; S3: Intelligently splices, combines, and modifies the identified text information, and completes item matching based on the correspondence between information; S4: Output the matched text information as a structured data table to achieve automated data extraction and organization.
[0022] This application, by adopting the above-mentioned technical solution, enables automated and intelligent information extraction and processing for batches of similar borehole columnar sections, effectively improving the efficiency and accuracy of data processing, significantly reducing the workload of manual data entry and verification, and minimizing human error. This method has good versatility and provides technical support for the efficient digitization and intelligent management of drilling data.
[0023] As one embodiment, the method is suitable for batch processing of multiple borehole column charts, realizing automated and high-precision extraction of key information, and significantly reducing the cost of manual intervention and verification.
[0024] Step S1 includes: The block segmentation employs image cropping technology, specifically including: Based on the layout structure of the borehole columnar section, key areas are located; Image processing algorithms are used to segment key regions. These algorithms include edge detection, contour extraction, or template matching methods. Output multiple independent key information image blocks, i.e. key regions.
[0025] Step S2 includes: Use a pre-trained OCR model to recognize text in key areas; The recognition results include the text content and its location information in the image; The recognition formula is:
[0026] in, Indicates the key regions after segmentation. This represents the text information obtained through recognition.
[0027] Step S3 includes: The entry matching and trimming process includes: The text is spliced together from the initial text information to a predetermined number of lines, restoring the original paragraph structure of the text information; Semantic analysis or rule matching methods are used to associate borehole number, formation name and bottom depth. The splicing formula is:
[0028] in, This indicates the identified scattered text fragments. This indicates a text concatenation operation for a preset number of lines. This represents the item matching and correction function. This represents the complete information entry after concatenation and matching.
[0029] Step S4 includes: The structured output includes: Organize the matched key information into a table according to a preset format; Output formats include Excel, CSV, or database tables; The output function is expressed as:
[0030] in, For the matched information entries, This is a formatted output function. This is the final structured data.
[0031] The overall processing steps of the method are as follows:
[0032] Where I is the input borehole histogram, C is the block segmentation and cropping function, S is each cropped key region, OCR is the image text recognition process, K is the text information obtained from the corresponding region, M is the item matching and correction function, T is the complete information item after splicing and matching, F is the item matching and formatted output function, and D is the output structured data table.
[0033] In one embodiment, this application provides an intelligent extraction method for key information from borehole columnar charts based on block identification and entry matching. First, a method is constructed as follows: Figure 1 The proposed method for intelligent extraction of key information from borehole columnar sections comprises four steps. The first stage uses image cropping technology to segment the borehole columnar section into key information blocks. The second stage utilizes OCR recognition technology to extract the key information images from the segmented regions. The third stage intelligently identifies, stitches, and trims the extracted key information, and performs item matching on each extracted piece of information. The fourth stage outputs the key information as structured data, achieving automated data extraction and processing. The specific steps are as follows: (1) Extract key information such as borehole number, formation name, and bottom depth from the borehole column chart. Then, cut the key information from the borehole column chart into blocks and use them as the core identification objects for subsequent information extraction and item matching.
[0034] (2) Use OCR recognition technology to perform image recognition processing on the block-segmented area and extract the text and symbol information. Determine the start of the entry by recognizing the specified symbol information or key stratigraphic information in the text, and automatically splice the subsequent unmarked content to the previous description to establish an entry matching table.
[0035] (3) Using the method proposed in the fourth stage, key information of the borehole columnar section is intelligently extracted, and a structured table of key information of the borehole columnar section is generated. The overall process result is as follows: Figure 2 and Figure 5 As shown.
[0036] (4) To verify the effectiveness of the proposed method, the performance differences between the proposed method, traditional OCR recognition methods, and manual input methods were compared and analyzed. The results are shown in Table 1. The comparison results between the proposed method and traditional OCR technology and manual extraction and correction methods are as follows: Figure 3 As shown.
[0037] Table 1. Comparison of extraction performance of various methods
[0038] (5) Table 2 presents a comparison of the key information extraction performance of a borehole columnar section. It can be seen that for a single borehole columnar section, the method presented in this paper can achieve information extraction and structured output within seconds, while traditional OCR technology and manual input typically take several minutes or even longer. Since geological drilling involves a large amount of geological exploration data, relying entirely on manual input and correction would consume a significant amount of manpower and time. The method presented in this paper, while appropriately reducing accuracy requirements, significantly improves the processing efficiency of batch borehole columnar sections, while effectively compensating for the insufficient recognition accuracy of traditional OCR methods. Experimental results verify the significant improvement in data extraction accuracy and processing efficiency achieved by the method presented in this paper.
[0039] Table 2 Comparison of key information extraction methods (taking extraction from a borehole bar chart as an example)
[0040] This application also discloses an electronic device. (See reference...) Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 500 may include: at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.
[0041] The communication bus 502 is used to enable communication between these components.
[0042] The user interface 503 may include a display screen, and optionally, the user interface 503 may also include a standard wired interface or a wireless interface.
[0043] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).
[0044] This application also discloses a computer-readable storage medium storing multiple instructions adapted for loading by a processor to execute the above-described method for intelligent extraction of key information from borehole column charts.
[0045] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure.
[0046] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.
Claims
1. A method for intelligent extraction of key information from borehole columnar section diagrams, characterized in that, The method includes the following steps: S1: The borehole columnar section is segmented into key information blocks to obtain key areas; the key information includes: borehole number, formation name, and bottom depth of the formation. S2: Use OCR technology to recognize text in key areas and extract text information; S3: Intelligently splices, combines, and modifies the identified text information, and completes item matching based on the correspondence between information; S4: Output the matched text information as a structured data table to achieve automated data extraction and organization.
2. The intelligent extraction method for key information from borehole columnar section diagrams as described in claim 1, characterized in that, Step S1 includes: The block segmentation employs image cropping technology, specifically including: Based on the layout structure of the borehole columnar section, key areas are located; Image processing algorithms are used to segment key regions. These algorithms include edge detection, contour extraction, or template matching methods. Output multiple independent key information image blocks, i.e. key regions.
3. The intelligent extraction method for key information from borehole columnar section diagrams as described in claim 1, characterized in that, Step S2 includes: Use a pre-trained OCR model to recognize text in key areas; The recognition results include the text content and its location information in the image; The recognition formula is: in, Indicates the key regions after segmentation. This represents the text information obtained through recognition.
4. The intelligent extraction method for key information from borehole columnar section diagrams as described in claim 1, characterized in that, Step S3 includes: The entry matching and trimming process includes: The text is spliced together from the initial text information to a predetermined number of lines, restoring the original paragraph structure of the text information; Semantic analysis or rule matching methods are used to associate borehole number, formation name and bottom depth. The splicing formula is: in, This indicates the identified scattered text fragments. This indicates a text concatenation operation for a preset number of lines. This represents the item matching and correction function. This represents the complete information entry after concatenation and matching.
5. The intelligent extraction method for key information from borehole columnar section diagrams as described in claim 1, characterized in that, Step S4 includes: The structured output includes: Organize the matched key information into a table according to a preset format; Output formats include Excel, CSV, or database tables; The output function is expressed as: in, For the matched information entries, This is a formatted output function. This is the final structured data.
6. The intelligent extraction method for key information from borehole columnar section diagrams as described in claim 1, characterized in that, The overall processing steps of the method are as follows: Where I is the input borehole histogram, C is the block segmentation and cropping function, S is each cropped key region, OCR is the image text recognition process, K is the text information obtained from the corresponding region, M is the item matching and correction function, T is the complete information item after splicing and matching, F is the item matching and formatted output function, and D is the output structured data table.
7. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to enable the electronic device to perform the intelligent extraction method for key information from borehole columnar diagrams as described in any one of claims 1-6.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed by a computer, perform the intelligent extraction method for key information from borehole columnar sections as described in any one of claims 1-6.